外观
论文arXiv 2606.276764 个月前
CWI框架解耦全身模仿控制，LimX Oli实现无动捕遥操作
针对人形机器人移动操作难题，CWI框架解耦上下肢MoCap数据使用，通过对抗运动先验与多评论家架构优化策略。经蒸馏后仅凭手部姿态与速度指令即可驱动LimX Oli完成稳健移动操作与无全身动捕遥操作。
逐际动力 Oli本文由 AI 根据公开内容整理，可能有误，请以原文为准：CWI: Composite Humanoid Whole-Body Imitation System for Loco-manipulation（arXiv 2606.27676）
核心内容
针对人形机器人移动操作中纯指令采样导致上肢动作失真、全身体感数据不平衡的问题，研究提出复合全身模仿（CWI）框架。该方法在仿真及LimX Oli全尺寸人形机器人实机部署中验证，实现了无需全身动作捕捉设备的实用化遥操作，并在移动操作任务中展现出稳健的全身协调能力与竞争性性能指标。
CWI技术上解耦了上下肢控制：上肢充分利用多样化操作MoCap数据，下肢采用对抗运动先验（AMP）双判别器引导稳定行走与下蹲。系统引入多评论家架构缓解 locomotion、manipulation 与风格目标冲突，并通过教师-学生蒸馏生成仅依赖双手姿态及速度/高度命令的端到端策略，有效规避了稀疏奖励与课程学习调参难点。
关键看点
- 数据解耦策略：分离上下肢MoCap使用，上肢复用全量操作数据，下肢仅用精选行走下蹲片段训练AMP判别器
- 多目标优化架构：采用Multi-critic结构独立评估移动、操作与风格目标，解决联合训练中梯度冲突问题
- 低维感知蒸馏：Teacher-student蒸馏输出仅依赖双手位姿与线速度/高度指令的策略，摆脱对全身关节状态观测依赖
- 实机部署验证：在LimX Oli全尺寸本体上实现无全身动捕设备下的实用遥操作与稳健移动操作
工程与产业观察
CWI通过数据解耦与蒸馏机制，解决了人形机器人移动操作中高质量全身数据稀缺与策略收敛难的工程痛点。其仅凭手部姿态与速度指令即可驱动全尺寸本体的能力，显著降低了真机数据采集门槛，为具身智能从仿真到实机的低成本迁移提供了可复用的算法范式。
英文摘要 (Abstract)
Achieving everyday tasks with humanoid robots requires coordinating stable locomotion with versatile manipulation. However, existing whole-body controllers still face significant challenges. Methods trained solely via command sampling, without motion-capture (MoCap) data, often struggle with sparse rewards and require carefully tuned curricula to converge. This is especially problematic for upper-body control, where the resulting motions deviate from human-like statistics and degrade whole-body coordination. Conversely, approaches that imitate full-body MoCap data suffer from dataset imbalance, as many locomotion trajectories are overly aggressive for stable-locomotion scenarios, necessitating extensive data filtering and augmentation. To address this, we present Composite Whole-Body Imitation (CWI), a framework that decouples the use of MoCap data for upper-body manipulation and lower-body locomotion. This decoupling allows us to exploit the full MoCap dataset of diverse manipulation references, while stable, command-conditioned lower-body locomotion is guided by dual discriminators trained on curated expert-quality walking and squatting clips via an Adversarial Motion Prior (AMP). A multi-critic architecture reduces conflicts among locomotion, manipulation, and motion-style objectives, and a teacher--student distillation stage yields a whole-body policy conditioned only on bimanual hand poses and velocity/height commands. We evaluate CWI through simulation experiments and real-world deployment on a full-size LimX Oli humanoid. The results show competitive loco-manipulation performance, robust whole-body coordination, and practical teleoperation without full-body motion-capture equipment. A project page with supplementary material can be found at https://cwi-ral.github.io/CWI-RAL-Webpage.
作者：Wenqi Ge, Junde Guo, Zhen Fu, Shunpeng Yang, Jiayu Chen, Hua Chen
来源
本页事实对应的公开页面，以原文为准。