SLAM System Research Articles

Bidirectional Trajectory Computation for Odometer-Aided Visual-Inertial SLAM

Odometer-aided visual-inertial SLAM systems typically have a good performance for navigation of wheeled platforms, while they usually suffer from degenerate cases before the first turning. In this paper, firstly we perform an observability analysis w.r.t. the extrinsic parameters before the first turning, which is a complement of the existing results of observability analyses. Secondly, inspired by the above observability analyses, we propose a bidirectional trajectory computation method, by which the poses before the first turning are refined in the backward computation thread, and the real-time trajectory is adjusted accordingly. Experimental results prove that our proposed method not only solves the problem of the unobservability of accelerometer bias and extrinsic parameters before the first turning, but also results in more accurate trajectories in comparison with the state-of-the-art approaches.

Neural guided visual slam system with Laplacian of Gaussian operator

Simultaneous localization and mapping (SLAM) addresses the problem of constructing the map from noisy sensor data and tracking the robot's path within the built map. After decades of development, a lot of mature systems achieve competent results in feature-based implementations. However, there are still problems when migrating the technology to practical applications. One typical example is the accuracy and robustness of SLAM in environment with illuminance and texture variations. To this end, two modules in the existing systems are improved here namely tracking and camera relocalization. In tracking module, image pyramid is processed with Laplacian of Gaussian (LoG) operator in feature extraction for enhanced edges and details. A majority voting mechanism is proposed to dynamically evaluate and redetermine the zero-mean sum of square difference threshold according to the matching error estimation in patch search. In camera relocalization module, full convolutional neural network which focuses on certain parts of the input data is utilized in guiding for accurate output predictions. The authors implement the two modules into OpenvSLAM and propose a neural guided visual SLAM system named LoG-SLAM. Experiments on publicly available datasets show that the accuracy and efficiency increase with LoG-SLAM when compared with other feature-based methods, and relocalization accuracy also improves compared with the recently proposed deep learning pipelines.

A Multi-Feature Fusion Slam System Attaching Semantic In-Variant to Points and Lines.

The traditional simultaneous localization and mapping (SLAM) system uses static points of the environment as features for real-time localization and mapping. When there are few available point features, the system is difficult to implement. A feasible solution is to introduce line features. In complex scenarios containing rich line segments, the description of line segments is not strongly differentiated, which can lead to incorrect association of line segment data, thus introducing errors into the system and aggravating the cumulative error of the system. To address this problem, a point-line stereo visual SLAM system incorporating semantic invariants is proposed in this paper. This system improves the accuracy of line feature matching by fusing line features with image semantic invariant information. When defining the error function, the semantic invariant is fused with the reprojection error function, and the semantic constraint is applied to reduce the cumulative error of the poses in the long-term tracking process. Experiments on the Office sequence of the TartanAir dataset and the KITTI dataset show that this system improves the matching accuracy of line features and suppresses the cumulative error of the SLAM system to some extent, and the mean relative pose error (RPE) is 1.38 and 0.0593 m, respectively.

An Adaptive Visual Dynamic-SLAM Method Based on Fusing the Semantic Information

The SLAM problem in dynamic scenes is regarded as a challenge. This article proposes a novel SLAM framework for dynamic environments, which combines neural network and motion information of dynamic objects, making the system more adaptable to dynamic scenes. Specifically, we adopt a fast object detection network, tightly couple the results of the object detection with the geometric information in the SLAM system. Then the feature point extracted from the image is associated with a dynamic probability. By utilizing the feature points which tend to be static, the localization result can be greatly improved in dynamic environments. We perform the experiments both on the public data set and the real environment. The result can demonstrate that the proposed method greatly improves the localization accuracy in a dynamic environment. An open-source version of the source code is available.

DT-SLAM: Dynamic Thresholding Based Corner Point Extraction in SLAM System

Visual localization estimation is highly depended on the quality of video frames or captured images. Estimation quality may be affected by the poor visibility, low background texture and overexposure. Low quality frames with blurred edges and poor contrast pose tremendous difficulties for corner point detection in SLAM impacting the overall accuracy of estimation. This paper introduces DT-SLAM, a dynamic self-adaptive threshold (DSAT) approach for ORB corner point extraction in FAST to improve SLAM’s localization performance. The proposed method replaces the existing static threshold-based ORB extraction approach, enabling improved performance in complex real-world scenes. In addition, this study introduces a threshold switching mechanism (TSM) to replace the existing SLAM’s frame-level and cell-level thresholds for corner point extraction. The proposed DT-SLAM approach is validated using the TUM RGB-D and EuRoC benchmark datasets for location tracking performances. The results indicate that the proposed DT-SLAM outperforms the current state-of-the-art ORB-SLAM3, especially in challenging environments.

Survey and Evaluation of RGB-D SLAM

The traditional visual SLAM systems take the monocular or stereo camera as input sensor, with complex map initialization and map point triangulation steps needed for 3D map reconstruction, which are easy to fail, computationally complex and can cause noisy measurements. The emergence of RGB-D camera which provides RGB image together with depth information breaks this situation. While a number of RGB-D SLAM systems have been proposed in recent years, the current classification research on RGB-D SLAM is very lacking, and their advantages and shortcomings remain unclear regarding different applications and perturbations, such as illumination transformation, noise and rolling shutter effect of sensors. In this paper, we mainly introduced the basic concept and structure of the RGB-D SLAM system, and then introduced the differences between the various RGB-D SLAM systems in the three aspects of tracking, mapping, and loop detection, and we make a classification study on different RGB-D SLAM algorithms according to the three aspect. Furthermore, we discuss some advanced topics and open problems of RGB-D SLAM, hoping that it will help for future exploring. In the end, we conducted a large number of evaluation experiments on multiple RGB-D SLAM systems, and analyzed their advantages and disadvantages, as well as performance differences in different application scenarios, and provided references for researchers and developers.

Workload Partitioning of a Bio-inspired Simultaneous Localization and Mapping Algorithm on an Embedded Architecture

Many algorithms were developed to perform visual localization and mapping (SLAM) for robotic applications. These algorithms used monocular or stereovision systems to solve constraints related to the navigation in unknown or dynamic environment. The requirement of SLAM systems in terms of processing time and precision is a factor that limits their use in many embedded applications like UAVs or autonomous vehicles. Meanwhile, trends towards low-cost and low-power processing require massive parallelism on hardware architectures. The emergence of recent heterogeneous embedded architectures should help design embedded systems dedicated to Visual SLAM applications. It was demonstrated in a previous work that bio-inspired algorithms are competitive compared to classical methods based on image processing and environment perception. This paper is a study of a bio-inspired SLAM algorithm with the aim of making it suitable for an implementation on a heterogeneous architecture dedicated for embedded applications. An algorithm-architecture adequation approach is used to achieve a workload partitioning on CPU-GPU architecture and hence speeding up processing tasks.

A SLAM System Based on RGBD Image and Point-Line Feature

Most of the existing visual SLAM schemes rely solely on point or line features to estimate camera trajectory. In some scenes such as texture missing or motion blurring, it’s difficult to find a sufficient number of reliable features, resulting in low positioning accuracy. To extract more features, an RPL-SLAM solution is proposed to extract point features and line features respectively. Ulteriorly, the depth information of RGBD image is used to restore the 3D information of point and line features, improving the accuracy of camera track positioning. RPL-SLAM scheme mainly includes three modules: tracking, local mapping and loop detection. Tracking module extends the application of line feature on the basis of point feature extraction and matching. A SLD line segment extraction algorithm which can eliminate the micro segments and a DBM segment matching algorithm based on word bag are proposed respectively. These two algorithms improve the matching efficiency while ensuring the matching accuracy, and effectively track and locate the camera of each frame. In the local mapping and loop detection module, the Plucker coordinates are applied to express the spatial line and define the re-projection error of the straight line, so that the back-end optimization error model of point-line fusion is unified to solve the instability problem in optimization. RPL-SLAM is tested on TUM RGBD and ICL-NUIM data set respectively, and compared with ORB-SLAM2. The result shows that RPL-SLAM can effectively improve the accuracy of pose estimation and map reconstruction while maintaining real-time performance by fusing point-line features with depth images.

Lost in the Woods? Place Recognition for Navigation in Difficult Forest Environments.

Forests present one of the most challenging environments for computer vision due to traits, such as complex texture, rapidly changing lighting, and high dynamicity. Loop closure by place recognition is a crucial part of successfully deploying robotic systems to map forests for the purpose of automating conservation. Modern CNN-based place recognition systems like NetVLAD have reported promising results, but the datasets used to train and test them are primarily of urban scenes. In this paper, we investigate how well NetVLAD generalizes to forest environments and find that it out performs state of the art loop closure approaches. Finally, integrating NetVLAD with ORBSLAM2 and evaluating on a novel forest data set, we find that, although suitable locations for loop closure can be identified, the SLAM system is unable to resolve matched places with feature correspondences. We discuss additional considerations to be addressed in future to deal with this challenging problem.

2D Lidar-Based SLAM and Path Planning for Indoor Rescue Using Mobile Robots

As the basic system of the rescue robot, the SLAM system largely determines whether the rescue robot can complete the rescue mission. Although the current 2D Lidar-based SLAM algorithm, including its application in indoor rescue environment, has achieved much success, the evaluation of SLAM algorithms combined with path planning for indoor rescue has rarely been studied. This paper studies mapping and path planning for mobile robots in an indoor rescue environment. Combined with path planning algorithm, this paper analyzes the applicability of three SLAM algorithms (GMapping algorithm, Hector-SLAM algorithm, and Cartographer algorithm) in indoor rescue environment. Real-time path planning is studied to test the mapping results. To balance path optimality and obstacle avoidance, A ∗ algorithm is used for global path planning, and DWA algorithm is adopted for local path planning. Experimental results validate the SLAM and path planning algorithms in simulated, emulated, and competition rescue environments, respectively. Finally, the results of this paper may facilitate researchers quickly and clearly selecting appropriate algorithms to build SLAM systems according to their own demands.

Research on Laser-Visual Fusion-based Simultaneous Localization and Mapping

In consideration of the restrictions of the single-sensor SLAM system in different application scenarios, this paper proposes a laser-visual sensor fusion strategy on the basis of analyzing the strengths and weaknesses of laser SLAM and visual SLAM. In the local mapping stage, the laser stability is used to facilitate the visual SLAM system while in the global map generation stage, the point cloud map with rich texture information as constructed by the visual SLAM system is used to improve the missing map information of the laser SLAM system and finally obtain a globally consistent 2D grid map. Through indoor real scene experiments, the fused SLAM system is verified so as to improve the accuracy of localization and mapping and yield a favorable robustness by combining the strengths of both effectively.

Diseño Distribuido de un Sistema de Mapeo y Localización basado en visión para un Robot Móvil

En este trabajo se presenta una arquitectura distribuida para el sistema de SLAM estéreo S-PTAM. Esta arquitectura está desarrollada sobre el framework ROS, separando los hilos de localización y mapeo en dos nodos independientes de ROS. El sistema de SLAM distribuido resulta ideal para robots móviles con bajo poder de cómputo ya que permite ejecutar el módulo de localización onboard y el módulo de mapeo -que tiene mayor costo computacional- en una estación base, aprovechando al máximo el procesamiento disponible onboard. Para la validación del sistema se realizaron experimentos en un dataset público. Los resultados obtenidos muestran la factibilidad de una arquitectura distribuida y su implementación eficiente.

Bi-direction Direct RGB-D Visual Odometry

ABSTRACT Direct visual odometry (DVO) is an important vision task which aims to obtain the camera motion via minimizing the photometric error across the different correlated images. However, the previous research on DVO rarely considered the motion bias and only calculated using single direction, therefore potentially ignoring useful information compared with leveraging diverse directions. We assume that jointly considering forward and backward calculation can improve the accuracy of pose estimation. To verify our assumption and solid this contribution, in this paper, we test various combination of direct dense methods, including different error metrics, e.g., (intensity, gradient magnitude), alignment strategies (Forward-Compositional, Inverse-Compositional), and calculation directions (forward, backward, and bi-direction). We further study the issue of motion bias in RGB-D visual odometry and propose four strategy options to improve pose estimation accuracy, e.g., joint bi-direction estimation; two stage bi-direction estimation; transform average with weights; and transform fusion with covariance. We demonstrate the effectiveness and efficiency of our proposed algorithms across a range of popular datasets, e.g., TUM RGB-D and ICL-NUIM, in which we achieve an impressive performance through comparing with state of the art methods and provide benefits for existing RGB-D visual odometry and visual SLAM systems.

S4-SLAM: A real-time 3D LIDAR SLAM system for ground/watersurface multi-scene outdoor applications

For outdoor ground/watersurface multi-scene applications with sparse feature points, high moving speed and high dynamic noises, a real-time 3D LIDAR SLAM system (S4-SLAM) for unmanned vehicles/ships is proposed in this paper, which is composed of the odometry function in front-end and the loop closure function in back-end. Firstly, linear interpolation is used to eliminate the motion distortion caused by robot motions in the data pre-processing step. Two nodes are constructed in the odometry function: the localization node combines the improved Super4PCS with the standard ICP to realize a coarse-to-fine scan matching and outputs the location information of the robot at a high frequency (5 Hz); the correction node introduces a local map with dynamic voxel grid storage structure, which can accelerate the NDT(Normal Distributions Transform) matching process between key-frames and the local map, and then corrects the localization node at a low frequency (1 Hz) to obtain more accurate location information. In the loop closure function, a location-based loop detection approach is introduced and the overlap rate of point clouds is used to verify the loops, so that the global optimization can be carried out to obtain high-precision trajectory and map estimates. The proposed method has been extensively evaluated on the KITTI odometry benchmark and also tested in real-life campus and harbor environments. The results show that our method has low dependence on GPS/INS, high positioning accuracy (with the global drift under 1%) and good environmental robustness.

Interactive 3D Graph SLAM for Map Correction

This letter presents an interactive graph SLAM framework with a 3D LIDAR. This framework allows the user to interactively correct a 3D environmental map generated by an automatic SLAM system. By optimizing a pose graph consisting of pose constraints created by the automatic SLAM and map correction constraints, which are created by the user through a graphical user interface, we obtain a large and globally consistent 3D environmental map. We propose semi-automatic loop closing and plane-based map correction techniques for creating map correction constraints. We also devise a pose constraint update approach to refine the pose constraints given by the automatic SLAM. The evaluation results demonstrate that the proposed system enables us to improve the consistency of mapping results and obtain a mapping accuracy that outperforms state-of-the-art automatic SLAM frameworks with minimal human effort.

Co-Planar Parametrization for Stereo-SLAM and Visual-Inertial Odometry

This work proposes a novel SLAM framework for stereo and visual inertial odometry estimation. It builds an efficient and robust parametrization of co-planar points and lines which leverages specific geometric constraints to improve camera pose optimization in terms of both efficiency and accuracy. %reduce the size of the Hessian matrix in the optimization. The pipeline consists of extracting 2D points and lines, predicting planar regions and filtering the outliers via RANSAC. Our parametrization scheme then represents co-planar points and lines as their 2D image coordinates and parameters of planes. We demonstrate the effectiveness of the proposed method by comparing it to traditional parametrizations in a novel Monte-Carlo simulation set. Further, the whole stereo SLAM and VIO system is compared with state-of-the-art methods on the public real-world dataset EuRoC. Our method shows better results in terms of accuracy and efficiency than the state-of-the-art. The code is released at https://github.com/LiXin97/Co-Planar-Parametrization.

SP-Flow: Self-supervised optical flow correspondence point prediction for real-time SLAM

This paper presents a self-supervised learning network called SP-Flow to generate keypoints in real-time for SLAM systems. Optical flows are employed to match the keypoints between two successive frames in the training process of SP-Flow. This approach enables the network to use datasets without manual annotations. To show the efficacy of our SP-Flow, we built an SP-Flow SLAM system by replacing ORB with SP-Flow in the ORB-SLAM2 system. The experimental results demonstrate that our SLAM system is able to achieve real-time performance and high accuracy with stereo or RGB-D images as inputs.

An Accurate, Robust Visual Odometry and Detail-Preserving Reconstruction System

Tracking and mapping functions in a monocular SLAM system remain active due to their challenging nature. In this paper, we propose a novel approach to perform the accurate and robust ego-motion estimation and provide the detail-preserving reconstruction in indoor environments. More specifically, we design a new algorithm called synchronous event measurement (SEM) to create event-based difference images (EDIs) so as to highlight frame-to-frame (F2F) difference. The observation indicates that F2F difference is highly correlated with the camera's motion change. We hereby feed EDIs into a deep convolutional neural network, in order to infer ego-motion of the camera. Subsequently, based on a monocular reconstruction framework (REMODE), we devise an algorithm named event region search or briefly ERS, to reduce possibility of mismatch on the depth estimation stage. Evaluations on a variety of datasets demonstrate the satisfactory performance of our proposed method: the ego-motion estimation is more accurate than some geometric based Visual Odometry (VO) and learning based approaches. The results are robust under extreme situations, such as brightness variation and motion blur. Meanwhile, our approach can provide more precise depth map with relatively rich textural information.

Multi-Feature Nonlinear Optimization Motion Estimation Based on RGB-D and Inertial Fusion

To achieve a high precision estimation of indoor robot motion, a tightly coupled RGB-D visual-inertial SLAM system is proposed herein based on multiple features. Most of the traditional visual SLAM methods only rely on points for feature matching and they often underperform in low textured scenes. Besides point features, line segments can also provide geometrical structure information of the environment. This paper utilized both points and lines in low-textured scenes to increase the robustness of RGB-D SLAM system. In addition, we implemented a fast initialization process based on the RGB-D camera to improve the real-time performance of the proposed system and designed a new backend nonlinear optimization framework. By minimizing the cost function formed by the pre-integrated IMU residuals and re-projection errors of points and lines in sliding windows, the state vector is optimized. The experiments evaluated on public datasets show that our system achieves higher accuracy and robustness on trajectories and in pose estimation compared with several state-of-the-art visual SLAM systems.

Autonomous Navigation Method for Mars Rover Using Distributed EKF-SLAM Assisted by Sun Sensor

Since the existing SLAM algorithm can not meet the actual demand of the Mars rover autonomous navigation problem in real-time and accuracy, a distributed EKF-SLAM algorithm is proposed based on heading assistance to achieve the rover's autonomous navigation. The solar azimuth is got by using the dual axis analog sun sensor, and then the rover heading information is calculated and added it to each subsystem of SLAM. Consequently, a SLAM model of EKF-SLAM system is built and the federal EKF is adopted to realize the state estimation of the distributed SLAM system. Finally, a whole astronomical heading assistant distributed system is constructed. The experiment test is performed in outdoor experimental environment using a mobile robot, and the experimental results demonstrate the accuracy and effectiveness of the proposed algorithm.