Simultaneous Localization And Mapping Techniques Research Articles

Improving SLAM Techniques with Integrated Multi-Sensor Fusion for 3D Reconstruction.

Simultaneous Localization and Mapping (SLAM) poses distinct challenges, especially in settings with variable elements, which demand the integration of multiple sensors to ensure robustness. This study addresses these issues by integrating advanced technologies like LiDAR-inertial odometry (LIO), visual-inertial odometry (VIO), and sophisticated Inertial Measurement Unit (IMU) preintegration methods. These integrations enhance the robustness and reliability of the SLAM process for precise mapping of complex environments. Additionally, incorporating an object-detection network aids in identifying and excluding transient objects such as pedestrians and vehicles, essential for maintaining the integrity and accuracy of environmental mapping. The object-detection network features a lightweight design and swift performance, enabling real-time analysis without significant resource utilization. Our approach focuses on harmoniously blending these techniques to yield superior mapping outcomes in complex scenarios. The effectiveness of our proposed methods is substantiated through experimental evaluation, demonstrating their capability to produce more reliable and precise maps in environments with variable elements. The results indicate improvements in autonomous navigation and mapping, providing a practical solution for SLAM in challenging and dynamic settings.

Current status and future prospects of SLAM technology in the field of blind navigation

This comprehensive review paper explores the progressive integration of Simultaneous Localization and Mapping (SLAM) technology within the realm of blind navigation. The study delves into the current landscape of research and practical implementations where SLAM techniques are harnessed to empower visually impaired individuals in navigating their surroundings. The paper takes a focused approach by elucidating the advancements achieved through RGB-D-based SLAM navigation systems and the intriguing developments within the realm of LSD-SLAM-based navigation. A paramount facet of this exploration involves the design and deployment of interactive devices that bridge the gap between blind individuals and navigation systems. Notably, the paper examines the intricacies of these interaction interfaces, highlighting their pivotal role in enhancing the efficacy and user-friendliness of SLAM-driven navigation. Furthermore, this review critically assesses the existing limitations that persist within the current application of SLAM technology for blind navigation. The discussion encompasses challenges related to environmental diversity, real-time processing constraints, and the need for robustness in complex scenarios. By acknowledging these limitations, the paper paves the way for a comprehensive examination of potential avenues for refinement and enhancement. In conclusion, this paper serves as a comprehensive guide to the progressive incorporation of SLAM technology into blind navigation. It underscores the transformative potential of RGB-D and LSD-SLAM systems, underscores the significance of interaction interfaces, and underscores the evolving trajectory towards a more inclusive and efficient navigation solution for the visually impaired.

Promising SLAM Methods for Automated Guided Vehicles and Autonomous Mobile Robots

Autonomous Mobile Robots, as the advanced version of Automated Guided Vehicles have received a lot of interest and recognition in recent years. Simultaneous Localization and Mapping (SLAM) techniques enable the vehicles to independently navigate and map their surroundings so that they can drive autonomously in changing and uncharted areas. Due to the increasing importance and contributive development of SLAMs for automated guided vehicles and autonomous mobile robots, this study seeks to provide an in-depth analysis of well-known SLAM techniques developed and applied during the previous ten years. Well-known SLAM algorithms considered in this paper include GMapping, Cartographer, LIO-SAM, and so on. They are mainly examined and compared from the viewpoints of basic principles, sensor requirements, computing complexity, and performance. The aim of this paper is to offer insights into various SLAM approaches to researchers, practitioners, and developers in the field of automated guided vehicles and autonomous mobile robots, facilitating the selection of suitable SLAM methods for specific applications and fostering innovation in autonomous navigation and mapping.

Researches advanced in path planning to indoor fire escape and rescue based on SLAM

Helping trapped people understand the external situation and provide navigation to escape the fire is the key to reducing fire casualties. Thanks to the rapid development of artificial intelligence technology, the combination of simultaneous localization and mapping (SLAM) and path planning technology has gradually become a new research hotspot, which can help provide on-site fire information, maps and navigation for trapped people and firefighters. However, improving the accuracy of SLAM techniques under harsh conditions (e.g., thick smoke, high temperature) is still an open topic. Focusing on SLAM noise reduction and path planning, in this paper, we detail the latest research progress of SLAM technology in fire escape assistance. Specifically, we first introduce the current development and application frontiers of SLAM technology, and then analyze and compare the application of SLAM technology in fire scenarios. In addition, the performance changes of the two continuous A* algorithms and the RRT algorithm during global path planning for fire scenarios are compared. Finally, we discuss the development trend of SLAM in future fire escape and rescue.

A multi-sensor fusion framework with tight coupling for precise positioning and optimization

In the dynamic landscape of artificial intelligence and robotics, the pursuit of accurate positioning in mobile robots has intensified. This research addresses the limitations of single-sensor SLAM (Simultaneous Localization and Mapping) techniques in complex settings by harnessing the collective strengths of LiDAR (Light Detection And Ranging), Camera, IMU (Inertial Measurement Unit), and GNSS (Global Navigation Satellite System) sensors. The proposed multi-sensor tightly-coupled SLAM framework is an integration of point-line feature-based laser–visual–inertial odometry, visual–laser fusion loop closure detection, and factor graph-based back-end optimization. Within the visual–inertial subsystem, an advanced LSD (Line Segment Detector) feature extraction strategy is introduced, incorporating point-line fusion to enhance visual line features. Additionally, the laser point cloud is projected onto the camera coordinate system, establishing depth associations with visual attributes. Strengthening the robustness of the visual–inertial subsystem in low-texture environments, camera poses undergo optimization through a sliding-window bundle adjustment method. In the laser-inertial subsystem, IMU preintegration mitigates laser point cloud distortion. Extracting edge and plane features, coupled with frame-to-local-map matching, enhances matching efficiency while streamlining computational intricacies. This amalgamation forms the basis of the laser–visual–inertial odometry fusion system. To overcome the limitations of standalone visual and laser-based loop closure detection, a dual-loop closure method utilizing visual–laser fusion is proposed. Leveraging the DBoW2 bag-of-words model, complemented by temporal–spatial consistency checks, enhances detection efficiency and accuracy. The integration of GNSS factors imparts global constraints for expansive outdoor scenarios. Employing factor graph-based back-end optimization, the refinement of laser–visual–inertial odometry factors, visual–inertial odometry factors, IMU preintegration factors, loop closure factors, and GNSS factors culminates in precise global pose estimation and high-fidelity point cloud maps. Through rigorous evaluation of the M2DGR dataset and a mobile robot platform, the proposed methodology emerges as an exemplar of performance, showcasing superiority over the state-of-the-art LIO-SAM technique. Achieving a reduction of 2.86m and 3.23m in the root mean square error of absolute pose estimation across divergent environments, this approach exhibits remarkable efficacy in outdoor scenarios, thereby elevating the precision and resilience of SLAM algorithms for mobile robots.

Simultaneous Localization and Mapping and Tag-Based Navigation for Unmanned Aerial Vehicles

This paper presents navigation techniques for an Unmanned Aerial Vehicle (UAV) in a virtual simulation of an indoor environment using Simultaneous Localization and Mapping (SLAM) and April Tag markers to reach a target destination. In many cases, UAVs can access locations that are inaccessible to people or regular vehicles in indoor environments, making them valuable for surveillance purposes. This study employs the Robot Operating System (ROS) to simulate SLAM techniques using LIDAR and GMapping packages for UAV navigation in two different environments. In the Tag-based simulation, the input topic for April Tag in ROS is camera images, and the calibration of position with a tag is done through assigning a message to each ID and its marker image. On the other hand, navigation in SLAM was achieved using a global and local planner algorithm. For localization, an Adaptive Monte-Carlo Localization (AMCL) technique has been used to identify factors contributing to inconsistent mapping results, such as heavy computational load, grid mapping accuracy, and inadequate UAV localization. Furthermore, this study analyzed the April Tag-based navigation algorithm, which showed satisfactory outcomes due to its lighter computing requirements. It can be ascertained that by using ROS packages, the simulation of SLAM and Tag-based UAV navigation inside a building can be achieved.

SLAM-based technology to improve the impact of uneven illumination on minimally invasive surgery

Due to developments in surgery, minimally invasive surgery (MIS) has become a common choice for surgical patients. Because of the small surgical incision in MIS, its postoperative effects will be less fat liquefaction, infection, splitting, numbness of the incision and weakness of the healing abdominal wall muscles compared to traditional surgery. However, many bottlenecks have been encountered in MIS, such as uneven illumination affecting the recognition of organ images. In other words, such problems are about improving the ability of Simultaneous Localization and Mapping (SLAM) to extract information about the environment. This paper summarises some relevant research on SLAM improvement methods. Scientists are now looking for more suitable methods for constructing maps of the human internal environment, including improvements on existing SLAM techniques. In the context of SLAM, what SLAM is and the history of SLAM is described. Traditional SLAM methods as well as SLAM improvement methods are also mentioned. Finally, its advantages and disadvantages are discussed, and its prospects are predicted.

Neural Network-Based Recent Research Developments in SLAM for Autonomous Ground Vehicles: A Review

The development of autonomous vehicles has prompted an interest in exploring various techniques in navigation. One such technique is simultaneous localization and mapping (SLAM), which enables a vehicle to comprehend its surroundings, build a map of the environment in real-time, and locate itself within that map. Although traditional techniques have been used to perform SLAM for a long time, recent advancements have seen the incorporation of neural network techniques into various stages of the SLAM pipeline. This review paper provides a focused analysis of the recent developments in neural network techniques for SLAM-based localization of autonomous ground vehicles. In contrast to the previous review studies that covered general navigation and SLAM techniques, this work specifically addresses the unique challenges and opportunities presented by the integration of neural networks in this context. Existing review studies have highlighted the limitations of conventional visual SLAM, and this paper aims to explore the potential of deep learning methods. The paper discusses the functions required for localization, as well as several neural network-based techniques proposed by researchers to carry out such functions, are discussed. Firstly, it presents a general background of the issue, the relevant review studies that have already been done, and the adopted methodology in this review. Then, it provides a thorough review of the findings regarding localization and odometry. Finally, it presents our analysis of the findings, open research questions in the field, and a conclusion. A semi-systematic approach is used to carry out the review.

FADM-SLAM: a fast and accurate dynamic intelligent motion SLAM for autonomous robot exploration involving movable objects

PurposeMany popular simultaneous localization and mapping (SLAM) techniques have low accuracy, especially when localizing environments containing dynamically moving objects since their presence can potentially cause inaccurate data associations. To address this issue, the proposed FADM-SLAM system aims to improve the accuracy of SLAM techniques in environments containing dynamically moving objects. It uses a pipeline of feature-based approaches accompanied by sparse optical flow and multi-view geometry as constraints to achieve this goal.Design/methodology/approachFADM-SLAM, which works with monocular, stereo and RGB-D sensors, combines an instance segmentation network incorporating an intelligent motion detection strategy (iM) with an optical flow technique to improve location accuracy. The proposed AS-SLAM system comprises four principal modules, which are the optical flow mask and iM, the ego motion estimation, dynamic point detection and the feature-based extraction framework.FindingsExperiment results using the publicly available RGBD-Bonn data set indicate that FADM-SLAM outperforms established visual SLAM systems in highly dynamic conditions.Originality/valueIn summary, the first module generates the indication of dynamic objects by using the optical flow and iM with geometric-wise segmentation, which is then used by the second module to compute the starting point of a posture. The third module, meanwhile, first searches for the dynamic feature points in the environment, and second, eliminates them from further processing. An algorithm based on epipolar constraints is implemented to do this. In this way, only the static feature points are retained, which are then fed to the fourth module for extracting important features.

Localization and tracking of stationary users for augmented reality

In augmented reality applications it is essential to know the position and orientation of the user to correctly register virtual 3D content in the user’s field of view. For this purpose, visual tracking through simultaneous localization and mapping (SLAM) is often used. However, when applied to the commonly occurring situation where the users are mostly stationary, many methods presented in previous research have two key limitations. First, SLAM techniques alone do not address the problem of global localization with respect to prior models of the environment. Global localization is essential in many applications where multiple users are expected to track within a shared space, such as spectators at a sporting event. Secondly, these methods often assume significant translational movement to accurately reconstruct and track from a local model of the environment, causing challenges for many stationary applications. In this paper, we extend recent research on Spherical Localization and Tracking to support relocalization after tracking failure, as well as global localization in large shared environments, and optimize the method for operation on mobile hardware. We also evaluate various state-of-the-art localization approaches, the robustness of our visual tracking method, and demonstrate the effectiveness of our system in real-life scenarios.

Accuracy Evaluation and Branch Detection Method of 3D Modeling Using Backpack 3D Lidar SLAM and UAV-SfM for Peach Trees during the Pruning Period in Winter

In the winter pruning operation of deciduous fruit trees, the number of pruning branches and the structure of the main branches greatly influence the future growth of the fruit trees and the final harvest volume. Terrestrial laser scanning (TLS) is considered a feasible method for the 3D modeling of trees, but it is not suitable for large-scale inspection. The simultaneous localization and mapping (SLAM) technique makes it possible to move the lidar on the ground and model quickly, but it is not useful enough for the accuracy of plant detection. Therefore, in this study, we used UAV-SfM and 3D lidar SLAM techniques to build 3D models for the winter pruning of peach trees. Then, we compared and analyzed these models and further proposed a method to distinguish branches from 3D point clouds by spatial point cloud density. The results showed that the 3D lidar SLAM technique had a shorter modeling time and higher accuracy than UAV-SfM for the winter pruning period of peach trees. The method had the smallest RMSE of 3084 g with an R2 = 0.93 compared to the fresh weight of the pruned branches. In the branch detection part, branches with diameters greater than 3 cm were differentiated successfully, regardless of whether before or after pruning.

Performance Evaluation of ROS-Based SLAM Algorithms for Handheld Indoor Mapping and Tracking Systems

Simultaneous localization and mapping (SLAM) is an important field of work not only in robotics, but also in mobile platforms. This research work provides insights into how SLAM techniques are deployed in an indoor environment to aid first responders with their duties. Due to the hazardous nature of the environment and the need for sensitivity due to the potential involvement of human subjects, autonomous robots cannot be used. So, the first responders must carry the scanning equipment and perform SLAM at the same time. As a result, unlike standard robot platforms, there will be no reliable odometry source, and SLAM will have to deal with the user’s unpredictable movement. In this work, we compare and examine robotic operating system (ROS)-based SLAM approaches without using any odometry for their application in the above-mentioned circumstances. Gmapping, HectorSLAM, and Cartographer have been chosen as the candidates for this evaluation. We evaluated these approaches in two different environments: a lab office and a long corridor. The research results show that Cartographer outperforms the other two techniques in our test setup in terms of map quality and trajectory tracking. The Cartographer’s mapping error ranged from 0.017 to 0.3548 m.

A Review of quadrotor UAV: Control and SLAM methodologies ranging from conventional to innovative approaches

There are two indispensable methodologies for autonomous flights performed by unmanned aerial vehicles (UAV). The first is flight control, and the other is simultaneous localization and mapping (SLAM). In the literature, these two issues are generally considered separately. However, they have very close relationships with each other. In this study, both methods were extensively examined in the literature, especially for quadrotors. Quadrotors, also known as quadrotors, are rotary-wing UAVs capable of vertical take-off and landing. As their use becomes widespread worldwide, the number of studies conducted to enable autonomous tasks is growing. The study was prepared under three subtitles. First, a fast and simple introduction of quadrotors was made, and the advances in this area were discussed. In the next section, studies on the position, attitude, and altitude control methods required for the autonomous use of such aircraft are analyzed based on linear, nonlinear, and intelligent methods. As the third subheading, research on SLAM techniques was widely discussed. Frequently used performance metrics, application environments, and results were presented in detailed tables for studies in both areas. Comparative studies were particularly emphasized, and the best results obtained were expressed in tables. The hardware implementations of the mentioned applications were also reviewed. Thus, hardware and method-based quick reference resource were created for researchers. As a consequence, the objective of this research is to provide a comprehensive resource for researchers working on quadrotor navigation systems to effectively select the flight control and SLAM methods they will employ.

A SLAM Method Based on Multi-Robot Cooperation for Pipeline Environments Underground

SLAM (simultaneous localization and mapping) technology has recently shown considerable forward progress; however, most of the mainstream SLAM technologies are currently based on laser- and vision-based fusion strategies. However, there are problems (e.g., a lack of geometric structure, no significant feature points in the surrounding environment, LiDAR degradation, and the longitudinal loss of constraints, as well as missing GPS signals within the pipeline) in special circumstances (e.g., in underground pipelines and tunnels), thus making it difficult to apply laser or vision SLAM techniques. To solve this issue, a multi-robot cooperation-based SLAM method is proposed in this study for pipeline environments, based on LIO-SAM. The proposed method can effectively perform SLAM tasks in spaces with high environmental similarity (e.g., tunnels), thus overcoming the limitation that existing SLAM methods have been poorly applied in pipeline environments due to the high environmental similarity. In this study, the laser-matching part of the LIO-SAM is removed, and a high-precision differential odometer, IMU inertial navigation sensor, and an ultrasonic sensor, which are not easily affected by the high similarity of the environment, are employed as the major sources of positioning information. Moreover, a front-to-back queue of two robots is trained in the pipeline environment; a unique period-creep method has been designed as a cooperation strategy between the two robots, and a multi-robot pose constraint factor (ultrasonic range factor) is built to constrain the robots’ relative poses. On that basis, the robot queue can provide a mutual reference when traveling through the pipeline and fulfill its pose correction with high quality, thus achieving high positioning accuracy. To validate the method presented in this study, four experiments were designed, and SLAM testing was performed in common environments, as well as simple and complex urban pipeline environments. Next, error analysis was conducted using EVO. The experimental results suggest that the method proposed in this study is less susceptible to environmental effects than the existing methods due to the benefits of multi-robot cooperation. This applies to a common environment (e.g., a room) and can achieve a good performance; this means that a wide variety of piping environments can be established with high similarity. The average error of SLAM in the pipeline was 0.047 m, and the maximum error was 0.713 m, such that the proposed method shows the advantages of controllable cumulative error, high reliability, and robustness with an increase in the scale of the pipeline and with an extension of the operation time.

SOLO-SLAM: A Parallel Semantic SLAM Algorithm for Dynamic Scenes.

Simultaneous localization and mapping (SLAM) is a core technology for mobile robots working in unknown environments. Most existing SLAM techniques can achieve good localization accuracy in static scenes, as they are designed based on the assumption that unknown scenes are rigid. However, real-world environments are dynamic, resulting in poor performance of SLAM algorithms. Thus, to optimize the performance of SLAM techniques, we propose a new parallel processing system, named SOLO-SLAM, based on the existing ORB-SLAM3 algorithm. By improving the semantic threads and designing a new dynamic point filtering strategy, SOLO-SLAM completes the tasks of semantic and SLAM threads in parallel, thereby effectively improving the real-time performance of SLAM systems. Additionally, we further enhance the filtering effect for dynamic points using a combination of regional dynamic degree and geometric constraints. The designed system adds a new semantic constraint based on semantic attributes of map points, which solves, to some extent, the problem of fewer optimization constraints caused by dynamic information filtering. Using the publicly available TUM dataset, SOLO-SLAM is compared with other state-of-the-art schemes. Our algorithm outperforms ORB-SLAM3 in accuracy (maximum improvement is 97.16%) and achieves better results than Dyna-SLAM with respect to time efficiency (maximum improvement is 90.07%).

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.

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.

Simultaneous Localization and Mapping (SLAM) and Data Fusion in Unmanned Aerial Vehicles: Recent Advances and Challenges

This article presents a survey of simultaneous localization and mapping (SLAM) and data fusion techniques for object detection and environmental scene perception in unmanned aerial vehicles (UAVs). We critically evaluate some current SLAM implementations in robotics and autonomous vehicles and their applicability and scalability to UAVs. SLAM is envisioned as a potential technique for object detection and scene perception to enable UAV navigation through continuous state estimation. In this article, we bridge the gap between SLAM and data fusion in UAVs while also comprehensively surveying related object detection techniques such as visual odometry and aerial photogrammetry. We begin with an introduction to applications where UAV localization is necessary, followed by an analysis of multimodal sensor data fusion to fuse the information gathered from different sensors mounted on UAVs. We then discuss SLAM techniques such as Kalman filters and extended Kalman filters to address scene perception, mapping, and localization in UAVs. The findings are summarized to correlate prevalent and futuristic SLAM and data fusion for UAV navigation, and some avenues for further research are discussed.

A Comprehensive Survey of Visual SLAM Algorithms

Simultaneous localization and mapping (SLAM) techniques are widely researched, since they allow the simultaneous creation of a map and the sensors’ pose estimation in an unknown environment. Visual-based SLAM techniques play a significant role in this field, as they are based on a low-cost and small sensor system, which guarantees those advantages compared to other sensor-based SLAM techniques. The literature presents different approaches and methods to implement visual-based SLAM systems. Among this variety of publications, a beginner in this domain may find problems with identifying and analyzing the main algorithms and selecting the most appropriate one according to his or her project constraints. Therefore, we present the three main visual-based SLAM approaches (visual-only, visual-inertial, and RGB-D SLAM), providing a review of the main algorithms of each approach through diagrams and flowcharts, and highlighting the main advantages and disadvantages of each technique. Furthermore, we propose six criteria that ease the SLAM algorithm’s analysis and consider both the software and hardware levels. In addition, we present some major issues and future directions on visual-SLAM field, and provide a general overview of some of the existing benchmark datasets. This work aims to be the first step for those initiating a SLAM project to have a good perspective of SLAM techniques’ main elements and characteristics.

Virtual simulation benchmark for the evaluation of simultaneous localization and mapping and 3D reconstruction algorithm uncertainty

Simultaneous localization and mapping (SLAM) algorithms allow us to obtain a unique 3D shape and 3D sensor trajectory by combining partial scans obtained by moving a 3D scanner. The performances of these algorithms are significantly affected by experimental conditions, characteristics of the target and values of the parameters of the reconstruction algorithm. Therefore, the uncertainty and reliability of SLAM techniques need to be assessed before their application, e.g. for robot navigation, autonomous vehicles or industrial fields. To evaluate the uncertainty of these algorithms, specific datasets containing 3D scans, with the possibility to control different conditions, e.g. sensor trajectory, depth or color noise, sensor velocity and framerate, are necessary. In this article, we present a procedure to obtain virtual datasets with complete control of the environment, 3D sensor and trajectory conditions, starting from any real 3D dataset acquisition, characterized by a sufficiently low uncertainty. These datasets can be generated to test the effect of SLAM algorithm parameters to determine the best parameters to be used to exploit the algorithm characteristics to obtain the best result in each operating context. The advantage of this procedure is the possibility to perfectly control each condition and to evaluate its effect on the final result. This procedure was applied to two reconstruction algorithms as examples; namely, the Open3D reconstruction tool and ElasticFusion. The results demonstrate that the setting of algorithm parameters, e.g. the tolerance on depth correspondence between frames or the number of fragments, or the change in number of frames acquired, can have a strong influence on the resulting 3D reconstruction and trajectory. Moreover, the effect of not closing the loop trajectory on reconstruction performance is quantified for different application scenarios.