Sensor Coverage and Target Detection Optimization using Genetic Algorithms

In battlefield environments, enhancing situational awareness requires particular attention to two critical factors: coverage and detection. This study aims to optimize the coverage of a designated region and the detection of multiple targets using a limited set of available sensors. A Genetic Algorithm (GA)–based approach is employed to determine the optimal sensor deployment, maximizing both area coverage and target detection while minimizing the number of sensors used and ensuring a uniform spatial distribution. Uniformity is achieved by minimizing the repulsive forces between sensors, where these forces are modeled as functions of sensor strength and inter sensor distance. From this perspective, the fitness function consists of multiple objectives that are combined into a single scalar value by applying appropriate weighting factors. A compact chromosome structure is developed to support this multi-objective formulation. Each gene block encodes both the deployment coordinates and the type of sensor to be placed. Binary gene encoding is used to represent a wide range of continuous position values as well as sensor types. Targets are randomly distributed within a specified region, and it is assumed that they move collectively within a localized neighborhood. During the GA selection phase, the best chromosome is preserved in the chromosome pool. If the best solution remains unchanged for a predefined number of iterations, the algorithm terminates and the corresponding chromosome is taken as the optimal sensor deployment configuration.