Advanced search
1 file | 4.22 MB Add to list

Populations of Spiking Neurons for Reservoir Computing: Closed Loop Control of a Compliant Quadruped

Alexander Vandesompele (UGent) , Gabriel Urbain (UGent) , Francis wyffels (UGent) and Joni Dambre (UGent)
Author
Organization
Abstract
Compliant robots can be more versatile than traditional robots, but their control is more complex. The dynamics of compliant bodies can however be turned into an advantage using the physical reservoir computing frame- work. By feeding sensor signals to the reservoir and extracting motor signals from the reservoir, closed loop robot control is possible. Here, we present a novel framework for implementing central pattern generators with spik- ing neural networks to obtain closed loop robot control. Using the FORCE learning paradigm, we train a reservoir of spiking neuron populations to act as a central pattern generator. We demonstrate the learning of predefined gait patterns, speed control and gait transition on a simulated model of a compliant quadrupedal robot.
Keywords
Experimental and Cognitive Psychology, Cognitive Neuroscience, Artificial Intelligence

Downloads

  • CogSys Draft.pdf
    • full text
    • |
    • open access
    • |
    • PDF
    • |
    • 4.22 MB

Citation

Please use this url to cite or link to this publication:

MLA
Vandesompele, Alexander et al. “Populations of Spiking Neurons for Reservoir Computing: Closed Loop Control of a Compliant Quadruped.” Cognitive Systems Research (2019): n. pag. Print.
APA
Vandesompele, A., Urbain, G., wyffels, F., & Dambre, J. (2019). Populations of Spiking Neurons for Reservoir Computing: Closed Loop Control of a Compliant Quadruped. Cognitive Systems Research.
Chicago author-date
Vandesompele, Alexander, Gabriel Urbain, Francis wyffels, and Joni Dambre. 2019. “Populations of Spiking Neurons for Reservoir Computing: Closed Loop Control of a Compliant Quadruped.” Cognitive Systems Research.
Chicago author-date (all authors)
Vandesompele, Alexander, Gabriel Urbain, Francis wyffels, and Joni Dambre. 2019. “Populations of Spiking Neurons for Reservoir Computing: Closed Loop Control of a Compliant Quadruped.” Cognitive Systems Research.
Vancouver
1.
Vandesompele A, Urbain G, wyffels F, Dambre J. Populations of Spiking Neurons for Reservoir Computing: Closed Loop Control of a Compliant Quadruped. Cognitive Systems Research. 2019;
IEEE
[1]
A. Vandesompele, G. Urbain, F. wyffels, and J. Dambre, “Populations of Spiking Neurons for Reservoir Computing: Closed Loop Control of a Compliant Quadruped,” Cognitive Systems Research, 2019.
@article{8625963,
  abstract     = {Compliant robots can be more versatile than traditional robots, but their
control is more complex. The dynamics of compliant bodies can however
be turned into an advantage using the physical reservoir computing frame-
work. By feeding sensor signals to the reservoir and extracting motor signals
from the reservoir, closed loop robot control is possible. Here, we present
a novel framework for implementing central pattern generators with spik-
ing neural networks to obtain closed loop robot control. Using the FORCE
learning paradigm, we train a reservoir of spiking neuron populations to act
as a central pattern generator. We demonstrate the learning of predefined
gait patterns, speed control and gait transition on a simulated model of a
compliant quadrupedal robot.
},
  author       = {Vandesompele, Alexander and Urbain, Gabriel and wyffels, Francis and Dambre, Joni},
  issn         = {1389-0417},
  journal      = {Cognitive Systems Research},
  keywords     = {Experimental and Cognitive Psychology,Cognitive Neuroscience,Artificial Intelligence},
  language     = {eng},
  title        = {Populations of Spiking Neurons for Reservoir Computing: Closed Loop Control of a Compliant Quadruped},
  url          = {http://dx.doi.org/10.1016/j.cogsys.2019.08.002},
  year         = {2019},
}

Altmetric
View in Altmetric