论文arXiv 2611.1392911 天前
ReACT框架解决人形机器人单手持物非对称负载速度跟踪偏差
本文由 AI 根据公开内容整理,可能有误,请以原文为准:ReACT: Reflection-Consistent Modulation and Cross-Load Consistency for Humanoid Velocity Tracking Under Asymmetric Loads(arXiv 2611.13929)
核心内容
人形机器人在全身抓取搬运任务中,单手持物产生的持续非对称上肢负载会严重干扰运动控制器对导航策略速度指令的执行,导致位置与航向累积偏差甚至导航失败。为此研究提出ReACT框架,旨在解决非对称负载下的速度跟踪难题。该方案在Unitree G1人形机器人上完成验证,仿真中显著降低方向性偏差,真机测试中40次单边手持重物导航试验均成功无碰撞抵达目标,验证了其在固定无图导航策略下的鲁棒性。
技术上,ReACT包含反射一致扰动调制与跨负载跟踪一致性训练两大核心机制。前者利用估计的外部力矩(wrench)调节Actor网络特征进行负载补偿,同时保持镜像观测下的动作对应关系;后者通过对比相同速度指令下加载与空载状态,强制模型学习跨负载条件的一致速度跟踪能力。该方法不依赖高精度负载建模,直接从数据层面消除非对称力矩对步态控制的耦合干扰,解决了传统控制器在动态负重场景下的跟踪失效问题。
关键看点
- 反射一致扰动调制:利用估计wrench调制Actor特征补偿负载,保持镜像观测下动作对应关系,消除非对称力矩干扰
- 跨负载一致性训练:对比同速度指令下加载与空载状态,强制模型学习跨工况一致的速度跟踪能力,提升泛化性
- 真机零碰撞验证:Unitree G1在40次单边手持重物导航试验中全部成功抵达目标,验证固定无图策略下的鲁棒性
- 解决累积偏差痛点:针对性抑制单手持物引起的持续性速度跟踪偏差,防止位置与航向误差累积导致的导航失败
工程与产业观察
该工作揭示了具身智能从空载演示走向真实作业的关键瓶颈:非对称负载下的动力学一致性。ReACT通过数据驱动的特征调制与对比训练,为loco-manipulation提供了无需精确负载建模的鲁棒控制范式,对人形机器人仓储搬运、家庭服务等实际落地场景的运动稳定性具有重要工程参考价值。
英文摘要 (Abstract)
In recent years, humanoid loco-manipulation has progressed to whole-body grasping, lifting, and transport. A basic requirement underlying these tasks is carrying the object to its destination, which depends on the locomotion controller accurately executing velocity commands from the navigation policy. However, carrying an object in one hand introduces a persistent asymmetric upper-body load that can degrade velocity tracking. Persistent tracking biases can accumulate into position and heading deviations, increasing the risk of collisions and navigation failure. To address this problem, we present ReACT, a framework for accurate velocity tracking under asymmetric upper-body loads. Reflection-consistent disturbance modulation uses the estimated wrench to modulate actor features for load compensation while preserving action correspondence under reflected observations. Cross-load tracking consistency training compares loaded and unloaded conditions under the same velocity commands to promote consistent velocity tracking across loading conditions. Simulation experiments on a Unitree G1 humanoid robot show improved velocity tracking and reduced directional bias under varying asymmetric loads. Real-world experiments demonstrate collision-free goal reaching in all 40 tested navigation trials under unilateral hand loads with a fixed mapless navigation policy.
作者:Xianghui Wang, Aoran Fu, Liyou Luo, Shanze Wang, Xiaoyu Shen, Dan Zhang, Wei Zhang
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)