Title: Adaptive vs. conventional potential field approaches for solving navigation problems of a real car-like wheeled robot
Authors: Subba Rao Amada, Pandu R. Vundavilli, Dilip Kumar Pratihar
Addresses: Soft Computing Lab., Department of Mechanical Engineering, Indian Institute of Technology Kharagpur, Kharagpur 721 302, India. ' Soft Computing Lab., Department of Mechanical Engineering, Indian Institute of Technology Kharagpur, Kharagpur 721 302, India. ' Soft Computing Lab., Department of Mechanical Engineering, Indian Institute of Technology Kharagpur, Kharagpur 721 302, India
Abstract: Adaptive Potential Field Methods (APFMs) have been proposed in this paper and their performances have been compared among them and with that of Conventional Potential Field Method (CPFM) to solve navigation problems of the mobile robot. The performance of a potential field method (PFM) depends on its chosen attractive and repulsive potential functions and the constant terms associated with them. Robots that navigate using the CPFM may not find time-optimal path and may suffer from the deadlock situations. APFM could solve the said problems by changing the constant terms associated with the potential functions to cope with the varying situations of the environment. The performances of the proposed adaptive and CPFMs have been tested through computer simulations and on a real car-like wheeled robot. The proposed PFM is found to perform better than the conventional one.
Keywords: car-like wheeled robots; mobile robots; navigation problems; APFM; adaptive potential field methods; FLC; fuzzy logic controllers; fuzzy control; genetic algorithms; robot navigation; simulation; robot control.
DOI: 10.1504/IJIDSS.2009.031414
International Journal of Intelligent Defence Support Systems, 2009 Vol.2 No.4, pp.290 - 318
Published online: 02 Feb 2010 *
Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article