Getting the Ball Rolling: Learning a Dexterous Policy for a Biomimetic Tendon-Driven Hand with Rolling Contact Joints

TL;DR

This paper presents a novel biomimetic tendon-driven robotic hand with rolling contact joints, trained via reinforcement learning in simulation, achieving successful zero-shot transfer of dexterous manipulation skills to the physical robot.

Contribution

Introduction of a 3D printable, high-DoF biomimetic hand with tendon-driven rolling contact joints and a simulation-based RL training framework for real-world dexterous manipulation.

Findings

Successful zero-shot transfer of in-hand sphere rotation skill to the physical hand.

Development of a robust, 3D printable tendon-driven hand design.

Effective simulation-to-real transfer using GPU-based RL training.

Abstract

Biomimetic, dexterous robotic hands have the potential to replicate much of the tasks that a human can do, and to achieve status as a general manipulation platform. Recent advances in reinforcement learning (RL) frameworks have achieved remarkable performance in quadrupedal locomotion and dexterous manipulation tasks. Combined with GPU-based highly parallelized simulations capable of simulating thousands of robots in parallel, RL-based controllers have become more scalable and approachable. However, in order to bring RL-trained policies to the real world, we require training frameworks that output policies that can work with physical actuators and sensors as well as a hardware platform that can be manufactured with accessible materials yet is robust enough to run interactive policies. This work introduces the biomimetic tendon-driven Faive Hand and its system architecture, which uses tendon-driven rolling contact joints to achieve a 3D printable, robust high-DoF hand design. We model each element of the hand and integrate it into a GPU simulation environment to train a policy with RL, and achieve zero-shot transfer of a dexterous in-hand sphere rotation skill to the physical robot hand.