Title

Event-Sampled Adaptive Neural Network Control of Robot Manipulators

Abstract

Event based sampling of feedback signals and control inputs are shown to reduce computations. In this paper, the design of event-sampled adaptive neural network (NN) state feedback control of robot manipulators is presented in the presence of uncertain robot dynamics. The event-sampled NN approximation property is utilized to represent the uncertain nonlinear dynamics of the robotic manipulator which is subsequently employed to generate the control torque. A novel weight tuning rule is designed using the Lyapunov method. Further, the Lyapunov stability theory is utilized to develop the event-sampling condition and to demonstrate the tracking performance of the robot manipulator. Finally, simulation results are presented to verify the theoretical claims and to demonstrate the reduction in the computations with event-sampled control execution.

Meeting Name

2016 International Joint Conference on Neural Networks, IJCNN (2016: Jul. 24-29, Vancouver, Canada)

Department(s)

Electrical and Computer Engineering

Comments

This research is supported in part by NSF grants ECCS #1128281 and #1406533 and Intelligent Systems Center, at the Missouri University of Science and Technology, Rolla.

Keywords and Phrases

Adaptive control systems; Feedback; Flexible manipulators; Industrial robots; Lyapunov methods; Machine design; Modular robots; Neural networks; Robot applications; Robots; State feedback; Uncertainty analysis; Adaptive neural network control; Adaptive neural networks; Approximation properties; Lyapunov stability theory; Robot manipulator; Robotic manipulators; Sampling conditions; Tracking performance; Manipulators; Event-sampled control

International Standard Book Number (ISBN)

978-1-5090-0620-5

International Standard Serial Number (ISSN)

2161-4407

Document Type

Article - Conference proceedings

Document Version

Citation

File Type

text

Language(s)

English

Rights

© 2016 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.

Share

 
COinS