Genetic algorithm in robot path planning problem in crisp and fuzzified environments

Two approaches, using the combination of a Hopfield neural network and a genetic algorithm for solving the robot motion planning problem both in crisp and fuzzified environments are presented. Based on the hypothesis of genetic algorithms, the genomes and chromosomes of the algorithm are modified so that they can be used to solve the motion planning problem. Because some problem restrictions and limits hinder us in using the generic genetic algorithm; some modifications are applied to the main algorithm to able us to solve the problem. Although the proposed algorithms both rely on a genetic algorithm, the heart of both is based on a Hopfield neural network robot path planner to find some partial answers in the robot's environment. In other words, in each new generation cycle of the main genetic algorithm, the Hopfield neural network path planner is launched regularly to improve the quality of each chromosome by reforming it. Simulation results demonstrate the correctness and efficiency of the proposed techniques.