自动化学报2026，Vol.52Issue(1)：65-77,13.DOI:10.16383/j.aas.c250313
基于部分可观蒙特卡洛树搜索算法的无人系统异步任务规划
Unmanned System Asynchronous Task Planning Based on Partially Observable Monte Carlo Tree Search Algorithm
摘要
Abstract
Unmanned systems are profoundly reshaping social lifestyles and modes of warfare.In the field of dy-namic planning for unmanned systems,the environment is first abstracted as a topological network composed of nodes and edges.Second,for the variable step time advancement problem of asynchronous planning,a novel asyn-chronous planning algorithm,namely,a partially observable Monte Carlo tree search algorithm in the semi-Markov environment(SPOMCP)is proposed.The innovation is that the topological network is transformed into a sub-goal graph with the simplest information representation,and enabling rapid policy optimization based on a variable step time advancement mechanism.Through theoretical analysis,it is proven that SPOMCP can generate the optimal strategies,and the computational complexity is exponentially correlated with the number of sub-goal nodes.Finally,simulation experiments demonstrate that SPOMCP outperforms the benchmark algorithm in terms of performance,with less than 89.18%of the benchmark algorithm＇s computation time,resulting in higher average rewards.关键词
异步规划/最简信息表示/半马尔科夫环境/蒙特卡洛树搜索Key words
asynchronous planning/simplest information representation/semi-Markov environment/Monte Carlo tree search引用本文复制引用
周鑫,陈子夷,周天..基于部分可观蒙特卡洛树搜索算法的无人系统异步任务规划[J].自动化学报,2026,52(1):65-77,13.基金项目
国家自然科学基金(72471234)资助 Supported by National Natural Science Foundation of China(72471234) （72471234）
