In the domains of the Internet of Things (IoT) and intelligent transportation, the importance of integrity monitoring has become increasingly prominent with the rapid development of autonomous driving. In complex environments, the redundancy of effective observations often fails to meet the stringent requirements of integrity monitoring. Moreover, due to the effects of multipath (MP) and Non-Line-of-Sight (NLOS), receiver noise frequently deviates from the Gaussian distribution, thereby significantly degrading the performance of traditional Global Navigation Satellite System (GNSS) / Inertial Navigation System (INS) integrated navigation algorithms. Capitalizing on the rapid deployment of Low Earth Orbit (LEO) satellite constellations, this paper proposes a novel integrity monitoring algorithm for GNSS/LEO/INS tightly coupled (TC) systems within the KalmanNet framework. First, LEO satellites provide enhanced observational redundancy, thereby improving the reliability of integrity monitoring. Second, the proposed algorithm relaxes the Gaussian noise assumption and instead utilizes a masked Convolutional Neural Network (CNN) - Long Short Term Memory (LSTM) - Attention (CLA) network to learn features from the observation data. Experimental results demonstrate that the proposed algorithm achieves root mean square error (RMSE) reductions of 55.53%, 51.74%, 36.42% and 29.50% compared to Standard Point Positioning (SPP), TC IGG3, RLAKF and BSRMCL algorithms, respectively.

Non-line of sight (NLOS) and multipath are known to cause pseudorange measurement errors, leading to excessive positioning errors in challenging urban environments. Although GNSS and inertial measurement units (IMU) integrated system can enhance the positioning performance, the positioning accuracy is still constrained by the filter performance. The existing pseudorange correction algorithm employs simple measurement noise covariance adjusting strategy, which is unable to adapt the varying measurement noise in the complex urban environment. To solve this issue, a 3-D grid-based resilient pseudorange error prediction algorithm is proposed to adjust the measurement noise covariance R in Kalman filter (3D-RKF) in urban areas. The urban area is divided by the proposed 3-D grid layout and the pseudorange errors are predicted by ensemble bagged regression tree (EBRT) grid by grid to achieve fine-scale pseudorange prediction. R is then updated by the proposed model reliability indicator (MRI)-based adaptive fusion strategy. Experimental results in complex urban areas prove the proposed algorithm can reach a 3-D accuracy of 10.16 m, with an improvement of 52% compared to the EKF-based fusion, 33% compared to 2-D grid-based adaptive Kalman filter algorithm without MRI-based adaptive fusion strategy (2D-AKF) and 22% compared to 3-D grid-based adaptive Kalman filter algorithm without MRI-based adaptive fusion strategy (3D-AKF), respectively.

Global navigation satellite systems (GNSS), integrated with an inertial measurement unit (IMU) and visual sensors, are widely used for vehicular navigation. With the advancement of emerging vehicular technologies, the performance requirements for positioning, navigation, and timing (PNT) have become critical, emphasizing not only positioning accuracy but also high reliability. However, GNSS signals are susceptible to reflection and diffraction in urban environments, leading to multipath effects, such as non-line-of-sight (NLOS) reception and multipath interference. The GNSS positioning errors will increase significantly, causing the integrated navigation system to fail to meet the high-performance navigation requirements. To address this issue, we have proposed a robust GNSS/IMU/visual odometry (VO) fusion algorithm with a new GNSS weighting model and an adaptive VO velocity measurement update algorithm for urban navigation. In particular, a multipath inflation factor, based on real-time IMU and VO data, is proposed for the GNSS weighting model to mitigate multipath effects. A VO variance attenuation factor based on zero velocity detection in a robust extended Kalman filter (REKF) is also designed to adaptively adjust the covariance of VO measurements, enhancing the overall robustness of the integrated system. A field test was conducted in urban environments. The results show that the proposed algorithm achieves horizontal and 3-D positioning accuracy of 3.38 m and 5.00 m, respectively, outperforming the conventional GNSS/IMU/VO integration using C/N0-based weighting model. The improvements in horizontal and 3-D positioning accuracy are 63.4% and 56.1%, respectively.

The rapidly increasing demand for high-precision positioning has prompted researchers to develop real-time kinematic (RTK) techniques. In urban areas, however, global navigation satellite system (GNSS) signals are susceptible to obstruction, reflection, and diffraction by dense foliage and buildings, leading to a reduction in the number of tracked satellites and a degradation of GNSS raw measurements due to nonline-of-sight (NLOS) signals and multipath errors. This, in turn, increases the difficulty of accurately resolving integer ambiguities. To address this issue, this article proposes a combined strategy to exclude satellites contaminated by NLOS or multipath. Based on the combined strategy, two single-epoch ambiguity resolution methods, proposed method 1 (PM1) and proposed method 2 (PM2), are introduced. Three kinematic field tests conducted in different typical urban environments are used to validate the effectiveness of the proposed strategy. The correctly fixed means a less than 0.1 m 3-D positional error. The results indicate that, with a mask angle of 10°, the correctly fixed rates of PM1 and PM2 are 96.0% and 97.0% in scenario 1, 63.9% and 64.4% in scenario 2, and 55.9% and 62.7% in scenario 3, respectively. These rates are higher than those of comparative method 1 (CM1) and comparative method 2 (CM2), which are 79.6% and 85.7%, 32.9% and 45.0%, and 29.9% and 45.0% in scenarios 1, 2, and 3, respectively. When the mask angle increases to 20°, the correctly fixed rates of PM1 and PM2 are 96.8% and 97.6% in scenario 1, 63.9% and 64.5% in scenario 2, and 56.8% and 63.9% in scenario 3, respectively. Compared to CM1 and CM2, this represents an improvement of between 7.8 and 27.4% points.

Integration of global navigation satellite systems (GNSS) with other sensors, such as inertial measurement units (IMU) and visual sensors, has been widely used to improve the positioning accuracy and availability of the vehicles for the Internet of Things (IoT) applications in smart cities. The traditional extended Kalman filter (EKF)-based fusion scheme, with the assumption of fixed measurements of different sensors and inaccurate GNSS quality assessment, is vulnerable to non-line-of-sight (NLOS) and multipath contaminated GNSS, as well as low-quality vision measurement. In order to tackle this issue, we have proposed an adaptive weighting strategy for GNSS/IMU/Vision integration. On the basis of dual-check GNSS assessment, we adjust the weights of the vision and GNSS measurements adaptively based on the chi-square test statistic. The field tests have demonstrated that the proposed algorithm achieves horizontal positioning root mean-square errors (RMSEs) of 11.92 and 3.61 m in deep and mild urban environments. The accuracy has improvements of 78.57% and 43.9% over traditional EKF-based GNSS/IMU fusion, and 21.53% and 23.49% over compared EKF-based GNSS/IMU/Vision fusion, respectively.

Positioning, navigation, and timing (PNT) is essential for Internet of Things (IoT) communications and location-based services. Although global navigation satellite system (GNSS) can provide accurate PNT in open areas, obtaining reliable PNT is still a considerable technical challenge in complex urban environments. This is because the GNSS signals are more likely to be affected by multipath interference and nonline of sight (NLOS) reception issues arising from the obstructions and reflections in built environments. These introduce range measurement errors that degrade the GNSS positioning accuracy. This article proposes two resilient pseudorange error prediction and correction strategies to improve the GNSS positioning accuracy in urban environments. In particular, considering the carrier-to-noise density ($C/N$textsubscript 0), satellite elevation angle, and local positional information, the random forest-based pseudorange error prediction and correction models are constructed in two variations, including: 1) the point-based correction (PBC) and 2) the grid-based correction (GBC). The final improved positioning solution is then calculated by using the least square method (LSM) of the corrected pseudoranges. Kinematic test results in urban environments show that both variations of the proposed model can improve the positioning accuracy by 42.9% and 40.8% in horizontal, and by 60.1% and 63.3% in 3-D, respectively, compared to the positioning results obtained by the traditional method without pseudorange error corrections. The improvements are 41.1% and 38.9% in horizontal, and 45.7% and 50.0% in 3-D, respectively, compared with traditional elevation angle weighting method.

The accuracy of location information, mainly provided by the global positioning system (GPS) sensor, is critical for Internet-of-Things applications in smart cities. However, built environments attenuate GPS signals by reflecting or blocking them resulting in some cases multipath and non-line-of-sight (NLOS) reception. These effects cause range errors that degrade GPS positioning accuracy. Enhancements in the design of antennae and receivers deliver a level of reduction of multipath. However, NLOS signal reception and residual effects of multipath are still to be mitigated sufficiently for improvements in range errors and positioning accuracy. Recent machine learning-based methods have shown promise in improving pseudorange-based position solutions by considering multiple variables from raw GPS measurements. However, positioning accuracy is limited by low accuracy signal reception classification. Unlike the existing methods, which use machine learning to directly predict the signal reception classification, we use a gradient boosting decision tree (GBDT)-based method to predict the pseudorange errors by considering the signal strength, satellite elevation angle and pseudorange residuals. With the predicted pseudorange errors, two variations of the algorithm are proposed to improve positioning accuracy. The first corrects pseudorange errors and the other either corrects or excludes the signals determined to contain the effects of multipath and NLOS signals. The results for a challenging urban environment characterized by high-rise buildings on one side, show that the 3-D positioning accuracy of the pseudorange error correction-based positioning measured in terms of the root mean square error is 23.3 m, an improvement of more than 70% over the conventional methods.

The detection of driving events could be useful for reducing accidents, fleet management and insurance premiums etc. Currently, top of the range vehicles and large fleets employ expensive driver monitoring systems. However, most drivers do not have access to such systems. The required monitoring platform would have to deliver the required performance while also being affordable and accessible. A candidate with considerable promise is the smartphone with sensors built-in that could be exploited for the detection of driving events. However, to date it has not been possible to achieve the required correct, missed and false detection rates in addition to the computational efficiency for real-time operations. This paper proposes a novel bagging tree and dynamic time warping (DTW) integrated algorithm for the detection of driving events employing acceleration and orientation data from a smartphone's low cost three-axis accelerometers and gyroscopes. The bagging tree-based machine learning algorithm provides the initial maneuver detection results, as well as the location of the event start and end points. Event detection is then achieved by calculating the similarity of the results predicted through the bagging tree algorithm with the corresponding templates extracted from the experience datasets, while also applying a number of constraints to verify the calculated results. Field test results show that the proposed integrated algorithm is superior to the state-of-the-art, achieving a high correct detection accuracy of 97.5%, a low missed detection of 2.5% and a false detection rate of 2.9%. The corresponding results for the best alternative candidate method are 90.2%, 9.8% and 11.7%. Furthermore, the improvement in computational efficiency offered by our proposed approach is three to more than ten times greater than that of the other state-of-the-art algorithms.

With the development of the Internet of Underwater Things (IoUT), two critical problems have been prominent, i.e., the energy constraint of underwater devices and large demand for data collection. In this article, we introduce an autonomous underwater vehicle (AUV)-aided underwater acoustic sensor networks (UWSNs) to solve these problems. To improve the performance of UWSNs, we formulate an optimization problem to maximize the energy consumption utility, which is defined to balance the energy consumption and network throughput. To solve this optimization problem, we decompose it into four parts. First, due to the constraint of communication distance, we construct a cluster-based network and formulate the selection of cluster heads as a maximal clique problem (MCP). Second, the clustering algorithm is proposed. Third, we design a novel media access control (MAC) protocol to coordinate data transmission between AUV and cluster heads, among intracluster nodes, as well as among intercluster nodes. Finally, path planning of AUV is formulated as a traveling salesman problem to minimize AUV travel time. Based on the above analysis, two algorithms, namely, AUV-aided energy-efficient data collection (AEEDCO) and approximate AUV-aided energy-efficient data collection (AEEDCO-A), are developed accordingly. The simulation results show that the proposed algorithms perform well and are very promising in UWSNs with demand for large-scale communication, large system capacity, long-term monitoring, and high data traffic load.