Neural Combinatorial Optimization for Coverage Planning in UGV Reconnaissance
Yang Xueke, Yu Zhang, Junren Luo, Kaiqiang Wang, Xin Li, Jiang Chao-yuan · 2021 China Automation Congress (CAC) · 2021
Urban combat environment is affected by buildings and traffic network with certain spatial characteristics. A single unmanned combat vehicle carries out the coverage reconnaissance task will be constrained by the limited information and low efficiency, so multiple UGVs(Unmanned Ground Vehicles) cooperative coverage becomes an effective means to solve the problem. In this paper, the urban coverage reconnaissance task is formulated as a vehicle routing problem, and a new traversal model is proposed, which takes account the connectivity characteristics of the road. At the same time, different from the traditional routing planning, which takes the total cost of executing tasks as the optimization objective. We consider the time efficiency of the battlefield, and takes the coverage reconnaissance time as the optimization objective function (in most cases of multiple UGVs coverage tasks, the longest task execution time is taken as the optimization objective). And we proposed a neural combinatorial optimization technique to solve the problem. Through simulation experiments, the feasibility and effectiveness of the proposed model is verified.