Robust 3D Indoor VLP System Based on ANN Using Hybrid RSS/PDOA

Abstract

Indoor location-based services are becoming crucial parts of smart living, smart manufacturing, and all kinds of the Internet of Things. Visible light-based positioning (VLP) system is one of the cost-efficient and RF radiation-free solutions. However, conventional received signal strength (RSS)-based VLP system suffers inaccurate modeling and intensity variations, especially in 3-D positioning cases. Hence, we propose an artificial neural network (ANN)-based approach for accurate modeling and positioning with on-site data. Likewise, the proposed approach is also proved applicable to accurate modeling of initial time delay distribution of LED chips in VLP systems based on phase differences of arrival (PDOA). To improve the robustness by mitigating the impact of intensity variations, we introduce a selection strategy utilizing both PDOA and RSS measurements. Through simulations, we demonstrate the feasibility of ANN-based on-site modeling and present the robustness of the hybrid positioning system under various levels of intensity variations.

Keywords

• ANN
• pre-training
• PDOA
• RSS
• VLP