中文说明：
运用博弈论，进行机器人避障避障，若多机器人之间存在动态碰撞，利用博弈论构建多机器人之间的动态避障模型，并利用虚拟行动法来解决博弈的求解问题及多Nash均衡的选择问题，确保每个机器人能够快速学习到最优Nash均衡。
English Description：
The game theory is used to avoid obstacles for robots. If there is dynamic collision between multiple robots, the game theory is used to build the dynamic obstacle avoidance model between multiple robots, and the virtual action method is used to solve the problem of solving the game and the selection of multiple Nash equilibrium, so as to ensure that each robot can quickly learn the optimal Nash equilibrium.