Genetic Algorithm Based PathPlanning and Optimization forAutonomous Mobile Robots
Fayyaz A. Afsar · 2006
Thispaperpresents analgorithm foroptimal pathplanning formobilerobotsusingGeneticAlgorithms coupledwith morphological imagepreprocessing oftheterrain. PathPlanning in agiven environment, being aNP-Hardproblem, iscomputationally demanding especially ifexactor deterministic techniques are employed. Thispavestheway fortheuseofevolutionary computing techniques, suchasGenetic Algorithms (GAs), forthe solution ofthisproblem. HoweverasGAstendtofindoptimal pathswithout considering thelocation anddistribution ofobstacles inthegivenmap,therefore alargeamountoftimemaybespent before evena feasible pathisfound. Thetechnique conferred in thispaperovercomesthisshortcoming by usingspecialized morphological preprocessing techniques applied onthelandscape representative image.The results obtained on a variety of structured, unstructured and clustered terrains indicate the efficacy ofthealgorithm presented andthepotential fortheuseof this algorithm inreal-time operation ofmobile robots.