Please use this identifier to cite or link to this item: https://doi.org/10.1016/S1672-6529(13)60237-1
Title: A GIM-based biomimetic learning approach for motion generation of a multi-joint robotic fish
Authors: Ren, Q.
Xu, J. 
Fan, L.
Niu, X.
Keywords: Biomimetic learning
GIM
Locomotion
Robotic fish
Issue Date: Oct-2013
Citation: Ren, Q., Xu, J., Fan, L., Niu, X. (2013-10). A GIM-based biomimetic learning approach for motion generation of a multi-joint robotic fish. Journal of Bionic Engineering 10 (4) : 423-433. ScholarBank@NUS Repository. https://doi.org/10.1016/S1672-6529(13)60237-1
Abstract: In this paper, we propose a biomimetic learning approach for motion generation of a multi-joint robotic fish. Based on a multi-joint robotic fish model, two basic Carangiform swimming patterns, namely "cruise" and "C sharp turning", are extracted as training samples from the observations of real fish swimming. A General Internal Model (GIM), which is an imitation of Central Pattern Generator (CPG) in nerve systems, is adopted to learn and to regenerate coordinated fish behaviors. By virtue of the universal function approximation ability and the temporal/spatial scalabilities of GIM, the proposed learning approach is able to generate the same or similar fish swimming patterns by tuning two parameters. The learned swimming patterns are implemented on a multi-joint robotic fish in experiments. The experiment results verify the effectiveness of the biomimetic learning approach in generating and modifying locomotion patterns for the robotic fish. © 2013 Jilin University.
Source Title: Journal of Bionic Engineering
URI: http://scholarbank.nus.edu.sg/handle/10635/54220
ISSN: 16726529
DOI: 10.1016/S1672-6529(13)60237-1
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

13
checked on Jul 16, 2018

WEB OF SCIENCETM
Citations

7
checked on Jul 16, 2018

Page view(s)

62
checked on Jul 6, 2018

Google ScholarTM

Check

Altmetric


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