Simultaneous Localization Problem Research Articles

Assessment of CNN-Based Models for Odometry Estimation Methods with LiDAR

The problem of simultaneous localization and mapping (SLAM) in mobile robotics currently remains a crucial issue to ensure the safety of autonomous vehicles’ navigation. One approach addressing the SLAM problem and odometry estimation has been through perception sensors, leading to V-SLAM and visual odometry solutions. Furthermore, for these purposes, computer vision approaches are quite widespread, but LiDAR is a more reliable technology for obstacles detection and its application could be broadened. However, in most cases, definitive results are not achieved, or they suffer from a high computational load that limits their operation in real time. Deep Learning techniques have proven their validity in many different fields, one of them being the perception of the environment of autonomous vehicles. This paper proposes an approach to address the estimation of the ego-vehicle positioning from 3D LiDAR data, taking advantage of the capabilities of a system based on Machine Learning models, analyzing possible limitations. Models have been used with two real datasets. Results provide the conclusion that CNN-based odometry could guarantee local consistency, whereas it loses accuracy due to cumulative errors in the evaluation of the global trajectory, so global consistency is not guaranteed.

VSLAM using Deep Learning for Semantic Mapping

As the domains of deep learning and computer vision are developing, we are trying to find new applications as well as utilization in old problems. In this paper we are trying to apply deep learning methods to augment the traditional robotics problem of Simultaneous Localization and Mapping (SLAM). Most traditional SLAM methods build metric maps only, but we are trying to build a semantic map which identifies individual objects in the map meaningfully. We are using basic RGB-D SLAM to start with for the localization part, along with a deep learning-based module for the object detection and recognition. These together provide a semantic map for the environment. For better computational performance and efficiency, we are using OctoMap for the map data structure. To be qualified, our approach has to yield good results in localization, mapping as well as in object detection.

Dynamics-Based Modified Fast Simultaneous Localization and Mapping for Unmanned Aerial Vehicles With Joint Inertial Sensor Bias and Drift Estimation

In this paper, the problem of simultaneous localization and mapping (SLAM) using a modified Rao Blackwellized Particle Filter (RBPF) (a modified FastSLAM) is developed for a quadcopter system. It is intended to overcome the problem of inaccurate localization and mapping caused by inertial sensory faulty measurements (due to biases, drifts and noises) injected in the kinematics (odometery based) which is commonly used as a motion model in FastSLAM approaches. In this paper, the quadcopter’s dynamics with augmented bias and drift models is employed to eliminate these faults from the localization and mapping process. A modified FastSLAM is then developed in which both Kalman Filter (KF) and Extended Kalman Filter (EKF) algorithms are embedded in a PF with modified particles weights to estimate biases, drifts and landmark locations, respectively. In order to make the SLAM process robust to model mismatches due to parameter uncertainties in the dynamics, measurements are incorporated in the PF and in the particle generation process. This leads to a cascaded two-stage modified FastSLAM in which the extended FastSLAM 1.0 (to include dynamics and sensory faults) is employed in first stage and the results are used in second stage in which probabilistic inverse sensor models are incorporated in the particle generation process of the PF. The efficiency of the proposed approach is demonstrated through a co-simulation between MATLAB-2019b and Gazebo in the robotic operating system (ROS) in which the quadcopter model is simulated in Gazebo in ROS using a modified version of the Hector quadcopter ROS package. The collected pointcloud data using LiDAR is then utilised for feature extraction in the Gazebo. The simulation environment used to this aim is validated based on experimental data.

An Adaptive Augmented Vision-Based Ellipsoidal SLAM for Indoor Environments.

In this paper, the problem of Simultaneous Localization And Mapping (SLAM) is addressed via a novel augmented landmark vision-based ellipsoidal SLAM. The algorithm is implemented on a NAO humanoid robot and is tested in an indoor environment. The main feature of the system is the implementation of SLAM with a monocular vision system. Distinguished landmarks referred to as NAOmarks are employed to localize the robot via its monocular vision system. We henceforth introduce the notion of robotic augmented reality (RAR) and present a monocular Extended Kalman Filter (EKF)/ellipsoidal SLAM in order to improve the performance and alleviate the computational effort, to provide landmark identification, and to simplify the data association problem. The proposed SLAM algorithm is implemented in real-time to further calibrate the ellipsoidal SLAM parameters, noise bounding, and to improve its overall accuracy. The augmented EKF/ellipsoidal SLAM algorithms are compared with the regular EKF/ellipsoidal SLAM methods and the merits of each algorithm is also discussed in the paper. The real-time experimental and simulation studies suggest that the adaptive augmented ellipsoidal SLAM is more accurate than the conventional EKF/ellipsoidal SLAMs.

INTEGRATED SYSTEM SIMULTANEUS LOCALIZATION AND MAPPING

In this paper, we consider the solution of the problem of simultaneous localization and the construction of a map for an unmanned aerial vehicle (a quadrocopter). The structure of the integrated navigation system is developed on the basis of the fusion of several sources of navigational information, which allows to compensate the shortcomings of each source, which includes the following blocks: an improved system of visual navigation based on the use of EKF-SLAM, satellite navigation system GPS, barometric altimeter, radio altimeter, Strapdown inertial navigation system, the converter of modes of navigation. To improve the quality of the visual navigation system, an improved EKF-SLAM algorithm is proposed with the adaptation of the surveillance zone and local data association based on the improved ants algorithm, thereby avoiding obstacles. Recognition of landmarks is based on the use of the algorithm SURF. The EKF-SLAM algorithm is integrated through Adaptive Observation Range. Algorithms for dynamically changing the size of the observation zone and determining the redundancy of the detected landmarks are proposed. The extended Kalman filtering procedure for the problem under consideration and the proposed improvements are given. It is shown that the problem of SLAM data association can be represented as an optimization problem. As an optimization algorithm, an ant algorithm is proposed.

Line Features of Detail Enhancement Thermal Infrared Image for SLAM

To solve the problem of simultaneous localization and mapping of mobile robot vision navigation using infrared thermal imaging, A point-line feature extraction and matching algorithm after infrared image enhancement is proposed for visual odometry. We first used a guided filter to smooth the input image and separate it into the base layer and the detail layer. Then constraining the gradient of the detail will be used gain mask to enhance it. Finally, the two parts of the image combined with weighted coefficients will be exported into the second guided filter. The output image will use LSD to extract line feature, then using ORB algorithm will get point feature extraction and matching from line feature image. The results show the it can effectively improve the defect of infrared image blurred with similar background temperature and difficult to extract image features for mobile robot visual SLAM.

Method of adjoint particle filters in nonlinear Bayesian estimation problems with a high prior uncertainty

A modification of the widely known scheme for solving nonlinear Bayesian optimal estimation problems in which the state vector contains a parameter not varying during the estimation process is proposed. Such problems are often solved by a technique in which the varying part of the state vector is modeled using sequential Monte Carlo methods (particle filters) and the parameter is modeled as a conditional distribution associated with a specific trajectory (implementation of the moving component). Different modifications of this scheme differ mainly in the ways of modeling the parameter. In some recent works devoted to the problem of simultaneous localization and mapping, the vector parameter which consists of coordinates of unknown reference points (landmarks) is modeled using the generalized Kalman filter, Gaussian sum filters, and more specific methods. We consider a modification in which the parameter, as well as the moving part of the state vector, is modeled using particle filters. The main recurrence relationships between weights of particle filters are derived. The proposed computational algorithm is illustrated by an application to the problem of bearing-only simultaneous localization and mapping.

Research on Simultaneous Localization, Calibration and Mapping of Network Robot System

In a network robot system, a robot and a sensor network are integrated smoothly to develop their advantages and benefit from each other. Robot localization, sensor network calibration and environment mapping are three coupled issues to be solved once network robot system is introduced into a service environment. In this article, the problem of simultaneous localization, calibration and mapping is raised in order to improve their precision. The coupled relations among localization, calibration and mapping are denoted as a joint conditional distribution and then decomposed into three separate analytic terms according to Bayesian and Markov properties. The framework of Rao-Blackwellized particle filtering is used to solve the three analytic terms, in which extended particle filter is used for localization and unscented Kalman filter is used for both calibration and mapping. Simulations have been performed to demonstrate the validity and efficiency of the proposed solutions.

A comparison of EKF and SGD applied to a view-based SLAM approach with omnidirectional images

The problem of Simultaneous Localization and Mapping (SLAM) is essential in mobile robotics. The obtention of a feasible map of the environment poses a complex challenge, since the presence of noise arises as a major problem which may gravely affect the estimated solution. Consequently, a SLAM algorithm has to cope with this issue but also with the data association problem. The Extended Kalman Filter (EKF) is one of the most traditionally implemented algorithms in visual SLAM. It linearizes the movement and the observation model to provide an effective online estimation. This solution is highly sensitive to non-linear observation models as it is the omnidirectional visual model. The Stochastic Gradient Descent (SGD) emerges in this work as an offline alternative to minimize the non-linear effects which deteriorate and compromise the convergence of traditional estimators. This paper compares both methods applied to the same approach: a navigation robot supported by an efficient map model, established by a reduced set of omnidirectional image views. We present a series of real data experiments to assess the behavior and effectiveness of both methods in terms of accuracy, robustness against errors and speed of convergence.

A method to convert floating to fixed-point EKF-SLAM for embedded robotics

Abstract The Extended Kalman Filter (EKF) is one of the most efficient algorithms to address the problem of Simultaneous Localization And Mapping (SLAM) in the area of autonomous mobile robots. The EKF simultaneously estimates a model of the environment (map) and the position of a robot based on sensor information. The EKF for SLAM is usually implemented using floating-point data representation demanding high computational processing power, mainly when the processing is performed online during the environment exploration. In this paper, we propose a method to automatically estimate the bit-range of the EKF variables to mitigate its implementation using only fixed-point representation. In this method is presented a model to monitor the algorithm stability, a procedure to compute the bit range of each variable and a first effort to analyze the maximum acceptable system error. The proposed system can be applied to reduce the overall system cost and power consumption, specially in SLAM applications for embedded mobile robots.

Creación de un modelo visual del entorno basado en imágenes omnidireccionales

This paper deals with the problem of Simultaneous Localization and Mapping (SLAM). The solution presented is based on the utilisation of a set of images to represent the environment. In this way, the estimation of the map considers the computation of the position and orientation of a set of omnidirectional views captured from the environment. The proposed idea sets apart from the usual representation of a visual map, in which the environment is represented by a set of three dimensional points in a common reference system. Each of these points is commonly denoted as visual landmark. In the case presented here, the robot is equipped by a single omnidirectional visual sensor that allows to extract a number of interest points in the images, each one described by a visual descriptor. The map building process can be summed up in the following way: as the robot traverses the environment, it captures omnidirectional images and extracts a set of interest points from each one. Next, a set of correspondences is found between the current image and the rest of omnidirectional images existing in the map. When the number of correspondences found is enough, a transformation is computed, consisting of a rotation and a translation (up to an unknown scale factor). In the paper we show a method that allows to build a map while localizing the robot using these kind of observations. We present results obtained in a simulated environment that validate the proposed idea. In addition, we present experimental results using real data that prove the suitability of the solution.

Algorithm of data fusion for visual data and range meter measurements for the problem of simultaneous localization and mapping (SLAM)

Algorithm of data fusion for visual data and range meter measurements for the problem of simultaneous localization and mapping (SLAM)

Global Optimization for One-Dimensional Structure and Motion Problems

We study geometric reconstruction problems in one-dimensional retina vision. In such problems, the scene is modeled as a two-dimensional plane, and the camera sensor produces one-dimensional images of the scene. Our main contribution is an efficient method for computing the global optimum to the structure and motion problem with respect to the $L_{\infty}$ norm of the reprojection errors. One-dimensional cameras have proven useful in several applications, most prominently for autonomous vehicles, where they are used to provide inexpensive and reliable navigational systems. Previous results on one-dimensional vision are limited to the classification and solving of minimal cases, bundle adjustment for finding local optima, and linear algorithms for algebraic cost functions. In contrast, we present an approach for finding globally optimal solutions with respect to the $L_{\infty}$ norm of the angular reprojection errors. We show how to solve intersection and resection problems as well as the problem of simultaneous localization and mapping (SLAM). The algorithm is robust to use when there are missing data, which means that all points are not necessarily seen in all images. Our approach has been tested on a variety of different scenarios, both real and synthetic. The algorithm shows good performance for intersection and resection and for SLAM with up to five views. For more views the high dimension of the search space tends to give long running times. The experimental section also gives interesting examples showing that for one-dimensional cameras with limited field of view the SLAM problem is often inherently ill-conditioned.

Constrained submap algorithm for simultaneous localization and mapping

When solving the problem of simultaneous localization and mapping (SLAM), a standard extended Kalman filter (EKF) is subject to linearization errors and causes optimistic estimation. This paper proposes a submap algorithm, which builds a weighted least squares (WLS) constraint between two adjacent submaps according to the different estimations of the common features and the relationship between the vehicle poses in the corresponding submaps. By establishing the constraint equation after loop closing, re-linearization is implemented and each submap’s reference frame tends to its equilibrium position quickly. Experimental results demonstrate that the algorithm could get a globally consistent map and linearization errors are limited in local regions.

Closing the Loop With Graphical SLAM

The problem of simultaneous localization and mapping (SLAM) is addressed using a graphical method. The main contributions are a computational complexity that scales well with the size of the environment, the elimination of most of the linearization inaccuracies, and a more flexible and robust data association. We also present a detection criteria for closing loops. We show how multiple topological constraints can be imposed on the graphical solution by a process of coarse fitting followed by fine tuning. The coarse fitting is performed using an approximate system. This approximate system can be shown to possess all the local symmetries. Observations made during the SLAM process often contain symmetries, that is to say, directions of change to the state space that do not affect the observed quantities. It is important that these directions do not shift as we approximate the system by, for example, linearization. The approximate system is both linear and block diagonal. This makes it a very simple system to work with especially when imposing global topological constraints on the solution. These global constraints are nonlinear. We show how these constraints can be discovered automatically. We develop a method of testing multiple hypotheses for data matching using the graph. This method is derived from statistical theory and only requires simple counting of observations. The central insight is to examine the probability of not observing the same features on a return to a region. We present results with data from an outdoor scenario using a SICK laser scanner.

Real‐time localization and elevation mapping within urban search and rescue scenarios

AbstractUrban search and rescue (USAR) is a time critical task. One goal in rescue robotics is to have a team of heterogeneous robots that explore autonomously the disaster area, while jointly creating a map of the terrain and registering victim locations, which can further be utilized by human task forces for rescue. Basically, the robots have to solve autonomously in real‐time the problem of simultaneous localization and mapping (SLAM), consisting of a continuous state estimation problem and a discrete data association problem. In this paper we contribute a novel method for efficient loop closure in harsh large‐scale environments that utilizes RFID technology for data association and slippage‐sensitive odometry for 2D pose tracking. Furthermore, we introduce a computational efficient method for building elevation maps by utilizing an extended Kalman filter for 3D pose tracking, which can be applied in real‐time while navigating on rough terrain. The proposed methods have been extensively evaluated within outdoor environments, as well as within USAR test arenas designed by the National Institute of Standards and Technology (NIST). Our results show that the proposed methods perform robustly and efficiently within the utilized benchmark scenarios. © 2007 Wiley Periodicals, Inc.

Immune evolutionary algorithms with domain knowledge for simultaneous localization and mapping

Immune evolutionary algorithms with domain knowledge were presented to solve the problem of simultaneous localization and mapping for a mobile robot in unknown environments. Two operators with domain knowledge were designed in algorithms, where the feature of parallel line segments without the problem of data association was used to construct a vaccination operator, and the characters of convex vertices in polygonal obstacle were extended to develop a pulling operator of key point grid. The experimental results of a real mobile robot show that the computational expensiveness of algorithms designed is less than other evolutionary algorithms for simultaneous localization and mapping and the maps obtained are very accurate. Because immune evolutionary algorithms with domain knowledge have some advantages, the convergence rate of designed algorithms is about 44% higher than those of other algorithms.

On actively closing loops in grid-based FastSLAM

Acquiring models of the environment belongs to the fundamental tasks of mobile robots. In the past, several researchers have focused on the problem of simultaneous localization and mapping (SLAM). Classical SLAM approaches are passive in the sense that they only process the perceived sensor data and do not influence the motion of the mobile robot. In this paper, we present a novel integrated approach that combines autonomous exploration with simultaneous localization and mapping. Our method uses a grid-based version of the FastSLAM algorithm and considers at each point in time actions to actively close loops during exploration. By re-entering already visited areas, the robot reduces its localization error and in this way learns more accurate maps. Experimental results presented in this paper illustrate the advantage of our method over previous approaches that lack the ability to actively close loops.

Simultaneous localization and map building for a team of cooperating robots: a set membership approach

The problem of simultaneous localization and map building for a team of cooperating robots moving in an unknown environment is addressed. The robots have to estimate the position of distinguishable static landmarks, and then localize themselves with respect to other robots and landmarks, exploiting distance and angle measurements. A novel set theoretic approach to this problem is presented. The proposed localization algorithm provides position estimates and guaranteed uncertainty regions for all robots and landmarks in the environment.