Open AccessContext Aware Combat COA Recommendation using Preference Learning
Author(s) -
Xin Jin,
XinNian Wang,
Fei Cai
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1993/1/012037
Subject(s) - battlefield , context (archaeology) , perspective (graphical) , computer science , duty , preference , value (mathematics) , risk analysis (engineering) , operations research , knowledge management , artificial intelligence , data science , engineering , machine learning , business , history , paleontology , ancient history , philosophy , theology , economics , biology , microeconomics
In the daily combat readiness duty, faced with emergencies, time window left for decision-making is limited, far from enough to research and design a totally new COA (Course of Actions). However, using the state-of-the-art AI technologies, it is yet unable to autonomously generate COAs of trust. From the perspective of practicality, it is effective to improve emergency response efficiency, by making use of historically accumulated COAs. Similar problems have similar solutions, which is especially suitable for fields with incomplete knowledge systems and limited data accumulation. An intelligent method of COA recommendation is proposed, which can accurately recommend appropriate COAs based on current mission requirements, battlefield situation, and preferences. Based on the recommended COAs, user can form a new COA more efficiently, faced with emergencies. As a solution for AI technology supported combat decision making closer to practical, the method has certain reference value.