This paper investigates a tightly-coupled Global Position System (GPS)/Ultra-Wideband (UWB)/Inertial Navigation System (INS) cooperative positioning scheme using a Robust Kalman Filter (RKF) supported by V2I communication. The scheme proposes a method that uses range measurements of UWB units transmitted among the terminals as augmentation inputs of the observations. The UWB range inputs are used to reform the GPS observation equations that consist of pseudo-range and Doppler measurements and the updated observation equation is processed in a tightly-coupled GPS/UWB/INS integrated positioning equation using an adaptive Robust Kalman Filter. The result of the trial conducted on the roof of the Nottingham Geospatial Institute (NGI) at the University of Nottingham shows that the integrated solution provides better accuracy and improves the availability of the system in GPS denied environments. RKF can eliminate the effects of gross errors. Additionally, the internal and external reliabilities of the system are enhanced when the UWB observables received from the moving terminals are involved in the positioning algorithm.

The integration of Global Positioning Systems (GPS) with Inertial Navigation Systems (INS) has been very actively studied and widely applied for many years. Some sensors and artificial intelligence methods have been applied to handle GPS outages in GPS/INS integrated navigation. However, the integrated system using the above method still results in seriously degraded navigation solutions over long GPS outages. To deal with the problem, this paper presents a GPS/INS/odometer integrated system using a fuzzy neural network (FNN) for land vehicle navigation applications. Provided that the measurement type of GPS and odometer is the same, the topology of a FNN used in a GPS/INS/odometer integrated system is constructed. The information from GPS, odometer and IMU is input into a FNN system for network training during signal availability, while the FNN model receives the observations from IMU and odometer to generate odometer velocity correction to enhance resolution accuracy over long GPS outages. An actual experiment was performed to validate the new algorithm. The results indicate that the proposed method can improve the position, velocity and attitude accuracy of the integrated system, especially the position parameters, over long GPS outages.

The radio map construction is usually time-consuming and labor-sensitive in indoor fingerprinting localization. We propose a fast construction method by using an adaptive path loss model interpolation. Received signal strength (RSS) fingerprints are collected at sparse reference points by using multiple smartphones based on crowdsourcing. Then, the path loss model of an access point (AP) can be built with several reference points by the least squares method in a small area. Afterwards, the RSS value can be calculated based on the constructed model and corresponding AP’s location. In the small area, all models of detectable APs can be built. The corresponding RSS values can be estimated at each interpolated point for forming the interpolated fingerprints considering RSS loss, RSS noise and RSS threshold. Through combining all interpolated and sparse reference fingerprints, the radio map of the whole area can be obtained. Experiments are conducted in corridors with a length of 211 m. To evaluate the performance of RSS estimation and positioning accuracy, inverse distance weighted and Kriging interpolation methods are introduced for comparing with the proposed method. Experimental results show that our proposed method can achieve the same positioning accuracy as complete manual radio map even with the interval of 9.6 m, reducing 85% efforts and time of construction.

Location-based services (LBS) are services offered through a mobile device that take into account a device’s geographical location. To provide position information for these services, location is a key process. GNSS (Global Navigation Satellite System) can provide sub-meter accuracy in open-sky areas using satellite signals. However, for indoor and dense urban environments, the accuracy deteriorates significantly because of weak signals and dense multipaths. The situation becomes worse in indoor environments where the GNSS signals are unreliable or totally blocked. To improve the accuracy of indoor positioning for location-based services, an improved WiFi/Pedestrian Dead Reckoning (PDR) integrated positioning and navigation system using an adaptive and robust filter is presented. The adaptive filter is based on scenario and motion state recognition and the robust filter is based on the Mahalanobis distance. They are combined and used in the WiFi/PDR integrated system to weaken the effect of gross errors on the dynamic and observation models. To validate their performance in the WiFi/PDR integrated system, a real indoor localization experiment is conducted. The results indicate that the adaptive filter is better able to adapt to the circumstances of the dynamic model by adjusting the covariance of the process noise and the robust Kalman filter is able to mitigate the harmful effect of gross errors from the WiFi positioning.

Currently, indoor locations based on the received signal strength (RSS) of Wi-Fi are attracting more and more attention thanks to the technology’s low cost, low power consumption and wide availability in mobile devices. However, the accuracy of Wi-Fi positioning is limited, due to the signal fluctuation and indoor multipath interference. In order to overcome this problem, this paper proposes a robust and accurate Wi-Fi fingerprint location recognition method based on a deep neural network (DNN). A stacked denoising auto-encoder (SDAE) is used to extract robust features from noisy RSS to construct a feature-weighted fingerprint database offline. We use the combination of the weights of posteriori probability and geometric relationship of fingerprint points to calculate the coordinates of unknown points online. In addition, we use constrained Kalman filtering and hidden Markov models (HMM) to smooth and optimize positioning results and overcome the influence of gross error on positioning results, combined with characteristics of user movement in buildings, both dynamic and static. The experiment shows that the DNN is feasible for position recognition, and the method proposed in this paper is more accurate and stable than the commonly used Wi-Fi positioning methods in different scenes.