论文arXiv 2611.01748今天

CompliantBot：无需力传感实现人形机器人全身柔顺与任务恢复

提出CompliantBot框架，通过状态依赖力场与动态奖励机制，使机器人在无外力传感器下实现全身柔顺。实测在强拉力下任务完成率最高，关节机械功率最低，撤力后能自动恢复运动跟踪。

AI 整理

本体 SDK 与控制
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：CompliantBot: Learning Whole-Body Compliance across Task Interfaces for Humanoid Control（arXiv 2611.01748）

核心内容

针对人形机器人柔顺控制中任务跟踪与外力顺应难以兼顾的痛点，研究提出CompliantBot训练框架。该方法适用于运动跟踪与速度指令两种接口，无需预构建柔顺数据或目标轨迹。实验表明，在恒定拉力干扰下，该策略比基线方法顺应位移更大、弹簧交互负载更低，且在强拉力条件下任务完成率居首，撤除力后能迅速恢复原始任务跟踪。

技术上引入状态依赖交互力场耦合负载与运动，配合力幅值奖励降低交互载荷，并在受力时动态下调任务奖励权重以协调顺应与恢复。策略仅依赖任务输入与本体感知历史，无需显式外力测量。实机验证展示了手臂运动、步态调整及躯干重定向等柔顺响应，且评估显示其平均关节机械功率为对比方法中最低，证实了能效与控制性能优势。

关键看点

无传感柔顺：仅凭本体感知历史与任务输入实现顺应，无需外部力传感器或预置柔顺轨迹数据
动态奖励调度：受力时自动下调任务奖励权重并施加力幅值惩罚，撤力后恢复权重以实现任务无缝接续
高负载鲁棒性：在更强恒定拉力测试中任务完成率最高，顺应位移大于基线且交互负载显著降低
低机械功耗：实机演示涵盖手臂、步态与躯干重定向，平均关节机械功率在所有对比方法中最低

工程与产业观察

该工作解决了人形机器人在非结构化环境中“抗扰”与“执行”的矛盾，证明了仅靠本体感知即可习得高质量全身柔顺策略。其免外力传感、免专家数据的特性大幅降低了Sim-to-Real门槛，为人形机器人在人机协作及未知接触场景下的安全部署提供了通用化算法范式。

英文摘要 (Abstract)

Humanoid controllers need the ability to yield to external forces while retaining the capacity to resume their original tasks. However, tracking objectives penalize the deviations needed for yielding, while relaxing tracking goals persistently can make task recovery harder. Existing approaches often rely on task-specific interaction command interfaces or constructed compliant motion data and reference trajectories, limiting the direct reuse of their compliance-training mechanisms across different task interfaces. We introduce CompliantBot, a compliance-training framework for motion tracking and velocity-command locomotion. It preserves the original task inputs and requires no preconstructed compliant data or target trajectories. A state-dependent interaction force field couples applied loads to the robot's motion, enabling local articulation and whole-body movement to change the forces experienced. A complementary force-magnitude reward encourages lower interaction loads, while task rewards are downweighted during loading and restored after release to coordinate yielding and task resumption. The trained policies use task inputs and proprioceptive history without explicit external-force measurements. Across both task interfaces, CompliantBot yields farther under constant pulls and experiences lower spring interaction loads than matched baselines, while resuming task tracking after force removal. CompliantBot achieves the highest task completion among the compared methods under stronger pulls. Power evaluations further show that CompliantBot has the lowest mean joint mechanical power among the compared methods. Real-robot demonstrations further illustrate compliant responses through arm motion, stepping, and body reorientation.

作者：Haoyang Li, Keqi Zhu, Zhanxiang Cao, Yang Zhang, Yizhi Chen, Xuekang Yang, Yue Gao