CoT4AD: A Vision-Language-Action Model with Explicit Chain-of-Thought Reasoning for Autonomous Driving
Wang, Zhaohui, Yu, Tengbo, Tang, Hao
–arXiv.org Artificial Intelligence
Vision-Language-Action (VLA) models have recently attracted growing attention in end-to-end autonomous driving for their strong reasoning capabilities and rich world knowledge. However, existing VLAs often suffer from limited numerical reasoning ability and overly simplified input-output mappings, which hinder their performance in complex driving scenarios requiring step-by-step causal reasoning. To address these challenges, we propose CoT4AD, a novel VLA framework that introduces Chain-of-Thought (CoT) reasoning for autonomous driving to enhance both numerical and causal reasoning in Vision-Language Models (VLMs). CoT4AD integrates visual observations and language instructions to perform semantic reasoning, scene understanding, and trajectory planning. During training, it explicitly models a perception-question-prediction-action CoT to align the reasoning space with the action space across multiple driving tasks. During inference, it performs implicit CoT reasoning to enable consistent numerical reasoning and robust decision-making in dynamic environments. Extensive experiments on both real-world and simulated benchmarks, including nuScenes and Bench2Drive, demonstrate that CoT4AD achieves state-of-the-art performance in both open-loop and closed-loop evaluations. Code will be released upon paper acceptance.
arXiv.org Artificial Intelligence
Dec-1-2025
- Genre:
- Research Report (0.82)
- Industry:
- Automobiles & Trucks (1.00)
- Information Technology > Robotics & Automation (0.96)
- Transportation > Ground
- Road (1.00)
- Technology:
- Information Technology > Artificial Intelligence
- Cognitive Science > Problem Solving (0.88)
- Machine Learning > Neural Networks
- Deep Learning (0.93)
- Natural Language > Large Language Model (0.95)
- Representation & Reasoning (1.00)
- Robots > Autonomous Vehicles (1.00)
- Vision (1.00)
- Information Technology > Artificial Intelligence