Hamilton-Jacobi Reachability-Based Safe Reinforcement Learning for Emergency Collision Avoidance

2026-06-13

AI Summary

This work addresses the challenge of emergency obstacle avoidance in extreme driving scenarios, where both obstacle proximity and vehicle dynamic stability must be jointly considered, yet existing approaches lack forward-looking safety guarantees within finite time horizons. The authors propose a lookahead safety mechanism that integrates Hamilton-Jacobi reachability analysis with reinforcement learning. A unified signed safety function is constructed to combine geometric collision margins with chassis stability limits and is embedded into a constrained Markov decision process. By employing PID-Lagrangian policy optimization, the method adaptively tunes the strength of safety constraints and leverages offline extreme-driving data to efficiently approximate the safe set, circumventing the high computational cost of traditional grid-based solutions. Simulations and real-world vehicle experiments demonstrate that the approach significantly improves goal-reaching success rates, generates smoother trajectories, and maintains larger safety margins in low-adhesion obstacle avoidance scenarios.

Abstract

Emergency collision avoidance under extreme driving conditions demands safety-critical control that accounts for both obstacle proximity and vehicle dynamic stability over a future time horizon, yet existing methods often rely on instantaneous or local safety evaluations. This paper proposes a safe reinforcement learning framework guided by a Hamilton-Jacobi (HJ) reachability based motion safety set that provides forward-looking safety supervision for constrained policy optimization. Specifically, a unified signed safety function is formulated by combining geometric collision margins and chassis stability limits, and is then extended through reachability analysis into a finite-horizon motion safety set that characterizes whether safety can be maintained under future vehicle state evolution. To enable practical computation, the motion safety set is approximated from offline extreme driving data, mitigating the computational burden of grid-based HJ solvers. The learned motion safety set is then embedded as a continuous safety cost into a constrained Markov decision process, and a PID-Lagrangian policy optimization scheme is employed to adaptively regulate the Lagrange multiplier for safety constraint enforcement. Simulation and real-vehicle experiments on low-adhesion obstacle-avoidance scenarios demonstrate that the proposed method achieves higher goal-reaching rates, produces smoother avoidance maneuvers, and maintains larger unified safety margins than baseline methods.

Problem

• emergency collision avoidance
• Hamilton-Jacobi reachability
• motion safety
• vehicle dynamic stability
• safe reinforcement learning

Innovation

• Hamilton-Jacobi reachability
• safe reinforcement learning
• motion safety set
• constrained policy optimization
• emergency collision avoidance