Advancing Indoor Environment Modeling: A Comparative Study of Evolutionary Algorithms for Optimal Sensor Placement

This study advances indoor environment modeling by focusing on the optimal placement of sensors. Our approach involves creating a detailed environment model from a 3D point cloud by identifying spatial boundaries and furniture in indoor spaces, which are then represented as a series of polygons. To validate our method, we compare its performance against ground truth data, demonstrating high accuracy in both simple and complex environments. The core of our study is a comprehensive experiment that evaluates the effectiveness of three evolutionary nature-inspired genetic and three metaheuristic iterative optimization algorithms in solving the sensor placement problem in a complex environment scenario. We perform a statistical analysis to understand the impact of the choice of optimization algorithm and the number of sensors on the achieved spatial coverage. This analysis provides insights into the comparative effectiveness of various evolutionary algorithms in enhancing sensor network design within intricate indoor spaces. In particular, the Artificial Bee Colony algorithm consistently delivered superior results.