An intensity-enhanced LiDAR SLAM for unstructured environments

Real-time dense mapping technology for multi-robot systems is crucial in scenarios like search and rescue. This paper presents CMDS-SLAM, a centralized multi-robot dense surfel SLAM system aimed at overcoming limitations in hardware constraints, data transmission, and real-time creation and updating of dense maps in multi-robot SLAM. CMDS-SLAM reduces the transmission of dense information by employing a dense information ﬁltering mechanism based on co-visual keyframes, in conjunction with the extraction and compression of superpixels. Additionally, the method employs a three-stage superpixel segmentation approach to optimize transmission and enhance the eﬃciency of surfel map generation. Finally, a surfel co-visibility graph is established, and multi-robot surfel map maintenance and updates are achieved through co-visibility graph and map optimization. A comprehensive evaluation of CMDS-SLAM indicates that the method enables multi-robot surfel mapping and signiﬁcantly alleviates data transmission pressures while achieving real-time updates and maintenance of the surfel map.

Section: Dense Mapping Slammentioning

confidence: 99%

CMDS-SLAM: real-time efficient centralized multi-robot dense surfel SLAM

Zuo,

Feng,

Xiao

2024

“…The similarity score between ScanContexts is calculated to determine if a loop closure is formed. Dai et al [1] proposed a method for constructing a multi-resolution intensity map using the geometric and intensity information of point clouds to enhance front-end odometry and back-end loop closure. Wang et al [12] proposed LiDAR Iris, which discretizes the bird'seye view image and encodes the discretized image to generate the LiDAR Iris descriptor.…”

Section: Related Workmentioning

confidence: 99%

“…Depending * Author to whom any correspondence should be addressed. on the sensors used, SLAM can be divided into LiDAR-based SLAM (LiDAR-SLAM) for mapping and navigation using LiDAR [1,2], and Visual SLAM based on single or stereo cameras for visual mapping and navigation [3][4][5]. Loop closure detection refers to the vehicle's ability to recognize if it has revisited a previous scene, which can reduce cumulative errors and ensure global consistency in mapping, making it a core step in ensuring the robustness of the SLAM process.…”

Section: Introductionmentioning

confidence: 99%

LiDAR-SLAM loop closure detection based on multi-scale point cloud feature transformer

Wang,

Zheng,

2023

Loop closure detection is an important part of simultaneous localization and mapping (SLAM), used to detect and correct map and trajectory drift issues caused by accumulated errors. For the LiDAR-SLAM system, the sparsity and disorder of point clouds make position recognition based on 3D point clouds more challenging. In recent years, many deep learning-based closed-loop detection algorithms have been proposed. However, due to the sparsity of point clouds, current deep learning algorithms often convert point clouds into histograms or depth maps and then process them using deep learning algorithms, undoubtedly causing information loss. In this paper, we propose a closed-loop detection method based on multi-scale point cloud features transformer, which introduces multi-scale point cloud feature extraction and transformer global context modeling. We use voxel sparse convolution to obtain features of original point clouds at different resolutions and establish contextual relationships between features at different resolutions using the transformer network to achieve multi-scale feature fusion, and then obtain global descriptors. The obtained global descriptors can be used not only for closed-loop detection but also for front-end registration to address the challenges of point cloud processing in the SLAM system, especially in enhancing global modeling capabilities and reducing information loss. Our method directly processes point cloud data and integrates multi-scale point cloud feature information, which can better adapt to the characteristics of LiDAR-SLAM systems, improving the accuracy and robustness of localization and map construction, thus having broad application prospects in the field of measurement. We evaluated our method on multiple sequences of the KITTI and KITTI-360 datasets, each containing more than 5000 frames of point clouds, and extensively evaluated on a self-collected dataset of over 3.6 km. The experimental results show that our method achieves an accuracy of over 80% on multiple datasets and demonstrates superior performance in different environments.

“…While lidar SLAM is one of the most well-known SLAM algorithms, its accuracy has plenty of room for improvement due to lidar's inherent limitations [11]. At the same time, the purely visual SLAM approaches described above have produced promising results in practical applications, their robustness is limited by camera characteristics such as motion blur and shutter delay.…”

Section: Introductionmentioning

confidence: 99%

A dynamic object removing 3D reconstruction system based on multi-sensor fusion

Zhao,

Liu,

Pan

et al. 2024

Currently, one of the key technologies for autonomous navigation of unmanned mobile robots is SLAM, which faces many challenges in practical applications. These challenges include a lack of texture, deterioration in sensor performance, and interference from moving objects in dynamic outdoor environments, all of which have an impact on the mapping system. To address these issues, this paper proposes a framework for lidar, vision camera, and inertial navigation data, resulting in fusion and dynamic object removing. The system consists of three sub-modules: the Lidar-Inertial Module (LIM), the Visual-Inertial Module (VIM), and the Dynamic-Object-Removing Module (DORM). LIM and VIM assist each other, with lidar point clouds providing three-dimensional information for the global voxel map and the camera providing pixel-level color information. At the same time, the DORM performs synchronous dynamic object detection to remove dynamic objects from the global map. The system constructs a multi-sensor factor graph using the state and observation models, and the optimal solution is obtained using least squares. Furthermore, this paper employs triangle descriptors and bundle adjustment methods for loop closure detection in order to reduce accumulated errors and maintain consistency. Experimental results demonstrate that the system can perform clean state estimation, dynamic removing and scene reconstruction in a variety of complex scenarios.