Conference PaperPDF Available

Fostering the NAO Platform as an Elderly care Robot - First Steps Toward a Low-Cost Off-the-Shelf Solution

Authors:

Abstract and Figures

Depression and loneliness among the elderly are one of the biggest problems affecting the world population. This leads to elderly isolation which is a major risk factor for sui-cide. Moreover, if isolation is coupled with physical illness and incapacitation, such a risk increases exponentially. To fight back this problem, roboticists have been proposing solutions to autonomously monitor, support and even promote physical activities among the elderly. Nevertheless, those appear as very high-cost and complex solutions that require an advanced technical expertise. Recent off-the-shelf solutions, such as the well-known NAO robot, emerged as possible alternatives. An extension to the NAO robot, denoted as RIA, is being devel-oped at the Engineering Institute of Coimbra (ISEC). The RIA is not only built for a social interaction with the elderly but also as an autonomous tool to promote professional care through the analysis of health and environmental parameters. There-fore, the RIA robot is an adapted NAO low-cost platform equipped with several sensors that can measure different pa-rameters like body temperature, blood pressure and heart rate. By validating this valuable platform, the foundations were laid for a whole new paradigm in elderly care.
Content may be subject to copyright.
Fostering the NAO Platform as an Elderly care Robot
First Steps Toward a Low-Cost Off-the-Shelf Solution
Jessica P.M. Vital
Engineering Institute of Coimbra
RoboCorp,
Coimbra, Portugal
A21200422@isec.pt
Micael S. Couceiro
Engineering Institute of Coimbra
RoboCorp, Department of Electrical Engineering
Coimbra, Portugal
micael@isec.pt
Nuno M. M. Rodrigues
Engineering Institute of Coimbra
RoboCorp,
Coimbra, Portugal
A21200432@isec.pt
Carlos M. Figueiredo
Engineering Institute of Coimbra
RoboCorp, Department of Electrical Engineering
Coimbra, Portugal
cfigueiredo@isec.pt
Nuno M. F. Ferreira
Engineering Institute of Coimbra
RoboCorp, Department of Electrical Engineering
Coimbra, Portugal
nunomig@isec.pt
Abstract Depression and loneliness among the elderly are one
of the biggest problems affecting the world population. This
leads to elderly isolation which is a major risk factor for sui-
cide. Moreover, if isolation is coupled with physical illness and
incapacitation, such a risk increases exponentially. To fight
back this problem, roboticists have been proposing solutions to
autonomously monitor, support and even promote physical
activities among the elderly. Nevertheless, those appear as very
high-cost and complex solutions that require an advanced
technical expertise. Recent off-the-shelf solutions, such as the
well-known NAO robot, emerged as possible alternatives. An
extension to the NAO robot, denoted as RIA, is being devel-
oped at the Engineering Institute of Coimbra (ISEC). The RIA
is not only built for a social interaction with the elderly but also
as an autonomous tool to promote professional care through
the analysis of health and environmental parameters. There-
fore, the RIA robot is an adapted NAO low-cost platform
equipped with several sensors that can measure different pa-
rameters like body temperature, blood pressure and heart rate.
By validating this valuable platform, the foundations were laid
for a whole new paradigm in elderly care.
I. INTRODUCTION
Depression and loneliness among the elderly are now one of
the biggest problems affecting the world population [1].
Moreover, the increasing isolation of the elderly, whether in
rural or urban society requires extra care and monitoring of
qualified professionals to ensure the welfare and health of
this population. However, it is difficult to ensure the con-
stant presence of professionals. Also, that care may not
reach every user, especially those living in poor and disad-
vantaged means. To combat this difficulty, many research-
ers have been addressing social robotics as a possible solu-
tion.
Figure 1. Robot NAO.
This paper will present the NAO robot (Fig. 1) as a social
platform ideally fitted to monitor and promote the physical
activity within the elderly population. To this end, the plat-
form must be able to able to replicate human motion with
twenty five degrees-of-freedom (DOF) so as to promote
physical activity among the elderly. The platform should
also be able to prevent osteoarticular diseases, i.e., arthrosis
and osteoporosis, as well as cardiovascular diseases, e.g.,
acute myocardial infarction. Moreover, and to protect the
elderly from possible treats, the platform should also be able
assess the environmental-contextual information.
Bearing these ideas in mind, this paper paves the way to-
ward the direction of a novel robotic platform denoted as
RIA, from the Portuguese Robô Idoso Activo (Elderly Active
Robot). The idea behind RIA is to equip the NAO robot
with several sensors in order to passively monitor multiple
parameters such as glucose levels, blood pressure, heart rate,
body temperature and, at the environmental level, monitor
the temperature, humidity, gas measurement and fire detec-
tion.
Yet, as a first step, this paper revolves around the choice
behind the NAO solution. In a broad sense, this robot can
accomplish several basic actions like sitting down, walking,
pick up things with hands, among others. Those are the
minimum necessary requirements for such a task of taking
care of someone. Nevertheless, those are not the only main
features from the NAO platform. Next section describes
some of its main applications around social robotics.
II. APPLICATIONS
The NAO robot has been used in many applications but this
paper focus on the ones regarding the interaction with hu-
mans an area usually known as social robotics. However,
it should be noteworthy that the NAO platform has been
used in many other applications, such as the traditional
robotic soccer (e.g., [2]).
a) Austism children
The NAO platform has been used to help autistic children in
improving their behaviour [3] [4]. These two articles pre-
sented a detailed information about the capabilities of NAO
under such applications. The authors in [3] presented some
interesting results about the use of analyzing the influence
of NAO robot in children with autism. The authors stated
how a basic human interactive robot is able to suppress the
autistic behavior during human-robot interactions and that
the child is able to maintain visual contact with the robot.
Similarly, the authors in [4] presented some identical results
concluding that children did not exhibit autistic behaviors
while interacting with the NAO platform (Fig. 2). Although
the number of studied cases is fairly small and cannot return
conclusive results, one may conclude that the use of the
NAO robot within such applications is still an alternative.
Figure 2. Interaction with children.
b) Visual Interaction
An interesting feature inherent to the NAO robot it is the
visual capability, being one of the fundamental requirements
for social robotics. The authors in [5] presented a real-time
visual system to interact with humans. The system was
based upon probability models that use color and the shape
of the object to be recognized. This algorithm is quite com-
putationally simple which means that it can be processed in
real time. Also, their object recognition was not only guided
by the distribution of color but also by the spatial distribu-
tion of pixels, thus meaning that there was an improved
control of various objects and reasoning about occlusions.
c) Interaction with humans
The interaction with humans (Fig. 3) is one of the main
attributes of NAO platform [6] [7] [8] [9] [10]. The authors
in [6] proposed a technique for programming the move-
ments of NAO’s entire body through observation. This was
accomplished using Jacobian matrices and a new form of
optimization of joint trajectories with B-Spline, thus gener-
ating optimal whole body movements. The authors in [7]
showed how the NAO’s vision and hearing features are
important for teaching tasks in a social environment.
Through this study one were able to withdraw some interest-
ing conclusions such as that the direct visual access to the
robot tends to build mental models of auditory cues that
help to improve the performance of the instructor. This
provides accurate information about the internal state of the
robot. The study revealed that people easily constructed
mental models in natural environments, but with an incom-
plete knowledge of how the robot operates / works.
The work in [9] concluded that the study provides evidence
that large mutual influences between cognitive neuroscience
and social robotics enable a better understanding of man
which leads to an increased acceptance of future robotic
companions in society. The authors in [10] presented a
transportation system of humanoid robots based on learning.
The objective of this study was to successfully transport an
object using two NAO robots by means of cooperation.
Preliminary results showed that this approach was very
effective, hence highlighting the cooperative capabilities
inherent to NAO (e.g., communication).
Figure 3. Interaction with humans.
III. COMERCIAL ALTERNATIVES FOR ELDERLY CARE
This section presents several alternatives to our proposed
solution inspired in the robot NAO. This section allows
withdrawing some conclusions regarding the choices carried
out in this paper, thus highlighting the low-cost advantage
of NAO.
a) Telehealth
The project Telehealth being currently developed by ISA
(Intelligent Sensing Anywhere) is one of the most interest-
ing solutions. However, it is the authors’ opinion that the
project still presents some gaps. It provides several meas-
urements with a high reliability regarding the patient’s envi-
ronment. This system focus on a more reliable record sav-
ings than in the social aspect regarding the elderlies needs.
Hence, although its usefulness, this project still lacks on one
of the biggest problems in our society: the loneliness of the
elderlies. Our project aims on using a lower number of sens-
ing information but plays an important role on the social
aspect.
b) Ambient Assisted Living
Ambient assisted living is one of the most recent research
areas. Such projects are interesting solutions to monitor
elders’ behavior. Nevertheless, to the similarity of
Telehealth, the authors highlight the problem of being static
solutions. In other words, the solution and the various sen-
sors that are included in those designs can be installed in
houses, but cannot be transported to any other location. The
proposed solution, on the other hand, has the portability
ability being easy to transport anywhere and with autono-
mous navigation capabilities. Moreover, it still allows moni-
toring vital signs and following up in person anywhere.
Figure 4. Nursebot.
Figure 5. PARO Therapeutic Robot
c) Nursebot
The Nursebot project (Fig. 4) is a mobile, personal service
robot that assists elderly people [11]. That robot provides a
research platform to test out a large range of ideas for assist-
ing elderly people such as intelligent reminding,
telepresence, data collection, mobile manipulation and so-
cial interaction. For instance, this robot can advertise the
patients to do not forget to take medicine. Nevertheless,
contrarily to the herein proposed platform, it does not pos-
sess any kind of sensing capabilities regarding both envi-
ronmental and health information. Moreover, the NAO
robot is a human-like platform, thus hastening its identifica-
tion and interaction by the elderly. It is also noteworthy that
the NAO platform is considerably less expensive than the
Nursebot.
d) PARO THERAPEUTIC ROBOT
PARO (Fig. 5) is a therapeutic robot baby harp seal [12].
PARO is an advanced interactive robot that fosters the bene-
fits of animal therapy to be administered to patients in envi-
ronments such as hospitals and nursing homes. PARO can
reduce the patient stress and stimulates the interaction be-
tween patients. The similarities with the NAO extension end
here. As previously mentioned, besides social interaction,
we aim at acquiring data that may be useful, e.g., measure
the healthy parameters, and at promoting physical exercises.
Moreover, the cost advantage regarding NAO still remains.
IV. FROM NAO TO RIA
The previous sections briefly presented the features and
applicability of the NAO robot. Despite all its advantages
over other alternatives, the NAO is not prepared for an el-
derly care task.
This section briefly summarizes our strategy to turn the
NAO robot in the ideal low-cost tool for the elderly care.
This will be a completely remodeled platform with several
new sensors, both environmental and health sensors. The
next topics give a brief overview on the sensors that will be
equipped on NAO:
Smoke detector: this sensor will allow detecting possible
fire outbreaks. In case of detection, NAO will alert the
patient, as well as the agents in charge of it. Further-
more, it will plan alternative paths to some predefined
safe locations and guide the elder toward those;
Temperature: the NAO robot will be able to sense two
different kinds of temperatures: the environmental and
the patient. If the corporal temperature of the patient is
not regular then the robot NAO will alert the patient and
the agents in charge of it. Regarding the environmental
temperature, the robot NAO may alert for irregular lev-
els to make a better environmental place for the patient;
Humidity: This sensor measures the humidity that exists
in the environment. If the values of humidity are not ap-
propriate for the health of the patient, the robot NAO
will send an alert with those levels.
Others: Health sensors that may monitor the blood pres-
sure, glucose and others will also be studied.
V. CONCLUSION
To attend the necessities of our community, the RIA robot
will not leave old people alone and may give the required
attention that this people need. People already have several
entertainments such as television, radio and others. Howev-
er, nothing compares to a humanoid robot when it comes to
assist the human being on social and daily life situations.
Robots can save many lives, either on a military field on in
our houses.
REFERENCES
[1]
J. F. d. Costa. (2012) Jornal Sol. [Online].
http://sol.sapo.pt/inicio/Sociedade/Interior.aspx?conte
nt_id=40618
[2]
T. Niemueller, et al., "Providing Ground-truth Data for
the Nao Robot Platform," in RoboCup 2010: Robot
Soccer World Cup XIV. Singapore: Springer, 2011, pp.
133-144.
[3]
S. Shamsuddin, et al., "Initial Response in HRI- A
Case study on evaluation of schild with autism
spectrum disorders interacting with humanoid robot
NAO," in International Symposium On Robotics and
Intelligent Sensors, 2012, pp. 1448-1455.
[4]
S. Shamsuddin, et al., "Humanoid Robot NAO
interacting with autistic children of moderately
impaired intelligence to augment communication
skills," in International Symposium on Robotics and
Intelligent Sensors, 2012, pp. 1533-1538.
[5]
A. Ude, T. Shibata, and C. G. Atkeson, "Real-Time
Visual System for Interaction with Humanoid Robot,"
in Robotics and Autonomous Systems, 2001, pp. 115-
125.
[6]
A. Ude, C. G. Atkeson, and M. Riley, "Programming
full-body movements for Humanoid Robots by
observation," in Robotics Autonomous Systems, 2004,
pp. 93-108.
[7]
N. Koenig, L. Takayama, and M. Mataric,
"Comunication and knowledge sharing in human-robot
interaction and learning from demonstration," Neural
Networks, pp. 1104-1112, 2010.
[8]
A. Stoica, "Robot Fostering Techniques for Sensory-
Motor Development of Humanoid Robots ," in
Robotics and Autonomous Systems, 2001, pp. 127-143.
[9]
T. Chaminade and G. Cheng, "Social cognitive
neuroscience and humanoide robotics," Journal of
Physiology - Paris, pp. 286-295, 2009.
[10]
Y. Inoue, T. Tohge, and H. Iba, "Cooperative
Transportation System for Humanoid Robots using
Simulation-Based Learning," in Applied Soft
Computing, 2007, pp. 115-125.
[11]
J. Matthews, et al. [Online].
http://www.cs.cmu.edu/~nursebot/web/index.html
[12]
PARO Robots U.S., Inc. Paro Therapeutic Robot.
[Online]. http://www.parorobots.com/
... Dautenhahn and Billard 21 have stated that social robots can participate in social interactions. 22 With the evolution of robotics, robots are increasingly used in environments that are suitable for human capabilities. The environment where the robot is present can change without any interference from the robot, for this reason, robots need to have the perception of the environment that surrounds them. ...
Article
Full-text available
This article proposes a robotic system that aims to support the elderly, to comply with the medication regimen to which they are subject. The robot uses its locomotion system to move to the elderly and through computer vision detects the packaging of the medicine and identifies the person who should take it at the correct time. For the accomplishment of the task, an application was developed supported by a database with information about the elderly, the medicines that they have prescribed and the respective timetable of taking. The experimental work was done with the robot NAO, using development tools like MySQL, Python, and OpenCV. The elderly facial identification and the detection of medicine packing are performed through computer vision algorithms that process the images acquired by the robot’s camera. Experiments were carried out to evaluate the performance of object recognition, facial detection, and facial recognition algorithms, using public databases. The tests made it possible to obtain qualitative metrics about the algorithms’ performance. A proof of concept experiment was conducted in a simple scenario that recreates the environment of a dwelling with seniors who are assisted by the robot in the taking of medicines.
... Literature reviews reveal that the real robot provides better performance to interact with human compared to a virtual agent. 42,43 Such a non-contact system can demonstrate rehabilitation exercise and verbally communicate with the users. Due to the lack of physical contact, such a system requires minimum safety concern and increased accessibility. ...
Article
Full-text available
Introduction The aim of this research is to develop a robot-assistive training approach for the disabled individuals with impaired upper limb functions. People with impaired upper limb function can regain their motor functionality undergoing intense rehabilitation exercises. With increasing number of disabled individuals, we face deficiency in the number of expert therapists. One promising remedy could be the use of robotic assistive devices. Method To instruct and demonstrate rehabilitation exercise, this research used NAO robot. A library of recommended rehabilitation exercises involving shoulder (i.e., abduction/adduction, vertical flexion/extension, and internal/external rotation), and elbow (i.e., flexion/extension) joint movements was formed in Choregraphe (graphical programming interface). For this purpose, a kinematic model of human upper-extremity was developed based on modified Denavit-Hartenberg notations. Result In experiments, NAO robot gave voice instruction and was maneuvered to cooperate and demonstrate the exercises from the library. NAO also plays some complex game with the subject that represents a multi-joint movement's exercise, which was also included in the library. Conclusions Experimental results with healthy participants reveal that the NAO robot can successfully instruct and demonstrate upper-extremity rehabilitation exercises for single and multi-joint movements. It implies a technical development of cooperative rehabilitation system for which target group will be individuals with upper limb impairment.
... Progress in scientific research and developments on industrial applications lead to the appearance of educational programs on robotics, covering a wide range of aspects such as kinematics, artificial intelligence and mechanical design. It is fundamental to involve students in the construction and development of robotic platforms, and in project-oriented learning in order to forest creative and divergent thinking, and promote acquisition of self-learning and practical skills [4][5][6][7][8][9]. For this reason we allows the students to develop different robotics platforms. ...
Chapter
This paper presents one methodology for teaching engineering students, which relies on open platform requiring basic knowledge of robotics, like mechanics, control or energy management. Walking robots are well known for being able to walk over rough terrain and adapt to various environments. Hexapod robots are chosen because of their better stability and higher number of different gaits. However, having to hold the whole weight of the body and a large number of actuators makes all walking robots less energetically efficient than wheeled robots. This platform endows students with an intuitive learning for current technologies, development and testing of new algorithms in the area of mobile robotics and also in generating good team-building.
... The students implement the proposed problem and the validation of the results is made on MATLAB® [2][3][4][5][6]8,14,[23][24][25]32,46]. In the example the development application was made with Matlab® GUI (Graphical User Interface) that had a virtual robot similar to MOTOMAN HP3L and slider buttons to change the internal coordinates of the robot links motors in order to allow the communication between the computer and the real robot. ...
Article
Full-text available
The paper describes the use of computer applications on education for industrial robotic systems. Robotics evolved as a central issue in teaching for scientific and engineering courses and inherently encompasses a spectrum of sciences and technologies and qualification levels. However, most current teaching approaches, related to robotics, concentrate on individual aspects or small student groups and do not involve dangerous situations. With a mixed‐reality robotics teaching, a true interdisciplinary setup can be reached, this approach has been used in a robotics course at higher education, to prepare students for future activities in industry and also in research. This active learning experience approach in the field of Industrial Robotics was implemented in a Master degree on Electrical Engineering.
... Progress in scientific research and developments on industrial applications lead to the appearance of educational programs on robotics, covering a wide range of aspects such as kinematics, artificial intelligence and mechanical design. It is fundamental to involve students in the construction and development of robotic platforms, and in project-oriented learning in order to forest creative and divergent thinking, and promote acquisition of self-learning and practical skills [4][5][6][7][8][9]. For this reason we allows the students to develop different robotics platforms. ...
Conference Paper
Full-text available
This paper presents one methodology for teaching engineering students, which relies on open platform requiring basic knowledge of robotics, like mechanics, control or energy management. Walking robots are well known for being able to walk over rough terrain and adapt to various environments. Hexapod robots are chosen because of their better stability and higher number of different gaits. However, having to hold the whole weight of the body and a large number of actuators makes all walking robots less energetically efficient than wheeled robots. This platform endows students with an intuitive learning for current technologies, development and testing of new algorithms in the area of mobile robotics and also in generating good team-building.
... This work aims to address this challenge by developing a cross platform compatible communication network among off-the-shelf robots. Our goal is to successfully establish an explicit communication between EPFL e-puck (wheeled robots) [2], [3] Aldebaran NAOs (humanoid robots) [4], [5], and Parrot AR Drones 2.0 (unmmaned aerial vehicle) [6], [7], [8] via a mobile ad hoc network (MANET). ...
Conference Paper
Full-text available
In this paper, we present a cross-platform com-patible mobile ad hoc network communication (MANET), which will allow heterogeneous robots to cooperate as a team. The system is novel as it is self-organized, based on simple connection laws, relies only on local communication and most of all, is both designed and deployed among off-the shelf robots. We aim to demonstrate the robots capabilities to adapt their behavior so as to maintain full connectivity of the MANET, despite being governed by connection laws. We will assess the system by conducting experiments under search-and-rescue environments in order to evaluate both its performance and scalability.
Chapter
This chapter will examine whether technologies can improve the wellbeing of older adults in nursing homes, day care centres and public hospitals and bring benefits to carers through five examples: NAO (i.e. a humanoid robot), PARO (i.e. a seal-type mental commitment robot), Virtual Reality (VR) Googles and Immersive VR Rooms, DFree® (i.e. wearable bladder scanner) and Smart Health Video Consultation (SHVC). Technologies, if used properly, can improve the quality of life and the quality of care of older adults and relieve the burden on care workers. They will not replace care workers. Instead, they complement care workers and free them up to do more meaningful tasks (e.g. care tasks). It is expected that the scale and the pace of using health information technologies, monitoring technologies, assistive technologies and robotics increase in the LTC sector in future due to manpower shortage and the increase in the number of older adults in Singapore. Factors such as awareness, acceptance, ease of use, trust, knowledge and perceived risk will affect technology adoption. It is important to strike a balance between technology and human touch. Implementing technology with a human touch can make older adults feel loved, valued and cared for.KeywordsDFree®Human touchNAOPAROTeleconsultationVirtual reality
Chapter
This paper presents the construction of an autonomous robot to participating in the autonomous driving competition of the National Festival of Robotics in Portugal, which relies on an open platform requiring basic knowledge of robotics, like mechanics, control, computer vision and energy management. The projet is an excellent way for teaching robotics concepts to engineering students, once the platform endows students with an intuitive learning for current technologies, development and testing of new algorithms in the area of mobile robotics and also in generating good team-building.
Article
Full-text available
The evolution of human-robot interaction (HRI) is now expanding its wings to aid children with Autism Spectrum Disorders (ASD) in areas of socialization, communication and playful behavior through robot-based intervention. Herein we present our holistic, long-standing goal to contribute to the lives of children with ASD; who suffer a lifelong developmental disability. The purpose of this paper is to elaborate on a case study in our pilot experiment where a child with ASD is exposed to the humanoid robot NAO in order to gauge his initial response and behavior in the presence of a robot. NAO robot is the chosen robotic agent as it is a commercially available humanoid with simpler in appearance compared to real humans, thus appears more approachable to children with ASD. The pilot procedures involve the robot executing basic, simple components of interaction through a series of 5 different modules. In this study, the principal results show that the basic HRI carried out by the robot is able to suppress the child's autistic behavior during the child-robot interaction. Also, more eye contact is observed between the child and robot compared to the child with his teacher during regular class session. Relating this to the child's IQ which falls in the moderate category, it is suggested that children with ASD in the same IQ group will be receptive to robot-based intervention even in the first interaction session. Hence, it can be concluded that the humanoid robot NAO has potential to serve as a platform to support and initiate interaction in children with ASD.
Article
Full-text available
This report presents the findings from our pilot study on the initial behavior of autistic children of moderately impaired intelligence when exposed to simple human-robot interaction (HRI) modules executed by a humanoid robot NAO. All 5 children have been specifically assessed using the Autism Diagnostic Observation Schedule (ADOS) and their diagnosis is classified as autistic disorder. We hypothesize that NAO's human-like appearance, its capability to blink its eyes, speak and play music; coupled with the simplicity of the HRI modules will be able to entice the children's interest to engage in communication. Hence, this would significantly reduce the children's autistic characteristics in communication behavior compared to the usual class setting. In this study, the principal result shows that 4 out of the 5 children exhibited a decrease of autistic behavior (in communication subscale) when the robot is executing HRI modules during the single session of child-robot interaction. This promising outcome indicates that the NAO robot were able to attract the children's attention, keep each child engaged with the robot during interaction and hence give positive impact to the children's communication behavior. Relating this to the children's FSIQ, it can be deducted that autistic children with FSIQ of moderately impaired (from 40-54) are receptive to robot-based intervention. This is again showed by the lower autistic traits observed during the HRI modules compared to in-class setting. Overall, this research suggests that autistic children of moderately impaired intelligence show good response to robot-based intervention. This finding is crucial to form a solid foundation and proof on the positive utilization of the humanoid robot NAO for the children affected by autism.
Conference Paper
Full-text available
Collecting ground truth-data for real-world applications is a non-trivial but very important task. In order to evaluate new algo- rithmic approaches or to benchmark system performance, they are in- evitable. This is particularly true for robotics applications. In this paper we present our data collection for the biped humanoid robot Nao. Re- ective markers were attached to Nao's body, and the positions and orientation of its body and head were tracked in 6D with an accurate professional vision-based body motion tracking system. While doing so, the data of Nao's internal state, i.e., the readings of all its servos, the inertial measurement unit, the force receptors plus a camera stream of the robot's camera were stored for dierent, typical robotic soccer sce- narios in the context of the RoboCup Standard Platform League. These data will be combined in order to compile an accurate ground-truth data set. We describe how the data were recorded, in which format they are stored, and show the usability of the logged data in some rst experi- ments on the recorded data sets. The data sets will be made publicly available for the RoboCup's Standard Platform League community.
Article
The research efforts addressing the control of robot behavior have been polarized; most robots are either fully guided through “strong” programming, or given a few learning algorithms and left alone to explore the world. This paper explores the area in-between, looking at robot fostering, referring to techniques by which skills can be transferred to robots through a close interaction with humans. While robot fostering can be the basis of interaction with a variety of robotic shapes, it is most natural and human-friendly when the robot apprentices are anthropomorphic/humanoid. Fostering techniques discussed here include teaching/learning by imitation, teaching by description/explanation, reinforcement, aid and collaboration. The paper illustrates an experiment in teaching/learning by imitation. The human fosters the robot by first imitating its uncoordinated arm movements, thus helping the robot develop its sensory-motor associative system. The human then shows arm movements and the robot visually tracks them; consecutively, the robot is able to learn arm movements by imitation. Fostering techniques, in addition to robot learning/acquisition techniques and more efficient man–machine interaction are considered key elements contributing to the nascence of a new research field, developmental robotics, which would focus on the robotics counterpart of human cognitive and motor development.
Article
The formulation and optimization of joint trajectories for humanoid robots is quite different from this same task for standard robots because of the complexity of humanoid robots’ kinematics and dynamics. In this paper we exploit the similarity between human motion and humanoid robot motion to generate joint trajectories for humanoids. In particular, we show how to transform human motion information captured by an optical tracking device into a high dimensional trajectory for a humanoid robot. We propose an automatic approach to relate humanoid robot kinematic parameters to the kinematic parameters of a human performer. Based on this relationship we infer the desired trajectories in robot joint space. B-spline wavelets are utilized to efficiently represent the trajectories. The density of the basis functions on the time axis is selected automatically. Large-scale optimization techniques are employed to solve the underlying computational problems efficiently. We applied our method to the task of teaching a humanoid robot how to make various naturally looking movements.
Article
In this paper, an approach to the behavior acquisition required for humanoid robots to carry out a cooperative transportation task is proposed. In the case of object transportation involving two humanoid robots, mutual position shifts may occur due to the body swinging of the robots. Therefore, it is necessary to correct the position in real-time. Developing the position shift correction system requires a great deal of effort. Solution to the problem of learning the required behaviors is obtained by using the Classifier System and Q-Learning. The successful cooperation of two HOAP-1 humanoid robots in the transportation task has been confirmed by several experimental results.
Article
In this paper, we describe a new real-time visual system that enables a humanoid robot to learn from and interact with humans. The core of the visual system is a probabilistic tracker that uses shape and color information to find relevant objects in the scene. Multiscale representations, windowing and masking are employed to accelerate the data processing. The perception system is directly coupled with the motor control system of our humanoid robot DB. We present two case studies of on-line interaction with a humanoid robot: mimicking of human hand motion and smooth pursuit of human head motion. The generation of humanoid robot motion based on the position of relevant body parts is accomplished in real time. Both studies are supported by experimental results on DB.
Article
Inexpensive personal robots will soon become available to a large portion of the population. Currently, most consumer robots are relatively simple single-purpose machines or toys. In order to be cost effective and thus widely accepted, robots will need to be able to accomplish a wide range of tasks in diverse conditions. Learning these tasks from demonstrations offers a convenient mechanism to customize and train a robot by transferring task related knowledge from a user to a robot. This avoids the time-consuming and complex process of manual programming. The way in which the user interacts with a robot during a demonstration plays a vital role in terms of how effectively and accurately the user is able to provide a demonstration. Teaching through demonstrations is a social activity, one that requires bidirectional communication between a teacher and a student. The work described in this paper studies how the user's visual observation of the robot and the robot's auditory cues affect the user's ability to teach the robot in a social setting. Results show that auditory cues provide important knowledge about the robot's internal state, while visual observation of a robot can hinder an instructor due to incorrect mental models of the robot and distractions from the robot's movements.
Article
We believe that humanoid robots provide new tools to investigate human social cognition, the processes underlying everyday interactions between individuals. Resonance is an emerging framework to understand social interactions that is based on the finding that cognitive processes involved when experiencing a mental state and when perceiving another individual experiencing the same mental state overlap, both at the behavioral and neural levels. We will first review important aspects of his framework. In a second part, we will discuss how this framework is used to address questions pertaining to artificial agents' social competence. We will focus on two types of paradigm, one derived from experimental psychology and the other using neuroimaging, that have been used to investigate humans' responses to humanoid robots. Finally, we will speculate on the consequences of resonance in natural social interactions if humanoid robots are to become integral part of our societies.
Conference Paper
We describe a real-time visual system that enables a humanoid robot to learn from and interact with humans. The core of the visual system is a probabilistic tracker that uses shape and color information to find relevant objects in the scene. Multiscale representations, windowing and masking are employed to accelerate the data processing. The perception system is directly coupled with the motor control system of our humanoid robot DB. We present an example of on-line interaction with a humanoid robot: mimicking of human hand motion. The generation of humanoid robot motion based on the human motion is accomplished in real-time. The study is supported by experimental results on DB