Learning rules for dynamic trajectories in the cerebellar cortex application to a bipedal robot

被引：0

作者：

Daya, B ^{[1
]}

Chauvet, P ^{[1
]}

Garenne, A ^{[1
]}

Chauvet, GA ^{[1
]}

机构：

[1] Univ Libanaise, IUT Saida, Beirut, Lebanon

来源：

PROCEEDINGS OF THE SECOND IASTED INTERNATIONAL CONFERENCE ON NEURAL NETWORKS AND COMPUTATIONAL INTELLIGENCE | 2004年

关键词：

coordinated movement; neural network; cerebellum; walking robot; learning rules;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper the problem of motion control of a biped is considered. We develop a new method based on multi-network associated with neural biological strategy. This method deals with organization and coordination aspects in an intelligent modeling of human motion. We propose a cooperative hierarchical multi-network model. The learning of the biped is performed using new dynamic learning rules in a recurrent network. Cognitive agents communicate with reactive (non-articulator) agents in order to generate the motion.

引用

页码：19 / 24

页数：6

共 16 条

[1] ON ASSOCIATIVE MOTOR LEARNING BY THE CEREBELLAR CORTEX - FROM PURKINJE UNIT TO NETWORK WITH VARIATIONAL LEARNING RULES [J].