Search

LiDAR-based place recognition is crucial for Simultaneous Localization and Mapping (SLAM) and autonomous driving. However, existing methods face challenges in achieving rotation invariance and are hindered by a large number of parameters and complex data preprocessing steps, such as ground point removal and extensive down-sampling. These limitations hinder their practical implementation in complex real-world scenarios. To address these challenges, we propose LR-Net, a lightweight and rotation-invariant place recognition network designed to handle large-scale raw point clouds. LR-Net tackles rotation invariance by efficiently capturing sparse local neighborhood information and generating rotation-invariant features through the analysis of spatial distribution and positional information within the local region. Furthermore, we enhance the network's feature perception by incorporating residual MLP structures to encode multi-level local region features, and integrating dual-attentional weighting blocks to emphasize important regions and features. Lastly, the Generalized-Mean pooling structure is utilized to aggregate the global descriptor, enabling efficient point cloud retrieval. Meanwhile, we introduce PRmate, an independent sub-network that effectively optimizes retrieval results by analyzing the descriptor similarity and location distribution of the top 25 matching candidates from the place recognition network. We extensively evaluated the proposed methods on four large-scale datasets, including both standardized point cloud scenes (Oxford RobotCar dataset and NUS In-house dataset) and raw point cloud scenes (MulRan dataset and Kitti odometry dataset). The experimental results demonstrate that LR-Net effectively attains rotation-invariance in place recognition and achieves state-of-the-art accuracy with a lightweight model size of 0.4 M parameters. Additionally, LR-Net eliminates the need for data preprocessing, as it can directly process raw point cloud data for stable place recognition and exhibits robustness against variations in point density and noise intensity, enhancing its suitability for challenging scenarios. Moreover, PRmate is compatible with all existing point cloud-based place recognition methods and improves their performance. These advantages make LR-Net and PRmate highly suitable for robotic applications that rely on LiDAR-based place recognition. Our code is publicly available on the project website (https://github.com/zhzhang023/LR-Net). [ABSTRACT FROM AUTHOR]

• Factor graph optimization is employed to combine observations from multi-sensors. • Proposed GNSS-to-VIO time synchronization method can adapt to the time instability of smartphones and is robust. • Our adaptive positioning mechanism enable smartphone to achieve seamless positioning. • The positioning accuracy of the proposed method is positively correlated with the precision of GNSS observations. With the diversification of functionalities and enhancement of performance in smartphones, low-cost GNSS chips, Micro-Electro-Mechanical System (MEMS) inertial measurement units (IMU), and cameras have become essential hardware components. Moreover, the computational power provided by smartphones for data processing has also become more robust. The fusion of multiple sensors in smartphones for positioning has emerged as a trend. In order to further enhance the positioning performance of smartphones in complex environments, this paper proposes a smartphone-based Vision/MEMS-IMU/GNSS tightly coupled integration for indoor-outdoor seamless positioning. Factor graph optimization is employed to combine observations from monocular vision, MEMS-IMU, and GNSS. To solve the unstable timing of current smartphone sensors, we present a GNSS-to-VIO time synchronization method. Furthermore, an adaptive positioning mechanism is devised based on the presence or absence of GNSS signals, allowing indoor and outdoor environment to switch. The proposed method is validated by integrating smartphone VIO with both smartphone built-in GNSS and high-performance geodetic GNSS receivers. The test results of the complex outdoor environments demonstrate that the proposed method significantly enhances GNSS positioning performance. The positioning accuracy of the proposed method using geodetic GNSS receiver is superior to that using smartphone GNSS. In outdoor environments, our method enables positioning accuracy of smartphone to improve 29.4, 53.0 and 69.9 % in three directions compared to single point positioning. Indoor and outdoor tests verified that the proposed method can provide continuous and reliable positioning in alternating interrupted and restored GNSS signals. [ABSTRACT FROM AUTHOR]

Abstract With the Global Navigation Satellite System (GNSS) developing, the single-frequency single-epoch multiple GNSSs (multi-GNSS) relative positioning has become feasible. Since a larger number of the observed satellites make the instantaneous (single-epoch) positioning time-consuming, a proper satellite selection is necessary. Among the present methods, the satellite selection with a fixed high cut-off elevation angle (CEA) is least time-consuming. However, there is no criterion how large a fixed high CEA should be to achieve a high success rate and less time consumption. Besides, a fixed high CEA makes the number of visible satellites largely variable, which affects the success rate. Hence, a satellite selection strategy based on ambiguity dilution of precision (ADOP) is proposed. Firstly, the theoretical proof that the ADOP increases the least when removing satellites are all low-elevation-angle satellites is given, which is important to achieve the fast positioning with a high success rate. Then, the threshold β is calculated for a different number of satellites and a given ADOP. The satellites are selected based on their elevation angles from high to low until β of the selected satellites becomes smaller than the corresponding threshold; this method is called the extended floating CEA multi-GNSS (EF-multi-GNSS). The comparison of the single-frequency single-epoch positioning performance of the EF-multi-GNSS with the satellite selections based on a fixed low CEA (L-multi-GNSS) and a fixed high CEA (H-multi-GNSS) via the relative positioning experiments shows that: (1) the EF-multi-GNSS with a minimal number of satellites can achieve the fast positioning and a high success rate close to 100%. It can greatly reduce the time consumption of the L-multi-GNSS, by about 64.0%, by selecting 12.6 satellites of 23.4 satellites; (2) the floating CEA of EF-multi-GNSS eliminates the consideration how large a fixed high CEA should be, and a CEA larger than the fixed high CEA of the H-multi-GNSS makes it more suitable for different conditions. [ABSTRACT FROM AUTHOR]