发表机构
Artificial General Intelligence Institute, University of Science and Technology of China; X-Humanoid; The University of Hong Kong; The Australian National University; The Hong Kong University of Science and Technology (Guangzhou); Shanghai Jiao Tong University; The Chinese University of Hong Kong; Tsinghua University（中国科学技术大学通用人工智能研究院; X-人形机器人; 香港大学; 澳大利亚国立大学; 香港科技大学（广州）; 上海交通大学; 香港中文大学; 清华大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
SOLO是解决长视距类人机器人运动脆弱性的统一框架，通过QR与TA-MSE蒸馏提升地形感知与策略学习，仿真及实际测试中通行成功率显著优于基线方法，可零样本完成长距离复杂地形任务。
AI 中文摘要
人类可在长距离复杂地形中保持平衡行进，而感知类人机器人策略会因感知与控制误差累积变得脆弱。本文提出SOLO这一统一框架，解决导致长视距脆弱性的两个复合原因：密集地形重建平滑了对动作关键的细节，而逐点模仿缺乏时间信用分配。其查询重构器（QR）采用傅里叶编码的单元查询，从深度-本体感受令牌中检索空间特定证据，保留清晰地形边界；轨迹感知均方误差（TA-MSE）蒸馏将下一状态的师生分歧添加到PPO奖励中，使广义优势估计能将未来分歧惩罚传播到先前动作。在仿真中，QR将高度图L1误差降低3.3-4.0倍，TA-MSE在课程进度上优于PPO和MSE+PPO；在压力测试地形上，SOLO实现97.5%的平均通行成功率和96%的踏脚石成功率，而密集重构器变体分别为75.0-75.6%和0-3%。仅使用胸部安装的深度相机和本体感受零样本部署时，SOLO完成了1.5公里的连续室外路线和室内混合地形路线。项目页面：this https URL
英文摘要
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/
