Replicating Human Anatomy with Vision Controlled Jetting – A Pneumatic Musculoskeletal Hand and Forearm

2024-04-14

International Conference on Soft Robotics

AI Summary

Existing myoelectric and robotic hand-forearm systems struggle to simultaneously achieve anatomical fidelity, dexterity, and low-cost actuation. Method: This work proposes a fully pneumatic, monolithic solution fabricated via single-step vision-controlled jetting 3D printing, integrating rigid skeletal structures, compliant joint capsules, biomimetic tendons, and embedded flexible tactile sensors. It introduces a novel thin-profile, low-cost pneumatic artificial muscle (PAM) with 30.1% strain, enabling a 22-channel independently controllable actuation array for anatomically accurate hand–forearm coordination. Results: The system enables individual finger control and multiscale grasping—from a 0.5 g coin to a 272 g aluminum can—with fingertip force, grip strength, and joint range of motion matching human physiological benchmarks. This represents the first demonstration of high-fidelity biomechanical performance coupled with fully pneumatic actuation in an integrated hand–forearm prosthesis.

Technology Category

• Intelligent Robots: Manipulation
• Computer Vision: Biometrics, Face, Gesture & Pose
• Humans and AI: Game Design — Procedural Content Generation & Storytelling

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

The functional replication and actuation of complex structures inspired by nature is a longstanding goal for humanity. Creating such complex structures combining soft and rigid features and actuating them with artificial muscles would further our understanding of natural kinematic structures. We printed a biomimetic hand in a single print process comprised of a rigid skeleton, soft joint capsules, tendons, and printed touch sensors. We showed it's actuation using electric motors. In this work, we expand on this work by adding a forearm that is also closely modeled after the human anatomy and replacing the hand's motors with 22 independently controlled pneumatic artificial muscles (PAMs). Our thin, high-strain (up to 30.1 %) PAMs match the performance of state-of-the-art artificial muscles at a lower cost. The system showcases human-like dexterity with independent finger movements, demonstrating successful grasping of various objects, ranging from a small, lightweight coin to a large can of 272 g in weight. The performance evaluation, based on fingertip and grasping forces along with finger joint range of motion, highlights the system's potential.

Problem

• Replicating human hand anatomy with pneumatic artificial muscles
• Developing low-cost high-strain artificial muscles for biomimetic systems
• Creating dexterous robotic hands capable of grasping diverse objects

Innovation

• Vision Controlled Jetting for single-print biomimetic structures
• Pneumatic artificial muscles replacing electric motors
• High-strain thin PAMs enabling human-like dexterity