Fast Simultaneous Localization And Mapping Research Articles

Tightly coupled stereo vision-inertial odometry based on point and line feature

Abstract To improve the accuracy and robustness of visual simultaneous localization and mapping (SLAM) in low-texture environments, this paper proposes a robust and fast stereo vision inertial SLAM pose estimation method that combines point and line features with an inertial measurement unit (IMU). The method tightly couples visual point and line features with IMU constraints, forming a least-squares problem through the error of each constraint term for nonlinear optimization. To address the issues of over-segmentation and time consumption in traditional line segment detection (LSD) algorithms, an improved LSD algorithm is adopted to accelerate line feature extraction. This approach merges nearby line segments based on spatial geometric relationships and filters out invalid segments, improving the time efficiency of the algorithm. Finally, experiments conducted in low-texture environments demonstrate that our algorithm achieves high localization accuracy and robustness.

VERIFICATION OF GRID BASED FASTSLAM WITH MULTIPLE CANDIDATES OF PARTICLES

In this paper, we propose a strategy for improving the accuracy of own positions in FastSLAM (Fast-Simultaneous Localization And Mapping). One can see that estimation of self-position and mapping are important for an autonomous mobile robot. As one approach to do this, GPS (Global Positioning System) based self-positioning methods have been proposed. However, GPS-based method has disadvantage that positioning is difficult in the environment where radio waves cannot be received. On the other hand, it is well known that SLAM can perform self-positioning by sensing the external environment based on LiDAR sensors, cameras and other devices. Since SLAM does not require online communication, estimate of self-position and mapping can be performed without being affected by the driving environment. FastSLAM is one of the SLAM algorithms, and samples the path using a particle filter. Each particle represents one possible motion path of robots in the particle filter, and the observed information is used to calculate the weight of each particle and evaluate each path. In FastSLAM, when self-location is determined, a particle is selected by comparing its likelihood as evaluated by the likelihood function. Since this depends on observed information, the reliability of the estimate depends on the accuracy of the sensor. Thus, there is possibility that there are more useful particles among those not selected. In this paper, we propose a new FastSLAM algorithm that selects multiple candidates of particles in FastSLAM algorithm. In the proposed approach, multiple candidates are stored and estimates of self-position is determined by using multiple candidates in the next step. By maintaining multiple particles, more robust self-position estimation and mapping can be performed comparing with the conventional FastSLAM. In this paper, we show the proposed algorithm and numerical simulations are shown to evaluate the performance of the proposed algorithm.

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.

A Universal LiDAR SLAM Accelerator System on Low-Cost FPGA

LiDAR (Light Detection and Ranging) SLAM (Simultaneous Localization and Mapping) serves as a basis for indoor cleaning, navigation, and many other useful applications in both industry and household. From a series of LiDAR scans, it constructs an accurate, globally consistent model of the environment and estimates a robot position inside it. SLAM is inherently computationally intensive; it is a challenging problem to realize a fast and reliable SLAM system on mobile robots with a limited processing capability. To overcome such hurdles, in this paper, we propose a universal, low-power, and resource-efficient accelerator design for 2D LiDAR SLAM targeting resource-limited FPGAs. As scan matching is at the heart of SLAM, the proposed accelerator consists of dedicated scan matching cores on the programmable logic part, and provides software interfaces to facilitate the use. Our accelerator can be integrated to various SLAM methods including the ROS (Robot Operating System)-based ones, and users can switch to a different method without modifying and re-synthesizing the logic part. We integrate the accelerator into three widely-used methods, i.e., scan matching, particle filter, and graph-based SLAM. We evaluate the design in terms of resource utilization, speed, and quality of output results using real-world datasets. Experiment results on a Pynq-Z2 board demonstrate that our design accelerates scan matching and loop-closure detection tasks by up to <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$14.84\times$ </tex-math></inline-formula> and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$18.92\times$ </tex-math></inline-formula> , yielding <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$4.67\times$ </tex-math></inline-formula> , <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$4.00\times$ </tex-math></inline-formula> , and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$4.06\times$ </tex-math></inline-formula> overall performance improvement in the above methods, respectively. Our design enables the real-time performance while consuming only 2.4W and maintaining accuracy, which is comparable to the software counterparts and even the state-of-the-art methods.

3FO: The Three-Frame-Only Approach for Fast and Accurate Monocular SLAM Initialization

The monocular simultaneous localization and mapping (SLAM) system is one of the most important among all visual or visual-inertial SLAM (VSLAM or VISLAM) systems due to its low cost, easy calibration and identification. Initialization is always crucial to bootstrap the monocular SLAM system. With the rapid growth of some quick-start required SLAM applications, e.g., augmented reality (AR) and unmanned aerial vehicles (UAVs), devising faster and more accurate initialization has become a central problem. Traditional initialization uses the first two frames to create landmarks and then computes camera poses for the subsequential frames, using a 3D-to-2D perspective-n-points (PnP) mechanism. In this paper, we propose a novel three-frame-only (3FO) initialization approach for the monocular SLAM system, which consists of two steps. In the first step, we use the first two frames to preinitialize poses and landmarks, and in the second step, we use the second and third frames to improve the preinitialization by using the scale consistency of the landmarks generated in the first step to filter out outliers and using inliers to generate more robust landmarks. In both steps, we use the pretrained multilayer perceptron (MLP) combined with homotopy continuation to solve the essential matrices. Finally, we perform a global bundle adjustment (BA) to refine the three camera poses and all the created landmarks. The proposed 3FO initialization approach is evaluated experimentally on the EuRoC benchmark data set with the initialization time and trajectory metrics. The results show that, compared to the traditional ORB-SLAM2 initialization, the 3FO approach reduces the initialization time by 5 times and improves the accuracy by 36.7% on average.

FSD-SLAM: a fast semi-direct SLAM algorithm

Current visual-based simultaneous localization and mapping(SLAM) system suffers from feature loss caused by fast motion and unstructured scene in complex environments. Addressing this problem, a fast semi-direct SLAM algorithm is proposed in this paper. The main idea of this method is to combine the feature point method with the direct method in order to improve the robustness of the system in the environment of scarce visual features and low texture. First, the feature enhancement module based on subgraph is developed to extract image feature points more stably. Second, an apparent shape weighted fusion method is proposed for camera pose estimation, which can still work robustly in the absence of feature points. Third, an incremental dynamic covariance scaling algorithm is studied for optimizing the error of camera pose estimation. Finally, based on the optimized camera pose, a face element model is designed to estimate and fuse the point cloud pose, and obtain an ideal three-dimensional point cloud map. The proposed algorithm has been tested extensively on the benchmark TUM dataset and the real environment. The results show that the algorithm has better performance than existing visual based SLAM algorithms.

Semi-Direct Monocular SLAM With Three Levels of Parallel Optimizations

In practical applications, how to use the complementary strengths of the direct and the feature-based methods for effective fusion may be the main challenge of simultaneous localization and mapping (SLAM). To solve this challenge, we propose the DO-SLAM, a novel fast and accurate semi-direct visual SLAM framework, which can maintain the direct method’s fast performance and the high precision and loop closure capability of the feature-based method. The direct method is used as the first half of the DO-SLAM to track the camera pose rapidly and robustly. The feature-based method is used as the second half of the DO-SLAM to refine the keyframe poses, perform loop closures, and build a globally consistent, long-term, sparse feature map that can be reused. The proposed pipeline fuses direct odometry and feature-based SLAM to perform three levels of parallel optimizations: (1) In the direct method module, the keyframe poses are estimated by minimizing the photometric error, (2) In the feature-based module, using the poses calculated by the inter-frame matching to correct and fuse the poses calculated by the direct method module as the initial poses, and the initial poses are optimized by the motion-only bundle adjustment, and (3) A pose graph optimization is used to achieve global map consistency in the presence of loop closures. Experimental evaluation on two benchmark datasets demonstrates that the proposed approach achieves higher accuracy and robustness on motion estimation compared to the other state-of-the-art methods.

SD-VIS: A Fast and Accurate Semi-Direct Monocular Visual-Inertial Simultaneous Localization and Mapping (SLAM).

In practical applications, how to achieve a perfect balance between high accuracy and computational efficiency can be the main challenge for simultaneous localization and mapping (SLAM). To solve this challenge, we propose SD-VIS, a novel fast and accurate semi-direct visual-inertial SLAM framework, which can estimate camera motion and structure of surrounding sparse scenes. In the initialization procedure, we align the pre-integrated IMU measurements and visual images and calibrate out the metric scale, initial velocity, gravity vector, and gyroscope bias by using multiple view geometry (MVG) theory based on the feature-based method. At the front-end, keyframes are tracked by feature-based method and used for back-end optimization and loop closure detection, while non-keyframes are utilized for fast-tracking by direct method. This strategy makes the system not only have the better real-time performance of direct method, but also have high accuracy and loop closing detection ability based on feature-based method. At the back-end, we propose a sliding window-based tightly-coupled optimization framework, which can get more accurate state estimation by minimizing the visual and IMU measurement errors. In order to limit the computational complexity, we adopt the marginalization strategy to fix the number of keyframes in the sliding window. Experimental evaluation on EuRoC dataset demonstrates the feasibility and superior real-time performance of SD-VIS. Compared with state-of-the-art SLAM systems, we can achieve a better balance between accuracy and speed.

Simulation of simultaneous localization and mapping using 3D point cloud data

&lt;span&gt;Abstract—This paper presents a simulation study of Simultaneous Localization and Mapping (SLAM) using 3D point cloud data from Light Detection and Ranging (LiDAR) technology. Methods like simulation is useful to simplify the process of learning algorithms particularly when collecting and annotating large volumes of real data is impractical and expensive. In this study, a map of a given environment was constructed in Robotic Operating System platform with Gazebo Simulator. The paper begins by presenting the most currently popular algorithm that are widely used in SLAM namely Extended Kalman Filter, Graph SLAM and Fast SLAM. The study performed the simulations by using standard SLAM with Turtlebot and Husky robots. Husky robot was further compared with ACML algorithm. The results showed that Hector SLAM could reach the goal faster than ACML algorithm in a pre-defined map. Further studies in this field with other SLAM algorithms would certainly beneficial to many parties due to the demands of robotic application.&lt;/span&gt;

Research on simultaneous localization and mapping for AUV by an improved method: Variance reduction FastSLAM with simulated annealing

At present, simultaneous localization and mapping (SLAM) for an autonomous underwater vehicle (AUV) is a research hotspot. Aiming at the problem of non-linear model and non-Gaussian noise in AUV motion, an improved method of variance reduction fast simultaneous localization and mapping (FastSLAM) with simulated annealing is proposed to solve the problems of particle degradation, particle depletion and particle loss in traditional FastSLAM, which lead to the reduction of AUV location estimation accuracy. The adaptive exponential fading factor is generated by the anneal function of simulated annealing algorithm to improve the effective particle number and replace resampling. By increasing the weight of small particles and decreasing the weight of large particles, the variance of particle weight can be reduced, the number of effective particles can be increased, and the accuracy of AUV location and feature location estimation can be improved to some extent by retaining more information carried by particles. The experimental results based on trial data show that the proposed simulated annealing variance reduction FastSLAM method avoids particle degradation, maintains the diversity of particles, weakened the degeneracy and improves the accuracy and stability of AUV navigation and localization system.

An Improved Transformed Unscented FastSLAM With Adaptive Genetic Resampling

Fast simultaneous localization and mapping (FastSLAM) is a well-known study for robot navigation. To enhance the performance of FastSLAM, an improved importance sampling is proposed in this paper based on the transformed unscented Kalman filter. The improvement is mainly composed of a novel fuzzy noise estimator, which can adjust the state and observation noises online according to the residual and related covariance, and thus mitigating the defects caused by model inaccuracy. In general, the FastSLAM algorithm suffers from the impoverishment problem since it is essentially a particle filter. Inspired by genetic optimization, an adaptive genetic resampling is proposed to substitute the conventional resampling step to overcome these defects. The proposed method, referred to as the improved transformed unscented FastSLAM, is compared with the unscented FastSLAM and the transformed unscented FastSLAM. The superiorities of the proposed method are verified by simulation and experiment under benchmark environments.

Intelligent Filter-Based SLAM for Mobile Robots With Improved Localization Performance

Fast simultaneous localization and mapping (FastSLAM) is one of the most popular methods for autonomous navigation of mobile robots. However, FastSLAM is essentially a particle filter (PF) that suffers from particle impoverishment and degeneracy problems. To improve its localization performance, this paper proposes an improved FastSLAM algorithm that contains an intelligent bat-inspired resampling whose iteration times can be adaptively tuned based on the degree of filter diverging. Additionally, the square root cubature filter is merged into the algorithm for better proposal distribution and mapping results. The advantages of the proposed method are verified by simulation and dataset-based tests. The test result demonstrates that the proposed IFastSLAM has better accuracy, computational efficiency and filter consistency compared to that of the square root unscented FastSLAM (SRUFastSLAM) and strong tracking square root central difference FastSLAM (STSRCDFastSLAM). Finally, a pool experiment is demonstrated to further verify the advantages of the proposed algorithm.

A Robot SLAM Improved by Quantum-Behaved Particles Swarm Optimization

We propose a new SLAM method based on fast simultaneous localization and mapping (FastSLAM). The technique presented uses an improved quantum-behaved particles swarm optimization (QPSO) to improve the proposal distribution of particles and optimize the estimated particles. This method makes the sampled particles closer to the true pose of the robot and improves the estimation accuracy of robot poses and landmarks. In the QPSO algorithm, the Gaussian disturbance is added to increase the diversity of the particles. By using this technique the premature convergence of particles swarm is overcome. In the resample step, the threshold value is used to evaluate the particle diversity. When the particle diversity is below the threshold value, the linear optimization is used to produce new sample particles, which increases the particle diversity and eliminates the loss of diversity. Simulations and experiments show that the proposed approach improves the accuracy of SLAM. The accuracy of estimated poses and landmarks with the proposed method is better than that with the traditional SLAM method.

A Fast Algorithm of SLAM Based on Combinatorial Interval Filters

Current FastSLAM algorithms face challenges such as heavy computing requirements and difficulty in enhancing estimation accuracy. This paper presents a fast algorithm of simultaneous localization and mapping (SLAM) based on combinatorial interval filters coupled with an improved box particle filter (IBPF) and extended interval Kalman filter (EIKF). First, strategies for improving box contracting and resampling are studied in depth via the linear programming contractor and dimension selection subdivision resampling methods. Then, we propose a weighted average based on a time-varying Markov model to increase the estimation accuracy of the EIKF. In this way, a kind of fast SLAM algorithm is designed through combinatorial synthetic integration, in which the IBPF algorithm is employed to realize simultaneous localization and the EIKF is utilized to build a map. A series of simulations and experiments demonstrate the superior performance of our interval filters based SLAM algorithm.

A Strong Tracking Square Root Central Difference FastSLAM for Unmanned Intelligent Vehicle With Adaptive Partial Systematic Resampling

An improved fast simultaneous localization and mapping (FastSLAM) algorithm based on the strong tracking square root central difference Kalman filter (STSRCDKF) with adaptive partial systematic resampling is proposed in this paper to solve the large-scale simultaneous localization and mapping (SLAM) problem for unmanned intelligent vehicle. In the proposed algorithm, STSRCDKF is composed of a strong tracking filter and a square root central difference Kalman filter. STSRCDKF is used to design an adaptive adjusting proposal distribution of the particle filter and to estimate the Gaussian densities of the landmarks. Moreover, an adaptive partial systematic resampling operation is carried out to reduce the degree of particle degeneracy and maintain the diversity of particles. The performance of the proposed algorithm is compared with that of central difference FastSLAM and FastSLAM2.0; the simulation results based on the simulator and two benchmark data sets verify that the proposed algorithm has better adaptability and robustness to respond with time-varying measurement noise. In addition, it reduces computational cost and improves state estimation accuracy and consistency. Furthermore, the validity of the proposed algorithm is verified by the experimental result in campus test site of Beijing University of Technology.

Posterior Elimination Fast Look-Ahead Rao-Blackwellized Particle Filtering for Simultaneous Localization and Mapping

In this paper, a method for further reducing computation time for Fast Look-Ahead Rao-Blackwellized Particle filtering (Fast la-RBPF) for Simultaneous Localization and Mapping (SLAM) problem is presented. By using the pose posterior probability, states with low posteriors are excluded from the Kalman filtering updates to the computation time can be reduced. In conjunction with Fast la-RBPF, the proposed algorithm is then called the Posterior Elimination Fast la-RBPF SLAM algorithm. Simulation results show that the proposed method is more efficient in terms of computation time than Fast la-RBPF without any sacrifice in both localization and mapping error performances.

Gaussian Kernel Posterior Elimination for Fast Look-Ahead Rao-Blackwellised Particle Filtering for SLAM

In this paper, we explore a method for posterior elimination for fast computation of the look-ahead Rao-Blackwellised Particle Filtering (Fast la-RBPF) algorithm for the simultaneous localization and mapping (SLAM) problem in the probabilistic robotics framework. In the case when a lot of SLAM states need to be estimated, large posterior states associated with the correct state may be outnumbered by multiple non-zero smaller posteriors. We show that by masking the low posterior weight states with a Gaussian kernel prior to weight selection the accuracy of the la-RBPF SLAM algorithm can be improved. Simulation results reveal that integrated with the proposed method the fast la-RBPF SLAM performance is enhanced over both the existing RBPF SLAM and the unmodified la-RBPF SLAM algorithms.

A Square Root Unscented FastSLAM With Improved Proposal Distribution and Resampling

An improved square root unscented fast simultaneous localization and mapping (FastSLAM) is proposed in this paper. The proposed method propagates and updates the square root of the state covariance directly in Cholesky decomposition form. Since the choice of the proposal distribution and that of the resampling method are the most critical issues to ensure the performance of the algorithm, its optimization is considered by improving the sampling and resampling steps. For this purpose, particle swarm optimization (PSO) is used to optimize the proposal distribution. PSO causes the particle set to tend to the high probability region of the posterior before the weights are updated; thereby, the impoverishment of particles can be overcome. Moreover, a new resampling algorithm is presented to improve the resampling step. The new resampling algorithm can conquer the defects of the resampling algorithm and solve the degeneracy and sample impoverishment problem simultaneously. Compared to unscented FastSLAM (UFastSLAM), the proposed algorithm can maintain the diversity of particles and consequently avoid inconsistency for longer time periods, and furthermore, it can improve the estimation accuracy compared to UFastSLAM. These advantages are verified by simulations and experimental tests for benchmark environments.

An Improved FastSLAM System Based on Distributed Structure for Autonomous Robot Navigation

Fast simultaneous localization and mapping (FastSLAM) is an efficient algorithm for autonomous navigation of mobile vehicle. However, FastSLAM must reconfigure the entire vehicle state equation when the feature points change, which causes an exponential growth in quantities of computation and difficulties in isolating potential faults. In order to overcome these limitations, an improved FastSLAM, based on the distributed structure, is developed in this paper. There are two state estimation parts designed in this improved FastSLAM. Firstly, a distributed unscented particle filter is used to avoid reconfiguring the entire system equation in the vehicle state estimation part. Secondly, in the landmarks estimation part, the observation model is designed as a linear one to update the landmarks states by using the linear observation errors. Then, the convergence of the proposed and improved FastSLAM algorithm is given in the sense of mean square. Finally, the simulation results show that the proposed distributed algorithm could reduce the computational complexity with high accuracy and high fault-tolerance performance.

FastSLAM Algorithm Based on Simulated Annealing for UAV

A large number of particles are needed to improve the precision of particle filtering of fast simultaneous localization and mapping (FastSLAM) for uninhabited aerial vehicle (UAV). Simulated annealing (SA) method is proposed to solve this problem. Through simulated annealing algorithm, the particle's prediction is updated and proposal distribution is adjusted in FastSLAM, so the particles are concentrated around the true pose. Stratified resampling is used to solve the degeneracy of particles. At last, the proposed algorithm is tested for UAV FastSLAM. The result shows this method is effective and feasible.