ReCogDrive：一种用于端到端自动驾驶的强化认知框架
ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving
AI总结：
针对 VLM 在端到端驾驶中语言输出动作不可行、格式错误且推理慢的问题，ReCogDrive 融合自回归认知与扩散规划，并通过分层数据流水线和 DiffGRPO 强化安全舒适，在多个基准上达到 SOTA。
摘要：
近期研究探索利用视觉-语言模型（VLM）的世界知识与认知能力，以解决端到端自动驾驶中的长尾问题。然而，现有方法通常将轨迹规划表述为语言建模任务，在语言空间中输出物理动作，这可能导致输出违反格式、动作不可行以及推理速度缓慢等问题。本文提出 ReCogDrive，这是一种用于端到端自动驾驶的新型强化认知框架，通过将自回归模型与扩散规划器相集成，统一驾驶理解与规划。首先，为将人类驾驶认知注入 VLM，我们引入了一个分层数据流水线，通过生成、精炼和质量控制三个阶段模拟人类驾驶员的顺序认知过程。在此认知基础上，我们随后通过将 VLM 学到的驾驶先验注入扩散规划器来解决语言-动作不匹配问题，以高效生成连续且稳定的轨迹。此外，为提升驾驶安全性并减少碰撞，我们引入扩散组相对策略优化（DiffGRPO）阶段，对规划器进行强化，以增强安全性和舒适性。在 NAVSIM 和 Bench2Drive 基准上的大量实验表明，ReCogDrive 取得了最先进的性能。此外，跨多种驾驶场景以及 DriveBench 的定性结果凸显了该模型的场景理解能力。所有代码、模型权重和数据集都将公开发布，以促进后续研究。
英文摘要：
Recent studies have explored leveraging the world knowledge and cognitive capabilities of Vision-Language Models (VLMs) to address the long-tail problem in end-to-end autonomous driving. However, existing methods typically formulate trajectory planning as a language modeling task, where physical actions are output in the language space, potentially leading to issues such as format-violating outputs, infeasible actions, and slow inference speeds. In this paper, we propose ReCogDrive, a novel Reinforced Cognitive framework for end-to-end autonomous Driving, unifying driving understanding and planning by integrating an autoregressive model with a diffusion planner. First, to instill human driving cognition into the VLM, we introduce a hierarchical data pipeline that mimics the sequential cognitive process of human drivers through three stages: generation, refinement, and quality control. Building on this cognitive foundation, we then address the language-action mismatch by injecting the VLM's learned driving priors into a diffusion planner to efficiently generate continuous and stable trajectories. Furthermore, to enhance driving safety and reduce collisions, we introduce a Diffusion Group Relative Policy Optimization (DiffGRPO) stage, reinforcing the planner for enhanced safety and comfort. Extensive experiments on the NAVSIM and Bench2Drive benchmarks demonstrate that ReCogDrive achieves state-of-the-art performance. Additionally, qualitative results across diverse driving scenarios and DriveBench highlight the model's scene comprehension. All code, model weights, and datasets will be made publicly available to facilitate subsequent research.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
