Skip to content

论文arXiv 2611.171429 天前

FORGE:无腕部力传感器实现人形机器人稳定接触操作控制 ​

本文由 AI 根据公开内容整理,可能有误,请以原文为准:FORGE: Force-Aware Multi-Granularity Control for Efficient Humanoid Loco-Manipulation(arXiv 2611.17142)

核心内容 ​

针对人形机器人移动操作中遥操演示采集难、接触控制不稳定痛点,研究团队提出FORGE力感知多粒度控制框架。该系统采用从粗到细的命令空间设计,涵盖速度导航、平面落足、腕部位姿跟踪及可选力条件输入。训练阶段摒弃了对全身人体运动轨迹或关节角参考的依赖,部署时仅需稀疏的双侧腕部相对骨盆位姿、粗略运动指令及期望负载输入,显著降低了数据采集门槛与硬件成本,为复杂接触任务提供了实用化控制方案。

技术上,FORGE融合动量观测器与基于仿真接触力监督学习的修正模块处理持续接触。在无腕部力/力矩传感器条件下,通过本体感知与重构的低层手臂PD扭矩估计低频腕部等效交互力,并利用准静态虚拟目标环自适应调整腕部目标。系统采用冻结的运动先验与非对称残差动作来稳定由操作引起的全身修正。实验验证了其在统一控制稳定性、任务空间跟踪、准静态力估计、刚性箱体挤压力控制及不同负载下蹲举任务中的Diffusion Policy执行效果。

关键看点 ​

  • 无传感力估计:利用本体感知与重构低层手臂PD扭矩替代腕部力矩传感器,实现低频腕部等效交互力的实时估计与反馈控制
  • 多粒度命令空间:构建包含速度导航、平面落足、腕部位姿及力条件输入的层级化指令集,解耦移动与操作的控制复杂度
  • 低门槛策略训练:训练过程无需全身人体运动轨迹或关节角参考数据,部署仅需稀疏腕部相对骨盆位姿与粗略运动指令
  • 全身稳定机制:采用冻结运动先验结合非对称残差动作策略,有效抑制操作诱导的全身扰动,保障持续接触下的平衡

工程与产业观察 ​

FORGE通过算法补偿弥补了人形机器人腕部力传感缺失的硬件短板,利用PD扭矩重构与动量观测实现了低成本接触力感知。其免全身动捕的训练范式与多粒度控制架构,为解决具身智能移动操作中‘稳态接触’与‘数据采集难’两大工程瓶颈提供了可复现的技术路径,对推动人形机器人在非结构化环境下的精密作业具有重要参考价值。

英文摘要 (Abstract) ​

Humanoid loco-manipulation requires coordinated locomotion, balance regulation, and manipulation under frequent contacts, making teleoperated demonstration collection difficult: a practical controller must simultaneously provide precision, stability, and contact awareness. We propose FORGE, a force-aware multi-granularity control system with a coarse-to-fine command space spanning velocity navigation, planar foot placement, wrist-pose tracking, and optional force-conditioning inputs. Policy training requires no full-body human motion trajectories or joint-angle references; deployment consumes only sparse bilateral wrist poses relative to the pelvis, coarse motion commands, and optional desired wrist-load inputs. For sustained contact, FORGE combines a momentum observer with a learned correction trained using simulator contact-force supervision. At deployment, it estimates low-frequency, wrist-equivalent interaction forces from proprioception and reconstructed low-level arm PD torques, without wrist force/torque sensors. A quasi-static virtual-target loop uses this estimate and an optional desired applied-force input to adapt the wrist target. A frozen locomotion prior and asymmetric residual actions stabilize manipulation-induced whole-body corrections. Experiments evaluate unified-control stability, task-space tracking, quasi-static wrist-equivalent force estimation, squeezing forces during sustained contact with a rigid box, and downstream diffusion-policy execution of a squat-and-lift task across payload conditions. Website: https://bb0928.github.io/forge/.

作者:Liangjun Xing, Ke Fan, Kailin Li, Bin Wang, Xiaojie Niu, Qingwei Ben, Jiafei Cao, Wei Yao, Yebin Liu, Jingbo Wang, Weinan Zhang

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 2611.17142:FORGE: Force-Aware Multi-Granularity Control for Efficient Humanoid Loco-Manipulation ↗访问 2026-11-14