Task planning for robots is computationally challenging due to the combinatorial complexity of the possible action space. This fact is amplified if there are several sub-goals to be achieved due to the increased length of the action sequences. In this work, we propose a multi-goal task planning algorithm for deterministic decision processes based on Monte Carlo Tree Search. We augment the algorithm by prioritized node expansion which prioritizes nodes that already have fulfilled some sub-goals. Due to its linear complexity in the number of sub-goals our algorithm is able to identify action sequences of 145 elements to reach the desired goal state with up to 48 sub-goals while the search tree is limited to under 6500 nodes. We use action reduction based on a kinematic reachability criterion to further ease computational complexity. We combine our algorithm with object localization and motion planning and apply it to a real-robot demonstration with two manipulators in an industrial bearing inspection setting.

翻译：机器人任务规划因动作空间的组合复杂性而面临计算挑战。当需要实现多个子目标时，由于动作序列长度增加，这一挑战更为突出。本文针对确定性决策过程提出了一种基于蒙特卡洛树搜索的多目标任务规划算法。我们通过优先节点扩展对该算法进行增强，其中优先扩展已达成部分子目标的节点。该算法在子目标数量上具有线性复杂度，能够在搜索树节点数限制在6500个以内的情况下，识别出包含145个动作元素的序列，以到达最多包含48个子目标的目标状态。我们采用基于运动学可达性判据的动作约简策略以进一步降低计算复杂度。最后，我们将该算法与目标定位及运动规划相结合，并在双机械臂工业轴承检测场景中进行了真实机器人实验验证。