Indoor localization and navigation have become an increasingly important problem in both industry and academia with the widespread use of mobile smart devices and the development of network techniques. The Wi-Fi-based technology shows great potential for applications due to the ubiquitous Wi-Fi infrastructure in public indoor environments. Most existing approaches use trilateration or machine learning methods to predict locations from a set of annotated Wi-Fi observations. However, annotated data are not always readily available. In this paper, we propose a robot-aided data collection strategy to obtain the limited but high-quality labeled data and a large amount of unlabeled data. Furthermore, we design two deep learning models based on a variational autoencoder for the localization and navigation tasks, respectively. To make full use of the collected data, a hybrid learning approach is developed to train the models by combining supervised, unsupervised and semi-supervised learning strategies. Extensive experiments suggest that our approach enables the models to learn effective knowledge from unlabeled data with incremental improvements, and it can achieve promising localization and navigation performance in a complex indoor environment with obstacles.
Keywords: Wi-Fi-based indoor localization and navigation; deep reinforcement learning; semi-supervised learning; unsupervised learning.