TY - JOUR
T1 - An Improved eXtended Classifier System for the Real-time-input Real-time-output (XCSRR) Stability Control of a Biped Robot
AU - Sabzehzar, A.
AU - Shan, W. L.
AU - Panahi, M. Shariat
AU - Saremi, O.
N1 - Publisher Copyright:
© 2015 Published by Elsevier B.V.
PY - 2015
Y1 - 2015
N2 - In this paper a revised reinforcement learning method is presented for stability control problems with real-value inputs and outputs. The revised eXtended Classifier System for Real-input and Real-output (XCSRR) controller is designed, which is capable of working at fully real-value environment such as stability control of robots. XCSRR is a novel approach to enhance the performance of classifier systems for more practical problems than systems with merely binary behaviour. As a case study, we use XCSRR to control the stability of a biped robot, which is subjected to unknown external forces that would disturb the robot equilibrium. The external forces and the dynamics of the upper body of the biped robot are modelled in MATLAB software to train the XCSRR controller. Theoretical and experimental results of the learning behaviour and the performance of stability control on the robot demonstrate the strength and efficiency of the proposed new approach.
AB - In this paper a revised reinforcement learning method is presented for stability control problems with real-value inputs and outputs. The revised eXtended Classifier System for Real-input and Real-output (XCSRR) controller is designed, which is capable of working at fully real-value environment such as stability control of robots. XCSRR is a novel approach to enhance the performance of classifier systems for more practical problems than systems with merely binary behaviour. As a case study, we use XCSRR to control the stability of a biped robot, which is subjected to unknown external forces that would disturb the robot equilibrium. The external forces and the dynamics of the upper body of the biped robot are modelled in MATLAB software to train the XCSRR controller. Theoretical and experimental results of the learning behaviour and the performance of stability control on the robot demonstrate the strength and efficiency of the proposed new approach.
KW - eXtended Classifier Systems (XCS)
KW - real-value problem
KW - reinforcement learning
UR - http://www.scopus.com/inward/record.url?scp=84962685209&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84962685209&partnerID=8YFLogxK
U2 - 10.1016/j.procs.2015.09.198
DO - 10.1016/j.procs.2015.09.198
M3 - Conference Article
AN - SCOPUS:84962685209
SN - 1877-0509
VL - 61
SP - 492
EP - 499
JO - Procedia Computer Science
JF - Procedia Computer Science
T2 - Complex Adaptive Systems, 2015
Y2 - 2 November 2015 through 4 November 2015
ER -