Abstract
Path planning is an important component for a mobile robot to be able to do its job in different types of environments. Furthermore, determining the safest and shortest path from the start location to a desired destination, intelligently and in quickly, is a major challenge, especially in a dynamic environment. Therefore, various optimisation methods are recommended to solve the problem, one of these being a genetic algorithm (GA). This paper investigates the capabilities of GA for solving the path planning problem for mobile robots in static and dynamic environments. First, it studies the different GA approaches. Then, it carefully designs a new GA with intelligent crossover to optimise the search process in static and dynamic environments. It also conducts a comprehensive statistical evaluation of the proposed GA approach in terms of solution quality and execution time, comparing it against the well-known A* algorithm and MGA in a static scenario, and against the Improved GA in a dynamic scenario. The simulation results show that the proposed GA is able to find an optimal or near optimal solution with fast execution time compared to the three other algorithms, especially in large problems.