I Know You Can't See Me: Dynamic Occlusion-Aware Safety Validation of Strategic Planners for Autonomous Vehicles Using Hypergames

Abstract

A particular challenge for both autonomous and human driving is dealing with risk associated with dynamic occlusion, i.e., occlusion caused by other vehicles in traffic. Based on the theory of hypergames, we develop a novel multi-agent dynamic occlusion risk (DOR) measure for assessing situational risk in dynamic occlusion scenarios. Furthermore, we present a white-box, scenario-based, accelerated safety validation framework for assessing safety of strategic planners in AV. Based on evaluation over a large naturalistic database, our proposed validation method achieves a 4000% speedup compared to direct validation on naturalistic data, a more diverse coverage, and ability to generalize beyond the dataset and generate commonly observed dynamic occlusion crashes in traffic in an automated manner.

arXiv commentThis work is 6 pages long and contains 5 figures. For the supplementary video, see https://youtu.be/-crio3rA_IU

References in corpus (6)

• Accelerated Evaluation of Automated Vehicles Safety in Lane Change Scenarios Based on Importance Sampling Techniques
• Occlusion-Aware Risk Assessment for Autonomous Driving in Urban Environments
• Tackling Occlusions & Limited Sensor Range with Set-based Safety Verification
• Safe Occlusion-aware Autonomous Driving via Game-Theoretic Active Perception
• Scalable End-to-End Autonomous Vehicle Testing via Rare-event Simulation
• Learning Game-Theoretic Models of Multiagent Trajectories Using Implicit Layers

Cited by in corpus (2)

• A Driver-Vehicle Model for ADS Scenario-based Testing
• Self-Improving Safety Performance of Reinforcement Learning Based Driving with Black-Box Verification Algorithms