Multi-Objective Optimization Robot Navigation Through a Graph-Driven PSO Mechanism.

In real-world robot applications such as service robots, mining mobile robots, and rescue robots, an autonomous mobile robot is required to visit multiple waypoints that it achieves multiple-objective optimizations. Such multiple-objective optimizations include robot travelling distance minimization, time minimization, turning minimization, etc. In this paper, a particle swarm optimization (PSO) algorithm incorporated with a Generalized Voronoi diagram (GVD) method is proposed for a robot to reach multiple waypoints with minimized total distance. Firstly, a GVD is used to form a Voronoi diagram in an obstacle populated environment to construct safety-conscious routes. Secondly, the sequence of multiple waypoints is created by the PSO algorithm to minimize the total travel cost. Thirdly, while the robot attempts to visit multiple waypoints, it traverses along the edges of the GVD to form a collision-free trajectory. The regional path locally from waypoints to nearest nodes or edges needs to be created to join the trajectory. A Node Selection Algorithm (NSA) is developed in this paper to implement such a protocol to build up regional path from waypoints to nearest nodes or edges on GVD. Finally, a histogram-based local reactive navigator is adopted for moving obstacle avoidance. Simulation and comparison studies validate the effectiveness and robustness of the proposed model.