Simultaneous Localization And Mapping Solution Research Articles

INS/LIDAR/Stereo SLAM Integration for Precision Navigation in GNSS-Denied Environments.

Traditionally, navigation systems have relied solely on global navigation satellite system (GNSS)/inertial navigation system (INS) integration. When a temporal loss of GNSS signal lock is encountered, these systems would rely on INS, which can sustain short bursts of outages, albeit drift significantly in prolonged outages. In this study, an extended Kalman filter (EKF) is proposed to develop an integrated INS/LiDAR/Stereo simultaneous localization and mapping (SLAM) navigation system. The first update stage of the filter integrates the INS with the LiDAR, after which the resultant navigation solution is integrated with the stereo SLAM solution, which yields the final integrated navigation solution. The system was tested for different driving scenarios in urban and rural environments using the raw Karlsruhe Institute of Technology and Toyota Technological Institute (KITTI) dataset in the complete absence of the GNSS signal. In addition, the selected KITTI drives covered low and high driving speeds in feature-rich and feature-poor environments. It is shown that the proposed INS/LiDAR/Stereo SLAM navigation system yielded better position estimations in comparison to using the INS without any assistance from onboard sensors. The accuracy improvement was expressed as a reduction of the root-mean-square error (RMSE) by 83% and 82% in the horizontal and up directions, respectively. In addition, the proposed system outperformed the positioning accuracy of some of the state-of-the-art algorithms.

A State of the Art in Simultaneous Localization and Mapping (SLAM) for Unmanned Ariel Vehicle (UAV): A Review

Abstract For the past decade, the main problem that has attracted researchers’ attention in aerial robotics is the position estimation or Simultaneous Localization and Mapping (SLAM) of Unmanned Aerial Vehicles (UAVs) where the GPS signal is poor or denied. This article reviews the strengths and weaknesses of existing methods in the field of aerial robotics. There are many different techniques and algorithms that are used to overcome the localization and mapping problem of these UAVs. These techniques and algorithms use different sensors, such as Red Green Blue-Depth (RGB_D), Light Detecting and Ranging (LIDAR), and Ultra-wideband (UWB). The most common technique is used, i.e., probability-based SLAM, which uses two algorithms: Linear Kalman Filter (LKF) and Extended Kalman Filter (EKF). LKF consists of five phases and this algorithm is just used for linear system problems. However, the EKF algorithm is used for non-linear systems. Aerial robots are used to perform many tasks, such as rescue, transportation, search, control, monitoring, and different military operations because of their vast top view. These properties are increasing their demand as compared to human service. In this paper, different techniques for the localization of aerial vehicles are discussed in terms of advantages and disadvantages, practicality and efficiency. This paper enables future researchers to find the suitable SLAM solution based on their problems; either the researcher is dealing with a linear problem or a non-linear problem.

Anchor Selection for SLAM Based on Graph Topology and Submodular Optimization

This article considers simultaneous localization and mapping (SLAM) problem for robots in situations where accurate estimates for some of the robot poses, termed anchors, are available. These may be acquired through external means, for example, by either stopping the robot at some previously known locations or pausing for a sufficient period of time to measure the robot poses with an external measurement system. The main contribution is an efficient algorithm for selecting a fixed number of anchors from a set of potential poses that minimizes estimated error in the SLAM solution. Based on a graph-topological connection between the D-optimality design metric and the tree-connectivity of the pose-graph, the anchor selection problem can be formulated approximately as a submatrix selection problem for reduced weighted Laplacian matrix, leading to a cardinality-constrained submodular maximization problem. Two greedy methods are presented to solve this submodular optimization problem with a performance guarantee. These methods are complemented by Cholesky decomposition, approximate minimum degree permutation, order reuse, and rank-1 update that exploit the sparseness of the weighted Laplacian matrix. We demonstrate the efficiency and effectiveness of the proposed techniques on public-domain datasets, Gazebo simulations, and real-world experiments.

A Mono SLAM Method Based on Depth Estimation by DenseNet-CNN

Currently, SLAM (simultaneous localization and mapping) systems based on monocular cameras cannot directly obtain depth information, and most of them have problems with scale uncertainty and need to be initialized. In some application scenarios that require navigation and obstacle avoidance, the inability to achieve dense mapping is also a defect of monocular SLAM. In response to the above problems, this paper proposes a method which learns depth estimation by DenseNet and CNN for a monocular SLAM system. We use an encoder-decoder architecture based on transfer learning and convolutional neural networks to estimate the depth information of monocular RGB images. At the same time, through the front-end ORB feature extraction and the back-end direct RGB-D Bundle Adjustment optimization method, it is possible to obtain accurate camera poses and achieve dense indoor mapping when using estimated depth information. The experimental results show that the monocular depth estimation model used in this paper can achieve good results, and it is also competitive in comparison with the current popular methods. On this basis, the error of camera pose estimation is also smaller than traditional monocular SLAM solutions and can complete the dense indoor reconstruction task. It is a complete SLAM system based on monocular camera.

Sensor-aware frontier exploration and mapping with application to thermal mapping of building interiors

The combination of simultaneous localization and mapping (SLAM) and frontier exploration enables a robot to traverse and map an unknown area autonomously. Most prior autonomous SLAM solutions utilize information only from depth sensing devices. However, in situations where the main goal is to collect data from auxiliary sensors such as thermal camera, existing approaches require two passes: one pass to create a map of the environment and another to collect the auxiliary data, which is time consuming and energy inefficient. We propose a sensor-aware frontier exploration algorithm that enables the robot to perform map construction and auxiliary data collection in one pass. Specifically, our method uses a real-time ray tracing technique to construct a map that encodes unvisited locations from the perspective of auxiliary sensors rather than depth sensors; this encourages the robot to fully explore those areas to complete the data collection task and map making in one pass. Our proposed exploration framework is deployed on a LoCoBot with the task to collect thermal images from building envelopes. We validate with experiments in both multi-room commercial buildings and cluttered residential buildings. Using a metric that evaluates the coverage of sensor data, our method significantly outperforms the baseline method with a naive SLAM algorithm.

A Graph Optimization-Based Acoustic SLAM Edge Computing System Offering Centimeter-Level Mapping Services with Reflector Recognition Capability

Robots can use echo signals for simultaneous localization and mapping (SLAM) services in unknown environments where its own camera is not available. In current acoustic SLAM solutions, the time of arrival (TOA) in the room impulse response (RIR) needs to be associated with the corresponding reflected wall, which leads to an echo labelling problem (ELP). The position of the wall can be derived from the TOA associated with the wall, but most of the current solutions ignore the effect of the cumulative error in the robot’s moving state measurement on the wall position estimation. In addition, the estimated room map contains only the shape information of the room and lacks position information such as the positions of doors and windows. To address the above problems, this paper proposes a graph optimization-based acoustic SLAM edge computing system offering centimeter-level mapping services with reflector recognition capability. In this paper, a robot equipped with a sound source and a four-channel microphone array travels around the room, and it can collect the room impulse response at different positions of the room and extract the RIR cepstrum feature from the room impulse response. The ELP is solved by using the RIR cepstrum to identify reflectors with different absorption coefficients. Then, the similarity of the RIR cepstrum vectors is used for closed-loop detection. Finally, this paper proposes a method to eliminate the cumulative error of robot movement by fusing IMU data and acoustic echo data using graph-optimized edge computation. The experiments show that the acoustic SLAM system in this paper can accurately estimate the trajectory of the robot and the position of doors, windows, and so on in the room map. The average self-localization error of the robot is 2.84 cm, and the mapping error is 4.86 cm, which meet the requirement of centimeter-level map service.

OntoSLAM: An Ontology for Representing Location and Simultaneous Mapping Information for Autonomous Robots

Autonomous robots are playing an important role to solve the Simultaneous Localization and Mapping (SLAM) problem in different domains. To generate flexible, intelligent, and interoperable solutions for SLAM, it is a must to model the complex knowledge managed in these scenarios (i.e., robots characteristics and capabilities, maps information, locations of robots and landmarks, etc.) with a standard and formal representation. Some studies have proposed ontologies as the standard representation of such knowledge; however, most of them only cover partial aspects of the information managed by SLAM solutions. In this context, the main contribution of this work is a complete ontology, called OntoSLAM, to model all aspects related to autonomous robots and the SLAM problem, towards the standardization needed in robotics, which is not reached until now with the existing SLAM ontologies. A comparative evaluation of OntoSLAM with state-of-the-art SLAM ontologies is performed, to show how OntoSLAM covers the gaps of the existing SLAM knowledge representation models. Results show the superiority of OntoSLAM at the Domain Knowledge level and similarities with other ontologies at Lexical and Structural levels. Additionally, OntoSLAM is integrated into the Robot Operating System (ROS) and Gazebo simulator to test it with Pepper robots and demonstrate its suitability, applicability, and flexibility. Experiments show how OntoSLAM provides semantic benefits to autonomous robots, such as the capability of inferring data from organized knowledge representation, without compromising the information for the application and becoming closer to the standardization needed in robotics.

An improved SLAM based on RK-VIF: Vision and inertial information fusion via Runge-Kutta method

Simultaneous Localization and Mapping (SLAM) is the foundation of autonomous navigation for unmanned systems. The existing SLAM solutions are mainly divided into the visual SLAM(vSLAM) equipped with camera and the lidar SLAM equipped with lidar. However, pure visual SLAM have shortcomings such as low positioning accuracy, the paper proposes a visual-inertial information fusion SLAM based on Runge-Kutta improved pre-integration. First, the Inertial Measurement Unit (IMU) information between two adjacent keyframes is pre-integrated at the front-end to provide IMU constraints for visual-inertial information fusion. In particular, to improve the accuracy in pre-integration, the paper uses the Runge-Kutta algorithm instead of Euler integral to calculate the pre-integration value at the next moment. Then, the IMU pre-integration value is used as the initial value of the system state at the current frame time. We combine the visual reprojection error and imu pre-integration error to optimize the state variables such as speed and pose, and restore map points' three-dimensional coordinates. Finally, we set a sliding window to optimize map points' coordinates and state variables. The experimental part is divided into dataset experiment and complex indoor-environment experiment. The results show that compared with pure visual SLAM and the existing visual-inertial fusion SLAM, our method has higher positioning accuracy.

Stratified Particle Filter Monocular SLAM

This paper presents a solution to the problem of simultaneous localization and mapping (SLAM), developed from a particle filter, utilizing a monocular camera as its main sensor. It implements a novel sample-weighting idea, based on the of sorting of particles into sets and separating those sets with an importance-factor offset. The grouping criteria for samples is the number of landmarks correctly matched by a given particle. This results in the stratification of samples and amplifies weighted differences. The proposed system is designed for a UAV, navigating outdoors, with a downward-pointed camera. To evaluate the proposed method, it is compared with different samples-weighting approaches, using simulated and real-world data. The conducted experiments show that the developed SLAM solution is more accurate and robust than other particle-filter methods, as it allows the employment of a smaller number of particles, lowering the overall computational complexity.

DUDMap: 3D RGB-D mapping for dense, unstructured, and dynamic environment

Simultaneous localization and mapping (SLAM) problem has been extensively studied by researchers in the field of robotics, however, conventional approaches in mapping assume a static environment. The static assumption is valid only in a small region, and it limits the application of visual SLAM in dynamic environments. The recently proposed state-of-the-art SLAM solutions for dynamic environments use different semantic segmentation methods such as mask R-CNN and SegNet; however, these frameworks are based on a sparse mapping framework (ORBSLAM). In addition, segmentation process increases the computational power, which makes these SLAM algorithms unsuitable for real-time mapping. Therefore, there is no effective dense RGB-D SLAM method for real-world unstructured and dynamic environments. In this study, we propose a novel real-time dense SLAM method for dynamic environments, where 3D reconstruction error is manipulated for identification of static and dynamic classes having generalized Gaussian distribution. Our proposed approach requires neither explicit object tracking nor object classifier, which makes it robust to any type of moving object and suitable for real-time mapping. Our method eliminates the repeated views and uses consistent data that enhance the performance of volumetric fusion. For completeness, we compare our proposed method using different types of high dynamic dataset, which are publicly available, to demonstrate the versatility and robustness of our approach. Experiments show that its tracking performance is better than other dense and dynamic SLAM approaches.

A Stereo SLAM System With Dense Mapping

The development of simultaneous localization and mapping (SLAM) technology plays an important role in robot navigation and autonomous vehicle innovation. The ORB-SLAM2 is a unified SLAM solution for monocular, binocular, and RGBD cameras which constructs a sparse feature point map for real-time positioning. However, a sparse map based approach cannot effectively meet the requirements of robot navigation, environment reconstruction, and other tasks. In this paper, a dense mapping thread is added to the existing ORB-SLAM2 system. The depth map and color image obtained by the stereo matching of a binocular camera are used to generate a three-dimensional point cloud for keyframes; then, the point cloud is fused by tracking and optimizing the motion track of a feature frame to obtain a real-time point cloud map. Through the experiments conducted on the KITTI dataset and the real environment under the ROS, it is proved that the proposed system constructs a clear three-dimensional point cloud map while constructing an accurate trajectory.

A Review on Map-Merging Methods for Typical Map Types in Multiple-Ground-Robot SLAM Solutions.

When multiple robots are involved in the process of simultaneous localization and mapping (SLAM), a global map should be constructed by merging the local maps built by individual robots, so as to provide a better representation of the environment. Hence, the map-merging methods play a crucial rule in multi-robot systems and determine the performance of multi-robot SLAM. This paper looks into the key problem of map merging for multiple-ground-robot SLAM and reviews the typical map-merging methods for several important types of maps in SLAM applications: occupancy grid maps, feature-based maps, and topological maps. These map-merging approaches are classified based on their working mechanism or the type of features they deal with. The concepts and characteristics of these map-merging methods are elaborated in this review. The contents summarized in this paper provide insights and guidance for future multiple-ground-robot SLAM solutions.

An Image-Based Real-Time Georeferencing Scheme for a UAV Based on a New Angular Parametrization

Simultaneous localization and mapping (SLAM) of a monocular projective camera installed on an unmanned aerial vehicle (UAV) is a challenging task in photogrammetry, computer vision, and robotics. This paper presents a novel real-time monocular SLAM solution for UAV applications. It is based on two steps: consecutive construction of the UAV path, and adjacent strip connection. Consecutive construction rapidly estimates the UAV path by sequentially connecting incoming images to a network of connected images. A multilevel pyramid matching is proposed for this step that contains a sub-window matching using high-resolution images. The sub-window matching increases the frequency of tie points by propagating locations of matched sub-windows that leads to a list of high-frequency tie points while keeping the execution time relatively low. A sparse bundle block adjustment (BBA) is employed to optimize the initial path by considering nuisance parameters. System calibration parameters with respect to global navigation satellite system (GNSS) and inertial navigation system (INS) are optionally considered in the BBA model for direct georeferencing. Ground control points and checkpoints are optionally included in the model for georeferencing and quality control. Adjacent strip connection is enabled by an overlap analysis to further improve connectivity of local networks. A novel angular parametrization based on spherical rotation coordinate system is presented to address the gimbal lock singularity of BBA. Our results suggest that the proposed scheme is a precise real-time monocular SLAM solution for a UAV.

A Survey of Ontologies for Simultaneous Localization and Mapping in Mobile Robots

Autonomous robots are playing important roles in academic, technological, and scientific activities. Thus, their behavior is getting more complex, particularly, in tasks related to mapping an environment and localizing themselves. These tasks comprise the Simultaneous Localization and Mapping (SLAM) problem. Representation of knowledge related to the SLAM problem with a standard, flexible, and well-defined model, provides the base to develop efficient and interoperable solutions. As many existing works demonstrate, Semantic Web seems to be a clear approach, since they have formulated ontologies, as the base data model to represent such knowledge. In this article, we survey the most popular and recent SLAM ontologies with our aim being threefold: (i) propose a classification of SLAM ontologies according to the main knowledge needed to model the SLAM problem; (ii) identify existing ontologies for classifying, comparing, and contrasting them, in order to conceptualize SLAM domain for mobile robots; and (iii) pin-down lessons to learn from existing solutions in order to design better solutions and identify new research directions and further improvements. We compare the identified SLAM ontologies according to the proposed classification and, finally, we explore new data fields to enrich existing ontologies and highlight new possibilities in terms of performance and efficiency for SLAM solutions.

MapperBot/iSCAN: open-source integrated robotic platform and algorithm for 2D mapping

Simultaneous localization and mapping (SLAM) of an unknown environment is a primary requirement for any autonomous robot. In this paper we present a cost-effective, robust, and integrated software/hardware SLAM solution for 2D mapping of large indoor environments. The presented SLAM solution consists of a robotic platform, referred as MapperBot, and an effective implementation of SLAM algorithm, referred as iSCAN. MapperBot is built using commercial of-the-shelf components with an open-source software/hardware design presented in this paper. The SLAM algorithm iSCAN is based on a highly robust laser-scan matching technique, incorporating Rao-Blackwellized particle filter as a mean to increase its accuracy. As a result, a minimal number of particles is required, and the computer processing time is dramatically reduced. MapperBot/iSCAN solution is fully integrated with the Matlab environment, thus providing researchers, students and developers a quick entry into the realm of the SLAM.

Humanoid Robot RGB-D SLAM in the Dynamic Human Environment

Unsteady locomotion and the dynamic environment are two problems that block humanoid robots to apply visual Simultaneous Localization and Mapping (SLAM) approaches. Humans are often considered as moving obstacles and targets in humanoid robots working space. Thus, in this paper, we propose a robust dense RGB-D SLAM approach for the humanoid robots working in the dynamic human environments. To deal with the dynamic human objects, a deep learning-based human detector is combined in the proposed method. After the removal of the dynamic object, we fast reconstruct the static environments through a dense RGB-D point clouds fusion framework. In addition to the humanoid robot falling problem, which usually results in visual sensing discontinuities, we propose a novel point clouds registration-based method to relocate the robot pose. Therefore, our robot can continue the self localization and mapping after the falling. Experimental results on both the public benchmarks and the real humanoid robot SLAM experiments indicated that the proposed approach outperformed state-of-the-art SLAM solutions in dynamic human environments.

MAPPING QUALITY EVALUATION OF MONOCULAR SLAM SOLUTIONS FOR MICRO AERIAL VEHICLES

Abstract. Monocular simultaneous localization and mapping (SLAM) attracted much attention in the mobile-robotics domain over the past decades along with the advancements of small-format, consumer-grade digital cameras. This is especially the case for micro air vehicles (MAV) due to their payload and power limitations. The quality of global 3D reconstruction by SLAM solutions is a critical factor in occupancy-grid mapping, obstacle avoidance, and map representation. Although several benchmarks have been created in the past to evaluate the quality of vision-based localization and trajectory-estimation, the quality of mapping products has been rarely studied. This paper evaluates the quality of three state-of-the-art open-source monocular SLAM solutions including LSD-SLAM, ORB-SLAM, and LDSO in terms of the geometric accuracy of the global mapping. Since there is no ground-truth information of the testing environment in existing visual SLAM benchmark datasets (e.g., EuRoC, TUM, and KITTI), an evaluation dataset using a quadcopter and a terrestrial laser scanner is created in this work. The dataset is composed of the image data extracted from the recorded videos by flying a drone in the test environment and the high-fidelity point clouds of the test area acquired by a terrestrial laser scanner as the ground truth reference. The mapping quality evaluation of the three SLAM algorithms was mainly conducted on geometric accuracy comparisons by calculating the deviation distance between each SLAM-derived point clouds and the laser-scanned reference. The mapping quality was also discussed with respect to their noise levels as well as further applications.

POU-SLAM: Scan-to-Model Matching Based on 3D Voxels

Purpose: Localization and mapping with LiDAR data is a fundamental building block for autonomous vehicles. Though LiDAR point clouds can often encode the scene depth more accurate and steadier compared with visual information, laser-based Simultaneous Localization And Mapping (SLAM) remains challenging as the data is usually sparse, density variable and less discriminative. The purpose of this paper is to propose an accurate and reliable laser-based SLAM solution. Design/methodology/approach: The method starts with constructing voxel grids based on the 3D input point cloud. These voxels are then classified into three types to indicate different physical objects according to the spatial distribution of the points contained in each voxel. During the mapping process, a global environment model with Partition of Unity (POU) implicit surface is maintained and the voxels are merged into the model from stage to stage, which is implemented by Levenberg–Marquardt algorithm. Findings: We propose a laser-based SLAM method. The method uses POU implicit surface representation to build the model and is evaluated on the KITTI odometry benchmark without loop closure. Our method achieves around 30% translational estimation precision improvement with acceptable sacrifice of efficiency compared to LOAM. Overall, our method uses a more complex and accurate surface representation than LOAM to increase the mapping accuracy at the expense of computational efficiency. Experimental results indicate that the method achieves accuracy comparable to the state-of-the-art methods. Originality/value: We propose a novel, low-drift SLAM method that falls into a scan-to-model matching paradigm. The method, which operates on point clouds obtained from Velodyne HDL64, is of value to researchers developing SLAM systems for autonomous vehicles.

A Computationally Efficient Semantic SLAM Solution for Dynamic Scenes

In various dynamic scenes, there are moveable objects such as pedestrians, which may challenge simultaneous localization and mapping (SLAM) algorithms. Consequently, the localization accuracy may be degraded, and a moving object may negatively impact the constructed maps. Maps that contain semantic information of dynamic objects impart humans or robots with the ability to semantically understand the environment, and they are critical for various intelligent systems and location-based services. In this study, we developed a computationally efficient SLAM solution that is able to accomplish three tasks in real time: (1) complete localization without accuracy loss due to the existence of dynamic objects and generate a static map that does not contain moving objects, (2) extract semantic information of dynamic objects through a computionally efficient approach, and (3) eventually generate semantic maps, which overlay semantic objects on static maps. The proposed semantic SLAM solution was evaluated through four different experiments on two data sets, respectively verifying the tracking accuracy, computational efficiency, and the quality of the generated static maps and semantic maps. The results show that the proposed SLAM solution is computationally efficient by reducing the time consumption for building maps by 2/3; moreover, the relative localization accuracy is improved, with a translational error of only 0.028 m, and is not degraded by dynamic objects. Finally, the proposed solution generates static maps of a dynamic scene without moving objects and semantic maps with high-precision semantic information of specific objects.

δ-Generalized Labeled Multi-Bernoulli Simultaneous Localization and Mapping with an Optimal Kernel-Based Particle Filtering Approach.

Under realistic environmental conditions, heuristic-based data association and map management routines often result in divergent map and trajectory estimates in robotic Simultaneous Localization And Mapping (SLAM). To address these issues, SLAM solutions have been proposed based on the Random Finite Set (RFS) framework, which models the map and measurements such that the usual requirements of external data association routines and map management heuristics can be circumvented and realistic sensor detection uncertainty can be taken into account. Rao–Blackwellized particle filter (RBPF)-based RFS SLAM solutions have been demonstrated using the Probability Hypothesis Density (PHD) filter and subsequently the Labeled Multi-Bernoulli (LMB) filter. In multi-target tracking, the LMB filter, which was introduced as an efficient approximation to the computationally expensive -Generalized LMB (-GLMB) filter, converts its representation of an LMB distribution to -GLMB form during the measurement update step. This not only results in a loss of information yielding inferior results (compared to the -GLMB filter) but also fails to take computational advantages in parallelized implementations possible with RBPF-based SLAM algorithms. Similar to state-of-the-art random vector-valued RBPF solutions such as FastSLAM and MH-FastSLAM, the performances of all RBPF-based SLAM algorithms based on the RFS framework also diverge from ground truth over time due to random sampling approaches, which only rely on control noise variance. Further, the methods lose particle diversity and diverge over time as a result of particle degeneracy. To alleviate this problem and further improve the quality of map estimates, a SLAM solution using an optimal kernel-based particle filter combined with an efficient variant of the -GLMB filter (-GLMB-SLAM) is presented. The performance of the proposed -GLMB-SLAM algorithm, referred to as -GLMB-SLAM2.0, was demonstrated using simulated datasets and a section of the publicly available KITTI dataset. The results suggest that even with a limited number of particles, -GLMB-SLAM2.0 outperforms state-of-the-art RBPF-based RFS SLAM algorithms.