Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

DexEXO: A Wearability-First Dexterous Exoskeleton for Operator-Agnostic Demonstration and Learning

Alvin Zhu, Mingzhang Zhu, Beom Jun Kim, Jose Victor S. H. Ramos, Yike Shi, Yufeng Wu, Raayan Dhar, Fuyi Yang, Ruochen Hou, Hanzhang Fang, Quanyou Wang, Yuchen Cui, Dennis W. Hong

Abstract

Scaling dexterous robot learning is constrained by the difficulty of collecting high-quality demonstrations across diverse operators. Existing wearable interfaces often trade comfort and cross-user adaptability for kinematic fidelity, while embodiment mismatch between demonstration and deployment requires visual post-processing before policy training. We present DexEXO, a wearability-first hand exoskeleton that aligns visual appearance, contact geometry, and kinematics at the hardware level. DexEXO features a pose-tolerant thumb mechanism and a slider-based finger interface analytically modeled to support hand lengths from 140~mm to 217~mm, reducing operator-specific fitting and enabling scalable cross-operator data collection. A passive hand visually matches the deployed robot, allowing direct policy training from raw wrist-mounted RGB observations. User studies demonstrate improved comfort and usability compared to prior wearable systems. Using visually aligned observations alone, we train diffusion policies that achieve competitive performance while substantially simplifying the end-to-end pipeline. These results show that prioritizing wearability and hardware-level embodiment alignment reduces both human and algorithmic bottlenecks without sacrificing task performance. Project Page: https://dexexo-research.github.io/

DexEXO: A Wearability-First Dexterous Exoskeleton for Operator-Agnostic Demonstration and Learning

Abstract

Scaling dexterous robot learning is constrained by the difficulty of collecting high-quality demonstrations across diverse operators. Existing wearable interfaces often trade comfort and cross-user adaptability for kinematic fidelity, while embodiment mismatch between demonstration and deployment requires visual post-processing before policy training. We present DexEXO, a wearability-first hand exoskeleton that aligns visual appearance, contact geometry, and kinematics at the hardware level. DexEXO features a pose-tolerant thumb mechanism and a slider-based finger interface analytically modeled to support hand lengths from 140~mm to 217~mm, reducing operator-specific fitting and enabling scalable cross-operator data collection. A passive hand visually matches the deployed robot, allowing direct policy training from raw wrist-mounted RGB observations. User studies demonstrate improved comfort and usability compared to prior wearable systems. Using visually aligned observations alone, we train diffusion policies that achieve competitive performance while substantially simplifying the end-to-end pipeline. These results show that prioritizing wearability and hardware-level embodiment alignment reduces both human and algorithmic bottlenecks without sacrificing task performance. Project Page: https://dexexo-research.github.io/
Paper Structure (35 sections, 8 equations, 7 figures, 2 tables)

This paper contains 35 sections, 8 equations, 7 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Teleoperation for Dexterous Manipulation
  4. Learning from Human Hand Videos
  5. Exoskeleton and Mechanically Coupled Interfaces
  6. Hardware Design
  7. Hardware Overview
  8. Passive Hand
  9. Wearability-First Design for Cross-Operator Deployment
  10. Slider-Based Finger Interface
  11. Swappable Compliant Thumb Interface
  12. Pose-tolerant Thumb Mechanism
  13. Mechanism overview
  14. Simplified kinematic model
  15. Residual pose freedom and self-alignment.
  16. ...and 20 more sections

Figures (7)

  • Figure 1: System overview of DexEXO. (a) Full device worn on a user's hand. (b) Demonstrations of piano playing, full-hand grasping, and scissors cutting. (c) Policy deployment on the robot.
  • Figure 2: Mechanical overview of DexEXO. DexEXO integrates a linkage-driven wearable exoskeleton, a passive data-capture hand, and an onboard sensing/power module. Insets highlight key subsystems: (a) passive finger slider for cross-user fit, (b) pose-tolerant thumb coupling interface, (c) parallel four-bar finger linkage for motion transmission, and (d) passive hand thumb that reproduces the intended thumb DOF
  • Figure 3: Kinematic schematic of the exoskeleton thumb and its distal and metacarpal linkages. The four swivel joints (shown in purple) allow self-alignment between the exoskeleton frame ${E}$ and the palm base frame ${B}$ while maintaining fixed linkage lengths $L_d$ and $L_m$.
  • Figure 4: An overview of the full demonstration data modalities, policy training, and inference with visual-aligned observations.
  • Figure 5: Subjective feedback results in user study (mean $\pm$ std.). $^{\dagger}$ Finger independence is not applicable to teleoperation, as the user’s natural hand motion is unconstrained.
  • ...and 2 more figures