CRAFT: A Tendon-Driven Hand with Hybrid Hard-Soft Compliance

πŸ“… 2026-03-12
πŸ“ˆ Citations: 0
✨ Influential: 0
πŸ“„ PDF
πŸ€– AI Summary
This work addresses the imbalance between rigidity and compliance in dexterous hands during contact-intensive manipulation, which often leads to poor impact resistance and limited load-bearing capacity. To overcome these limitations, the authors propose a tendon-driven anthropomorphic hand that innovatively integrates a hybrid hard–soft compliant structure: soft materials are embedded at the joints to absorb impacts, while rigid linkages are retained to ensure high payload capability and motion accuracy. The design further incorporates rolling-contact joints and a 15-motor fingertip actuation layout. Integrated with an open-source vision-based teleoperation and simulation platform, the hand demonstrates high repeatability, robustness, and exceptional durability in experiments, successfully achieving stable grasps of fragile and low-friction objects across all 33 Feix grasp types, with a total hardware cost under $600.

Technology Category

Application Category

πŸ“ Abstract
We introduce CRAFT hand, a tendon-driven anthropomorphic hand with hybrid hard-soft compliance for contact-rich manipulation. The design is based on a simple idea: contact is not uniform across the hand. Impacts concentrate at joints, while links carry most of the load. CRAFT places soft material at joints and keeps links rigid, and uses rollingcontact joint surfaces to keep flexion on repeatable motion paths. Fifteen motors mounted on the fingers drive the hand through tendons, keeping the form factor compact and the fingers light. In structural tests, CRAFT improves strength and endurance while maintaining comparable repeatability. In teleoperation, CRAFT improves handling of fragile and low-friction items, and the hand covers 33/33 grasps in the Feix taxonomy. The full design costs under $600 and will be released open-source with visionbased teleoperation and simulation integration. Project page: http://craft-hand.github.io/
Problem

Research questions and friction points this paper is trying to address.

tendon-driven hand
hybrid compliance
contact-rich manipulation
anthropomorphic hand
grasping fragile objects
Innovation

Methods, ideas, or system contributions that make the work stand out.

hybrid hard-soft compliance
tendon-driven hand
rolling-contact joints
anthropomorphic manipulation
open-source robotic hand
πŸ”Ž Similar Papers
No similar papers found.
L
Leo Lin
University of Illinois Urbana-Champaign
S
Shivansh Patel
University of Illinois Urbana-Champaign
J
Jay Moon
University of Illinois Urbana-Champaign
Svetlana Lazebnik
Svetlana Lazebnik
University of Illinois at Urbana-Champaign
Computer visionrecognition
Unnat Jain
Unnat Jain
University of California, Irvine
Deep LearningComputer VisionRobotics