Physical Twins: Accelerating and Enabling Robot Learning with Phantom Platforms

2026-10-02

AI Summary

This study addresses the safety risks, ethical constraints, and limited reproducibility inherent in human-robot physical interaction experiments by proposing a novel phantom platform as a physical human twin to replace live subjects during robotic reinforcement learning evaluations. Overcoming the limitations of conventional devices, the platform achieves high-fidelity replication of the shoulder ball-and-socket joint and scapular multidimensional kinematics, supporting complex three-dimensional joint limit rendering. Integrated with the Franka Panda manipulator’s perception system and reinforcement learning algorithms, it enables efficient real-world validation of interaction policies. Experimental results demonstrate that the device exhibits superior multi-degree-of-freedom limit rendering capabilities, effectively validating the manipulator’s safe perception and interactive performance in activities of daily living and human-robot collaboration tasks.

Abstract

Improvements in human-robot physical interaction (pHRI) can have major implications for physical therapy, search and rescue, and telemedicine. However, a major challenge concerns human constraints and safety in human-robot physical experiments. Concerns about human studies also include repeatability, scalability, and participant diversity. To conduct such experiments, an IRB and willing human participants are required. In this work, we present an improved phantom device, a physical twin, that enables real-world RL-type testing for physically interactive algorithms. The new device not only replicates the ball-and-socket motion of the shoulder but also renders scapular and protraction/retraction motions. The experiments showcase the device's ability to render multiple 3D joint limits and demonstrate a Franka Panda arm sensing limits and interacting with the device as an arm for ADLs (activities of daily living) and pHRI tasks.

Problem

• physical human-robot interaction
• robot learning
• safety constraints
• reproducibility
• phantom device

Innovation

• Physical Twins
• Phantom Platforms
• Robot Learning
• Human-Robot Physical Interaction
• Reinforcement Learning