Multi-Adversarial Safety Analysis for Autonomous Vehicles
This addresses safety verification for autonomous vehicles in complex, multi-agent environments, but appears incremental as it builds on existing reachability-based methods.
The paper tackles safety analysis for autonomous vehicles in multi-agent driving scenarios by formulating it as a differential game, proposing a modeling strategy to account for subtle agent interactions, and aims to reduce conservativeness in Hamilton-Jacobi analysis to improve safety guarantees.
This work in progress considers reachability-based safety analysis in the domain of autonomous driving in multi-agent systems. We formulate the safety problem for a car following scenario as a differential game and study how different modelling strategies yield very different behaviors regardless of the validity of the strategies in other scenarios. Given the nature of real-life driving scenarios, we propose a modeling strategy in our formulation that accounts for subtle interactions between agents, and compare its Hamiltonian results to other baselines. Our formulation encourages reduction of conservativeness in Hamilton-Jacobi safety analysis to provide better safety guarantees during navigation.