Generalization of cut-in pre-crash scenarios for autonomous vehicles based on accident data

Abstract

Abstract The utilization of high-risk test cases constitutes an effective approach to enhance the safety testing of autonomous vehicles (AVs) and enhance their efficiency. This research paper presents a derivation of 2052 high-hazard pre-crash scenarios for testing autonomous driving, which were based on 23 high-hazard cut-in accident scenarios from the National Automobile Accident In-Depth Investigation System (NAIS) through combining importance sampling and combined testing methods. Compared to the direct combination of the original distribution after sampling, the proposed method has a 2.92 times higher crash rate of 69.32% for the test case set in this paper. It also has a 5.8 times higher rate of triggering Automatic Emergency Braking (AEB), improving hazardous scenario coverage. Using the proposed method, the generated parameters of the cut-in accident scenario test set were compared with those of the cut-in test scenarios included in existing Chinese autonomous driving test protocols and standards. The velocity of the ego-vehicle obtained using the proposed method matched those in the existing protocols, whereas the velocity, time gap, and time to collision of the target vehicle were significantly lower than those existing protocols indicating scenarios obtained from accident data can enrich the selection of testing scenarios for autonomous driving.