Skip to content

论文arXiv 2611.04083今天

MABEL开源移动双臂平台发布:56自由度成本8.1千美元支持全身遥操 ​

本文由 AI 根据公开内容整理,可能有误,请以原文为准:MABEL: An Open Anthropomorphic Mobile Bimanual Platform for Teleoperation and Learning(arXiv 2611.04083)

核心内容 ​

针对现有商业移动双臂平台昂贵及开源方案能力割裂的痛点,研究团队发布MABEL开源人形移动双臂机器人。该平台拥有56个自由度,零部件成本控制在8100美元,指尖作业高度覆盖地面至2.23米。其核心突破在于利用Apple Vision Pro头手追踪实现无手柄全身遥操作,立体视频玻璃到玻璃平均延迟仅137ms,并验证了从遥操数据采集到策略部署的端到端模仿学习管线。

硬件架构集成双7自由度机械臂、17自由度灵巧手、俯仰躯干、升降机构、3自由度颈部及全向底盘,臂体支持背驱顺应交互。感知方面,头颈联动使相机建模覆盖范围较固定躯干提升约3倍。软件层提供统一指令接口与全身控制器,解决多部件协同难题,确保遥操作数据可直接用于训练,降低了具身智能研究中高机动双臂平台的软硬件集成与算法验证门槛。

关键看点 ​

  • 整机规格:56自由度含17DOF灵巧手与升降躯干,指尖触达2.23m,BOM成本8.1k美元
  • 遥操性能:基于Apple Vision Pro全身追踪,Wi-Fi热点下立体视频平均延迟137ms
  • 感知增强:3DOF颈部与俯仰躯干联动,相机建模覆盖范围较固定躯干方案提升约3倍
  • 学习闭环:提供共享指令接口与全身控制器,打通遥操采集到模仿学习策略部署全流程

工程与产业观察 ​

MABEL以8.1k美元成本补齐了开源社区在“移动+双臂+灵巧手”全栈平台的空白。其基于消费级VR设备的低延迟全身遥操方案与标准化 imitation learning 管线,显著降低了高质量具身数据采集与算法验证的工程门槛,为学术界与初创团队提供了高性价比的移动操作研究基准。

英文摘要 (Abstract) ​

As robot learning moves beyond the tabletop, many tasks require mobility, adjustable reach, active perception, and bimanual dexterity. Commercial platforms combining these capabilities are costly, while affordable open-source alternatives cover only a subset and require software integration. We present MABEL, an open-source anthropomorphic mobile bimanual robot with 56 degrees of freedom (DOF) and a US$8.1k parts cost. It combines two 7-DOF arms with 17-DOF hands, a pitching torso, a lift, a 3-DOF neck, and a holonomic base. Back-drivable arms and torso support compliant interaction, with fingertip reach from floor level to 2.23 m. The head and torso roughly triple modeled camera coverage relative to a torso-fixed camera. Apple Vision Pro head and hand tracking enables whole-body teleoperation without handheld controllers, with 137 ms mean glass-to-glass stereo video latency over the robot's Wi-Fi hotspot. We demonstrate an end-to-end imitation learning pipeline, from teleoperated data collection to policy deployment, using a shared command interface and whole-body controller.

作者:Qilong Cheng, Rooholla Khorrambakht, Mohamed Yassine Kabouri, Quang Nam Nguyen, Luca Macesanu, Haoran Zhou, Yipeng Wang, Ludovic Righetti

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。

来源

本页事实对应的公开页面,以原文为准。

  1. arXiv 2611.04083:MABEL: An Open Anthropomorphic Mobile Bimanual Platform for Teleoperation and Learning访问 2026-11-04