(EN) The invention provides a robot state planning method based on a Monte Carlo tree search algorithm. The robot state planning method comprises the steps of: acquiring an initial state and a target stateof a robot; taking the initial state as an initial node, and expanding a Monte Carlo tree by adopting the Monte Carlo tree search algorithm until a generated target node reaches the target state; anddetermining a state sequence of the robot according to all nodes from the starting node to the target node. According to the robot state planning method, the overall state of the motion process is planned, the state sequence is generated, the front-back coupling influence caused by periodic planning can be avoided, and the traffic capacity of the hexapod robot in complex terrains is improved.
(ZH) 本发明提供了一种基于蒙特卡洛树搜索算法的机器人状态规划方法，该方法包括获取机器人的初始状态和目标状态；以所述初始状态为起始节点，采用蒙特卡洛树搜索算法扩展蒙特卡洛树，直至生成的目标节点到达所述目标状态；根据所述起始节点到所述目标节点的所有节点确定所述机器人的状态序列。本发明的技术方案，对运动过程整体状态进行规划，生成状态序列，能够避免分周期规划带来的前后耦合影响，提高了六足机器人在复杂地形中的通行能力。
