Accurate Navigation Solution Research Articles

Adaptive Cubature Kalman Filter for Inertial/Geomagnetic Integrated Navigation System Based on Long Short-Term Memory Network

Inertial navigation systems experience error accumulation over time, leading to the use of integrated navigation as a classical solution to mitigate inertial drift. This provides a novel approach to navigation and positioning by using the combined advantages of inertial and geomagnetic navigation systems. However, inertial/geomagnetic navigation is affected by significant magnetic interference in practical scenarios, resulting in reduced navigation accuracy. This research introduces a new neural network-assisted integrated inertial–geomagnetic navigation method (IM-NN), and utilizes the adaptive cubature Kalman filter to integrate attitude information from geomagnetism and inertial sensors. A model was created utilizing a Long Short-Term Memory Network (LSTM) to represent the relationship between specific force, angular velocity, and integrated navigation attitude information. The dynamics were estimated based on current and previous Inertial Measurement Unit (IMU) data using IM-NN. This study demonstrated that the method effectively corrected inertial accumulation errors and mitigated geomagnetic disruption, resulting in a more accurate and dependable navigation solution in environments with geomagnetic rejection compared to conventional single inertial navigation methods.

A Comprehensive Review of the GNSS with IoT Applications and Their Use Cases with Special Emphasis on Machine Learning and Deep Learning Models

This paper presents a comprehensive review of the Global Navigation Satellite System (GNSS) with Internet of Things (IoT) applications and their use cases with special emphasis on Machine learning (ML) and Deep Learning (DL) models. Various factors like the availability of a huge amount of GNSS data due to the increasing number of interconnected devices having low-cost data storage and low-power processing technologies - which is majorly due to the evolution of IoT - have accelerated the use of machine learning and deep learning based algorithms in the GNSS community. IoT and GNSS technology can track almost any item possible. Smart cities are being developed with the use of GNSS and IoT. This survey paper primarily reviews several machine learning and deep learning algorithms and solutions applied to various GNSS use cases that are especially helpful in providing accurate and seamless navigation solutions in urban areas. Multipath, signal outages with less satellite visibility, and lost communication links are major challenges that hinder the navigation process in crowded areas like cities and dense forests. The advantages and disadvantages of using machine learning techniques are also highlighted along with their potential applications with GNSS and IoT.

Improving Self-Consistency in Underwater Mapping Through Laser-Based Loop Closure

Accurate, self-consistent bathymetric maps are needed to monitor changes in subsea environments and infrastructure. These maps are increasingly collected by underwater vehicles, and mapping requires an accurate vehicle navigation solution. Commercial off-the-shelf (COTS) navigation solutions for underwater vehicles often rely on external acoustic sensors for localization; however, survey-grade acoustic sensors are expensive to deploy and limit the range of the vehicle. Techniques from the field of simultaneous localization and mapping, particularly loop closures, can improve the quality of the navigation solution over dead reckoning, but are difficult to integrate into COTS navigation systems. This article presents a method to improve the self-consistency of bathymetric maps by smoothly integrating loop-closure measurements into the state estimate produced by a commercial subsea navigation system. Integration is done using a white-noise-on-acceleration motion prior, without access to raw sensor measurements or proprietary models. Improvements in map self-consistency are shown for both simulated and experimental datasets, including a 3-D scan of an underwater shipwreck in Wiarton, ON, Canada.

Artificial Neural Networks for Navigation Systems: A Review of Recent Research

Several machine learning (ML) methodologies are gaining popularity as artificial intelligence (AI) becomes increasingly prevalent. An artificial neural network (ANN) may be used as a “black-box” modeling strategy without the need for a detailed system physical model. It is more reasonable to solely use the input and output data to explain the system’s actions. ANNs have been extensively researched, as artificial intelligence has progressed to enhance navigation performance. In some circumstances, the Global Navigation Satellite System (GNSS) can offer consistent and dependable navigational options. A key advancement in contemporary navigation is the fusion of the GNSS and inertial navigation system (INS). Numerous strategies have been put out recently to increase the accuracy for jamming, GNSS-prohibited environments, the integration of GNSS/INS or other technologies by means of a Kalman filter as well as to solve the signal blockage issue in metropolitan areas. A neural-network-based fusion approach is suggested to address GNSS outages. The overview, inquiry, observation, and performance evaluation of the present integrated navigation systems are the primary objectives of the review. The important findings in ANN research for use in navigation systems are reviewed. Reviews of numerous studies that have been conducted to investigate, simulate, and integrate navigation systems in order to produce accurate and dependable navigation solutions are offered.

Robust estimation‐based multipath detection for vector tracking loop

AbstractMultipath interference in cities has always been one of the main problems leading to abnormal positioning results of a global navigation satellite system. Vector tracking is superior to conventional scalar tracking in the ability of mitigating multipath interference. However, due to the special sharing structure, fault propagation which easily occurs in the vector tracking loop leads to false alarms of normal satellite signals during multipath detection. To solve this problem, a fault‐tolerant algorithm based on robust estimation is applied to suppress fault propagation. Meanwhile, in order to improve the ability of detecting multiple short delayed multipath signals, chi‐square detection is proposed to be used before applying the fault‐tolerant algorithm. By taking advantage of the characteristic that the occurrence of multipath signals will cause significant deviation of code phase errors, the mean value of code phase errors is used as the detection metric. Both simulation test and field experiment are carried out to verify the detection performance. Experimental results show that the proposed algorithm can effectively prevent fault propagation and solve the problem of false positives of normal satellite signals. As a result, not only multipath signals are detected more accurately, but also more accurate navigation solution is obtained.

A Novel Deep Odometry Network for Vehicle Positioning Based on Smartphone

Smartphone with multiple sensors integration has been widely used for navigation. The inertial measurement unit (IMU) embedded in smartphones has been widely used for pedestrian navigation for counting steps. However, it is a challenge to measure the accurate velocity of the vehicle from the smartphone-embedded IMU data with a high noise level. Thus, current vehicle navigation with a smartphone relies substantially on the Global Navigation Satellite System (GNSS), which provides unreliable positions in urban dense areas due to the blockage and the reflection of GNSS signals. In this study, we propose a smartphone-based positioning method to improve vehicle positioning performance continuously in GNSS-degraded areas through the improvement of IMU velocity estimation. A convolutional neural network–gated recurrent unit (CNN-GRU) combined deep learning odometry network, termed DeepOdo, is proposed to estimate the velocity of the vehicle with the IMU and barometer data as the input, rather than the traditional integral of the IMU measurements. Raw sensor data is utilized to boost the robustness. Labels of the DeepOdo are obtained from the integrated GNSS/IMU/barometer solutions in the smartphone which significantly simplifies the dataset collection. In GNSS-denied areas, IMU, barometer, and DeepOdo are integrated to provide accurate navigation solutions for the vehicle. Results of the proposed method show 73.14% and 98.33% improvements in horizontal and vertical directions, respectively, compared with the non-holonomic constraints (NHCs) aided IMU. Finally, the DeepOdo network is deployed in Android smartphones to demonstrate that the proposed solution can work properly on the mobile platform.

Estimating DVL Velocity in Complete Beam Measurement Outage Scenarios

Autonomous underwater vehicles (AUVs) commonly employ a Doppler velocity log (DVL) to achieve an accurate navigation solution. In real-world scenarios, like when operating in complex environments, situations of complete DVL outages may occur, leading to rapid degradation in the navigation solution. To circumvent such situations, this article proposes an approach to estimate the platform’s velocity vector based on past DVL measurements and a motion model, for short time periods. At-sea experiments were conducted using two types of AUVs, each with a different DVL, to collect data for a total time duration of 90 min. This dataset was employed to show the benefits of using the proposed approach.

Solar Flare and Radio Burst Effects on GNSS Signals and the Ionosphere During September 2017

AbstractStrong solar flare events can occur even during the decay phase of the solar cycle. During these events concurrent increases in the X‐ray and Enhanced UV (EUV) fluxes and solar radio bursts (SRBs) can be observed. The SRBs cover a large range of frequencies including the L band, giving rise to signal fades in the GNSS carrier‐to‐noise ratio and fluctuations in its amplitude and phase. The increases in the X‐ray, UV, and EUV fluxes cause increase in the ionospheric D, E, and F region electron densities. The aim of this work is to analyze the effects in the GNSS signal, in the ionosphere and in the magnetic field H component of the X9.3 and X1.3 solar flares that occurred on 06 and 07 September 2017, respectively. Data from a network of six GNSS receivers, two magnetometers, and four Digisondes are used in the analysis. Fades of about 5 and 10 dB were observed in the signals of GNSS L1 and L2/L5 frequencies, respectively. Significant positioning errors, were observed for the strongest X9.3 flare. A sudden increase in Total Electron Content with the rates of 2.5–5.0 TECU/min was observed. An increase in the E layer density gave origin to an increase in the Equatorial Electrojet intensity, whose signatures were observed in the H component of two magnetometers. Another observed effect was the ionospheric D region density increase that caused disruption in the Digisonde signal. As a consequence of the described effects, GNSS receivers may fail to produce accurate navigation solution.

Analysis of Vehicle Location Prediction Errors for Safety Applications in Cooperative-Intelligent Transportation Systems

Cooperative-Intelligent Transportation System (C-ITS) safety applications depend on reliable location information timely exchanged by road users. Due to inter-vehicle communication delays and sampling frequency, there always exists a time gap between the state observation update time and safety decision time. Predicting the vehicle’s locations into a future time epoch common to both host and subject vehicles enables real-time collision detection. Current studies of vehicle positioning performance mostly focus on the accuracy and availability of vehicle navigation solutions at equal observation intervals. Location error propagation over the prediction time intervals and dependence on various factors is not much understood. In this paper, we analyzed how the accuracy of the location prediction degrades depending on prediction intervals and state estimate errors from the measurement updates. We adopted the Kalman Filter method to predict locations with two representative location data sets collected in real road environments. Results from a dual-frequency Global Navigation Satellite System (GNSS)/Real-time Kinematic (RTK) receiver show that the Root Mean Square Error (RMSE) of prediction locations grow from a few centimeters at the state updates to about 50 and 100 cm within the prediction intervals of 1 and 2 seconds, respectively. This implies that GNSS/RTK positioning capability is a prerequisite for C-ITS safety applications. The experimental results from a surveying-grade GNSS/Inertial Navigation System (INS) receiver show that the RMSE can remain within 10 cm for the prediction interval of 2 s. High-rate INS velocity measurements provide significant advantages in efficient control of the error growth of the predicted vehicle locations.

High-Resolution Spectral Estimation for Continuous Wave Jamming Mitigation of GNSS Signals in Autonomous Vehicles

Future autonomous vehicles will rely mainly on global navigation satellite system (GNSS) receivers for positioning services. However, GNSS cannot maintain an accurate, continuous and reliable navigation solution in the presence of jamming. The widespread availability of in-car jammers or personal privacy devices (PPDs) made GNSS receivers an attractive target for signal jamming. Jammers not only jeopardize current positioning and timing services; they can indeed endanger the safety of the evolving intelligent transportation, autonomous road vehicles and critical infrastructure. The disruption of GNSS signal in some applications, especially safety-critical ones can lead to crucial consequences and risks such as loss of time synchronization and potential loss of life, to name a few. Thus, it is essential for future autonomous vehicles and transport service providers to deploy reliable GNSS anti-jamming techniques. This paper introduces a novel anti-jamming technique based on a high-resolution spectral estimation that utilizes fast orthogonal search (FOS) algorithm in which the jamming signal is modeled using a set of candidate functions and then eliminated from the received signal. The performance of the proposed method is assessed using experiments obtained from Spirent_TM GSS6700 simulation system. The jamming signal is either obtained from a real jammer or simulated using interference signal generator that is connected to Spirent_TM system. The results showed that the developed anti-jamming algorithm was able to successfully suppress the continuous wave (CW) interference signal, thus, the performance of the acquisition, tracking and navigation modules within a GPS software receiver were all enhanced.

Loosely Coupled GNSS and IMU Integration for Accurate i-Boat Horizontal Navigation

Global Navigation Satellite System (GNSS) has been widely utilized as a navigation solution for a mobile vehicle, yet stand-alone GNSS is unable to achieve sufficient accuracy in some applications. For example, in aquatic environment, the accuracy position of Unmanned Surface Vehicle (USV) is affected by the wind, current, and waves dynamics. In this case, the integration of GNSS and Inertial Measurement Unit (IMU) is an approach that can be used to support USV localization to achieve an accurate navigation solution. This study integrates GNSS and IMU using Extended Kalman Filter (EKF) to process loosely coupled integration. The integration results show that the estimated x-position is 0.3058 m accurately and the y-position has an accuracy of 0.2780 m. Then, the loosely coupled integration results of EKF were compared with Unscented Kalman Filter (UKF) simulation in the previous studies. The integration of GNSS and IMU using EKF produces a higher RMSE value of 2D position and attitude angle than UKF Scenario I. However, due to the smoothing process, EKF can provide a visually smoother trajectory than UKF, although it has a significant difference from the observed trajectory. On the other hand, the linear velocity estimated by EKF shows better stability compared to UKF in both Scenario I and II.

A novel hybrid observation prediction methodology for bridging GNSS outages in INS/GNSS systems

AbstractThe integration of the inertial navigation system (INS) and global navigation satellite system (GNSS) is suited for localisation and navigation applications, such as aircrafts, land vehicles and ships. The primary challenge is for navigation system to achieve accurate and reliable navigation solution during GNSS outages. This paper presents an observation prediction methodology for INS/GNSS bridging GNSS outages, which combines partial least squares regression (PLSR) and Gaussian process regression (GPR) to model the INS/GNSS observations and enable a Kalman filter to estimate INS errors. The performance of proposed PLSR/GPR prediction methodology was validated through four GNSS outages taken on flight experiment data, including diverse manoeuvre conditions. The experiment results demonstrate that remarkable performance enhancements are achieved through applying the proposed PLSR/GPR prediction methodology into INS/GNSS integration.

Deep Learning-Enabled Fusion to Bridge GPS Outages for INS/GPS Integrated Navigation

The low cost inertial navigation system (INS) suffers from bias and measurement noise, which would result in poor navigation accuracy during global positioning system (GPS) outages. Aiming to bridge GPS outages duration and enhance the navigation performance, a deep learning network architecture named GPS/INS neural network (GI-NN) is proposed in this paper to assist the INS. The GI-NN combines a convolutional neural network and a gated recurrent unit neural network to extract spatial features from inertial measurement unit (IMU) signals and track their temporal characteristics. The relationship among the attitude, specific force, angular rate and the GPS position increment is modelled, while the current and previous IMU data are used to estimate the dynamics of the vehicle by GI-NN. Numerical simulations, real field tests and public data tests are performed to evaluate the effectiveness of the proposed algorithm. Compared with the traditional machine learning algorithms, the results illustrate that the proposed method can provide more accurate and reliable navigation solutions in GPS denied environments.

Error modeling of Doppler velocity logs using a point-based scattering model

As Doppler Velocity Log (DVL) systems become smaller, cheaper, and increasingly capable, they are becoming standard options on even low-end undersea vehicles. DVLs are the principal sensor that provide ground-referenced velocity measurements to compensate for the bias and drift errors found in inertial navigation systems. Therefore, DVLs fill an essential role in achieving an accurate navigation solution for unmanned undersea vehicles. Although there are many modeling and simulation techniques for comparing a fused-sensor inertial navigation solution to earth-reference, there is a sparsity in the literature for models and simulation environments that are suited for estimating the performance of a standalone DVL system. A practical model must incorporate sufficient environmental fidelity so as to match with empirical results, while still remaining computationally efficient. The point-based scattering model described by Brown et al. [JASA Elect. Lett. i(2017)] may be a useful tool for modeling DVL performance. The implemented model incorporates seafloor roughness, scatterer density, textures, and is well-suited for integration into Monte Carlo simulations. This presentation will compare the DVL performance predicted by this point-based scattering model to several other error models and discuss the utility for predicting performance in natural marine environments.

Magnetic Navigation on an F-16 Aircraft Using Online Calibration

Magnetic anomaly navigation is gaining popularity as an alternative-navigation system that addresses the challenges of GPS denial. Magnetic anomaly navigation has recently been flight test proven on an F-16 aircraft. The corrupting magnetic environment on this operational platform is 2–3 orders of magnitude larger than previous flight-tests on geo-survey aircraft, while also displaying stochastic drift. The difficult magnetic environment of the platform necessitated a combination of batch and online calibration to obtain accurate navigation solutions. Superiority of the new method is shown in comparison to prior published methods. Real navigation results on the F-16 are shown to obtain accuracies 50% better than these competing methods, with low-altitude results obtaining 59-m distance root-mean-squared errors on 1.5 h flights versus 111 m using batch-only calibrations.

The Autonomous Platforms Inertial Dataset

One of the critical tasks required for fully autonomous functionality is the ability to achieve an accurate navigation solution; that is, to determine the platform position, velocity, and orientation. Various sensors, depending on the vehicle environment (air, sea, or land), are employed to achieve this goal. In parallel to the development of novel navigation and sensor fusion algorithms, machine-learning based algorithms are penetrating into the navigation and sensor fusion fields. An excellent example for this trend is pedestrian dead reckoning, used for indoor navigation, where both classical and machine learning approaches are used to improve the navigation accuracy. To facilitate machine learning algorithms’ derivation and validation for autonomous platforms, a huge quantity of recorded sensor data is needed. Unfortunately, in many situations, such datasets are not easy to collect or are not publicly available. To advance the development of accurate autonomous navigation, this paper presents the autonomous platforms inertial dataset. It contains inertial sensor raw data and corresponding ground truth trajectories. The dataset was collected using a variety of platforms including a quadrotor, two autonomous underwater vehicles, a land vehicle, a remote controlled electric car, and a boat. A total of 805.5 minutes of recordings were made using different types of inertial sensors, global navigation satellite system receivers, and Doppler velocity logs. After describing the sensors that were employed for the recordings, a detailed description of the conducted experiments is provided. The autonomous platform inertial dataset is available at: <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/ansfl/Navigation-Data-Project/</uri> .

Adaptive Step Size Learning With Applications to Velocity Aided Inertial Navigation System

Autonomous underwater vehicles (AUV) are commonly used in many underwater applications. Recently, the usage of multi-rotor unmanned autonomous vehicles (UAV) for marine applications is receiving more attention in the literature. Usually, both platforms employ an inertial navigation system (INS), and aiding sensors for an accurate navigation solution. In AUV navigation, Doppler velocity log (DVL) is mainly used to aid the INS, while for UAVs, it is common to use global navigation satellite systems (GNSS) receivers. The fusion between the aiding sensor and the INS requires a definition of step size parameter in the estimation process. It is responsible for the solution frequency update and, eventually, its accuracy. The choice of the step size poses a tradeoff between computational load and navigation performance. Generally, the aiding sensors update frequency is considered much slower compared to the INS operating frequency (hundreds Hertz). Such high rate is unnecessary for most platforms, specifically for low dynamics AUVs. In this work, a supervised machine learning based adaptive tuning scheme to select the proper INS step size is proposed. To that end, a velocity error bound is defined, allowing the INS/DVL or the INS/GNSS to act in a sub-optimal working conditions, and yet minimize the computational load. Results from simulations and field experiment show the benefits of using the proposed approach. In addition, the proposed framework can be applied to any other fusion scenarios between any type of sensors or platforms.

Smartphone Location Recognition with Unknown Modes in Deep Feature Space.

Smartphone location recognition aims to identify the location of a smartphone on a user in specific actions such as talking or texting. This task is critical for accurate indoor navigation using pedestrian dead reckoning. Usually, for that task, a supervised network is trained on a set of defined user modes (smartphone locations), available during the training process. In such situations, when the user encounters an unknown mode, the classifier will be forced to identify it as one of the original modes it was trained on. Such classification errors will degrade the navigation solution accuracy. A solution to detect unknown modes is based on a probability threshold of existing modes, yet fails to work with the problem setup. Therefore, to identify unknown modes, two end-to-end ML-based approaches are derived utilizing only the smartphone’s accelerometers measurements. Results using six different datasets shows the ability of the proposed approaches to classify unknown smartphone locations with an accuracy of 93.12%. The proposed approaches can be easily applied to any other classification problems containing unknown modes.

A gradient descend method‐based none‐line‐of‐sight‐induced code delay searching in global navigation satellite system

In urban areas with narrow streets and tall buildings, none-line-of-sight (NLOS) or multipath (MP) signals severely attenuate the positioning accuracy of the global navigation satellite system (GNSS). vector tracking loop (VT) has been employed in NLOS/MP signal detection and correction; its feasibility and superior performance have been assessed and demonstrated in previous research studies. In VT, the navigation solutions are fed back to calculate the signal tacking parameters and complete the carrier and code tracking. The NLOS/MP reception induces code delay to the code tracking. The generated local signal replicas are mixed with the received signal; the code and carrier discriminators’ outputs are employed as the measurements to estimate the navigation solutions in the VT navigation filter. In order to extract the code delay induced by the NLOS or MP, multiple correlators (MCs) are usually utilised to search for the code delay. However, more correlators will bring much heavier computation load and a real position is necessary for calculating the signal tracking parameters. The strap-down inertial navigation system (SINS) can generate short-term accurate navigation solutions. In this work, a gradient descend (GD) method is designed for extracting the NLOS/MP-induced delay in the correlators’ measurements level. The VT/SINS ultra-tightly coupled navigation system (VT-UTC) is developed to obtain mutual aiding between these individual systems. In VT-UTC, the corrected SINS navigation solutions are employed for calculating the signal tracking parameters, and reliable navigation solutions from the SINS can help to extract the code delays induced by the NLOS. Two field tests with global positioning system L1 signal are carried out for assessing the performance of the GD method in the VT-UTC framework. Comparisons between the MC and GD method show that the correlators’ computation reduces a lot since much fewer correlators are calculated in the code delay searching. Also, reliable navigation solutions from the SINS could help to calculate the signal tracking parameter while in-view GNSS satellites are limited.

Real-Time Navigation for Drogue-Type Autonomous Aerial Refueling Using Vision-Based Deep Learning Detection

This article develops a deep learning object detector to provide accurate six-degree-of-freedom (DoF) information of the drogue relative to a monocular camera onboard a flying unmanned aerial vehicle. An object detector helps to provide the needed information for an autonomous vehicle to dock and refuel without the need for human intervention. This object detector can detect eight different beacons by training on 8746 images of a mock drogue. Once these beacons were detected, a nonlinear least squares algorithm that uses the collinearity equations as a system model takes the beacon's location on the captured image to provide an accurate six-DoF navigation solution. These navigation solutions from the object detector were evaluated on multiple metrics and then compared to navigation solutions provided by a VICON motion tracking system. Finally, Monte Carlo analysis, using the collinearity equations as a system model, evaluates an object detector's performance with various noise levels.