TriFinger: An Open-Source Robot for Learning Dexterity

TL;DR

TriFinger is an affordable, open-source robotic platform designed for safe, real-time dexterous manipulation experiments, enabling rapid development and testing of machine learning algorithms in robotics.

Contribution

The paper introduces a cost-effective, robust, and versatile robotic platform with software that supports real-time control and deep learning, facilitating research in robotic dexterity.

Findings

Successfully performed real-time optimal control experiments

Enabled deep reinforcement learning from scratch

Demonstrated complex interactions like throwing and writing

Abstract

Dexterous object manipulation remains an open problem in robotics, despite the rapid progress in machine learning during the past decade. We argue that a hindrance is the high cost of experimentation on real systems, in terms of both time and money. We address this problem by proposing an open-source robotic platform which can safely operate without human supervision. The hardware is inexpensive (about \SI{5000}[\$]{}) yet highly dynamic, robust, and capable of complex interaction with external objects. The software operates at 1-kilohertz and performs safety checks to prevent the hardware from breaking. The easy-to-use front-end (in C++ and Python) is suitable for real-time control as well as deep reinforcement learning. In addition, the software framework is largely robot-agnostic and can hence be used independently of the hardware proposed herein. Finally, we illustrate the potential of the proposed platform through a number of experiments, including real-time optimal control, deep reinforcement learning from scratch, throwing, and writing.