基于协同进化的多智能体机器人路径规划

协同进化是一种新兴的、简单有效的智能优化方法,具有较好的收敛性、鲁棒性和高效性,在多目标优化问题中得到很广泛应用。将其应用到复杂环境下多智能体机器人的路径规划中,并设计适应度评价函数。同时,引入一系列新的变异操作算子,有效地对多智能体机器人规划的路径进行优化,加速了整体的规划速度,避免规划陷入局部最优,从而获得多智能体系统的全局最优或次优解。最后给出了的仿真结果证明方法可行、有效。

Path Planning Research for Multi-Agent Robot Based on Co-Evolution

Co-Evolution is a novel, simple and effective Intelligent Optimization approach, has good convergence, robustness and efficiency in multi-objective optimization problem has been very widely used. In this paper, its application to complex environment of multi-robot path planning, and design of the fitness evaluation function. At the same time, the introduction of a new series of operator variability and effective manner to multi-robot path planning, optimization, accelerated the pace of overall planning to avoid a local optimum planning, multi-robot system in order to obtain the global optimal or sub-optimal solution. Finally, the simulation results prove the method is feasible and effective.