3D SLAM based on NDT matching and ground constraints for ground robots in complex environments

Simultaneous localization and mapping (SLAM) has been investigated in the field of robotics for two decades, as it is considered to be an effective method for solving the positioning and mapping problem in a single framework. In the SLAM community, the Extended Kalman Filter (EKF) based SLAM and particle filter SLAM are the most mature technologies. After years of development, graph-based SLAM is becoming the most promising technology and a lot of progress has been made recently with respect to accuracy and efficiency. No matter which SLAM method is used, loop closure is a vital part for overcoming the accumulated errors. However, in 2D Light Detection and Ranging (LiDAR) SLAM, on one hand, it is relatively difficult to extract distinctive features in LiDAR scans for loop closure detection, as 2D LiDAR scans encode much less information than images; on the other hand, there is also some special mapping scenery, where no loop closure exists. Thereby, in this paper, instead of loop closure detection, we first propose the method to introduce extra control network constraint (CNC) to the back-end optimization of graph-based SLAM, by aligning the LiDAR scan center with the control vertex of the presurveyed control network to optimize all the poses of scans and submaps. Field tests were carried out in a typical urban Global Navigation Satellite System (GNSS) weak outdoor area. The results prove that the position Root Mean Square (RMS) error of the selected key points is 0.3614 m, evaluated with a reference map produced by Terrestrial Laser Scanner (TLS). Mapping accuracy is significantly improved, compared to the mapping RMS of 1.6462 m without control network constraint. Adding distance constraints of the control network to the back-end optimization is an effective and practical method to solve the drift accumulation of LiDAR front-end scan matching.

This paper presents a Light Detection and Ranging (LiDAR) data set that targets complex urban environments. Urban environments with high-rise buildings and congested traffic pose a significant challenge for many robotics applications. The presented data set is unique in the sense it is able to capture the genuine features of an urban environment (e.g. metropolitan areas, large building complexes and underground parking lots). Data of two-dimensional (2D) and threedimensional (3D) LiDAR, which are typical types of LiDAR sensors, are provided in the data set. The two 16-ray 3D LiDARs are tilted on both sides for maximal coverage. One 2D LiDAR faces backward while the other faces forwards to collect data of roads and buildings, respectively. Raw sensor data from Fiber Optic Gyro (FOG), Inertial Measurement Unit (IMU), and the Global Positioning System (GPS) are presented in a file format for vehicle pose estimation. The pose information of the vehicle estimated at 100 Hz is also presented after applying the graph simultaneous localization and mapping (SLAM) algorithm. For the convenience of development, the file player and data viewer in Robot Operating System (ROS) environment were also released via the web page. The full data sets are available at: http://irap.kaist.ac.kr/dataset. In this website, 3D preview of each data set is provided using WebGL.

Accurate vehicle ego-localization is key for autonomous vehicles to complete high-level navigation tasks. The state-of-the-art localization methods adopt visual and light detection and ranging (LiDAR) simultaneous localization and mapping (SLAM) to estimate the position of the vehicle. However, both of them may suffer from error accumulation due to long-term running without loop optimization or prior constraints. Actually, the vehicle cannot always return to the revisited location, which will cause errors to accumulate in Global Navigation Satellite System (GNSS)-challenged environments. To solve this problem, we proposed a novel localization method with prior dense visual point cloud map constraints generated by a stereo camera. Firstly, the semi-global-block-matching (SGBM) algorithm is adopted to estimate the visual point cloud of each frame and stereo visual odometry is used to provide the initial position for the current visual point cloud. Secondly, multiple filtering and adaptive prior map segmentation are performed on the prior dense visual point cloud map for fast matching and localization. Then, the current visual point cloud is matched with the candidate sub-map by normal distribution transformation (NDT). Finally, the matching result is used to update pose prediction based on the last frame for accurate localization. Comprehensive experiments were undertaken to validate the proposed method, showing that the root mean square errors (RMSEs) of translation and rotation are less than 5.59 m and 0.08°, respectively.

Remotely Operated Underwater Vehicles (ROUVs) are increasingly important for high-resolution surveying of narrow shipping lanes. This paper presents 3Clifs, a LiDAR- and AI-enhanced ROUV designed for near-real-time topographic mapping and navigation support in shallow, constrained waterways, demonstrated at three cliff sites in the Suez Canal. The system integrates three-dimensional Light Detection and Ranging (LiDAR) scanning, an Inertial Measurement Unit (IMU), and an onboard processor running the Robot Operating System (ROS) for Simultaneous Localization and Mapping (SLAM). To address data loss from underwater LiDAR (caused by scattering and reflection), we introduce an AI-driven optimisation module that reconstructs missing point cloud data and improves SLAM continuity. We also report propulsion and propeller design changes (propeller v05_1) that reduce flow turbulence and improve scan stability. We compare our approach to sonar-only ROUV mapping and to recent ROUV/LiDAR studies using metrics including point-cloud completeness, SLAM continuity, and navigation-path deviation. The main contributions are: (i) an integrated LiDAR, ROS and AI pipeline for underwater SLAM with missing-point recovery; (ii) a propulsion configuration optimized for LiDAR scanning stability; and (iii) a real-world Suez Canal case study demonstrating practical benefits for narrow-lane navigation.

Light Detection and Ranging (LiDAR)-based simultaneous localization and mapping (SLAM) is a core technology for autonomous vehicles and robots. One key contribution of this work to 3D LiDAR SLAM and localization is a fierce defense of view-based maps (pose graphs with time-stamped sensor readings) as the fundamental representation of maps. As will be shown, they allow for the greatest flexibility, enabling the posterior generation of arbitrary metric maps optimized for particular tasks, for example, obstacle avoidance and real-time localization. Moreover, this work introduces a new framework in which mapping pipelines can be defined without coding, defining the connections of a network of reusable blocks much like deep-learning networks are designed by connecting layers of standardized elements. We also introduce tightly-coupled estimation of linear and angular velocity vectors within the Iterative Closest Point (ICP)-like optimizer, leading to superior robustness against aggressive motion profiles without the need for an IMU. Extensive experimental validation reveals that the proposal compares well to, or improves, former state-of-the-art (SOTA) LiDAR odometry systems, while also successfully mapping some hard sequences where others diverge. A proposed self-adaptive configuration has been used, without parameter changes, for all 3D LiDAR datasets with sensors between 16 and 128 rings, and has been extensively tested on 83 sequences over more than 250 km of automotive, hand-held, airborne, and quadruped LiDAR datasets, both indoors and outdoors. The system flexibility is demonstrated with additional configurations for 2D LiDARs and for building 3D NDT-like maps. The framework is open-sourced online: https://github.com/MOLAorg/mola.

Navigation system for orchard spraying robot based on 3D LiDAR SLAM with NDT_ICP point cloud registration

In the field of robotics, four tasks of autonomous robots such as navigation, localization, object tracking, and motion planning, play a crucial role to ensure the autonomy and intelligence of system in the complex and diverse environment. All of its operation relies on the working ability of laser scanner or LiDAR (Light Detection and Ranging) sensor which becomes a promising tool for these tasks due to the accurate distance measurement and wide field of view. The objective of this paper is to evaluate and compare the working performance between 2D and 3D LiDAR sensor in the specific tasks. In the different applications, 2D LiDAR sensor scans on a single plane while the 3D one uses lasers to capture precise 3D data of objects and environments. A series of real-world experiments are conducted in a laboratory setting, focusing on three main tasks: object detection and tracking, mapping capabilities, and motion planning. Owing to these practical tests, the results highlight the strengths and weaknesses of both 2D and 3D LiDAR sensors in such tasks. Experimental results show that, compared with 2D LiDAR, the 3D LiDAR reduces measurement error by up to 59% in the Y-axis, improves human detection accuracy by 28.8% under occlusion conditions, and eliminates navigation collisions caused by planar blind spots, albeit at the cost of a lower frame rate.

The accuracy and stability of front-end point cloud registration algorithms are crucial for the mapping and localization precision in laser SLAM (simultaneous localization and mapping) systems. Traditional point-to-line and point-to-plane iterative closest point (ICP) registration algorithms, widely used in SLAM front ends, often suffer from low efficiency, significant data dependency during the matching process, and a propensity for local optima. This registration method exhibits a more pronounced local optimum issue in large-scale SLAM mapping, thereby diminishing matching accuracy and increasing reliance on initial values. To address these limitations, this paper introduces NI-LIO, a novel SLAM algorithm that integrates ICP with normal distributions transform (NDT) to enhance localization accuracy, computational efficiency and robustness. By combining the precision of ICP with the robustness of NDT, the proposed algorithm significantly improves system stability and localization accuracy. The analysis of mapping and localization experiments indicates a significant reduction in errors compared to traditional SLAM algorithms, with experiments showing a REMS value decrease of over 20%. Compared to ALOAM, FAST_LIO2 and Lego-LOAM algorithms, the new NI-LIO algorithm shows improvements in both accuracy and stability, enabling the construction of a more precise and consistent global map. This algorithm exhibits excellent adaptability to various environments.

<span lang="EN-US">In recent years, there has been a strong demand for self-driving cars. For safe navigation, self-driving cars need both precise localization and robust mapping. While global navigation satellite system (GNSS) can be used to locate vehicles, it has some limitations, such as satellite signal absence (tunnels and caves), which restrict its use in urban scenarios. Simultaneous localization and mapping (SLAM) are an excellent solution for identifying a vehicle’s position while at the same time constructing a representation of the environment. SLAM-based visual and light detection and ranging (LIDAR) refer to using cameras and LIDAR as source of external information. This paper presents an implementation of SLAM algorithm for building a map of environment and obtaining car’s trajectory using LIDAR scans. A detailed overview of current visual and LIDAR SLAM approaches has also been provided and discussed. Simulation results referred to LIDAR scans indicate that SLAM is convenient and helpful in localization and mapping.</span>

Simultaneous Localization and Mapping (SLAM) has been studied a lot since 20 years in the robotics community: a SLAM method copes with the incremental construction of a geometrical model from the successive fusion of observations acquired from moving sensors. When sensors are embedded on a mobile robot, robot localization and environment mapping must be performed in the same function. Many methods aim to build sparse representations, made of 2D segments (from 2D laser data for indoor applications) or 3D points (from a single camera or stereovision): this paper discusses some issues related to 3D and dense SLAM, i.e. the incremental construction of a textured surfacic model from the fusion of sensory data acquired from a 3D laser range finder coupled with a camera: the fusion of multisensory data in a unified 3D representation makes more robust the data association between features perceived from different viewpoints. First an heterogeneous model, made of a stochastic map and of appearance-based information, is described, before focusing on the data association function; our approach is validated by experimental results obtained from data acquired on our Jido robot.

This paper proposes a method for generating highly accurate point cloud maps of orchards using an unmanned aerial vehicle (UAV) equipped with light detection and ranging (LiDAR). The point cloud captured by the UAV-LiDAR was converted to a geographic coordinate system using a global navigation satellite system / inertial measurement unit (GNSS/IMU). The converted point cloud is then aligned with the simultaneous localization and mapping (SLAM) technique. As a result, a 3D model of an orchard is generated in a low-cost and easy-to-use manner for pesticide application with precision. The method of direct point cloud alignment with real-time kinematic-global navigation satellite system (RTK-GNSS) had a root mean square error (RMSE) of 42 cm between the predicted and true crop height values, primarily due to the effects of GNSS multipath and vibration of automated vehicles. Contrastingly, our method demonstrated better results, with RMSE of 5.43 cm and 2.14 cm in the vertical and horizontal axes, respectively. The proposed method for predicting crop location successfully achieved the required accuracy of less than 1 m with errors not exceeding 30 cm in the geographic coordinate system.

This article aims at demonstrating the feasibility of modern deep learning techniques for the real-time detection of non-stationary objects in point clouds obtained from 3-D light detecting and ranging (LiDAR) sensors. The motion segmentation task is considered in the application context of automotive Simultaneous Localization and Mapping (SLAM), where we often need to distinguish between the static parts of the environment with respect to which we localize the vehicle, and non-stationary objects that should not be included in the map for localization. Non-stationary objects do not provide repeatable readouts, because they can be in motion, like vehicles and pedestrians, or because they do not have a rigid, stable surface, like trees and lawns. The proposed approach exploits images synthesized from the received intensity data yielded by the modern LiDARs along with the usual range measurements. We demonstrate that non-stationary objects can be detected using neural network models trained with 2-D grayscale images in the supervised or unsupervised training process. This concept makes it possible to alleviate the lack of large datasets of 3-D laser scans with point-wise annotations for non-stationary objects. The point clouds are filtered using the corresponding intensity images with labeled pixels. Finally, we demonstrate that the detection of non-stationary objects using our approach improves the localization results and map consistency in a laser-based SLAM system.

In recent years, low-cost and lightweight RGB and depth (RGB-D) sensors, such as Microsoft Kinect, have made available rich image and depth data, making them very popular in the field of simultaneous localization and mapping (SLAM), which has been increasingly used in robotics, self-driving vehicles, and augmented reality. The RGB-D SLAM constructs 3D environmental models of natural landscapes while simultaneously estimating camera poses. However, in highly variable illumination and motion blur environments, long-distance tracking can result in large cumulative errors and scale shifts. To address this problem in actual applications, in this study, we propose a novel multithreaded RGB-D SLAM framework that incorporates a highly accurate prior terrestrial Light Detection and Ranging (LiDAR) point cloud, which can mitigate cumulative errors and improve the system’s robustness in large-scale and challenging scenarios. First, we employed deep learning to achieve system automatic initialization and motion recovery when tracking is lost. Next, we used terrestrial LiDAR point cloud to obtain prior data of the landscape, and then we applied the point-to-surface inductively coupled plasma (ICP) iterative algorithm to realize accurate camera pose control from the previously obtained LiDAR point cloud data, and finally expanded its control range in the local map construction. Furthermore, an innovative double window segment-based map optimization method is proposed to ensure consistency, better real-time performance, and high accuracy of map construction. The proposed method was tested for long-distance tracking and closed-loop in two different large indoor scenarios. The experimental results indicated that the standard deviation of the 3D map construction is 10 cm in a mapping distance of 100 m, compared with the LiDAR ground truth. Further, the relative cumulative error of the camera in closed-loop experiments is 0.09%, which is twice less than that of the typical SLAM algorithm (3.4%). Therefore, the proposed method was demonstrated to be more robust than the ORB-SLAM2 algorithm in complex indoor environments.

The millimeter-wave (mmWave) communication technology, which employs large-scale antenna arrays, enables inherent sensing capabilities. Simultaneous localization and mapping (SLAM) can utilize channel multipath angle estimates to realize integrated sensing and communication design in 6G communication systems. However, existing works have ignored the significant overhead required by the mmWave beam management when implementing SLAM with angle estimates. This study proposes a joint beam management and SLAM design that utilizes the strong coupling between the radio map and channel multipath for simultaneous beam management, localization, and mapping. In this approach, we first propose a hierarchical sweeping and sensing service design. The path angles are estimated in the hierarchical sweeping, enabling angle-based SLAM with the aid of an inertial measurement unit (IMU) to realize sensing service. Then, feature-aided tracking is proposed that utilizes prior angle information generated from the radio map and IMU. Finally, a switching module is introduced to enable flexible switching between hierarchical sweeping and feature-aided tracking. Simulations show that the proposed joint design can achieve sub-meter level localization and mapping accuracy (with an error < 0.5 m). Moreover, the beam management overhead can be reduced by approximately 40% in different wireless environments.

Recently, light detection and ranging (LiDAR) technology has emerged as a promising approach to enhance sensing systems, particularly in human activity recognition (HAR). Advances in computer vision and LiDAR sensor development are revolutionizing HAR systems. This work proposes a novel method to detect and classify human exercise poses using 3D LiDAR technology by taking advantage of deep learning techniques. We utilize the Point Pillars network for 3D object detection and employ pseudo-image transformation for effective 3D to 2D data conversion, enhancing the applicability of 2D CNNs for 3D point cloud data analysis. To account for temporal dependencies in 3D point cloud data streams, we use the "smush" technique, which considers a few consecutive 3D LiDAR point cloud frames. This method significantly improves the detection accuracy of dynamic exercises, highlighting the potential of our approach in enhancing fitness monitoring technologies. This research not only demonstrates the effective use of 3D LiDAR in capturing complex activities but also lays the groundwork for future advancements in mapping human movement using 3D LiDAR. <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup>