用扩散模型实现自动驾驶的灵活规划，无需规则后处理。
Diffusion-Based Planning for Autonomous Driving with Flexible Guidance
- 基于Transformer的扩散模型统一建模预测与规划
- 在nuPlan和200小时真实数据上达顶尖闭环性能
- 支持多车协同，适配不同驾驶风格
在复杂开放世界环境中实现类人驾驶行为是自动驾驶的关键挑战。现有基于学习的规划方法如模仿学习常难以平衡多重目标，缺乏安全性保障，且对复杂多模态人类行为建模能力不足，还严重依赖预设规则的备用策略。本文提出一种基于Transformer的扩散规划器（Diffusion Planner），实现闭环规划，可有效建模多模态驾驶行为并保证轨迹质量，无需任何基于规则的后处理。该模型在同一架构下联合建模预测与规划任务，促进车辆间协同。通过学习轨迹评分函数梯度并采用灵活分类器引导机制，实现安全且自适应的规划行为。在大规模真实世界基准nuPlan及新收集的200小时配送车驾驶数据集上的评估表明，Diffusion Planner在多样化驾驶风格下展现卓越闭环性能与强泛化能力。
原文摘要 · Abstract (English)
Achieving human-like driving behaviors in complex open-world environments is a critical challenge in autonomous driving. Contemporary learning-based planning approaches such as imitation learning methods often struggle to balance competing objectives and lack of safety assurance,due to limited adaptability and inadequacy in learning complex multi-modal behaviors commonly exhibited in human planning, not to mention their strong reliance on the fallback strategy with predefined rules. We propose a novel transformer-based Diffusion Planner for closed-loop planning, which can effectively model multi-modal driving behavior and ensure trajectory quality without any rule-based refinement. Our model supports joint modeling of both prediction and planning tasks under the same architecture, enabling cooperative behaviors between vehicles. Moreover, by learning the gradient of the trajectory score function and employing a flexible classifier guidance mechanism, Diffusion Planner effectively achieves safe and adaptable planning behaviors. Evaluations on the large-scale real-world autonomous planning benchmark nuPlan and our newly collected 200-hour delivery-vehicle driving dataset demonstrate that Diffusion Planner achieves state-of-the-art closed-loop performance with robust transferability in diverse driving styles.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。