| Title |
Multi-agent based Manned/unmanned Collaboration System for Combatant’s Battlefield Situation Awareness |
| Authors |
이창은(Changeun Lee) ; 백재욱(Jaeuk Baek) ; 손진희(Jeany Son) ; 이소연(So Yeon Lee) ; 하영국(Yjungguk Ha) |
| DOI |
https://doi.org/10.5573/ieie.2022.59.2.126 |
| Keywords |
Multi-agent; unmanned collaboration system; tactical map creation; battlefield situation awareness |
| Abstract |
This paper propose a multi-agent based manned/unmanned collaboration system. The system aims to reduce the cognitive burden of combatants by supporting battlefield situational awareness, threat judgment and command decision under poor battlefield conditions such as buildings, underground bunkers, and GNSS-denied. This manned/unmanned collaboration system consists of three core technologies. First, it is a collaborative neuroagent technology that serves as the brain of a ball-type robot that supports combatants' situations awareness, threat judgment in battlefield. The second technology is a military tactical map generation technology that is robust to poor environments using meta-learning of very small amounts of data to understand the battlefield environment by utilizing object information, semantic information, and geometric information. The third, it consists of real-time battlefield recognition technology that supports decision-making by fusing individually processed multimodal knowledge information from collaborative neuroagent. We design an architecture and generate dataset for training the core network. Simulation results are provided to demonstrate the performance of a multi-agent based manned/unmanned collaboration system. |