Multi-Adversarial Safety Analysis for Autonomous Vehicles

TL;DR

This paper explores a reachability-based safety analysis for autonomous vehicles in multi-agent scenarios, using differential games to model interactions and improve safety guarantees with less conservativeness.

Contribution

It introduces a novel modeling strategy for multi-agent safety analysis that accounts for subtle interactions and compares Hamiltonian results to baseline methods.

Findings

Modeling strategies significantly affect safety behavior.

Proposed approach reduces conservativeness in Hamilton-Jacobi analysis.

Enhanced safety guarantees during autonomous navigation.

Abstract

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.