DigitalWorld 2015
February 22 - 27, 2015 - Lisbon, Portugal

ComputationWorld 2015
March 22 - 27, 2015 - Nice, France

NexComm 2015
April 19 - 24, 2015 - Barcelona, Spain

InfoSys 2015
May 24 - 29, 2015 - Rome, Italy

BioSciencesWorld 2015
May 24 - 29, 2015 - Rome, Italy

DataSys 2015
June 21 - 26, 2015 - Brussels, Belgium

NexTech 2015
July 19 - 24, 2015 - Nice, France

NetWare 2015
August 23 - 28, 2015 - Venice, Italy

InfoWare 2015
October 11 - 16, 2015 - St. Julians, Malta

SoftNet 2015
November 15 - 20, 2015 - Barcelona, Spain


ThinkMind // International Journal On Advances in Intelligent Systems, volume 3, numbers 3 and 4, 2010 // View article intsys_v3_n34_2010_15

Unscented Transform-based Dual Adaptive Control for Mobile Robots: Comparative Analysis and Experimental Validation

Marvin Bugeja
Simon Fabri

Keywords: Dual adaptive control; nonlinear stochastic control; neural networks; unscented transform; mobile robots

Adaptive control involves both estimation and control, which are generally interdependent and partly in conflict. Yet, the majority of adaptive controllers separate the two by assuming that certainty equivalence holds, even if this is not the case. In contrast a dual adaptive controller, based on the idea postulated by A. Fel'dbaum in the early 1960s, aims to strike a balance between estimation and control at all times. In this manner, the control law is a function of the estimates' uncertainty, besides the estimates themselves, thereby leading to improved control performance. Few such controllers have ever been implemented and tested in practice, especially within the context of intelligent control, and to the best of our knowledge none on mobile robots. This paper present two novel dual adaptive neural control schemes for the dynamic control of mobile robots in the presence of functional uncertainty. Furthermore, by means of realistic Monte Carlo simulations and real-life experiments, a thorough comparative analysis is performed. A notable novel contribution of this work is the use of the unscented transform within the context of dual adaptive control, aimed at improving further the performance of the system.

Pages: 358 to 375

Copyright: Copyright (c) to authors, 2010. Used with permission.

Publication date: April 6, 2011

Published in: journal

ISSN: 1942-2679

2010 - 2014 © ThinkMind. All rights reserved.
Read Terms of Service and Privacy Policy.