CoT4AD: A Vision-Language-Action Model with Explicit Chain-of-Thought Reasoning for Autonomous Driving
By: Zhaohui Wang, Tengbo Yu, Hao Tang
Potential Business Impact:
Helps self-driving cars think step-by-step to drive safely.
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.
Similar Papers
CoC-VLA: Delving into Adversarial Domain Transfer for Explainable Autonomous Driving via Chain-of-Causality Visual-Language-Action Model
Robotics
Teaches self-driving cars to handle tricky situations.
Reasoning-VLA: A Fast and General Vision-Language-Action Reasoning Model for Autonomous Driving
CV and Pattern Recognition
Helps self-driving cars drive smarter and faster.
GraphCoT-VLA: A 3D Spatial-Aware Reasoning Vision-Language-Action Model for Robotic Manipulation with Ambiguous Instructions
Robotics
Robots understand confusing orders and see in 3D.