ICRA 2012 Paper Abstract


Paper TuA06.2

Rombokas, Eric (University Of Washington), Theodorou, Evangelos (University of Southern California), Malhotra, Mark (University of Washington), Todorov, Emanuel (University of Washington), Matsuoka, Yoky (University of Washington)

Tendon-Driven Control of Biomechanical and Robotic Systems: A Path Integral Reinforcement Learning Approach

Scheduled for presentation during the Regular Session "Applied Machine Learning" (TuA06), Tuesday, May 15, 2012, 08:45−09:00, Meeting Room 6 (Oya'te)

2012 IEEE International Conference on Robotics and Automation, May 14-18, 2012, RiverCentre, Saint Paul, Minnesota, USA

This information is tentative and subject to change. Compiled on August 19, 2018

Keywords Multifingered Hands, Biologically-Inspired Robots, Robust/Adaptive Control of Robotic Systems


We apply path integral reinforcement learning to a biomechanically accurate dynamics model of the index finger and then to the Anatomically Correct Testbed (ACT) robotic hand. We illustrate the applicability of Policy Improvement with Path Integrals to parameterized and non-parameterized control policies. This method is based on sampling variations in control, executing them in the real world, and minimizing a cost function on the resulting performance. Iteratively improving the control policy based on real-world performance requires no direct modeling of tendon network nonlinearities and contact transitions, allowing improved task performance.



Technical Content © IEEE Robotics & Automation Society

This site is protected by copyright and trademark laws under US and International law.
All rights reserved. © 2002-2018 PaperCept, Inc.
Page generated 2018-08-19  23:32:03 PST  Terms of use