Improved visual SLAM: a novel approach to mapping and localization using visual landmarks in consecutive frames

Pathfinding is becoming more and more common in autonomous vehicle navigation, robot localization, and other computer vision applications. In this paper, a novel approach to mapping and localization is presented that extracts visual landmarks from a robot dataset acquired by a Kinect sensor. The visual landmarks are detected and recognized using the improved scale-invariant feature transform (I-SIFT) method. The methodology is based on detecting stable and invariant landmarks in consecutive (red-green-blue depth) RGB-D frames of the robot dataset. These landmarks are then used to determine the robot path, and a map is constructed by using the visual landmarks. A number of experiments were performed on various datasets in an indoor environment. The proposed method performs efficient landmark detection in various environments, which includes changes in rotation and illumination. The experimental results show that the proposed method can solve the simultaneous localization and mapping (SLAM) problem using stable visual landmarks, but with less computation time.     

A new approach to solve SLAM challenges by relative map filter

In this paper we propose a new approach to solve some challenges in the simultaneous localization and mapping (SLAM) problem based on the relative map filter (RMF). This method assumes that the relative distances between the landmarks of relative map are estimated fully independently. This considerably reduces the computational complexity to average number of landmarks observed in each scan. To solve the ambiguity that may happen in finding the absolute locations of robot and landmarks, we have proposed two separate methods, the lowest position error (LPE) and minimum variance position estimator (MVPE). Another challenge in RMF is data association problem where we also propose an algorithm which works by using motion sensors without engaging in their cumulative error. To apply these methods, we switch successively between the absolute and relative positions of landmarks. Having a sufficient number of landmarks in the environment, our algorithm estimates the positions of robot and landmarks without using motion sensors and kinematics of robot. Motion sensors are only used for data association. The empirical studies on the proposed RMF-SLAM algorithm with the LPE or MVPE methods show a better accuracy in localization of robot and landmarks in comparison with the absolute map filter SLAM.     

Vision-based global localization and mapping for mobile robots

We have previously developed a mobile robot system which uses scale-invariant visual landmarks to localize and simultaneously build three-dimensional (3-D) maps of unmodified environments. In this paper, we examine global localization, where the robot localizes itself globally, without any prior location estimate. This is achieved by matching distinctive visual landmarks in the current frame to a database map. A Hough transform approach and a RANSAC approach for global localization are compared, showing that RANSAC is much more efficient for matching specific features, but much worse for matching nonspecific features. Moreover, robust global localization can be achieved by matching a small submap of the local region built from multiple frames. This submap alignment algorithm for global localization can be applied to map building, which can be regarded as alignment of multiple 3-D submaps. A global minimization procedure is carried out using the loop closure constraint to avoid the effects of slippage and drift accumulation. Landmark uncertainty is taken into account in the submap alignment and the global minimization process. Experiments show that global localization can be achieved accurately using the scale-invariant landmarks. Our approach of pairwise submap alignment with backward correction in a consistent manner produces a better global 3-D map.     

Range-only SLAM with indistinguishable landmarks; a constraint programming approach

This paper deals with the simultaneous localization and mapping problem (SLAM) for a robot. The robot has to build a map of its environment while localizing itself using a partially built map. It is assumed that (i) the map is made of point landmarks, (ii) the landmarks are indistinguishable, (iii) the only exteroceptive measurements correspond to the distance between the robot and the landmarks. This paper shows that SLAM can be cast into a constraint network the variables of which being trajectories, digraphs and subsets of \(\mathbb {R}^{n}.\) Then, we show how constraint propagation can be extended to deal with such generalized constraint networks. As a result, due to the redundancy of measurements of SLAM, we demonstrate that a constraint-based approach provides an efficient backtrack-free algorithm able to solve our SLAM problem in a guaranteed way.     

Multi-observation sensor resetting localization with ambiguous landmarks

Successful approaches to the robot localization problem include particle filters, which estimate non-parametric localization belief distributions. Particle filters are successful at tracking a robot’s pose, although they fare poorly at determining the robot’s global pose. The global localization problem has been addressed for robots that sense unambiguous visual landmarks with sensor resetting, by performing sensor-based resampling when the robot is lost. Unfortunately, for robots that make sparse, ambiguous and noisy observations, standard sensor resetting places new pose hypotheses across a wide region, in poses that may be inconsistent with previous observations. We introduce multi-observation sensor resetting (MOSR) to address the localization problem with sparse, ambiguous and noisy observations. MOSR merges observations from multiple frames to generate new hypotheses more effectively. We demonstrate experimentally on the NAO humanoid robots that MOSR converges more efficiently to the robot’s true pose than standard sensor resetting, and is more robust to systematic vision errors.     

Monocular Vision for Mobile Robot Localization and Autonomous Navigation

This paper presents a new real-time localization system for a mobile robot. We show that autonomous navigation is possible in outdoor situation with the use of a single camera and natural landmarks. To do that, we use a three step approach. In a learning step, the robot is manually guided on a path and a video sequence is recorded with a front looking camera. Then a structure from motion algorithm is used to build a 3D map from this learning sequence. Finally in the navigation step, the robot uses this map to compute its localization in real-time and it follows the learning path or a slightly different path if desired. The vision algorithms used for map building and localization are first detailed. Then a large part of the paper is dedicated to the experimental evaluation of the accuracy and robustness of our algorithms based on experimental data collected during two years in various environments.     

基于人工路标的易部署室内机器人全局定位系统

在一些布局易变或存在较多动态障碍物的室内,移动机器人的全局定位依然面临较大的应用挑战.针对这类场景,实现了一种新的基于人工路标的易部署室内机器人全局定位系统.该系统将人工路标粘贴在不易被遮挡的天花板上来作为参照物,仅依赖一个摄像头即能实现稳定的全局定位.整个系统根据具体的功能分为地图构建和全局定位两个过程.在地图构建过程中,系统使用激光SLAM算法所输出的位姿估计结果为基准,根据相机对路标点的观测信息来自动估计人工路标点在全局坐标系中的位姿,建立人工路标地图.而在全局定位过程中,该系统则是根据相机对地图中已知位姿的人工路标点的观测信息,结合里程计与IMU融合的预积分信息来对位姿进行实时估计.充分的实验测试表明,机器人在该系统所部署范围内运行的定位误差稳定在10 cm以内,且运行过程可以保证实时位姿输出,满足典型实际室内移动机器人全局定位的应用需求.     

Dual FastSLAM: Dual Factorization of the Particle Filter Based Solution of the Simultaneous Localization and Mapping Problem

The process of building a map with a mobile robot is known as the Simultaneous Localization and Mapping (SLAM) problem, and is considered essential for achieving true autonomy. The best existing solutions to the SLAM problem are based on probabilistic techniques, mainly derived from the basic Bayes Filter. A recent approach is the use of Rao-Blackwellized particle filters. The FastSLAM solution factorizes the Bayes SLAM posterior using a particle filter to estimate over the possible paths of the robot and several independent Kalman Filters attached to each particle to estimate the location of landmarks conditioned to the robot path. Although there are several successful implementations of this idea, there is a lack of applications to indoor environments where the most common feature is the line segment corresponding to straight walls. This paper presents a novel factorization, which is the dual of the existing FastSLAM one, that decouples the SLAM into a map estimation and a localization problem, using a particle filter to estimate over maps and a Kalman Filter attached to each particle to estimate the robot pose conditioned to the given map. We have implemented and tested this approach, analyzing and comparing our solution with the FastSLAM one, and successfully building feature based maps of indoor environments.     

Vision-Based SLAM: Stereo and Monocular Approaches

Building a spatially consistent model is a key functionality to endow a mobile robot with autonomy. Without an initial map or an absolute localization means, it requires to concurrently solve the localization and mapping problems. For this purpose, vision is a powerful sensor, because it provides data from which stable features can be extracted and matched as the robot moves. But it does not directly provide 3D information, which is a difficulty for estimating the geometry of the environment. This article presents two approaches to the SLAM problem using vision: one with stereovision, and one with monocular images. Both approaches rely on a robust interest point matching algorithm that works in very diverse environments. The stereovision based approach is a classic SLAM implementation, whereas the monocular approach introduces a new way to initialize landmarks. Both approaches are analyzed and compared with extensive experimental results, with a rover and a blimp.     

Dependence maximization localization: a novel approach to 2D street-map-based robot localization

Recently, localization methods based on detailed maps constructed using simultaneous localization and mapping have been widely used for mobile robot navigation. However, the cost of building such maps increases rapidly with expansion of the target environment. Here, we consider the problem of localization of a mobile robot based on existing 2D street maps. Although a large amount of research on this topic has been reported, the majority of the previous studies have focused on car-like vehicles that navigate on roadways; thus, the efficacy of such methods for sidewalks is not yet known. In this paper, we propose a novel localization approach that can be applied to sidewalks. Whereas roadways are typically marked, e.g. by white lines, sidewalks are not and, therefore, road boundary detection is not straightforward. Thus, obtaining exact correspondence between sensor data and a street map is complex. Our approach to overcoming this difficulty is to maximize the statistical dependence between the sensor data and the map, and localization is achieved through maximization of a mutual-information-based criterion. Our method employs a computationally efficient estimator of squared-loss mutual information, through which we achieve near real-time performance. The efficacy of our method is evaluated through localization experiments using real-world data-sets     

特征序列数据关联机器人同步定位与地图构建

针对噪声不确定性增大的数据关联问题,提出特征点序列数据关联机器人同步定位与地图构建方法。根据机器人环境特征点的空间几何信息,基于图论建立特征点间的信息相关性。利用相邻两步的特征点观测信息协方差的变化,转化成求解特征点TSP问题和特征序列最大相关函数,以此确定所观测特征点的数据关联。实验证明,提出的方法可在噪声不确定性增大的情况下,保证同步定位与地图构建算法的一致性。     

Selecting Landmarks for Localization in Natural Terrain

We describe techniques to optimally select landmarks for performing mobile robot localization by matching terrain maps. The method is based upon a maximum-likelihood robot localization algorithm that efficiently searches the space of possible robot positions. We use a sensor error model to estimate a probability distribution over the terrain expected to be seen from the current robot position. The estimated distribution is compared to a previously generated map of the terrain and the optimal landmark is selected by minimizing the predicted uncertainty in the localization. This approach has been applied to the generation of a sensor uncertainty field that can be used to plan a robot's movements. Experiments indicate that landmark selection improves not only the localization uncertainty, but also the likelihood of success. Examples of landmark selection are given using real and synthetic data.     

Localization and map building using laser range sensors in outdoor applications

This paper presents the design of a high accuracy outdoor navigation system based on standard dead reckoning sensors and laser range and bearing information. The data validation problem is addressed using laser intensity information. The beacon design aspect and location of landmarks are also discussed in relation to desired accuracy and required area of operation. The results are important for simultaneous localization and map building applications (SLAM), since the feature extraction and validation are resolved at the sensor level using laser intensity. This facilitates the use of additional natural landmarks to improve the accuracy of the localization algorithm. The modelling aspects to implement SLAM with beacons and natural features are also presented. These results are of fundamental importance because the implementation of the algorithm does not require the surveying of beacons. Furthermore we demonstrate that by using natural landmarks accurate localization can be achieved by only requiring the initial estimate of the position of the vehicle. The algorithms are validated in outdoor environments using a standard utility car retrofitted with the navigation sensors and a 1 cm precision Kinematic GPS used as ground truth. © 2000 John Wiley & Sons, Inc.     

Reliable and efficient landmark-based localization for mobile robots

This paper describes an efficient and robust localization system for indoor mobile robots and AGVs. The system utilizes a sensor that measures bearings to artificial landmarks, and an efficient triangulation method. We present a calibration method for the system components and overcome typical problems for sensors of the mentioned type, which are localization in motion and incorrect identification of landmarks. The resulting localization system was tested on a mobile robot. It consumes less than 4% of a Pentium4 3.2 GHz processing power while providing an accurate and reliable localization result every 0.5 s. The system was successfully incorporated within a real mobile robot system which performs many other computational tasks in parallel.     

Landmark detection in mobile robotics using fuzzy temporal rules

Detection of landmarks is essential in mobile robotics for navigation tasks like building topological maps or robot localization. Doors are one of the most common landmarks since they show the topological structure of indoor environments. In this paper, the novel paradigm of fuzzy temporal rules is used for detecting doors from the information of ultrasound sensors. This paradigm can be used both to model the necessary knowledge for detection and to consider the temporal variation of several sensor signals. Experimental results using a Nomad 200 mobile robot in a real environment produce 91% of doors were correctly detected, which show the reliability and robustness of the system.     

Autonomous vision-based robotic exploration and mapping using hybrid maps and particle filters

This paper addresses the problem of exploring and mapping an unknown environment using a robot equipped with a stereo vision sensor. The main contribution of our work is a fully automatic mapping system that operates without the use of active range sensors (such as laser or sonic transducers), can operate on-line and can consistently produce accurate maps of large-scale environments. Our approach implements a Rao-Blackwellised particle filter (RBPF) to solve the simultaneous localization and mapping problem and uses efficient data structures for real-time data association, mapping, and spatial reasoning. We employ a hybrid map representation that infers 3D point landmarks from image features to achieve precise localization, coupled with occupancy grids for safe navigation. We demonstrate two exploration approaches, one based on a greedy strategy and one based on an iteratively deepening strategy. This paper describes our framework and implementation, and presents our exploration method, and experimental results illustrating the functionality of the system.     

SLAM问题中的模糊几何地图与顶点自定位法

在模糊几何地图的基础上提出了顶点定位法来解决机器人的室内SLAM中的实时自定位问题．顶点定位法是从传感信息中抽取多边形顶点作为路标进行定位．顶点定位法与传统的边匹配定位法比较有计算量小,定位精度高等优点．此外本文提出了基于空间距离的传感数据两次分类方法构建模糊几何地图,提高了数字地图精确度．实验结果表明其性能优于传统的方法．     

A Neuro-Fuzzy Assisted Extended Kalman Filter-Based Approach for Simultaneous Localization and Mapping (SLAM) Problems

Extended Kalman filter (EKF) has been a popular choice to solve simultaneous localization and mapping (SLAM) problems for mobile robots or vehicles. However, the performance of the EKF depends on the correct a priori knowledge of process and sensor/measurement noise covariance matrices (Q and R, respectively). Imprecise knowledge of these statistics can cause significant degradation in performance. The present paper proposes the development of a new neurofuzzy based adaptive Kalman filtering algorithm for simultaneous localization and mapping of mobile robots or vehicles, which attempts to estimate the elements of the R matrix of the EKF algorithm, at each sampling instant when a ldquomeasurement updaterdquo step is carried out. The neuro-fuzzy based supervision for the EKF algorithm is carried out with the aim of reducing the mismatch between the theoretical and the actual covariance of the innovation sequences. The free parameters of the neuro-fuzzy system are learned offline, by employing particle swarm optimization in the training phase, which configures the training problem as a high-dimensional stochastic optimization problem. By employing a mobile robot to localize and simultaneously acquire the map of the environment, under several benchmark environment situations with varying landmarks and under several conditions of wrong knowledge of sensor statistics, the performance of the proposed scheme has been evaluated. It has been successfully demonstrated that in each case, the neuro-fuzzy assistance is able to improve highly unpredictable, degrading performance of the EKF and can provide robust and accurate solutions.     

Convergence and Consistency Analysis for Extended Kalman Filter Based SLAM

This paper investigates the convergence properties and consistency of extended Kalman filter (EKF) based simultaneous localization and mapping (SLAM) algorithms. Proofs of convergence are provided for the nonlinear two-dimensional SLAM problem with point landmarks observed using a range-and-bearing sensor. It is shown that the robot orientation uncertainty at the instant when landmarks are first observed has a significant effect on the limit and/or the lower bound of the uncertainties of the landmark position estimates. This paper also provides some insights to the inconsistencies of EKF based SLAM that have been recently observed. The fundamental cause of EKF SLAM inconsistency for two basic scenarios are clearly stated and associated theoretical proofs are provided.     

一种新颖的基于两个特征点的室内移动机器人定位方法

提出了一种新颖的基于两个特征点的室内移动机器人定位方法。与已有的几何位姿估计方法或航标匹配方法不同，该方法不需要人工航标，也不需要准确的环境地图，只需一幅由传统的CCD相机拍摄的图像。从机器人接近的目标上选取相对于地面等高的两个点作为两个特征点。基于这两点建立一个目标坐标系。在相机平视且这两个特征点与相机投影中心相对于地面不是恰好等高的条件下，就可以根据这两个特征点在图像中的坐标确定机器人相对于目标坐标系的位置和运动方向。该方法非常灵活，适用范围广，可以大大简化机器人定位问题。试验结果表明这一新的方法不仅简单灵活而且具有很高的定位精度。