You are on page 1of 7

See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/335364048

Management of Potential Conflicts between Pedestrians and Autonomous


Vehicles

Conference Paper · May 2019


DOI: 10.1109/SCSP.2019.8805678

CITATIONS READS
0 62

2 authors, including:

Csaba Csiszar
Budapest University of Technology and Economics
100 PUBLICATIONS   326 CITATIONS   

SEE PROFILE

Some of the authors of this publication are also working on these related projects:

PASSENGER HANDLING FUNCTIONS IN AUTONOMOUS PUBLIC TRANSPORTATION View project

Method for selection of appropriate location of charging stations for electric vehicles View project

All content following this page was uploaded by Csaba Csiszar on 27 August 2019.

The user has requested enhancement of the downloaded file.


Smart Cities Symposium Prague 2019

Management of Potential Conflicts between


Pedestrians and Autonomous Vehicles
Summair Anis, Csaba Csiszár

This research is focused on the ranking of conflict factors


Abstract— Pedestrians are the most vulnerable road users. using multi-criteria analysis method. The input is taken from
There are a lot of studies regarding the interaction of pedestrians the stakeholders; who are professionals in the field of AVs and
with conventional vehicles, but the way a pedestrian interacts with transportation technology. These are identified based on the
Autonomous Vehicles (AVs) still needs to be explored. Therefore,
group discussions with the colleagues working in the same
this study addresses identification, prioritization, and
management of conflict situation types between AVs and field. Their input is taken via questionnaire survey.
pedestrians. For this purpose, an analytical hierarchical process Accordingly, improvements to the road infrastructure are
(AHP) method is applied to analyze qualitative data sets of a suggested in order to accommodate AVs. In this way, relevant
questionnaire survey. The factors (e.g. decision making by AVs knowledge about the pedestrians can be provided to the vehicle
according to varying pedestrian behavior, limitations of the road industry as well as to the authorities in order to improve the
infrastructure in terms of conflict generation, etc.) that cause these
conditions for non-motorized road users.
conflict situations are ranked and compared. The input is taken
from the key stakeholders (professionals), and the results are A brief overview of the current literature and identification
analyzed using multi-criteria analysis method (AHP). It has been of the research gap have been presented in section II. Based on
found that the most important factor to be considered is the the literature review, our research objective has been identified
decision-making ability of the AVs, according to the varying in the section III. In order to accomplish these objectives, a
pedestrian behavior. Based on the ranking of factors, mitigation methodological framework has been defined in section IV.
measures are recommended to eradicate the effects of the factors.
Results of data collection and analysis along with the mitigation
Index Terms— autonomous vehicles (AVs), pedestrian, conflict,
linear rating, relative rating, stakeholders (professionals) measures has been summarized in section V. Based on these
results, major conclusions and some recommendations in the
I. INTRODUCTION form of future applications have been presented in section VI.

P EDESTRAINS are considered to be at a greater risk of road


accidents; especially in the developing countries. The major
reasons for the accidents include road geometrical design
II. LITERATURE REVIEW
The research gap has been identified according to the current
problems (poor sight distances, slippery pavements, etc.), law literature. Pedestrian behavior has already been studied in many
violations by pedestrians (J-walkers) and drivers, poor weather papers to eliminate the conflicts between conventional vehicles
conditions, etc. [1]. According to the report published by the and pedestrians. The drivers of the conventional vehicles are
World Health Organization, about 1.2 million road users die able to react to the unexpected events, but AVs only react to the
each year, 22% of which are non-motorized road users. This pre-programmed situations. Therefore, the ability of AVs to
situation is the worst in low income countries [2]. respond to these unexpected events caused by varying behavior
With the introduction of AVs, it can be changed. The most of pedestrians still needs to be studied and improved. The most
important factor to be considered for the successful operation relevant research results achieved so far are summarized:
of AVs is the collision avoidance decision. Maneuvering either A. Understanding Pedestrian Behavior
toward other vehicles (bikes, cars, buses, etc.) or toward
Factors that may alter the decision making of the pedestrian
pedestrians are critical and represent a significant risk [3].
while crossing the road have been identified [6]. Pedestrian
Consequently, these conflict situations should be identified, and
behavior at different situations have been recorded and
suitable mitigation measures should be elaborated to reduce the
compared with the suggested behavior from the literature. It
risk of accidents [4].
was concluded that prediction of pedestrian movement patterns
It is currently impossible to understand the pattern of
is a rather complex task, but an average behavior can be
pedestrian movements and program every situation into the
determined and programmed to the AVs.
AVs. Therefore, the pedestrian behavior should be investigated
to reveal how they interact with the vehicular traffic and road
infrastructure [5].

S. Anis and Cs. Csiszár are with the Department of Transport Technology (BME), Budapest, Hungary (e-mails: summairuetian66@gmail.com,
and Economics (KUKG), Faculty of Transportation Engineering and Vehicle csiszar.csaba@mail.bme.hu).
Engineering (KJK), Budapest University of Technology and Economics The publication of the work reported herein has been supported by ETDB at
BME.

978-1-7281-0497-3/19/$31.00 ©2019 European Union


B. Introducing Driverless Cars • AV side:
Interaction of AVs with the road users has been summarized o limitations to recognize non-motorized road
[7]. A list of questions for each conflict situation is prepared users as pedestrians;
and presented to different road users. Each question represents o imperfections of AVs in decision making and
a conflict situation with the AVs. It is concluded that the the barriers for its operation in road
successful operation of AVs in an urban environment is infrastructure (e.g. poor lighting, lane
possible by carrying out suggested improvements (e.g. marking, pedestrian infrastructure, etc.);
installation of variable message signs for the pedestrians, o provision of mitigation measures based on
making zebra crossing safer, etc.) in road infrastructure. questionnaire survey results.
C. Barriers for the Operation of AVs IV. METHODOLOGICAL FRAMEWORK
Potential threats and opportunities for the operation of AVs
The research is divided into four phases as presented in Fig.
have been identified [8] by the evaluation of current literature.
1.
It has been concluded that operation of AVs requires special
changes in the transport infrastructure like provision of
Phase I (Scope Definition)
charging points, designated parking spaces, a centralized
Literature Review
information management system, etc. Several changes in the
road policy are also recommended to accommodate the AVs.
Current Accident
Reserach Reports
D. Passengers Trust on AVs
Accident Stats
Reliability and passenger trust of the driverless cars have Pedestrian Safety
AV-Pedestrian
been evaluated [9]. In this research, two prototypes of AVs with Conflicts
different configurations (one with fully automated and one Previous Methodology
Future Work
semi-automated) are applied. Real world scenarios are
simulated under these conditions and the behaviors of
passengers are observed. The level of satisfaction and reliability LEGEND
are investigated in different conflict conditions. It has been Phase II (Data Collection) INPUT

Questionnaire Surveys
concluded that most of the respondents feel more comfortable PROCESS
with using the semi-automated AV. AHP Method
It is found that these conflicts should be identified and Data Sets
prioritized, in order to increase the safety for non-motorized Prioritization of Conflict
Factors OUTPUT
road users. This prioritization can be done by taking opinions Stakeholders Input
Suggested Mitigation
from the stakeholders working in this field. The best tool to Measures NEXT STEP

accomplish this task is the questionnaire survey. The survey TWO WAY CONNECTION

results highlight the major improvement opportunities to be INPUT FROM PREVIOUS STEP
carried out in the road infrastructure. The results also highlight Phase III (Data Analysis)
important aspects of pedestrian behaviors that needs to be AHP Method
Normalization of Datasets
studied, in terms of their interactions with AVs. In this way, Calculation of Weight Factors
safe and efficient operation of AVs can be achieved. Determination of Qualities
Estimation of Choice Probabilities

III. RESEARCH OBJECTIVE


Phase IV
The research objective is the identification of the factors, Conclusions
from the previous studies and the questionnaire survey, which
produce the conflicts between pedestrians and AVs. It is also
important to prioritize them based on their importance through Recommendations
the AHP method. For this purpose, factors are identified, and
these are further segregated into sub-factors (appendix I). The Fig. 1. Methodological framework
factors are assigned to either the AV or pedestrian side as
follows: A. Data Collection (Phase II):
• pedestrian side: The input from the key stakeholders (Fig. 2.) were taken via
o illegal crossing (especially with a drunk or questionnaire survey. It was sent to them as a Google form. The
tired condition); stated preferences were revealed. Although 50 respondents
o collision avoidance decisions by the were targeted, 20 responses were received and analyzed. This
pedestrians; input from the stakeholders is analyzed using the AHP method
o imperfections in the road infrastructure in for the prioritization of conflicts and presentation of mitigation
terms of conflict generation. measures in the next phase.
B. Normalization of Data Sets and Calculation of Weights:
Universities Tables have been prepared for each factor. The normalization
of the dataset has been done by dividing each entity in the table
Research by the sum of the corresponding column. This is done by using
Academia
Institutes (1) given below:

Organizations N’ij = ∑ (1)


Stake Holders

Vehicle
where:
Industry
Industry N’ij are values of entries in the table after normalization,
Transport Nij are the original values of the entries,
Operator ΣNj is the sum of all the entries in a column.
Weightage factors are determined for sub-factors, which are
Fig. 2. Identified key stakeholders for questionnaire survey represented by a row in each table, using (2):
B. Data Analysis (Phase III):

Several techniques can be applied to analyze data, including gi= (2)
mutual correspondences, regression analyses, AHP methods,
etc. Among these different techniques, AHP methods are where:
effective for use when a rating of factors according to their gi is the weight factor for sub factors,
comparison with other factors is needed. Using the AHP ∑N’i is the sum of the normalized values in each row,
method, the final goal is the calculation of choice probabilities n is the total number of entries in each row.
of factors based on the sub-factors. For this purpose, different C. Calculation of Qualities:
steps (e.g. normalization, weight factor calculations, etc.) have
been carried out as explained in section V. The term “quality” is a standard term used in an AHP. This
term represents the effect of a sub-factor on the particular
V. RESULTS & DISCUSSION factor, according to the weightage. Quality is further used for
the calculation of choice probability of factors. The calculated
A. Application of AHP Method: quality values are presented in Table I and Table II. The quality
Two tables are filled with factors from the stakeholders. In values are determined as follows (3):
the first table, each factor is rated from 1-5 according to the
importance. This table gives linear ratings. In the second table, Qi = ∑ g ∗ r (3)
each factor is compared with the other one and the score from
1-5 is given as relative importance. This table gives relative where:
ratings [10]. The rating scale of 1-5 represents the following Qi is the quality value for each factor,
values: gi is the weight factor for each sub-factor,
1. not important, ri is the linear rating of each sub-factor (this represents
2. less important, the scoring of each sub-factor based on its own
3. equal weightage, uniqueness without the comparison with other sub-
4. important, factors).
5. very important. In Table I, sub-factors are given by their codes (see appendix
I). Linear rating values are indicated by ri, while relative rating
values are indicated by gi.
TABLE I
QUALITIES OF PEDESTRIAN SIDE FACTORS
Illegal Crossings Collision Avoidance Decisions Drunk/ Tired Pedestrians Poor Road Infrastructure
Factors Factors Factors Factors
ri gi ri gi ri gi ri gi
Codes Codes Codes Codes
P.1.1 4.1 0.64 P.2.1 3.7 0.88 P.3.1 4.3 0.28 P.4.1 4.1 0.13
P.1.2 3.2 0.44 P.2.2 4.3 1.14 P.3.2 3.8 0.23 P.4.2 3.7 0.14
P.1.3 4.3 1.04 P.2.3 3.5 0.99 P.3.3 3.1 0.22 P.4.3 3.2 0.14
P.1.4 4.1 0.80 P.2.4 4 0.86 P.3.4 3.5 0.27 P.4.4 3.6 0.14
P.1.5 2.7 0.38 P.4.5 3.8 0.13
P.1.6 3.3 0.43 P.4.6 3.5 0.10
P.4.7 4 0.13
P.4.8 3.4 0.10
Qi 3.72 3.87 3.70 3.67
TABLE II Conflict Factors
QUALITIES OF AV SIDE FACTORS
Identification of Collision Avoidance Barriers for the Analysis of factors on Analysis of factors on AV
Pedestrians Decisions Operation Pedestrian Side Side
Factors Factors Factors
ri gi ri gi ri gi
Codes Codes Codes
A.1.1 3.4 0.75 A.2.1 4 0.25 A.3.1 4.2 0.18 Calculation of Choice Probabilities
A.1.2 3.7 1.04 A.2.2 4.1 0.27 A.3.2 3.5 0.17
A.1.3 3.1 0.88 A.2.3 4.3 0.26 A.3.3 3.2 0.15 Factors Sub-Factor
A.1.4 2.9 0.62 A.2.4 4 0.22 A.3.4 3.1 0.19
A.3.5 4.6 0.14
NO Are Values of Choice Are Values of weights NO
A.3.6 4.7 0.18
Probability >10% >10%
Qi 3.29 4.10 3.87

YES YES
D. Calculation of Choice Probabilities:
Severity Levels:
In order to determine the relative importance of the factors, >10% - < 30%----------Less Important
Particular Sub-Factor to be
Ignored, >30% - < 50%-----------------Important
the choice probability values are calculated. It shows the Not Important >50% - < 70%----------Very Important
Ignored,
Not Important
percentage by which one factor is more important than others. >70% - < 90%------- Actions Required
>90%---Top Priority, Immediate Actions
It can be calculated by (4): LEGEND

Decision Making
Mitigation
Measures
Pi = ∑ (4) Process

Fig. 3. Decision making process regarding conflict factors


where: F. Suggested Mitigation Measures:
Pi is the choice probability of a factor, Severity levels provide the decision makers with the
Qi are quality values for each factor. information about which factor should be considered
Using eq. 4, choice probabilities are calculated, and these are immediately for the mitigation. Severity levels have been
presented in Table III. defined in the Table IV.
TABLE III
TABLE IV
CALCULATED CHOICE PROBABILITIES
SEVERITY LEVELS OF CONFLICT FACTORS
Choice
Quality Choice
Factors Probability Severity
(Qi) Factors for Main-Categories Probability
(Pi) Levels
(%)
Pedestrian Side Illegal Crossings by Pedestrians 13.61 Important
Illegal Crossings 3.72 13.61 Collision Avoidance Decisions by
Pedestrian

Collision Avoidance Decisions 3.87 15.67 15.67 Important


Pedestrians
Drunk/Tired Pedestrians 3.70 13.29 Drunk/Tired Pedestrians 13.29 Important
Side

Poor Road Infrastructure 3.67 12.94 Poor Road Infrastructure 12.94 Important
AV Side
Identification of Pedestrians by AVs 8.83 Ignored
Identification of Pedestrians 3.29 8.83
Side

Collision Avoidance Decisions by AVs 19.89 Important


AV

Collision Avoidance Decisions 4.10 19.89


Barriers for the Operation of AVs 15.78 Important
Barriers for the Operation 3.87 15.78
SUM 100
The closer values of choice probabilities (Table IV) represent
that all categories are important, except identification of
E. Evaluation Criteria: pedestrians by AVs. Accordingly, certain mitigation measures
The flowchart (Fig. 3.) represents the decision-making have been presented in Table V, where the sub-factors are
process, in order to evaluate the results and decide which factors represented by their code (Appendix I). The proposed
are to be considered. Thus, factors and sub-factors are evaluated mitigation measures have been derived from the literature, as
based on the values of choice probabilities and weights, well as the opinion of the stakeholders, to minimize each
respectively. If these values are less than 10%, they are simply conflict factor in most of the cases. Colors represent the
Ignored. following:
However, it is still important to check the sub-factors • red (immediate action is required),
according to same criteria using weights, and relevant • yellow (important factor),
mitigation measures are provided. For values more than 10%, • green (not important, and it can be Ignored).
three levels are defined according to different studies. This
criteria of 10% is applied while keeping in mind the concept of
road design where an error of 10% is allowed. A similar concept
is applied here.
TABLE V VI. CONCLUSIONS
SUGGESTED MITIGATION MEASURES
Weight This research provides the prioritized conflict factors for
Factors Mitigation Measures
(%) interactions between AVs and pedestrians. AVs technology is
P.1.1 15.49 • Enforcement of Traffic Laws still relatively new and under development, and this research is
• Penalties for the violation
focused on the pedestrian-AVs interactions. The main
P.1. Illegal Crossings by

P.1.2 13.72 • Installation of guard rails


• Installing automatic gates at the public contribution of this research is provision of mitigation measures
Pedestrians

P.1.3 24.19 transit stops for the prioritized factors. It can be decided which factors are to
P.1.4 19.54 • Installation of variable message signs be considered for mitigation in the long term and short term
• Coding of pedestrian behavioral data
P.1.5 13.97 into the AVs
based on the severity levels.
• Improvement of the ability of AVs to As a result of questionnaire survey the following key findings
P.1.6 13.08 locate (and apply breaks automatically are identified:
upon seeing) a pedestrian • The most important factors which cause conflicts
• Teaching pedestrians for improvement
Decisions by Pedestrians
A.2. Collision Avoidance P.2. Collision Avoidance

P.2.1 23.83 of road crossing behavior between pedestrians and AVs are the decision making
• Increasing awareness regarding road abilities of AVs and road crossing behavior of the
P.2.2 26.40 safety pedestrians.
• Observation of pedestrian movement
trajectories over time and programming
• It has been identified that current road structure is
P.2.3 28.30
them into the AVs suitable for the operation of AVs; only a few
P.2.4 21.47 • Provision of separated pedestrian modifications are required.
facilities (underpass/overpass)
• Applications of suggested mitigation measures in the
• Separation of pedestrian and normal
A.2.1 25.30 traffic during peak periods physical form can guarantee the successful operation of
Decisions by AVs

• Programming of the AVs for AVs.


A.2.2 27.04 unpredictable situations During the survey, it was identified that a separate study on
• Sending of bugs and error reports to
developers immediately
the evaluation of human behavior towards the adoption of AVs
A.2.3 25.73
• Collection of real time data and solving must be conducted. The results of this research can be used to
A.2.4 21.93 situational problems automatically by evaluate the highlighted factors by further classification of the
AVs; for provision of suitable solutions sub-factors. In this way, the development of computer
• Allocation of special care hours during
P.3.1 27.71 night when drivers should drive more simulations in different software can be facilitated.
P.3, Drunk/Tired

Furthermore, these results can be used within the vehicle


Pedestrians

carefully especially in the city centers


P.3.2 22.89 • Diversion of normal traffic from city industries and government departments for carrying out
centers or rush areas to the main roads to
minimize conflicts
relevant measures.
P.3.3 22.28
• Application of efficient traffic
P.3.4 27.13 management strategies REFERENCES
P.4.1 13.20
[1] L.F. Miranda-Moreno, O. Morency, and A.M. El-Geneidy,
P.4.2 13.64 • Scheduled and routine maintenance “The link between built environment, pedestrian activity
P.4. Poor Road
Infrastructure

P.4.3 13.81 activities for road infrastructure


P.4.4 13.88 • Application of different traffic calming
and pedestrian–vehicle collision occurrence at signalized
P.4.5 12.55 techniques intersections,” Accident Analysis & Prevention, vol 43, no.
P.4.6 9.65 • Installation of proper signs especially 5, pp. 1624–1634, 2011. DOI: 10.1016/j.aap.2011.02.005
near the construction zone [2] S. Ye, L. Wangg, K.H. Cheong, and N, Xie, “Pedestrian
P.4.7 13.50
• Improvement of the ability of AVs to Group-Crossing Behavior Modeling and Simulation Based
P.4.8 9.77 operate under poor weather conditions
A.3.1 17.87 • Judgment by AVs of real traffic on Multidimensional Dirty Faces Gam,” Complexity.
the Operation of
A.3. Barriers for

A.3.2 16.83 conditions even if the traffic signals are not 2017. DOI: 10.1155/2017/1723728
A.3.3 14.94 working [3] D.F. Llorca, V. Milanes, I.P. Alonso, M. Gavilan, I.G.
AVs

A.3.4 18.59 • Improvement of the hazard management Daza, J. Perez, and M.Á. Sotelo, “Autonomous Pedestrian
system for the AVs
A.3.5 14.21 Collision Avoidance sing a Fuzzy Steering Controller,”
A.3.6 17.57 IEEE Transactions on Intelligent Transportation Systems,
• Automatic repair system for AVs to vol. 12, no. 2, pp. 390-401. 2011. DOI:
determine and restore faults automatically.
• Ability of the AVs to send error reports
10.1109/TITS.2010.2091272
to the developers in case of failure [4] J. Levinson, J. Askelnad, J. Becnker, J. Dolson, D. Held,
A.1. Identification of

• Installation of extra cameras for the AVs S. Kammel, J.Z. Kolter, D. Langer, O. Pink, V. Pratt, M.
Pedestrians by AVs

in case of main cameras not working. Sokolsky, G. Stanek, D. Stavens, A. Teichman, M.


• Automatic cleaning mechanism for Werling, and S. Thrun, “Towards fully autonomous
A.1.1 22.16 cameras to clean if they are covered with
fog, water etc. driving: Systems and algorithms,” in Intelligent Vehicles
• Coding each and every aspect of Symposium (IV). Baden Germany, 5-6 June 2011. DOI:
pedestrian movements and interaction to 10.1109/IVS.2011.5940562
the AVs, to identify each and every [5] Zs. Szalay, T. Tettamanti, D. Esztergár-Kiss, I. Varga, and
behavior of pedestrians. This is important
for the differentiation of pedestrians from C. Bartolini, “Development of a Test Track for Driverless
the normal traffic. Cars: Vehicle Design, Track Configuration, and Liability
Considerations,” Periodica Polytechnica Transportation APPENDIX I:
Engineering vol. 6, no. 1, pp. 29-35. 2018. DOI: (FACTOR CODES)
10.3311/PPtr.10753. The table below represents the factor codes used in Table I,
[6] A. Rasouli, I. Kotseruba, and J.K. Tsotsos, “Understanding Table II, and Table V.
Pedestrian Behavior in Complex Traffic Scenes,” IEEE
Transactions, Intelligent Vehicles, vol. 3, no. 1, pp. 61-70.
Factor
2018. DOI: 10.1109/TIV.2017.2788193 Code
Factors
[7] J. Parkin, B. Clark, W. Clyton, M. Ricci, and G. Parkhurst, P.1. Illegal crossing by pedestrians
“Understanding interactions between autonomous vehicles
P.1.1 Individual pedestrian crossing at red light:
and other road users: A literature review,”. Technical
Report. University of the West of England, Bristol. 2016. P.1.2 Group of pedestrians crossing at red light:
Available: http://eprints.uwe.ac.uk/29153 Not using the zebra crossing (crossing at the middle of
P.1.3
[8] D.J. Fagnant, and K. Kockelman, “Preparing a nation for intersection/street):
autonomous vehicles: opportunities, barriers and policy P.1.4 Pedestrian appearing suddenly from the back of vehicles:
P.1.5 Crossing between the queue of vehicles:
recommendations,” Transportation Research Part A: P.1.6 Crossing between tram tracks:
Policy and Practice, vol 77, pp. 167–181. 2015. DOI: P.2. Collision avoidance decisions by pedestrians
10.1016/j.tra.2015.04.003 P.2.1 Walking to middle of street and then coming back
[9] S. Nordhoff, B. van Arem, and R. Happee, “Conceptual P.2.2 Jumping forward/backward to avoid accident
P.2.3 Avoiding one vehicle but then moving in front of other
Model to Explain, Predict, and Improve User Acceptance P.2.4 Jumping backward from the edge of a tram platform
of Driverless Podlike Vehicles,” Transportation Research P.3. Hazardous locations for creation of conflicts if pedestrians are
Board, Transportation Research Record, vol 2602, pp. 60– drunk/tired
67. 2016. DOI: 10.3141/2602-08 P.3.1 Intersections
[10] Department of Communities and Local Government, P.3.2 Roads
P.3.3 Tram tracks
“Multi-criteria analysis: a manual,” Technical Report, P.3.4 Tram platforms
London. UK., 2009 ISBN: 978-1-4098-1023-0 P.4. Road environment which causes the conflicts with pedestrians
P.4.1 Invisibility of zebra crossing
P.4.2 Poor lane marking
P.4.3 Fluctuation in signal lights
P.4.4 Inappropriate location of signal lights
P.4.5 Poor sight distance
P.4.6 Slippery pavement
P.4.7 Inappropriate traffic signs
P.4.8 Absence of information management system
A.1. Limitations of AVs in identification of pedestrians under different
sets of conditions
A.1.1 In darkness
A.1.2 In poor weather conditions
A.1.3 Mismatching a group of pedestrians as a vehicle
A.1.4 Individual pedestrian standing
A.2. Decision taken by the AVs to avoid conflict situations
A.2.1 Hitting pedestrian or a vehicle (considering no other choice)
A.2.2 Mid-block pedestrian crossing
A.2.3 Pedestrian crossing at red light
Pedestrian jumps in front of AVs (in the event that the
A.2.4
Pedestrian tries to avoid collision with the other vehicles)
A.3. Limitations of the road infrastructure that causes barriers for the
operation of AVs
A.3.1 Poor street markings
A.3.2 Invisible zebra crossing
A.3.3 Fluctuation in signal lights
A.3.4 Slippery pavement
A.3.5 Inappropriate traffic signs
A.3.6 Absence of proper signs in construction zone

View publication stats

You might also like