ROAD: Responsibility-Oriented Reward Design for Reinforcement Learning in Autonomous Driving
This work addresses the problem of reward design for autonomous driving systems, offering a domain-specific solution that is incremental in automating reward assignment using existing techniques.
The paper tackles the challenge of designing effective reward functions for reinforcement learning in autonomous driving by introducing a responsibility-oriented reward function that incorporates traffic regulations, resulting in significant improvements in accident responsibility assignment accuracy and reduced agent liability in traffic incidents.
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.