Home
Resource
Designing and learning CPG gaits for spherical tensegrity robots using Bayesian optimization
PDF
PDF format is widely accepted and good for printing.
Plug-in required
PDF-1(3.59 MB)
Citation & Export
View Usage Statistics
Staff View

Citation & Export
Hide

Simple citation

Rennie, Colin M.. Designing and learning CPG gaits for spherical tensegrity robots using Bayesian optimization. Retrieved from https://doi.org/doi:10.7282/T3BK1GKV

Export

Click here for information about Citation Management Tools at Rutgers.

Statistics
Hide

Description

TitleDesigning and learning CPG gaits for spherical tensegrity robots using Bayesian optimization
NameRennie, Colin M. (author); Bekris, Kostas E (chair); Michmizos, Konstantinos (internal member); Boularias, Abdeslam (internal member); Rutgers University; School of Graduate Studies
Date Created2018
Other Date2018-01 (degree)
SubjectComputer Science, Robotics
Extent1 online resource (viii, 32 p. : ill.)
DescriptionThis thesis presents a framework for developing a library of gaits for highly non-linear, hyper-redundant, potentially compliant robotic systems. Examples of such systems that motivate this work include tensegrity robots, which combine both soft and rigid elements, and snake-like salamander robots. A library of gaits for such complex robots can be integrated with a search-based method so as to achieve more efficient exploration of the underlying state space when solving trajectory planning problems. The first component of the work corresponds to the definition of a Central Pattern Generator (CPG) for a spherical tensegrity robot inspired by similar solutions in the domain of modular, bio-inspired snake robots. The CPG provides a reparametrization of the underlying system, which can easily result in the generation of rhythmic gaits. The second component is a novel framework for simultaneously discovering effective gaits along different directions of motion by searching the space of CPG parameters. The framework defines multiple objectives, which are maximized though a parallel Bayesian Optimization (BO) process. The samples, which correspond to different gait parameters, are biased towards areas of previously observed high reward using a set of binary kNN classifiers with on-line updates. This integrated method is shown to be more efficient than Monte Carlo sampling of gait parameters or BO without classification or the classification only approach. The evaluation is performed in simulation using a high-dimensional spherical tensegrity robot.
NoteM.S.
NoteIncludes bibliographical references
Noteby Colin M. Rennie
Genretheses, ETD graduate
Persistent URLhttps://doi.org/doi:10.7282/T3BK1GKV
Languageeng
CollectionSchool of Graduate Studies Electronic Theses and Dissertations
Organization NameRutgers, The State University of New Jersey
RightsThe author owns the copyright to this work.
Version 8.5.5
Rutgers University Libraries - Copyright ©2024