DexEXO: A Wearability-First Dexterous Exoskeleton for Operator-Agnostic Demonstration and Learning
This work addresses the problem of scalable cross-operator data collection for robot learning, representing an incremental improvement by simplifying the pipeline without sacrificing task performance.
The authors tackled the challenge of collecting high-quality demonstrations for dexterous robot learning across diverse operators by developing DexEXO, a wearability-first hand exoskeleton that aligns visual appearance, contact geometry, and kinematics at the hardware level, achieving competitive performance with diffusion policies trained from raw RGB observations.
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/