Whole-Body Teleoperation for Mobile Manipulation at Zero Added Cost

被引:0
作者
Honerkamp, Daniel [1 ]
Mahesheka, Harsh [1 ]
Von Hartz, Jan Ole [1 ]
Welschehold, Tim [1 ]
Valada, Abhinav [1 ]
机构
[1] University of Freiburg, Department of Computer Science, Freiburg im Breisgau
关键词
imitation learning; mobile manipulation; Teleoperation;
D O I
10.1109/LRA.2025.3540582
中图分类号
学科分类号
摘要
Demonstration data plays a key role in learning complex behaviors and training robotic foundation models. While effective control interfaces exist for static manipulators, data collection remains cumbersome and time intensive for mobile manipulators due to their large number of degrees of freedom. While specialized hardware, avatars, or motion tracking can enable whole-body control, these approaches are either expensive, robot-specific, or suffer from the embodiment mismatch between robot and human demonstrator. In this work, we present MoMa-Teleop, a novel teleoperation method that infers end-effector motions from existing interfaces and delegates the base motions to a previously developed reinforcement learning agent, leaving the operator to focus fully on the task-relevant end-effector motions. This enables whole-body teleoperation of mobile manipulators with no additional hardware or setup costs via standard interfaces such as joysticks or hand guidance. Moreover, the operator is not bound to a tracked workspace and can move freely with the robot over spatially extended tasks. We demonstrate that our approach results in a significant reduction in task completion time across a variety of robots and tasks. As the generated data covers diverse whole-body motions without embodiment mismatch, it enables efficient imitation learning. By focusing on task-specific end-effector motions, our approach learns skills that transfer to unseen settings, such as new obstacles or changed object positions, from as little as five demonstrations. © 2025 IEEE.
引用
收藏
页码:3198 / 3205
页数:7
相关论文
共 46 条
  • [41] Unified Approach for Hybrid Motion Control of MOCA Based on Weighted Whole-Body Cartesian Impedance Formulation
    Wu, Yuqiang
    Lamon, Edoardo
    Zhao, Fei
    Kim, Wansoo
    Ajoudani, Arash
    [J]. IEEE ROBOTICS AND AUTOMATION LETTERS, 2021, 6 (02) : 3505 - 3512
  • [42] Remote mobile manipulation with the centauro robot: Full-body telepresence and autonomous operator assistance
    Klamt, Tobias
    Schwarz, Max
    Lenz, Christian
    Baccelliere, Lorenzo
    Buongiorno, Domenico
    Cichon, Torben
    DiGuardo, Antonio
    Droeschel, David
    Gabardi, Massimiliano
    Kamedula, Malgorzata
    Kashiri, Navvab
    Laurenzi, Arturo
    Leonardis, Daniele
    Muratore, Luca
    Pavlichenko, Dmytro
    Periyasamy, Arul S.
    Rodriguez, Diego
    Solazzi, Massimiliano
    Frisoli, Antonio
    Gustmann, Michael
    Rossmann, Juergen
    Suess, Uwe
    Tsagarakis, Nikos G.
    Behnke, Sven
    [J]. JOURNAL OF FIELD ROBOTICS, 2020, 37 (05) : 889 - 919
  • [43] Where Should I Look? Optimised Gaze Control for Whole-Body Collision Avoidance in Dynamic Environments
    Finean, Mark Nicholas
    Merkt, Wolfgang
    Havoutis, Ioannis
    [J]. IEEE ROBOTICS AND AUTOMATION LETTERS, 2022, 7 (02) : 1095 - 1102
  • [44] Whole Body Control of Mobile Manipulators With Series Elastic Actuators for Cart Pushing Tasks
    Ren, Xiaoqian
    Li, Zhijun
    Zhou, MengChu
    [J]. IEEE TRANSACTIONS ON CYBERNETICS, 2024, 54 (12) : 7891 - 7904
  • [45] Whole-body motion generation integrating operator's intention and robot's autonomy in controlling humanoid robots
    Neo, Ee Sian
    Yokoi, Kazuhito
    Kajita, Shuuji
    Tanie, Kazuo
    [J]. IEEE TRANSACTIONS ON ROBOTICS, 2007, 23 (04) : 763 - 775
  • [46] Whole Body Control of a Dual-Arm Mobile Robot Using a Virtual Kinematic Chain
    Wang, Yuquan
    Smith, Christian
    Karayiannidis, Yiannis
    Ogren, Petter
    [J]. INTERNATIONAL JOURNAL OF HUMANOID ROBOTICS, 2016, 13 (01)