Skip to content

论文arXiv 2611.0866413 天前

ForPC框架实现人形机器人无外力传感器精准推车与零样本真机迁移 ​

本文由 AI 根据公开内容整理,可能有误,请以原文为准:ForPC: Force-Aware Whole-Body Control for Precise Humanoid Cart Pushing(arXiv 2611.08664)

核心内容 ​

针对人形机器人双手推车时力耦合导致平衡失稳及负载动态变化难题,研究提出ForPC力感知全身控制框架。该方法采用两阶段强化学习策略,先训练适应多变手部负载与上身姿态的运动先验提供平衡支撑,再基于本体观测推断力与状态隐变量输入残差策略,协调臂、腰、腿调整与底盘速度指令。多目标奖励函数显式惩罚双臂内力对抗、抓取滑移及执行器饱和,使策略无需人类演示即可按需施加接触力。

Sim-to-sim实验显示,ForPC相比纯运动基线在多弯道路径上将推车速度RMSE降低68.2%、横向跟踪误差降低74.2%。该策略仅经仿真训练即零样本迁移至Unitree G1物理样机,无需真实世界微调或负载特定参数调整,成功实现承载30kg负载以0.5m/s速度稳定推车。系统完全依赖本体感知推断外力,摆脱了对昂贵腕部六维力传感器的依赖,为人形机器人在制造与物流场景复用现有轮式载具提供了低成本控制范式。

关键看点 ​

  • 无传感器力推断:利用本体观测推断力与状态隐变量替代外部力传感器,通过残差策略协调全身关节与底盘速度指令
  • 两阶段RL架构:先训练抗扰动运动先验保障平衡,再训练残差策略处理力耦合,多目标奖励抑制双臂内力对抗与抓取滑移
  • 零样本真机迁移:纯仿真训练策略直接部署至Unitree G1,无需Real-world微调即可推动30kg负载以0.5m/s稳定行进
  • 量化性能提升:相比Loco-only基线,仿真中推车速度RMSE降低68.2%,多弯道横向跟踪误差降低74.2%

工程与产业观察 ​

ForPC证明了基于本体感知的隐变量推断可替代昂贵力传感器解决重载操作中的力耦合问题。其两阶段RL与零样本迁移能力显著降低了人形机器人物料搬运的部署门槛,为具身智能在非结构化工业场景中复用现有基础设施提供了高鲁棒性、低硬件成本的控制算法参考。

英文摘要 (Abstract) ​

Humanoid robots are expected to take over strenuous material handling in manufacturing, logistics, and healthcare, where operating existing wheeled carts would let them move heavy loads without modifying the workplace. However, humanoid cart pushing remains challenging because the bimanual grasp closes a force-coupled loop in which the contact wrenches that drive the cart also disturb the robot's balance, and payload changes alter the coupled dynamics. We propose ForPC, a force-aware whole-body control framework that regulates cart velocity through two-stage reinforcement learning. A locomotion prior is first trained under varied hand loads and upper-body postures to provide balance support. A force latent and a state latent are then inferred from onboard observations, without external force sensors, and fed to a residual policy that coordinates bounded arm, waist, and leg adjustments with base-velocity commands. Multi-objective rewards penalize bimanual internal opposition, grasp slip, and actuator saturation, encouraging the policy to apply contact force on demand without human demonstrations. Sim-to-sim experiments show that ForPC reduces cart-velocity RMSE by up to 68.2% relative to a locomotion-only baseline (Loco-only) and cross-track RMSE by up to 74.2% on the multi-bend route. Trained solely in simulation, the policy also transfers to a physical Unitree G1 without real-world training or fine-tuning and, with no payload-specific adjustment, pushes a cart carrying up to 30 kg at 0.5 m/s. These results suggest that humanoid robots could eventually replace humans for efficient material handling in daily life.

作者:ZhenYu Zou, Xing Liu, ShiChuang Wang, YunLong Dong, LiNan Deng, Feng Hua, Jun Wan, Cheng Cheng

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 2611.08664:ForPC: Force-Aware Whole-Body Control for Precise Humanoid Cart Pushing ↗访问 2026-11-09