Local Navigation Research Articles

Gravity Predictions in Data-Missing Areas Using Machine Learning Methods

Gravity data, comprising a key foundational dataset, are crucial for various research, including land subsidence monitoring, geological exploration, and navigational positioning. However, the collection of gravity data in specific regions is difficult because of environmental, technical, and economic constraints, resulting in a non-uniform distribution of the observational data. Traditionally, interpolation methods such as Kriging have been widely used to deal with data gaps; however, their predictive accuracy in regions with sparse data still needs improvement. In recent years, the rapid development of artificial intelligence has opened up a new opportunity for data prediction. In this study, utilizing the EGM2008 satellite gravity model, we conducted a comprehensive analysis of three machine learning algorithms—random forest, support vector machine, and recurrent neural network—and compared their performances against the traditional Kriging interpolation method. The results indicate that machine learning methods exhibit a marked advantage in gravity data prediction, significantly enhancing the predictive accuracy.

Differential Positioning with Bluetooth Low Energy (BLE) Beacons for UAS Indoor Operations: Analysis and Results

Localization of unmanned aircraft systems (UASs) in indoor scenarios and GNSS-denied environments is a difficult problem, particularly in dynamic scenarios where traditional on-board equipment (such as LiDAR, radar, sonar, camera) may fail. In the framework of autonomous UAS missions, precise feedback on real-time aircraft position is very important, and several technologies alternative to GNSS-based approaches for UAS positioning in indoor navigation have been recently explored. In this paper, we propose a low-cost IPS for UAVs, based on Bluetooth low energy (BLE) beacons, which exploits the RSSI (received signal strength indicator) for distance estimation and positioning. Distance information from measured RSSI values can be degraded by multipath, reflection, and fading that cause unpredictable variability of the RSSI and may lead to poor-quality measurements. To enhance the accuracy of the position estimation, this work applies a differential distance correction (DDC) technique, similar to differential GNSS (DGNSS) and real-time kinematic (RTK) positioning. The method uses differential information from a reference station positioned at known coordinates to correct the position of the rover station. A mathematical model was established to analyze the relation between the RSSI and the distance from Bluetooth devices (Eddystone BLE beacons) placed in the indoor operation field. The master reference station was a Raspberry Pi 4 model B, and the rover (unknown target) was an Arduino Nano 33 BLE microcontroller, which was mounted on-board a UAV. Position estimation was achieved by trilateration, and the extended Kalman filter (EKF) was applied, considering the nonlinear propriety of beacon signals to correct data from noise, drift, and bias errors. Experimental results and system performance analysis show the feasibility of this methodology, as well as the reduction of position uncertainty obtained by the DCC technique.

Virtual Crowds Rheology: Evaluating the Effect of Character Representation on User Locomotion in Crowds.

Crowd data is a crucial element in the modeling of collective behaviors, and opens the way to simulation for their study or prediction. Given the difficulty of acquiring such data, virtual reality is useful for simplifying experimental processes and opening up new experimental opportunities. This comes at the cost of the need to assess the biases introduced by the use of this technology. Our paper is part of this effort, and investigates the effect of the graphical representation of a crowd on the behavior of a user immersed within. More specifically, we inspect the virtual navigation through virtual crowds, in terms of travel speeds and local navigation choices as a function of the visual representation of the virtual agents that make up the crowd (simple geometric model, anthropomorphic model or realistic model). Through an experiment in which we ask a user to navigate virtual crowds of varying densities, we show that the effect of the visual representation is limited, but that an anthropomorphic representation offers the best trade-off between computational complexity and ecological validity, even though a more realistic representation can be preferred when user behaviour is studied in more details. Our work leads to clear recommendations on the design of immersive simulations for the study of crowd behavior.

An Automatic Mapping Method of Navigation Map for Outdoor Road Scenes

Abstract. In the process of autonomous navigation of outdoor mobile robots, four modules are involved: perception, localization, planning, and controlling. The perception module utilizes sensors such as cameras and radars based on various principles to analyze the robot's surroundings in real-time. The localization module uses GPS (Global Positioning System), IMU (Inertial Measurement Unit), and prior maps for real-time positioning analysis. The planning module plans optimal path based on the outputs of the first two modules, and the controlling module directs the robot's chassis to move along the planned optimal path. For the localization module, the accuracy of GPS positioning results heavily depends on weather conditions and GPS signal receptions. Even if the positioning results of imu are integrated, the positioning accuracy still cannot meet the needs of robot navigation. Therefore, using prior maps for repositioning can compensate for this accuracy deficiency. The planning module also requires path planning based on prior maps. If the a priori map storage is large, it will lead to difficulties in usage, maintenance, and updates. Therefore, it is crucial to research lightweight navigation map mapping methods. In this paper, an automatically mapping method of lightweight navigation maps is proposed, combining cameras and LiDAR (Light Detection and Ranging), including semantic informations necessary for outdoor navigation positioning, such as pole-like objects and traffic signs for robot longitudinal positioning, and lane line elements for robot lateral positioning. This method automatic generates robot navigation maps in Lanelet2 format, providing support for subsequent positioning and path planning modules.

GNSS/IMU integrated navigation heading angle enhancement algorithm based on dual-antenna TDCP

In the integrated navigation system of Global Navigation Satellite System (GNSS) and Inertial Measurement Unit (IMU), attitude estimation, especially accurate estimation of heading angle, is particularly important for real-time monitoring of vehicle driving status. However, since IMU is divergent in the altitude channel, its error will gradually accumulate if it is not accurately constrained. Therefore, the estimation accuracy of heading angle is insufficient in vehicle-mounted applications where the heading angle changes frequently. In order to solve the problem of poor navigation attitude estimation accuracy in the loose combination of traditional GNSS and IMU, this paper proposes a GNSS/IMU integrated navigation heading angle enhancement algorithm based on dual-antenna epoch carrier phase difference (TDCP). This method solves the vehicle heading angle through dual-antenna TDCP to increase the input dimension of the integrated navigation filter fusion observation value, and uses Hatch filtering and anti-error adaptive filtering to improve the observation domain pseudorange accuracy and GNSS/IMU integrated navigation positioning and attitude determination performance respectively. Experimental results show that compared with the traditional GNSS/IMU integrated navigation method, the proposed algorithm improves the positioning and speed measurement accuracy in the three-dimensional direction by and respectively 22.12%, 41.27%and the vehicle heading angle accuracy is improved 46.29%.

Hybrid Mobile Robot Path Planning Using Safe JBS-A*B Algorithm and Improved DWA Based on Monocular Camera

This paper addresses the formidable challenge of enabling autonomous navigation in Mobile Robots (MRs), focusing on the development of advanced path planning strategies. Despite their pivotal role in diverse applications, they face challenges in dynamic settings due to limitation in existing Global Path Planning (GPP) and Local Path Planning (LPP) techniques. In response to this, we propose an innovative hybrid path planning approach that enhances the A* algorithm with a risk-aware heuristic function and integrates the Jump Point Search (JPS) technique for route optimization. Additionally, B-spline smoothing is employed for perceptually global trajectory refinement. Our approach also includes an innovative improvement to the Dynamic Window Approach (DWA) to align with the proposed enhanced A* algorithm for effective local navigation. Acknowledging the importance of high-quality input in path planning, we present substantial improvements to the IRDC-Net, a monocular-image semantic-segmentation model that we studied previously. Novel improvements include the integration of quantization and the Adam optimizer, along with the implementation of the Balanced Cross-Entropy loss function. These enhancements not only elevate the output quality of IRDC-Net but also reduce the model’s training parameters. The experimental results demonstrate the performance and viability of the proposed algorithm. Ultimately, the hybrid MR’s path planning algorithm exhibits proficiency across various tasks, particularly in addressing the challenge of evading moving obstacles to ensure the robot’s safety while adhering to the global path.

An optimized BP neural network for modeling zenith tropospheric delay in the Chinese mainland using coupled particle swarm and genetic algorithm

ABSTRACT Tropospheric delay influences high-precision navigation positioning and precipitable water vapor retrieval with the Global Navigation Satellite System (GNSS). Existing Zenith Tropospheric Delay (ZTD) models often struggle to accurately capture the non-linear variations in tropospheric delay. Therefore, this study employs the coupled Particle Swarm Optimization (PSO) algorithm with the Genetic Algorithm Back Propagation (GABP) neural network, combined with ERA5 reanalysis meteorological data, to develop an optimized model (PSO-GABP) for ZTD in the Chinese mainland. Nevertheless, ZTD data at the target point are obtained through four different methods: the integration method, model method, and GPT3 models at varying resolutions (EZTD_P, EZTD_S, GPT3_1, and GPT3_5). The analysis reveals the following: (1) The Root Mean Square (RMS) errors of the ZTD values obtained through these different methods are 1.86 cm, 3.42 cm, 3.99 cm, and 4.09 cm, respectively, when verified against GNSS_ZTD data from 2016. The optimized model yields ZTD values with the RMS error of 0.98 cm, 1.96 cm, 2.34 cm, and 2.36 cm, representing improvements of 47.3%, 42.7%, 41.4%, and 42.3% compared to the pre-optimization results. These improvements are significant; (2) The predictive capability of the constructed ZTD model is evaluated using GNSS_ZTD data from 2019 as a reference. The PSO_EZTD_P model demonstrates excellent accuracy and practicality in the Chinese mainland. As a result, the tropospheric delay optimization model based on the PSO-GABP neural network can provide valuable references for real-time GNSS navigation positioning and precipitable water vapor detection in the Chinese mainland.

Design and experiment of Beidou satellite navigation railway tunnel coverage enhancement system

Abstract In areas of satellite navigation signals being obstructed, coveraging the interior of the tunnel with Satellite navigation signals based on navigation signals real-time regeneration technology is an important way to achieve the applications of satellite navigation in railway mobile equipment positioning and auxiliary protection for operators. We analyzed the application requirements on navigation positioning and time synchronization, and technical requirements on universality and electromagnetic compatibility, etc. The article designed the composition and logical architecture of the Beidou satellite navigation railway tunnel coverage enhancement system, proposed the design of system functions and performance parameters, and verified the system’s functionality and performance through static mode testing and dynamic mode testing. The design and implementation of the Beidou satellite navigation railway tunnel coverage enhancement system have important practical value for the application in mobile equipment positioning and auxiliary protection for operators in railway tunnel.

Global integrated navigation position correction algorithm and virtual polar region technology based on normal vector

To achieve the inherent uniformity of all-earth navigation for autonomous underwater vehicles (AUV), a global integrated navigation position correction algorithm based on the normal vector (n-vector) is proposed. First, a four-element vector comprising the non-singular n-vector and height represents the carrier’s position in the Earth-centered Earth-fixed (ECEF) frame. The integrated navigation systems are designed with the strapdown inertial navigation system (SINS), Doppler velocity log (DVL), and other equipment. Secondly, the reverse navigation algorithm in the ECEF mechanization is derived, and the results of forward and reverse navigation are fused to correct the AUV’s underwater position. Additionally, a virtual polar region technology based on the ECEF attitude, velocity, and height invariant method (E-AVHIM) is proposed to convert the actual test data obtained at low and middle latitudes into high latitudes for more convincing polar region algorithm verification. Simulations and lake trial demonstrated the excellence and efficiency of the proposed algorithm.

Risk Assessment of Community-Scale High-Temperature and Rainstorm Waterlogging Disasters: A Case Study of the Dongsi Community in Beijing

With the advancement of urbanization and acceleration of global warming, extreme weather and climate events are becoming increasingly frequent and severe, and climate risk continues to rise. Each community is irreplaceable and important in coping with extreme climate risk and improving urban resilience. In this study, the Dongsi Community in the functional core area of Beijing was explored, and the risk assessment of high temperatures and rainstorm waterlogging was implemented at the community scale. Local navigation observations were integrated into a theoretical framework for traditional disaster risk assessment. The risk assessment indicator system for community-scale high-temperature and rainstorm waterlogging disasters was established and improved from a microscopic perspective (a total of 22 indicators were selected from the three dimensions of hazard, exposure, and vulnerability). Geographic Information Systems (GIS) technology was used to integrate geographic information, meteorological, planning, municipal, socioeconomic and other multisource information layers, thus enabling more detailed spatial distribution characteristics of the hazard, exposure, vulnerability, and risk levels of community-scale high temperatures and rainstorm waterlogging to be obtained. The results revealed that the high-risk area and slightly high-risk area of high-temperature disasters accounted for 13.5% and 15.1%, respectively. The high-risk area and slightly high-risk area of rainstorm waterlogging disasters accounted for 9.8% and 31.6%, respectively. The high-risk areas common to high temperatures and waterlogging accounted for 3.9%. In general, the risk of high-temperature and rainstorm waterlogging disasters at the community scale showed obvious spatial imbalances; that is, the risk in the area around the middle section of Dongsi Santiao was the lowest, while a degree of high temperatures or rainstorm waterlogging was found in other areas. In particular, the risk of high-temperature and rainstorm waterlogging disasters along Dongsi North Street, the surrounding areas of Dongsi Liutiao, and some areas along the Dongsi Jiutiao route was relatively high. These spatial differences were affected to a greater extent by land cover (buildings, vegetation, etc.) and population density within the community. This study is a useful exploration of climate risk research for resilient community construction, and provides scientific support for the planning of climate-adaptive communities, as well as the proposal of overall adaptation goals, action frameworks, and specific planning strategies at the community level.

Impact of proton radiation and annealing of CMOS image sensors on star sensor performance

Star sensors play a crucial role as high-precision optical attitude navigation devices in satellite attitude control systems. The CMOS image sensor is an important component of the imaging system of the star sensor and experiences performance degradation due to the total ionizing dose effect and displacement damage effect in the radiation environment of its long-term operational workspace. As a result, the detection capability and attitude positioning accuracy of the star sensor gradually deteriorate. The performance of CMOS image sensors can be partially restored after annealing but the impact on the performance of star sensors is unclear. This study conducted 100 MeV proton irradiation experiments with different fluences on CMOS image sensors and performed room temperature and high temperature annealing treatments. By testing and analyzing the performance of star sensors equipped with irradiated and different annealing treatments on CMOS image sensors, the impact mechanism of CMOS image sensor radiation damage and annealing recovery on the performance variation of star sensors was obtained. This study provides theoretical support for reliability of long-term in-orbit star sensors.

An Integrated Navigation Method Aided by Position Correction Model and Velocity Model for AUVs.

When autonomous underwater vehicles (AUVs) perform underwater tasks, the absence of GPS position assistance can lead to a decrease in the accuracy of traditional navigation systems, such as the extended Kalman filter (EKF), due to the accumulation of errors. To enhance the navigation accuracy of AUVs in the absence of position assistance, this paper proposes an innovative navigation method that integrates a position correction model and a velocity model. Specifically, a velocity model is developed using a dynamic model and the Optimal Pruning Extreme Learning Machine (OP-ELM) method. This velocity model is trained online to provide velocity outputs during the intervals when the Doppler Velocity Log (DVL) is not updating, ensuring more consistent and reliable velocity estimation. Additionally, a position correction model (PCM) is constructed, based on a hybrid gated recurrent neural network (HGRNN). This model is specifically designed to correct the AUV's navigation position when GPS data are unavailable underwater. The HGRNN utilizes historical navigation data and patterns learned during training to predict and adjust the AUV's estimated position, thereby reducing the drift caused by the lack of real-time position updates. Experimental results demonstrate that the proposed VM-PCM-EKF algorithm can significantly improve the positioning accuracy of the navigation system, with a maximum accuracy improvement of 87.2% compared to conventional EKF algorithms. This method not only improves the reliability and accuracy of AUV missions but also opens up new possibilities for more complex and extended underwater operations.

Effects of simulated gas of thermobaric bomb charge explosion on Tau protein phosphorylation and cognitive function in rats

Objective: To explore the effect of simulated gas of thermobaric bomb charge explosion on cognitive function and the related mechanism of damage. Methods: In January 2022, thirty-two SPF rats were selected and randomly divided into control group, exposed group 1, 2 and 3 (the exposure time of the simulated gas of the explosion of the thermobaric bomb charge was 5 min, 10 min and 15 min, respectively) according to random number table method, with 8 rats in each group. The simulated gas of the explosion of the thermobaric bomb charge were CO 0.15%, CO(2) 3%, NO 0.1%, O(2) 15%, and the rest were N(2). After 30 days of exposure, water maze was used to detect the learning and memory function of rats. Golgi staining was used to observe the number distribution and morphological structure of hippocampal neurons in rats. Western blot was used to detect the expression of Tau-5, pSer262, pSer396, pThr181 and pThr231 proteins in rats. Repeated measure ANOVA was used to compare the design data of repeated measure, one-way ANOVA was used for multi-group mean comparison, and LSD method was used for pound-wise comparison. Results: There were significant differences in the results of repeated measurement ANOVA of the water maze localization navigation test (F=80.98, P<0.001), and there was an interaction between the group and the training days (F=2.16, P=0.022). There were significant differences in escape latency of rats at the 2nd, 3rd, 4th and 5th days among all groups (P<0.05). The results of spatial exploration showed that the frequency of rats crossing the platform was significantly different among all groups (F=4.49, P=0.011). The frequency of rats crossing the platform in exposed group 2 and exposed group 3 was lower than that in control group, and the frequency of rats crossing the platform in exposed group 3 was lower than that in exposed group 1 (P<0.05). With the increase of exposure time, the number of hippocampal neurons decreased, and the dendrite spine density of neurons in CA1 region decreased (P<0.05). Compared with the control group, there was no significant difference in the relative expression level of Tau-5 protein in all exposed groups (P>0.05), but the expression level of pSer262 protein was significantly increased (P<0.05). Compared with the control group, the protein expressions of pSer396, pThr181 and pThr231 in exposed group 2 and exposed group 3 were significantly increased (P<0.05) . Conclusion: The simulated gas of the explosion of the thermobaric bomb charge may contribute to the development of cognitive dysfunction by damaging hippocampal neurons with aberrant phosphorylation of Tau proteins.

Application of Atmospheric Augmentation for PPP-RTK with Instantaneous Ambiguity Resolution in Kinematic Vehicle Positioning

The long convergence time and non-robust positioning accuracy are the main factors limiting the application of precision single-point positioning (PPP) in kinematic vehicle navigation. Therefore, a dual/triple-frequency multi-constellation PPP-RTK method with atmospheric augmentation is proposed to achieve cm-level reliable kinematic positioning. The performance was assessed using a set of static station and kinematic vehicle positioning experiments conducted in Wuhan. In the static experiments, instantaneous convergence within 1 s and centimeter-level positioning accuracy were achieved for PPP-RTK using dual-frequency observation. For the kinematic experiments, instantaneous convergence was also achieved for dual-frequency PPP-RTK in open areas, with RMS of 2.6 cm, 2.6 cm, and 7.5 cm in the north, east, and up directions, respectively, with accuracy similar to short-baseline real-time kinematic positioning (RTK). Horizontal positioning errors of less than 0.1 m and 3D positional errors of less than 0.2 m were 99.54% and 98.46%, respectively. Additionally, after the outage of GNSS and during satellite reduction in obstructed environments, faster reconvergence and greater accuracy stability were realized compared with PPP without atmospheric enhancement. Triple-frequency PPP-RTK was able to further enhance the robustness and accuracy of positioning, with RMS of 2.2 cm, 2.0 cm, and 7.3 cm, respectively. In summary, a performance similar to RTK was achieved based on dual-frequency PPP-RTK, demonstrating that PPP-RTK has the potential for lane-level navigation.

Combining spatial clustering and tour planning for efficient full area exploration

AbstractAutonomous exploration in unknown environments has become a critical capability of mobile robots. Many methods often suffer from problems such as exploration goal selection based solely on information gain and inefficient tour optimization. Recent reinforcement learning-based methods do not consider full area coverage and the performance of transferring learned policy to new environments cannot be guaranteed. To address these issues, a dual-stage exploration method has been proposed, which combines spatial clustering of possible exploration goals and Traveling Salesman Problem (TSP) based tour planning on both local and global scales, aiming for efficient full-area exploration in highly convoluted environments. Our method involves two stages: exploration and relocation. During the exploration stage, we introduce to generate local navigation goal candidates straight from clusters of all possible local exploration goals. The local navigation goal is determined through tour planning, utilizing the TSP framework. Moreover, during the relocation stage, we suggest clustering all possible global exploration goals and applying TSP-based tour planning to efficiently direct the robot toward previously detected but yet-to-be-explored areas. The proposed method is validated in various challenging simulated and real-world environments. Experimental results demonstrate its effectiveness and efficiency. Videos and code are available at https://github.com/JiatongBao/exploration.

Robust Bluetooth AoA Estimation for Indoor Localization Using Particle Filter Fusion

With the growing demand for positioning services, angle-of-arrival (AoA) estimation or direction-finding (DF) has been widely investigated for applications in fifth-generation (5G) technologies. Many existing AoA estimation algorithms only require the measurement of the direction of the incident wave at the transmitter to obtain correct results. However, for most cellular systems, such as Bluetooth indoor positioning systems, due to multipath and non-line-of-sight (NLOS) propagation, indoor positioning accuracy is severely affected. In this paper, a comprehensive algorithm that combines radio measurements from Bluetooth AoA local navigation systems with indoor position estimates is investigated, which is obtained using particle filtering. This algorithm allows us to explore new optimized methods to reduce estimation errors in indoor positioning. First, particle filtering is used to predict the rough position of a moving target. Then, an algorithm with robust beam weighting is used to estimate the AoA of the multipath components. Based on this, a system of pseudo-linear equations for target positioning based on the probabilistic framework of PF and AoA measurement is derived. Theoretical analysis and simulation results show that the algorithm can improve the positioning accuracy by approximately 25.7% on average.

Deep-learning-assisted triboelectric whisker for near field perception and online state estimation of underwater vehicle

Agile near field perception remains a challenge for underwater vehicles, which could significantly enhance their capability of online state estimation. Harbor seals have evolved a whisker array that can accurately measure and identify environmental information in their surroundings. Inspired by the "smart" whiskers of harbor seals, the study has designed a deep learning-assisted bionic underwater triboelectric whisker sensor (UTWS) to passively perceive diverse hydrodynamic flow fields, including omni-directional steady flow and wakes induced by bluff body upstream. The device mainly comprised an elliptical whisker shaft with a high-aspect-ratio of 0.403, four flexible triboelectric sensing units mimicking the nerve in the follicular sinus complex, and a flexible corrugated joint imitating the surface skin of marine organisms' cheeks. The UTWS demonstrated impressive advantages of rapid response times of 21 ms, high sensitivity of 1.16 V/m.s−1, high signal-to-noise-ratio of 61.66 dB. By implementing deep learning analytics to process the multi-channel signals, the underwater vehicle equipped with the UTWS can accomplish online velocity estimation proficiently, with an approximate root mean square error of approximately 0.093 in the verification case. Thus, this UTWS-based, deep-learning-assisted perception could become a promising tool for integration with underwater vehicles in the local navigation tasks.

Methodology for substantiating the parameters of navigation signals with double meander modulation for local navigation systems based on land pseudo-satellites

Formulation of the problem. The development of local navigation systems based on land pseudo-satellites in order to solve the problem of insufficient noise immunity of global navigation satellite systems determines the relevance of the improvement of the theory of multicriteria synthesis of new types of navigation signals. Purpose. Ensuring high accuracy and continuity of navigation-time definitions with the level of out-of-band radiation reduced to compliance with electromagnetic compatibility requirements and an acceptable decrease in the energy efficiency of transmitters by developing a methodology for substantiating the parameters of navigation signals with double meander modulation for local navigation systems based on land pseudo-satellites. Results. The use of navigation signals with double meander modulation in local navigation systems based on land pseudo-satellites is proposed, and their advantages over currently used signals are shown. A methodology of multi-criteria substantiating of navigation signal parameters has been developed, taking into account spectral, correlation characteristics, as well as the effect of reducing the level of out-of-band radiation of land radio transmitting devices in order to ensure electromagnetic compatibility requirements on the time characteristics of the signal. Practical significance. The obtained results can be used by specialists in the field of local and global radio navigation systems when considering the introduction of new types of navigation signals that ensure high quality indicators of tracking their parameters, as well as the application of new and existing navigation signals in local navigation systems based on land pseudo-satellites.

Formation of CBOC signals with a reduced level of out-of-band radiation

Formulation of the problem. The article considers the issues of choosing low-pass filters with finite and infinite pulse characteristics used to generate CBOC signals with phase manipulation with a reduced level of out-of-band radiation. Purpose. The influence of the filter frequency band on the distortion of CBOC signals in the frequency and time domain is estimated by mathematical modeling. Results. The following filter parameters, peak factor and ACPR (Adjacent Channel Power Ratio) were studied and calculated. Practical significance. The results obtained can be used by developers of local navigation systems.

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.