Physical Twins: Accelerating and Enabling Robot Learning with Phantom Platforms

Elizabeth Peiros, Derek Chen, Lucas Yager, Edward Lee, Kevin Wang, Zoe Samuels, Michael C. Yip · N/A · 2026

Summary

Abstract Summary

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.

Key Points

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.

Methods

Our physical twin design features a mechanical mechanism that emulates the complex anatomy of the shoulder, with attention to realistic grasping and maneuvering points: the wrist, arm, and armpit, typically used for lifting, dressing, and weight shifting.

The device provides the robot manipulator with forces that are sensible at a scale safe for the lab environment and supports an infinite number of individual user profiles, enabling proper testing of the true safety of a robotically assisted task.

Methods — Physical Twins: Accelerating and Enabling Robot Learning with Phantom Platforms — Figure 2: Top image, Fig (a), highlights the rotation of the clavicle bone when x-rayed. The labeling shows both the angular change and the translational motion of the shoulder socket. Bottom image, Fig (b), shows the translation of joint motion into a mechanical mechanism. From top to bottom the acromioclavicular joint is transformed into a pivot joint, the shoulder socket is transformed into a spherical manipulator, and the scapular motion is re-imagined as a 4-bar mechanism.

Experiments and Results

Taking the Jacobian for the three unique joints, the overall reachable space can be defined using the superposition (addition) of each joint’s ROM. A number of these results can be seen in Table I The humeral rotation given the initial pose, where the $\mathcal{B}$ and $\mathcal{C}$ frames are aligned, is [+330°, -270°]. Analysis of the force capabilities and singularities was done and is shown in Figure 5 (a).

Sources and Demonstrations

Figures are reproduced from Peiros et al. See the full paper for experimental details and the project page, when the paper links one, for demonstrations and videos.