Path Planning Optimization Using Bio-Inspirited Algorithms

Path Planning is one of the problems in robotics. It consists on automatically determine a path from an initial position of the robot to its final position. This process has to be adaptable in order to work over several environments. Bio-inspirited algorithms, particularly ant colony optimizations (ACO) [9] are adaptable to any environments. Taking advantage of this fact, in this paper we show how bio-inspired algorithms can be used to optimize the path that a robot can follow in order to reach its target destination. We will use principles of Swarm intelligence that emulate the behavior of ants' colonies when they are looking for food aimed to find the shortest path. In addition, we propose to evolve some parameters of ACO algorithm by using a genetic algorithm (ACO-GA) in order to optimize the search of the shortest path. We also verify and compare the accuracy of ACO against ACO-GA. In order to test the accuracy of the proposed algorithm, we firstly obtain a graph from an environment and then we apply the two proposed algorithms in order to determine the best route from the origin to the target destination. To test the proposal some labyrinths of varied complexity were used.