ROAD: Responsibility-Oriented Reward Design for Reinforcement Learning in Autonomous Driving

TL;DR

This paper presents a responsibility-oriented reward function for reinforcement learning in autonomous driving, integrating traffic regulations via knowledge graphs and vision-language models to improve rule adherence and decision-making.

Contribution

It introduces a novel reward design that explicitly encodes traffic laws using knowledge graphs and retrieval-augmented models, automating reward assignment in RL for autonomous driving.

Findings

Improved accuracy in assigning accident responsibilities

Reduced rule violations in driving scenarios

Enhanced decision-making performance

Abstract

Reinforcement learning (RL) in autonomous driving employs a trial-and-error mechanism, enhancing robustness in unpredictable environments. However, crafting effective reward functions remains challenging, as conventional approaches rely heavily on manual design and demonstrate limited efficacy in complex scenarios. To address this issue, this study introduces a responsibility-oriented reward function that explicitly incorporates traffic regulations into the RL framework. Specifically, we introduced a Traffic Regulation Knowledge Graph and leveraged Vision-Language Models alongside Retrieval-Augmented Generation techniques to automate reward assignment. This integration guides agents to adhere strictly to traffic laws, thus minimizing rule violations and optimizing decision-making performance in diverse driving conditions. Experimental validations demonstrate that the proposed methodology significantly improves the accuracy of assigning accident responsibilities and effectively reduces the agent's liability in traffic incidents.