Neural network control of a three-link leg

Author

Doerschuk, Peggy Israel ; Nguyen, Vinh D. ; Li, Andrew L.

Author_Institution

Dept. of Comput. Sci., Lamar Univ., Beaumont, TX, USA

fYear

1995

fDate

5-8 Nov 1995

Firstpage

278

Lastpage

281

Abstract

Locomotion training of legged machines is a difficult and challenging problem in robotics and artificial intelligence. The work focuses on controlling the running stride of a three link leg. The objective is to control the height, distance and angular momentum of the stride, all of which are determined at takeoff from the ground. We use a CMAC neural network (J.S. Albus, 1975) to control the leg during takeoff. The CMAC network uses local learning and also permits incremental learning. This enables the net to be retrained online to produce the correct signals for locally changed conditions. The CMAC controller trains quickly and generalizes well

Keywords

cerebellar model arithmetic computers; intelligent control; learning (artificial intelligence); legged locomotion; neurocontrollers; CMAC controller; CMAC neural network; angular momentum; artificial intelligence; incremental learning; legged machines; local learning; locally changed conditions; locomotion training; neural network control; robotics; running stride; three-link leg; Computer science; Equations; Foot; Intelligent robots; Leg; Legged locomotion; Mechanical engineering; Mobile robots; Neural networks; Robot control;

fLanguage

English

Publisher

ieee

Conference_Titel

Tools with Artificial Intelligence, 1995. Proceedings., Seventh International Conference on

Conference_Location

Herndon, VA

ISSN

1082-3409

Print_ISBN

0-8186-7312-5

Type

conf

DOI

10.1109/TAI.1995.479614

Filename

479614