Global localization in 3D maps for structured environment

Localization is one of many issues in mobile robot study. Localization is an essential ability for mobile robot to determine its location, so that it can plan a movement and go to a desired location. The mutual method for mobile robot localization is using a particle filter. High computation needs in particle filter is one of problem in particle filtering to get accurate location. The paper proposes a low computational mobile robot localization using a particle filter. It uses two methods: local localization using a dead reckoning method and global localization using a landmark-based vision sensor. Simulation results show that the proposed method provides a good estimation on the mobile robot position and orientation.

Owing to the presence of multiple obstacles or changes in the positions of surroundings objects, the localization of a mobile robot using only natural landmarks is difficult in indoor environments. Consequently, in these environments, the use of artificial landmarks to achieve robust localization is necessary. To this end, we propose a global localization method for mobile robots, using reflectors as indistinguishable artificial landmarks, not the manmade signs have a certain pattern. In previous studies, it has been shown that localization is possible using information about the distance between indistinguishable artificial landmarks. We applied this principle in a real-world situation with many obstacles or in a dynamic environment and confirmed that robust, high-accuracy global localization is possible.

Global localization is essential for unmanned vehicle navigation in a prebuilt map especially in weak or erroneous GNSS signals areas. Unlike images containing rich features, point clouds are sparse and almost contain pure geometric information which makes global localization using a single scan still a challenging problem. Based on Scan Context framework, we propose a road-centric 3D point cloud descriptor for global localization in urban environment. Rather than generate the descriptor in the raw sensor coordinate, we incorporate road measurements and topological information to transform the point cloud into a road-centric coordinate and generate the descriptor which makes it theoretically rotation-invariant and translation-invariant. In addition, we can obtain more precise initial pose to align point cloud with the prebuilt map through the transformation between raw sensor coordinate and road-centric coordinate. Evaluation on KITTI dataset shows that our proposed method has better performance in global localization and the success rate is 26% higher than Scan Context.

Global localization in a prior map is an important field in virtual and augmented reality systems, but it is always a challenge to conduct point cloud based localization in the large-scale scene prior map. A large-scale prior map usually means huge amount of calculation for point cloud processing, which leads to the long time required for global localization. To deal with this problem, we propose a fast point cloud global localization method based on point clouds segmentation and learning-based descriptor. On the one hand, cylindrical filtering, ground-point removal and point cloud segmentation are adopted to eliminate a large number of useless points and retain points with rich structures, which improves the efficiency of point cloud registration. On the other hand, reliable 3D point cloud descriptor, two-phase search strategy for place recognition and geometric consistency verification are used to ensure the localization accuracy. Experiments prove that the proposed method achieves good localization effect on both KITTI and MVSEC datasets. Under the condition of ensuring the high localization accuracy, the time for point clouds to complete the global localization is greatly reduced.

Autonomous shuttle development has gained popularity as one of the research development areas in autonomous vehicle field. In this chapter, the shuttle development in Universiti Malaysia Pahang is highlighted, while its vehicle simulation environment is developed to mimic the real environment of the university which consists of many roundabout junctions. The roundabout environment is constructed in vehicle simulator for data logging and testing and then published to the ROS network. Point cloud matrices from different moving frames are stitched using iterative closest point (ICP) algorithm to form a final useful map for further post-processing. The ICP algorithm performance is shown with different number of stitching frames and the results show that the algorithm is capable to show a reliable single map from different point cloud frames.

With the development of computer vision technologies, 3D reconstruction has become a hotspot. At present, 3D reconstruction relies heavily on expensive equipment and has poor real-time performance. In this paper, we aim at solving the problem of 3D reconstruction of an indoor scene with large vertical span. In this paper, we propose a novel approach for 3D reconstruction of indoor scenes with only a Kinect. Firstly, this method uses a Kinect sensor to get color images and depth images of an indoor scene. Secondly, the combination of scale-invariant feature transform and random sample consensus algorithm is used to determine the transformation matrix of adjacent frames, which can be seen as the initial value of iterative closest point (ICP). Thirdly, we establish the relative coordinate relation between pair-wise frames which are the initial point cloud data by using ICP. Finally, we achieve the 3D visual reconstruction model of indoor scene by the top-down image registration of point cloud data. This approach not only mitigates the sensor perspective restriction and achieves the indoor scene reconstruction of large vertical span, but also develops the fast algorithm of indoor scene reconstruction with large amount of cloud data. The experimental results show that the proposed algorithm has better accuracy, better reconstruction effect, and less running time for point cloud registration. In addition, the proposed method has great potential applied to 3D simultaneous location and mapping.

This paper presents a method for pose estimation of a rigid body using unit dual quaternions where pose measurements from point clouds are filtered with a multiplicative extended Kalman filter (MEKF). The point clouds come from a 3D camera fixed to the moving rigid body, and then consecutive point clouds are aligned with the Iterative Closest Point (ICP) algorithm to obtain pose measurements. The unit constraint of the dual quaternion is ensured in the filtering process with the Dual Quaternion MEKF (DQ-MEKF), where the measurement updates are performed using the dual quaternion product so that the result is a unit dual quaternion. In addition, we use the Cayley transform for the discrete time propagation of the DQ-MEKF estimate, eliminating the need for normalization and projection of the resulting unit dual quaternion. The ICP algorithm is initialized with the time propagated state of the filter to give faster and more accurate pose measurements. To further improve the accuracy of the initialization, angular velocity measurements from a gyroscope fixed to the camera are included in the filter. The proposed method has been tested in experiments using a Kinect v2 3D camera mounted rigidly on a KUKA KR6 robotic arm, while a customized ICP algorithm was successfully implemented on a Graphical Processing Unit (GPU) system.

Localization and mapping are key requirements for autonomous mobile systems to perform navigation and interaction tasks. Iterative Closest Point (ICP) is widely applied for LiDAR scan-matching in the robotic community. In addition, the standard ICP algorithm only considers geometric information when iteratively searching for the nearest point. However, ICP individually cannot achieve accurate point-cloud registration performance in challenging environments such as dynamic environments and highways. Moreover, the computation of searching for the closest points is an expensive step in the ICP algorithm, which is limited to meet real-time requirements, especially when dealing with large-scale point-cloud data. In this paper, we propose a segment-based scan-matching framework for six degree-of-freedom pose estimation and mapping. The LiDAR generates a large number of ground points when scanning, but many of these points are useless and increase the burden of subsequent processing. To address this problem, we first apply an image-based ground-point extraction method to filter out noise and ground points. The point cloud after removing the ground points is then segmented into disjoint sets. After this step, a standard point-to-point ICP is applied into to calculate the six degree-of-freedom transformation between consecutive scans. Furthermore, once closed loops are detected in the environment, a 6D graph-optimization algorithm for global relaxation (6D simultaneous localization and mapping (SLAM)) is employed. Experiments based on publicly available KITTI datasets show that our method requires less runtime while at the same time achieves higher pose estimation accuracy compared with the standard ICP method and its variants.

As 3D point cloud acquisition sensors become increasingly prevalent in urban environments (e.g., LiDAR sensors for autonomous vehicles), the need arises to find efficient ways to align large amounts of such 3D data, often in real-time. In this work, we propose a novel method for 3D point cloud registration refinement in an urban environment (e.g., between Terrestrial LiDAR Scans - TLS - and Airborne LiDAR Scans - ALS), assuming an initial coarse registration is available. The proposed method is based on estimation of the direction of gravity, wall detection, projection of the point clouds on a perpendicular horizontal plane, and conversion into 2D edge-maps. Then, two methods are considered for alignment between the 2D edge-maps: a 2D variant of the well-known ICP (Iterative Closest Point) algorithm, and Edge-Map Phase-Correlation (EMPC). We demonstrate the usefulness of the proposed methods for registration in this challenging task, where the 2D variant of ICP achieves a meaningful advantage over 3D ICP in terms of runtime, while maintaining comparable registration accuracy.

Iterative closest point-based data fusion of non-synchronized in-situ and ex-situ data in laser powder bed fusion

The Iterative Closest Point (ICP) algorithm is a classical approach to obtaining relative pose estimates of a robot by scan matching successive point clouds captured by an onboard depth camera such as the Kinect V1, which has enjoyed tremendous popularity for indoor robotics due to its low cost and good performance. Because the sensed 3D point clouds are noticeably corrupted by noise, it is useful to associate a covariance matrix to the relative pose estimates, either for diagnostics or for fusing them with other onboard sensors by means of a probabilistic sensor fusion method such as the Extended Kalman Filter (EKF). In this paper, we review the sensing characteristics of the Kinect camera, then present a novel approach to estimating the covariance of pose estimates obtained from ICP-based scan matching of point clouds from this sensor. Our key observation is that the prevailing source of error for ICP registration of Kinect-measured point clouds is quantization noise rather than white noise. We then derive a closed-form formula which can be computed in real time onboard the robot's hardware, for the case where only 1D translations are considered. Experimental testing against a ground truth provided by an optical motion capture system validates the effectiveness of our proposed method.

In this paper, we propose an efficient way to produce an initial transposed matrix for two point clouds, which can effectively avoid the drawback of local optimism caused by using standard Iterative Closest Points (ICP)[ algorithm when matching two point clouds. In our approach, the correspondences used to calculate the transposed matrix are confirmed before the point cloud forms. We use the depth images which have been carefully target-segmented to find the boundaries of the shapes that reflect different views of the same target object. Then each contour is affected by curvature scale space (CSS)[ method to find a sequence of characteristic points. After that, our method is applied on these characteristic points to find the most matching pairs of points. Finally, we convert the matched characteristic points to 3D points, and the correspondences are there being confirmed. We can use them to compute an initial transposed matrix to tell the computer which part of the first point cloud should be matched to the second. In this way, we put the two point clouds in a correct initial location, so that the local optimism of ICP and its variations can be excluded.

The registration of point clouds in a three-dimensional space is an important task in many areas of computer vision, including robotics and autonomous driving. The purpose of registration is to find a rigid geometric transformation to align two point clouds. The registration problem can be affected by noise and partiality (two point clouds only have a partial overlap). The Iterative Closed Point (ICP) algorithm is a common method for solving the registration problem. Recently, artificial neural networks have begun to be used in the registration of point clouds. The drawback of ICP and other registration algorithms is the possible convergence to a local minimum. Thus, an important characteristic of a registration algorithm is the ability to avoid local minima. In this paper, we propose an ICP-type registration algorithm (λ-ICP) that uses a multiparameter functional (λ-functional). The proposed λ-ICP algorithm generalizes the NICP algorithm (normal ICP). The application of the λ-functional requires a consistent choice of the eigenvectors of the covariance matrix of two point clouds. The paper also proposes an algorithm for choosing the directions of eigenvectors. The performance of the proposed λ-ICP algorithm is compared with that of a standard point-to-point ICP and neural network Deep Closest Points (DCP).

Differential LiDAR (Light Detection and Ranging) from repeated surveys has recently emerged as an effective tool to measure three-dimensional (3D) change for applications, such as quantifying slip and spatially distributed warping associated with earthquake ruptures, and examining the spatial distribution of beach erosion after hurricane impact. Currently, the primary method for determining 3D change from LiDAR is through the use of the iterative closest point (ICP) algorithm and its variants. However, all current studies using ICP have assumed that all LiDAR points in the compared point clouds have uniform accuracy. This assumption is simplistic given that the error for each LiDAR point is variable, and dependent upon time varying factors such as target range, angle of incidence, and aircraft trajectory accuracy. Therefore, to rigorously determine spatial change, it would be ideal to model the random error for every LiDAR observation in the differential point cloud, and use these error estimates as apriori weights in the ICP algorithm. To test this approach, we implemented a rigorous LiDAR observation error propagation method to generate estimated random error for each point in a LiDAR point cloud, and then determine 3D displacements between two point clouds using an anisotropic weighted ICP (A-ICP) algorithm. The algorithm was evaluated by qualitatively and quantitatively comparing point clouds with synthetic fault ruptures between a uniform weight and anistropically weighted ICP algorithm. Then post-earthquake slip is estimated for the 2010 El Mayor-Cucapah Earthquake (EMC), using pre- and post-event LiDAR. Based on the analysis, Moving Window A-ICP is able to better estimate the synthetic surface ruptures, and provides a smoother estimate of actual displacement for the EMC earthquake.

The iterative closest point (ICP) tends to fall into local optimality due to inaccurate initial poses during the registration of the multi-view 3D cloud. Therefore, this paper proposes a parallel ICP algorithm with conditional constraint corresponding points. To achieve a fine registration of the point cloud, the corresponding point set is first filtered by adding the normal and color information. Then the OpenMP is introduced to accelerate the program in parallel for ICP. To verify the effectiveness of our algorithm, in the V-Rep simulation environment, the multi-view point cloud data of the scene is obtained by the RGB-D cameras from different angles point cloud. The results show that our algorithm can fuse the multi-view point cloud, improve the accuracy and real-time performance of ICP. Furthermore, in a large-scale calculation, the average single iteration time is less than 0.1s, and the RMSE (root mean square error) is about 0.1, which meets the need of target recognition and sorting in a three-dimensional industrial scene.