Neural-fuzzy control system for robotic manipulators

Author

Peng, Limin ; Woo, Peng-Yung

Author_Institution

Dept. of Electr. Eng., Northern Illinois Univ., DeKalb, IL, USA

Volume

22

Issue

1

fYear

2002

fDate

2/1/2002 12:00:00 AM

Firstpage

53

Lastpage

63

Abstract

This article presents a control system structure, as well as a control algorithm, that combines neural networks with fuzzy logic for dynamical compensation of both structured and unstructured uncertainties.<P>A new fuzzy reasoning method is derived in the neural mechanism and implemented with a cerebellar model articulation controller (CMAC), which outperforms conventional fuzzy controllers by reducing computational complexity and providing a learning ability that conventional fuzzy systems do not have. The overall control system is proven to be stable. The simulation results confirm that the system can track the desired position for both set-point and dynamic tracking in the presence of uncertainties such as changing payload, various frictions, and unknown disturbances

Keywords

cerebellar model arithmetic computers; compensation; computational complexity; fuzzy control; fuzzy neural nets; learning (artificial intelligence); manipulators; neurocontrollers; stability; tracking; uncertain systems; CMAC; cerebellar model articulation controller; changing payload; compensation; computational complexity; dynamic tracking; frictions; fuzzy reasoning; learning; neural-fuzzy control system; position tracking; robotic manipulators; set-point tracking; stable; structured uncertainties; unknown disturbances; unstructured uncertainties; Control system synthesis; Control systems; Fuzzy control; Fuzzy logic; Fuzzy neural networks; Fuzzy reasoning; Fuzzy systems; Manipulator dynamics; Neural networks; Robot control;

fLanguage

English

Journal_Title

Control Systems, IEEE

Publisher

ieee

ISSN

1066-033X

Type

jour

DOI

10.1109/37.980247

Filename

980247