Islam, Md Rayhanul (Iowa State University), Wongpiromsarn, Tichakorn (Iowa State University), Basu, Samik (Iowa State University)

Analysis of the Effects of Perception Inconsistency among Interacting Vehicles in Partially Observable Environments

Scheduled for presentation during the Invited Session "Self-Assessment of Perception Systems" (WeAT5), Wednesday, September 25, 2024, 11:50−12:10, Salon 13

2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC), September 24- 27, 2024, Edmonton, Canada

This information is tentative and subject to change. Compiled on October 3, 2024

Abstract

This paper employs formal verification techniques to analyze how inconsistencies in perception and decision-making between autonomous and human-driven vehicles impact system safety. Owing to the partial observability of the environment, autonomous vehicles may maintain a set of transition models to represent the behavior of the environment. We propose an approach to construct a belief environment model from the set of transition models to synthesize policies. The findings show that synthesizing policies without considering other agents' differences in perception and decision-making may increase the probability of making the system unsafe. Finally, this approach is demonstrated using a vehicle simulator, CARLA, to support our findings.