GNSS outage

Inertial navigation systems (INS) are widely recognized for providing precise location, velocity, and attitude data over short durations. However, their accuracy deteriorates over time. To maintain accurate navigation, it is crucial to characterize and model both deterministic and stochastic error components of inertial sensors. This article employs three techniques for modeling stochastic errors: the autocorrelation function (ACF), the Allan variance (AV), and the generalized method of wavelet moments (GMWM). Two different-grade inertial measurement units (IMUs) evaluate the effectiveness of ACF, AV, and GMWM in modeling inertial sensor noise: The ADIS low-cost microelectromechanical systems (MEMS) grade IMU and the Spatial MEMS tactical-grade IMU. A laboratory calibration test is conducted to eliminate deterministic errors. A strategy for modeling stochastic errors of MEMS inertial sensors is presented, involving selecting the best model for each sensor using the three techniques rather than applying a single model. Based on a comparison of the three techniques, GMWM measurements are used for the navigation algorithms. GMWM’s performance modeling stochastic errors are analyzed using real dynamic in-field datasets collected by both IMUs, with induced GPS signal outages. Three extended Kalman filter (EKF) INS/GNSS integrated navigation algorithms are implemented based on ACF analysis and GMWM-based model selection. A 15-state algorithm based on a $1{\text{st}}$ order Gauss-Markov (GM) estimated by ACF, a 45-state algorithm based on ADIS IMU data, and a 57-state algorithm based on Spatial IMU data are compared. The experimental results demonstrate that the proposed 45-state navigation algorithm reduces the 2-D position RMSE by approximately 67% compared to the conventional 15-state algorithm, while the 57-state algorithm achieves an improvement of around 64%.

Autonomous vehicles are widely used in logistics, public transportation, and specialized industries, its high-precision navigation and positioning is predominantly supported through strapdown inertial navigation system/global navigation satellite system (SINS/GNSS) integrated navigation, thus ensuring safe and efficient operations. In practice, GNSS is prone to intermittent outage due to environment interference, while Non-Holonomic Constraint (NHC) can significantly improve navigation accuracy. Unfortunately, the mounting error angle and lever arm lead to NHC mismatch, and the performance of existing NHC method is also affected by the state-space model inconsistency and non-stationarity outlier noises. To solve the problems, a consistent-robust SINS/GNSS/NHC integrated navigation method is proposed, which includes two stages: off-line calibration and online navigation. In off-line calibration stage, a two-step-based estimation method is proposed to determine the mounting error angle and lever arm. The more consistent state-space model is deduced to estimate mounting error angle using the virtual dead-reckoning constructed from the posteriori straight-driving data, based on which the lever arm can be accurately estimated using posterior turn-driving data. In online navigation stage, the Lie group-based NHC model is established, and the non-stationary outlier noise is modeled as Gaussian-Student's t mixture distribution. Meanwhile, the strong tracking method is introduced to fine-calibrate the accuracy of initial parameter. Finally, the variational Bayesian is used to jointly estimate the navigation state and parameters. The simulation and car-mounted field test results illustrate that the proposed method has better estimation accuracy than existing state-of-the-art methods, enhancing the navigation and positioning capabilities of autonomous vehicles during intermittent GNSS outage.

To address the performance degradation of inertial navigation systems (INSs) during global navigation satellite system (GNSS) signal outages in complex environments, this article proposes an error compensation method for INS nonholonomic constraints (NHCs) based on gated recurrent units (GRUs). The method leverages the GRU neural network to generate pseudo-measurements during GNSS signal outage. These pseudo-measurements are then fused with INS NHC information using an optimized adaptive Kalman filter (AKF), forming an error compensation model for the integrated navigation system. Additionally, a training optimization strategy based on the ratio test value is introduced, which dynamically adjusts the weights of samples in the loss function, enabling differential treatment of measurements with varying confidence levels. The effectiveness of the proposed method is evaluated across three representative trajectory scenarios. Experimental results demonstrate that, compared to traditional methods, the proposed approach reduces positioning errors by more than 25% in all three scenarios, confirming its superior performance and robustness during GNSS signal outages.

The integrated navigation system consisting of an inertial navigation system (INS) and Global Navigation Satellite System (GNSS) provides continuous high-accuracy positioning whereas the navigation accuracy during a GNSS outage inevitably degrades owing to INS error divergence. To reduce such degradation, a gated recurrent unit (GRU) and adaptive Kalman filter (AKF)-based hybrid algorithm is proposed. The GRU network, which has advantages of high accuracy and efficiency, is constructed to predict the position variations during GNSS outage. Furthermore, this paper takes the GRU-predicted error accumulation into consideration, and introduces AKF as a supplementary methodology to improve the navigation performance. The proposed hybrid algorithm is trained and tested by practical road datasets and compared with four algorithms, including the standard KF, Multi-Layer Perceptron (MLP)-aided KF, Long Short Time Memory (LSTM) aided KF, and GRU-aided KF. Periods of 180 and 120 s GNSS outage are employed to test the performance of the proposed algorithm in different time scales. The comparison result between the standard KF and neural network-aided KF indicates that the neural network is an effective methodology for bridging GNSS outages. The performance comparison between three kinds of neural networks demonstrate that both recurrent neural networks surpass the MLP in prediction position variation, and the GRU transcends the LSTM in prediction accuracy and training efficiency. Furthermore, it is concluded that the adaptive estimation theory is an effective complement to neural network-aided navigation, as the GRU-aided AKF reduced the horizontal error of GRU-aided KF by 31.71% and 16.12% after 180 and 120s of GNSS outage, respectively.

In the fields of positioning and navigation, the integrated inertial navigation system (INS)/global navigation satellite systems (GNSS) are frequently employed. Currently, high-precision INS typically utilizes fiber optic gyroscopes (FOGs) and quartz flexural accelerometers (QFAs) rather than MEMS sensors. But when GNSS signals are not available, the errors of high-precision INS also disperse rapidly, similar to MEMS-INS when GNSS signals would be unavailable for a long time, leading to a serious degradation of the navigation accuracy. This paper presents a new AI-assisted method for the integrated high-precision INS/GNSS navigation system. The position increments during GNSS outage are predicted by the convolutional neural network-gated recurrent unit (CNN-GRU). In the process, the CNN is utilized to quickly extract the multi-dimensional sequence features, and GRU is used to model the time series. In addition, a new real-time training strategy is proposed for practical application scenarios, where the duration of the GNSS outage time and the motion state information of the vehicle are taken into account in the training strategy. The real road test results verify that the proposed algorithm has the advantages of high prediction accuracy and high training efficiency.

No abstract available

No abstract available

When INS/GNSS (inertial navigation system/global navigation satellite system) integrated system is applied, it will be affected by the insufficient number of visible satellites, and even the satellite signal will be lost completely. At this time, the positioning error of INS accumulates with time, and the navigation accuracy decreases rapidly. Therefore, in order to improve the performance of INS/GNSS integration during the satellite signals interruption, a novel learning algorithm for neural network has been presented and used for intelligence integrated system in this article. First of all, determine the input and output of neural network for intelligent integrated system and a nonlinear model for weighs updating during neural network learning has been established. Then, the neural network learning based on strong tracking and square root UKF (unscented Kalman filter) is proposed for iterations of the nonlinear model. In this algorithm, the square root of the state covariance matrix is used to replace the covariance matrix in the classical UKF to avoid the filter divergence caused by the negative definite state covariance matrix. Meanwhile, the strong tracking coefficient is introduced to adjust the filter gain in real-time and improve the tracking capability to mutation state. Finally, an improved calculation method of strong tracking coefficient is presented to reduce the computational complexity in this algorithm. The results of the simulation test and the field-positioning data show that the proposed learning algorithm could improve the calculation stability and robustness of neural network. Therefore, the error accumulation of INS/GNSS integration is effectively compensated, and then the positioning accuracy of INS/GNSS intelligence integrated system has been improved.

No abstract available

The absence of a reliable Global Navigation Satellite System (GNSS) signal leads to degraded position robustness in standalone receivers. To address this issue, integrating GNSS with inertial measurement units (IMUs) can improve positioning accuracy. This article analyzes the performance of tightly coupled GNSS/IMU integration, specifically the forward Kalman filter and smoothing algorithm, using both single and network GNSS stations and the post-processed kinematic (PPK) method. Additionally, the impact of simulated GNSS signal outage on exterior orientation parameters (EOPs) solutions is investigated. Results demonstrate that the smoothing algorithm enhances positioning uncertainty (RMSE) for north, east, and heading by approximately 17–43% (e.g., it improves north RMSE from 51 mm to a range of 42 mm, representing a 17% improvement). Orientation uncertainty is reduced by about 60% for roll, pitch, and heading. Moreover, the algorithm mitigates the effects of GNSS signal outage, improving position uncertainty by up to 95% and orientation uncertainty by up to 60% using the smoothing algorithm instead of the forward Kalman filter for signal outages up to 180 s.

No abstract available

Integration of inertial navigation system (INS) and global navigation satellite systems (GNSS) is a promising approach to vehicle self-localization. However, such a scheme may have poor performance during GNSS outages, and the errors of INS also disperse rapidly, leading to a serious degradation of the positioning accuracy. To address the issue of GNSS signal failure, this article presents an enhanced vehicle self-positioning method based on factor graph optimization (FGO) and convolutional neural network (CNN)-long short-term memory (LSTM)-Attention. An odometer (ODO) sensor is introduced to provide additional velocity information in the direction of the vehicle’s movement, and the FGO is employed for achieving the fusion of GNSS/INS/ODO data. The position increments during GNSS outage are predicted by a CNN-LSTM-Attention model, which utilize a CNN to quickly extract features from the input signals, an LSTM network to model the time series, and an attention mechanism to dynamically focus on the most important parts of the input sequence, thereby improving the overall prediction accuracy and robustness of the model. The road experiments based on the real-world data collected from practical vehicle platform have demonstrated the effectiveness and advantage of our proposed method in enhancing the vehicle self-positioning performance during GNSS outages. For instance, in the experiments of GNSS interruption for 60 and 90 s, the RMSEs of CNN-LSTM-Attention + FGO(INS/ODO) for the position have the performance improvement of 34.62% and 46.58% over LSTM + FGO(INS/ODO), respectively.

Navigation for autonomous robots in hazardous environments demands robust localization solutions. In challenging environments such as tunnels and urban disaster areas, autonomous robots and vehicles are particularly important for search and rescue operations. However, especially in these environments, sensor failures and errors make the localization task particularly difficult. We propose a robust sensor fusion algorithm that integrates data from a thermal camera, a LiDAR sensor, and a GNSS to provide reliable localization, even in environments where individual sensor data may be compromised. The thermal camera and LiDAR sensor employ distinct SLAM and odometry techniques to estimate movement and positioning, while an extended Kalman filter (EKF) fuses all three sensor inputs, accommodating varying sampling rates and potential sensor outages. To evaluate the algorithm, we conduct a field test in an urban environment using a vehicle equipped with the appropriate sensor suite while simulating an outage one at a time, to demonstrate the approach’s effectiveness under real-world conditions.

An integrated navigation system that combines the global navigation satellite system (GNSS) and the inertial navigation system (INS) provides accurate navigation and positioning information for carriers. However, the complex traffic environment leads to frequent GNSS outages. The positioning accuracy of the GNSS/INS integrated navigation system decreases due to the lack of global positioning information. In order to address this problem, we propose a hybrid GNSS/INS integrated navigation method for GNSS outage conditions, combining the GNSS pseudo-measurement regression model and the covariance-adaptive factor graph optimization (CAFGO). The GNSS pseudo-measurement regression model is prone to gradient vanishing caused by high-dimensional data input from high-frequency INS data, leading to a decline in long-sequence feature dependency. To overcome this limitation, an enhanced GNSS pseudo-measurement regression model integrating gated recurrent units (GRU) with self-attention (SA) is proposed, which adaptively weights GRU outputs to enhance focus on critical temporal features. Meanwhile, to address the fluctuations in the measurement covariance matrix of GNSS pseudo-measurements caused by the uncertainty of neural networks, we propose a CAFGO method, which adaptively adjusts the covariance of GNSS factors in the optimization process based on model prediction errors. Real-world experiment results indicate that the proposed method effectively improves the positioning accuracy of the GNSS/INS integrated navigation system during GNSS outages. In the 60 s and 120 s GNSS outages comparison experiment, the positioning root mean square error of the proposed method decreased by 70.40% and 49.69% compared to the GRU-factor graph optimization method.

Low-cost Inertial Measurement Units (IMUs) suffer from significant noise and drift, leading to degraded navigation accuracy, particularly in the absence of Global Navigation Satellite System (GNSS) signals. To address this challenge, this paper proposes an optimized Nonlinear Autoregressive Network with Exogenous Inputs (NARX)-based denoising framework, designed through a structured grid search for optimal performance. The proposed model utilizes six input delays and a two-layer neural architecture with 6 and 10 neurons, respectively, to effectively capture temporal dependencies in IMU signals. Two separate NARX networks are trained to denoise acceleration and angular velocity signals using ground truth data from a high-end IMU. The denoised outputs are compared against an Adaptive NeuroFuzzy Inference System (ANFIS) and evaluated across four GNSS outage scenarios, where navigation performance is benchmarked against a radar-aided navigation system. Experimental results demonstrate that the NARX-based approach significantly outperforms both ANFIS and radar-aided solutions, achieving superior IMU signal reconstruction and improved navigation accuracy. This highlights the potential of NARX networks as a robust and reliable alternative for IMU-based navigation in sensor-limited environments, particularly when GNSS is unavailable or degraded.

With the rapid development of intelligent unmanned systems and autonomous navigation technologies, particularly driven by the strategic demands of the low-altitude economy, navigation systems are facing increasingly higher requirements for accuracy and robustness. During global navigation satellite system(GNSS) outages, GNSS/INS integrated navigation degrades into standalone inertial navigation system(INS), which leads to rapid accumulation of positioning errors. This paper proposes the GNSS pseudo-increment prediction method based on the Transformer-long short-term memory (LSTM) network. It utilizes inertial measurement unit measurements and INS output navigation results as inputs, where the Transformer is employed to extract global temporal features and the LSTM is used to model temporal dependencies. The predicted GNSS pseudo-increments are then fused with INS outputs via the Kalman filter(KF) for state updates. Experiments based on the publicly available vehicle dataset demonstrate that during 50s GNSS outage, the proposed method achieves over 90% reduction in horizontal errors compared to pure INS, and over 40% compared with LSTM and Transformer models, respectively. These results confirm that the method effectively mitigates INS drift and significantly enhances the accuracy and robustness of navigation and positioning.

The GNSS-RTK and MEMS-IMU integrated navigation system is a commonly used high-precision, low-cost solution for outdoor positioning. However, the significant measurement error of MEMS-IMU can rapidly lead to divergence in navigation state predictions based on inertial error propagation models. To overcome this limitation and enhance accuracy, maintaining the continuity of RTK measurement information is crucial. Nevertheless, due to the instability of wireless transmission links and communication equipment, or disruptions in base station observations, differential corrections often experience outages, resulting in a decline in measurement information quality and affecting the accuracy of integrated navigation. Therefore, this paper proposes a stable RTK/MEMS-IMU tightly coupled algorithm. During outages of differential corrections, the proposed algorithm utilizes historical differential corrections from the base station along with real-time rover station information to construct a stable double-difference carrier phase vector. This approach ensures the stability of measurement information and enhances positioning accuracy. Simulation results have verified the effectiveness of this method, and land tests have demonstrated that, compared to the traditional RTK/MEMS-IMU tightly coupled algorithm, the position and velocity accuracy of this algorithm during outages of differential corrections have been improved by 29.5% and 18.4%, respectively.

Getting higher precision positioning and velocity result with lower cost in urban environment is an important pursuit of modern intelligent transportation, autonomous driving, and other fields. While a low-cost inertial navigation system (INS) and global navigation satellite systems (GNSS) integrated system have the potential to achieve the pursuit, its performance can be significantly affected by the occasional GNSS outage and variable measurement noise in complex driving environments. Inspired by AI-type solutions for predicting vehicle behavior, and to get rid of their disadvantage of environmental sensitive, we abstract vehicle behaviors in urban environments as constraint models. A multiple constraint fused Kalman-based navigation (MCKN) method for INS/GNSS integrated navigation system is introduced by combining multiple model interaction principle with zero-velocity update (ZVU) error correction algorithm. This novel MCKN approach allows multiple zero-velocity constrained models to work in parallel. The optimal navigation results are obtained by calculating the weights of each model at every positioning epoch. Road test results in the Zhongguancun area of Beijing show that the MCKN method effectively limits the accumulation of low-cost INS errors. During 1-hour experiment, the positioning and velocity error of MCKN method in ±3σ interval were 1.72 m and 0.12 m/s respectively, maintaining a high-level performance.

In cities, global navigation satellite system (GNSS)-based land vehicle navigation is often interrupted due to the occlusion of satellite signals. Even after GNSS signals recover from occlusion, it will take some time for the GNSS receiver to acquire and track the signals again. To restore the navigation service as soon as possible, a micro-electromechanical system (MEMS)-assisted signal tracking method based on adaptive motion constraints is proposed. During GNSS outage, the vehicle’s motion state is identified by detecting the output of MEMS sensor. Meanwhile, in order to improve the identification accuracy of motion states, fuzzy inference is adopted to adaptively adjust the detection threshold, and then, motion constraints-derived virtual measurements are generated and used to maintain the work of the GNSS/inertial navigation system (INS) loosely integrated navigation system. Finally, the parameters of GNSS signals are predicted in real time based on the navigation solution, and the uninterrupted tracking of the occluded GNSS signals is realized. The proposed method is verified by utilizing the low-grade MEMS in different motion states. Experimental results show that the identification of motion states is more accurate based on fuzzy inference, and the prediction errors are reduced with adaptive motion constraints and kept within the tracking range of GNSS receiver. As a result, GNSS signals that are lost for up to 50 s can be locked immediately when they are recovered.

UAVs are nowadays used for several surveying activities, some of which imply flying close to tall walls, in and out of tunnels, under bridges, and so forth. In these applications, RTK GNSS positioning delivers results with very variable quality. It allows for centimetric-level kinematic navigation in real time in ideal conditions, but limitations in sky visibility or strong multipath effects negatively impact the positioning quality. This paper aims at assessing the RTK positioning limitations for lightweight and low-cost drones carrying cheap GNSS modules when used to fly in some meaningful critical operational conditions. Three demanding scenarios have been set up simulating the trajectories of drones in tasks such as infrastructure (i.e., building or bridges) inspection. Different outage durations, flight dynamics, and obstacle sizes have been considered in this work to have a complete overview of the positioning quality. The performed tests have allowed us to define practical recommendations to safely fly drones in potentially critical environments just by considering common software and standard GNSS parameters.

GNSS/INS-based positioning must be revised for forest mapping, especially inside the forest. This study deals with the issue of the processability of GNSS/INS-positioned MLS data collected in the forest environment. GNSS time-based point clustering processed the misaligned MLS point clouds collected from skid trails under a forest canopy. The points of a point cloud with two misaligned copies of the forest scene were manually clustered iteratively until two partial point clouds with the single forest scene were generated using a histogram of GNSS time. The histogram’s optimal bin width was the maximum bin width used to create the two correct point clouds. The influence of GNSS outage durations, signal strength statistics, and point cloud parameters on the optimal bin width were then analyzed using correlation and regression analyses. The results showed no significant influence of GNSS outage duration or GNSS signal strength from the time range of scanning the two copies of the forest scene on the optimal width. The optimal bin width was strongly related to the point distribution in time, especially by the duration of the scanned plot’s occlusion from reviewing when the maximum occlusion period influenced the optimal bin width the most (R2 = 0.913). Thus, occlusion of the sub-plot scanning of tree trunks and the terrain outside it improved the processability of the MLS data. Therefore, higher stem density of a forest stand is an advantage in mapping as it increases the duration of the occlusions for a point cloud after it is spatially tiled.

Time synchronization utilizing the Global Navigation Satellite System (GNSS) is being increasingly investigated for vehicular networks. Due to GNSS signal blockages, the availability and accuracy of GNSS timing solutions in various road settings is a recognized challenge. With the recent improvement of Multi-GNSS technology and the increased capacity of consumer-grade receivers, the application of GNSS in vehicular environments has brightened up. This paper systematically analyzes the required time synchronization of vehicular networks and presents a GNSS-based time synchronization solution. It also experimentally demonstrates the availability and capabilities of GNSS time synchronization using commercial-grade GNSS receivers and off-the-shelf communication devices. Our experiments show that the timing accuracy of an individual vehicular node can be as good as ±2 microseconds, resulting in synchronization accuracy of sub-10 microseconds among nodes. A momentary complete outage of the GNSS time solution due to signal blockage on the road adds clock error, leading to synchronization inaccuracy of up to sub-20 microseconds. This level of inaccuracy still meets the desired requirement for most applications in vehicular communication.

We present a position and attitude estimation algorithm of moving platforms based on the tightly coupled sensor fusion of low-cost multi baseline GNSS, inertial, magnetic and barometric observations obtained by low-cost sensors and affordable dual-frequency GNSS receivers. The sensor fusion algorithm is realized by an Extended Kalman Filter and estimates the states including GNSS receiver inter-channel biases, integer ambiguities and non-GNSS receiver biases. Tightly coupled sensor fusion increases the reliability of the position and attitude solution in challenging environments such as urban canyons by utilizing the inertial observations in case of GNSS outage. Moreover, GNSS observations can be efficiently used to mitigate IMU sensor drifts. Standard GNSS cycle slips detection methods, such as the application of triple differences or linear combinations such as Melbourne–Wübbena combination and the phase ionospheric residual extended TurboEdit method. However, these techniques are not well suited for the localization in quickly changing environments such as urban canyons. We present a new method of tightly coupled sensor fusion supported by a prediction based cycle slip detection technique, applied to a GNSS setup using three antennas leading to multiple moving baselines on the platform. Thus, not only the GNSS signal properties but also the dynamics of the moving platform are considered in the cycle slip detection. The developed algorithm is tested in an open-sky validation measurement and two sets of measurement in an urban canyon area. The sensor fusion algorithm processes the data sets using the proposed prediction-based cycle slip method, the loss-of-lock indicator-based, and for comparison, the Melbourne–Wübbena and the TurboEdit cycle slip detection methods are also included. The obtained position and attitude estimation results are compared to the internal solution of raw data source GNSS receivers and to the observations of a high-accuracy GNSS/INS unit including a fiber optic gyro. The validation test confirms the proper cycle slip detection in an ideal environment. The more challenging urban canyon test results show the reliability and the accuracy of the proposed method. In the case of the second urban canyon test, the proposed method improved the integer ambiguity resolution success rate by 19% and these results show the lowest horizontal and vertical coordinate distortion in comparison of the linear combination and the loss-of-lock-based cycle slip methods.

Global Navigation Satellite System (GNSS) and Inertial Measurement Unit (IMU) are popular navigation sensor for position fixing technique and dead reckoning system that complement each other. GNSS can provide accurate position and velocity information when it establishes a Line of Sight (LOS) with a minimum of four satellites. However, this accuracy can decrease due to signal outage, jamming, interference, and multipath effects. On the other hand, the IMU has the advantage of measuring the platform’s orientation with a high-frequency update and is not affected by environmental conditions. However, a drift effect causes the measurement errors to accumulate. Several studies have demonstrated the fusion of both sensors in terms of the Extended Kalman Filter (EKF). This study conduct sensor fusion for car localization in an urban environment based on the loosely coupled integration scheme. In order to improve the sensor fusion performance, pre-processing GNSS and IMU data were applied. The result shows that pre-processing DGNSS and IMU filtering can increase the accuracy of the integrated navigation solution up to 80.02% in the east, 80.13% in the north, and 89.45% in the up direction during the free outage period.

Ionospheric density irregularities embedded in Equatorial Plasma Bubbles (EPBs), with scale sizes varying from several hundred kilometers to several tens of meters, may cause amplitude and phase scintillation of transionospheric radio waves, degrading the performance and availability of space-based communication and navigation systems. A recent computer simulation study, based on ionospheric irregularities detected by the Planar Langmuir Probe (PLP) onboard the Communication/Navigation Outage Forecasting System (C/NOFS) satellite, analyzed the mitigation effects from space diversity on amplitude scintillation of transionospheric signals received on the ground. The present work, based on experimental data, will confirm and extend the previous results, indicating, in statistically quantitative terms, how space diversity, effective on uplink and downlink ground-satellite paths, particularly in the strong and saturated scintillation regimes, depends on Ionospheric Pierce Point (IPP) dip-latitude and distance intervals, as well as on a well-known amplitude scintillation index.

Traditional navigation systems rely on GNSS/inertial navigation system (INS) integration, in which the INS can provide reliable positioning during short GNSS outages. However, if the GNSS outage persists for prolonged periods of time, the performance of the system will be solely dependent on the INS, which can lead to a significant drift over time. As a result, the need to integrate additional onboard sensors is essential. This study proposes a robust loosely coupled (LC) integration between the INS and LiDAR simultaneous mapping and localization (SLAM) using an extended Kalman filter (EKF). The proposed integrated navigation system was tested for three different driving scenarios and environments using the raw KITTI dataset. The first scenario used the KITTI residential datasets, totaling 48 min, while the second case study considered the KITTI highway datasets, totaling 7 min. For both case studies, a complete absence of the GNSS signal was assumed for the whole trajectory of the vehicle in all drives. In contrast, the third case study considered the use of minimal assistance from GNSS, which mimics the intermittent receipt and loss of GNSS signals for different driving environments. The positioning results of the proposed INS/LiDAR SLAM integrated system outperformed the performance of the INS for the residential datasets with an average reduction in the root mean square error (RMSE) in the horizontal and up directions of 88% and 32%, respectively. For the highway datasets, the RMSE reductions were 70% and 0.2% for the horizontal and up directions, respectively.

Nowadays, the availability of accurate vehicle position becomes more and more indispensable. The GNSS/INS (Global Navigation Satellite Systems/Inertial Navigation System) is currently the most widely-used integrated navigation scheme for land vehicles, which is capable of provide high-accuracy and continuous positioning results in the open-sky environments. However, under the GNSS-denied conditions, the existing GNSS/INS integrated system often fails to provide reliable positioning results due to various and nonlinear errors contained in the MEMS (Micro-Electro-Mechanical System) IMU (Inertial Measurement Unit) measurements. To improve the positioning accuracy during GNSS outage, deep learning has been introduced into the GNSS/INS integrated system in recent years. In this paper, we propose a residual attention network-based confidence (i.e., measurement noise covariance) estimation algorithm for non-holonomic constraint in GNSS/INS integrated navigation system, which adopts a residual attention network to dynamically estimate the noise covariance of the pseudo-observation (i.e., non-holonomic constraint) for optimal Kalman filtering (KF) fusion. To emphasize the more representative features with larger weights for accurate noise covariance estimation, we introduce an attention mechanism to automatically assign proper weights to the learned features according to their contributions. We evaluate our proposed method on three practical road datasets and compare it with other seven methods including the traditional KF, Pure INS, KF with three deep learning networks, K-means, and the Input-Delayed Neural Networks based method. Extensive experimental results demonstrate that our proposed RA-NHC bounds the errors associated with velocities and achieves reasonable accuracy improvement in position and velocity estimation.

Most navigation systems in GNSS-challenged environments rely on GNSS/INS integrated navigation system, with the INS potentially providing reliable positioning during short GNSS outages. However, in the event of a prolonged GNSS signal outage, the performance of the system will be solely dependent on the INS solution, which can lead to significant drift over time. As a result, adding more onboard sensors is crucial to mitigate the limitation the GNSS/INS systems, and thereby increase the robustness of the navigation system. This study proposes a loosely-coupled (LC) integration between the INS, LiDAR simultaneous localization and mapping (SLAM), and visual SLAM using an extended Kalman filter (EKF). The developed integrated navigation system is tested on the residential and highway drive segments of the raw KITTI dataset, which simulates various driving outdoor environments in terms of feature density and driving speed. In both cases, a complete artificial GNSS outage is enforced. The results show that the proposed INS/LiDAR/visual SLAM integrated system drastically outperforms the use of INS only. The proposed integrated navigation system yielded an average reduction in the root-mean-square error (RMSE) of approximately 95%, 87%, and 53%, in the east, north, and up directions, respectively. Finally, the proposed algorithm outperformed considered state-of-the-art LiDAR SLAM algorithms.

No abstract available

The realization of decision-making, trajectory planning, and motion control of intelligent vehicles highly depends on the precise and continuous position information. To provide reliable pose information during GNSS (Global Navigation Satellite Systems)outage, an integrated position strategy based on the GNSS, INS (Inertial Navigation System), DR (dead reckoning) considering nonholonomic constraints (NHC) was proposed in this paper. First, a positioning algorithm of GNSS/INS was established using an Error State Kalman Filer (ESKF). Nonholonomic constraints and vehicle speed were used to correct the navigation error to improve positioning accuracy. Then, the available time of the algorithm during GNSS signal outage was further extended by designing a DR system based on vehicle dynamics. An Extended Kalman Filter (EKF) was used to process the nonlinear system and the information of wheel speed and front wheel angle were integrated into the system. Finally, the fusion positioning algorithm was validated by NI HIL platform. The results showed that, during GNSS outage, the positioning strategy proposed in this paper could reduce the root means square errors (RMSE) of positioning accuracy, compared to the GNSS/INS positioning algorithm, by 78.2% along x-axis and 83.0% along y-axis.