|
Neural Network Vision-Based Visual Servoing And Navigation for KSU-IMR Mobile Robot Using Epipolar Geometry
|
|
|
Khalid AlMutib1, Ebrahim Mattar2, H. Ramdane Muhammad Emad AL-Dean3
*1King Saud University, Email:muteb@ksu.edu.sa
2Member of IEEE, IET. Electrical & Electronics Eng. Dept. College of Engineering University of Bahrain
3 Comp & Information Sciences College King Saud University
|
|
|
|
Abstract
.Mobile robots visual control system does suffer from a number of issues, as due to speed and complexity. Complicated kinematics relations, in addition, the needed computational time to execute a task, are also some related issues. This manuscript highlights a mechanism through which to approximate an inter-related visual kinematics relations that are part of visual servo closed loop system through an Artificial Neural Networks (ANN) system for a mobile robot visual servoing. The methodology followed and being applied to KSU-IMR mobile robot project, is based on the concept of integration of Neural Networks with an Image Based Visual Servoing system. ANN have been fully employed here to learn and approximate relations that relate a target movements to the mobile robot movement (POWERROB,[1]), through a visual servo.
|
|
|
|
Keywords
:
Visual Servo; ANN; Epipolar Gemetry; KSU-IMR Robo ; Visual Servo; ANN; Epipolar Gemetry; KSU-IMR Robo
|
|
|
|
URL: http://dx.doi.org/10.7321/jscse.v3.n3.136
|
|
|
|
|