通过紧密耦合高低层规划，提升长时序任务的扩散模型表现
CHD: Coupled Hierarchical Diffusion for Long-Horizon Tasks
- 将高层子目标与底层轨迹在统一扩散过程中共建模
- 在复杂场景中实现90%以上成功率，优于基线方法
- 适合需要长期规划的机器人任务，如导航与操作
基于扩散的规划器在短时序任务中表现优异，但在复杂长时序场景中常失效。我们发现失败源于高层（HL）子目标选择与底层（LL）轨迹生成之间的松散耦合，导致计划不连贯、性能下降。为此提出耦合分层扩散（CHD）框架，将高层子目标与底层轨迹在统一扩散过程中联合建模。共享分类器将底层反馈向上游传递，使子目标在采样过程中自我修正。这种紧密的高低层耦合提升了轨迹一致性，实现了可扩展的长时序扩散规划。在迷宫导航、桌面操作和家庭环境等任务中，CHD持续优于扁平化和分层扩散基线。官网：https://sites.google.com/view/chd2025/home
原文摘要 · Abstract (English)
Diffusion-based planners have shown strong performance in short-horizon tasks but often fail in complex, long-horizon settings. We trace the failure to loose coupling between high-level (HL) sub-goal selection and low-level (LL) trajectory generation, which leads to incoherent plans and degraded performance. We propose Coupled Hierarchical Diffusion (CHD), a framework that models HL sub-goals and LL trajectories jointly within a unified diffusion process. A shared classifier passes LL feedback upstream so that sub-goals self-correct while sampling proceeds. This tight HL-LL coupling improves trajectory coherence and enables scalable long-horizon diffusion planning. Experiments across maze navigation, tabletop manipulation, and household environments show that CHD consistently outperforms both flat and hierarchical diffusion baselines. Our website is: https://sites.google.com/view/chd2025/home
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。