Trustworthy Human-AI Collaboration: Reinforcement Learning with Human Feedback and Physics Knowledge for Safe Autonomous Driving

TL;DR

This paper introduces PE-RLHF, a physics-enhanced reinforcement learning framework with human feedback, ensuring safe, trustworthy autonomous driving even with imperfect human input by integrating physics knowledge and dynamic human-AI collaboration.

Contribution

The paper proposes PE-RLHF, a novel framework combining physics knowledge and human feedback in reinforcement learning for autonomous driving, guaranteeing baseline safety and improving performance.

Findings

PE-RLHF outperforms traditional methods in safety and efficiency.

It maintains performance even with poor human feedback.

The approach generalizes well across diverse driving scenarios.

Abstract

In the field of autonomous driving, developing safe and trustworthy autonomous driving policies remains a significant challenge. Recently, Reinforcement Learning with Human Feedback (RLHF) has attracted substantial attention due to its potential to enhance training safety and sampling efficiency. Nevertheless, existing RLHF-enabled methods often falter when faced with imperfect human demonstrations, potentially leading to training oscillations or even worse performance than rule-based approaches. Inspired by the human learning process, we propose Physics-enhanced Reinforcement Learning with Human Feedback (PE-RLHF). This novel framework synergistically integrates human feedback (e.g., human intervention and demonstration) and physics knowledge (e.g., traffic flow model) into the training loop of reinforcement learning. The key advantage of PE-RLHF is its guarantee that the learned policy will perform at least as well as the given physics-based policy, even when human feedback quality deteriorates, thus ensuring trustworthy safety improvements. PE-RLHF introduces a Physics-enhanced Human-AI (PE-HAI) collaborative paradigm for dynamic action selection between human and physics-based actions, employs a reward-free approach with a proxy value function to capture human preferences, and incorporates a minimal intervention mechanism to reduce the cognitive load on human mentors. Extensive experiments across diverse driving scenarios demonstrate that PE-RLHF significantly outperforms traditional methods, achieving state-of-the-art (SOTA) performance in safety, efficiency, and generalizability, even with varying quality of human feedback. The philosophy behind PE-RLHF not only advances autonomous driving technology but can also offer valuable insights for other safety-critical domains. Demo video and code are available at: \https://zilin-huang.github.io/PE-RLHF-website/