FootQuery: Future-Touchdown-Guided Retrieval from Depth History for Perceptive Humanoid Locomotion

2026-09-18

AI Summary

为了解决复杂地形下人形机器人行走时的落脚点预测问题，提出了一种基于历史深度信息检索的方法FootQuery，通过预测落脚位置并结合历史深度图像来生成控制动作。

Abstract

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.

Problem

• humanoid locomotion
• complex terrain
• foot touchdown prediction
• depth history retrieval
• perceptive navigation

Innovation

• foot touchdown prediction
• depth history retrieval
• perceptive locomotion
• feature fusion
• force-assistance curriculum