LiDAR is widely used in Simultaneous Localization and Mapping (SLAM) and autonomous driving. The LiDAR odometry is of great importance in multi-sensor fusion. However, in some unstructured environments, the point cloud registration cannot constrain the poses of the LiDAR due to its sparse geometric features, which leads to the degeneracy of multi-sensor fusion accuracy. To address this problem, we propose a novel real-time approach to sense and compensate for the degeneracy of LiDAR. Firstly, this paper introduces the degeneracy factor with clear meaning, which can measure the degeneracy of LiDAR. Then, the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) clustering method adaptively perceives the degeneracy with better environmental generalization. Finally, the degeneracy perception results are utilized to fuse LiDAR and IMU, thus effectively resisting degeneracy effects. Experiments on our dataset show the method’s high accuracy and robustness and validate our algorithm’s adaptability to different environments and LiDAR scanning modalities.

Fingerprinting has become a mainstream method for indoor positioning. With the popularization of smart devices, the construction of indoor positioning databases is no longer limited to fingerprints collected in a single carrier; instead, it includes those collected by various platforms, such as IoT devices, smartphones, and robots. To adapt to this new trend, it is key to answer the question: how do fuse fingerprints collected by using various carriers to generate a database for localization? This paper has three contributions: 1) It reveals the necessity of involving the location uncertainty of localization feature measurements. This topic has yet to be considered in the existing research works because they only have fingerprints collected from a single platform. 2) Considering such location uncertainty, this paper proposes an improved database training and location estimation method. 3) This paper presents an approach combining sparse professional fingerprints and dense consumer fingerprints to create a database that is key to the ubiquitous positioning of smart devices. In field tests, the proposed method improved positioning accuracy by over 35% and brought other benefits. The source code of this research is available at https://github.com/zhenqizhen/Location-Uncertainty-FP.git.

As a commonly used indoor Internet of Things (IoT) positioning method, fingerprinting is frequently carried out by fusing inertial and magnetic data. However, magnetic signals may exhibit high similarity in extensive indoor environments, leading to increased mismatching in magnetic fingerprinting positioning results. It negatively impacts the overall accuracy of positioning outcomes, leading to inaccuracies. To address this challenge, this article presents a multilevel error elimination approach that refines magnetic positioning outcomes from coarse to fine-grained adjustments. It marks the inaugural research on error detection and elimination specifically focused on magnetic field positioning. The method employs velocity information, sliding median filtering, and neighborhood filtering to rapidly, accurately, and effectively detect and eliminate the errors of magnetic positioning results. This methodology primarily employs velocity information to rapidly and comprehensively eliminate coarse errors. Subsequently, sliding median filtering addresses scenarios where velocity-based error correction is unreliable, effectively facilitating the intermediate removal of errors in magnetic field positioning outcomes. Ultimately, neighborhood filtering addresses unreliable situations in the above processes, enabling small-scale and detailed elimination of errors in magnetic field positioning results. Within a 100 m $\times $ 60 m indoor parking lot, the proposed approaches retained 51% to 80% of magnetic positioning results and enhanced the accuracy of magnetic positioning by over 80%.

Multi-sensor integrated navigation, combining Global Navigation Satellite System (GNSS), Inertial Navigation System (INS), and Light Detection and Ranging (LiDAR), is at the forefront of high-precision positioning technology. However, existing integration methods rely on raw point cloud data, which cannot be obtained in some projects due to geospatial data privacy concerns. For this problem, this work introduces the Trajectory-Layer-Enhanced GNSS/INS/LiDAR Integrated Navigation System (TL-GILNS), which operates without raw point cloud data. This novel approach faces two primary challenges: 1) the difficulty in resolving the divergence of LiDAR positioning results due to cumulative errors, and 2) the challenge of accurately assigning weights to LiDAR data in the integrated system. To overcome these obstacles, we propose a trajectory-layer LiDAR positioning enhancement method to reduce cumulative errors and a trajectory-layer LiDAR positioning accuracy quantification method to determine the weight of LiDAR. Finally, the performance of TL-GILNS is verified through experiments conducted in semi-open and large-scale complex scenes. In these scenes, TL-GILNS achieves horizontal accuracy better than 0.3 m, vertical accuracy better than 0.7 m, and yaw angle accuracy better than 1∘. These results demonstrate the potential of TL-GILNS as a leading approach for high-precision navigation and positioning in complex environments.

Visible light positioning (VLP) has emerged as a promising indoor localization technology due to its high accuracy, low cost. However, it still faces challenges, such as environmental interference, signal noise, and occlusion. To address the above issues, a bidirectional encoder representations from transformer (BERT)-enhanced VLP and inertial navigation fusion positioning system is developed. First, to tackle the problem of inaccurate ranging caused by signal noise, we propose a Transformer-based network, VLP-BERT, which leverages long-sequence masking to enhance the network’s feature extraction capabilities from visible light (VL) signals. Moreover, the VLP-BERT is integrated into an autoencoder–decoder architecture for signal denoising. Second, to overcome the limitations of traditional ranging models (RMs) in complex environments, a deep learning-based centralized VLP RM is proposed. Finally, to enhance the system’s reliability under varying conditions, a tightly coupled fusion method integrating VLP with pedestrian dead reckoning (PDR) is proposed, incorporating error detection and state-constrained strategies. Extensive experimental evaluations demonstrate the effectiveness of VLP-BERT in both denoising and accurate ranging. The system was compared with nine different methods, the results show that the proposed tightly coupled approach not only achieves submeter-level accuracy but also significantly enhances the system’s robustness, even in challenging scenarios, such as signal blockage and poor signal quality.

Visible Light Positioning (VLP) has attracted considerable attention due to its widespread infrastructure, low energy consumption, and high precision. However, existing VLP methods often struggle to respond promptly to environment and receiver status changes, with fixed parameters throughout execution. This limitation hinders their ability to adjust system model parameters adaptively. In this paper, we propose a robust data-model dual-driven tightly-coupled integration of VLP and inertial navigation with uncertainty estimation to take complementary advantage of data-driven and model-driven methods. We develop a model-driven feature encoder that consists of VLP-BERT and VLP-GAT, enabling the system to detect abnormal observations in a changing environment. VLP-BERT is designed to effectively encode VL signal features, while VLP-GAT is developed to encode the correlations feature between the signal characteristics and the anchors' spatial configuration. These encoded features are then decoded into distance confidence. Subsequently, the data-driven results are incorporated into a tightly coupled integration model, allowing for the adaptive adjustment of system parameters. Additionally, the receiver is inevitably subject to occlusion and slight tilting. To address these issues, we implement occlusion detection and error detection strategies based on signal-changed features. We further use the system state from the tightly coupled integration model to exclude low-accuracy observations and solve the receiver title in VLP. Extensive experiments have been conducted to validate the presented navigator and the effectiveness of VLP-BERT and VLP-GAT. Compared to existing methods, the proposed navigator achieves precise and robust navigation in complex, changing environments.