Learning control of nonhonolomic robot based on support vector machine
来源期刊：中南大学学报(英文版)2012年第12期
论文作者：FENG Yong(冯勇) GE Yun-jian(葛运建) CAO Hui-bin(曹会彬) SUN Yu-xiang(孙玉香)
文章页码：3400 - 3406
Key words：nonhonolomic robot; learning control; support vector machine; nonlinear control law; dynamic control
Abstract: A learning controller of nonhonolomic robot in real-time based on support vector machine (SVM) is presented. The controller includes two parts: one is kinematic controller based on nonlinear law, and the other is dynamic controller based on SVM. The kinematic controller is aimed to provide desired velocity which can make the steering system stable. The dynamic controller is aimed to transform the desired velocity to control torque. The parameters of the dynamic system of the robot are estimated through SVM learning algorithm according to the training data of sliding windows in real time. The proposed controller can adapt to the changes in the robot model and uncertainties in the environment. Compared with artificial neural network (ANN) controller, SVM controller can converge to the reference trajectory more quickly and the tracking error is smaller. The simulation results verify the effectiveness of the method proposed.
FENG Yong(冯勇)1,2, GE Yun-jian(葛运建)2, CAO Hui-bin(曹会彬)2, SUN Yu-xiang(孙玉香)2
(1. Department of Automation, University of Science and Technology of China, Hefei 230031, China;
2. Institute of Intelligent Machine, Chinese Academy of Science, Hefei 230031, China)
Abstract:A learning controller of nonhonolomic robot in real-time based on support vector machine (SVM) is presented. The controller includes two parts: one is kinematic controller based on nonlinear law, and the other is dynamic controller based on SVM. The kinematic controller is aimed to provide desired velocity which can make the steering system stable. The dynamic controller is aimed to transform the desired velocity to control torque. The parameters of the dynamic system of the robot are estimated through SVM learning algorithm according to the training data of sliding windows in real time. The proposed controller can adapt to the changes in the robot model and uncertainties in the environment. Compared with artificial neural network (ANN) controller, SVM controller can converge to the reference trajectory more quickly and the tracking error is smaller. The simulation results verify the effectiveness of the method proposed.
Key words:nonhonolomic robot; learning control; support vector machine; nonlinear control law; dynamic control
