Localization with Wi-Fi Ranging and Built-in Sensors: Self-Learning Techniques

Securing precise distance measurements from nearby reference nodes is a critical task in determining the performance of range-based positioning solutions. However, the multipath propagation characteristics of wireless channels render it difficult to obtain precise ranging results. In this context, this chapter utilizes machine learning techniques that extract useful features from Wi-Fi measurements to identify channel conditions and thus produce enhanced ranging results. Specifically, two neural networks (NN) are designed to perform ranging procedures for signal strength-based and round-trip time-based ranging scenarios. Furthermore, self-learning techniques that train the proposed NN-based ranging models with unlabeled training data are discussed in detail. The effectiveness of the proposed ranging models and self-learning techniques is extensively verified using a real-time positioning application.