Bayesian Optimization for Learning Gaits under Uncertainty

File Description SizeFormat 
AMAI.pdfAccepted version2.23 MBAdobe PDFView/Open
Title: Bayesian Optimization for Learning Gaits under Uncertainty
Authors: Calandra, R
Seyfarth, A
Peters, J
Deisenroth, MP
Item Type: Journal Article
Abstract: © 2015, Springer International Publishing Switzerland.Designing gaits and corresponding control policies is a key challenge in robot locomotion. Even with a viable controller parametrization, finding near-optimal parameters can be daunting. Typically, this kind of parameter optimization requires specific expert knowledge and extensive robot experiments. Automatic black-box gait optimization methods greatly reduce the need for human expertise and time-consuming design processes. Many different approaches for automatic gait optimization have been suggested to date. However, no extensive comparison among them has yet been performed. In this article, we thoroughly discuss multiple automatic optimization methods in the context of gait optimization. We extensively evaluate Bayesian optimization, a model-based approach to black-box optimization under uncertainty, on both simulated problems and real robots. This evaluation demonstrates that Bayesian optimization is particularly suited for robotic applications, where it is crucial to find a good set of gait parameters in a small number of experiments.
Issue Date: 26-Jun-2015
Date of Acceptance: 16-May-2015
URI: http://hdl.handle.net/10044/1/24167
DOI: https://dx.doi.org/10.1007/s10472-015-9463-9
ISSN: 1012-2443
Publisher: Springer
Start Page: 5
End Page: 23
Journal / Book Title: Annals in Mathematics and Artificial Intelligence
Volume: 76
Issue: 1
Copyright Statement: The final publication is available at Springer via https://dx.doi.org/10.1007/s10472-015-9463-9
Keywords: Artificial Intelligence & Image Processing
0801 Artificial Intelligence And Image Processing
0802 Computation Theory And Mathematics
0102 Applied Mathematics
Publication Status: Published
Appears in Collections:Faculty of Engineering
Computing



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

Creative Commons