Author
Kormushev, P., Uğurlu, Regaip Barkan, Caldwell, D. G., Tsagarakis, N. G.
Publication Date
2019-01
Publication Place
-
Springer Nature
Subject
Bipedal walking, Energy efficiency, Reinforcement learning, Passive compliance
Type
Periodical
Language
English
Digital
Yes
Manuscript
No
Library
Özyeğin University
Library Asset ID
0929-5593
Record ID
a0ae91cf-57bb-4ed3-9446-ee83c9e30625
Library Location
Mechanical Engineering
Date
2019-01
Notes
EU project AMARSi
Sample Text
Modern humanoid robots include not only active compliance but also passive compliance. Apart from improved safety and dependability, availability of passive elements, such as springs, opens up new possibilities for improving the energy efficiency. With this in mind, this paper addresses the challenging open problem of exploiting the passive compliance for the purpose of energy efficient humanoid walking. To this end, we develop a method comprising two parts: an optimization part that finds an optimal vertical center-of-mass trajectory, and a walking pattern generator part that uses this trajectory to produce a dynamically-balanced gait. For the optimization part, we propose a reinforcement learning approach that dynamically evolves the policy parametrization during the learning process. By gradually increasing the representational power of the policy parametrization, it manages to find better policies in a faster and computationally efficient way. For the walking generator part, we develop a variable-center-of-mass-height ZMP-based bipedal walking pattern generator. The method is tested in real-world experiments with the bipedal robot COMAN and achieves a significant 18% reduction in the electric energy consumption by learning to efficiently use the passive compliance of the robot.
DOI
10.1007/s10514-018-9697-6
Cilt
43
