Skip to content

论文arXiv 2611.226954 天前

四足机械臂引入末端惯性反馈强化学习,轨迹跟踪误差降低28% ​

本文由 AI 根据公开内容整理,可能有误,请以原文为准:Learning Accurate End-Effector Trajectory Tracking with Inertial Feedback for a Quadruped Manipulator(arXiv 2611.22695)

核心内容 ​

针对四足机械臂因执行器、足地接触及几何误差在腿臂运动链中传播导致的末端轨迹跟踪难题,该研究提出一种结合末端惯性反馈的强化学习框架。该方法旨在保持机身姿态与支撑构型不变的前提下,利用末端惯性测量单元(IMU)数据补偿仅靠本体感知无法推断的系统不确定性。仿真与真机连续轨迹跟踪实验表明,新策略显著优于标称模型及纯本体感知基线,验证了外部惯性反馈对提升操作精度的有效性。

真机实验量化数据显示,在两种分布内指令条件下,该策略较标称基线的MoCap RMSE分别降低17.3%和28.0%,较纯本体感知基线进一步降低12.6%和15.9%。对比分析揭示,正运动学重构位置与动捕实测位置的轨迹RMSE均值为12.61±2.15mm,证实了名义运动学模型与实际末端运动存在显著偏差。该结果确立了在关节编码器之外引入末端惯性传感对于抑制齿隙、结构形变等未建模误差的工程价值。

关键看点 ​

  • 精度提升:真机测试中,引入末端惯性反馈的策略较标称基线RMSE最高降低28.0%,较纯本体感知基线额外降低15.9%
  • 误差量化:24组控制器-轨迹组合测试显示,FK重构与动捕实测位置偏差均值达12.61±2.15mm,揭示名义模型局限
  • 感知增强:利用末端IMU数据补偿关节编码器无法观测的齿隙、尺寸误差及结构形变,解决腿臂耦合运动链不确定性
  • 控制约束:策略专注于局部高精度操作,维持机身标称姿态与支撑构型,不依赖主动机身运动或足端重定位

工程与产业观察 ​

该研究证实仅靠关节编码器难以满足四足机械臂高精度作业需求,末端惯性反馈是低成本补偿机械链累积误差的有效手段。对于具身智能硬件工程而言,在灵巧操作终端集成IMU并纳入RL状态空间,可作为解决本体标定偏差与动态形变的标准范式,显著提升非结构化环境下的操作鲁棒性。

英文摘要 (Abstract) ​

Accurate end-effector trajectory tracking on quadruped manipulators is challenging because uncertainties in actuators, foot-ground contact, and geometric errors are propagated through the leg-arm kinematic chain. Detecting such errors requires sensing beyond joint encoders that can capture the effects of these uncertainties on the robot's motion, since joint encoders only provide measurements at the actuated joints and cannot fully observe mechanical errors such as backlash, dimensional inaccuracies, or structural deformation. This work addresses these challenges using a reinforcement learning framework with end-effector (EE) inertial feedback, targeting local high-accuracy manipulation while maintaining a nominal body pose and support configuration without intentional body motion or foot repositioning. The learned policy uses EE inertial measurements to compensate for tracking errors induced by uncertainties throughout the leg-arm system that cannot be fully inferred from proprioception alone. Simulation and real-world experiments on continuous EE trajectory tracking show overall improvements relative to nominal and proprioception-only baselines. In real-world experiments, the proposed policy reduces the MoCap-based RMSE by 17.3% and 28.0% relative to the nominal baseline under the two in-distribution (ID) command conditions, respectively, and by an additional 12.6% and 15.9% relative to the proprioception-only baseline. Furthermore, the trajectory-wise RMSE between FK-reconstructed and motion-capture-measured end-effector positions averaged 12.61+-2.15mm (mean+-standard deviation) across 24 controller-trajectory combinations, revealing a substantial discrepancy between nominal kinematic reconstruction and measured end-effector motion.

作者:Dohyeon Kim, Seungyong Han, Yeongtae Jung

基于本页技术方向关联的整机参数、核心零部件、实测报告与同赛道选型横评。

外部来源

本页事实对应的公开页面,以原文为准。(点击将离开本站)

  1. arXiv 2611.22695:Learning Accurate End-Effector Trajectory Tracking with Inertial Feedback for a Quadruped Manipulator ↗访问 2026-11-18