Abstract:
Before entering cities and highways, autonomous vehicles must be thoroughly tested. Most autonomous vehicle evaluation methods are static and inefficient at generating challenging scenarios for tested vehicles. This paper proposes an adaptive evaluation framework to efficiently evaluate autonomous vehicles in adversarial environments generated by deep reinforcement learning. We use ensemble models to represent different local optimums for diversity in multimodal dangerous scenarios. We cluster adversarial policies using a nonparametric Bayesian method. A typical lane-change scenario with frequent ego vehicle-surrounding vehicle interactions validates the proposed method. Our adversarial scenarios significantly decrease vehicle performance. We demonstrate adversarial environment patterns that can reveal vehicle weaknesses.
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here
