Multiagent fuzzy-neural control of a 3-link uniped
- 23 December 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 239-245
- https://doi.org/10.1109/fuzzy.1996.551748
Abstract
Kgroo, a simulated 3-link folding legged uniped robot is presented and locomotion training of Kgroo with fuzzy-neural control is discussed. It is observed that for the uniped locomotion problem, global training of a fuzzy or neural controller is subject to failure. It is shown that, starting with a single jump example, a multiagent cerebellum model (MAC-J) can enable Kgroo to learn different jumps with a geometrical learning rate based on a learning-tuning-brainstorming theory. Technically, this work introduces effective means for decomposing the high-dimensional locomotion control problem into kernel spaces; theoretically, incremental learning and coordinated cerebellar agent discovery provide a natural explanation to certain explosive learning behaviors in human and animal locomotion control.Keywords
This publication has 5 references indexed in Scilit:
- Partitions of unity improve neural function approximatorsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Modular design of fuzzy controller integrating deliberative and reactive strategiesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Emulation of spline curves and its applications in robot motion controlPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Why triangular membership functions?Fuzzy Sets and Systems, 1994
- Fuzzy input-output controllers are universal approximatorsFuzzy Sets and Systems, 1993