Learning Fast and Precise Pixel-to-Torque Control: A Platform for Reproducible Research of Learning on Hardware

IEEE Robotics & Automation Magazine, vol. 29, pp. 75–84

Abstract

In the field, robots often need to operate in unknown and unstructured environments, where accurate sensing and state estimation (SE) become a major challenge. Cameras have been used with great success in mapping and planning in such environments[1]as well as complex but quasi-static tasks, such as grasping[2], but are rarely integrated into the control loop for unstable systems. Learning pixel-to-torque control promises to enable robots to flexibly handle a wider variety of tasks. While reinforcement learning (RL) offers a solution in principle, learning pixel-to-torque control for unstable systems that require precise and high-bandwidth control still presents a significant practical challenge, and best practices have not been established. Part of the reason is that many of the most auspicious tools, such as deep neural networks (DNNs), are opaque: the cause for success on one system is difficult to interpret and generalize.

Authors 3

1. Steffen Bleher

   Max Planck Institute for Intelligent Systems

   Affiliation as printed

   Intelligent Control Systems Group, Max Planck Institute for Intelligent Systems, Stuttgart, Germany

   Intelligent Control Systems Group, Max Planck Institute for Intelligent Systems, Stuttgart, Germany;

2. Steve Heim

   Massachusetts Institute of Technology · Max Planck Institute for Intelligent Systems

   Affiliation as printed

   Intelligent Control Systems Group, Max Planck Institute for Intelligent Systems, Stuttgart, Germany

   Biomimetic Robotics Lab, Massachusetts Institute of Technology, Cambridge, USA;

   Intelligent Control Systems Group, Max Planck Institute for Intelligent Systems, Stuttgart, Germany;

3. Sebastian Trimpe Aachen Institute for Data Science in Mechanical Engineering

   RWTH Aachen University · Max Planck Institute for Intelligent Systems

   Affiliation as printed

   Intelligent Control Systems Group, Max Planck Institute for Intelligent Systems, Stuttgart, Germany

   Institute for Data Science in Mechanical Engineering, RWTH Aachen University, Aachen, Germany

   Intelligent Control Systems Group, Max Planck Institute for Intelligent Systems, Stuttgart, Germany;