Universal Manipulation Exoskeleton: Learning Compliant Whole-body Policies with Real-time Torque Feedback
arXiv:2606.14218v1 Announce Type: cross Abstract: For robots to work safely in household environments, they need to be compliant and react to torque and force feedback during contact. However, the majority of existing data collection pipelines still lack the ability to capture force and torque data for learning active compliant policies. In this paper, we present Universal Manipulation Exoskeleton (UME), an upper-limb exoskeleton that provides real-time haptic torque feedback while recording whole-arm configurations and joint torque signals for teleoperation. With transparent torque feedback,
The increasing demand for robots in everyday environments necessitates advanced compliance and feedback mechanisms, making this development timely for safer human-robot interaction.
This exoskeleton directly addresses a critical bottleneck in robotic learning: the ability to capture real-time force and torque data for developing truly compliant and adaptive AI policies.
The development and deployment of Universal Manipulation Exoskeleton (UME) could significantly accelerate the training and capabilities of compliant robots, particularly for unstructured environments.
- · Robotics research institutions
- · AI development companies
- · Automated logistics
- · Elder care providers
- · Companies relying on non-compliant robotic solutions
- · Manual labor in repetitive physical tasks
Improved robotic manipulation and safety through enhanced data collection for compliant policies.
Faster development and deployment of advanced humanoid robots capable of interacting safely in human-centric spaces.
Accelerated integration of robots into household and service sectors, transforming daily life and labor markets.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.AI