摘要：Ubiquitous global positioning is not feasible by GNSS alone, as it lacks accurate position fixes in dense urban centres and indoors. Hybrid positioning methods have been developed to aid GNSS in those environments. Fingerprinting localization in wireless local area networks (WLANs) is a promising aiding system because of its availability, accuracy, and error mechanisms opposed to that of GNSS. This article presents a low-cost approach to ubiquitous, seamless positioning based on a particle filter integrating GNSS pseudoranges and WLAN received signal strength indicators (RSSIs). To achieve accurate location estimates indoors/outdoors and in the transition zones, appropriate likelihood functions are essential as they determine the influence of each sensor information on the position estimate. We model the spatial RSSI distributions with Gaussian processes and use these models to predict RSSIs at the particle’s positions to obtain point estimates of the RSSI likelihood function. The particle filter’s performance is assessed with real data of two test trajectories in an environment challenging for GNSS and WLAN fingerprinting localization. Outcomes of an extended Kalman filter using pseudoranges and a WLAN position as observation is included as benchmark. The proposed algorithm achieves accurate and robust seamless localization with a median accuracy of five meters.
