Simultaneous Localization And Mapping Algorithm Research Articles

New Tools for Urban Analysis: A SLAM-Based Research in Venice

This research proposes a detailed analysis of the potential of MMS (Mobile Mapping Systems), supported by SLAM (Simultaneous Localisation And Mapping) algorithms, performed on a multiscale test field in order to make a concrete contribution to the morphological study of cities. These systems, developed with the aim of acquiring a large number of points in a short time, are able to map the surrounding area and automatically localise themselves in real time in relation to a determined reference system. The analysed area, located in Venice, was divided into three different test fields characterised by typical elements potentially comparable to those of other urban realities. The data were acquired using the LiBackPack C50, Kaarta Stencil and Heron Lite systems and compared quantitatively and qualitatively with data obtained from more traditional surveying techniques. Specifically, the data obtained from TLS (Terrestrial Laser Scanning) surveys, supported by topographic measurements, were the most accurate basis on which to evaluate the accuracy and completeness of the three different MMS devices. The standard deviation values were initially analysed in the final 3D global models using the C2C (Cloud to Cloud) and C2M (Cloud to Mesh) distance calculation methods. Subsequently, the geometric differences were investigated through the extraction of horizontal profiles, and two more specific 2D analyses were carried out: the first inspecting the residual parameters calculated after the Helmert transformation from two sets of control points obtained from the profiles, followed by a local strain analysis. The study of the local deformation parameters allowed us to validate the results obtained and to identify the real limits of these survey instruments. The aim was to make a concrete contribution to the formalisation of an operative protocol for the morphological study of the city, exploiting the potential of these technologies to overcome the differences in scale and the gap between outdoor and indoor spaces.

MOLISENS: MObile LIdar SENsor System to exploit the potential of small industrial lidar devices for geoscientific applications

Abstract. We propose a newly developed modular MObile LIdar SENsor System (MOLISENS) to enable new applications for small industrial lidar (light detection and ranging) sensors. The stand-alone modular setup supports both monitoring of dynamic processes and mobile mapping applications based on SLAM (Simultaneous Localization and Mapping) algorithms. The main objective of MOLISENS is to exploit newly emerging perception sensor technologies developed for the automotive industry for geoscientific applications. However, MOLISENS can also be used for other application areas, such as 3D mapping of buildings or vehicle-independent data collection for sensor performance assessment and sensor modeling. Compared to TLSs, small industrial lidar sensors provide advantages in terms of size (on the order of 10 cm), weight (on the order of 1 kg or less), price (typically between EUR 5000 and 10 000), robustness (typical protection class of IP68), frame rates (typically 10–20 Hz), and eye safety class (typically 1). For these reasons, small industrial lidar systems can provide a very useful complement to currently used TLS (terrestrial laser scanner) systems that have their strengths in range and accuracy performance. The MOLISENS hardware setup consists of a sensor unit, a data logger, and a battery pack to support stand-alone and mobile applications. The sensor unit includes the small industrial lidar Ouster OS1-64 Gen1, a ublox multi-band active GNSS (Global Navigation Satellite System) with the possibility for RTK (real-time kinematic), and a nine-axis Xsens IMU (inertial measurement unit). Special emphasis was put on the robustness of the individual components of MOLISENS to support operations in rough field and adverse weather conditions. The sensor unit has a standard tripod thread for easy mounting on various platforms. The current setup of MOLISENS has a horizontal field of view of 360∘, a vertical field of view with a 45∘ opening angle, a range of 120 m, a spatial resolution of a few centimeters, and a temporal resolution of 10–20 Hz. To evaluate the performance of MOLISENS, we present a comparison between the integrated small industrial lidar Ouster OS1-64 and the state-of-the-art high-accuracy and high-precision TLS Riegl VZ-6000 in a set of controlled experimental setups. We then apply the small industrial lidar Ouster OS1-64 in several real-world settings. The mobile mapping application of MOLISENS has been tested under various conditions, and results are shown from two surveys in the Lurgrotte cave system in Austria and a glacier cave in Longyearbreen on Svalbard.

Occupancy Grid-Based AUV SLAM Method with Forward-Looking Sonar

Simultaneous localization and mapping (SLAM) is an active localization method for Autonomous Underwater Vehicle (AUV), and it can mainly be used in unknown and complex areas such as coastal water, harbors, and wharfs. This paper presents a practical occupancy grid-based method based on forward-looking sonar for AUV. The algorithm uses an extended Kalman filter (EKF) to estimate the AUV motion states. First, the SLAM method fuses the data coming from the navigation sensors to predict the motion states. Subsequently, a novel particle swarm optimization genetic algorithm (PSO-GA) scan matching method is employed for matching the sonar scan data and grid map, and the matching pose would be used to correct the prediction states. Lastly, the estimated motion states and sonar scan data would be used to update the grid map. The experimental results based on the field data have validated that the proposed SLAM algorithm is adaptable to underwater conditions, and accurate enough to use for ocean engineering practical applications.

The Hilti SLAM Challenge Dataset

Research in Simultaneous Localization and Mapping (SLAM) has made outstanding progress over the past years. SLAM systems are nowadays transitioning from academic to real world applications. However, this transition has posed new demanding challenges in terms of accuracy and robustness. To develop new SLAM systems that can address these challenges, new datasets containing cutting-edge hardware and realistic scenarios are required. We propose the Hilti SLAM Challenge Dataset. Our dataset contains indoor sequences of offices, labs, and construction environments and outdoor sequences of construction sites and parking areas. All these sequences are characterized by featureless areas and varying illumination conditions that are typical in real-world scenarios and pose great challenges to SLAM algorithms that have been developed in confined lab environments. Accurate sparse ground truth, at millimeter level, is provided for each sequence. The sensor platform used to record the data includes a number of visual, lidar, and inertial sensors, which are spatially and temporally calibrated. The purpose of this dataset is to foster the research in sensor fusion to develop SLAM algorithms that can be deployed in tasks where high accuracy and robustness are required, e.g., in construction environments. Many academic and industrial groups tested their SLAM systems on the proposed dataset in the Hilti SLAM Challenge. The results of the challenge, which are summarized in this paper, show that the proposed dataset is an important asset in the development of new SLAM algorithms that are ready to be deployed in the real-world.

Simultaneous Localization and Mapping: Through the Lens of Nonlinear Optimization

Simultaneous Localization and Mapping (SLAM) algorithms perform visual-inertial estimation via filtering or batch optimization methods. Empirical evidence suggests that filtering algorithms are computationally faster, while optimization methods are more accurate. This work presents an optimization-based framework that unifies these approaches, and allows users to flexibly implement different design choices, e.g., the number and types of variables maintained in the algorithm at each time. We prove that filtering methods correspond to specific design choices in our generalized framework. We then reformulate the Multi-State Constrained Kalman Filter (MSCKF) and contrast its performance with that of sliding-window based filters. Our approach modularizes state-of-the-art SLAM algorithms to allow for adaptation to various scenarios. Experiments on the EuRoC MAV dataset verify that our implementations of these algorithms are competitive with the performance of off-the-shelf implementations in the literature. Using these results, we explain the relative performance characteristics of filtering and batch-optimization based algorithms in the context of our framework. We illustrate that under different design choices, our empirical performance interpolates between those of state-of-the-art approaches.

$\mathcal {PLC}$-LiSLAM: LiDAR SLAM With Planes, Lines, and Cylinders

Planes, lines, and cylinders widely exist in man-made environments. This letter introduces a LiDAR simultaneous localization and mapping (SLAM) system using those three types of landmarks. Our algorithm has three components including local mapping, global mapping, and localization. The local and global mapping jointly adjust planes, lines, and cylinders with LiDAR poses to minimize the point-to-model cost, which is referred to as plane-line-cylinder adjustment (PLCA). We prove that, with some preprocessing, PLCA is independent of the number of points captured from the three types of landmarks, which makes efficiently solving a large-scale PLCA problem feasible. The localization component conducts real-time pose estimation through registering local planes, lines, and cylinders to the global ones, which is referred to as plane-line-cylinder registration (PLCR). We present an efficient solution for PLCR. The detection and data association may introduce errors. We correct these errors through checking the cost in the back-end. It is difficult for the registration-based algorithm, such as LOAM and ICP, to correct these errors, as they do not maintain the data association. Experimental results show that out algorithm outperforms the state-of-the-art LiDAR SLAM algorithms and achieves real-time performance.

EKF-LOAM: An Adaptive Fusion of LiDAR SLAM With Wheel Odometry and Inertial Data for Confined Spaces With Few Geometric Features

A precise localization system and a map that properly represents the environment are fundamental for several robotic applications. Traditional LiDAR SLAM algorithms are particularly susceptible to underestimating the distance covered by real robots in environments with few geometric features. Common industrial confined spaces, such as ducts and galleries, have long and homogeneous structures, which are difficult to map. In this paper, we propose a novel approach, the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">EKF-LOAM</i> , which fuses wheel odometry and IMU (Inertial Measurement Unit) data into the LeGO-LOAM algorithm using an Extended Kalman Filter. For that, the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">EKF-LOAM</i> uses a simple and lightweight adaptive covariance matrix based on the number of detected geometric features. Simulated and real-world experiments with the EspeleoRobô, a service robot designed to inspect confined places, show that the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">EKF-LOAM</i> method reduces the underestimating problem, with improvements greater than 50% when compared to the original LeGO-LOAM algorithm. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —This paper is motivated by the challenges of autonomous navigation for mobile ground robots within confined and unstructured environments. Here, we propose a data fusion framework that uses common sensors (such as LiDARs, wheel odometry, and inertial devices) to improve the simultaneous localization and mapping (SLAM) capabilities of a robot without GPS and compass. This approach does not need artificial landmarks nor ideal light and, in scenarios with few geometric features, increases the performance of LiDAR SLAM techniques based on edge and planar features. We also provide a robust controller for the autonomous navigation of the robot during the mapping of a tunnel. Experiments carried out in simulation and real-world confined places show the effectiveness of our approach. In future work, we shall incorporate other sensors, such as cameras, to improve the SLAM process.

LiDAR Odometry by Deep Learning-Based Feature Points with Two-Step Pose Estimation

An accurate ego-motion estimation solution is vital for autonomous vehicles. LiDAR is widely adopted in self-driving systems to obtain depth information directly and eliminate the influence of changing illumination in the environment. In LiDAR odometry, the lack of descriptions of feature points as well as the failure of the assumption of uniform motion may cause mismatches or dilution of precision in navigation. In this study, a method to perform LiDAR odometry utilizing a bird’s eye view of LiDAR data combined with a deep learning-based feature point is proposed. Orthographic projection is applied to generate a bird’s eye view image of a 3D point cloud. Thereafter, an R2D2 neural network is employed to extract keypoints and compute their descriptors. Based on those keypoints and descriptors, a two-step matching and pose estimation is designed to keep these feature points tracked over a long distance with a lower mismatch ratio compared to the conventional strategy. In the experiment, the evaluation of the proposed algorithm on the KITTI training dataset demonstrates that the proposed LiDAR odometry can provide more accurate trajectories compared with the handcrafted feature-based SLAM (Simultaneous Localization and Mapping) algorithm. In detail, a comparison of the handcrafted descriptors is demonstrated. The difference between the RANSAC (Random Sample Consensus) algorithm and the two-step pose estimation is also demonstrated experimentally. In addition, the data collected by Velodyne VLP-16 is also evaluated by the proposed solution. The low-drift positioning RMSE (Root Mean Square Error) of 4.70 m from approximately 5 km mileage shown in the result indicates that the proposed algorithm has generalization performance on low-resolution LiDAR.

A PRIMARY TEST RESULTS OF A HANDHELD MOBILE LASER SCANNER IN EXTRACTION OF TREE PARAMETERS

Abstract. Sustainable forest planning and management require accurate and precise information about the estimation of forest resources. In particular, two tree parameters are very important among the others: diameter-at-breast height (DBH) and height that are used to estimate the volume and biomass of the tree. With the development of Remote Sensing (RS), information about the tree parameters can be acquired in more accurately and precisely with laser scanning technology. In this study, a Handheld Mobile Laser Scanner (HMLS), called TORCH, was tested for extracting tree parameters with 3D Forest software. The TORCH uses the SLAM (Simultaneous Localization and Mapping) algorithm to locate the scanner in an unknown environment and register the obtained 3D point clouds. Estimated DBH and height parameters from HMLS data extracted using 3D Forest software were compared with the field measurements (i.e., reference data). The preliminary results of the study showed that estimated DBH from HMLS data were relatively higher than ground measurement, while estimated height from point clouds data was slightly lower than the reference data. The continuous improvement in mobile laser scanners will improve the success of the devices while acquiring 3D structural information of tree parameters and reducing the cost and time spent in forest inventory.

THE USE OF A WIDE FOV LASER SCANNING SYSTEM AND A SLAM ALGORITHM FOR MOBILE APPLICATIONS

Abstract. This paper presents the assessment of a wide-angle laser scanner and a simultaneous localisation and mapping (SLAM) algorithm to estimate the trajectory and generate a 3D map of the environment. A backpack platform composed of an OS0-128 Ouster (FoV 90° × 360°) laser scanner was used to acquire laser data in an area with urban and forest features. Web SLAM, an online SLAM algorithm implemented by Ouster, Inc., was used to estimate the trajectory and generate a 3D map in a local reference system. Then, the 3D point clouds were transformed into the ground coordinate system with a rigid body transformation. Three datasets were used: (I) the entire trajectory consisting of forwarding and backwards paths, (II) only forward path, and (III) only backward path. Visual analysis showed a double mapping error in the point cloud of dataset I. Therefore, the point cloud registration was performed only for datasets II and III, achieving a centimetric accuracy, which is compatible with the OS0-128 laser scanner accuracy (∼5cm).

APPLICATION OF RGB-D SLAM IN 3D TUNNEL RECONSTRUCTION BASED ON SUPERPIXEL AIDED FEATURE TRACKING

Abstract. In large-scale projects such as hydropower and transportation, the real-time acquisition and generation of the 3D tunnel model can provide an important basis for the analysis and evaluation of the tunnel stability. The Simultaneous Localization And Mapping (SLAM) technology has the advantages of low cost and strong real-time, which can greatly improve the data acquisition efficiency during tunnel excavation. Feature tracking and matching are critical processes of traditional 3D reconstruction technologies such as Structure from Motion (SfM) and SLAM. However, the complicated rock mass structures on the tunnel surface and the limited lighting environment make feature tracking and matching difficult. Manhattan SLAM is a technology integrating superpixels and Manhattan world assumptions, in which both line features and planar features can be better extracted. Rock mass discontinuities including traces and structural planes are distributed on the inner surface of tunnels, which can be extracted for feature tracking and matching. Therefore, this paper proposes a 3D reconstruction pipeline for tunnels, in which, the Manhattan SLAM algorithm is applied for camera pose parameters estimation and the sparse point cloud generation, and the Patch-based Multi-View Stereo (PMVS) is adopted for dense reconstruction. In this paper, the Azure Kinect DK sensor is used for data acquisition. Experiments are proceeded and the results show that the proposed pipeline based on Manhattan SLAM and PMVS performs good robustness and feasibility for tunnels 3D reconstruction.

Mobile Robot Localization and Mapping Algorithm Based on the Fusion of Image and Laser Point Cloud.

Given the lack of scale information of the image features detected by the visual SLAM (simultaneous localization and mapping) algorithm, the accumulation of many features lacking depth information will cause scale blur, which will lead to degradation and tracking failure. In this paper, we introduce the lidar point cloud to provide additional depth information for the image features in estimating ego-motion to assist visual SLAM. To enhance the stability of the pose estimation, the front-end of visual SLAM based on nonlinear optimization is improved. The pole error is introduced in the pose estimation between frames, and the residuals are calculated according to whether the feature points have depth information. The residuals of features reconstruct the objective function and iteratively solve the robot’s pose. A keyframe-based method is used to optimize the pose locally in reducing the complexity of the optimization problem. The experimental results show that the improved algorithm achieves better results in the KITTI dataset and outdoor scenes. Compared with the pure visual SLAM algorithm, the trajectory error of the mobile robot is reduced by 52.7%. The LV-SLAM algorithm proposed in this paper has good adaptability and robust stability in different environments.

A Robust 2D Lidar SLAM Method in Complex Environment

The two-dimensional (2D) lidar is a ranging optical sensor that can measure the cross-section of the geometric structure of the environment. We propose a robust 2D lidar simultaneous localization and mapping (SLAM) algorithm working in ambiguous environments. To improve the front-end scan-matching module’s accuracy and robustness, we propose performing degeneration analysis, line landmark tracking, and environment coverage analysis. The max-clique selection and odometer verification are introduced to increase the stability of the SLAM algorithm in an ambiguous environment. Moreover, we propose a tightly coupled framework that integrates lidar, wheel odometer, and inertial measurement unit (IMU). The framework achieves the accurate mapping in large-scale environments using a factor graph to model the multi-sensor fusion SLAM problem. The experimental results demonstrate that the proposed method achieves a highly accurate front-end scan-matching module with an error of 3.8% of the existing method. And it can run stably in ambiguous environments where the existing method will be failed. Moreover, it ccan successfully construct a map with an area of more than 250 000 square meters.

A Tightly Coupled LiDAR-Inertial SLAM for Perceptually Degraded Scenes.

Realizing robust six degrees of freedom (6DOF) state estimation and high-performance simultaneous localization and mapping (SLAM) for perceptually degraded scenes (such as underground tunnels, corridors, and roadways) is a challenge in robotics. To solve these problems, we propose a SLAM algorithm based on tightly coupled LiDAR-IMU fusion, which consists of two parts: front end iterative Kalman filtering and back end pose graph optimization. Firstly, on the front end, an iterative Kalman filter is established to construct a tightly coupled LiDAR-Inertial Odometry (LIO). The state propagation process for the a priori position and attitude of a robot, which uses predictions and observations, increases the accuracy of the attitude and enhances the system robustness. Second, on the back end, we deploy a keyframe selection strategy to meet the real-time requirements of large-scale scenes. Moreover, loop detection and ground constraints are added to the tightly coupled framework, thereby further improving the overall accuracy of the 6DOF state estimation. Finally, the performance of the algorithm is verified using a public dataset and the dataset we collected. The experimental results show that for perceptually degraded scenes, compared with existing LiDAR-SLAM algorithms, our proposed algorithm grants the robot higher accuracy, real-time performance and robustness, effectively reducing the cumulative error of the system and ensuring the global consistency of the constructed maps.

크레인 충돌 방지를 위한 특징 추출 기반의 SLAM 기법

There is an increasing need for Simultaneous Localization and Mapping (SLAM) technology due to the recent demand for autonomous driving, metaverse, and augmented reality (AR) technologies. On industrial sites, demands for SLAM technologies that accurately estimate locations and generate precise maps of surrounding areas are becoming increasingly important for collision prevention between cranes. The research in this paper proposes a SLAM technology based on feature extraction techniques that create a precise map of the workspace in an industrial site by attaching a double-axis rotary Lidar to a tower crane. This configuration compensates for the limitation in single-axis rotary Lidar’s detection range. The double-axis rotary Lidar has a wider detection range than rotary Lidar, but the distribution of the collected data is irregular due to shaking and the difference in rotational speeds of the two motors in separate axes. SLAM techniques, including feature extraction and motion estimation suitable for these data characteristics, were introduced to aid in improving these data irregularities. Even when the SLAM algorithm operates accurately, the presence of afterimages from a dynamic object on the map can prevent effective collision performance and result in an inaccurate representation of the workspace. This paper explores an algorithm that effectively removes afterimages by scoring all the points collected by Lidar. The performance accuracy of the proposed SLAM method was evaluated by comparing the results of Mapping with those of conventional LOAM and G-ICP processes using data from attaching double-axis Lidar to the tower crane.

Semantic SLAM Based on Deep Learning in Endocavity Environment

Traditional endoscopic treatment methods restrict the surgeon’s field of view. New approaches to laparoscopic visualization have emerged due to the advent of robot-assisted surgical techniques. Lumen simultaneous localization and mapping (SLAM) technology can use the image sequence taken by the endoscope to estimate the pose of the endoscope and reconstruct the lumen scene in minimally invasive surgery. This technology gives the surgeon better visual perception and is the basis for the development of surgical navigation systems as well as medical augmented reality. However, the movement of surgical instruments in the internal cavity can interfere with the SLAM algorithm, and the feature points extracted from the surgical instruments may cause errors. Therefore, we propose a modified endocavity SLAM method combined with deep learning semantic segmentation that introduces a convolution neural network based on U-Net architecture with a symmetric encoder–decoder structure in the visual odometry with the goals of solving the binary segmentation problem between surgical instruments and the lumen background and distinguishing dynamic feature points. Its segmentation performance is improved by using pretrained encoders on the network model to obtain more accurate pixel-level instrument segmentation. In this setting, the semantic segmentation is used to reject the feature points on the surgical instruments and reduce the impact caused by dynamic surgical instruments. This can provide more stable and accurate mapping results compared to ordinary SLAM systems.

CNN-Based Dense Monocular Visual SLAM for Real-Time UAV Exploration in Emergency Conditions

Unmanned Aerial Vehicles (UAVs) for 3D indoor mapping applications are often equipped with bulky and expensive sensors, such as LIDAR (Light Detection and Ranging) or depth cameras. The same task could be also performed by inexpensive RGB cameras installed on light and small platforms that are more agile to move in confined spaces, such as during emergencies. However, this task is still challenging because of the absence of a GNSS (Global Navigation Satellite System) signal that limits the localization (and scaling) of the UAV. The reduced density of points in feature-based monocular SLAM (Simultaneous Localization and Mapping) then limits the completeness of the delivered maps. In this paper, the real-time capabilities of a commercial, inexpensive UAV (DJI Tello) for indoor mapping are investigated. The work aims to assess its suitability for quick mapping in emergency conditions to support First Responders (FR) during rescue operations in collapsed buildings. The proposed solution only uses images in input and integrates SLAM and CNN-based (Convolutional Neural Networks) Single Image Depth Estimation (SIDE) algorithms to densify and scale the data and to deliver a map of the environment suitable for real-time exploration. The implemented algorithms, the training strategy of the network, and the first tests on the main elements of the proposed methodology are reported in detail. The results achieved in real indoor environments are also presented, demonstrating performances that are compatible with FRs’ requirements to explore indoor volumes before entering the building.

Loop Closure Detection Based on Image Semantic Segmentation in Indoor Environment

When mobile robots run in indoor environment, a large number of similar images are easy to appear in the images collected, probably causing false-positive judgment in loop closure detection based on simultaneous localization and mapping (SLAM). To solve this problem, a loop closure detection algorithm for visual SLAM based on image semantic segmentation is proposed in this paper. Specifically, the current frame is semantically segmented by optimized DeepLabv3+ model to obtain semantic labels in the image. The 3D semantic node coordinates corresponding to each semantic label are then extracted by combining mask centroid and image depth information. According to the distribution of semantic nodes, the DBSCAN density clustering algorithm is adopted to cluster densely distributed semantic nodes to avoid mismatching due to the close distance of semantic nodes in the subsequent matching process. Finally, the multidimensional similarity comparison of first rough and then fine is adopted to screen the candidate frames of loop closure from key frames and then confirm the real loop closure to complete accurate loop closure detection. Testing with public datasets and self-filmed datasets, experimental results show that being well adapted to illumination change, viewpoint deviation, and item movement or missing, the proposed algorithm can effectively improve the accuracy of loop closure detection in indoor environment.

Robust Object-Level Semantic Visual SLAM Using Semantic Keypoints

Simultaneous Localization and Mapping (SLAM) has traditionally relied on representing the environment as low-level, geometric features, such as points, lines, and planes. Recent advances in object recognition capabilities, however, as well as demand for environment representations that facilitate higher-level autonomy, have motivated an object-based Semantic SLAM. We present a Semantic SLAM algorithm that directly incorporates a sparse representation of objects into a factor-graph SLAM optimization, resulting in a system that is efficient, robust to varying object shapes and environments, and easy to incorporate into an existing SLAM pipeline. Our keypoint-based representation facilitates robust detection in varying conditions and intraclass shape variation, as well as computational efficiency. We demonstrate the performance of our algorithm in two different SLAM systems and in varying environments.

Autonomous Navigation System of Greenhouse Mobile Robot Based on 3D Lidar and 2D Lidar SLAM.

The application of mobile robots is an important link in the development of intelligent greenhouses. In view of the complex environment of a greenhouse, achieving precise positioning and navigation by robots has become the primary problem to be solved. Simultaneous localization and mapping (SLAM) technology is a hot spot in solving the positioning and navigation in an unknown indoor environment in recent years. Among them, the SLAM based on a two-dimensional (2D) Lidar can only collect the environmental information at the level of Lidar, while the SLAM based on a 3D Lidar demands a high computation cost; hence, it has higher requirements for the industrial computers. In this study, the robot navigation control system initially filtered the information of a 3D greenhouse environment collected by a 3D Lidar and fused the information into 2D information, and then, based on the robot odometers and inertial measurement unit information, the system has achieved a timely positioning and construction of the greenhouse environment by a robot using a 2D Lidar SLAM algorithm in Cartographer. This method not only ensures the accuracy of a greenhouse environmental map but also reduces the performance requirements on the industrial computer. In terms of path planning, the Dijkstra algorithm was used to plan the global navigation path of the robot while the Dynamic Window Approach (DWA) algorithm was used to plan the local navigation path of the robot. Through the positioning test, the average position deviation of the robot from the target positioning point is less than 8 cm with a standard deviation (SD) of less than 3 cm; the average course deviation is less than 3° with an SD of less than 1° at the moving speed of 0.4 m/s. The robot moves at the speed of 0.2, 0.4, and 0.6 m/s, respectively; the average lateral deviation between the actual movement path and the target movement path is less than 10 cm, and the SD is less than 6 cm; the average course deviation is <3°, and the SD is <1.5°. Both the positioning accuracy and the navigation accuracy of the robot can meet the requirements of mobile navigation and positioning in the greenhouse environment.