A Cognitive Model with Growing Structure and Its Application to Learning to Control the Inverted Pendulum

摘要：

A growing cognitive model of motor balance skill, which simulates the manners of human beings and animals in motor balance skill learning, is constructed. A neuro-controller based on the model is proposed to balance an inverted pendulum. The cognitive model, whose architecture is similar to the reflex arc of the biologic nerve, adopts a growing algorithm from reference to Growing Cell Structures in order to perform the pattern classification in the nerve center. This growing mechanism is able to be evolved through the continuous growing of the new nerve cell. And reinforcement Hebbian Synaptic Modification is used as the self-learning method in the cognitive model to make the neurons in difference fields to respond to the different stimulus in the best way. The experimental results are shown that the growing cognitive model can interact autonomously with the environment and develop the motor balance skill by the growing manners of neural system itself.

关键词： Cognitive model Growing Cell Structures Inverted Pendulum

作者: Zhang Shao-bai Ruan Xiao-gang Cheng Xie-feng Feng Zhi-quan

作者单位: College of Computer, Nanjing University of Posts and Telecommunications, Nanjing, Jiangsu 210003,Chi College of Electronic Information and Control Engineering,Beijing University of Technology, Beijing College of Computer, Nanjing University of Posts and Telecommunications, Nanjing, Jiangsu 210003,Chi School of Information Science and Engineering ,Jinan University, Jinan, Shandong 250022,China

会议类型: 国际会议

会议名称: 2009年中国控制与决策会议(2009 Chinese Control and Decision Conference)

会议地点: 广西桂林

会议语种:英文

页码: 4361-4364

在线出版日期: 2009-06-17（万方平台首次上网日期，不代表论文的发表时间）