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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Noronha, Aarati Andrea, Oh, Jean
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917284045389824
author Noronha, Aarati Andrea
Oh, Jean
author_facet Noronha, Aarati Andrea
Oh, Jean
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2602_18097
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Interacting safely with cyclists using Hamilton-Jacobi reachability and reinforcement learning
Noronha, Aarati Andrea
Oh, Jean
Robotics
Machine Learning
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.
title Interacting safely with cyclists using Hamilton-Jacobi reachability and reinforcement learning
topic Robotics
Machine Learning
url https://arxiv.org/abs/2602.18097