ANZCC 2019 Paper Abstract


Paper TC1.4

Takahashi, Kazuhiko (Doshisha University)

Remarks on Quaternion Neural Networks with Application to Trajectory Control of a Robot Manipulator

Scheduled for presentation during the Regular Session "Control Applications" (TC1), Thursday, November 28, 2019, 16:30−16:45, WZ Building Room WZ416

2019 Australian & New Zealand Control Conference (ANZCC), November 27-29, 2019, Auckland, New Zealand

This information is tentative and subject to change. Compiled on September 25, 2020

Keywords Fuzzy and Neural Systems, Learning Systems, Control Applications


This paper presents a quaternion neural network-based controller for a robot manipulator that can be used to investigate the possibility of using quaternion neural networks in practical applications. The quaternion neural network, which synthesises the control input for tracking an end-effector of the robot manipulator to the desired trajectory, assumes the role of an adaptive-type servo controller in a control system. Two types of network, such as feed-forward quaternion neural network and a recurrent quaternion neural network, were used to design servo-level controller and their performances were compared. Numerical simulations for controlling a three-link robot manipulator are performed to evaluate the characteristics of the proposed controllers and to demonstrate the feasibility as well as the effectiveness of the proposed controllers.



All Content © PaperCept, Inc.

This site is protected by copyright and trademark laws under US and International law.
All rights reserved. © 2002-2020 PaperCept, Inc.
Page generated 2020-09-25  15:11:19 PST  Terms of use