Search

This paper examines the model of autonomous surveillance using a swarm of unmanned aerial vehicles with the simultaneous detection principle. This model enables to specify a number of sensors needed to detect an object of interest located in the area of interest; objects are detected only if scanned by the specified number of sensors simultaneously. The model plans deployment of individual vehicles in the swarm during the surveillance operation in a such a way that the surveillance is performed in the maximum quality; the quality is measured as a percentage of the area of interest that is covered during the operation. Furthermore, the surveillance is assumed to be conducted in the complex area of operations (including urban environments, build-up areas, or mountain environments with very uneven terrain) where occlusions caused by obstacles or terrain may occur often. For solution, the metaheuristic algorithm based on the simulated annealing is proposed. This algorithm deploys the number of waypoints, from which the monitoring is performed, maximizing the surveillance quality and taking the simultaneous detection principle into consideration. The algorithm is verified by a set of experiments based on typical surveillance scenarios.

This article examines autonomous reconnaissance in a complex urban environment using unmanned aerial vehicles (UAVs). Environments with many buildings and other types of obstacles and/or an uneven terrain are harder to be explored as occlusion of objects of interest may often occur. First, in this article, the problem of autonomous reconnaissance in a complex urban environment via a swarm of UAVs is formulated. Then, the algorithm based on the metaheuristic approach is proposed for a solution. This solution lies in deploying a number of waypoints in the area of interest to be explored, from which the monitoring is performed, and planning the routes for available UAVs among these waypoints so that the monitored area is as large as possible and the operation as short as possible. In the last part of this article, two types of main experiments based on computer simulations are designed to verify the proposed algorithms. The first type focuses on comparing the results achieved on the benchmark instances with the optimal solutions. The second one presents and discusses the results obtained from a number of scenarios, which are based on typical reconnaissance operations in real environments.

This paper deals with the model of observation posts deployment in the area of operations. The goal of the model is to find optimal positions for a number of observation posts in order to observe as large area of interest as possible provided that the tactical requirements and conditions for the task at hand are kept. The first part of the paper presents the mathematical formulation of the model. Then, a stochastic algorithm based on the simulated annealing principle is proposed for the problem solution. Next part shows the application of the model which is implemented in the Tactical Decision Support System, the purpose of which is to aid commanders on the tactical level in their decision-making process. The last part shows results from experiments conducted on a set of benchmark problems which are based on the typical military scenarios.

In recent years, the use of modern technology in military operations has become standard practice. Unmanned systems play an important role in operations such as reconnaissance and surveillance. This article examines a model for planning aerial reconnaissance using a fleet of mutually cooperating unmanned aerial vehicles to increase the effectiveness of the task. The model deploys a number of waypoints such that, when every waypoint is visited by any vehicle in the fleet, the area of interest is fully explored. The deployment of waypoints must meet the conditions arising from the technical parameters of the sensory systems used and tactical requirements of the task at hand. This paper proposes an improvement of the model by optimizing the number and position of waypoints deployed in the area of interest, the effect of which is to improve the trajectories of individual unmanned systems, and thus increase the efficiency of the operation. To achieve this optimization, a modified simulated annealing algorithm is proposed. The improvement of the model is verified by several experiments. Two sets of benchmark problems were designed: (a) benchmark problems for verifying the proposed algorithm for optimizing waypoints, and (b) benchmark problems based on typical reconnaissance scenarios in the real environment to prove the increased effectiveness of the reconnaissance operation. Moreover, an experiment in the SteelBeast simulation system was also conducted.