Robot Localization Research Articles

Sequential batch fusion magnetic anomaly navigation for a low-cost indoor mobile robot

This paper describes a new magnetic map-matching algorithm structure based on sequential batch fusion. The proposed algorithm enables real-time computation and more stable indoor localization of mobile robots. Conventional magnetic map-matching-based localization has the disadvantage that real-time navigation is not possible when using a batch process, and navigation fails or has significant localization errors owing to similar magnetic field distortion. This study proposes that measurement updates should be performed based on the convergence of weights with several grid points by repeatedly updating the weights of the grid points using magnetic field similarity. The performance of the proposed navigation algorithm was verified using an open dataset, and the proposed technique had a position error of 1 m even in a path in which navigation using the conventional method failed. It provides an indoor mobile robot navigation algorithm that is significantly cheaper than other conventional sensor-based indoor navigation systems.

A robust method for approximate visual robot localization in feature-sparse sewer pipes.

Buried sewer pipe networks present many challenges for robot localization systems, which require non-standard solutions due to the unique nature of these environments: they cannot receive signals from global positioning systems (GPS) and can also lack visual features necessary for standard visual odometry algorithms. In this paper, we exploit the fact that pipe joints are equally spaced and develop a robot localization method based on pipe joint detection that operates in one degree-of-freedom along the pipe length. Pipe joints are detected in visual images from an on-board forward facing (electro-optical) camera using a bag-of-keypoints visual categorization algorithm, which is trained offline by unsupervised learning from images of sewer pipe joints. We augment the pipe joint detection algorithm with drift correction using vision-based manhole recognition. We evaluated the approach using real-world data recorded from three sewer pipes (of lengths 30, 50 and 90m) and benchmarked against a standard method for visual odometry (ORB-SLAM3), which demonstrated that our proposed method operates more robustly and accurately in these feature-sparse pipes: ORB-SLAM3 completely failed on one tested pipe due to a lack of visual features and gave a mean absolute error in localization of approximately 12%-20% on the other pipes (and regularly lost track of features, having to re-initialize multiple times), whilst our method worked successfully on all tested pipes and gave a mean absolute error in localization of approximately 2%-4%. In summary, our results highlight an important trade-off between modern visual odometry algorithms that have potentially high precision and estimate full six degree-of-freedom pose but are potentially fragile in feature sparse pipes, versus simpler, approximate localization methods that operate in one degree-of-freedom along the pipe length that are more robust and can lead to substantial improvements in accuracy.

Point-based metric and topological localisation between lidar and overhead imagery

In this paper, we present a method for solving the localisation of a ground lidar using overhead imagery only. Public overhead imagery such as Google satellite images are readily available resources. They can be used as the map proxy for robot localisation, relaxing the requirement for a prior traversal for mapping as in traditional approaches. While prior approaches have focused on the metric localisation between range sensors and overhead imagery, our method is the first to learn both place recognition and metric localisation of a ground lidar using overhead imagery, and also outperforms prior methods on metric localisation with large initial pose offsets. To bridge the drastic domain gap between lidar data and overhead imagery, our method learns to transform an overhead image into a collection of 2D points, emulating the resulting point-cloud scanned by a lidar sensor situated near the centre of the overhead image. After both modalities are expressed as point sets, point-based machine learning methods for localisation are applied.

EANet: A Point Cloud Registration Network Based on EdgeConv with Dual Attention Mechanism

In machine vision, point cloud registration is one of the core elements, which has been applied to many fields such as robot localisation, medical image processing, and autonomous driving. The main problem solved by point cloud registration is to solve the rotation matrix and translation vectors from one point cloud to another. This paper proposes a point cloud registration network based on EdgeConv with spatial attention mechanism. EdgeConv can dynamically construct graph structure and build topological relationships within the point cloud, so that each point can obtain multi-level feature representation; the attention mechanism can capture contextual information and improve the accuracy of the registration. Experimental results show that EANet has higher registration accuracy, stronger generalisation ability and robustness compared to ICP, Go ICP, FGR, PCRNet and PointNetLK.

An Accuracy Reconfigurable Vector Accelerator based on Approximate Logarithmic Multipliers for Energy-Efficient Computing

The approximate logarithmic multiplier proposed by Mitchell provides an efficient alternative for processing dense multiplication or multiply-accumulate operations in applications such as image processing and real-time robotics. It offers the advantages of small area, high energy efficiency and is suitable for applications that do not necessarily achieve high accuracy. However, its maximum error of 11.1% makes it challenging to deploy in applications requiring relatively high accuracy. This paper proposes a novel operand decomposition method (OD) that decomposes one multiplication into the sum of multiple approximate logarithmic multiplications to widely reduce Mitchell multiplier errors while taking full advantage of its area savings. Based on the proposed OD method, this paper also proposes an accuracy reconfigurable multiply-accumulate (MAC) unit that provides multiple reconfigurable accuracies with high parallelism. Compared to a MAC unit consisting of accurate multipliers, the area is significantly reduced to less than half, improving the hardware parallelism while satisfying the required accuracy for various scenarios. The experimental results show the excellent applicability of our proposed MAC unit in image smoothing and robot localization and mapping application. We have also designed a prototype processor that integrates the minimum functionality of this MAC unit as a vector accelerator and have implemented a software-level accuracy reconfiguration in the form of an instruction set extension. We experimentally confirmed the correct operation of the proposed vector accelerator, which provides the different degrees of accuracy and parallelism at the software level.

GAN-Based Robust Motion Planning for Mobile Robots Against Localization Attacks

Motion planning (MP) is essential but challenging for mobile robots. Most of the existing MP methods, at each instant, compute an action based on the states of the robot and the surrounding obstacles, assuming that the robot's localization module is attack-free. Unfortunately, the localization module is vulnerable to sensor attacks, such as GPS spoofing attacks. In this letter, we propose a novel robust framework, <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">GAN-MP</monospace> , where a generative adversarial network (GAN) is exploited to mitigate the localization attacks, and the state-of-the-art MP methods are applied to generate collision-free actions. Specifically, <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">GAN-MP</monospace> aims to learn a Generator to compute the potential positions of the robot. Consequently, it can reserve the robot's benign states while correcting the attacked states. Hence, it is suitable for benign and attacked scenarios without any attack detector. In addition, <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">GAN-MP</monospace> is method-agnostic and can be easily integrated with any existing MP method. We instantiate <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">GAN-MP</monospace> with a deep reinforcement learning method to demonstrate its design and training processes. Comprehensive experiments show that <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">GAN-MP</monospace> can mitigate localization attacks and guarantee safe motion. We also demonstrate the robustness and generalization of <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">GAN-MP</monospace> .

Robust Simultaneous Localization and Mapping Using Range and Bearing Estimation of Radio Ultra High Frequency Identification Tags

In this article, we consider an indoor simultaneous localization and mapping (SLAM) problem for a mobile robot measuring the phase of the signal backscattered by a set of passive radio ultra high frequency identification (ID) tags, deployed in unknown position on the ceiling of the environment. The solution approach is based on the introduction, for each radio frequency identification (RFID) tag observed, of a multihypothesis extended Kalman filter (MHEKF) which, based on the measured phases and on the wheel encoder readings, provides an estimate of the range and of the bearing of the observed tag with respect to the robot. This information is then used in an extended Kalman filter (EKF) solving the SLAM problem. Since an effective range and bearing estimate is available only after some steps, a resilient module is added to the algorithm to evaluate the reliability of the position estimate of each observed tag. As shown through numerical and experimental results, this makes the proposed approach robust with respect to several kinds of unmodeled disturbances, like multipath effects or even the unexpected change of the position of a tag.

Adaptive Adjustment of Factor’s Weight for a Multi-Sensor SLAM

A multi-sensor fusion simultaneous localization and mapping(SLAM) method based on factor graph optimization that can adaptively modify the weight of the graph factor is proposed in this study, to enhance the localization and mapping capability of autonomous robots in tough situations. Firstly, the algorithm fuses multi-lines lidar, monocular camera, and inertial measurement unit(IMU) in the odometry. Second, the factor graph is constructed using lidar and visual odometry as the unary edge and binary edge constraints, respectively, with the motion determined by IMU odometry serving as the primary odometry in the system. Finally, different increments of IMU odometry, lidar odometry and visual odometry are computed as favor factors to realize the adaptive adjustment of the factor’s weight. The suggested method has greater location accuracy and a better mapping effect in complex situations when compared to previous algorithms.

A ROS-based distributed multi-robot localization and orientation strategy for heterogeneous robots

The problem of estimating and tracking the location and orientation of a mobile robot by another in heterogeneous distributed multi-robots is studied in this paper. We propose a distributed multi-robot localization strategy (DMLS) that is Robotic Operating System (ROS) based. It consists of an algorithm that fuses data of diverse sensors from 2 heterogeneous robots that are not connected within their transform trees to localize and measure the relative position and orientation.The method exploits the robust detection of the Convolutional Neural Networks (CNN) and the accurate relative position measurements from the local costmap. The algorithm is composed of two parts: The localization part and the relative orientation measurement part. Localization is done by optimization and alignment calibration of the CNN output with the costmap in an individual robot. The relative orientation measurement is done by a collaborative multi-robot fusing of diverse sensor data to align and synchronize the transform frames of both robots in their costmaps. To illustrate the performance of this strategy, the proposed method is compared with a conventional object localization and orientation measuring method that uses computer vision and QR codes. The results show that this proposed method is robust and accurate while maintaining a degree of simplicity and efficiency in costs. The paper also presents various application experiments in laboratory and simulation environments. By using the proposed method, distributed multi-robots collaborate to achieve collective intelligence from individuals, which increases team performance.

Design and Manufacture of an Optimised Side-Shifted PPM EMAT Array for Use in Mobile Robotic Localisation.

Guided wave Electro Magnetic Acoustic Transducers (EMATs) offer an elegant method for structural inspection and localisation relative to geometric features, such as welds. This paper presents a Lorentz force EMAT construction framework, where a numerical model has been developed for optimising Printed Circuit Board (PCB) coil parameters as well as a methodology for optimising magnet array parameters to a user's needs. This framework was validated experimentally to show its effectiveness through comparison to an industry built EMAT. The framework was then used to design and manufacture a Side-Shifted Unidirectional Periodic Permanent Magnet (PPM) EMAT for use on a mobile robotic system, which uses guided waves for ranging to build internal maps of a given subject, identifying welded sections, defects and other structural elements. The unidirectional transducer setup was shown to operate in simulation and was then manufactured to compare to the bidirectional transmitter and two-receiver configurations on a localisation system. The unidirectional setup was shown to have clear benefits over the bidirectional setup for mapping an unknown environment using guided waves as there were no dead spots of mapping where signal direction could not be interpreted. Additionally, overall package size was significantly reduced, which in turn allows more measurements to be taken within confined spaces and increases robotic crawler mobility.

A Dynamic Scene Vision SLAM Method Incorporating Object Detection and Object Characterization

Simultaneous localization and mapping (SLAM) based on RGB-D cameras has been widely used for robot localization and navigation in unknown environments. Most current SLAM methods are constrained by static environment assumptions and perform poorly in real-world dynamic scenarios. To improve the robustness and performance of SLAM systems in dynamic environments, this paper proposes a new RGB-D SLAM method for indoor dynamic scenes based on object detection. The method presented in this paper improves on the ORB-SLAM3 framework. First, we designed an object detection module based on YOLO v5 and relied on it to improve the tracking module of ORB-SLAM3 and the localization accuracy of ORB-SLAM3 in dynamic environments. The dense point cloud map building module was also included, which excludes dynamic objects from the environment map to create a static environment point cloud map with high readability and reusability. Full comparison experiments with the original ORB-SLAM3 and two representative semantic SLAM methods on the TUM RGB-D dataset show that: the method in this paper can run at 30+fps, the localization accuracy improved to varying degrees compared to ORB-SLAM3 in all four image sequences, and the absolute trajectory accuracy can be improved by up to 91.10%. The localization accuracy of the method in this paper is comparable to that of DS-SLAM, DynaSLAM and the two recent target detection-based SLAM algorithms, but it runs faster. The RGB-D SLAM method proposed in this paper, which combines the most advanced object detection method and visual SLAM framework, outperforms other methods in terms of localization accuracy and map construction in a dynamic indoor environment and has a certain reference value for navigation, localization, and 3D reconstruction.

SemanticLoop: Loop Closure With 3D Semantic Graph Matching

Loop closure can effectively correct the accumulated error in robot localization, which plays a critical role in the long-term navigation of the robot. Traditional appearance-based methods rely on local features and are prone to failure in ambiguous environments. On the other hand, object recognition can infer objects' category, pose, and extent. These objects can serve as stable semantic landmarks for viewpoint-independent and non-ambiguous loop closure. However, there is a critical object-level data association problem due to the lack of efficient and robust algorithms. We introduce a novel object-level data association algorithm, which incorporates IoU, instance-level embedding, and detection uncertainty, formulated as a linear assignment problem. Then, we model the objects as TSDF volumes and represent the environment as a 3D graph with semantics and topology. Next, we propose a graph matching-based loop detection based on the reconstructed 3D semantic graphs and correct the accumulated error by aligning the matched objects. Finally, we refine the object poses and camera trajectory in an object-level pose graph optimization. Experimental results show that the proposed object-level data association method significantly outperforms the commonly used nearest neighbor method in accuracy. Our graph matching-based loop closure is more robust to environmental appearance changes than existing appearance-based methods.

KPPR: Exploiting Momentum Contrast for Point Cloud-Based Place Recognition

Place recognition plays an important role in robot localization and SLAM. Being able to retrieve the current position in a given map allows, for instance, localizing without relying on GPS reception. In this letter, we address the problem of point cloud-based place recognition, we especially focus on reducing the often significant training time needed by learning-based approaches. We propose a novel neural network architecture that first extracts local features using a pre-trained encoder network plus a stem architecture. The local features are aggregated to a global descriptor, which allows us to compute the similarity between locations. In line with with several existing approaches, we target the generation of descriptors, which are similar for spatially near locations and dissimilar to other places. By exploiting the recent success of feature banks, we are able to bypass the computation of the negative examples, which enables faster training, bigger batch sizes, or the use of more sophisticated networks. As a key result, able to speed up the training process by a factor of 17 against the most common training procedure while increasing also the performance.

The Integrated Strategy of LIDAR Points’ Evaluation Localization and Lateral Tracking Optimization for a New Parking Robot's Tight Space Transportation

With the increase of car's number, the problem of insufficient parking space in cities is becoming more and more prominent. The high-density parking lots using parking robots can greatly improve space utilization. However, there is a great collision risk in the parking lot's tight space navigation. So, precise LIDAR localization and trajectory tracking control are the key technologies of autonomous driving along a predetermined path. Due to the laser points’ sparse character, the LIDAR points’ extracted features have distribution errors. In order to further optimize the LIDAR's localization, this article establishes the feature's error ellipsoid model, and the model's information and error entropies are calculated separately. The error entropy is utilized to optimize the feature-matching weight and improve the localization accuracy. Based on the higher localization result, a state-of-the-art lateral tracking model is proposed to address the challenges faced by the long parking robot. Then, the adaptive fuzzy control is designed to achieve precise control of wheel motion. Finally, an experimental platform is built to compare the effectiveness of different positioning and tracking algorithms. The comparison results show that the integration of laser evaluation localization and lateral tracking optimization algorithm can provides a collision-free improvement of 50% in the parking lot's tight spaces.

A Dynamic Window-Based UWB-Odometer Fusion Approach for Indoor Positioning

The positioning system based on ultrawideband (UWB) can achieve centimeter-level positioning accuracy, which is now widely used for indoor positioning. However, UWB is subject to multipath effects and nonline-of-sight (NLOS), which can cause positioning errors. And a UWB positioning system with a minimum of three anchors is costly and difficult to deploy, which is not an economical option. This article presents a low-cost UWB-odometer fusion method for mobile robot localization, which enables global localization using only one UWB anchor. To improve the positioning accuracy and eliminate the influence of cumulative odometer error, we propose a dynamic window-based particle filter (DWBPF). It solves the problem of particle convergence and track loss. It also adaptively modifies the score weights according to the power difference of the UWB to achieve a more robust and accurate positioning. The experimental result shows that the system has a high positioning accuracy of 0.061 m.

Hot-NetVLAD: Learning Discriminatory Key Points for Visual Place Recognition

Hot-NetVLAD implements a hot-spot detector on a learned local key-patch descriptor algorithm for Visual Place Recognition (VPR), thereby greatly cutting down the size of features extracted. The hot-spots pinpoint which regions are crucial for comparison when performing VPR. As hot-spots land on only a small portion of the feature space, the number of local descriptors extracted is greatly reduced. A novel method to extract ground truths of hot-spots in the context of VPR is proposed so that the hot-spot detector in Hot-NetVLAD can be trained for VPR purposes. Hot-NetVLAD is evaluated on the Pittsburgh250k and Tokyo24/7 datasets. While results show that Hot-NetVLAD trades some accuracy loss for storage efficiency, the recall remains competitive when compared to state-of-the-art methods. Furthermore, identified hot-spots bring new insights to key regions required for VPR, as they tend to fall on distinguishable static objects in the scene. This can potentially be applied to increase the robustness of mobile robot localization by increasing resilience to dynamic environments, whilst still being able to perform static obstacle matching effectively.

SPINS: A structure priors aided inertial navigation system

AbstractWe propose a navigation system combining sensor‐aided inertial navigation and prior‐map‐based localization to improve the stability and accuracy of robot localization in structure‐rich environments. Specifically, we adopt point, line, and plane features in the navigation system to enhance the feature richness in low‐texture environments and improve the localization reliability. We additionally integrate structure prior information of the environments to constrain the localization drifts and improve the accuracy. The prior information is called structure priors and parameterized as low‐dimensional relative distances/angles between different geometric primitives. The localization is formulated as a graph‐based optimization problem that contains sliding‐window‐based variables and factors, including Inertial Measurement Unit, heterogeneous features, and structure priors. A limited number of structure priors are selected based on the information gain to alleviate the computation burden. Finally, the proposed framework is extensively tested on synthetic data, public data sets, and, more importantly, on the real Unmanned Aerial Vehicle flight data obtained from both indoor and outdoor inspection tasks. The results show that the proposed scheme can effectively improve the accuracy and robustness of localization for autonomous robots in civilian applications.

Design of an Application-specific VLIW Vector Processor for ORB Feature Extraction

In computer-vision feature extraction algorithms, compressing the image into a sparse set of trackable keypoints, empowers navigation-critical systems such as Simultaneous Localization And Mapping (SLAM) in autonomous robots, and also other applications such as augmented reality and 3D reconstruction. Most of those applications are performed in battery-powered gadgets featuring in common a very stringent power-budget. Near-to-sensor computing of feature extraction algorithms allows for several design optimizations. First, the overall on-chip memory requirements can be lessened, and second, the internal data movement can be minimized. This work explores the usage of an Application Specific Instruction Set Processor (ASIP) dedicated to perform feature extraction in a real-time and energy-efficient manner. The ASIP features a Very Long Instruction Word (VLIW) architecture comprising one RV32I RISC-V and three vector slots. The on-chip memory sub-system implements parallel multi-bank memories with near-memory data shuffling to enable single-cycle multi-pattern vector access. Oriented FAST and Rotated BRIEF (ORB) are thoroughly explored to validate the proposed architecture, achieving a throughput of 140 Frames-Per-Second (FPS) for VGA images for one scale, while reducing the number of memory accesses by 2 orders of magnitude as compared to other embedded general-purpose architectures.

Joint actuator fault estimation and localization under Round-Robin protocol for wheeled mobile robot

In this paper, the joint actuator fault estimation (AFE) and the wheeled mobile robot (WMR) localization under the Round-Robin protocol (RRP) problems are concerned. In order to complete the joint AFE and the WMR localization, a nominal joint system is constructed, which consists of the drive subsystem and WMR localization subsystem. In the drive subsystem of the WMR, the DC motor is used as an actuator to drive the WMR. When the faults occur, the performance of the actuator will be degraded, and the mobility of the WMR will be affected. In order to maintain a satisfactory mobility of the WMR, the faults need to be estimated timely such that some appropriate decisions or remedies can be made. In the WMR localization subsystem, for saving the network resources, the RRP is introduced to schedule the transmission of sensor measurements used for the WMR localization. The purpose of this paper is, by designing a time-varying filter for the constructed joint nominal system, to ensure the filtering error to meet the given [Formula: see text] performance requirement, such that the joint AFE and the WMR localization can be achieved simultaneously. Specifically, the sufficient condition is derived first and then the desired filter gain is designed by the recursive linear matrix inequality technology. Finally, a simulation experiment is conducted to certify the usefulness of the proposed algorithm.

A SLAM-Based Localization and Navigation System for Social Robots: The Pepper Robot Case

Robot navigation in indoor environments has become an essential task for several applications, including situations in which a mobile robot needs to travel independently to a certain location safely and using the shortest path possible. However, indoor robot navigation faces challenges, such as obstacles and a dynamic environment. This paper addresses the problem of social robot navigation in dynamic indoor environments, through developing an efficient SLAM-based localization and navigation system for service robots using the Pepper robot platform. In addition, this paper discusses the issue of developing this system in a way that allows the robot to navigate freely in complex indoor environments and efficiently interact with humans. The developed Pepper-based navigation system has been validated using the Robot Operating System (ROS), an efficient robot platform architecture, in two different indoor environments. The obtained results show an efficient navigation system with an average localization error of 0.51 m and a user acceptability level of 86.1%.