Simulation of pedestrian interaction with autonomous vehicles via social force model

Abstract

Simulation of pedestrian motion in urban traffic networks is crucial for designing autonomous vehicle systems. In a mixed traffic system, a complex interaction occurs between a pedestrian and a vehicle. To understand this interaction pattern and evaluate traffic safety analysis, a simulation tool can be useful. It can help autonomous vehicle designers to visualize pedestrian and vehicle trajectory, extract velocity and acceleration profile of both agents, test different autonomous vehicle planning algorithms, and assess the traffic safety in severe traffic conflicts. This paper presents a rule-based social force model to simulate pedestrian trajectories during interaction with an autonomous vehicle. The social force model is then integrated with an autonomous vehicle control and planning algorithm for simulating the behavior of both pedestrian and vehicle in traffic conflicts by varying different parameters such as agent's initial speed, different vehicle sensor types (error percentage of pedestrian detection varies), different pedestrian types (risk-taking, cautious, and distracted), etc. This simulation tool provides minimum distance accepted by a pedestrian during a road crossing scenario as output. Additionally, the simulation illustrates the impact of vehicle initial speed on crossing decision and minimum distance accepted by pedestrians before crossing. The simulation tool can be useful to simulate risky interaction scenarios to understand the effectiveness of autonomous vehicle planning algorithm while interacting with different types of pedestrians.