Path planning for autonomous mobile robots with metaheuristic algorithms

Planning the path of autonomous mobile robots from the starting point to the target point without hitting the obstacles in a limited environment with static obstacles is a problem that remains current. With this goal, various metaheuristic optimization algorithms are used to plan the path of the robot from a starting point to an ending point by avoiding obstacles. Metaheuristic algorithms are mathematically modeled based on nature and animal behavior and are used in many fields such as business, engineering and industry. In this study, experimental studies of five popular metaheuristic algorithms to solve the robot path planning problem in a limited environment are presented. The performances of the Antlion Optimization (ALO), Gray Wolf Optimization (GWO), Differential Evolution Algorithm (DE), Particle Swarm Optimization (PSO) and Golden Jackal Optimization (GJO) algorithms used in the study were examined for autonomous mobile robots in environments with different shapes and numbers of obstacles. Metaheuristic algorithms do not provide an exact solution to a problem, but thanks to their convergence properties, they try to find the best solution or the shortest path under their conditions. Violations made by the metaheuristic algorithm while planning the path are added to the cost function and the algorithm updates itself to avoid the obstacle and get closer to the solution. The metaheuristic algorithms used in the study were evaluated according to the results obtained from runs performed on different path problems and under the same conditions. As a result of the experimental studies, it is seen that the PSO algorithm produces stable results with the best performance.