Grey wolf optimization algorithm for robot path planning

The path planning problem plays an important role in mobile robot work. Robot systems use different techniques to plan the path of the robot from one point to another. The main purpose of the path planning problem is to find the shortest path that a robot does not hit obstacles from the start position to the target position in an environment with obstacles. In this study, the Gray Wolf Optimization algorithm is adapted to the robot path planning problem. The Gray Wolf Optimizer (GWO) mimics the hunting behavior and social leadership of gray wolves in nature. The leadership hierarchy consists of four groups. These are alpha, beta, delta and omega groups. In this algorithm, the hunting mechanism comprises in three stages. These are searching for prey, encircling prey and attacking prey. Three, four, and five circular disabled maps were used in the test work of robot path planning. While there are candidate solutions in the path planning, three coordinate points are used between the start and destination points. At each iteration, these coordinate points are updated to be closer to the solution by the GWO algorithm. If the solution point is in the obstacle area, the value of the infringement is added to the cost function. In this thesis study, the performance of the GWO algorithm is evaluated together with other meta-heuristic algorithms to solve the robot path planning problem. The results obtained with the GWO algorithm show that the most suitable path is used for the test map used.