Search

High‐definition maps are essential for autonomous vehicle navigation, but indoor parking lots remain poorly mapped due to high costs. To address this, a crowdsourcing model gathers data from consumer‐grade sensors in mass‐produced vehicles to create semantic maps. Indoor parking lots lack GNSS signals, and most of them do not have high‐definition maps or navigation maps as references, making it difficult to ensure the accuracy of the final mapping results. Additionally, the semantic information of indoor parking lots is relatively limited, and the geometric features are overly similar, which significantly impacts the accuracy of point cloud registration. Therefore, this article proposes a crowdsourcing‐based approach, where vehicles generate local semantic maps at the client end and upload them to the cloud. Leveraging the scene characteristics of indoor parking lots, the cloud optimizes and fits a large amount of crowdsourced data to obtain a high‐precision base map without prior information. Enhanced ICP point cloud registration merges subsequent maps with the base. Additionally, parking space occupancy information is provided. This map can furnish the necessary information for Autonomous Valet Parking (AVP) tasks. Evaluation on the BEVIS dataset shows a root mean square error of 0.482446 m for vehicle localization on the cloud‐based map. [ABSTRACT FROM AUTHOR]

Abstract High‐definition maps are essential for autonomous vehicle navigation, but indoor parking lots remain poorly mapped due to high costs. To address this, a crowdsourcing model gathers data from consumer‐grade sensors in mass‐produced vehicles to create semantic maps. Indoor parking lots lack GNSS signals, and most of them do not have high‐definition maps or navigation maps as references, making it difficult to ensure the accuracy of the final mapping results. Additionally, the semantic information of indoor parking lots is relatively limited, and the geometric features are overly similar, which significantly impacts the accuracy of point cloud registration. Therefore, this article proposes a crowdsourcing‐based approach, where vehicles generate local semantic maps at the client end and upload them to the cloud. Leveraging the scene characteristics of indoor parking lots, the cloud optimizes and fits a large amount of crowdsourced data to obtain a high‐precision base map without prior information. Enhanced ICP point cloud registration merges subsequent maps with the base. Additionally, parking space occupancy information is provided. This map can furnish the necessary information for Autonomous Valet Parking (AVP) tasks. Evaluation on the BEVIS dataset shows a root mean square error of 0.482446 m for vehicle localization on the cloud‐based map.

This letter introduces a novel integrated framework for simultaneous localization and mapping (SLAM) tailored for general agricultural applications. The framework combines a cutting‐edge SLAM method, LIO‐SAM, with covariance intersection for sensor fusion. Agricultural robots often operate in unstructured environments with sparse feature points and encounter repeated similar information, such as trees. Therefore, a fusion framework based on 3D SLAM augmented with additional information, such as feature‐independent GPS data, becomes essential. This study proposes an integrated SLAM framework by introducing a convergence strategy based on covariance analysis, incorporating a state‐of‐the‐art 3D SLAM technique. The convergence methods, namely "dynamic weight assignment" and "winner takes all", are presented alternatively, tailored to seamlessly integrate with the proposed framework. Evaluations using a public dataset and an experiment demonstrate the effectiveness of the approach through numerical analysis and visual representation. The results illustrate that this method surpasses conventional approaches in accurately estimating the robot's position. In the future, this research will focus on automating crop cultivation and harvesting by integrating the proposed system with robot arm control. [ABSTRACT FROM AUTHOR]

Abstract Sampling is a crucial concern for outdoor light detection and ranging (LiDAR) point cloud registration due to the large amounts of point cloud. Numerous algorithms have been devised to tackle this issue by selecting key points. However, these approaches often necessitate extensive computations, giving rise to challenges related to computational time and complexity. This letter proposes a multi‐domain uniform sampling method (MDU‐sampling) for large‐scale outdoor LiDAR point cloud registration. The feature extraction based on deep learning aggregates information from the neighbourhood, so there is redundancy between adjacent features. The sampling method in this paper is carried out in the spatial and feature domains. First, uniform sampling is executed in the spatial domain, maintaining local point cloud uniformity. This is believed to preserve more potential point correspondences and is beneficial for subsequent neighbourhood information aggregation and feature sampling. Subsequently, a secondary sampling in the feature domain is performed to reduce redundancy among the features of neighbouring points. Notably, only points on the same ring in LiDAR data are considered as neighbouring points, eliminating the need for additional neighbouring point search and thereby speeding up processing rates. Experimental results demonstrate that the approach enhances accuracy and robustness compared with benchmarks.

Abstract To improve the autonomous navigation capability of unmanned platforms, an accurate semi‐direct lidar‐inertial odometry algorithm with a new point cloud alignment evaluation metric is proposed. The lidar scan points are corrected through IMU (Inertial Measurement Unit) backward propagation, and the navigation states are predicted through IMU forward propagation. In the update of the navigation states, the point cloud alignment is evaluated based on the distances and the minimum normal direction deviations between the lidar scan points and the local fitted planes of the built map, achieving accurate observations for the navigation states. The proposed algorithm updates navigation states based on the iterative extended Kalman filter. Experiments indicate that the proposed algorithm has higher positioning accuracy than the state‐of‐the‐art method, which gets smaller positioning error (7.868 m) and 52.3% improvement on average.

To improve the autonomous navigation capability of unmanned platforms, an accurate semi‐direct lidar‐inertial odometry algorithm with a new point cloud alignment evaluation metric is proposed. The lidar scan points are corrected through IMU (Inertial Measurement Unit) backward propagation, and the navigation states are predicted through IMU forward propagation. In the update of the navigation states, the point cloud alignment is evaluated based on the distances and the minimum normal direction deviations between the lidar scan points and the local fitted planes of the built map, achieving accurate observations for the navigation states. The proposed algorithm updates navigation states based on the iterative extended Kalman filter. Experiments indicate that the proposed algorithm has higher positioning accuracy than the state‐of‐the‐art method, which gets smaller positioning error (7.868 m) and 52.3% improvement on average. [ABSTRACT FROM AUTHOR]

Sampling is a crucial concern for outdoor light detection and ranging (LiDAR) point cloud registration due to the large amounts of point cloud. Numerous algorithms have been devised to tackle this issue by selecting key points. However, these approaches often necessitate extensive computations, giving rise to challenges related to computational time and complexity. This letter proposes a multi‐domain uniform sampling method (MDU‐sampling) for large‐scale outdoor LiDAR point cloud registration. The feature extraction based on deep learning aggregates information from the neighbourhood, so there is redundancy between adjacent features. The sampling method in this paper is carried out in the spatial and feature domains. First, uniform sampling is executed in the spatial domain, maintaining local point cloud uniformity. This is believed to preserve more potential point correspondences and is beneficial for subsequent neighbourhood information aggregation and feature sampling. Subsequently, a secondary sampling in the feature domain is performed to reduce redundancy among the features of neighbouring points. Notably, only points on the same ring in LiDAR data are considered as neighbouring points, eliminating the need for additional neighbouring point search and thereby speeding up processing rates. Experimental results demonstrate that the approach enhances accuracy and robustness compared with benchmarks. [ABSTRACT FROM AUTHOR]

Abstract In response to the transformer oil sampling requirements within substations, this paper presents the design and development of a highly intelligent transformer oil sampling system. The robot employs a tracked mobile chassis and a gantry robotic arm, offering high mobility stability and operational reliability. The system effectively conducted oil sampling operations in an extra‐high voltage substation, obtaining valuable oil samples that validate the structural and functional reliability of the system, as well as its stability in complex working environments. This research provides a promising solution for transformer maintenance and health monitoring, with the potential to play a significant role in power equipment maintenance.

In response to the transformer oil sampling requirements within substations, this paper presents the design and development of a highly intelligent transformer oil sampling system. The robot employs a tracked mobile chassis and a gantry robotic arm, offering high mobility stability and operational reliability. The system effectively conducted oil sampling operations in an extra‐high voltage substation, obtaining valuable oil samples that validate the structural and functional reliability of the system, as well as its stability in complex working environments. This research provides a promising solution for transformer maintenance and health monitoring, with the potential to play a significant role in power equipment maintenance. [ABSTRACT FROM AUTHOR]

Abstract Small unmanned aerial vehicles (UAVs) have developed rapidly and are widely used for disaster relief, traffic monitoring and military surveillance. To perform these tasks better, it is necessary to improve the environmental perception ability of UAVs in a dynamic environment, including their static and dynamic perception ability. Specifically, both three‐dimensional reconstruction for a static scene and localization for moving objects are required. Simultaneous Localization And Mapping technology has made great progress in static scene structure reconstruction and UAV self‐motion estimation. However, accurate real‐time localization of moving objects is still challenging. In this article, a global averaging based localization method is proposed to locate moving objects for a small UAV platform. Inspired by global structure from motion, this idea is applied to the localization of moving objects. To solve moving object localization, the relative motion estimation and global position optimisation methods are proposed. The proposed method was tested in various scenarios with a several trajectories. The extensive experimental results demonstrate the robustness and effectiveness of the proposed method.

Abstract A novel distributed control architecture for unmanned aircraft system (UASs) based on the new Robot Operating System (ROS) 2 middleware is proposed, endowed with industrial‐grade tools that establish a novel standard for high‐reliability distributed systems. The architecture has been developed for an autonomous quadcopter to design an inclusive solution ranging from low‐level sensor management and soft real‐time operating system setup and tuning to perception, exploration, and navigation modules orchestrated by a finite‐state machine. The architecture proposed in this study builds on ROS 2 with its scalability and soft real‐time communication functionalities, while including security and safety features, optimised implementations of localisation algorithms, and integrating an innovative and flexible path planner for UASs. Finally, experimental results have been collected during tests carried out both in the laboratory and in a realistic environment, showing the effectiveness of the proposed architecture in terms of reliability, scalability, and flexibility.

Abstract Among so‐called active sensors that use self‐generated signals, sonar sensors are more challenging to implement than lidar and radar due in part to their limited angular field of sensing. A common solution to this challenge is scanning sensors that sweep an angular range with successive measurements. However, scanning sensors are particularly problematic for sonar because of the relatively slow sound speed and the inertia of the sonar head. Studies of bat behaviour suggest that bats may eavesdrop on their conspecifics during group flight. In other words, they fuse information gathered by their own active sonar with information they receive by passively listening to peers. Because bats are extremely skilled in using sonar, this behaviour inspired an investigation into whether fusing active and passive sonar can be a solution to the challenges of implementing sonar sensors. A model of fused sensing is defined, and a numerical simulation is used to answer this question on the test bed problem of simultaneous localization and mapping (SLAM). The simulation results show that when the angular range of active sonar and associated noise is relatively small, the robot's performance in solving SLAM is improved.

Abstract Simultaneous localization and mapping (SLAM) refers to a process that permits a mobile robot to build up a map of the environment and, at the same time, to use it to compute its location. One of its most important components is its ability to associate the most recently perceived visual measurement to the one derived from previsited locations, a technique widely known as loop closure detection. In this article, we evolve our previous approach, dubbed as ‘DOSeqSLAM’ by presenting a low complexity loop closure detection pipeline wherein the traversed trajectory (map) is represented by sequence‐based locations (submaps). Each of these groups of images, referred to as place, is generated online through a point tracking repeatability check employed on the perceived visual sensory information. When querying the database, the proper candidate place is selected and, through an image‐to‐image search, the appropriate location is chosen. The method is subjected to an extensive evaluation on seven publicly available datasets, revealing a substantial improvement in computational complexity and performance over its predecessors, while performing favourably against other state‐of‐the art solutions. The system’s effectiveness is owed to the reduced number of places, which, compared to the original approach, is at least one order of magnitude less.

The matching algorithm is an important part of simultaneous location and mapping. Aiming at the problem of large computation and poor real‐time performance of two‐dimensional lidar traditional correlation scan matching (CSM) algorithm, a multi‐resolution auxiliary historical point cloud matching algorithm is proposed, which combines high and low resolution and adopts a single‐frame to multi‐frame step‐by‐step matching scheme. The algorithm was carried out on the sweeping robot. Compared with the traditional CSM algorithm and iterative closest points algorithm, the single position accuracy of the method in this study is improved. In the indoor space of ∼10 m × 10 m, the cumulative error is reduced by 16.24 and 33.96%, respectively. Consequently, our algorithm can still manage to process in real‐time. [ABSTRACT FROM AUTHOR]

A multi‐sensor fusion approach for simultaneous localisation and mapping (SLAM) based on a bio‐inspired polarised skylight sensor is presented in this study. The innovation of the proposed approach is that a newly designed bio‐inspired polarised skylight sensor, which is inspired by the navigation principle of desert ant, is introduced to improve the accuracy of SLAM. The measurement equations based on a polarised skylight sensor and a lidar are derived to obtain the orientation and position of the mobile robot and landmarks. Three kinds of non‐linear filters, extended Kalman filter (EKF), unscented Kalman filter, and particle filter, are adopted and compared to fuse the polarised skylight sensor, lidar, and odometry to estimate the position, orientation, and map in the experiments. Simulation tests and experiments are conducted to validate the effectiveness of the proposed method. The simulations show that the EKF–SLAM with the polarised skylight sensor reduces the error of localisation about 30% and the error of mapping about 25%. Experiments indicate that the proposed EKF–SLAM approach can reduce the error of position and the heading angle, which verifies the proposed EKF–SLAM method, can be used for the outdoor with the low‐cost multi‐sensor. [ABSTRACT FROM AUTHOR]

The camera is one of the important sensors to realise the intelligent driving environment. It can realise lane detection and tracking, obstacle detection, traffic sign detection, identification and discrimination and visual simultaneous localisation and mapping. The visual sensor model, quantity and installation location are different on different intelligent driving hardware experimental platform as well as the visual sensor information processing module, thus a number of intelligent driving system software modules and interfaces are different. In this study, the software architecture of the autonomous vehicle based on the driving brain is used to adapt to different types of visual sensors. The target segment is extracted by the image segmentation algorithm, and then the segmentation of the region of interest is carried out. According to the input feature calculation results, the obstacle search is done in the second segmentation region, the output of the accessible road area. As driving information is complete, the authors will increase or reduce one or more visual sensors, change the visual sensor model or installation location, which will no longer directly affect the intelligent driving decision, they make the multi-vision sensors adapted to the requirements of different intelligent driving hardware test platforms.

The common problem of visual simultaneous localisation and mapping systems is to suffer from featureless environments. It is possible for all environments to have such featureless situations; even though most of the mapped areas contain sufficient textures. This Letter brings a new approach using not only RGB values of the objects but also their positions in the map for feature extraction in order to decrease odometry loss in such situations. DepthTiling recolours RGB image using associated depth data. The experiments give promising results to increase the capability of visual odometry tracking. This study shows that it is possible to increase number of features using related depth data when RGB images are insufficient. [ABSTRACT FROM AUTHOR]

Loop closure detection is an indispensable component to reduce the error accumulation in localisation applications, however, it is hard to be implemented as a real‐time application with high accuracy on the mobile platform. A place recognition method called gridding place recognition (GPR) is proposed for ultra‐fast loop closure detection with high accuracy maintained. The GPR splits the images into multiple grids for high parallelism and uses bags of word features to summarise each grid. The matching results for each grid are then retrieved and merged for further determination of loop closure under extra temporal and spatial constraints. The authors implement the method on a mobile platform, and the best accuracy and fastest execution time of 47 frames per second are achieved on several public benchmarks compared with other typical or fast loop closure algorithms. [ABSTRACT FROM AUTHOR]

The dense matching of pairs is the basis of advanced image processing applications, such as 3D reconstruction and simultaneous localisation and mapping (SLAM). However, it is difficult to obtain efficient dense matching results in wide baseline image pairs due to various conditions. For this reason, the authors propose a dense matching method for wide baseline images based on an equal proportion of triangulation. Firstly, this Letter proves the mathematical property of equal proportion of triangulation affine transformation, and then builds a triangulation based on the set of sparse matching points. By using this property, the positions of equal proportion points in the corresponding triangulation of the two images to be matched are calculated, respectively. Secondly, to eliminate the points and obtain the inner point set, these proportional points are used to check the similarity of the matching triangle regions. Finally, the inner point set is used to calculate the positions of the dense matching points as the final dense matching result. The experimental results verified the validity and accuracy of the proposed method and this method is suitable for tilt photography, multispectral and multidate remote sensing image dense registration, and more. [ABSTRACT FROM AUTHOR]

Recognising places under extreme perceptual changes is a challenging problem. A new dynamic programming method to align sequences of image features extracted from a deep convolutional auto‐encoder to efficiently solve this problem is proposed. As this method considers not only environmental variations, but also the motion constraint of the mobile robot, places from changing environment can be successfully recognised by finding the most likely path sequence. Experimental results show improved precision–recall performance compared with other algorithms. [ABSTRACT FROM AUTHOR]

Multi‐robot map merging without inter‐robot observations, common landmarks, and the knowledge of initial relative poses is a challenging problem due to lack of features or local maxima. This Letter proposes a multi‐hypothesis map merging algorithm with sinogram‐based particle swarm optimisation to solve the problem. Experimental results show that the proposed algorithm can merge individual robot maps much more accurately than the existing algorithms. [ABSTRACT FROM AUTHOR]