SOLO: Stable Omni-terrain Long-Horizon Perceptive Humanoid Locomotion

2026-08-26

AI Summary

研究提出SOLO框架，通过Query Reconstructor和TA-MSE Distillation方法解决长距离复杂地形中人形机器人行走不稳定的问题。

Abstract

Humans traverse complex terrain over long distances without losing balance, whereas perceptive humanoid policies become fragile as perception and control errors accumulate. We present SOLO, a unified framework addressing two compounding causes of this long-horizon fragility: dense terrain reconstruction smooths action-critical details, and pointwise imitation lacks temporal credit assignment. Its Query Reconstructor (QR) uses Fourier-encoded cell queries to retrieve spatially specific evidence from depth-proprioception tokens, preserving sharp terrain boundaries. Trajectory-Aware MSE (TA-MSE) Distillation adds next-state teacher-student disagreement to the PPO reward, enabling Generalized Advantage Estimation to propagate future disagreement penalties to preceding actions. In simulation, QR reduces height-map L1 error by factors of 3.3-4.0, while TA-MSE surpasses PPO and MSE+PPO in curriculum progression. On stress-test terrains, SOLO achieves 97.5% mean traversal success and 96% stepping-stone success, versus 75.0-75.6% and 0-3% for dense-reconstructor variants. Deployed zero-shot with only a chest-mounted depth camera and proprioception, SOLO completes a continuous 1.5-km outdoor route and an indoor mixed-terrain course. Project page: https://sunpihai-up.github.io/solo/

Problem

• perceptive humanoid
• long-horizon fragility
• terrain reconstruction
• temporal credit assignment

Innovation

• Query Reconstructor
• Trajectory-Aware MSE
• Long-Horizon Locomotion
• Terrain Reconstruction
• Temporal Credit Assignment