Autonomous vehicles must be comprehensively evaluated before deployed in cities and highways. However, most existing evaluation approaches for autonomous vehicles are static and lack adaptability, so they are usually inefficient in generating challenging scenarios for tested vehicles. In this paper, we propose an adaptive evaluation framework to efficiently evaluate autonomous vehicles in adversarial environments generated by deep reinforcement learning. Considering the multimodal nature of dangerous scenarios, we use ensemble models to represent different local optimums for diversity. We then utilize a nonparametric Bayesian method to cluster the adversarial policies. The proposed method is validated in a typical lane-change scenario that involves frequent interactions between the ego vehicle and the surrounding vehicles. Results show that the adversarial scenarios generated by our method significantly degrade the performance of the tested vehicles. We also illustrate different patterns of generated adversarial environments, which can be used to infer the weaknesses of the tested vehicles.
Adversarial Evaluation of Autonomous Vehicles in Lane-Change Scenarios
IEEE Transactions on Intelligent Transportation Systems ; 23 , 8 ; 10333-10342
2022-08-01
1899343 byte
Article (Journal)
Electronic Resource
English
ADVERSARIAL SCENARIOS FOR SAFETY TESTING OF AUTONOMOUS VEHICLES
European Patent Office | 2021
|Adversarial scenarios for safety testing of autonomous vehicles
European Patent Office | 2024
|ADVERSARIAL SCENARIOS FOR SAFETY TESTING OF AUTONOMOUS VEHICLES
European Patent Office | 2023
|Adversarial scenarios for safety testing of autonomous vehicles
European Patent Office | 2023
|