Autonomous Vehicle–Pedestrian Interaction Modeling Platform: A Case Study in Four Major Cities

Abstract

Accurately evaluating the safety effects of autonomous vehicles (AVs) has become more pressing with the increased adoption rate of AVs. This study utilizes a multiagent adversarial inverse reinforcement learning (MAAIRL) framework for modeling the interactions between AVs and pedestrians in four different cities: Boston, Las Vegas, Pittsburgh, and Singapore. Multiagent actor-critic with Kronecker factors deep reinforcement learning (MACK DRL), a paradigm that extends deep reinforcement learning (DRL), was used to model the behavior of both AVs and pedestrians and to determine their policies and collision avoidance strategies. Simulated trajectories are compared to actual trajectories and the results are evaluated to analyze the behavior of both AVs and pedestrians in terms of their evasive actions such as swerving, accelerating, or decelerating. The multiagent model provides a more comprehensive insight into how road users act in situations of conflict and accounts for changes in the environment. The study also shows that the level of competition between AVs and pedestrians varies significantly across different cities. Las Vegas has the most competitive relationship between AVs and pedestrians, while Singapore has the least competitive environment. The study also highlights the importance of cooperative behavior, particularly in yielding to pedestrians, in reducing the level of competition between AVs and pedestrians. In summary, this research provides valuable insights into the behavior of AVs and pedestrians and can be used to inform the development of more efficient and safe autonomous mobility systems.