Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

WHED: A Wearable Hand Exoskeleton for Natural, High-Quality Demonstration Collection

Mingzhang Zhu, Alvin Zhu, Jose Victor S. H. Ramos, Beom Jun Kim, Yike Shi, Yufeng Wu, Ruochen Hou, Quanyou Wang, Eric Song, Tony Fan, Yuchen Cui, Dennis W. Hong

TL;DR

WHED addresses the bottleneck in scalable, high-fidelity dexterous demonstrations by combining a wearability-first hand exoskeleton with a free-to-move thumb and a passive data-capture hand. It delivers an end-to-end pipeline that synchronizes finger encoders, AR-based end-effector pose, and wrist-mounted vision, plus post-processing for time alignment and replay. The approach enables demonstrations that span precision pinch to full-hand enclosure and shows qualitative replay fidelity, suggesting a practical path toward scalable dexterous manipulation learning in-the-wild. The work combines mechanical design with an integrated data pipeline to lower barriers to large-scale, realistic demonstrations for high-DoF robotic hands.

Abstract

Scalable learning of dexterous manipulation remains bottlenecked by the difficulty of collecting natural, high-fidelity human demonstrations of multi-finger hands due to occlusion, complex hand kinematics, and contact-rich interactions. We present WHED, a wearable hand-exoskeleton system designed for in-the-wild demonstration capture, guided by two principles: wearability-first operation for extended use and a pose-tolerant, free-to-move thumb coupling that preserves natural thumb behaviors while maintaining a consistent mapping to the target robot thumb degrees of freedom. WHED integrates a linkage-driven finger interface with passive fit accommodation, a modified passive hand with robust proprioceptive sensing, and an onboard sensing/power module. We also provide an end-to-end data pipeline that synchronizes joint encoders, AR-based end-effector pose, and wrist-mounted visual observations, and supports post-processing for time alignment and replay. We demonstrate feasibility on representative grasping and manipulation sequences spanning precision pinch and full-hand enclosure grasps, and show qualitative consistency between collected demonstrations and replayed executions.

WHED: A Wearable Hand Exoskeleton for Natural, High-Quality Demonstration Collection

TL;DR

WHED addresses the bottleneck in scalable, high-fidelity dexterous demonstrations by combining a wearability-first hand exoskeleton with a free-to-move thumb and a passive data-capture hand. It delivers an end-to-end pipeline that synchronizes finger encoders, AR-based end-effector pose, and wrist-mounted vision, plus post-processing for time alignment and replay. The approach enables demonstrations that span precision pinch to full-hand enclosure and shows qualitative replay fidelity, suggesting a practical path toward scalable dexterous manipulation learning in-the-wild. The work combines mechanical design with an integrated data pipeline to lower barriers to large-scale, realistic demonstrations for high-DoF robotic hands.

Abstract

Scalable learning of dexterous manipulation remains bottlenecked by the difficulty of collecting natural, high-fidelity human demonstrations of multi-finger hands due to occlusion, complex hand kinematics, and contact-rich interactions. We present WHED, a wearable hand-exoskeleton system designed for in-the-wild demonstration capture, guided by two principles: wearability-first operation for extended use and a pose-tolerant, free-to-move thumb coupling that preserves natural thumb behaviors while maintaining a consistent mapping to the target robot thumb degrees of freedom. WHED integrates a linkage-driven finger interface with passive fit accommodation, a modified passive hand with robust proprioceptive sensing, and an onboard sensing/power module. We also provide an end-to-end data pipeline that synchronizes joint encoders, AR-based end-effector pose, and wrist-mounted visual observations, and supports post-processing for time alignment and replay. We demonstrate feasibility on representative grasping and manipulation sequences spanning precision pinch and full-hand enclosure grasps, and show qualitative consistency between collected demonstrations and replayed executions.
Paper Structure (26 sections, 1 equation, 9 figures)

This paper contains 26 sections, 1 equation, 9 figures.

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 Modification
  9. Thumb Linkage
  10. Finger Linkage
  11. Wearability Attachment
  12. Electronics
  13. Data Collection Pipeline
  14. Data Collection
  15. Finger Position Data
  16. ...and 11 more sections

Figures (9)

  • Figure 1: A demonstration of a user picking up tweezers and using it to grasp an XT-30 connector.
  • Figure 2: Mechanical overview of WHED. WHED integrates a linkage-driven wearable exoskeleton, a passive data-capture hand, and an onboard sensing/power module. Insets highlight key subsystems: (a) pose-tolerant thumb coupling interface, (b) passive finger slider for cross-user fit, and (c) parallel four-bar finger linkage for motion transmission.
  • Figure 3: Passive-hand modification for kinematic executability and robust sensing. (a) URDF-based kinematic identification of the underactuated thumb informs a linkage–slider mechanism that decouples and reproduces the intended thumb DOFs. (b) Rigid encoder mounting with alignment ribs suppresses backlash-induced noise during dynamic operation.
  • Figure 4: Pose-tolerant thumb coupling: (a) Kinematic schematic of the thumb exoskeleton and its distal/metacarpal linkages with multi-DoF joints (a1–a8). (b) Example “wiggle space” during which the exoskeleton body can translate/rotate relative to the palm while the passive thumb posture remains unchanged.
  • Figure 5: Electronic system overview of the exoskeleton.
  • ...and 4 more figures