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(robot avoiding　if there are dynamic collisions between multi-agents, the game theory is used to construct a dynamic obstacle avoidance model between multi-agents, and the virtual action method is used to solve the problem of solving the game and the selection of multiple Nash equilibriums to ensure that each agent can quickly learn the optimal Nash equilibrium.)