Entropy Regularization Method for Coordinated Multiple Target Assignment
Air Combat Decision-Making for Coordinated Multiple Target Assignment is an important yet difficult problem in the modern information warfare. Previous methods, such as neural network, genetic algorithm, ant colony algorithm, particle swarm optimization and auction algorithm, used to resolve this problem have proved to be either too brittle or not stable. To address this problem, a new continuous and distributed method based on Entropy Regularization is proposed. Based on the Probability Collective, the discrete problem is converted to be continuous by adding an Entropy Regular Item in the original basis of the global utility function, in order to amend the pathosis of the original function. Then, the optimization probability algorithm updating is done by jointly minimizing a Lagrangian of their joint state probability distribution. The experiment results show that as compared with conventional methods, the proposed method is be able to converge to the global optimum with more precision and stability.
Air Combat Decision-Making Coordinated Multi-Target Assignment Entropy Regularization
Xuan-ping Zhang Wei-hu Yu Jing-jing Liang Bo Liu
School of Electronics and Information Engineering,Xian Jiaotong University,Xian 710049,Shaanxi,Peoples Republic of China
国际会议
成都
英文
165-169
2010-07-07（万方平台首次上网日期，不代表论文的发表时间）