TY - GEN
T1 - Expert Knowledge-Assisted Drone Combat Strategy via Intention Interpretation
AU - Wang, Xindi
AU - Liu, Hao
AU - Liu, Dawei
AU - Cheng, Ming
AU - Liu, Chenguang
AU - Wang, Xiaoguang
AU - Guo, Mutian
N1 - Publisher Copyright:
© 2023 Technical Committee on Control Theory, Chinese Association of Automation.
PY - 2023
Y1 - 2023
N2 - In this paper, a drone game strategy generation model is designed in a denied environment. A typical nonlinear model of drone formation dynamics is first constructed. A behavior prediction algorithm based on neural network is then utilized to predict the trajectory and behavior characteristics of the attack drones, and a neural network algorithm achieves intelligent interpretation of the attack drones intention based on the result of the prediction. A game strategy generation algorithm assisted by expert knowledge and game experience library is finally proposed using the result of the intention interpretation. These algorithms overcome the difficulty of obtaining the game strategy under the deceptive and elusive characteristics of attacking drones and realize high real-time and pertinence of decision-making. Simulation results of typical scenarios are provided to verify the effectiveness of the proposed algorithm model.
AB - In this paper, a drone game strategy generation model is designed in a denied environment. A typical nonlinear model of drone formation dynamics is first constructed. A behavior prediction algorithm based on neural network is then utilized to predict the trajectory and behavior characteristics of the attack drones, and a neural network algorithm achieves intelligent interpretation of the attack drones intention based on the result of the prediction. A game strategy generation algorithm assisted by expert knowledge and game experience library is finally proposed using the result of the intention interpretation. These algorithms overcome the difficulty of obtaining the game strategy under the deceptive and elusive characteristics of attacking drones and realize high real-time and pertinence of decision-making. Simulation results of typical scenarios are provided to verify the effectiveness of the proposed algorithm model.
UR - https://www.scopus.com/pages/publications/85175521803
U2 - 10.23919/CCC58697.2023.10240854
DO - 10.23919/CCC58697.2023.10240854
M3 - 会议稿件
AN - SCOPUS:85175521803
T3 - Chinese Control Conference, CCC
SP - 8143
EP - 8147
BT - 2023 42nd Chinese Control Conference, CCC 2023
PB - IEEE Computer Society
T2 - 42nd Chinese Control Conference, CCC 2023
Y2 - 24 July 2023 through 26 July 2023
ER -