Bayesian Gait Optimization for Bipedal Locomotion

File Description SizeFormat 
LION8.pdfAccepted version1.94 MBAdobe PDFDownload
Title: Bayesian Gait Optimization for Bipedal Locomotion
Author(s): Calandra, R
Gopalan, N
Seyfarth, A
Peters, J
Deisenroth, MP
Item Type: Chapter
Abstract: One of the key challenges in robotic bipedal locomotion is finding gait parameters that optimize a desired performance criterion, such as speed, robustness or energy efficiency. Typically, gait optimization requires extensive robot experiments and specific expert knowledge. We propose to apply data-driven machine learning to automate and speed up the process of gait optimization. In particular, we use Bayesian optimization to efficiently find gait parameters that optimize the desired performance metric. As a proof of concept we demonstrate that Bayesian optimization is near-optimal in a classical stochastic optimal control framework. Moreover, we validate our approach to Bayesian gait optimization on a low-cost and fragile real bipedal walker and show that good walking gaits can be efficiently found by Bayesian optimization. © 2014 Springer International Publishing.
Publication Date: 16-Feb-2014
URI: http://hdl.handle.net/10044/1/15225
DOI: http://dx.doi.org/10.1007/978-3-319-09584-4
ISBN: 978-3-319-09584-4
Publisher: Springer
Start Page: 274
End Page: 290
Journal / Book Title: Learning and Intelligent Optimization
Lecture Note in Computer Science
Format Info.: 8426
Copyright Statement: © Springer International Publishing Switzerland 2014. The final publication is available at link.springer.com
Publication Status: Published
Appears in Collections:Computing



Items in Spiral are protected by copyright, with all rights reserved, unless otherwise indicated.

Creative Commons