TWINS: A Tactile Wearable Isomorphic Arm Networked System for Contact-Rich Manipulation Learning

2026-08-03

AI Summary

This work addresses the challenge that existing robotic systems struggle to effectively capture and reproduce manipulation demonstrations involving contact between the arms and torso. To overcome this limitation, the authors propose an end-to-end imitation learning framework that integrates a wearable dual-arm device with an isomorphic robot, enabling, for the first time, synchronized motion and tactile sensing of full-body human contact—including both torso and arms—and facilitating demonstration, learning, and execution of contact-intensive tasks. The system combines distributed tactile sensing, wearable hardware, and imitation learning algorithms to successfully collect data from four representative tasks. Experimental validation on a physical robot demonstrates the effectiveness of the learned policies, significantly enhancing manipulation capabilities guided by bodily contact.

Abstract

Recent advances in robot learning for manipulation have increased the importance of collecting real-world demonstration data. However, existing robotic systems primarily focus on end-effector manipulation, making it difficult to teach and execute manipulation tasks involving body-surface contact with the arms and chest. This paper presents TWINS (Tactile Wearable Isomorphic Arm Networked System), a robotic system for manipulation involving body-surface contact. TWINS consists of a Wearable Dual-Arm Device, which is worn by the operator, and an Isomorphic Robot with the same joint configuration and external dimensions. Distributed tactile sensors embedded in the chest and arms enable the measurement of body-surface contact synchronized with joint motion. Using the Wearable Dual-Arm Device, we collected demonstrations for four manipulation tasks involving body-surface contact. We then trained imitation learning policies using the collected demonstrations and deployed them on the Isomorphic Robot, enabling manipulation guided by body-surface tactile observations. Experimental results demonstrate that TWINS provides a unified robotic system for demonstration, learning, and execution of manipulation involving body-surface contact. https://mmurooka.github.io/twins-project-page/

Problem

• body-surface contact
• manipulation learning
• tactile sensing
• wearable robotics
• contact-rich manipulation

Innovation

• tactile sensing
• wearable robotics
• isomorphic robot
• contact-rich manipulation
• imitation learning