This paper considers a capability construction problem of the C4ISR system under serviceoriented architecture. A capability construction model is first established and described in the planning domain definition language as an artificial intelligence (AI) planning problem. To adapt the complex requirements of a C4ISR system and large scale of required services, an incremental macro-operation learning method based on n-gram analysis is proposed, and an enhanced domain is generated using a relaxation scheme. To improve the efficiency of the search algorithm, an ordered-hill-climbing (OHC) method is designed based on the length of the operations. With the above procedures, the AI planner, using macro-operation and the OHC, is presented for capability construction problems. The simulation results show that this method can effectively shorten the search time of capability construction. INDEX TERMS Artificial intelligence planning, C4ISR, capability construction, service-oriented architecture.

No abstract

The dynamic resource scheduling problem is a field of intense research in command and control organization mission planning. This paper analyzes the emergencies in the battlefield first and divides them into three categories: the changing of task attributes, reduction of available platforms, and change in the number of tasks. To deal with these emergencies, in this paper, we built a series of multiobjective optimization models that maximizes the task execution quality and minimizes the cost of plan adjustment. To solve the model, we proposed an improved multi-objective evolutionary algorithm. A type of mapping operator and an improved crowding-distance sorting method are designed for the algorithm. Finally, the availability of the model and the solving algorithm were proved through a series of experiments. The Pareto frontier for the multi-objective dynamic resource scheduling problem can be found effectively, and the algorithm proposed in this paper shows better convergence compared with the AMP-NSGA-II algorithm.INDEX TERMS Command and control organization, dynamic resource scheduling, multi-objective evolutionary algorithm, multi-objective optimization.

Unmanned Combat Aerial Vehicle (UCAV) cooperative task allocation under Manned Combat Aerial Vehicle’s (MCAV) limited control is one of the important problems in UCAV research field. Hereto, we analyze the key technical and tactical indices influence task allocation problem and build an appropriate model to maximize the objective function values as well as reflecting various constraints. A novel improved multigroup ant colony algorithm (IMGACA) is proposed to solve the model; the algorithm mainly includes random sequence-based UCAV selection strategy, constraint-based candidate task generation strategy, objective function value-based state transition strategy, and crossover operator-based local search strategy. Simulation results show that the built model is reasonable and the proposed algorithm performs well in feasibility, timeliness, and stability.

No abstract