BiDexHand: Design and Evaluation of an Open-Source 16-DoF Biomimetic Dexterous Hand

2025-04-20

AI Summary

How can human-level dexterity be achieved in robotic hands? This work introduces BiDexHand, an open-source 16-degree-of-freedom biomimetic dexterous hand. To address the trade-off between dexterity and manufacturability, we propose a novel mechanically coupled phalangeal design enabling natural, coordinated motion of five joints under a single actuator—preserving anthropomorphic dexterity while enhancing fabrication feasibility. The hand employs cable-driven actuation and modular, biomimetic phalanges, supporting full independent joint control and multimodal interfaces—including vision-based teleoperation. Experimental evaluation comprehensively covers all 33 grasp types in the GRASP Taxonomy; achieves 9 out of 11 Kapandji opposition scores; delivers fingertip forces up to 2.14 N and static load capacity of 4.54 kg. This work provides an open-hardware platform and a systematic, reproducible benchmark for low-cost, high-dexterity robotic hand research.

Technology Category

• Intelligent Robots: Manipulation
• Computer Vision: Biometrics, Face, Gesture & Pose
• Humans and AI: Interaction Techniques and Devices

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Economics, Online Markets and Human Computation: Research challenges in human and human-AI computation

Abstract

Achieving human-level dexterity in robotic hands remains a fundamental challenge for enabling versatile manipulation across diverse applications. This extended abstract presents BiDexHand, a cable-driven biomimetic robotic hand that combines human-like dexterity with accessible and efficient mechanical design. The robotic hand features 16 independently actuated degrees of freedom and 5 mechanically coupled joints through novel phalange designs that replicate natural finger motion. Performance validation demonstrated success across all 33 grasp types in the GRASP Taxonomy, 9 of 11 positions in the Kapandji thumb opposition test, a measured fingertip force of 2.14,N, and the capability to lift a 10,lb weight. As an open-source platform supporting multiple control modes including vision-based teleoperation, BiDexHand aims to democratize access to advanced manipulation capabilities for the broader robotics research community.

Problem

• Achieving human-level dexterity in robotic hands
• Designing accessible biomimetic hands for versatile manipulation
• Validating performance across diverse grasp and force tasks

Innovation

• Cable-driven biomimetic robotic hand design
• 16-DoF with novel phalange motion replication
• Open-source platform with vision-based teleoperation