COVLM-RL: Critical Object-Oriented Reasoning for Autonomous Driving Using VLM-Guided Reinforcement Learning
Li, Lin, Cai, Yuxin, Fang, Jianwu, Xue, Jianru, Lv, Chen
–arXiv.org Artificial Intelligence
End-to-end autonomous driving frameworks face persistent challenges in generalization, training efficiency, and interpretability. While recent methods leverage Vision-Language Models (VLMs) through supervised learning on large-scale datasets to improve reasoning, they often lack robustness in novel scenarios. Conversely, reinforcement learning (RL)-based approaches enhance adaptability but remain data-inefficient and lack transparent decision-making. % contribution To address these limitations, we propose COVLM-RL, a novel end-to-end driving framework that integrates Critical Object-oriented (CO) reasoning with VLM-guided RL. Specifically, we design a Chain-of-Thought (CoT) prompting strategy that enables the VLM to reason over critical traffic elements and generate high-level semantic decisions, effectively transforming multi-view visual inputs into structured semantic decision priors. These priors reduce the input dimensionality and inject task-relevant knowledge into the RL loop, accelerating training and improving policy interpretability. However, bridging high-level semantic guidance with continuous low-level control remains non-trivial. To this end, we introduce a consistency loss that encourages alignment between the VLM's semantic plans and the RL agent's control outputs, enhancing interpretability and training stability. Experiments conducted in the CARLA simulator demonstrate that COVLM-RL significantly improves the success rate by 30\% in trained driving environments and by 50\% in previously unseen environments, highlighting its strong generalization capability.
arXiv.org Artificial Intelligence
Dec-11-2025
- Country:
- Asia
- China > Shaanxi Province
- Xi'an (0.04)
- Middle East > Republic of Türkiye
- Karaman Province > Karaman (0.04)
- Singapore (0.05)
- China > Shaanxi Province
- Asia
- Genre:
- Research Report (0.64)
- Industry:
- Information Technology > Robotics & Automation (0.63)
- Transportation > Ground
- Road (1.00)
- Technology:
- Information Technology > Artificial Intelligence
- Machine Learning
- Neural Networks > Deep Learning (0.46)
- Reinforcement Learning (1.00)
- Natural Language (1.00)
- Representation & Reasoning > Object-Oriented Architecture (0.72)
- Robots > Autonomous Vehicles (0.73)
- Vision (1.00)
- Machine Learning
- Information Technology > Artificial Intelligence