Trajectory synthesis based on different fuzzy modeling network pruning algorithms

Author

Juang, Jih-Gau

Author_Institution

Dept. of Guidance & Commun. Technol., Nat. Taiwan Ocean Univ., Taiwan, China

fYear

2000

fDate

2000

Firstpage

315

Lastpage

320

Abstract

In this paper, trajectory synthesis based on different fuzzy modeling network pruning algorithms is investigated. The learning scheme uses a fuzzy neural network as the controller. Simulations focus on refinement and a thorough understanding of the pruned fuzzy modeling network. The learning scheme can control a biped robot that satisfies prespecified constraints such as the steplength, crossing clearance, and walking speed. Different issues regarding the scheme have been examined. They include the effects of using weight truncation and the effects of using weight decay. The proposed scheme is tested with simulations of the BLR-G1 walking robot

Keywords

fuzzy control; fuzzy neural nets; learning (artificial intelligence); legged locomotion; neurocontrollers; BLR-G1 walking robot; biped robot; crossing clearance; fuzzy modeling network pruning algorithms; fuzzy neural network controller; steplength; trajectory synthesis; walking speed; weight truncation; Communication system control; Fuzzy control; Fuzzy neural networks; Fuzzy set theory; Gravity; Leg; Legged locomotion; Network synthesis; Neural networks; Robot control;

fLanguage

English

Publisher

ieee

Conference_Titel

Control Applications, 2000. Proceedings of the 2000 IEEE International Conference on

Conference_Location

Anchorage, AK

Print_ISBN

0-7803-6562-3

Type

conf

DOI

10.1109/CCA.2000.897443

Filename

897443