外观
论文arXiv 2609.039841 个月前
MulDP：用于复杂地形自主四足跑酷导航的多模态扩散策略
原文链接：MulDP: Multimodal Diffusion Policy for Autonomous Quadruped Parkour Navigation across Complex Terrains（arXiv 2609.03984 · 发布日期：2026-09-03）
MulDP: Multimodal Diffusion Policy for Autonomous Quadruped Parkour Navigation across Complex Terrains
针对四足跑酷导航依赖人工高层规划的问题，MulDP融合视觉、本体感知与目标信息，在仿真和真实实验中验证复杂地形自主导航。
核心要点
- 当前四足跑酷多依赖人工高层规划，自主导航仍缺乏充分探索。
- MulDP融合视觉感知、机器人本体感知和目标信息，生成时间一致且具预判性的导航速度指令。
- 构建首个QPND多模态数据集，覆盖多样导航行为和复杂地形，用于支持MulDP训练。
- 仿真与真实世界实验表明，MulDP可实现稳健长时域自主导航并有效穿越复杂地形。
验证范围与局限：验证范围为仿真和真实世界实验中的复杂地形四足跑酷导航。
英文摘要 (Abstract)
Quadruped robots have demonstrated impressive agility in parkour locomotion across complex terrains. However, most systems still rely on human intervention for high-level planning, and autonomous parkour navigation remains underexplored. The key challenges include fine-grained velocity regulation, long-horizon anticipatory behaviors, and tight coupling between perception and embodied execution. To address these challenges, we propose a Multimodal Diffusion Policy (MulDP) that integrates visual perception with robot proprioception and goal information to generate temporally coherent and anticipatory navigation velocity commands, tightly coupling perception with embodied control to enable robust autonomous navigation. To support the training of MulDP, we construct the first Quadruped Parkour Navigation Dataset (QPND), a multimodal dataset that encompasses diverse navigation behaviors and complex terrains. Extensive simulation and real-world experiments demonstrate that MulDP enables robust long-horizon autonomous navigation and effective traversal across complex terrains.
作者：Kangmai Hu, Yueqi Zhang, Peng Zhai, Xiaoyi Wei, Jiabin Hu, Zhixiang Liu, Quancheng Qian, Lihua Zhang
来源
本页事实对应的公开页面，以原文为准。