FootQuery：基于深度历史的未来触地引导检索用于感知型人形机器人运动
FootQuery: Future-Touchdown-Guided Retrieval from Depth History for Perceptive Humanoid Locomotion
- Institute for AI Industry Research (AIR), Tsinghua University（清华大学人工智能产业研究院（AIR））
- University of Science and Technology Beijing（北京科技大学）
- Nanyang Technological University（南洋理工大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对复杂地形中人形机器人落脚点不可见问题，提出FootQuery框架，利用预测触地位置查询深度历史并融合视觉记忆生成控制动作，仿真与真实实验验证其有效性。
AI中文摘要：
在复杂地形上的人形机器人运动需要在触地时预测可能已不可见的落脚点。有限的相机覆盖范围和自遮挡使得有必要从早期观测中检索相关地形信息。我们提出了FootQuery，一种感知型运动框架，它利用每只脚预测的下一次触地位置来查询深度历史。该策略从本体感觉中预测触地位置和不确定性，并利用这些分布以及每只脚的特征，来查询稀疏采样的历史深度帧。在训练期间，将实际接触点投影到历史图像中，以监督在那些接触点可见区域的检索。检索到的每只脚特征与全局视觉记忆融合以生成控制动作。渐进式力辅助课程支持早期探索，而事件一致的踏板中线整形则促进协调的楼梯接触。部署仅需本体感觉和机载深度图像。在仿真中，完整的框架在最具挑战性的测试楼梯、间隙和平台上优于其组件消融版本。在Unitree G1上的真实世界实验展示了单一策略在户外楼梯和结合楼梯上下行、平台和间隙的室内路线上的连续穿越。这些结果支持围绕预期接触点组织视觉历史以用于感知型人形机器人运动。
英文摘要：
Humanoid locomotion over complex terrain requires anticipating footholds that may no longer be visible at touchdown. Limited camera coverage and self-occlusion make it necessary to retrieve relevant terrain information from earlier observations. We present FootQuery, a perceptive locomotion framework that queries depth history using each foot's predicted next touchdown. The policy predicts touchdown locations and uncertainty from proprioception and uses these distributions, together with per-foot features, to query sparsely sampled historical depth frames. During training, realized contacts are projected into historical images to supervise retrieval at the regions where those contacts were visible. The retrieved per-foot features are fused with global visual memory to generate control actions. A progressive force-assistance curriculum supports early exploration, while event-consistent tread-midline shaping encourages coordinated stair contacts. Deployment requires only proprioception and onboard depth images. In simulation, the complete framework outperforms its component ablations on the most challenging tested stairs, gaps, and platforms. Real-world experiments on a Unitree G1 demonstrate continuous traversal with a single policy across outdoor stairs and indoor routes combining stair ascent and descent, platforms, and gaps. These results support organizing visual history around anticipated contacts for perceptive humanoid locomotion.
