mlsanityData to 13 Oct 2026

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

arXiv 2505.24317 ↗First posted 30 May 2025cs.LGcited by 0

On the map: End-to-end autonomous driving → Reinforcement learning for driving

also in 1 more
Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 13 Oct 2026). Placed in Reinforcement learning for driving, one of 9 directions in End-to-end autonomous driving. Builds on 24 of its 42 references that are in the map. First posted on arXiv 30 May 2025.

Builds on

24 of 42 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025Design of Reward Function on Reinforcement Learning for Automated Driving20 Mar
  2. 2024Trustworthy Human-AI Collaboration: Reinforcement Learning with Human Feedback and Physics Knowledge for Safe Autonomous Driving1 Sep
  3. 2024Research on Autonomous Driving Decision-making Strategies based Deep Reinforcement Learning6 Aug
  4. 2021MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learning26 Sep
  5. 2021Reward (Mis)design for Autonomous Driving28 Apr

Other references · 19

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,043
  2. 2017Proximal Policy Optimization Algorithmscited by 14,592
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,376
  4. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,986
  5. 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,243
  6. 2024A Survey on Hallucination in Large Vision-Language Modelscited by 352
  7. 2023Drive Like a Human: Rethinking Autonomous Driving with Large Language Modelscited by 160
  8. 2024RL-VLM-F: Reinforcement Learning from Vision Language Foundation Model Feedbackcited by 148
  9. 2023LingoQA: Visual Question Answering for Autonomous Drivingcited by 145
  10. 2022Imitation Is Not Enough: Robustifying Imitation with Reinforcement Learning for Challenging Driving Scenarioscited by 124
  11. 2022REVEAL: Retrieval-Augmented Visual-Language Pre-Training with Multi-Source Multimodal Knowledge Memorycited by 122
  12. 2024IBD: Alleviating Hallucinations in Large Vision-Language Models via Image-Biased Decodingcited by 118
7 more
  1. 2023Can Knowledge Graphs Reduce Hallucinations in LLMs? : A Surveycited by 92
  2. 2024Self-Introspective Decoding: Alleviating Hallucinations for Large Vision-Language Modelscited by 91
  3. 2024VLM-RL: A Unified Vision Language Models and Reinforcement Learning Framework for Safe Autonomous Drivingcited by 51
  4. 2024Code as Reward: Empowering Reinforcement Learning with VLMscited by 39
  5. 2024A Large Language Model-Driven Reward Design Framework via Dynamic Feedback for Reinforcement Learningcited by 30
  6. 2025Speaking the Language of Teamwork: LLM-Guided Credit Assignment in Multi-Agent Reinforcement Learningcited by 10
  7. 2025CARIL: Confidence-Aware Regression in Imitation Learning for Autonomous Drivingcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Balancing Progress and Safety: A Novel Risk-Aware Objective for RL in Autonomous Driving
  2. 2024A Review of Reward Functions for Reinforcement Learning in the context of Autonomous Driving
  3. 2024Generating and Evolving Reward Functions for Highway Driving with Large Language Models
  4. 2023Risk-Aware Reward Shaping of Reinforcement Learning Agents for Autonomous Driving
  5. 2025A Survey of Reinforcement Learning-Based Motion Planning for Autonomous Driving: Lessons Learned from a Driving Task Perspective
  6. 2026DriveReward: A Comprehensive Dataset and Generative Vision-Language Reward Model for Autonomous Driving
  7. 2025Ethics-Aware Safe Reinforcement Learning for Rare-Event Risk Control in Interactive Urban Driving
  8. 2022Automatically Learning Fallback Strategies with Model-Free Reinforcement Learning in Safety-Critical Driving Scenarios