Learning Fast and Precise Pixel-to-Torque Control

TL;DR

This paper introduces a platform for learning pixel-to-torque control on unstable systems, demonstrated on a vision-based Furuta pendulum, enabling high-frequency control and reproducible research in this challenging area.

Contribution

The authors present a flexible, reproducible platform for learning pixel-to-torque control on unstable systems, and demonstrate the first high-frequency (over 100 Hz) learning on such a system.

Findings

Successful implementation of pixel-to-torque control at over 100 Hz.

Platform supports reproducible research with off-the-shelf hardware.

First demonstration of high-frequency learning on an unstable system.

Abstract

In the field, robots often need to operate in unknown and unstructured environments, where accurate sensing and state estimation (SE) becomes a major challenge. Cameras have been used to great success in mapping and planning in such environments, as well as complex but quasi-static tasks such as grasping, but are rarely integrated into the control loop for unstable systems. Learning pixel-to-torque control promises to allow robots to flexibly handle a wider variety of tasks. Although they do not present additional theoretical obstacles, learning pixel-to-torque control for unstable systems that that require precise and high bandwidth control still poses a significant practical challenge, and best practices have not yet been established. To help drive reproducible research on the practical aspects of learning pixel-to-torque control, we propose a platform that can flexibly represent the entire process, from lab to deployment, for learning pixel-to-torque control on a robot with fast, unstable dynamics: the vision-based Furuta pendulum. The platform can be reproduced with either off-the-shelf or custom-built hardware. We expect that this platform will allow researchers to quickly and systematically test different approaches, as well as reproduce and benchmark case studies from other labs. We also present a first case study on this system using DNNs which, to the best of our knowledge, is the first demonstration of learning pixel-to-torque control on an unstable system with update rates faster than 100 Hz. A video synopsis can be found online at https://youtu.be/S2llScfG-8E, and in the supplementary material.