Mobile Robot Path Planning in a Trajectory with Multiple Obstacles Using Genetic Algorithms

Abstract

Path planning is an essential algorithm to help robots complete their task in the field quickly. However, some path planning algorithms are computationally expensive and cannot adapt to new environments with a distinctly different set of obstacles. This paper presents optimal path planning based on a genetic algorithm (GA) that is proposed to be carried out in a dynamic environment with various obstacles. First, the points of the feasible path are found by performing a local search procedure. Then, the points are optimized to find the shortest path. When the optimal path is calculated, the position of the points on the path is smoothed to avoid obstacles in the environment. Thus, the average fitness values and the GA generation are better than the traditional method. The simulation results show that the proposed algorithm successfully finds the optimal path in an environment with multiple obstacles. Compared to a traditional GA-based method, our proposed algorithm has a smoother route due to path optimization. Therefore, this makes the proposed method advantageous in a dynamic environment.