MetaLoc: Learning to Learn Indoor RSS Fingerprinting Localization over Multiple Scenarios

The existing indoor fingerprinting methods based on received signal strength (RSS) are rather accurate after intensive offline calibration for a specific scenario, but the well-calibrated localization model (can be a pure statistical one or a data-driven one) will present poor generalization ability in a new scenario, which results in big loss in knowledge and human effort. To break the scenario-specific localization bottleneck, we propose a new-fashioned data-driven fingerprinting method for localization based on meta-learning, named by MetaLoc, that can adapt itself rapidly to a new, possibly unseen, scenario with very little calibration work. Specifically, the underlying localization model is taken to be a deep neural network (NN), and we train an optimal set of group-specific meta-parameters by leveraging historical data collected from diverse well-calibrated indoor scenarios and the maximum mean discrepancy criterion. Simulation results confirm that the meta-parameters obtained for MetaLoc achieves very rapid adaptation to new scenarios, competitive localization accuracy, and high resistance to significantly reduced reference points (RPs), saving a lot of calibration effort.