Bio-inspired locomotion controller design for legged robots

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

To control a humanoid locomotion, much work can be found in the literature that has been focused on the Zero Moment Point approach. More recently, biologically inspired control strategies such as Central Pattern Generators have been proposed to generate autonomously adaptable rhythmic movement. Despite the extensive research works in this area, suitable autonomous control system that can adapt and interact safely with the surrounding environment while delivering high robustness is yet to be discovered. In this paper, therefore, we deal with the design of oscillatory neural network for bipedal motion pattern generator and locomotion controller. Locomotion pattern will be generated by a neural network that represents the lower layer of the overall control system of the humanoid. The neural network will be augmented by neural controllers with sensory connections to maintain the stability of the system. Moreover, we investigate the stability of the system simplified as an inverted pendulum and we propose analytical method on how to decide the parameters of the motion To validate the theoretical results, we use the humanoid robots "HOAP-3".

Original languageEnglish
Title of host publicationField Robotics - Proceedings of the 14th International Conference on Climbing and Walking Robots and the Support Technologies for Mobile Machines, CLAWAR 2011
Pages615-622
Number of pages8
Publication statusPublished - 2012
Event14th International Conference on Climbing and Walking Robots and the Support Technologies for Mobile Machines, CLAWAR 2011 - Paris, France
Duration: Sep 6 2011Sep 8 2011

Other

Other14th International Conference on Climbing and Walking Robots and the Support Technologies for Mobile Machines, CLAWAR 2011
CountryFrance
CityParis
Period9/6/119/8/11

Fingerprint

Robots
Neural networks
Controllers
Control systems
Pendulums

ASJC Scopus subject areas

  • Artificial Intelligence
  • Human-Computer Interaction

Cite this

Zaier, R. (2012). Bio-inspired locomotion controller design for legged robots. In Field Robotics - Proceedings of the 14th International Conference on Climbing and Walking Robots and the Support Technologies for Mobile Machines, CLAWAR 2011 (pp. 615-622)

Bio-inspired locomotion controller design for legged robots. / Zaier, Riadh.

Field Robotics - Proceedings of the 14th International Conference on Climbing and Walking Robots and the Support Technologies for Mobile Machines, CLAWAR 2011. 2012. p. 615-622.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Zaier, R 2012, Bio-inspired locomotion controller design for legged robots. in Field Robotics - Proceedings of the 14th International Conference on Climbing and Walking Robots and the Support Technologies for Mobile Machines, CLAWAR 2011. pp. 615-622, 14th International Conference on Climbing and Walking Robots and the Support Technologies for Mobile Machines, CLAWAR 2011, Paris, France, 9/6/11.
Zaier R. Bio-inspired locomotion controller design for legged robots. In Field Robotics - Proceedings of the 14th International Conference on Climbing and Walking Robots and the Support Technologies for Mobile Machines, CLAWAR 2011. 2012. p. 615-622
Zaier, Riadh. / Bio-inspired locomotion controller design for legged robots. Field Robotics - Proceedings of the 14th International Conference on Climbing and Walking Robots and the Support Technologies for Mobile Machines, CLAWAR 2011. 2012. pp. 615-622
@inproceedings{ae117649c7c44afa939f9ff0cce1743e,
title = "Bio-inspired locomotion controller design for legged robots",
abstract = "To control a humanoid locomotion, much work can be found in the literature that has been focused on the Zero Moment Point approach. More recently, biologically inspired control strategies such as Central Pattern Generators have been proposed to generate autonomously adaptable rhythmic movement. Despite the extensive research works in this area, suitable autonomous control system that can adapt and interact safely with the surrounding environment while delivering high robustness is yet to be discovered. In this paper, therefore, we deal with the design of oscillatory neural network for bipedal motion pattern generator and locomotion controller. Locomotion pattern will be generated by a neural network that represents the lower layer of the overall control system of the humanoid. The neural network will be augmented by neural controllers with sensory connections to maintain the stability of the system. Moreover, we investigate the stability of the system simplified as an inverted pendulum and we propose analytical method on how to decide the parameters of the motion To validate the theoretical results, we use the humanoid robots {"}HOAP-3{"}.",
author = "Riadh Zaier",
year = "2012",
language = "English",
isbn = "981437427X",
pages = "615--622",
booktitle = "Field Robotics - Proceedings of the 14th International Conference on Climbing and Walking Robots and the Support Technologies for Mobile Machines, CLAWAR 2011",

}

TY - GEN

T1 - Bio-inspired locomotion controller design for legged robots

AU - Zaier, Riadh

PY - 2012

Y1 - 2012

N2 - To control a humanoid locomotion, much work can be found in the literature that has been focused on the Zero Moment Point approach. More recently, biologically inspired control strategies such as Central Pattern Generators have been proposed to generate autonomously adaptable rhythmic movement. Despite the extensive research works in this area, suitable autonomous control system that can adapt and interact safely with the surrounding environment while delivering high robustness is yet to be discovered. In this paper, therefore, we deal with the design of oscillatory neural network for bipedal motion pattern generator and locomotion controller. Locomotion pattern will be generated by a neural network that represents the lower layer of the overall control system of the humanoid. The neural network will be augmented by neural controllers with sensory connections to maintain the stability of the system. Moreover, we investigate the stability of the system simplified as an inverted pendulum and we propose analytical method on how to decide the parameters of the motion To validate the theoretical results, we use the humanoid robots "HOAP-3".

AB - To control a humanoid locomotion, much work can be found in the literature that has been focused on the Zero Moment Point approach. More recently, biologically inspired control strategies such as Central Pattern Generators have been proposed to generate autonomously adaptable rhythmic movement. Despite the extensive research works in this area, suitable autonomous control system that can adapt and interact safely with the surrounding environment while delivering high robustness is yet to be discovered. In this paper, therefore, we deal with the design of oscillatory neural network for bipedal motion pattern generator and locomotion controller. Locomotion pattern will be generated by a neural network that represents the lower layer of the overall control system of the humanoid. The neural network will be augmented by neural controllers with sensory connections to maintain the stability of the system. Moreover, we investigate the stability of the system simplified as an inverted pendulum and we propose analytical method on how to decide the parameters of the motion To validate the theoretical results, we use the humanoid robots "HOAP-3".

UR - http://www.scopus.com/inward/record.url?scp=84885601636&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84885601636&partnerID=8YFLogxK

M3 - Conference contribution

SN - 981437427X

SN - 9789814374279

SP - 615

EP - 622

BT - Field Robotics - Proceedings of the 14th International Conference on Climbing and Walking Robots and the Support Technologies for Mobile Machines, CLAWAR 2011

ER -