Optimal motion planning for mobile robots using genetic algorithms

Abstract

This paper reports the initial experiments undertaken on a programme of work whose aim is the development of real time motion planning algorithms for mobile robots operating in uncertain and unstructured environments. These experiments were performed with the purpose of evaluating the potential of applying genetic algorithms (GA) to the path planning stage. Three scenarios of increasing complexity are considered and the results of each presented. Of particular interest is the formulation and representation of the problem into a form suitable for solution by a genetic algorithm. The results show that the approach provides respectable results and provide a solid foundation upon which more sophisticated algorithms can be built.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>