DEVELOPMENT OF A ALGORITHM FOR ROBOT PATH PLANNING BASED ON MODIFIED PROBABILISTIC ROADMAP AND ARTIFICIAL POTENTIAL FIELD

Path planning is one of the most interesting topics in robotics field for researchers. It is responsible to find the best path between the start and the goal point for a given environment and task. In this paper, a new approach has been proposed to solve the path planning problem by combining the methods of probabilistic roadmap (PRM) and artificial potential field (APF), where the attractive potential filed is used to enhance the construction of roadmap by improving the nodes’ location. These new locations of the nodes ensure better path planning possibilities in a given complex static known environment. A* heuristic method is used to find the shortest path within the constructed roadmap. This path represented by segments of straight lines therefore, a non-uniform rational B-spline (NURBS) curve is used to smoothen the path and reduce the path length. Particle swarm optimization (PSO) is used to obtain the optimized weights that needed for each control point that participate to form the spline curve. The optimized weights ensure shortest and collision free path. The results that come out from the proposed approach can guarantee the path feasibility and reasonability between the start and the goal points in complex, static, and known environment. Moreover, the final path ensured to be continues, smooth, safe and absolutely optimal in terms of path length.