Terrain Estimation for Planetary Exploration Robots

Abstract

A planetary exploration rover’s ability to detect the type of supporting surface is critical to the successful accomplishment of the planned task, especially for long-range and long-duration missions. This paper presents a general approach to endow a robot with the ability to sense the terrain being traversed. It relies on the estimation of motion states and physical variables pertaining to the interaction of the vehicle with the environment. First, a comprehensive proprioceptive feature set is investigated to evaluate the informative content and the ability to gather terrain properties. Then, a terrain classifier is developed grounded on Support Vector Machine (SVM) and that uses an optimal proprioceptive feature set. Following this rationale, episodes of high slippage can be also treated as a particular terrain type and detected via a dedicated classifier. The proposed approach is tested and demonstrated in the field using SherpaTT rover, property of DFKI (German Research Center for Artificial Intelligence), that uses an active suspension system to adapt to terrain unevenness.

Full text

applied
sciences
Article
Terrain Estimation for Planetary Exploration Robots †
Mauro Dimastrogiovanni 1, Florian Cordes 2and Giulio Reina 3, *
1Department of Engineering for Innovation, University of Salento Via per Arnesano, 73100 Lecce, Italy;
mauro.dimastrogiovanni@unisalento.it
2DFKI Robotics Innovation Center Bremen Robert-Hooke-Str. 1, 28359 Bremen, Germany;
florian.cordes@dfki.de
3Department of Mechanics, Mathematics and Management, Politecnico di Bari, via Orabona 4,
70126 Bari, Italy
*Correspondence: giulio.reina@poliba.it
†Parts of this paper were presented at the Third International Conference of IFToMM Naples, Italy,
9–11 September 2020.
Received: 5 August 2020; Accepted: 26 August 2020; Published: 31 August 2020


Abstract:
A planetary exploration rover’s ability to detect the type of supporting surface is
critical to the successful accomplishment of the planned task, especially for long-range and
long-duration missions. This paper presents a general approach to endow a robot with the ability
to sense the terrain being traversed. It relies on the estimation of motion states and physical
variables pertaining to the interaction of the vehicle with the environment. First, a comprehensive
proprioceptive feature set is investigated to evaluate the informative content and the ability to gather
terrain properties. Then, a terrain classifier is developed grounded on Support Vector Machine
(SVM) and that uses an optimal proprioceptive feature set. Following this rationale, episodes of high
slippage can be also treated as a particular terrain type and detected via a dedicated classifier. The
proposed approach is tested and demonstrated in the field using SherpaTT rover, property of DFKI
(German Research Center for Artificial Intelligence), that uses an active suspension system to adapt
to terrain unevenness.
Keywords:
space robotics; planetary surface exploration; terrain awareness; mechanics of
vehicle–terrain interaction; vehicle dynamics
1. Introduction
The main challenges that planetary exploration rovers must face refer to: long-range operations in
hostile environmental conditions, lack of maintenance, and limited human supervision. It is of primary
importance to increase their autonomy level to reduce the reliance on ground control and maximize
the mission’s scientific return. One of the key technologies for autonomous navigation is the ability
to sense and characterize the incoming terrain, avoiding potential hazards. For example, the terrain
being traversed may exhibit high deformability and low traction properties due to low packing density
and/or limited cohesion. This could result in loss of traction as well as in excessive sinkage that in
extreme cases may lead to robot entrapment. For example, in April 2005, the Mars Exploration Rover
Opportunity became embedded in a dune of loosely packed drift material and delayed its operations
for more than a month. A similar embedding event led to the end of mobility for the Spirit rover in
2010 [1].
Beyond general safety and stability assessment, terrain sensing can be used to improve trajectory
tracking by applying methods for slip estimation and compensation (e.g., [
2
–
4
]) or traction control
(e.g., [
5
]). Future planetary rovers are expected to be able to extend methods for rough-terrain
navigation to infer scientific information of different geological formations [6].
Appl. Sci. 2020,10, 6044; doi:10.3390/app10176044 www.mdpi.com/journal/applsci

Appl. Sci. 2020,10, 6044 2 of 15
Early research in terrain estimation has relied on forward looking sensors and used limited
learning [
7
]. Monocular and stereo cameras have been the most common sensors used for terrain
estimation from a distance [
8
], followed by lidars and radars [
9
], which have been often proposed
in terrestrial applications [
10
,
11
]. The use of exteroceptive sensing leads to the generation of a local
digital elevation model (DEM) to obtain and maintain a discrete traversability map. The appearance
(e.g., texture, color) of different terrain patches can provide important clues to analyze the surrounding
terrain [12].
However, observation of a given terrain from a distance does not provide any information about
its impact on the vehicle mobility. It is known that off-road traversability largely depends on the
interaction between the robot and the terrain [
13
]. Dynamic ill-effects including wheel sinkage, slippage
and rolling resistance are the result of this complex interplay. For example, ground can be considered
drivable based on the geometric elevation map. Yet, the robot can incur serious risks if this terrain
offers low traction properties due to high slippage and consequent lack of progression as explained
in [
14
]. An extensive discussion on methods for slippage estimation in planetary rovers can be found
in [
15
], whereas the impact of the irregularity and deformability of the traversed surface on the robot’s
dynamic response are investigated in [16].
Therefore, recently, methods for terrain estimation have been also presented that use proprioceptive
sensing [
17
,
18
]. The envisaged idea is that terrain properties can be obtained directly by the rover
wheels that serve as tactile sensors. Proprioceptive signals are modulated by the vehicle–terrain
interaction and they contain substantial information, which can help to characterize terrain. In addition,
learning approaches have been introduced in order to make intelligent autonomous robots adaptive
to the site-specific environment [
19
]. Natural terrains represent a challenging scenario due to
variability in surface and lighting conditions, lack of structure, no prior information, and in which
learning approaches have proved to be more appropriate than expert rule-based or heuristic strategies.
For example, the vertical acceleration was used as the main sensory input to train classifiers based on
different learning algorithms, including AdaBoost [
20
], neural network [
21
], and Cubature Kalman
filtering [
22
]. Methods that attempt to directly measure some important terrain parameters such as
friction angle and cohesion have been proposed using a linear least squares approximation of the
classical terramechanics theory [
23
] or via a Bayesian procedure to deal effectively with the presence of
uncertainty [24].
The general learning approach includes data gathering pertaining to the wheel-terrain interaction
followed by a mapping stage of proprioceptive data with the corresponding terrain. This functional
relationship can help addressing various issues: (a) difficulty in creating a physics-based terrain
model due to the large number of variables involved, (b) the mapping from proprioceptive input to
a mechanical terrain property is an extremely complicated function, which does not have a known
analytical form or a physical model and one possible way to observe it and learn about it is via training
examples, (c) a learning approach promotes adaptability of the vehicle’s behavior.
This paper presents an approach for terrain identification by gathering important information
pertaining to the mechanics of vehicle–environment interaction. The underlying assumption is that
characteristic traits of the supporting surface can be extracted using vehicle wheels as “tactile” sensors
that generate signals modulated by the physical wheel-soil contact. First, the main features that hold
the highest discriminative power for terrain identification are studied. They form a feature space
upon which a terrain classifier can be built via support vector machine (SVM). By observing these
features during nominal robot operation, different types of surfaces can be discriminated. Following
this rationale, conditions of high slippage can also be treated as a particular terrain and detected
though a dedicated classifier that represents an additional contribution of this research. The idea for
the proposed approach was previously presented in [
25
], where preliminary results were presented.
Here, the method is fully detailed in terms of optimal feature selection and classifier building. It is also
generalized to include as well the case of slippage estimation. Finally, extended experimental results
are included to quantitatively evaluate the system performance.

Appl. Sci. 2020,10, 6044 3 of 15
Materials and methods used in this research are presented in Section 2, whereas the proprioceptive
“traits” and the proposed selection approach for the optimal feature set are described in Section 3.
The terrain classifier is described in Section 4providing experimental results obtained from the rover
SherpaTT. Finally, lessons learned, and future developments conclude the paper.
2. Materials and Methods
The system is tested and developed using the rover SherpaTT that is shown in Figure 1. SherpaTT
was built by DFKI for long-distance exploration applications [
26
], negotiation of highly challenging
terrains or non-nominal conditions (sinkage in soft soil, getting entangled between rocks or alike),
cooperation tasks between heterogeneous rovers in a collaborative sample return mission, search
and rescue and/or security missions. SherpaTT is a four-wheeled mobile robot [
27
] outfitted with an
actively articulated suspension system, independent drive and steer wheel motors and a six degrees
of freedom (DOF) manipulation arm. The rover is also a hybrid wheeled-leg rover, so it can take
advantage of both wheeled and legged locomotion according to the terrain difficulty. SherpaTT has a
mass of about 166 kg and a payload capacity of at least 80 kg. Each of the four suspended legs has
five DOF that include the rotation of the whole leg about the shoulder or pan axis with respect to the
robot body, the two rotations of the inner and outer leg parallelograms, the steer and drive angle of
the wheel. SherpaTT’s footprint can vary between 1
×
1m in a folded configuration to 2.4
×
2.4 m in a
maximum square footprint. Various predefined footprint shapes (stances) can be adopted as explained
in Figure 2.
Each of the 20 suspension and six arm joints delivers telemetry data at a rate of 100 Hz.
The telemetry includes joint position (absolute and incremental), speed, current, PWM duty cycle and
two temperatures (housing and motor windings). Additionally, a 6-DOF force-torque sensor (FTS) is
placed at the mounting flange of each wheel-drive actuator enabling the direct measurement of the
generalized forces that each wheel exchanges with the supporting surface. Active force control for
the wheel-ground contact as well as the roll-pitch adaption are two processes of the so-called Ground
Adaption Process (GAP) in SherpaTT [
28
]. Autonomy modules do not need to cope with the limb
articulation in rough terrain [29].
Appl. Sci. 2020, 10, x FOR PEER REVIEW 3 of 16
in Section 3. The terrain classifier is described in Section 4 providing experimental results obtained
from the rover SherpaTT. Finally, lessons learned, and future developments conclude the paper.
2. Materials and Methods
The system is tested and developed using the rover SherpaTT that is shown in Figure 1.
SherpaTT was built by DFKI for long-distance exploration applications [26], negotiation of highly
challenging terrains or non-nominal conditions (sinkage in soft soil, getting entangled between rocks
or alike), cooperation tasks between heterogeneous rovers in a collaborative sample return mission,
search and rescue and/or security missions. SherpaTT is a four-wheeled mobile robot [27] outfitted
with an actively articulated suspension system, independent drive and steer wheel motors and a six
degrees of freedom (DOF) manipulation arm. The rover is also a hybrid wheeled-leg rover, so it can
take advantage of both wheeled and legged locomotion according to the terrain difficulty. SherpaTT
has a mass of about 166 kg and a payload capacity of at least 80 kg. Each of the four suspended legs
has five DOF that include the rotation of the whole leg about the shoulder or pan axis with respect to
the robot body, the two rotations of the inner and outer leg parallelograms, the steer and drive angle
of the wheel. SherpaTT’s footprint can vary between 1 × 1m in a folded configuration to 2.4 × 2.4 m
in a maximum square footprint. Various predefined footprint shapes (stances) can be adopted as
explained in Figure 2.
Each of the 20 suspension and six arm joints delivers telemetry data at a rate of 100 Hz. The
telemetry includes joint position (absolute and incremental), speed, current, PWM duty cycle and
two temperatures (housing and motor windings). Additionally, a 6-DOF force-torque sensor (FTS) is
placed at the mounting flange of each wheel-drive actuator enabling the direct measurement of the
generalized forces that each wheel exchanges with the supporting surface. Active force control for
the wheel-ground contact as well as the roll-pitch adaption are two processes of the so-called Ground
Adaption Process (GAP) in SherpaTT [28]. Autonomy modules do not need to cope with the limb
articulation in rough terrain [29].
Figure 1. SherpaTT in soft sand dunes during Morocco field trials in 2018.
Figure 1. SherpaTT in soft sand dunes during Morocco field trials in 2018.

Appl. Sci. 2020,10, 6044 4 of 15
Appl. Sci. 2020, 10, x FOR PEER REVIEW 4 of 16
Figure 2. Examples of possible footprint configurations and resulting support polygons.
2.1. Data Sets
Two extensive field trials have been conducted by SherpaTT in the desert of Morocco (2019) and
in the desert of Utah (2016). Both sites have been shown to be representative of Mars analogue terrain
[30]. During these field trials, different test tracks in natural terrain, GAP-modes and footprints have
been tested. Since the focus of those campaigns was different from the aim of this research, only a
small portion of the data logs can be effectively used for terrain estimation purposes. Table 1 sums
up the datasets available for terrain and slippage classification, clarifying specific terrain, total run
time and logged sensors. Specifically, the only available run in the Morocco campaign is performed
on sandy dunes of flat/moderate slopes, while Utah data logs are available on flat, moderate sloped
and steep sloped rocky terrains. Utah moderate sloped terrain presents an inclination less than 10
deg, while steep sloped terrain had a grade up to 28 degrees. All the available experimental runs are
performed following a straight path. Sensor signals are logged together with a synchronized
timestamp. Four sensor modalities are available on SherpaTT: the four FTSs, the body’s IMU, a
Differential Global Positioning System (DGPS) on the rover body and joint telemetry. The FTSs are
six axial sensors able to measure the three cartesian components of forces and moments acting on
each wheel. The IMU outputs the rover’s attitude ad accelerations, while DGPS provides an absolute
position of the rover and it is used for ground truthing. Joint position and speed, as well as each
joint’s electrical current and PWM duty cycle, are available for this study.
Proprioceptive data streams have been associated with a sequence of terrain patches with the
same length. In this work, a patch length of 0.3 m is considered. In such a way, for each terrain patch,
a set of features has been computed, as extensively explained in the following section.
Table 1. Datasets gathered by SherpaTT during field trials; for each test run, terrain description,
testing time and available logged sensors are indicated.
Run
ID
Test
Site
Terrain
Type Slope Run Time
[s] FTS IMU DGPS Encoders
R01 Morocco Sand Flat/Moderate 381.5 ✓ ✗ ✗ ✓
R02 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R03 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R04 Utah Rock Moderate 152.4 ✓ ✓ ✗ ✓
R05 Utah Rock Steep 453.9 ✓ ✓ ✓ ✓
R06 Utah Rock Steep 457.7 ✓ ✓ ✓ ✓
R07 Utah Rock Steep 481.2 ✓ ✓ ✓ ✓
Figure 2. Examples of possible footprint configurations and resulting support polygons.
2.1. Data Sets
Two extensive field trials have been conducted by SherpaTT in the desert of Morocco (2019)
and in the desert of Utah (2016). Both sites have been shown to be representative of Mars analogue
terrain [
30
]. During these field trials, different test tracks in natural terrain, GAP-modes and footprints
have been tested. Since the focus of those campaigns was different from the aim of this research, only a
small portion of the data logs can be effectively used for terrain estimation purposes. Table 1sums
up the datasets available for terrain and slippage classification, clarifying specific terrain, total run
time and logged sensors. Specifically, the only available run in the Morocco campaign is performed
on sandy dunes of flat/moderate slopes, while Utah data logs are available on flat, moderate sloped
and steep sloped rocky terrains. Utah moderate sloped terrain presents an inclination less than 10
deg, while steep sloped terrain had a grade up to 28 degrees. All the available experimental runs are
performed following a straight path. Sensor signals are logged together with a synchronized timestamp.
Four sensor modalities are available on SherpaTT: the four FTSs, the body’s IMU, a Differential Global
Positioning System (DGPS) on the rover body and joint telemetry. The FTSs are six axial sensors able
to measure the three cartesian components of forces and moments acting on each wheel. The IMU
outputs the rover’s attitude ad accelerations, while DGPS provides an absolute position of the rover
and it is used for ground truthing. Joint position and speed, as well as each joint’s electrical current
and PWM duty cycle, are available for this study.
Table 1.
Datasets gathered by SherpaTT during field trials; for each test run, terrain description, testing
time and available logged sensors are indicated.
Run ID Test Site Terrain
Type Slope Run
Time [s] FTS IMU DGPS Encoders
R01 Morocco Sand
Flat/Moderate
381.5
Appl. Sci. 2020, 10, x FOR PEER REVIEW 4 of 16
Figure 1. SherpaTT in soft sand dunes during Morocco field trials in 2018.
Figure 2. Examples of possible footprint configurations and resulting support polygons.
2.1. Data Sets
Two extensive field trials have been conducted by SherpaTT in the desert of Morocco (2019) and
in the desert of Utah (2016). Both sites have been shown to be representative of Mars analogue terrain
[30]. During these field trials, different test tracks in natural terrain, GAP-modes and footprints have
been tested. Since the focus of those campaigns was different from the aim of this research, only a
small portion of the data logs can be effectively used for terrain estimation purposes. Table 1 sums
up the datasets available for terrain and slippage classification, clarifying specific terrain, total run
time and logged sensors. Specifically, the only available run in the Morocco campaign is performed
on sandy dunes of flat/moderate slopes, while Utah data logs are available on flat, moderate sloped
and steep sloped rocky terrains. Utah moderate sloped terrain presents an inclination less than 10
deg, while steep sloped terrain had a grade up to 28 degrees. All the available experimental runs are
performed following a straight path. Sensor signals are logged together with a synchronized
timestamp. Four sensor modalities are available on SherpaTT: the four FTSs, the body’s IMU, a
Differential Global Positioning System (DGPS) on the rover body and joint telemetry. The FTSs are
six axial sensors able to measure the three cartesian components of forces and moments acting on
each wheel. The IMU outputs the rover’s attitude ad accelerations, while DGPS provides an absolute
position of the rover and it is used for ground truthing. Joint position and speed, as well as each
joint’s electrical current and PWM duty cycle, are available for this study.
Proprioceptive data streams have been associated with a sequence of terrain patches with the
same length. In this work, a patch length of 0.3 m is considered. In such a way, for each terrain patch,
a set of features has been computed, as extensively explained in the following section.
Table 1. Datasets gathered by SherpaTT during field trials; for each test run, terrain description,
testing time and available logged sensors are indicated.
Run
ID
Test
Site
Terrain
Type Slope Run Time
[s] FTS IMU DGPS Encoders
R01 Morocco Sand Flat/Moderate 381.5 ✓ ✗ ✗ ✓
R02 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R03 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R04 Utah Rock Moderate 152.4 ✓ ✓ ✗ ✓
R05 Utah Rock Steep 453.9 ✓ ✓ ✓ ✓
R06 Utah Rock Steep 457.7 ✓ ✓ ✓ ✓
R07 Utah Rock Steep 481.2 ✓ ✓ ✓ ✓
Appl. Sci. 2020, 10, x FOR PEER REVIEW 4 of 16
Figure 1. SherpaTT in soft sand dunes during Morocco field trials in 2018.
Figure 2. Examples of possible footprint configurations and resulting support polygons.
2.1. Data Sets
Two extensive field trials have been conducted by SherpaTT in the desert of Morocco (2019) and
in the desert of Utah (2016). Both sites have been shown to be representative of Mars analogue terrain
[30]. During these field trials, different test tracks in natural terrain, GAP-modes and footprints have
been tested. Since the focus of those campaigns was different from the aim of this research, only a
small portion of the data logs can be effectively used for terrain estimation purposes. Table 1 sums
up the datasets available for terrain and slippage classification, clarifying specific terrain, total run
time and logged sensors. Specifically, the only available run in the Morocco campaign is performed
on sandy dunes of flat/moderate slopes, while Utah data logs are available on flat, moderate sloped
and steep sloped rocky terrains. Utah moderate sloped terrain presents an inclination less than 10
deg, while steep sloped terrain had a grade up to 28 degrees. All the available experimental runs are
performed following a straight path. Sensor signals are logged together with a synchronized
timestamp. Four sensor modalities are available on SherpaTT: the four FTSs, the body’s IMU, a
Differential Global Positioning System (DGPS) on the rover body and joint telemetry. The FTSs are
six axial sensors able to measure the three cartesian components of forces and moments acting on
each wheel. The IMU outputs the rover’s attitude ad accelerations, while DGPS provides an absolute
position of the rover and it is used for ground truthing. Joint position and speed, as well as each
joint’s electrical current and PWM duty cycle, are available for this study.
Proprioceptive data streams have been associated with a sequence of terrain patches with the
same length. In this work, a patch length of 0.3 m is considered. In such a way, for each terrain patch,
a set of features has been computed, as extensively explained in the following section.
Table 1. Datasets gathered by SherpaTT during field trials; for each test run, terrain description,
testing time and available logged sensors are indicated.
Run
ID
Test
Site
Terrain
Type Slope Run Time
[s] FTS IMU DGPS Encoders
R01 Morocco Sand Flat/Moderate 381.5 ✓ ✗ ✗ ✓
R02 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R03 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R04 Utah Rock Moderate 152.4 ✓ ✓ ✗ ✓
R05 Utah Rock Steep 453.9 ✓ ✓ ✓ ✓
R06 Utah Rock Steep 457.7 ✓ ✓ ✓ ✓
R07 Utah Rock Steep 481.2 ✓ ✓ ✓ ✓
Appl. Sci. 2020, 10, x FOR PEER REVIEW 4 of 16
Figure 1. SherpaTT in soft sand dunes during Morocco field trials in 2018.
Figure 2. Examples of possible footprint configurations and resulting support polygons.
2.1. Data Sets
Two extensive field trials have been conducted by SherpaTT in the desert of Morocco (2019) and
in the desert of Utah (2016). Both sites have been shown to be representative of Mars analogue terrain
[30]. During these field trials, different test tracks in natural terrain, GAP-modes and footprints have
been tested. Since the focus of those campaigns was different from the aim of this research, only a
small portion of the data logs can be effectively used for terrain estimation purposes. Table 1 sums
up the datasets available for terrain and slippage classification, clarifying specific terrain, total run
time and logged sensors. Specifically, the only available run in the Morocco campaign is performed
on sandy dunes of flat/moderate slopes, while Utah data logs are available on flat, moderate sloped
and steep sloped rocky terrains. Utah moderate sloped terrain presents an inclination less than 10
deg, while steep sloped terrain had a grade up to 28 degrees. All the available experimental runs are
performed following a straight path. Sensor signals are logged together with a synchronized
timestamp. Four sensor modalities are available on SherpaTT: the four FTSs, the body’s IMU, a
Differential Global Positioning System (DGPS) on the rover body and joint telemetry. The FTSs are
six axial sensors able to measure the three cartesian components of forces and moments acting on
each wheel. The IMU outputs the rover’s attitude ad accelerations, while DGPS provides an absolute
position of the rover and it is used for ground truthing. Joint position and speed, as well as each
joint’s electrical current and PWM duty cycle, are available for this study.
Proprioceptive data streams have been associated with a sequence of terrain patches with the
same length. In this work, a patch length of 0.3 m is considered. In such a way, for each terrain patch,
a set of features has been computed, as extensively explained in the following section.
Table 1. Datasets gathered by SherpaTT during field trials; for each test run, terrain description,
testing time and available logged sensors are indicated.
Run
ID
Test
Site
Terrain
Type Slope Run Time
[s] FTS IMU DGPS Encoders
R01 Morocco Sand Flat/Moderate 381.5 ✓ ✗ ✗ ✓
R02 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R03 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R04 Utah Rock Moderate 152.4 ✓ ✓ ✗ ✓
R05 Utah Rock Steep 453.9 ✓ ✓ ✓ ✓
R06 Utah Rock Steep 457.7 ✓ ✓ ✓ ✓
R07 Utah Rock Steep 481.2 ✓ ✓ ✓ ✓
Appl. Sci. 2020, 10, x FOR PEER REVIEW 4 of 16
Figure 1. SherpaTT in soft sand dunes during Morocco field trials in 2018.
Figure 2. Examples of possible footprint configurations and resulting support polygons.
2.1. Data Sets
Two extensive field trials have been conducted by SherpaTT in the desert of Morocco (2019) and
in the desert of Utah (2016). Both sites have been shown to be representative of Mars analogue terrain
[30]. During these field trials, different test tracks in natural terrain, GAP-modes and footprints have
been tested. Since the focus of those campaigns was different from the aim of this research, only a
small portion of the data logs can be effectively used for terrain estimation purposes. Table 1 sums
up the datasets available for terrain and slippage classification, clarifying specific terrain, total run
time and logged sensors. Specifically, the only available run in the Morocco campaign is performed
on sandy dunes of flat/moderate slopes, while Utah data logs are available on flat, moderate sloped
and steep sloped rocky terrains. Utah moderate sloped terrain presents an inclination less than 10
deg, while steep sloped terrain had a grade up to 28 degrees. All the available experimental runs are
performed following a straight path. Sensor signals are logged together with a synchronized
timestamp. Four sensor modalities are available on SherpaTT: the four FTSs, the body’s IMU, a
Differential Global Positioning System (DGPS) on the rover body and joint telemetry. The FTSs are
six axial sensors able to measure the three cartesian components of forces and moments acting on
each wheel. The IMU outputs the rover’s attitude ad accelerations, while DGPS provides an absolute
position of the rover and it is used for ground truthing. Joint position and speed, as well as each
joint’s electrical current and PWM duty cycle, are available for this study.
Proprioceptive data streams have been associated with a sequence of terrain patches with the
same length. In this work, a patch length of 0.3 m is considered. In such a way, for each terrain patch,
a set of features has been computed, as extensively explained in the following section.
Table 1. Datasets gathered by SherpaTT during field trials; for each test run, terrain description,
testing time and available logged sensors are indicated.
Run
ID
Test
Site
Terrain
Type Slope Run Time
[s] FTS IMU DGPS Encoders
R01 Morocco Sand Flat/Moderate 381.5 ✓ ✗ ✗ ✓
R02 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R03 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R04 Utah Rock Moderate 152.4 ✓ ✓ ✗ ✓
R05 Utah Rock Steep 453.9 ✓ ✓ ✓ ✓
R06 Utah Rock Steep 457.7 ✓ ✓ ✓ ✓
R07 Utah Rock Steep 481.2 ✓ ✓ ✓ ✓
R02 Utah Rock Flat 214.8
Appl. Sci. 2020, 10, x FOR PEER REVIEW 4 of 16
Figure 1. SherpaTT in soft sand dunes during Morocco field trials in 2018.
Figure 2. Examples of possible footprint configurations and resulting support polygons.
2.1. Data Sets
Two extensive field trials have been conducted by SherpaTT in the desert of Morocco (2019) and
in the desert of Utah (2016). Both sites have been shown to be representative of Mars analogue terrain
[30]. During these field trials, different test tracks in natural terrain, GAP-modes and footprints have
been tested. Since the focus of those campaigns was different from the aim of this research, only a
small portion of the data logs can be effectively used for terrain estimation purposes. Table 1 sums
up the datasets available for terrain and slippage classification, clarifying specific terrain, total run
time and logged sensors. Specifically, the only available run in the Morocco campaign is performed
on sandy dunes of flat/moderate slopes, while Utah data logs are available on flat, moderate sloped
and steep sloped rocky terrains. Utah moderate sloped terrain presents an inclination less than 10
deg, while steep sloped terrain had a grade up to 28 degrees. All the available experimental runs are
performed following a straight path. Sensor signals are logged together with a synchronized
timestamp. Four sensor modalities are available on SherpaTT: the four FTSs, the body’s IMU, a
Differential Global Positioning System (DGPS) on the rover body and joint telemetry. The FTSs are
six axial sensors able to measure the three cartesian components of forces and moments acting on
each wheel. The IMU outputs the rover’s attitude ad accelerations, while DGPS provides an absolute
position of the rover and it is used for ground truthing. Joint position and speed, as well as each
joint’s electrical current and PWM duty cycle, are available for this study.
Proprioceptive data streams have been associated with a sequence of terrain patches with the
same length. In this work, a patch length of 0.3 m is considered. In such a way, for each terrain patch,
a set of features has been computed, as extensively explained in the following section.
Table 1. Datasets gathered by SherpaTT during field trials; for each test run, terrain description,
testing time and available logged sensors are indicated.
Run
ID
Test
Site
Terrain
Type Slope Run Time
[s] FTS IMU DGPS Encoders
R01 Morocco Sand Flat/Moderate 381.5 ✓ ✗ ✗ ✓
R02 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R03 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R04 Utah Rock Moderate 152.4 ✓ ✓ ✗ ✓
R05 Utah Rock Steep 453.9 ✓ ✓ ✓ ✓
R06 Utah Rock Steep 457.7 ✓ ✓ ✓ ✓
R07 Utah Rock Steep 481.2 ✓ ✓ ✓ ✓
Appl. Sci. 2020, 10, x FOR PEER REVIEW 4 of 16
Figure 1. SherpaTT in soft sand dunes during Morocco field trials in 2018.
Figure 2. Examples of possible footprint configurations and resulting support polygons.
2.1. Data Sets
Two extensive field trials have been conducted by SherpaTT in the desert of Morocco (2019) and
in the desert of Utah (2016). Both sites have been shown to be representative of Mars analogue terrain
[30]. During these field trials, different test tracks in natural terrain, GAP-modes and footprints have
been tested. Since the focus of those campaigns was different from the aim of this research, only a
small portion of the data logs can be effectively used for terrain estimation purposes. Table 1 sums
up the datasets available for terrain and slippage classification, clarifying specific terrain, total run
time and logged sensors. Specifically, the only available run in the Morocco campaign is performed
on sandy dunes of flat/moderate slopes, while Utah data logs are available on flat, moderate sloped
and steep sloped rocky terrains. Utah moderate sloped terrain presents an inclination less than 10
deg, while steep sloped terrain had a grade up to 28 degrees. All the available experimental runs are
performed following a straight path. Sensor signals are logged together with a synchronized
timestamp. Four sensor modalities are available on SherpaTT: the four FTSs, the body’s IMU, a
Differential Global Positioning System (DGPS) on the rover body and joint telemetry. The FTSs are
six axial sensors able to measure the three cartesian components of forces and moments acting on
each wheel. The IMU outputs the rover’s attitude ad accelerations, while DGPS provides an absolute
position of the rover and it is used for ground truthing. Joint position and speed, as well as each
joint’s electrical current and PWM duty cycle, are available for this study.
Proprioceptive data streams have been associated with a sequence of terrain patches with the
same length. In this work, a patch length of 0.3 m is considered. In such a way, for each terrain patch,
a set of features has been computed, as extensively explained in the following section.
Table 1. Datasets gathered by SherpaTT during field trials; for each test run, terrain description,
testing time and available logged sensors are indicated.
Run
ID
Test
Site
Terrain
Type Slope Run Time
[s] FTS IMU DGPS Encoders
R01 Morocco Sand Flat/Moderate 381.5 ✓ ✗ ✗ ✓
R02 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R03 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R04 Utah Rock Moderate 152.4 ✓ ✓ ✗ ✓
R05 Utah Rock Steep 453.9 ✓ ✓ ✓ ✓
R06 Utah Rock Steep 457.7 ✓ ✓ ✓ ✓
R07 Utah Rock Steep 481.2 ✓ ✓ ✓ ✓
Appl. Sci. 2020, 10, x FOR PEER REVIEW 4 of 16
Figure 1. SherpaTT in soft sand dunes during Morocco field trials in 2018.
Figure 2. Examples of possible footprint configurations and resulting support polygons.
2.1. Data Sets
Two extensive field trials have been conducted by SherpaTT in the desert of Morocco (2019) and
in the desert of Utah (2016). Both sites have been shown to be representative of Mars analogue terrain
[30]. During these field trials, different test tracks in natural terrain, GAP-modes and footprints have
been tested. Since the focus of those campaigns was different from the aim of this research, only a
small portion of the data logs can be effectively used for terrain estimation purposes. Table 1 sums
up the datasets available for terrain and slippage classification, clarifying specific terrain, total run
time and logged sensors. Specifically, the only available run in the Morocco campaign is performed
on sandy dunes of flat/moderate slopes, while Utah data logs are available on flat, moderate sloped
and steep sloped rocky terrains. Utah moderate sloped terrain presents an inclination less than 10
deg, while steep sloped terrain had a grade up to 28 degrees. All the available experimental runs are
performed following a straight path. Sensor signals are logged together with a synchronized
timestamp. Four sensor modalities are available on SherpaTT: the four FTSs, the body’s IMU, a
Differential Global Positioning System (DGPS) on the rover body and joint telemetry. The FTSs are
six axial sensors able to measure the three cartesian components of forces and moments acting on
each wheel. The IMU outputs the rover’s attitude ad accelerations, while DGPS provides an absolute
position of the rover and it is used for ground truthing. Joint position and speed, as well as each
joint’s electrical current and PWM duty cycle, are available for this study.
Proprioceptive data streams have been associated with a sequence of terrain patches with the
same length. In this work, a patch length of 0.3 m is considered. In such a way, for each terrain patch,
a set of features has been computed, as extensively explained in the following section.
Table 1. Datasets gathered by SherpaTT during field trials; for each test run, terrain description,
testing time and available logged sensors are indicated.
Run
ID
Test
Site
Terrain
Type Slope Run Time
[s] FTS IMU DGPS Encoders
R01 Morocco Sand Flat/Moderate 381.5 ✓ ✗ ✗ ✓
R02 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R03 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R04 Utah Rock Moderate 152.4 ✓ ✓ ✗ ✓
R05 Utah Rock Steep 453.9 ✓ ✓ ✓ ✓
R06 Utah Rock Steep 457.7 ✓ ✓ ✓ ✓
R07 Utah Rock Steep 481.2 ✓ ✓ ✓ ✓
Appl. Sci. 2020, 10, x FOR PEER REVIEW 4 of 16
Figure 1. SherpaTT in soft sand dunes during Morocco field trials in 2018.
Figure 2. Examples of possible footprint configurations and resulting support polygons.
2.1. Data Sets
Two extensive field trials have been conducted by SherpaTT in the desert of Morocco (2019) and
in the desert of Utah (2016). Both sites have been shown to be representative of Mars analogue terrain
[30]. During these field trials, different test tracks in natural terrain, GAP-modes and footprints have
been tested. Since the focus of those campaigns was different from the aim of this research, only a
small portion of the data logs can be effectively used for terrain estimation purposes. Table 1 sums
up the datasets available for terrain and slippage classification, clarifying specific terrain, total run
time and logged sensors. Specifically, the only available run in the Morocco campaign is performed
on sandy dunes of flat/moderate slopes, while Utah data logs are available on flat, moderate sloped
and steep sloped rocky terrains. Utah moderate sloped terrain presents an inclination less than 10
deg, while steep sloped terrain had a grade up to 28 degrees. All the available experimental runs are
performed following a straight path. Sensor signals are logged together with a synchronized
timestamp. Four sensor modalities are available on SherpaTT: the four FTSs, the body’s IMU, a
Differential Global Positioning System (DGPS) on the rover body and joint telemetry. The FTSs are
six axial sensors able to measure the three cartesian components of forces and moments acting on
each wheel. The IMU outputs the rover’s attitude ad accelerations, while DGPS provides an absolute
position of the rover and it is used for ground truthing. Joint position and speed, as well as each
joint’s electrical current and PWM duty cycle, are available for this study.
Proprioceptive data streams have been associated with a sequence of terrain patches with the
same length. In this work, a patch length of 0.3 m is considered. In such a way, for each terrain patch,
a set of features has been computed, as extensively explained in the following section.
Table 1. Datasets gathered by SherpaTT during field trials; for each test run, terrain description,
testing time and available logged sensors are indicated.
Run
ID
Test
Site
Terrain
Type Slope Run Time
[s] FTS IMU DGPS Encoders
R01 Morocco Sand Flat/Moderate 381.5 ✓ ✗ ✗ ✓
R02 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R03 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R04 Utah Rock Moderate 152.4 ✓ ✓ ✗ ✓
R05 Utah Rock Steep 453.9 ✓ ✓ ✓ ✓
R06 Utah Rock Steep 457.7 ✓ ✓ ✓ ✓
R07 Utah Rock Steep 481.2 ✓ ✓ ✓ ✓
R03 Utah Rock Flat 214.8
Appl. Sci. 2020, 10, x FOR PEER REVIEW 4 of 16
Figure 1. SherpaTT in soft sand dunes during Morocco field trials in 2018.
Figure 2. Examples of possible footprint configurations and resulting support polygons.
2.1. Data Sets
Two extensive field trials have been conducted by SherpaTT in the desert of Morocco (2019) and
in the desert of Utah (2016). Both sites have been shown to be representative of Mars analogue terrain
[30]. During these field trials, different test tracks in natural terrain, GAP-modes and footprints have
been tested. Since the focus of those campaigns was different from the aim of this research, only a
small portion of the data logs can be effectively used for terrain estimation purposes. Table 1 sums
up the datasets available for terrain and slippage classification, clarifying specific terrain, total run
time and logged sensors. Specifically, the only available run in the Morocco campaign is performed
on sandy dunes of flat/moderate slopes, while Utah data logs are available on flat, moderate sloped
and steep sloped rocky terrains. Utah moderate sloped terrain presents an inclination less than 10
deg, while steep sloped terrain had a grade up to 28 degrees. All the available experimental runs are
performed following a straight path. Sensor signals are logged together with a synchronized
timestamp. Four sensor modalities are available on SherpaTT: the four FTSs, the body’s IMU, a
Differential Global Positioning System (DGPS) on the rover body and joint telemetry. The FTSs are
six axial sensors able to measure the three cartesian components of forces and moments acting on
each wheel. The IMU outputs the rover’s attitude ad accelerations, while DGPS provides an absolute
position of the rover and it is used for ground truthing. Joint position and speed, as well as each
joint’s electrical current and PWM duty cycle, are available for this study.
Proprioceptive data streams have been associated with a sequence of terrain patches with the
same length. In this work, a patch length of 0.3 m is considered. In such a way, for each terrain patch,
a set of features has been computed, as extensively explained in the following section.
Table 1. Datasets gathered by SherpaTT during field trials; for each test run, terrain description,
testing time and available logged sensors are indicated.
Run
ID
Test
Site
Terrain
Type Slope Run Time
[s] FTS IMU DGPS Encoders
R01 Morocco Sand Flat/Moderate 381.5 ✓ ✗ ✗ ✓
R02 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R03 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R04 Utah Rock Moderate 152.4 ✓ ✓ ✗ ✓
R05 Utah Rock Steep 453.9 ✓ ✓ ✓ ✓
R06 Utah Rock Steep 457.7 ✓ ✓ ✓ ✓
R07 Utah Rock Steep 481.2 ✓ ✓ ✓ ✓
Appl. Sci. 2020, 10, x FOR PEER REVIEW 4 of 16
Figure 1. SherpaTT in soft sand dunes during Morocco field trials in 2018.
Figure 2. Examples of possible footprint configurations and resulting support polygons.
2.1. Data Sets
Two extensive field trials have been conducted by SherpaTT in the desert of Morocco (2019) and
in the desert of Utah (2016). Both sites have been shown to be representative of Mars analogue terrain
[30]. During these field trials, different test tracks in natural terrain, GAP-modes and footprints have
been tested. Since the focus of those campaigns was different from the aim of this research, only a
small portion of the data logs can be effectively used for terrain estimation purposes. Table 1 sums
up the datasets available for terrain and slippage classification, clarifying specific terrain, total run
time and logged sensors. Specifically, the only available run in the Morocco campaign is performed
on sandy dunes of flat/moderate slopes, while Utah data logs are available on flat, moderate sloped
and steep sloped rocky terrains. Utah moderate sloped terrain presents an inclination less than 10
deg, while steep sloped terrain had a grade up to 28 degrees. All the available experimental runs are
performed following a straight path. Sensor signals are logged together with a synchronized
timestamp. Four sensor modalities are available on SherpaTT: the four FTSs, the body’s IMU, a
Differential Global Positioning System (DGPS) on the rover body and joint telemetry. The FTSs are
six axial sensors able to measure the three cartesian components of forces and moments acting on
each wheel. The IMU outputs the rover’s attitude ad accelerations, while DGPS provides an absolute
position of the rover and it is used for ground truthing. Joint position and speed, as well as each
joint’s electrical current and PWM duty cycle, are available for this study.
Proprioceptive data streams have been associated with a sequence of terrain patches with the
same length. In this work, a patch length of 0.3 m is considered. In such a way, for each terrain patch,
a set of features has been computed, as extensively explained in the following section.
Table 1. Datasets gathered by SherpaTT during field trials; for each test run, terrain description,
testing time and available logged sensors are indicated.
Run
ID
Test
Site
Terrain
Type Slope Run Time
[s] FTS IMU DGPS Encoders
R01 Morocco Sand Flat/Moderate 381.5 ✓ ✗ ✗ ✓
R02 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R03 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R04 Utah Rock Moderate 152.4 ✓ ✓ ✗ ✓
R05 Utah Rock Steep 453.9 ✓ ✓ ✓ ✓
R06 Utah Rock Steep 457.7 ✓ ✓ ✓ ✓
R07 Utah Rock Steep 481.2 ✓ ✓ ✓ ✓
Appl. Sci. 2020, 10, x FOR PEER REVIEW 4 of 16
Figure 1. SherpaTT in soft sand dunes during Morocco field trials in 2018.
Figure 2. Examples of possible footprint configurations and resulting support polygons.
2.1. Data Sets
Two extensive field trials have been conducted by SherpaTT in the desert of Morocco (2019) and
in the desert of Utah (2016). Both sites have been shown to be representative of Mars analogue terrain
[30]. During these field trials, different test tracks in natural terrain, GAP-modes and footprints have
been tested. Since the focus of those campaigns was different from the aim of this research, only a
small portion of the data logs can be effectively used for terrain estimation purposes. Table 1 sums
up the datasets available for terrain and slippage classification, clarifying specific terrain, total run
time and logged sensors. Specifically, the only available run in the Morocco campaign is performed
on sandy dunes of flat/moderate slopes, while Utah data logs are available on flat, moderate sloped
and steep sloped rocky terrains. Utah moderate sloped terrain presents an inclination less than 10
deg, while steep sloped terrain had a grade up to 28 degrees. All the available experimental runs are
performed following a straight path. Sensor signals are logged together with a synchronized
timestamp. Four sensor modalities are available on SherpaTT: the four FTSs, the body’s IMU, a
Differential Global Positioning System (DGPS) on the rover body and joint telemetry. The FTSs are
six axial sensors able to measure the three cartesian components of forces and moments acting on
each wheel. The IMU outputs the rover’s attitude ad accelerations, while DGPS provides an absolute
position of the rover and it is used for ground truthing. Joint position and speed, as well as each
joint’s electrical current and PWM duty cycle, are available for this study.
Proprioceptive data streams have been associated with a sequence of terrain patches with the
same length. In this work, a patch length of 0.3 m is considered. In such a way, for each terrain patch,
a set of features has been computed, as extensively explained in the following section.
Table 1. Datasets gathered by SherpaTT during field trials; for each test run, terrain description,
testing time and available logged sensors are indicated.
Run
ID
Test
Site
Terrain
Type Slope Run Time
[s] FTS IMU DGPS Encoders
R01 Morocco Sand Flat/Moderate 381.5 ✓ ✗ ✗ ✓
R02 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R03 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R04 Utah Rock Moderate 152.4 ✓ ✓ ✗ ✓
R05 Utah Rock Steep 453.9 ✓ ✓ ✓ ✓
R06 Utah Rock Steep 457.7 ✓ ✓ ✓ ✓
R07 Utah Rock Steep 481.2 ✓ ✓ ✓ ✓
Appl. Sci. 2020, 10, x FOR PEER REVIEW 4 of 16
Figure 1. SherpaTT in soft sand dunes during Morocco field trials in 2018.
Figure 2. Examples of possible footprint configurations and resulting support polygons.
2.1. Data Sets
Two extensive field trials have been conducted by SherpaTT in the desert of Morocco (2019) and
in the desert of Utah (2016). Both sites have been shown to be representative of Mars analogue terrain
[30]. During these field trials, different test tracks in natural terrain, GAP-modes and footprints have
been tested. Since the focus of those campaigns was different from the aim of this research, only a
small portion of the data logs can be effectively used for terrain estimation purposes. Table 1 sums
up the datasets available for terrain and slippage classification, clarifying specific terrain, total run
time and logged sensors. Specifically, the only available run in the Morocco campaign is performed
on sandy dunes of flat/moderate slopes, while Utah data logs are available on flat, moderate sloped
and steep sloped rocky terrains. Utah moderate sloped terrain presents an inclination less than 10
deg, while steep sloped terrain had a grade up to 28 degrees. All the available experimental runs are
performed following a straight path. Sensor signals are logged together with a synchronized
timestamp. Four sensor modalities are available on SherpaTT: the four FTSs, the body’s IMU, a
Differential Global Positioning System (DGPS) on the rover body and joint telemetry. The FTSs are
six axial sensors able to measure the three cartesian components of forces and moments acting on
each wheel. The IMU outputs the rover’s attitude ad accelerations, while DGPS provides an absolute
position of the rover and it is used for ground truthing. Joint position and speed, as well as each
joint’s electrical current and PWM duty cycle, are available for this study.
Proprioceptive data streams have been associated with a sequence of terrain patches with the
same length. In this work, a patch length of 0.3 m is considered. In such a way, for each terrain patch,
a set of features has been computed, as extensively explained in the following section.
Table 1. Datasets gathered by SherpaTT during field trials; for each test run, terrain description,
testing time and available logged sensors are indicated.
Run
ID
Test
Site
Terrain
Type Slope Run Time
[s] FTS IMU DGPS Encoders
R01 Morocco Sand Flat/Moderate 381.5 ✓ ✗ ✗ ✓
R02 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R03 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R04 Utah Rock Moderate 152.4 ✓ ✓ ✗ ✓
R05 Utah Rock Steep 453.9 ✓ ✓ ✓ ✓
R06 Utah Rock Steep 457.7 ✓ ✓ ✓ ✓
R07 Utah Rock Steep 481.2 ✓ ✓ ✓ ✓
R04 Utah Rock Moderate 152.4
Appl. Sci. 2020, 10, x FOR PEER REVIEW 4 of 16
Figure 1. SherpaTT in soft sand dunes during Morocco field trials in 2018.
Figure 2. Examples of possible footprint configurations and resulting support polygons.
2.1. Data Sets
Two extensive field trials have been conducted by SherpaTT in the desert of Morocco (2019) and
in the desert of Utah (2016). Both sites have been shown to be representative of Mars analogue terrain
[30]. During these field trials, different test tracks in natural terrain, GAP-modes and footprints have
been tested. Since the focus of those campaigns was different from the aim of this research, only a
small portion of the data logs can be effectively used for terrain estimation purposes. Table 1 sums
up the datasets available for terrain and slippage classification, clarifying specific terrain, total run
time and logged sensors. Specifically, the only available run in the Morocco campaign is performed
on sandy dunes of flat/moderate slopes, while Utah data logs are available on flat, moderate sloped
and steep sloped rocky terrains. Utah moderate sloped terrain presents an inclination less than 10
deg, while steep sloped terrain had a grade up to 28 degrees. All the available experimental runs are
performed following a straight path. Sensor signals are logged together with a synchronized
timestamp. Four sensor modalities are available on SherpaTT: the four FTSs, the body’s IMU, a
Differential Global Positioning System (DGPS) on the rover body and joint telemetry. The FTSs are
six axial sensors able to measure the three cartesian components of forces and moments acting on
each wheel. The IMU outputs the rover’s attitude ad accelerations, while DGPS provides an absolute
position of the rover and it is used for ground truthing. Joint position and speed, as well as each
joint’s electrical current and PWM duty cycle, are available for this study.
Proprioceptive data streams have been associated with a sequence of terrain patches with the
same length. In this work, a patch length of 0.3 m is considered. In such a way, for each terrain patch,
a set of features has been computed, as extensively explained in the following section.
Table 1. Datasets gathered by SherpaTT during field trials; for each test run, terrain description,
testing time and available logged sensors are indicated.
Run
ID
Test
Site
Terrain
Type Slope Run Time
[s] FTS IMU DGPS Encoders
R01 Morocco Sand Flat/Moderate 381.5 ✓ ✗ ✗ ✓
R02 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R03 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R04 Utah Rock Moderate 152.4 ✓ ✓ ✗ ✓
R05 Utah Rock Steep 453.9 ✓ ✓ ✓ ✓
R06 Utah Rock Steep 457.7 ✓ ✓ ✓ ✓
R07 Utah Rock Steep 481.2 ✓ ✓ ✓ ✓
Appl. Sci. 2020, 10, x FOR PEER REVIEW 4 of 16
Figure 1. SherpaTT in soft sand dunes during Morocco field trials in 2018.
Figure 2. Examples of possible footprint configurations and resulting support polygons.
2.1. Data Sets
Two extensive field trials have been conducted by SherpaTT in the desert of Morocco (2019) and
in the desert of Utah (2016). Both sites have been shown to be representative of Mars analogue terrain
[30]. During these field trials, different test tracks in natural terrain, GAP-modes and footprints have
been tested. Since the focus of those campaigns was different from the aim of this research, only a
small portion of the data logs can be effectively used for terrain estimation purposes. Table 1 sums
up the datasets available for terrain and slippage classification, clarifying specific terrain, total run
time and logged sensors. Specifically, the only available run in the Morocco campaign is performed
on sandy dunes of flat/moderate slopes, while Utah data logs are available on flat, moderate sloped
and steep sloped rocky terrains. Utah moderate sloped terrain presents an inclination less than 10
deg, while steep sloped terrain had a grade up to 28 degrees. All the available experimental runs are
performed following a straight path. Sensor signals are logged together with a synchronized
timestamp. Four sensor modalities are available on SherpaTT: the four FTSs, the body’s IMU, a
Differential Global Positioning System (DGPS) on the rover body and joint telemetry. The FTSs are
six axial sensors able to measure the three cartesian components of forces and moments acting on
each wheel. The IMU outputs the rover’s attitude ad accelerations, while DGPS provides an absolute
position of the rover and it is used for ground truthing. Joint position and speed, as well as each
joint’s electrical current and PWM duty cycle, are available for this study.
Proprioceptive data streams have been associated with a sequence of terrain patches with the
same length. In this work, a patch length of 0.3 m is considered. In such a way, for each terrain patch,
a set of features has been computed, as extensively explained in the following section.
Table 1. Datasets gathered by SherpaTT during field trials; for each test run, terrain description,
testing time and available logged sensors are indicated.
Run
ID
Test
Site
Terrain
Type Slope Run Time
[s] FTS IMU DGPS Encoders
R01 Morocco Sand Flat/Moderate 381.5 ✓ ✗ ✗ ✓
R02 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R03 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R04 Utah Rock Moderate 152.4 ✓ ✓ ✗ ✓
R05 Utah Rock Steep 453.9 ✓ ✓ ✓ ✓
R06 Utah Rock Steep 457.7 ✓ ✓ ✓ ✓
R07 Utah Rock Steep 481.2 ✓ ✓ ✓ ✓
Appl. Sci. 2020, 10, x FOR PEER REVIEW 4 of 16
Figure 1. SherpaTT in soft sand dunes during Morocco field trials in 2018.
Figure 2. Examples of possible footprint configurations and resulting support polygons.
2.1. Data Sets
Two extensive field trials have been conducted by SherpaTT in the desert of Morocco (2019) and
in the desert of Utah (2016). Both sites have been shown to be representative of Mars analogue terrain
[30]. During these field trials, different test tracks in natural terrain, GAP-modes and footprints have
been tested. Since the focus of those campaigns was different from the aim of this research, only a
small portion of the data logs can be effectively used for terrain estimation purposes. Table 1 sums
up the datasets available for terrain and slippage classification, clarifying specific terrain, total run
time and logged sensors. Specifically, the only available run in the Morocco campaign is performed
on sandy dunes of flat/moderate slopes, while Utah data logs are available on flat, moderate sloped
and steep sloped rocky terrains. Utah moderate sloped terrain presents an inclination less than 10
deg, while steep sloped terrain had a grade up to 28 degrees. All the available experimental runs are
performed following a straight path. Sensor signals are logged together with a synchronized
timestamp. Four sensor modalities are available on SherpaTT: the four FTSs, the body’s IMU, a
Differential Global Positioning System (DGPS) on the rover body and joint telemetry. The FTSs are
six axial sensors able to measure the three cartesian components of forces and moments acting on
each wheel. The IMU outputs the rover’s attitude ad accelerations, while DGPS provides an absolute
position of the rover and it is used for ground truthing. Joint position and speed, as well as each
joint’s electrical current and PWM duty cycle, are available for this study.
Proprioceptive data streams have been associated with a sequence of terrain patches with the
same length. In this work, a patch length of 0.3 m is considered. In such a way, for each terrain patch,
a set of features has been computed, as extensively explained in the following section.
Table 1. Datasets gathered by SherpaTT during field trials; for each test run, terrain description,
testing time and available logged sensors are indicated.
Run
ID
Test
Site
Terrain
Type Slope Run Time
[s] FTS IMU DGPS Encoders
R01 Morocco Sand Flat/Moderate 381.5 ✓ ✗ ✗ ✓
R02 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R03 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R04 Utah Rock Moderate 152.4 ✓ ✓ ✗ ✓
R05 Utah Rock Steep 453.9 ✓ ✓ ✓ ✓
R06 Utah Rock Steep 457.7 ✓ ✓ ✓ ✓
R07 Utah Rock Steep 481.2 ✓ ✓ ✓ ✓
Appl. Sci. 2020, 10, x FOR PEER REVIEW 4 of 16
Figure 1. SherpaTT in soft sand dunes during Morocco field trials in 2018.
Figure 2. Examples of possible footprint configurations and resulting support polygons.
2.1. Data Sets
Two extensive field trials have been conducted by SherpaTT in the desert of Morocco (2019) and
in the desert of Utah (2016). Both sites have been shown to be representative of Mars analogue terrain
[30]. During these field trials, different test tracks in natural terrain, GAP-modes and footprints have
been tested. Since the focus of those campaigns was different from the aim of this research, only a
small portion of the data logs can be effectively used for terrain estimation purposes. Table 1 sums
up the datasets available for terrain and slippage classification, clarifying specific terrain, total run
time and logged sensors. Specifically, the only available run in the Morocco campaign is performed
on sandy dunes of flat/moderate slopes, while Utah data logs are available on flat, moderate sloped
and steep sloped rocky terrains. Utah moderate sloped terrain presents an inclination less than 10
deg, while steep sloped terrain had a grade up to 28 degrees. All the available experimental runs are
performed following a straight path. Sensor signals are logged together with a synchronized
timestamp. Four sensor modalities are available on SherpaTT: the four FTSs, the body’s IMU, a
Differential Global Positioning System (DGPS) on the rover body and joint telemetry. The FTSs are
six axial sensors able to measure the three cartesian components of forces and moments acting on
each wheel. The IMU outputs the rover’s attitude ad accelerations, while DGPS provides an absolute
position of the rover and it is used for ground truthing. Joint position and speed, as well as each
joint’s electrical current and PWM duty cycle, are available for this study.
Proprioceptive data streams have been associated with a sequence of terrain patches with the
same length. In this work, a patch length of 0.3 m is considered. In such a way, for each terrain patch,
a set of features has been computed, as extensively explained in the following section.
Table 1. Datasets gathered by SherpaTT during field trials; for each test run, terrain description,
testing time and available logged sensors are indicated.
Run
ID
Test
Site
Terrain
Type Slope Run Time
[s] FTS IMU DGPS Encoders
R01 Morocco Sand Flat/Moderate 381.5 ✓ ✗ ✗ ✓
R02 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R03 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R04 Utah Rock Moderate 152.4 ✓ ✓ ✗ ✓
R05 Utah Rock Steep 453.9 ✓ ✓ ✓ ✓
R06 Utah Rock Steep 457.7 ✓ ✓ ✓ ✓
R07 Utah Rock Steep 481.2 ✓ ✓ ✓ ✓
R05 Utah Rock Steep 453.9
Appl. Sci. 2020, 10, x FOR PEER REVIEW 4 of 16
Figure 1. SherpaTT in soft sand dunes during Morocco field trials in 2018.
Figure 2. Examples of possible footprint configurations and resulting support polygons.
2.1. Data Sets
Two extensive field trials have been conducted by SherpaTT in the desert of Morocco (2019) and
in the desert of Utah (2016). Both sites have been shown to be representative of Mars analogue terrain
[30]. During these field trials, different test tracks in natural terrain, GAP-modes and footprints have
been tested. Since the focus of those campaigns was different from the aim of this research, only a
small portion of the data logs can be effectively used for terrain estimation purposes. Table 1 sums
up the datasets available for terrain and slippage classification, clarifying specific terrain, total run
time and logged sensors. Specifically, the only available run in the Morocco campaign is performed
on sandy dunes of flat/moderate slopes, while Utah data logs are available on flat, moderate sloped
and steep sloped rocky terrains. Utah moderate sloped terrain presents an inclination less than 10
deg, while steep sloped terrain had a grade up to 28 degrees. All the available experimental runs are
performed following a straight path. Sensor signals are logged together with a synchronized
timestamp. Four sensor modalities are available on SherpaTT: the four FTSs, the body’s IMU, a
Differential Global Positioning System (DGPS) on the rover body and joint telemetry. The FTSs are
six axial sensors able to measure the three cartesian components of forces and moments acting on
each wheel. The IMU outputs the rover’s attitude ad accelerations, while DGPS provides an absolute
position of the rover and it is used for ground truthing. Joint position and speed, as well as each
joint’s electrical current and PWM duty cycle, are available for this study.
Proprioceptive data streams have been associated with a sequence of terrain patches with the
same length. In this work, a patch length of 0.3 m is considered. In such a way, for each terrain patch,
a set of features has been computed, as extensively explained in the following section.
Table 1. Datasets gathered by SherpaTT during field trials; for each test run, terrain description,
testing time and available logged sensors are indicated.
Run
ID
Test
Site
Terrain
Type Slope Run Time
[s] FTS IMU DGPS Encoders
R01 Morocco Sand Flat/Moderate 381.5 ✓ ✗ ✗ ✓
R02 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R03 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R04 Utah Rock Moderate 152.4 ✓ ✓ ✗ ✓
R05 Utah Rock Steep 453.9 ✓ ✓ ✓ ✓
R06 Utah Rock Steep 457.7 ✓ ✓ ✓ ✓
R07 Utah Rock Steep 481.2 ✓ ✓ ✓ ✓
Appl. Sci. 2020, 10, x FOR PEER REVIEW 4 of 16
Figure 1. SherpaTT in soft sand dunes during Morocco field trials in 2018.
Figure 2. Examples of possible footprint configurations and resulting support polygons.
2.1. Data Sets
Two extensive field trials have been conducted by SherpaTT in the desert of Morocco (2019) and
in the desert of Utah (2016). Both sites have been shown to be representative of Mars analogue terrain
[30]. During these field trials, different test tracks in natural terrain, GAP-modes and footprints have
been tested. Since the focus of those campaigns was different from the aim of this research, only a
small portion of the data logs can be effectively used for terrain estimation purposes. Table 1 sums
up the datasets available for terrain and slippage classification, clarifying specific terrain, total run
time and logged sensors. Specifically, the only available run in the Morocco campaign is performed
on sandy dunes of flat/moderate slopes, while Utah data logs are available on flat, moderate sloped
and steep sloped rocky terrains. Utah moderate sloped terrain presents an inclination less than 10
deg, while steep sloped terrain had a grade up to 28 degrees. All the available experimental runs are
performed following a straight path. Sensor signals are logged together with a synchronized
timestamp. Four sensor modalities are available on SherpaTT: the four FTSs, the body’s IMU, a
Differential Global Positioning System (DGPS) on the rover body and joint telemetry. The FTSs are
six axial sensors able to measure the three cartesian components of forces and moments acting on
each wheel. The IMU outputs the rover’s attitude ad accelerations, while DGPS provides an absolute
position of the rover and it is used for ground truthing. Joint position and speed, as well as each
joint’s electrical current and PWM duty cycle, are available for this study.
Proprioceptive data streams have been associated with a sequence of terrain patches with the
same length. In this work, a patch length of 0.3 m is considered. In such a way, for each terrain patch,
a set of features has been computed, as extensively explained in the following section.
Table 1. Datasets gathered by SherpaTT during field trials; for each test run, terrain description,
testing time and available logged sensors are indicated.
Run
ID
Test
Site
Terrain
Type Slope Run Time
[s] FTS IMU DGPS Encoders
R01 Morocco Sand Flat/Moderate 381.5 ✓ ✗ ✗ ✓
R02 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R03 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R04 Utah Rock Moderate 152.4 ✓ ✓ ✗ ✓
R05 Utah Rock Steep 453.9 ✓ ✓ ✓ ✓
R06 Utah Rock Steep 457.7 ✓ ✓ ✓ ✓
R07 Utah Rock Steep 481.2 ✓ ✓ ✓ ✓
Appl. Sci. 2020, 10, x FOR PEER REVIEW 4 of 16
Figure 1. SherpaTT in soft sand dunes during Morocco field trials in 2018.
Figure 2. Examples of possible footprint configurations and resulting support polygons.
2.1. Data Sets
Two extensive field trials have been conducted by SherpaTT in the desert of Morocco (2019) and
in the desert of Utah (2016). Both sites have been shown to be representative of Mars analogue terrain
[30]. During these field trials, different test tracks in natural terrain, GAP-modes and footprints have
been tested. Since the focus of those campaigns was different from the aim of this research, only a
small portion of the data logs can be effectively used for terrain estimation purposes. Table 1 sums
up the datasets available for terrain and slippage classification, clarifying specific terrain, total run
time and logged sensors. Specifically, the only available run in the Morocco campaign is performed
on sandy dunes of flat/moderate slopes, while Utah data logs are available on flat, moderate sloped
and steep sloped rocky terrains. Utah moderate sloped terrain presents an inclination less than 10
deg, while steep sloped terrain had a grade up to 28 degrees. All the available experimental runs are
performed following a straight path. Sensor signals are logged together with a synchronized
timestamp. Four sensor modalities are available on SherpaTT: the four FTSs, the body’s IMU, a
Differential Global Positioning System (DGPS) on the rover body and joint telemetry. The FTSs are
six axial sensors able to measure the three cartesian components of forces and moments acting on
each wheel. The IMU outputs the rover’s attitude ad accelerations, while DGPS provides an absolute
position of the rover and it is used for ground truthing. Joint position and speed, as well as each
joint’s electrical current and PWM duty cycle, are available for this study.
Proprioceptive data streams have been associated with a sequence of terrain patches with the
same length. In this work, a patch length of 0.3 m is considered. In such a way, for each terrain patch,
a set of features has been computed, as extensively explained in the following section.
Table 1. Datasets gathered by SherpaTT during field trials; for each test run, terrain description,
testing time and available logged sensors are indicated.
Run
ID
Test
Site
Terrain
Type Slope Run Time
[s] FTS IMU DGPS Encoders
R01 Morocco Sand Flat/Moderate 381.5 ✓ ✗ ✗ ✓
R02 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R03 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R04 Utah Rock Moderate 152.4 ✓ ✓ ✗ ✓
R05 Utah Rock Steep 453.9 ✓ ✓ ✓ ✓
R06 Utah Rock Steep 457.7 ✓ ✓ ✓ ✓
R07 Utah Rock Steep 481.2 ✓ ✓ ✓ ✓
Appl. Sci. 2020, 10, x FOR PEER REVIEW 4 of 16
Figure 1. SherpaTT in soft sand dunes during Morocco field trials in 2018.
Figure 2. Examples of possible footprint configurations and resulting support polygons.
2.1. Data Sets
Two extensive field trials have been conducted by SherpaTT in the desert of Morocco (2019) and
in the desert of Utah (2016). Both sites have been shown to be representative of Mars analogue terrain
[30]. During these field trials, different test tracks in natural terrain, GAP-modes and footprints have
been tested. Since the focus of those campaigns was different from the aim of this research, only a
small portion of the data logs can be effectively used for terrain estimation purposes. Table 1 sums
up the datasets available for terrain and slippage classification, clarifying specific terrain, total run
time and logged sensors. Specifically, the only available run in the Morocco campaign is performed
on sandy dunes of flat/moderate slopes, while Utah data logs are available on flat, moderate sloped
and steep sloped rocky terrains. Utah moderate sloped terrain presents an inclination less than 10
deg, while steep sloped terrain had a grade up to 28 degrees. All the available experimental runs are
performed following a straight path. Sensor signals are logged together with a synchronized
timestamp. Four sensor modalities are available on SherpaTT: the four FTSs, the body’s IMU, a
Differential Global Positioning System (DGPS) on the rover body and joint telemetry. The FTSs are
six axial sensors able to measure the three cartesian components of forces and moments acting on
each wheel. The IMU outputs the rover’s attitude ad accelerations, while DGPS provides an absolute
position of the rover and it is used for ground truthing. Joint position and speed, as well as each
joint’s electrical current and PWM duty cycle, are available for this study.
Proprioceptive data streams have been associated with a sequence of terrain patches with the
same length. In this work, a patch length of 0.3 m is considered. In such a way, for each terrain patch,
a set of features has been computed, as extensively explained in the following section.
Table 1. Datasets gathered by SherpaTT during field trials; for each test run, terrain description,
testing time and available logged sensors are indicated.
Run
ID
Test
Site
Terrain
Type Slope Run Time
[s] FTS IMU DGPS Encoders
R01 Morocco Sand Flat/Moderate 381.5 ✓ ✗ ✗ ✓
R02 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R03 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R04 Utah Rock Moderate 152.4 ✓ ✓ ✗ ✓
R05 Utah Rock Steep 453.9 ✓ ✓ ✓ ✓
R06 Utah Rock Steep 457.7 ✓ ✓ ✓ ✓
R07 Utah Rock Steep 481.2 ✓ ✓ ✓ ✓
R06 Utah Rock Steep 457.7
Appl. Sci. 2020, 10, x FOR PEER REVIEW 4 of 16
Figure 1. SherpaTT in soft sand dunes during Morocco field trials in 2018.
Figure 2. Examples of possible footprint configurations and resulting support polygons.
2.1. Data Sets
Two extensive field trials have been conducted by SherpaTT in the desert of Morocco (2019) and
in the desert of Utah (2016). Both sites have been shown to be representative of Mars analogue terrain
[30]. During these field trials, different test tracks in natural terrain, GAP-modes and footprints have
been tested. Since the focus of those campaigns was different from the aim of this research, only a
small portion of the data logs can be effectively used for terrain estimation purposes. Table 1 sums
up the datasets available for terrain and slippage classification, clarifying specific terrain, total run
time and logged sensors. Specifically, the only available run in the Morocco campaign is performed
on sandy dunes of flat/moderate slopes, while Utah data logs are available on flat, moderate sloped
and steep sloped rocky terrains. Utah moderate sloped terrain presents an inclination less than 10
deg, while steep sloped terrain had a grade up to 28 degrees. All the available experimental runs are
performed following a straight path. Sensor signals are logged together with a synchronized
timestamp. Four sensor modalities are available on SherpaTT: the four FTSs, the body’s IMU, a
Differential Global Positioning System (DGPS) on the rover body and joint telemetry. The FTSs are
six axial sensors able to measure the three cartesian components of forces and moments acting on
each wheel. The IMU outputs the rover’s attitude ad accelerations, while DGPS provides an absolute
position of the rover and it is used for ground truthing. Joint position and speed, as well as each
joint’s electrical current and PWM duty cycle, are available for this study.
Proprioceptive data streams have been associated with a sequence of terrain patches with the
same length. In this work, a patch length of 0.3 m is considered. In such a way, for each terrain patch,
a set of features has been computed, as extensively explained in the following section.
Table 1. Datasets gathered by SherpaTT during field trials; for each test run, terrain description,
testing time and available logged sensors are indicated.
Run
ID
Test
Site
Terrain
Type Slope Run Time
[s] FTS IMU DGPS Encoders
R01 Morocco Sand Flat/Moderate 381.5 ✓ ✗ ✗ ✓
R02 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R03 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R04 Utah Rock Moderate 152.4 ✓ ✓ ✗ ✓
R05 Utah Rock Steep 453.9 ✓ ✓ ✓ ✓
R06 Utah Rock Steep 457.7 ✓ ✓ ✓ ✓
R07 Utah Rock Steep 481.2 ✓ ✓ ✓ ✓
Appl. Sci. 2020, 10, x FOR PEER REVIEW 4 of 16
Figure 1. SherpaTT in soft sand dunes during Morocco field trials in 2018.
Figure 2. Examples of possible footprint configurations and resulting support polygons.
2.1. Data Sets
Two extensive field trials have been conducted by SherpaTT in the desert of Morocco (2019) and
in the desert of Utah (2016). Both sites have been shown to be representative of Mars analogue terrain
[30]. During these field trials, different test tracks in natural terrain, GAP-modes and footprints have
been tested. Since the focus of those campaigns was different from the aim of this research, only a
small portion of the data logs can be effectively used for terrain estimation purposes. Table 1 sums
up the datasets available for terrain and slippage classification, clarifying specific terrain, total run
time and logged sensors. Specifically, the only available run in the Morocco campaign is performed
on sandy dunes of flat/moderate slopes, while Utah data logs are available on flat, moderate sloped
and steep sloped rocky terrains. Utah moderate sloped terrain presents an inclination less than 10
deg, while steep sloped terrain had a grade up to 28 degrees. All the available experimental runs are
performed following a straight path. Sensor signals are logged together with a synchronized
timestamp. Four sensor modalities are available on SherpaTT: the four FTSs, the body’s IMU, a
Differential Global Positioning System (DGPS) on the rover body and joint telemetry. The FTSs are
six axial sensors able to measure the three cartesian components of forces and moments acting on
each wheel. The IMU outputs the rover’s attitude ad accelerations, while DGPS provides an absolute
position of the rover and it is used for ground truthing. Joint position and speed, as well as each
joint’s electrical current and PWM duty cycle, are available for this study.
Proprioceptive data streams have been associated with a sequence of terrain patches with the
same length. In this work, a patch length of 0.3 m is considered. In such a way, for each terrain patch,
a set of features has been computed, as extensively explained in the following section.
Table 1. Datasets gathered by SherpaTT during field trials; for each test run, terrain description,
testing time and available logged sensors are indicated.
Run
ID
Test
Site
Terrain
Type Slope Run Time
[s] FTS IMU DGPS Encoders
R01 Morocco Sand Flat/Moderate 381.5 ✓ ✗ ✗ ✓
R02 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R03 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R04 Utah Rock Moderate 152.4 ✓ ✓ ✗ ✓
R05 Utah Rock Steep 453.9 ✓ ✓ ✓ ✓
R06 Utah Rock Steep 457.7 ✓ ✓ ✓ ✓
R07 Utah Rock Steep 481.2 ✓ ✓ ✓ ✓
Appl. Sci. 2020, 10, x FOR PEER REVIEW 4 of 16
Figure 1. SherpaTT in soft sand dunes during Morocco field trials in 2018.
Figure 2. Examples of possible footprint configurations and resulting support polygons.
2.1. Data Sets
Two extensive field trials have been conducted by SherpaTT in the desert of Morocco (2019) and
in the desert of Utah (2016). Both sites have been shown to be representative of Mars analogue terrain
[30]. During these field trials, different test tracks in natural terrain, GAP-modes and footprints have
been tested. Since the focus of those campaigns was different from the aim of this research, only a
small portion of the data logs can be effectively used for terrain estimation purposes. Table 1 sums
up the datasets available for terrain and slippage classification, clarifying specific terrain, total run
time and logged sensors. Specifically, the only available run in the Morocco campaign is performed
on sandy dunes of flat/moderate slopes, while Utah data logs are available on flat, moderate sloped
and steep sloped rocky terrains. Utah moderate sloped terrain presents an inclination less than 10
deg, while steep sloped terrain had a grade up to 28 degrees. All the available experimental runs are
performed following a straight path. Sensor signals are logged together with a synchronized
timestamp. Four sensor modalities are available on SherpaTT: the four FTSs, the body’s IMU, a
Differential Global Positioning System (DGPS) on the rover body and joint telemetry. The FTSs are
six axial sensors able to measure the three cartesian components of forces and moments acting on
each wheel. The IMU outputs the rover’s attitude ad accelerations, while DGPS provides an absolute
position of the rover and it is used for ground truthing. Joint position and speed, as well as each
joint’s electrical current and PWM duty cycle, are available for this study.
Proprioceptive data streams have been associated with a sequence of terrain patches with the
same length. In this work, a patch length of 0.3 m is considered. In such a way, for each terrain patch,
a set of features has been computed, as extensively explained in the following section.
Table 1. Datasets gathered by SherpaTT during field trials; for each test run, terrain description,
testing time and available logged sensors are indicated.
Run
ID
Test
Site
Terrain
Type Slope Run Time
[s] FTS IMU DGPS Encoders
R01 Morocco Sand Flat/Moderate 381.5 ✓ ✗ ✗ ✓
R02 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R03 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R04 Utah Rock Moderate 152.4 ✓ ✓ ✗ ✓
R05 Utah Rock Steep 453.9 ✓ ✓ ✓ ✓
R06 Utah Rock Steep 457.7 ✓ ✓ ✓ ✓
R07 Utah Rock Steep 481.2 ✓ ✓ ✓ ✓
Appl. Sci. 2020, 10, x FOR PEER REVIEW 4 of 16
Figure 1. SherpaTT in soft sand dunes during Morocco field trials in 2018.
Figure 2. Examples of possible footprint configurations and resulting support polygons.
2.1. Data Sets
Two extensive field trials have been conducted by SherpaTT in the desert of Morocco (2019) and
in the desert of Utah (2016). Both sites have been shown to be representative of Mars analogue terrain
[30]. During these field trials, different test tracks in natural terrain, GAP-modes and footprints have
been tested. Since the focus of those campaigns was different from the aim of this research, only a
small portion of the data logs can be effectively used for terrain estimation purposes. Table 1 sums
up the datasets available for terrain and slippage classification, clarifying specific terrain, total run
time and logged sensors. Specifically, the only available run in the Morocco campaign is performed
on sandy dunes of flat/moderate slopes, while Utah data logs are available on flat, moderate sloped
and steep sloped rocky terrains. Utah moderate sloped terrain presents an inclination less than 10
deg, while steep sloped terrain had a grade up to 28 degrees. All the available experimental runs are
performed following a straight path. Sensor signals are logged together with a synchronized
timestamp. Four sensor modalities are available on SherpaTT: the four FTSs, the body’s IMU, a
Differential Global Positioning System (DGPS) on the rover body and joint telemetry. The FTSs are
six axial sensors able to measure the three cartesian components of forces and moments acting on
each wheel. The IMU outputs the rover’s attitude ad accelerations, while DGPS provides an absolute
position of the rover and it is used for ground truthing. Joint position and speed, as well as each
joint’s electrical current and PWM duty cycle, are available for this study.
Proprioceptive data streams have been associated with a sequence of terrain patches with the
same length. In this work, a patch length of 0.3 m is considered. In such a way, for each terrain patch,
a set of features has been computed, as extensively explained in the following section.
Table 1. Datasets gathered by SherpaTT during field trials; for each test run, terrain description,
testing time and available logged sensors are indicated.
Run
ID
Test
Site
Terrain
Type Slope Run Time
[s] FTS IMU DGPS Encoders
R01 Morocco Sand Flat/Moderate 381.5 ✓ ✗ ✗ ✓
R02 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R03 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R04 Utah Rock Moderate 152.4 ✓ ✓ ✗ ✓
R05 Utah Rock Steep 453.9 ✓ ✓ ✓ ✓
R06 Utah Rock Steep 457.7 ✓ ✓ ✓ ✓
R07 Utah Rock Steep 481.2 ✓ ✓ ✓ ✓
R07 Utah Rock Steep 481.2
Appl. Sci. 2020, 10, x FOR PEER REVIEW 4 of 16
Figure 1. SherpaTT in soft sand dunes during Morocco field trials in 2018.
Figure 2. Examples of possible footprint configurations and resulting support polygons.
2.1. Data Sets
Two extensive field trials have been conducted by SherpaTT in the desert of Morocco (2019) and
in the desert of Utah (2016). Both sites have been shown to be representative of Mars analogue terrain
[30]. During these field trials, different test tracks in natural terrain, GAP-modes and footprints have
been tested. Since the focus of those campaigns was different from the aim of this research, only a
small portion of the data logs can be effectively used for terrain estimation purposes. Table 1 sums
up the datasets available for terrain and slippage classification, clarifying specific terrain, total run
time and logged sensors. Specifically, the only available run in the Morocco campaign is performed
on sandy dunes of flat/moderate slopes, while Utah data logs are available on flat, moderate sloped
and steep sloped rocky terrains. Utah moderate sloped terrain presents an inclination less than 10
deg, while steep sloped terrain had a grade up to 28 degrees. All the available experimental runs are
performed following a straight path. Sensor signals are logged together with a synchronized
timestamp. Four sensor modalities are available on SherpaTT: the four FTSs, the body’s IMU, a
Differential Global Positioning System (DGPS) on the rover body and joint telemetry. The FTSs are
six axial sensors able to measure the three cartesian components of forces and moments acting on
each wheel. The IMU outputs the rover’s attitude ad accelerations, while DGPS provides an absolute
position of the rover and it is used for ground truthing. Joint position and speed, as well as each
joint’s electrical current and PWM duty cycle, are available for this study.
Proprioceptive data streams have been associated with a sequence of terrain patches with the
same length. In this work, a patch length of 0.3 m is considered. In such a way, for each terrain patch,
a set of features has been computed, as extensively explained in the following section.
Table 1. Datasets gathered by SherpaTT during field trials; for each test run, terrain description,
testing time and available logged sensors are indicated.
Run
ID
Test
Site
Terrain
Type Slope Run Time
[s] FTS IMU DGPS Encoders
R01 Morocco Sand Flat/Moderate 381.5 ✓ ✗ ✗ ✓
R02 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R03 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R04 Utah Rock Moderate 152.4 ✓ ✓ ✗ ✓
R05 Utah Rock Steep 453.9 ✓ ✓ ✓ ✓
R06 Utah Rock Steep 457.7 ✓ ✓ ✓ ✓
R07 Utah Rock Steep 481.2 ✓ ✓ ✓ ✓
Appl. Sci. 2020, 10, x FOR PEER REVIEW 4 of 16
Figure 1. SherpaTT in soft sand dunes during Morocco field trials in 2018.
Figure 2. Examples of possible footprint configurations and resulting support polygons.
2.1. Data Sets
Two extensive field trials have been conducted by SherpaTT in the desert of Morocco (2019) and
in the desert of Utah (2016). Both sites have been shown to be representative of Mars analogue terrain
[30]. During these field trials, different test tracks in natural terrain, GAP-modes and footprints have
been tested. Since the focus of those campaigns was different from the aim of this research, only a
small portion of the data logs can be effectively used for terrain estimation purposes. Table 1 sums
up the datasets available for terrain and slippage classification, clarifying specific terrain, total run
time and logged sensors. Specifically, the only available run in the Morocco campaign is performed
on sandy dunes of flat/moderate slopes, while Utah data logs are available on flat, moderate sloped
and steep sloped rocky terrains. Utah moderate sloped terrain presents an inclination less than 10
deg, while steep sloped terrain had a grade up to 28 degrees. All the available experimental runs are
performed following a straight path. Sensor signals are logged together with a synchronized
timestamp. Four sensor modalities are available on SherpaTT: the four FTSs, the body’s IMU, a
Differential Global Positioning System (DGPS) on the rover body and joint telemetry. The FTSs are
six axial sensors able to measure the three cartesian components of forces and moments acting on
each wheel. The IMU outputs the rover’s attitude ad accelerations, while DGPS provides an absolute
position of the rover and it is used for ground truthing. Joint position and speed, as well as each
joint’s electrical current and PWM duty cycle, are available for this study.
Proprioceptive data streams have been associated with a sequence of terrain patches with the
same length. In this work, a patch length of 0.3 m is considered. In such a way, for each terrain patch,
a set of features has been computed, as extensively explained in the following section.
Table 1. Datasets gathered by SherpaTT during field trials; for each test run, terrain description,
testing time and available logged sensors are indicated.
Run
ID
Test
Site
Terrain
Type Slope Run Time
[s] FTS IMU DGPS Encoders
R01 Morocco Sand Flat/Moderate 381.5 ✓ ✗ ✗ ✓
R02 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R03 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R04 Utah Rock Moderate 152.4 ✓ ✓ ✗ ✓
R05 Utah Rock Steep 453.9 ✓ ✓ ✓ ✓
R06 Utah Rock Steep 457.7 ✓ ✓ ✓ ✓
R07 Utah Rock Steep 481.2 ✓ ✓ ✓ ✓
Appl. Sci. 2020, 10, x FOR PEER REVIEW 4 of 16
Figure 1. SherpaTT in soft sand dunes during Morocco field trials in 2018.
Figure 2. Examples of possible footprint configurations and resulting support polygons.
2.1. Data Sets
Two extensive field trials have been conducted by SherpaTT in the desert of Morocco (2019) and
in the desert of Utah (2016). Both sites have been shown to be representative of Mars analogue terrain
[30]. During these field trials, different test tracks in natural terrain, GAP-modes and footprints have
been tested. Since the focus of those campaigns was different from the aim of this research, only a
small portion of the data logs can be effectively used for terrain estimation purposes. Table 1 sums
up the datasets available for terrain and slippage classification, clarifying specific terrain, total run
time and logged sensors. Specifically, the only available run in the Morocco campaign is performed
on sandy dunes of flat/moderate slopes, while Utah data logs are available on flat, moderate sloped
and steep sloped rocky terrains. Utah moderate sloped terrain presents an inclination less than 10
deg, while steep sloped terrain had a grade up to 28 degrees. All the available experimental runs are
performed following a straight path. Sensor signals are logged together with a synchronized
timestamp. Four sensor modalities are available on SherpaTT: the four FTSs, the body’s IMU, a
Differential Global Positioning System (DGPS) on the rover body and joint telemetry. The FTSs are
six axial sensors able to measure the three cartesian components of forces and moments acting on
each wheel. The IMU outputs the rover’s attitude ad accelerations, while DGPS provides an absolute
position of the rover and it is used for ground truthing. Joint position and speed, as well as each
joint’s electrical current and PWM duty cycle, are available for this study.
Proprioceptive data streams have been associated with a sequence of terrain patches with the
same length. In this work, a patch length of 0.3 m is considered. In such a way, for each terrain patch,
a set of features has been computed, as extensively explained in the following section.
Table 1. Datasets gathered by SherpaTT during field trials; for each test run, terrain description,
testing time and available logged sensors are indicated.
Run
ID
Test
Site
Terrain
Type Slope Run Time
[s] FTS IMU DGPS Encoders
R01 Morocco Sand Flat/Moderate 381.5 ✓ ✗ ✗ ✓
R02 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R03 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R04 Utah Rock Moderate 152.4 ✓ ✓ ✗ ✓
R05 Utah Rock Steep 453.9 ✓ ✓ ✓ ✓
R06 Utah Rock Steep 457.7 ✓ ✓ ✓ ✓
R07 Utah Rock Steep 481.2 ✓ ✓ ✓ ✓
Appl. Sci. 2020, 10, x FOR PEER REVIEW 4 of 16
Figure 1. SherpaTT in soft sand dunes during Morocco field trials in 2018.
Figure 2. Examples of possible footprint configurations and resulting support polygons.
2.1. Data Sets
Two extensive field trials have been conducted by SherpaTT in the desert of Morocco (2019) and
in the desert of Utah (2016). Both sites have been shown to be representative of Mars analogue terrain
[30]. During these field trials, different test tracks in natural terrain, GAP-modes and footprints have
been tested. Since the focus of those campaigns was different from the aim of this research, only a
small portion of the data logs can be effectively used for terrain estimation purposes. Table 1 sums
up the datasets available for terrain and slippage classification, clarifying specific terrain, total run
time and logged sensors. Specifically, the only available run in the Morocco campaign is performed
on sandy dunes of flat/moderate slopes, while Utah data logs are available on flat, moderate sloped
and steep sloped rocky terrains. Utah moderate sloped terrain presents an inclination less than 10
deg, while steep sloped terrain had a grade up to 28 degrees. All the available experimental runs are
performed following a straight path. Sensor signals are logged together with a synchronized
timestamp. Four sensor modalities are available on SherpaTT: the four FTSs, the body’s IMU, a
Differential Global Positioning System (DGPS) on the rover body and joint telemetry. The FTSs are
six axial sensors able to measure the three cartesian components of forces and moments acting on
each wheel. The IMU outputs the rover’s attitude ad accelerations, while DGPS provides an absolute
position of the rover and it is used for ground truthing. Joint position and speed, as well as each
joint’s electrical current and PWM duty cycle, are available for this study.
Proprioceptive data streams have been associated with a sequence of terrain patches with the
same length. In this work, a patch length of 0.3 m is considered. In such a way, for each terrain patch,
a set of features has been computed, as extensively explained in the following section.
Table 1. Datasets gathered by SherpaTT during field trials; for each test run, terrain description,
testing time and available logged sensors are indicated.
Run
ID
Test
Site
Terrain
Type Slope Run Time
[s] FTS IMU DGPS Encoders
R01 Morocco Sand Flat/Moderate 381.5 ✓ ✗ ✗ ✓
R02 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R03 Utah Rock Flat 214.8 ✓ ✓ ✓ ✓
R04 Utah Rock Moderate 152.4 ✓ ✓ ✗ ✓
R05 Utah Rock Steep 453.9 ✓ ✓ ✓ ✓
R06 Utah Rock Steep 457.7 ✓ ✓ ✓ ✓
R07 Utah Rock Steep 481.2 ✓ ✓ ✓ ✓
Proprioceptive data streams have been associated with a sequence of terrain patches with the
same length. In this work, a patch length of 0.3 m is considered. In such a way, for each terrain patch,
a set of features has been computed, as extensively explained in the following section.

Appl. Sci. 2020,10, 6044 5 of 15
2.2. Data Pre Processing
Each sensor modality could have a different sample rate. Table 2specifies sensors logging
frequencies. The highest frequency is adopted for the definition of a common absolute timestamp:
a frequency of 100 Hz corresponding to one observation each of 0.01 s. Signals with lower sample rates
are linearly interpolated to obtain signals at 100 Hz.
Table 2. Sensor sample rates.
Sensor Modality Sample Rate [Hz]
FTS 100
IMU 100
DGPS 10–20
Encoders 100
In order to have the same time–space association logic for all datasets, and since DGPS is not
available on Morocco tests, an odometry-based approach is adopted to relate time-stamp with rover
traversed distance. The distance travelled by one of the four rover wheels, d
V
, between two successive
time-stamps is defined in Equation (1):
dV=ωR∆t(1)
where
∆t
is the sampling interval,
ω
is the wheel angular speed measured by the encoder and
R
is the
wheel undeformed radius. Sensor data have been subdivided into sub-logs that are associated with
each virtual patch. It should be noted that two patches of the same length, in general, may correspond
to different actual travel distances due to the extent of wheel slippage. It is also worth mentioning that
the use of “distance” windows is used under the underlying assumption of continuous motion of the
robot without any stop-and-go manoeuvre.
3. Proprioceptive Sensing
This section presents the set of proprioceptive features used to characterize the properties of a
given terrain patch. For each feature, the four statistical moments (mean, variance, skewness and
kurtosis) are computed. Data have been manually labelled in terms of two terrain types (sand for
Morocco and rocky terrain for Utah) and in terms of three discrete classes of slippage (only for Utah,
where slippage can be directly calculated by comparing DGPS with wheel encoders). Data labelling is
necessary, as explained later, for the successive stages of feature selection using validity indices and for
training the terrain and slippage classifiers.
3.1. Proprioceptive Features
A large amount of sensory data can be gathered from Sherpa and potentially used for classification
purposes. However, only a few signals bring significant information related to terrain type.
Here, only the most relevant features that we found are discussed. From the FTSs, three forces
and three moments are available for each wheel. Among these, we retain the longitudinal force F
X
and the wheel drive torque T
D
. The wheel drive torque can be also estimated indirectly from the
electrical current, C
D
, whereas the wheel angular velocity
ω
can be obtained from wheel encoders.
The three body accelerations a
x
,a
y
and a
z
are estimated from the IMU. The mechanical power P
M
and
the electrical power PEare computed, respectively, in Equations (2) and (3):
PM=TDω, (2)
PE=VIdPWM, (3)
where V,Iand d
PWM
are, respectively, the motor voltage, current and PWM duty cycle of the wheel
drive. Apart from this set of “primary” quantities, a second set of “derivate” features has been found

Appl. Sci. 2020,10, 6044 6 of 15
to be effective for terrain characterization. Derivate features can be obtained by combining primary
features according to well-known physics-based relationships. As an example, the friction coefficients
µcan be estimated using three different sensor data according to Equations (4)–(6):
µ1=FX/FZ, (4)
µ2=TD/RFZ, (5)
µ3=CD/RFZ, (6)
where F
Z
is the wheel vertical force and Ris the wheel unloaded radius. Another key feature is the
so-called wheel speed deviation, SD, that is the absolute value of the difference between the angular
speed of each wheel
ω
and the average angular speed of the four wheels
ω
as defined by Equation (7):
SD =|ω−ω|, (7)
Note that the SD can be extended as well to turning motion, as explained in [
31
]. Wheel
longitudinal stiffness LS is computed as the ratio between the friction coefficient and the wheel slip
s. In the simplified case of a linear relation between friction coefficient and wheel slip, this physical
quantity should represent the slope of friction—slippage plot. Three different LS
i
values are computed
in Equation (8) using the three friction coefficients defined before:
LSi=µi
s,i=1, 2, 3, (8)
The slippage sis univocally estimated for both accelerating and braking and for each wheel based
on Equation (9):
s=d 1−VX
ωRd!,d=(+1ωR−VX≥0
−1ωR−VX<0, (9)
where V
X
is estimated with the DGPS and dis positive for accelerating and negative for braking.
An approximate estimate of wheel sinkage zcan be obtained by Equation (10) [32]:
z=R·






1−cos






2·
TD
R−FX
FZ












, (10)
Table 3sums up the proprioceptive feature space spanned by the above considerations.
Table 3. Proprioceptive features with relative feature ID number and symbol.
FID Feature Symbol
F1 Longitudinal Force FX
F2 Drive Torque TD
F3 Drive Current CD
F4 Mechanical Power PM
F5 Electrical Power PE
F6 Friction Coefficient 1 µ1
F7 Friction Coefficient 2 µ2
F8 Friction Coefficient 3 µ3
F9 Acceleration X aX
F10 Acceleration Z aZ
F11 Speed Deviation SD
F12 Longitudinal Stiffness 1 LS1
F13 Longitudinal Stiffness 2 LS2
F14 Longitudinal Stiffness 3 LS3
F15 Sinkage z

Appl. Sci. 2020,10, 6044 7 of 15
3.2. Statistical Feature and Validity Indices
For the i-th feature, the main statistical moments are estimated: mean
Ei
, variance
σi2
, skewness
Ski
and kurtosis
Kui
of the feature signal for a single terrain patch. These statistics are defined according
to Equations (11)–(14):
Ei=1
N
N
X
n=1
xn(11)
σi2=1
N
N
X
n=1
(xn−Ei)2(12)
Ski=1
NPN
n=1(xn−Ei)3
pσi23(13)
Kui=1
NPN
n=1(xn−Ei)4
pσi24(14)
where
xn
is the value assumed by the feature at the time-step
n
and
N
is the total number of time-steps
for the considered terrain patch.
In addition, each terrain patch is labelled for terrain type, sand for Morocco data or rock for Utah
data, and slippage level; high slip is for absolute value of slip greater than 0.5 and all other conditions
are low slip.
The statistical features are divided into clusters according to patch labels and a validity index value
is associated with each statistical feature. Two validity indices are proposed to obtain a quantitative
measure of “feature goodness” for terrain patch classification: the WB index [
33
] and a Pearson
Coefficient based index (PC) [
34
]. These indices are employed in the feature selection method described
in the following section. The WB index is computed as:
WB =m·SSW
SSB , (15)
The sum of square within cluster SSW and between clusters SSB can be computed as follows:
SSW =Xm
k=1Xnk
i=1(xi−µk)2, (16)
SSB =Xm
k=1nk(µk−µ)2, (17)
where x
i
is the generic statistical feature value for the patch i,
µk
is the cluster kcentroid value,
µ
is the
overall dataset centroid value, n
k
is the number of patches in the cluster kand mis the number of clusters.
In this study mis 2 since we have two classes for the terrain classifier. WB index assumes lower values
for higher distance between different cluster centroids and for lower variance within clusters. A good
classifier feature allows us to obtain distant and compact clusters, and thus generally corresponds
to a low value of the WB index. A PC index could be computed through the linear regression of a
feature against the m classes, giving a progressive numerical value to each class. A higher value of PC
potentially corresponds to a better classifier feature.
Figures 3and 4show, respectively, the WB−1and PC indices values for all the statistical features
computed both on terrain and slippage labelled datasets. Some features are missing because the
correspondent sensor suite is not available in the classification dataset (please refer to Table 1).

Appl. Sci. 2020,10, 6044 8 of 15
Appl. Sci. 2020, 10, x FOR PEER REVIEW 8 of 16
(a)
(b)
Figure 3. 𝑊𝐵 index values for each feature (F1 to F15), for each statistic (S1 to S4,
respectively, mean, variance, skewness and kurtosis) and for terrain (a) and slippage (b)
classifier.
(a)
Figure 3. WB−1
index values for each feature (F1 to F15), for each statistic (S1 to S4, respectively, mean,
variance, skewness and kurtosis) and for terrain (a) and slippage (b) classifier.
Appl. Sci. 2020, 10, x FOR PEER REVIEW 8 of 16
(a)
(b)
Figure 3. 𝑊𝐵 index values for each feature (F1 to F15), for each statistic (S1 to S4,
respectively, mean, variance, skewness and kurtosis) and for terrain (a) and slippage (b)
classifier.
(a)
Figure 4. Cont.

Appl. Sci. 2020,10, 6044 9 of 15
Appl. Sci. 2020, 10, x FOR PEER REVIEW 9 of 16
(b)
Figure 4. 𝑃𝐶 index values for each feature (F1 to F15), for each statistic (S1 to S4,
respectively, mean, variance, skewness and kurtosis) and for terrain (a) and slippage (b)
classifier.
3.3. Feature Selection
In a classification problem, plenty of features can be thought of and used for training. Features
can be raw data signals, or a combination of raw signals, signal statistics and so on. However, only a
small amount of the available feature set may be actually relevant to address the classification
problem.
The selection of the “most significant features” can be tackled in different ways, i.e., as an
optimization or a search problem [34]. Those techniques can find a local or global optimum feature
set but could be also computationally expensive. The method proposed in this work has a low
computational cost, since the number of its iterations equals the total number of features in the initial
feature space. For the purpose of this work the initial feature space is made up of 15 features and 4
statistics per feature, for a total number of 60 statistical features.
The feature selection method needs as input the labelled initial feature space, the value of a
validity index (VI) associated with each statistical feature and a classifier to be iteratively trained. The
VIs employed in this research were the WB index and the PC index. The classification algorithm is a
linear Support Vector Machine (SVM), one of the most adopted techniques for terrain classification
problem [18], which guarantees good results with a lower computational effort compared with other
techniques such as Convolutional Neural Networks [35]. The feature selection algorithm is described
by the following pseudo-code:
01. INPUT: initial feature set (Ifs), VI vector associated with features VIv
02. arrange IFs features in decreasing order of VIv
03. initialize (F1 score)i−1 = 60%, initialize reduced feature set (RFs) as an empty set
04. for i from 1 to (number of features)
05. add the i feature from IFs to the RFs
06. train n times the classifier, compute average (F1 score)i
07. if (F1 score)i − (F1 score)i−1 ≤ (F1 threshold)
08. remove i feature from RFs
09. end if
10. update (F1 score)i = (F1 score)i−1
11. end for
12. OUTPUT: RFs
At each iteration step, a feature is added to the training set and the algorithm verifies if this new
feature leads to a significant increase in the classifier performance. The metric used to quantify the
Figure 4. PC
index values for each feature (F1 to F15), for each statistic (S1 to S4, respectively, mean,
variance, skewness and kurtosis) and for terrain (a) and slippage (b) classifier.
3.3. Feature Selection
In a classification problem, plenty of features can be thought of and used for training. Features
can be raw data signals, or a combination of raw signals, signal statistics and so on. However, only a
small amount of the available feature set may be actually relevant to address the classification problem.
The selection of the “most significant features” can be tackled in different ways, i.e., as an
optimization or a search problem [
34
]. Those techniques can find a local or global optimum feature
set but could be also computationally expensive. The method proposed in this work has a low
computational cost, since the number of its iterations equals the total number of features in the initial
feature space. For the purpose of this work the initial feature space is made up of 15 features and 4
statistics per feature, for a total number of 60 statistical features.
The feature selection method needs as input the labelled initial feature space, the value of a
validity index (VI) associated with each statistical feature and a classifier to be iteratively trained.
The VIs employed in this research were the WB index and the PC index. The classification algorithm is
a linear Support Vector Machine (SVM), one of the most adopted techniques for terrain classification
problem [
18
], which guarantees good results with a lower computational effort compared with other
techniques such as Convolutional Neural Networks [
35
]. The feature selection algorithm is described
by the following pseudo-code:
01.
INPUT: initial feature set (Ifs), VI vector associated with features VIv
02.
arrange IFs features in decreasing order of VIv
03.
initialize (F1 score)i−1=60%, initialize reduced feature set (RFs) as an empty set
04.
for ifrom 1to (number of features)
05.
add the ifeature from IFs to the RFs
06.
train ntimes the classifier, compute average (F1 score)i
07.
if (F1 score)i−(F1 score)i−1≤(F1 threshold)
08.
remove ifeature from RFs
09.
end if
10.
update (F1 score)i=(F1 score)i−1
11.
end for
12.
OUTPUT:RFs
At each iteration step, a feature is added to the training set and the algorithm verifies if this new
feature leads to a significant increase in the classifier performance. The metric used to quantify the
classifier performance is the F1 score. In this work the F1 score percentage improvement threshold

Appl. Sci. 2020,10, 6044 10 of 15
for a feature to be accepted has been set to 0.5%. The training phase is repeated three times for each
feature (n=3) and an average F1 score of the three trained classifiers is computed. The output of the
algorithm is a reduced feature set, including the only features that bring a significant improvement in
the classifier performance. The algorithm has been tested both with the PC index and the reciprocal of
WB index (
WB−1
), which allows the first selected features to be potentially the most suitable for the
classifier. Figure 5shows the algorithm results in terms of F1 score for each iteration and for the terrain
(above) and slippage (below) classifier. If the performance increase, the new feature is added to the
“optimal” or reduced feature set (RFs). It is apparent how the most relevant features are found in the
first half of the iterations, where both PC and WB
−1
have higher values. This figure shows that the
chosen validity indices are effective for the selection of relevant features.
Tables 4and 5show the F1 score and the number of selected features for the terrain classifier and
for different feature selection methods. PC and WB indicate the feature selection method that uses
the singular VI, as described before. In addition, two combined selections have been also tested that
use the intersection
Int(PC,WB)
and the union
Un(PC,WB)
of the selected feature set obtained from
the
PC
and
WB
selection method. Finally, the training method “All” involves the use of the entire
feature set.
All the proposed selection methods for the terrain classifier achieve similar F1 score of about 93%.
However, the intersection method Int(PC,WB) is the most suitable both for the F1 score and the size of
the reduced feature set. Both single VI methods lead also to similar reduced feature sets. In fact, nine
of the features selected by both WB and PC methods fall into the intersection Int(PC,WB). Taking all
initial features (see “All” method), without any selection phase allows us to reach a good F1 score of
90.4%, but with a higher training set dimensionality and so a higher computational effort.
Appl. Sci. 2020, 10, x FOR PEER REVIEW 10 of 16
classifier performance is the F1 score. In this work the F1 score percentage improvement threshold
for a feature to be accepted has been set to 0.5%. The training phase is repeated three times for each
feature (n = 3) and an average F1 score of the three trained classifiers is computed. The output of the
algorithm is a reduced feature set, including the only features that bring a significant improvement
in the classifier performance. The algorithm has been tested both with the PC index and the reciprocal
of WB index (𝑊𝐵), which allows the first selected features to be potentially the most suitable for
the classifier. Figure 5 shows the algorithm results in terms of F1 score for each iteration and for the
terrain (above) and slippage (below) classifier. If the performance increase, the new feature is added
to the “optimal” or reduced feature set (RFs). It is apparent how the most relevant features are found
in the first half of the iterations, where both PC and WB−1 have higher values. This figure shows that
the chosen validity indices are effective for the selection of relevant features.
(a)
(b)
Figure 5. Feature selection performance results for terrain (a) and slippage (b) classifier.
Tables 4 and 5 show the F1 score and the number of selected features for the terrain classifier
and for different feature selection methods. PC and WB indicate the feature selection method that
uses the singular VI, as described before. In addition, two combined selections have been also tested
that use the intersection 𝐼𝑛𝑡𝑃𝐶,𝑊𝐵 and the union 𝑈𝑛𝑃𝐶,𝑊𝐵 of the selected feature set obtained
from the 𝑃𝐶 and 𝑊𝐵 selection method. Finally, the training method “All” involves the use of the
entire feature set.
Table 4. Comparison of different feature selection methods for terrain classification.
𝐏𝐂 𝐖𝐁 𝐈𝐧
𝐭
𝐏𝐂,𝐖𝐁 𝐔𝐧𝐏𝐂,𝐖𝐁 𝐀𝐥𝐥
N° features 11 10 9 12 40
F1 score 0.924 0.929 0.931 0.928 0.904
Table 5. Comparison of different feature selection methods for slippage classification.
Figure 5. Feature selection performance results for terrain (a) and slippage (b) classifier.

Appl. Sci. 2020,10, 6044 11 of 15
Table 4. Comparison of different feature selection methods for terrain classification.
PC WB Int(PC,WB) Un(PC,WB) All
N◦features 11 10 9 12 40
F1 score 0.924 0.929 0.931 0.928 0.904
Table 5. Comparison of different feature selection methods for slippage classification.
PC WB Int(PC,WB) Un(PC,WB) All
N◦features 6 10 2 14 60
F1 score 0.939 0.940 0.914 0.936 0.765
The same selection procedure has been performed with the slippage classifier. PC and WB methods
select different features. The most relevant features fall into the intersection, which has a slightly lower
F1 but a minimal feature set, hence it can be preferred as the selection method. Table 6collects the
reduced feature space for both algorithms.
Table 6. Reduced feature sets for terrain (a) and slippage (b) classification.
PC WB Int(PC,WB) Un(PC,WB)
F5S1 F5S1 F2S1 F1S1
F4S1 F4S1 F3S1 F2S1
F4S2 F4S2 F4S1 F3S1
F3S2 F3S1 F5S1 F4S1
F3S1 F4S4 F8S1 F5S1
F2S1 F2S1 F11S1 F8S1
F4S4 F8S1 F4S2 F11S1
F8S1 F11S2 F7S2 F3S2
F1S1 F11S1 F4S4 F4S2
F11S1 F7S2 F7S2
F7S2 F11S2
F4S4
F3S2 F8S2 F1S2 F1S1
F2S2 F3S1 F3S2 F3S1
F4S2 F8S1 F5S1
F1S2 F3S2 F8S1
F11S1 F15S2 F11S1
F1S3 F5S1 F1S2
F1S2 F2S2
F1S1 F3S2
F11S3 F4S2
F11S2 F8S2
F11S2
F15S2
F1S3
F11S3
Figure 6shows the 3D scatter plot of the three statistical features that present the highest value of
WB and PC index, respectively, for the terrain and high-slippage classifier. For visualization purposes
and for the terrain classifier only, the corresponding 2D feature distribution is also shown in Figure 7.
As seen from these figures, the feature distribution indicates a good separation level between sand and
rock and it suggests the implementation of a classification algorithm.

Appl. Sci. 2020,10, 6044 12 of 15
Appl. Sci. 2020, 10, x FOR PEER REVIEW 12 of 16
(a) (b)
Figure 6. 3D plot of the first three most relevant features selected for terrain (a) and slippage (b)
classification.
(a) (b)
Figure 7. 2D distribution of the most relevant features selected for the terrain classifier: F4S2-F5S1
plane (a), F4S2-F4S1 plane (b).
4. Classification Task
In this section, the results obtained from the two classifiers for terrain and slippage detection are
presented. The classifiers were trained and tested on real data gathered by SherpaTT in the field. The
reduced feature sets to be used for training and testing have been obtained with the intersection
method described in the previous section (refer to Table 6). For both classifiers, the observations
(terrain patches) of the reduced feature dataset have been subdivided into two datasets, according to
the patch class. In addition, 75% of the observations of each class dataset were randomly extracted to
build the training datasets, while the remaining 25% were then used for testing the trained classifiers
[36]. Tables 7 and 8 show the performance metrics of the trained classifiers. The terrain classifier
reaches a global accuracy of 96.3% and a global F1 score of 92.2%, while the slippage classifier has an
accuracy of 99.0% and an F1 score of 92.7%.
Table 7. Performance metrics of the terrain classifier.
Precision Recall Specificity F1 Score
Sand 77.6% 97.7% 96.1% 86.5%
Rock 99.7% 96.1% 97.7% 97.9%
Table 8. Performance metrics of the slippage classifier.
Figure 6.
3D plot of the first three most relevant features selected for terrain (
a
) and slippage
(b) classification.
Appl. Sci. 2020, 10, x FOR PEER REVIEW 12 of 16
(a) (b)
Figure 6. 3D plot of the first three most relevant features selected for terrain (a) and slippage (b)
classification.
(a) (b)
Figure 7. 2D distribution of the most relevant features selected for the terrain classifier: F4S2-F5S1
plane (a), F4S2-F4S1 plane (b).
4. Classification Task
In this section, the results obtained from the two classifiers for terrain and slippage detection are
presented. The classifiers were trained and tested on real data gathered by SherpaTT in the field. The
reduced feature sets to be used for training and testing have been obtained with the intersection
method described in the previous section (refer to Table 6). For both classifiers, the observations
(terrain patches) of the reduced feature dataset have been subdivided into two datasets, according to
the patch class. In addition, 75% of the observations of each class dataset were randomly extracted to
build the training datasets, while the remaining 25% were then used for testing the trained classifiers
[36]. Tables 7 and 8 show the performance metrics of the trained classifiers. The terrain classifier
reaches a global accuracy of 96.3% and a global F1 score of 92.2%, while the slippage classifier has an
accuracy of 99.0% and an F1 score of 92.7%.
Table 7. Performance metrics of the terrain classifier.
Precision Recall Specificity F1 Score
Sand 77.6% 97.7% 96.1% 86.5%
Rock 99.7% 96.1% 97.7% 97.9%
Table 8. Performance metrics of the slippage classifier.
Figure 7.
2D distribution of the most relevant features selected for the terrain classifier: F4S2-F5S1
plane (a), F4S2-F4S1 plane (b).
4. Classification Task
In this section, the results obtained from the two classifiers for terrain and slippage detection
are presented. The classifiers were trained and tested on real data gathered by SherpaTT in the field.
The reduced feature sets to be used for training and testing have been obtained with the intersection
method described in the previous section (refer to Table 6). For both classifiers, the observations (terrain
patches) of the reduced feature dataset have been subdivided into two datasets, according to the patch
class. In addition, 75% of the observations of each class dataset were randomly extracted to build
the training datasets, while the remaining 25% were then used for testing the trained classifiers [
36
].
Tables 7and 8show the performance metrics of the trained classifiers. The terrain classifier reaches a
global accuracy of 96.3% and a global F1 score of 92.2%, while the slippage classifier has an accuracy of
99.0% and an F1 score of 92.7%.
Table 7. Performance metrics of the terrain classifier.
Precision Recall Specificity F1 Score
Sand 77.6% 97.7% 96.1% 86.5%
Rock 99.7% 96.1% 97.7% 97.9%
Table 8. Performance metrics of the slippage classifier.
Precision Recall Specificity F1 Score
Low slip 99.7% 99.2% 92.0% 99.5%
High slip 80.8% 92.0% 99.2% 86.0%

Appl. Sci. 2020,10, 6044 13 of 15
The confusion matrix of the training and testing phases are reported in Figures 8and 9. The training
and testing classifier performance are very similar, demonstrating the prediction capability of the two
classifiers on new data.
Appl. Sci. 2020, 10, x FOR PEER REVIEW 13 of 16
Precision Recall Specificity F1 Score
Low slip 99.7% 99.2% 92.0% 99.5%
High slip 80.8% 92.0% 99.2% 86.0%
The confusion matrix of the training and testing phases are reported in Figures 8 and 9. The
training and testing classifier performance are very similar, demonstrating the prediction capability
of the two classifiers on new data.
(a) (b)
Figure 8. Confusion matrix for training (a) and testing (b) of the terrain classifier.
(a) (b)
Figure 9. Confusion matrix for training (a) and testing (b) of the slippage classifier.
5. Discussion and Conclusions
A general approach for terrain and slippage classification has been proposed and validated
through field experimental data. A SherpaTT rover testing campaign performed in Morocco and Utah
Figure 8. Confusion matrix for training (a) and testing (b) of the terrain classifier.
Appl. Sci. 2020, 10, x FOR PEER REVIEW 13 of 16
Precision Recall Specificity F1 Score
Low slip 99.7% 99.2% 92.0% 99.5%
High slip 80.8% 92.0% 99.2% 86.0%
The confusion matrix of the training and testing phases are reported in Figures 8 and 9. The
training and testing classifier performance are very similar, demonstrating the prediction capability
of the two classifiers on new data.
(a) (b)
Figure 8. Confusion matrix for training (a) and testing (b) of the terrain classifier.
(a) (b)
Figure 9. Confusion matrix for training (a) and testing (b) of the slippage classifier.
5. Discussion and Conclusions
A general approach for terrain and slippage classification has been proposed and validated
through field experimental data. A SherpaTT rover testing campaign performed in Morocco and Utah
Figure 9. Confusion matrix for training (a) and testing (b) of the slippage classifier.
5. Discussion and Conclusions
A general approach for terrain and slippage classification has been proposed and validated
through field experimental data. A SherpaTT rover testing campaign performed in Morocco and Utah
deserts provided proprioceptive datasets on different soil types. A set of features have been defined
and extracted from raw experimental data. Two labels for terrain type (Sand–Rock) and slippage level
(High Slip–Low Slip) have been associated with each terrain patch, together with a set of statistical
features (predictors), obtained from the computation of feature statistical moments on the terrain patch.
Different selection methods based on validity index have been tested and proved to be effective for the
extraction of relevant features. Different selection methods based on validity index have been tested.
The tested validity indices are the WB index and a Pearson Coefficient (PC)-based index. Both indices
are demonstrated to be effective for the extraction of relevant features. Only the features selected by
both WB and PC methods have been kept in the reduced feature set used for classifiers training and
testing. Thanks to the selection, the initial statistical feature set of 60 features was reduced to 9 features

Appl. Sci. 2020,10, 6044 14 of 15
and to 2 features for slippage classification. The reduced feature set observations, one per terrain patch,
were randomly subdivided into a training set and a testing set, including, respectively, 75% and 25%
of the observations. The two classifiers were trained on the training set and then tested on the new
samples of the testing set, giving as result a global classifier accuracy of 96.7% for terrain classification
and 98.8% for slippage classification.
New experimental tests will be performed in the near future on different terrain types and during
various rover maneuvers. Those new data will be used to further validate the proposed approach and
to improve the classifier generalization. The combination of proprioceptive sensing with exteroceptive
perception, as suggested in [18], will be also investigated.
Author Contributions:
Conceptualization, M.D., G.R.; Methodology, M.D., G.R.; Data curation and experiments
and validation, F.C.; writing—original draft preparation, M.D, G.R.; writing—review and editing, F.C. All authors
have read and agreed to the published version of the manuscript.
Funding:
This research was funded by the Horizon 2020 European Commission under grant agreement n.
821988 ADE.
Conflicts of Interest: The authors declare no conflict of interest.
References
1.
Gonzalez, R.; Iagnemma, K. Slippage estimation and compensation for planetary exploration rovers. State of
the art and future challenges. J. Field Robot. 2017,35, 564–577. [CrossRef]
2.
Filip, J.; Azkarate, M.; Visentin, G. Trajectory Control for Autonomous Planetary Rovers. In Proceedings of
the Symposium on Advanced Space Technologies in Automation and Robotics, Leiden, The Netherlands,
20–22 June 2017; pp. 1–6.
3.
Reina, G.; Ishigami, G.; Nagatani, K.; Yoshida, K. Odometry Correction Using Visual Slip Angle Estimation
for Planetary Exploration Rovers. Adv. Robot. 2010,24, 359–385. [CrossRef]
4.
Ojeda, L.; Reina, G.; Cruz, D.; Borenstein, J. The FLEXnav precision dead-reckoning system.
Int. J. Veh. Auton. Syst. 2006,4, 173. [CrossRef]
5.
Bussmann, K.; Meyer, L.; Steidle, F.; Wedler, A. Slip Modeling and Estimation for a Planetary Exploration
Rover: Experimental Results from Mt. Etna. In Proceedings of the 2018 IEEE/RSJ International Conference
on Intelligent Robots and Systems (IROS), Madrid, Spain, 1–5 October 2018; pp. 2449–2456.
6.
Sanguino, T.D.J.M. 50 years of rovers for planetary exploration: A retrospective review for future directions.
Robot. Auton. Syst. 2017,94, 172–185.
7.
Goldberg, S.B.; Maimone, M.; Matthies, L. Stereo vision and rover navigation software for planetary
exploration. In Proceedings of the IEEE Aerospace Conference; Institute of Electrical and Electronics
Engineers (IEEE), Big Sky, MT, USA, 8–15 March 2003.
8.
Helmick, D.; Angelova, A.; Matthies, L. Terrain Adaptive Navigation for planetary rovers. J. Field Robot.
2009,26, 391–410. [CrossRef]
9.
Gingras, D.; Lamarche, T.; Bedwani, J.-L.; Dupuis,
É
. Rough Terrain Reconstruction for Rover
Motion Planning. In Proceedings of the 2010 Canadian Conference on Computer and Robot Vision,
Ottawa, ON, Canada, 31 May–2 June 2010; pp. 191–198.
10.
Thrun, S.; Montemerlo, M.; Dahlkamp, H.; Stavens, D.; Aron, A.; Diebel, J.; Fong, P.; Gale, J.; Halpenny, M.;
Hoffmann, G.; et al. Stanley: The Robot that Won the DARPA Grand Challenge. J. Field Robot.
2006
,
23, 661–692. [CrossRef]
11.
Milella, A.; Reina, G.; Underwood, J.; Douillard, B. Combining radar and vision for self-supervised ground
segmentation in outdoor environments. In Proceedings of the IEEE International Conference on Intelligent
Robots and Systems, San Francisco, CA, USA, 25–30 September 2011; pp. 255–260.
12.
Milella, A.; Reina, G.; Underwood, J.; Douillard, B. Visual ground segmentation by radar supervision.
Robot. Auton. Syst. 2014,62, 696–706. [CrossRef]
13. Bekker, M. The development of a moon rover. J. Br. Interpl. Soc. 1985,38, 537.
14.
Angelova, A.; Matthies, L.; Helmick, D.; Perona, P. Learning and prediction of slip from visual information.
J. Field Robot. 2007,24, 205–231. [CrossRef]

Appl. Sci. 2020,10, 6044 15 of 15
15.
Gonzalez, R.; Chandler, S.; Apostolopoulos, D. Characterization of machine learning algorithms for slippage
estimation in planetary exploration rovers. J. Terramech. 2019,82, 23–34. [CrossRef]
16.
Reina, G.; Leanza, A.; Messina, A. On the vibration analysis of off-road vehicles: Influence of terrain
deformation and irregularity. J. Vib. Control. 2018,24, 5418–5436. [CrossRef]
17.
Valada, A.; Burgard, W. Deep spatiotemporal models for robust proprioceptive terrain classification.
Int. J. Robot. Res. 2017,36, 1521–1539. [CrossRef]
18.
Reina, G.; Milella, A.; Galati, R. Terrain assessment for precision agriculture using vehicle dynamic modelling.
Biosyst. Eng. 2017,162, 124–139. [CrossRef]
19.
Brooks, C.A.; Iagnemma, K. Self-supervised terrain classification for planetary surface exploration rovers.
J. Field Robot. 2012,29, 445–468. [CrossRef]
20.
Krebs, A.; Pradalier, C.; Siegwart, R. Adaptive rover behavior based on online empirical evaluation:
Rover–terrain interaction and near-to-far learning. J. Field Robot. 2010,27, 158–180. [CrossRef]
21.
Dupont, E.M.; Moore, C.A.; Collins, E.G.; Coyle, E.; Collins, E.G. Frequency response method for terrain
classification in autonomous ground vehicles. Auton. Robot. 2008,24, 337–347. [CrossRef]
22.
Reina, G.; Leanza, A.; Messina, A. Terrain estimation via vehicle vibration measurement and cubature
Kalman filtering. J. Vib. Control. 2019,26, 885–898. [CrossRef]
23.
Iagnemma, K.; Kang, S.; Shibly, H.; Dubowsky, S. Online Terrain Parameter Estimation for Wheeled Mobile
Robots with Application to Planetary Rovers. IEEE Trans. Robot. 2004,20, 921–927. [CrossRef]
24.
Gallina, A.; Krenn, R.; Scharringhausen, M.; Uhl, T.; Schafer, B. Parameter Identification of a Planetary Rover
Wheel-Soil Contact Model via a Bayesian Approach. J. Field Robot. 2013,31, 161–175. [CrossRef]
25.
Dimastrogiovanni, M.; Cordes, F.; Reina, G. Terrain Sensing for Planetary Rovers. In Proceedings of the
International Conference of IFToMM ITALY, Naples, Italy, 9–11 September 2020; pp. 269–277.
26.
Cordes, F.; Dettmann, A.; Kirchner, F. Locomotion modes for a hybrid wheeled-leg planetary rover.
In Proceedings of the 2011 IEEE International Conference on Robotics and Biomimetics, Phuket, Thailand,
7–11 December 2011; pp. 2586–2592.
27.
Sonsalla, R.U.; Cordes, F.; Christensen, L.; Roehr, T.M.; Stark, T.; Planthaber, S.; Maurus, M.; Mallwitz, M.;
Kirchner, E.A. Field Testing of a Cooperative Multi-Robot Sample Return Mission in Mars Analogue
Environment. In Proceedings of the 14th Symposium on Advanced Space Technologies in Robotics and
Automation (ASTRA’17), Noordwijk, The Netherlands, 27–28 May 2017.
28.
Cordes, F.; Kirchner, F.; Babu, A. Design and field testing of a rover with an actively articulated suspension
system in a Mars analog terrain. J. Field Robot. 2018,35, 1149–1181. [CrossRef]
29.
Cordes, F.; Babu, A.; Kirchner, F. Static force distribution and orientation control for a rover with an actively
articulated suspension system. In Proceedings of the 2017 IEEE/RSJ International Conference on Intelligent
Robots and Systems (IROS), Vancouver, BC, Canada, 24–28 September 2017; pp. 5219–5224.
30.
Clarke, J.; Stoker, C.R. Concretions in exhumed and inverted channels near Hanksville Utah: Implications
for Mars. Int. J. Astrobiol. 2011,10, 161–175. [CrossRef]
31. Reina, G. Cross-Coupled Control for All-Terrain Rovers. Sensors 2013,13, 785–800. [CrossRef] [PubMed]
32.
Guo, J.; Guo, T.; Zhong, M.; Gao, H.; Huang, B.; Ding, L.; Li, W.; Deng, Z. In-situ evaluation of terrain
mechanical parameters and wheel-terrain interactions using wheel-terrain contact mechanics for wheeled
planetary rovers. Mech. Mach. Ther. 2020,145, 103696. [CrossRef]
33.
Zhao, Q.; Fränti, P. WB-index: A sum-of-squares based index for cluster validity. Data Knowl. Eng.
2014
,92,
77–89. [CrossRef]
34.
Hastie, T.; Tibshirani, R.; Friedman, J. The Elements of Statistical Learning; Springer: New York, NY, USA, 2009.
35.
Rothrock, B.; Kennedy, R.; Cunningham, C.; Papon, J.; Heverly, M.; Ono, M. SPOC: Deep
Learning-based Terrain Classification for Mars Rover Missions. In Proceedings of the AIAA SPACE 2016,
Long Beach, CA, USA, 13–16 September 2016.
36.
Milella, A.; Marani, R.; Petitti, A.; Reina, G. In-field high throughput grapevine phenotyping with a
consumer-grade depth camera. Comput. Electron. Agric. 2019,156, 293–306. [CrossRef]
©
2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access
article distributed under the terms and conditions of the Creative Commons Attribution
(CC BY) license (http://creativecommons.org/licenses/by/4.0/).