论文/arXiv 2603.03733·7 个月前

X-Loco框架实现视觉通用人形运动控制与跌倒恢复

X-Loco提出协同策略蒸馏框架，训练单一视觉策略集成直立行走、全身协调及跌倒恢复技能。该方案仅依赖速度指令无需参考动作，通过动态专家选择机制解决多目标冲突，显著提升地形穿越与鲁棒性。

AI 整理

• 仿真与训练
• 具身模型

本文由 AI 根据公开内容整理，可能有误，请以原文为准：X-Loco: Towards Generalist Humanoid Locomotion Control via Synergetic Policy Distillation（arXiv 2603.03733）

核心内容

针对人形机器人单一策略难以兼顾直立行走、跌倒恢复及全身协调等冲突控制目标的难题，研究团队提出X-Loco通用运动控制框架。该工作首次实现了纯视觉输入下，仅凭速度指令即可联合执行多种复杂技能的通用人形运动策略，摆脱了对参考动作轨迹的依赖，在跌倒恢复与地形穿越任务中验证了优越性能。

技术上采用协同策略蒸馏范式，先训练多个Oracle专家策略，再通过案例自适应专家选择机制动态指导学生策略学习。该架构有效解决了多样化动力学与控制目标冲突问题，消融实验证实了专家知识迁移的有效性。系统完全基于视觉感知与速度指令驱动，为无动捕环境下的具身智能体通用运动能力提供了新范式。

关键看点

• 协同蒸馏架构：采用案例自适应专家选择机制，动态融合多专家策略指导视觉学生模型学习
• 零参考动作依赖：仅凭速度指令驱动，无需预定义参考运动轨迹即可实现通用运动控制
• 全技能集成：单一策略同时覆盖直立行走、全身协调及跌倒恢复，解决多目标控制冲突
• 纯视觉感知：端到端视觉输入直接映射运动输出，验证了非结构化环境下的地形穿越能力

工程与产业观察

X-Loco通过协同蒸馏解决了人形机器人多技能策略融合的痛点，证明了脱离参考动作与动捕数据的纯视觉通用运动可行性。其案例自适应机制为具身大模型从仿真到真机的技能泛化提供了高效训练范式，对降低数据采集成本与提升本体鲁棒性具有重要工程参考价值。

英文摘要 (Abstract)

While recent advances have demonstrated strong performance in individual humanoid skills such as upright locomotion, fall recovery and whole-body coordination, learning a single policy that masters all these skills remains challenging due to the diverse dynamics and conflicting control objectives involved. To address this, we introduce X-Loco, a framework for training a vision-based generalist humanoid locomotion policy. X-Loco trains multiple oracle specialist policies and adopts a synergetic policy distillation with a case-adaptive specialist selection mechanism, which dynamically leverages multiple specialist policies to guide a vision-based student policy. This design enables the student to acquire a broad spectrum of locomotion skills, ranging from fall recovery to terrain traversal and whole-body coordination skills. To the best of our knowledge, X-Loco is the first framework to demonstrate vision-based humanoid locomotion that jointly integrates upright locomotion, whole-body coordination and fall recovery, while operating solely under velocity commands without relying on reference motions. Experimental results show that X-Loco achieves superior performance, demonstrated by tasks such as fall recovery and terrain traversal. Ablation studies further highlight that our framework effectively leverages specialist expertise and enhances learning efficiency.

作者：Dewei Wang, Xinmiao Wang, Chenyun Zhang, Jiyuan Shi, Yingnan Zhao, Chenjia Bai, Xuelong Li

来源

本页事实对应的公开页面，以原文为准。

1. arXiv 2603.03733：X-Loco: Towards Generalist Humanoid Locomotion Control via Synergetic Policy Distillation访问 2026-10-23