Ning, Haijing (Chang'an University), Wei, Yaxin (Chang'an University), An, Dier (Dalian Maritime University), Li, Ting (Chang'an University), Liu, Shumei (Chang'an University), An, Yisheng (Chang'an University)

Qualitative Fault Diagnosis of Autonomous Emergency Braking System Based on Partially Observable Petri Nets

Scheduled for presentation during the Regular Session "Advanced Vehicle Safety Systems I" (WeBT8), Wednesday, September 25, 2024, 15:10−15:30, Salon 16

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 December 26, 2024

Abstract

Autonomous Emergency Braking (AEB) system can issue early warnings or execute brakes in emergency situations, effectively avoiding collision accidents. However, faults during AEB operation will pose a great threat to driving safety, making it essential to diagnose faults in the AEB system. Additionally, when the AEB system malfunctions, drivers can only observe restricted output states, which makes it difficult to diagnose the specific faults within the AEB system. Faced with this challenge, this paper proposes a qualitative fault diagnosis method for the AEB system based on the Partially Observable Petri Nets (POPN). This method first models the AEB system based on POPN. Next, an AEB system observer is designed to estimate the entire state based on the observable outputs. On this basis, a fault diagnosis scheme for the AEB system is proposed, which uses the residuals of the entire state between the normal AEB system and the tested AEB system to diagnose event or state faults within the tested AEB system. Finally, experimental verification demonstrates the effectiveness of the proposed method.