A Novel Simulation Framework for Adaptive Stress Testing of Autonomous Driving Systems

Abstract

Identifying vulnerable scenarios is of great importance in autonomous vehicles (AVs) and other safety-critical systems. Since failure events are rare, naive random search approaches require a large number of vehicle operation hours to identify potential system failures. Adaptive Stress Testing (AST) is a method addressing this constraint by effectively exploring the failure trajectories of AV using a Markov decision process and employs reinforcement learning techniques to identify driving scenarios with high probability of failures. However, existing AST frameworks are able to handle only simple scenarios, such as one vehicle moving longitudinally on a single lane road which is not realistic and has a limited applicability. In this article, we propose a novel AST framework to systematically explore corner cases of intelligent driving models that can result in safety concerns involving both longitudinal and lateral vehicle.s movements. Specially, we develop a new reward function for Deep Reinforcement Learning to guide the AST in identifying crash scenarios based on the collision probability estimate between the autonomous driving system under test (i.e., the ego vehicle) and the trajectory of other vehicles on the multilane roads, as well as pedestrian and complex traffic interactions at an intersection with traffic lights. To demonstrate the effectiveness of our framework, we tested it with a complex driving model vehicle that can be controlled in both longitudinal and lateral directions. Quantitative and qualitative analyses of our experimental results demonstrate that our framework outperforms the state-of-the-art AST scheme in identifying corner cases with complex driving maneuvers.