Autonomous Traffic Management: Open Issues and New Directions

Abstract

Many technical communities are vigorously pursuing research topics that contribute to the Autonomous Traffic Management (ATM). ATM is a research field of Intelligent Transportation Systems (ITS) that aims to decrease traffic congestion based on autonomous vehicles cooperation and capacities. However, a literature review reveals that many issues related to ATM and autonomous vehicles are up for discussion, and so are the key research challenges lying ahead. We first present the ATM aims and scope to provide a basis for discussing related open research problems. This paper enumerates and discusses six key research topics and research problems within those issues.

Full text

Autonomous Traffic Management: Open Issues and New
Directions
Sara El Hamdani#1, Nabil Benamar #2
# University Moulay Ismail, Meknes Morocco
1 s.elhamdani@edu.umi.ac.ma
2 n.benamar@est.umi.ac.ma
Abstract— Many technical communities are vigorously pursuing
research topics that contribute to the Autonomous Traffic
Management (ATM). ATM is a research field of Intelligent
Transportation Systems (ITS) that aims to decrease traffic
congestion based on autonomous vehicles cooperation and
capacities. However, a literature review reveals that many issues
related to ATM and autonomous vehicles are up for discussion,
and so are the key research challenges lying ahead. We first
present the ATM aims and scope to provide a basis for
discussing related open research problems. This paper
enumerates and discusses six key research topics and research
problems within those issues.
Keywords— Autonomous vehicle, self-driving car, cooperative
system, Vehicle to vehicle communication (V2V), traffic
management, ITS
I. INTRODUCTION
Traffic management is one of the most challenging
problems within transportation system for keeping traffic
safety and decreasing traffic congestion. Meanwhile, traffic
congestion is often a contributing cause of accidents [1] and
has an important impact on the economy [2].
To reduce congestion rate, traffic management used road
signs and infrastructure such as traffic lights controller system.
However, traditional systems for traffic management did not
prove their efficiency, while the number of vehicles on the
roads is growing and hence congestion rate is still increasing.
Accordingly, Intelligent Transportation Systems (ITS) play a
crucial role in diminishing traffic jams using new
technologies such as autonomous vehicles.
Nowadays, autonomous vehicles are equipped with
advanced sensors and cameras that provide much more
detailed environmental information, supporting richer
perception of local surroundings. Likewise, wireless
communication allows vehicles to share information with
other vehicles (and with infrastructure). Thus, vehicles are
able to cooperate and manage the road autonomously based
on an Autonomous Traffic Management (ATM) system.
ATM has a key role in decreasing vehicles traffic delay
and hence in diminishing road congestion which make it a
central research field of ITS where important efforts were
done. However, many ATM issues related to autonomous
vehicles real capacities in complex road architectures and
situations, to communication limitations and the ability of
cohabitation between autonomous vehicles and other road
users.
In this paper, we briefly mention a vision for autonomous
vehicles and ATM scope in section II. We then
discuss open research questions categorized into six topics in
section III. Finally, we conclude the paper in section IV.
II. AUTONOMOUS TRAFFIC MANAGEMENT SCOPE
A. Autonomous vehicle
ATM systems are based on autonomous vehicles as the
powerful agents that are capable to cooperate between them
to manage the traffic more efficiently. As illustrated in figure
1, autonomous vehicle is equipped with diverse cameras and
sensors that permit full vision of the different elements of the
road. High-accuracy Global Positioning System (GPS) device
in turn allows the vehicle to follow the road indicated by a
digital road-map database that the vehicle has access to.
Furthermore, the smart vehicle is able to collect more
complex traffic information based on vehicle to vehicle (V2V)
or generally Vehicle to another entity (V2X) communication
using the wireless interface.
In the other hand, the central computer provides the
vehicle with a high computation capacity and enables it to
analyze the set of collected data, to achieve complex
processing and to take smart driving decisions. Thus, the
vehicle is capable to participate to the fully autonomous
management of the traffic.
B. Autonomous traffic management
As a research field of ITS, ATM is concerned by the
development of smart systems for traffic management based
Fig. 1 An illustration of autonomous vehicle.

on autonomous vehicles capacity of cooperation. Such new
technologies enable ATM to have a key role in increasing
traffic flow and solving many road concerns. As illustrated in
figure 2, the following summarizes some features provided by
ATM:
 Improving Traffic Light Controller System (TLCS):
Toward fully autonomous system, ATM
participates also to the improvement of smart
TLCS based on Vehicle to Infrastructure (V2I)
communication.
 Replacing stop signs: A fully ATM aims to replace
traditional TLCS and signs which are using
autonomous vehicles cooperation based on V2V
communication.
 Enhancing road throughput: By replacing road signs
and using vehicles coordination, ATM systems
aims to increase traffic flow. This later is enhanced
by minimizing vehicles stopping which contributes
to decreasing vehicles travel delay.
 Intersection management: Intersections are
considered as traffic bottleneck of that signalized
systems failed in managing it efficiently. Hence, a
big part of ATM works are concerned by
cooperative management of intersection.
 Enhancing security: Like the rest of ITS research
areas, security is the most important objective of
ATM, since transportation is a direct cause of
death injury of human beings. Cooperative
vehicles exchange data and coordinate while
driving to avoid collisions.
 Decreasing Congestion rate: Directly or indirectly, all
previous discussed ATM aims has an important
effect in decreasing road congestion. This later is a
serious issue of ITS due to its negative impact on
the economy (big waste of fuel and time).
III. RESEARCH DIRECTIONS
The spectrum of research required to reach ATM at the
scale intended above involves significant investigation along
many directions. In this section, issues and required research
directions are introduced in six topic areas: complex situations,
complex architecture, communication, data privacy,
coexistence of driverless/ normal vehicles and vulnerable users.
The research topics presented in each case are
representative and not complete. Some issues such as the
development of standards and the cultural impact on
application of these systems are outside the scope of the paper.
A. Complex situations
As aforementioned in the previous section, ATM rely on
autonomous vehicles capacities of communication [3],
computation and taking smart decisions [4]. Thus, it aim to
manage intersections and roads efficiently based on a
cooperative approach. Thus, ATM are able to decrease
vehicles travel delay and accordingly, to diminish significantly
road congestion rates.
Autonomous vehicles, in turn, are based on machine
learning and pattern recognition [5] using sensors [6] and
cameras [7]. Thus, the vehicle is able to recognize persons,
objects and road signs before arriving to them. Moreover, it is
capable to avoid obstacles [8] and respect road marks [9]
based on smart decisions that it can take in real time, for
instance: breaking, changing line or slowing down according
to the situation. The issue here is that autonomous vehicles
capacities require a perfect road conditions. In other words, the
vehicles could easily stump due to undefined situations such as
inclement weather, detours and rerouted roads, dramatic
crashes or roads without clear lane marking.
Moreover, autonomous vehicles are not able to drive
defensively like a human driver can interact by anticipating
potential risks when navigating in construction zones for
instance, or when driving near drunks, wild animals or
children. Likewise, the vehicle could straggle due to a simple
misreading harmless puddle of water as pothole or a little
mistake made by Google maps for instance. In other words,
how will an autonomous vehicle react in imperfect road
conditions?
The majority of existing autonomous architectures [10][11]
ignore this big issue and require perfect conditions that allow
them to suppose a faultless behavior from autonomous
vehicles. However, this field of research is very critical since it
is related to human beings’ safety and the smallest mistake
could cause a tragedy; hence, it should not be ignored by the
system.
Despite the big effort made on cyber physical systems [12]
and on accurate object recognition technologies [13][14] of
autonomous driving vehicles, the hardest reasoning tasks
remain unsolved to date, as no autonomous vehicle has yet
Fig. 2 An illustration of a set of important features autonomous traffic
management. aims.

proved a capacity to navigate in such undefined situations [15].
Thus, works on ATM need focus more on complex situations
and should take into consideration the limited capacities of
autonomous vehicles.
B. Complex Architecture
The main objective of ATM is to avoid possible collisions
with other vehicle using the capacities of autonomous vehicles
[16]. To do so, the system drives from a starting point to an
ending point following the path indicated using the GPS. Thus,
the vehicle’s system uses cameras and sensors to visualize the
path elements such as lines, pedestrian crossing and
roundabout.
Regarding vehicle-collision avoidance, the system needs to
model the road architecture that it can define the collision
region. Accordingly, the majority of the ATM tend to model
the road architecture especially in urban area as simple squares
[17][14] as shown in the figure 3 a). For instance, several
works [18][19] modelled the intersection as a grid of small
cells to make the vehicle able to recognize its trajectory
accurately in order to detect the collision region before
arriving to it. As illustrated in Fig. 3. (b), the trajectory of
vehicle “A” inside the junction is {2, 6, 10, 14}, when vehicle
“B”’s trajectory is {8, 7, 6, 5}. Thus, the cell number 6 is
expected as a region where a collision may happen between
the two vehicles.
Such simple modelling of road enable a more accurate
collision detection for the system. However, it is too far to be
feasible in real world because intersections are not always a
junction of two simple road and do not have a perfect
geometric shape.
Road network topologies even in urban area are more
complex than the topology used in simulations. Thus, these
systems are not designed to manage traffic in real world roads.
Excluding some works which used real topologies in
simulations such as [20], researches in this field should be
directed towards more complicated topologies to be more valid
for real life road architectures.
C. Communication
In ATM, vehicles are cooperative and generally do not rely
on road signs and infrastructure; hence, communication has the
key role in the autonomous management of the traffic.
Autonomous vehicles require communication [21][22] to share
their information with infrastructure and to deduce the
situation of the road. Based on this data, autonomous vehicle
decide to change route [23], to stop, to slow down…
Generally, the mode of dissemination used in V2V
communication is geocast which is a broadcast but limited
only to within a specific area using Dedicated Short Range
Communications/Wireless Access in Vehicular Environments
(DSRC/WAVE) [24] in a range of 1km [25]. Thus, in an ATM
vehicles broadcast and receive information to all vehicles in
their range permanently [26] [27].
The main drawback is that the packet delivery ratio
increases with the density of traffic environment [28] which is
inconsistent with the main objective of the system which is
congestion avoidance. Moreover, increasing the transmission
power require involving more vehicles which increases the
channel load in turn significantly and ends in channel
congestion.
Furthermore, ATM systems should study the ability of the
vehicle’s system: to receive hundreds or even thousands of
messages in a congested area, to handle them simultaneously,
to remove essential information, to do complex calculations
based on it, to take critical decisions and to apply them in real
time.
Thus, future works on ATM must take into account this
issue and should study the real communication capacity of
autonomous vehicles and should measure the maximum
number of packet that a vehicle can handle and respond to in
real time. Likewise, they should make more efforts on
minimizing communication between vehicles like in [29]
where researchers worked on replacing physical
communication with virtual communication.
D. Data privacy
Despite of security issues of autonomous vehicles that are
b)
a)
Fig. 3 An illustration of road architecture modelling as squares.
a) An urban road network modelled as squares. b) An
intersection modelled as a grid of numbered small cells to detect
collision region.
“A”
“B”

not solved until now such as the frightening possibility of
hacking the entire vehicle, ATM requires from vehicle to share
their personal information with other vehicles and/or with
servers across the country.
ATM assumes that all vehicles should share private
information such as current position, depart station and arrival
station [30][31]. However, such information is not always
without value or easy to share. In fact, vehicles information
could be used badly in espionage or in criminal operations
easily from where comes the necessity of safeguarding of
some persons (habitually public figures) information.
Nevertheless, even normal persons may have the issue of
losing the confidentiality of their information while travelling
on the road and they have the right to require data privacy.
Existing research proposed security systems to protect
external communication for autonomous vehicles. The
proposed system in [32] is able to detect malicious vehicles,
likewise the system in [33] can detect black hole attacks before
they causes significant damage.
Nonetheless, vehicles data privacy should be considered in
researches on ATM. The system should value the information
exchanged between vehicles and should protect as possible
vehicles data and limit its circulation to only essential cases.
E. Coexistence of Driverless/ Normal vehicles
Autonomous vehicles are seen as the future trend in
Intelligent ITS world. Therefore, ATM for traffic management
centers around autonomous vehicles and the exploitation of
their capacities to improve the effectiveness of urban vehicular
mobility. Thus, majority of ATM systems assumes that all the
existing vehicles on the road are fully autonomous with perfect
function [34].
However, autonomous vehicles are still under test and are
not ready for use in real-world roads soon for many reasons
[35]. Moreover, when self-driving vehicles will be ready for
use they cannot replace all normal vehicles at once, but they
will be inserted gradually due to social and economic obstacles.
Therefore, researches on autonomous vehicles should focus
first on the integration of autonomous vehicles with normal
vehicles.
Accordingly, in some existing works [36][37] the system
considers the existence of non-connected vehicles side by side
with autonomous vehicles on the same road network.
Nevertheless, works on ATM should focus more on the
transition phase from normal vehicles to autonomous vehicles.
Thus, the system should be able to detect a normal vehicle and
to avoid it without requiring communication or a smart
reaction from it.
F. Vulnerable users
As aforementioned in the previous subsection, the problem
with the majority of ATM focus only on autonomous vehicles
and do not consider normal vehicles. Furthermore, the systems
ignore the existence of vulnerable road users [38] such as
motorcycles, bicycles and pedestrians so they do not include
them [30][39][40].
Nevertheless, vulnerable users do not have the same
autonomous vehicles capacities such as communication and
detection; hence, it is difficult to deal with them on the road.
Moreover, many security issues are related to vulnerable users
such as detection and warning.
Actually, important effort were done in this research field
for vehicular detection of pedestrians [8], pedestrian collision
avoidance [41], vehicular to pedestrian (V2P) communication
based approach for pedestrian crossing [42]. Likewise, in [43]
researchers worked on motorcycle crash avoidance based on
V2X communication.
Nevertheless, ATM trend to replace traditional road signals
and infrastructure that manage all road users now by
cooperative architectures that rely only communication
between vehicles [39]. Thus, vulnerable users’ detection,
avoidance or even warning are not enough.
To replace existing traffic management mechanisms for
signalized roads, ATM should consider all road users and their
rights of navigating or crossing the road. Furthermore,
vulnerable users such as pedestrians should be prioritized
without requiring specific devices to be able to cross the road.
IV. CONCLUSIONS AND FUTURE WORKS
In summary, ITS relies on ATM to solve traffic problems in
the future such as decreasing congestion rate and economic
cost when autonomous vehicles are ready for use. Generally,
ATM assumes perfect function from autonomous vehicles, and
simple road architectures. Likewise, they assume defined
situation, unlimited wireless communication and the existence
of autonomous vehicles as the only road user. In fact, these
assumptions and requirements open many issues of the
application of ATM in real world roads. We discussed these
issues in six point to provide clear research directions that
would help to improve ATM.
LIST OF ACRONYMS
ATM
Autonomous Traffic Management
DSRC
Dedicated Short Range Communications
GPS
Global Positioning System
ITS
Intelligent Transportation Systems
TLCS
Traffic Light Controller System
V2I
Vehicle to Infrastructure
V2P
Vehicle to Pedestrian
V2V
Vehicle to Vehicle
V2X
Vehicle to another entity
WAVE
Wireless Access in Vehicular Environments
REFERENCES
[1] C. A. Kahn and C. S. Gotschall, “The economic and societal impact
of motor vehicle crashes, 2010 (Revised),” Ann. Emerg. Med., vol.
66, no. 2, pp. 194–196, 2015.
[2] D. Schrank., B. Eisele., T. Lomax., and J. Bak., “2015 Urban
Mobility Scorecard,” Texas A&M Transp. Institue, vol. 39, no.
August, p. 5, 2015.
[3] V. Gradinescu, C. Gorgorin, R. Diaconescu, V. Cristea, and L.
Iftode, “Adaptive Traffic Lights Using Car-to-Car Communication,”
in 2007 IEEE 65th Vehicular Technology Conference - VTC2007-
Spring, 2007, no. 1, pp. 21–25.
[4] J. R. Perez, V. Milanes, T. De Pedro, and L. Vlacic, “Autonomous

Driving Manoeuvres In Urban Road Traffic Environment : A Study
On Roundabouts,” 18th World Congr. Int. Fed. Autom. Control,
2012.
[5] J. Wei, J. M. Snider, J. Kim, J. M. Dolan, R. Rajkumar, and B.
Litkouhi, “Towards a Viable Autonomous Driving Research
Platform.”
[6] N. Radwan, W. Winterhalter, C. Dornhege, and W. Burgard, “Why
did the Robot Cross the Road? - Learning from Multi-Modal Sensor
Data for Autonomous Road Crossing,” 2017.
[7] P. Dollar, C. Wojek, B. Schiele, and P. Perona, “Pedestrian detection:
An evaluation of the state of the art,” IEEE Trans. Pattern Anal.
Mach. Intell., vol. 34, no. 4, pp. 743–761, 2012.
[8] Y. Morales, A. Carballo, E. Takeuchi, A. Aburadani, and T.
Tsubouchi, “Autonomous robot navigation in outdoor cluttered
pedestrian walkways,” J. F. Robot., vol. 26, no. 8, pp. 609–635,
2009.
[9] U. Franke, D. Gavrila, S. Görzig, F. Lindner, F. Paetzold, and C.
Wöhler, “Autonomous Driving approaches Downtown,” IEEE Intell.
Syst., vol. 13, no. 6, pp. 1–14, 1999.
[10] K. Dresner and P. Stone, “A multiagent approach to autonomous
intersection management,” J. Artif. Intell. Res., vol. 31, pp. 591–656,
2008.
[11] R. Azimi, G. Bhatia, and R. R. Rajkumar, “STIP : Spatio-Temporal
Intersection Protocols for Autonomous Vehicles,” pp. 1–12, 2014.
[12] C. Berger and B. Rumpe, “Autonomous Driving - 5 Years after the
Urban Challenge: The Anticipatory Vehicle as a Cyber-Physical
System,” no. September, pp. 789–798, 2014.
[13] A. Teichman, J. Levinson, and S. Thrun, “Towards 3D object
recognition via classification of arbitrary object tracks,” Proc. -
IEEE Int. Conf. Robot. Autom., pp. 4034–4041, 2011.
[14] D. Mitzel, “Taking {M}obile {M}ulti-{O}bject {T}racking to the
{N}ext {L}evel,” PhD thesis, pp. 566–579, 2013.
[15] J. Levinson, J. Askeland, J. Becker, J. Dolson, D. Held, S. Kammel,
J. Z. Kolter, D. Langer, O. Pink, V. Pratt, M. Sokolsky, G. Stanek, D.
Stavens, A. Teichman, M. Werling, and S. Thrun, “Towards fully
autonomous driving: Systems and algorithms,” IEEE Intell. Veh.
Symp. Proc., pp. 163–168, 2011.
[16] S. B. Raut and L. G. Malik, “Survey on vehicle collision prediction
in VANET,” 2014 IEEE Int. Conf. Comput. Intell. Comput. Res.
IEEE ICCIC 2014, no. Idm, pp. 735–751, 2015.
[17] S. Huang, A. W. Sadek, and Y. Zhao, “Assessing the Mobility and
Environmental Benefits of Reservation-Based Intelligent
Intersections Using an Integrated Simulator,” vol. 13, no. 3, pp.
1201–1214, 2012.
[18] L. Chen and C. Englund, “Cooperative Intersection Management: A
Survey,” IEEE Trans. Intell. Transp. Syst., vol. 17, no. 2, pp. 570–
586, 2016.
[19] R. Azimi, G. Bhatia, R. Rajkumar, and P. Mudalige, “V2V-
Intersection Management at Roundabouts,” SAE Int. J. Passeng.
Cars - Mech. Syst., vol. 6, no. 2, pp. 681–690, 2013.
[20] P. Bellavista, L. Foschini, and E. Zamagni, “V2X Protocols for low-
penetration-rate and cooperative traffic estimations,” IEEE Veh.
Technol. Conf., no. November, 2014.
[21] G. Karagiannis, O. Altintas, E. Ekici, G. Heijenk, B. Jarupan, K. Lin,
and T. Weil, “Vehicular networking: A survey and tutorial on
requirements, architectures, challenges, standards and solutions,”
IEEE Commun. Surv. Tutorials, vol. 13, no. 4, pp. 584–616, 2011.
[22] G. Lu, L. Li, Y. Wang, R. Zhang, Z. Bao, and H. Chen, “A rule
based control algorithm of connected vehicles in uncontrolled
intersection,” Intell. Transp. Syst. (ITSC), 2014 IEEE 17th Int. Conf.,
pp. 115–120, 2014.
[23] S. Gupte and M. Younis, “Vehicular networking for intelligent and
autonomous traffic management,” IEEE Int. Conf. Commun., pp.
5306–5310, 2012.
[24] “J2735D: Dedicated Short Range Communications (DSRC)
Message Set DictionaryTM - SAE International,” p. 2735, 2016.
[25] K. Dar, M. Bakhouya, J. Gaber, M. Wack, and P. Lorenz, “Wireless
communication technologies for ITS applications,” IEEE Commun.
Mag., vol. 48, no. 5, pp. 156–162, 2010.
[26] R. Azimi, G. Bhatia, R. Rajkumar, and P. Mudalige, “Intersection
Management using Vehicular Networks,” Soc. Automot. Eng. World
Congr., pp. 1–13, 2012.
[27] L. Makarem and D. Gillet, “Information sharing among autonomous
vehicles crossing an intersection,” Conf. Proc. - IEEE Int. Conf. Syst.
Man Cybern., no. 1, pp. 2563–2567, 2012.
[28] S. Azimi, G. Bhatia, R. Rajkumar, and P. Mudalige, “Reliable
intersection protocols using vehicular networks,” 2013 ACM/IEEE
Int. Conf. Cyber-Physical Syst. ICCPS 2013, pp. 1–10, 2013.
[29] P. Desai, S. W. Loke, A. Desai, and J. Singh, “CARAVAN:
Congestion avoidance and route allocation using virtual agent
negotiation,” IEEE Trans. Intell. Transp. Syst., vol. 14, no. 3, pp.
1197–1207, 2013.
[30] M. Zhu, X. Li, H. Huang, L. Kong, M. Li, and M. Wu, “LICP : A
Look-ahead Intersection Control Policy with Intelligent Vehicles.”
[31] M. M. Abdelhameed, M. Abdelaziz, S. Hammad, and O. M. Shehata,
“Development and Evaluation of a Multi-Agent Autonomous
Vehicles Intersection Control System,” pp. 0–5, 2014.
[32] K. M. A. Alheeti, A. Gruebler, K. D. McDonald-Maier, and A.
Fernando, “Prediction of DoS attacks in external communication for
self-driving vehicles using a fuzzy petri net model,” 2016 IEEE Int.
Conf. Consum. Electron., no. 1, pp. 502–503, 2016.
[33] K. M. A. Alheeti, A. Gruebler, and K. McDonald-Maier, “Using
discriminant analysis to detect intrusions in external communication
for self-driving vehicles,” Digit. Commun. Networks, vol. 3, no. 3,
pp. 180–187, 2017.
[34] T.-C. Au, N. Shahidi, and P. Stone, “Enforcing Liveness in
Autonomous Traffic Management,” AAAI’11 Proc. Twenty-Fifth
AAAI Conf. Artif. Intell., no. August, pp. 1317–1322, 2011.
[35] D. J. Fagnant and K. Kockelman, “Preparing a nation for
autonomous vehicles: Opportunities, barriers and policy
recommendations,” Transp. Res. Part A Policy Pract., vol. 77, pp.
167–181, 2015.
[36] L. C. Bento, R. Parafita, S. Santos, and U. Nunes, “Intelligent traffic
management at intersections: Legacy mode for vehicles not
equipped with v2v and v2i communications,” in 16th International
IEEE Conference on Intelligent Transportation Systems (ITSC 2013),
2013, pp. 726–731.
[37] M. Guériau, R. Billot, N. E. El Faouzi, J. Monteil, F. Armetta, and S.
Hassas, “How to assess the benefits of connected vehicles? A
simulation framework for the design of cooperative traffic
management strategies,” Transp. Res. Part C Emerg. Technol., vol.
67, pp. 266–279, 2016.
[38] S. El Hamdani and N. Benamar, “A Comprehensive Study of
Intelligent Transportation System Architectures for Road
Congestion Avoidance,” in International Symposium on Ubiquitous
Networking, vol. 10542, Cham: Springer, 2017, pp. 95–106.
[39] P. S. VanMiddlesworth, Mark, Kurt Dresner, “Replacing the Stop
Sign: Unmanaged Intersection Control for Autonomous Vehicles,”
in Proceedings of the 7th international joint conference on
Autonomous agents and multiagent systems-Volume 3, 2008, pp.
1413–1416.
[40] R. Azimi, G. Bhatia, R. Rajkumar, and P. Mudalige, “Ballroom
intersection protocol: Synchronous autonomous driving at
intersections,” Proc. - IEEE 21st Int. Conf. Embed. Real-Time
Comput. Syst. Appl. RTCSA 2015, pp. 167–175, 2015.
[41] D. F. Llorca, V. Milanés, I. P. Alonso, M. Gavilán, I. G. Daza, J.
Pérez, and M. Á. Sotelo, “Autonomous pedestrian collision
avoidance using a fuzzy steering controller,” IEEE Trans. Intell.
Transp. Syst., vol. 12, no. 2, pp. 390–401, 2011.
[42] M. Bagheri, M. Siekkinen, and J. K. Nurminen, “Cellular-based
vehicle to pedestrian (V2P) adaptive communication for collision
avoidance,” 2014 Int. Conf. Connect. Veh. Expo, ICCVE 2014 -
Proc., no. February 2016, pp. 450–456, 2014.
[43] E. Gogou, G. Katsaros, E. Derens, G. Alvarez, P. S. Taoukis, and C.
Chain, “Application of Vehicle to another entity (V2X)
Communications for Motorcycle Crash Avoidance,” J. Intell. Transp.
Syst., vol. 21, no. 285–295, pp. 1–31, 2017.