Whole-Body Teleoperation for Mobile Manipulation at Zero Added Cost

TL;DR

This paper introduces MoMa-Teleop, a cost-effective teleoperation method enabling whole-body control of mobile manipulators using standard interfaces, which accelerates data collection and improves learning transferability.

Contribution

MoMa-Teleop allows whole-body teleoperation without additional hardware by inferring end-effector motions and delegating base movements to reinforcement learning, reducing setup costs and increasing flexibility.

Findings

Reduces task completion time across various robots and tasks.

Enables efficient imitation learning from minimal demonstrations.

Transfers skills to new settings with limited data.

Abstract

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. We make code and videos available at https://moma-teleop.cs.uni-freiburg.de.