基于博弈论的多机器人任务分配算法

为了寻找一种合理有效的多机器人任务分配算法,基于多机器人协作救火任务环境,以博弈论纳什均衡为基础,研究多机器人的任务分配问题。根据任务模型特点和纳什均衡的主要特征提出了一种基于博弈论的任务分配算法。博弈的效用函数同时考虑了距离、火势和燃烧时间等因素,机器人根据此效用函数选择行为策略,促使机器人尽快扑灭惩罚值较大的火灾而获得较大的奖励值。利用任务总收益函数值的大小评价算法的优劣性。收益函数与火势、燃烧时间和机器人扑灭火灾数有关,这切合实际救火模型。实验结果证明了该任务分配算法的有效性。

Game-Theory Based Multi-Robot Task Allocation Algorithm

In order to find a reasonable and effective multi-robot task allocation algorithm,multi-robot system task allocation problem is studied based on the multi-robot cooperation fire-fighting environment and Nash equilibrium in game theory.According to the primary features of task model and Nash equilibrium,a task allocation algorithm based on game theory is presented.The utility function takes into account the distance,fire and burning time factors,robots select their behavior strategies according to this utility function and induce them to extinguish the greater fire with larger publish value to get larger reward value.The value of total task revenue is used to evaluate the advantages and disadvantages of this algorithm.Task revenue function is related to fire density,burning time and number of fire put out by robots,which is consistent with the realistic fire-fighting task model.Experimental results show the effectiveness of this algorithm.