Solving multi-objective path planning for service robot by a pareto-based optimization algorithm

To achieve the autonomous navigation of service robots, effective path planning is a necessary prerequisite. In this paper, a Pareto-based path planning optimization algorithm is proposed. Three objectives are optimized simultaneously. They are path length, path safety and path smoothness. First, the grid method is employed to represent the model of the working environment. Grid map extension is implemented to ensure the safety of path planning. In the optimized process, each solution is represented as a passable path. The relationship of Pareto dominance is then introduced to handle the performance of solutions. In addition, elite record library is used to reserve the Pareto optimal solutions in the iterative process of the algorithm. To maintain the diversity of the solution, an adaptive grid partitioning strategy is realized. The metric hypervolume and set coverage are used to give a comprehensive evaluation. Finally, the simulation results verify the effectiveness of the proposed algorithm.