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
AN - SCOPUS:84885601636
SN - 981437427X
SN - 9789814374279
T3 - Field Robotics - Proceedings of the 14th International Conference on Climbing and Walking Robots and the Support Technologies for Mobile Machines, CLAWAR 2011
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
T2 - 14th International Conference on Climbing and Walking Robots and the Support Technologies for Mobile Machines, CLAWAR 2011
Y2 - 6 September 2011 through 8 September 2011
ER -