Filtration analysis of pedestrian-vehicle interactions for autonomous vehicle control

Abstract. Interacting with humans remains a challenge for autonomous vehicles (AVs). When a pedestrian wishes to cross the road in front of the vehicle at an unmarked crossing, the pedestrian and AV must compete for the space, which may be considered as a game-theoretic interaction in which one agent must yield to the other. To inform development of new real-time AV controllers in this setting, this study collects and analy- ses detailed, manually-annotated, temporal data from real-world human road crossings as they interact with manual drive vehicles. It studies the temporal orderings (filtrations) in which features are revealed to the ve- hicle and their informativeness over time. It presents a new framework suggesting how optimal stopping controllers may then use such data to enable an AV to decide when to act (by speeding up, slowing down, or otherwise signalling intent to the pedestrian) or alternatively, to continue at its current speed in order to gather additional information from new features, including signals from that pedestrian, before acting itself.

[1]  Wendy Ju,et al.  Ghost driver: A field study investigating the interaction between pedestrians and driverless vehicles , 2016, 2016 25th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN).

[2]  Jacques M. B. Terken,et al.  Pedestrian Interaction with Vehicles: Roles of Explicit and Implicit Communication , 2017, AutomotiveUI.

[3]  Stefania Bandini,et al.  Towards Modelling Pedestrian-Vehicle Interactions: Empirical Study on Urban Unsignalized Intersection , 2016, ArXiv.

[4]  John K. Tsotsos,et al.  Agreeing to cross: How drivers and pedestrians communicate , 2017, 2017 IEEE Intelligent Vehicles Symposium (IV).

[5]  Shrikanth V. Mamidipalli.  A Review of Analysis Techniques and Data Collection Methods for Modeling Pedestrian Crossing Behaviors , 2015 .

[6]  Natasha Merat,et al.  When Should the Chicken Cross the Road? - Game Theory for Autonomous Vehicle - Human Interactions , 2018, VEHITS.

[7]  Irene Gohl,et al.  Analyzing driver-pedestrian interaction at crosswalks: A contribution to autonomous driving in urban environments , 2016, 2016 IEEE Intelligent Vehicles Symposium (IV).

[8]  Valentina Basarić,et al.  PEDESTRIAN CROSSING BEHAVIOUR AT UNSIGNALIZED CROSSINGS 1 , 2017 .

[9]  George Yannis,et al.  Pedestrian Risk Taking While Road Crossing: A Comparison of Observed and Declared Behaviour , 2016 .

[10]  Shinpei Kato,et al.  An Open Approach to Autonomous Vehicles , 2015, IEEE Micro.

[11]  Nicolas Guéguen,et al.  A pedestrian’s stare and drivers’ stopping behavior: A field experiment at the pedestrian crossing , 2015 .

[12]  John K. Tsotsos,et al.  Understanding Pedestrian Behavior in Complex Traffic Scenes , 2018, IEEE Transactions on Intelligent Vehicles.

[13]  Guangquan Lu,et al.  Modeling Crossing Behavior of Drivers at Unsignalized Intersections with Consideration of Risk Perception , 2017 .

[14]  Ananthan K. Pillai,et al.  Virtual Reality based Study to Analyse Pedestrian attitude towards Autonomous Vehicles , 2017 .

[15]  M. Humphery‐Jenner.  Optimal VWAP Trading Under Noisy Conditions , 2011 .

[16]  Natasha Merat,et al.  Empirical game theory of pedestrian interaction for autonomous vehicles , 2018 .