Interacting safely with cyclists using Hamilton-Jacobi reachability and reinforcement learning

TL;DR

This paper introduces a novel framework combining Hamilton-Jacobi reachability and reinforcement learning to enable autonomous vehicles to interact safely and efficiently with cyclists, accounting for human behavior and providing safety guarantees.

Contribution

The paper presents an integrated approach that combines safety analysis with reinforcement learning, modeling cyclist responses for improved autonomous vehicle interactions.

Findings

The framework achieves safety guarantees in simulated interactions.

It outperforms existing methods in efficiency and safety metrics.

The approach effectively models cyclist behavior and human comfort considerations.

Abstract

In this paper, we present a framework for enabling autonomous vehicles to interact with cyclists in a manner that balances safety and optimality. The approach integrates Hamilton-Jacobi reachability analysis with deep Q-learning to jointly address safety guarantees and time-efficient navigation. A value function is computed as the solution to a time-dependent Hamilton-Jacobi-Bellman inequality, providing a quantitative measure of safety for each system state. This safety metric is incorporated as a structured reward signal within a reinforcement learning framework. The method further models the cyclist's latent response to the vehicle, allowing disturbance inputs to reflect human comfort and behavioral adaptation. The proposed framework is evaluated through simulation and comparison with human driving behavior and an existing state-of-the-art method.