摘要
随着航天技术的发展,保护好太空资产变得愈加重要,针对非合作航天器的意图识别正是保护太空资产的关键技术之一。传统基于目标特征状态推理意图的方法,需要大量的领域专家知识对特征状态的权重、先验概率等进行量化,明确特征状态与意图之间的对应关系,而机器学习可以在领域专家知识不足条件下,基于大量的带有标签的数据集,训练得到特征状态与意图之间的规则,快速识别出非合作目标的意图。
With the development of space technology,it becomes more and more important to protect space assets.The intention identification of non-cooperative spacecraft is one of the key technologies to protect space assets.The traditional method of reasoning intention based on target feature state requires a large amount of domain expert knowledge to quantify the weight and prior probability of feature state and to clarify the corresponding relationship between feature state and intention,while machine learning can train rules between feature state and intention based on a large number of labeled data sets under the condition of insufficient domain expert knowledge.The intent of non-cooperative targets can be quickly identified.
作者
伏立峰
朱阅訸
李海阳
FU Lifeng;ZHU Yuehe;LI Haiyang(College of Aerospace Science and Engineering,National University of Defense Technology,Changsha 410073,China;Hunan Key Laboratory of Intelligent Planning and Simulation for Aerospace Missions,Changsha 410073,China)
出处
《火力与指挥控制》
北大核心
2025年第6期13-20,共8页
Fire Control & Command Control
基金
国家自然科学基金资助项目(12102460)。
关键词
意图识别
机器学习
非合作航天器
领域专家
intention recognition
machine learning
non-cooperative spacecraft
domain expert
