Abstract:There is a large body of literature on solving the SLAM problem for various autonomous vehicle applications. A substantial part of the solutions is formulated based on using statistical (mainly Bayesian) filters such as Kalman filter and its extended version. In such solutions, the measurements are commonly some point features or detections collected by the sensor(s) on board the autonomous vehicle. With the increasing utilization of scanners with common autonomous cars, and availability of 3D point clouds in … Show more
“…Passthrough filtering performs point cloud clip in the X-, Y-, and Z-directions and first removes large-area outliers and obstacles. The point cloud is further refined by statistical filtering to remove small outliers 22 . Statistical filtering performs statistical analysis on the neighborhood of each point to calculate the average distance between adjacent points in a given neighborhood, and the mean μ and standard deviation σ can be calculated.…”
Section: Point Cloud Composite Filteringmentioning
At present, the non-contact measurement of mine tunnel deformation is mainly realized by laser scanning technology. To address the issues of poor flexibility, slow detection speed, and low automation in multi-site measurement, a new method for tunnel deformation detection is proposed that combines visual SLAM (simultaneous localization and mapping) and 3D point cloud slicing technology. The mobile robot carries a depth camera to continuously capture RGB and depth images of underground tunnels and uses the visual SLAM algorithm to reconstruct the entire 3D dense map of underground tunnels. A composite filtering method is designed for point cloud denoising. Comparative tests were conducted on the reconstruction effect of point cloud structures under different lighting conditions. The dense point clouds in the whole area at different times are sliced, and the deformation volume and position of the roadway are accurately identified through pairing comparison with skeleton line algorithm and point cloud slicing algorithm. The experimental results show that this method can establish a high-precision 3D dense model of underground tunnels under lighting conditions above 50lx. The composite filtering method can remove a large amount of point cloud noise, and the measurement error of tunnel deformation point cloud is less than 5 mm. It can achieve precise detection of tunnel deformation and determination of deformation position, with fast detection speed, and can meet the needs of under-ground tunnel deformation detection in coal mines.
“…Passthrough filtering performs point cloud clip in the X-, Y-, and Z-directions and first removes large-area outliers and obstacles. The point cloud is further refined by statistical filtering to remove small outliers 22 . Statistical filtering performs statistical analysis on the neighborhood of each point to calculate the average distance between adjacent points in a given neighborhood, and the mean μ and standard deviation σ can be calculated.…”
Section: Point Cloud Composite Filteringmentioning
At present, the non-contact measurement of mine tunnel deformation is mainly realized by laser scanning technology. To address the issues of poor flexibility, slow detection speed, and low automation in multi-site measurement, a new method for tunnel deformation detection is proposed that combines visual SLAM (simultaneous localization and mapping) and 3D point cloud slicing technology. The mobile robot carries a depth camera to continuously capture RGB and depth images of underground tunnels and uses the visual SLAM algorithm to reconstruct the entire 3D dense map of underground tunnels. A composite filtering method is designed for point cloud denoising. Comparative tests were conducted on the reconstruction effect of point cloud structures under different lighting conditions. The dense point clouds in the whole area at different times are sliced, and the deformation volume and position of the roadway are accurately identified through pairing comparison with skeleton line algorithm and point cloud slicing algorithm. The experimental results show that this method can establish a high-precision 3D dense model of underground tunnels under lighting conditions above 50lx. The composite filtering method can remove a large amount of point cloud noise, and the measurement error of tunnel deformation point cloud is less than 5 mm. It can achieve precise detection of tunnel deformation and determination of deformation position, with fast detection speed, and can meet the needs of under-ground tunnel deformation detection in coal mines.
“…Secondly, two objects with proper distance are randomly selected from the current frame. Then, all relationship pairs set between the selected two objects in current frame and the objects in frame m-5 are obtained according to the corresponding point query method in section (2).…”
Section: ) Query Corresponding Points Based On Multiple Featuresmentioning
In urban dynamic environment, most of the existing works on LiDAR SLAM are based on static scene assumption and are greatly affected by dynamic obstacles. In order to solve this problem, this paper is based on F-LOAM, and adopts FA-RANSAC algorithm, improved ScanContext algorithm and global optimization to propose a robust and fast LiDAR Odometry and Mapping (RF-LOAM). Firstly, the Region Growing algorithm is used to cluster the fan-shaped grids. Then, we propose FA-RANSAC algorithm base on feature information and adaptive threshold for dynamic objects removal, and extracts the static edge and planar feature points for the first distortion compensation. Afterward, estimated pose is calculated by the static feature points and is used to perform the second distortion compensation. Then, the height difference and adaptive distance threshold are used to improve the accuracy of ScanContext, and the efficiency of ScanContext is improved by deleting the loop closure historical matching frames and simplifying the feature matching. Finally, global optimization is used for keyframe. The experimental tests are carried out on the KITTI datasets, Urbanloco datasets and our Extracted dataset. The results show that compared with the state-of-the-art SLAM methods, our method can not only accurately complete dynamic objects removal and loop closure detection, but also achieve more robust and faster localization and mapping in urban dynamic scenes.
“…In order to merge planes segmented in different frames or merge the local maps generated by different robots, it is highly necessary to transform the planes into the same coordinate system to simplify computation. Gostar et al [97] proposed a plane transition model to convert the plane parameters in the vehicle coordinate system to the global coordinate system. This method can be employed to transform the planes obtained in different frames into the same coordinate system for map-merging purposes.…”
When multiple robots are involved in the process of simultaneous localization and mapping (SLAM), a global map should be constructed by merging the local maps built by individual robots, so as to provide a better representation of the environment. Hence, the map-merging methods play a crucial rule in multi-robot systems and determine the performance of multi-robot SLAM. This paper looks into the key problem of map merging for multiple-ground-robot SLAM and reviews the typical map-merging methods for several important types of maps in SLAM applications: occupancy grid maps, feature-based maps, and topological maps. These map-merging approaches are classified based on their working mechanism or the type of features they deal with. The concepts and characteristics of these map-merging methods are elaborated in this review. The contents summarized in this paper provide insights and guidance for future multiple-ground-robot SLAM solutions.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.