Ruka-v2: Tendon Driven Open-Source Dexterous Hand with Wrist and Abduction for Robot Learning

2026-03-27

AI Summary

This work addresses the limited dexterity of existing open-source anthropomorphic hands, which commonly lack wrist mobility and independent finger abduction/adduction degrees of freedom essential for human-like manipulation. To overcome this, the authors present Ruka-v2—an open-source, tendon-driven robotic hand that integrates, for the first time, a decoupled two-degree-of-freedom parallel wrist mechanism with independently actuated finger abduction/adduction joints, all realized through 3D-printed components and enhanced by a data-driven fingertip control strategy. This design substantially improves fine manipulation capabilities and task adaptability in confined spaces. User studies demonstrate a 51.3% reduction in task completion time and a 21.2% increase in success rate compared to baseline systems. The platform’s effectiveness is further validated across 13 teleoperation tasks and three autonomous policy learning scenarios.

Abstract

Lack of accessible and dexterous robot hardware has been a significant bottleneck to achieving human-level dexterity in robots. Last year, we released Ruka, a fully open-sourced, tendon-driven humanoid hand with 11 degrees of freedom - 2 per finger and 3 at the thumb - buildable for under $1,300. It was one of the first fully open-sourced humanoid hands, and introduced a novel data-driven approach to finger control that captures tendon dynamics within the control system. Despite these contributions, Ruka lacked two degrees of freedom essential for closely imitating human behavior: wrist mobility and finger adduction/abduction. In this paper, we introduce Ruka-v2: a fully open-sourced, tendon-driven humanoid hand featuring a decoupled 2-DOF parallel wrist and abduction/adduction at the fingers. The parallel wrist adds smooth, independent flexion/extension and radial/ulnar deviation, enabling manipulation in confined environments such as cabinets. Abduction enables motions such as grasping thin objects, in-hand rotation, and calligraphy. We present the design of Ruka-v2 and evaluate it against Ruka through user studies on teleoperated tasks, finding a 51.3% reduction in completion time and a 21.2% increase in success rate. We further demonstrate its full range of applications for robot learning: bimanual and single-arm teleoperation across 13 dexterous tasks, and autonomous policy learning on 3 tasks. All 3D print files, assembly instructions, controller software, and videos are available at https://ruka-hand-v2.github.io/ .

Problem

• dexterous robot hand
• open-source hardware
• tendon-driven actuation
• wrist mobility
• finger abduction/adduction

Innovation

• tendon-driven
• dexterous hand
• parallel wrist
• abduction/adduction
• open-source robotics