Search

This work considers the path planning problem of personal mobility vehicle (PMV) for indoor navigation using the Artificial Potential Field (APF) method. The APF method sometimes suffers from an infinite loop problem during the planning phase when the goal is blocked by obstacles with certain characteristics. To address the issue, this study deploys the map augmentation method for replanning. When infinite loop situations occur, the map is transformed and the search for drivable path is initiated. The method successfully generates a feasible trajectory when the map is rotated at a certain angle. The scenario of successful planning is shown in the result.

Robot Exploration can be used to autonomously map an area or conduct search missions in remote or hazardous environments. Using multiple robots to perform this task can improve efficiency for time-critical applications. In this work, a distributed method for multi-robot exploration using a Harmonic Map Transformation (HMT) is presented. We employ SLAM to construct a map of the unknown area and utilize map merging to share terrain information amongst robots. Then, a frontier allocation strategy is proposed to increase efficiency. The HMT is used to safely navigate the robots to the frontiers until the exploration task is complete. We validate the efficacy of the proposed strategy via tests in simulated and real-world environments. Our method is compared to other recent schemes for multi-robot exploration and is shown to outperform them in terms of total path distance.

With the rapid development of robotics and in-depth research of automatic navigation technology, mobile robots have been applied in a variety of fields. Map construction is one of the core research focuses of mobile robot development. In this paper, we propose an autonomous map calibration method using visible light positioning (VLP) landmarks and Simultaneous Localization and Mapping (SLAM). A layout map of the environment to be perceived is calibrated by a robot tracking at least two landmarks mounted in the venue. At the same time, the robot’s position on the occupancy grid map generated by SLAM is recorded. The two sequences of positions are synchronized by their time stamps and the occupancy grid map is saved as a sensor map. A map transformation method is then performed to align the orientation of the two maps and to calibrate the scale of the layout map to agree with that of the sensor map. After the calibration, the semantic information on the layout map remains and the accuracy is improved. Experiments are performed in the robot operating system (ROS) to verify the proposed map calibration method. We evaluate the performance on two layout maps: one with high accuracy and the other with rough accuracy of the structures and scale. The results show that the navigation accuracy is improved by 24.6 cm on the high-accuracy map and 22.6 cm on the rough-accuracy map, respectively.

Robot Exploration can be used to autonomously map an area or conduct search missions in remote or hazardous environments. Using multiple robots to perform this task can improve efficiency for time-critical applications. In this work, a distributed method for multi-robot exploration using a Harmonic Map Transformation (HMT) is presented. We employ SLAM to construct a map of the unknown area and utilize map merging to share terrain information amongst robots. Then, a frontier allocation strategy is proposed to increase efficiency. The HMT is used to safely navigate the robots to the frontiers until the exploration task is complete. We validate the efficacy of the proposed strategy via tests in simulated and real-world environments. Our method is compared to other recent schemes for multi-robot exploration and is shown to outperform them in terms of total path distance. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Zhejiang University: Science A is the property of Springer Nature and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Counting people in crowd scenarios is extensively conducted in drone inspections, video surveillance, and public safety applications. Today, crowd count algorithms with supervised learning have improved significantly, but with a reliance on a large amount of manual annotation. However, in real world scenarios, different photo angles, exposures, location heights, complex backgrounds, and limited annotation data lead to supervised learning methods not working satisfactorily, plus many of them suffer from overfitting problems. To address the above issues, we focus on training synthetic crowd data and investigate how to transfer information to real-world datasets while reducing the need for manual annotation. CNN-based crowd-counting algorithms usually consist of feature extraction, density estimation, and count regression. To improve the domain adaptation in feature extraction, we propose an adaptive domain-invariant feature extracting module. Meanwhile, after taking inspiration from recent innovative meta-learning, we present a dynamic- β MAML algorithm to generate a density map in unseen novel scenes and render the density estimation model more universal. Finally, we use a counting map refiner to optimize the coarse density map transformation into a fine density map and then regress the crowd number. Extensive experiments show that our proposed domain adaptation- and model-generalization methods can effectively suppress domain gaps and produce elaborate density maps in cross-domain crowd-counting scenarios. We demonstrate that the proposals in our paper outperform current state-of-the-art techniques. [ABSTRACT FROM AUTHOR]

Based on an improved generative adversarial networks algorithm (CGAN), this paper explores a technical way to realize map transformation through autonomous learning and training of remote sensing images. Just skip the trial process vector data update and cumbersome process of mapping the basic map elements can be automatically transform, the image on the main streets and typical rules of construction material, can achieve automatic identification and transformation, greatly shorten the tile map production and update cycle, improve the efficiency of the network map service quality. The results of the test platform have proved that it can be applied to a certain extent and can basically meet the requirements of network map production. [ABSTRACT FROM AUTHOR]

Coordinate transformations refer to mathematical processing that enables overlay of digital maps that use different coordinate reference systems, that is, map projections. The transformation from geographical to map (plane) coordinates is the conventional practice in cartography, which is called forward transformation. The inverse transformation, which yields geographical coordinates from map coordinates, is a more recent development, due to the need for transformation between different map projections, especially in geographic information systems (GIS). The combination of the inverse and forward transformation from one projection to another, which may be called grid-on-grid or map-to-map transformation, can be necessary for some custom applications in GIS and in automated cartography. Many different approximation algorithms can be used for this problem on desktop computers. In this paper a new local transformation method called a non-Sibsonian transformation, which uses non-Sibson local coordinates, is suggested for map-to-map transformation or for improving geometrical accuracy of scanned maps. A case study is performed using the Lambert conformal conic projection and is presented with results. [ABSTRACT FROM AUTHOR]

Potholes and other road surface damages pose significant risks to vehicles and traffic safety. The current methods of in situ visual inspection for potholes or cracks are inefficient, costly, and hazardous. Therefore, there is a pressing need to develop automated systems for assessing road surface conditions, aiming to efficiently and accurately reconstruct, recognize, and locate potholes. In recent years, various methods utilizing (a) computer vision, (b) three-dimensional (3D) point clouds, or (c) smartphone data have been employed to map road surface quality conditions. Machine learning and deep learning techniques have increasingly enhanced the performance of these methods. This review aims to provide a comprehensive overview of cutting-edge computer vision and machine learning algorithms for pothole detection. It covers topics such as sensing systems for acquiring two-dimensional (2D) and 3D road data, classical algorithms based on 2D image processing, segmentation-based algorithms using 3D point cloud modeling, machine learning, deep learning algorithms, and hybrid approaches. The review highlights that hybrid methods combining traditional image processing and advanced machine learning techniques offer the highest accuracy in pothole detection. Machine learning approaches, particularly deep learning, demonstrate superior adaptability and detection rates, while traditional 2D and 3D methods provide valuable baseline techniques. By reviewing and evaluating existing vision-based methods, this paper clarifies the current landscape of pothole detection technologies and identifies opportunities for future research and development. Additionally, insights provided by this review can inform the design and implementation of more robust and effective systems for automated road surface condition assessment, thereby contributing to enhanced roadway safety and infrastructure management. [ABSTRACT FROM AUTHOR]

In this paper, we proposed Mix-VIO, a monocular and binocular visual-inertial odometry, to address the issue where conventional visual front-end tracking often fails under dynamic lighting and image blur conditions. Mix-VIO adopts a hybrid tracking approach, combining traditional handcrafted tracking techniques with Deep Neural Network (DNN)-based feature extraction and matching pipelines. The system employs deep learning methods for rapid feature point detection, while integrating traditional optical flow methods and deep learning-based sparse feature matching methods to enhance front-end tracking performance under rapid camera motion and environmental illumination changes. In the back-end, we utilize sliding window and bundle adjustment (BA) techniques for local map optimization and pose estimation. We conduct extensive experimental validations of the hybrid feature extraction and matching methods, demonstrating the system's capability to maintain optimal tracking results under illumination changes and image blur. [ABSTRACT FROM AUTHOR]

The Arnold Cat Map (ACM) is a popular chaotic map used in image encryption. Chaotic maps are known for their sensitivity to initial conditions and their ability to permute, or rearrange, pixels. However, ACM is periodic, and its period is relatively short. This periodicity decreases the effective key-space and security of a cryptosystem using ACM. Further, ACM is typically only able to be performed on square images. To solve the low periodicity and typical limitation to square images, this paper proposes performing ACM on overlapping square partitions which cover the entirety of an image. The presence of overlap results in a greatly increased image period. The resulting system will be referred to as overlapping ACM or OACM. Several papers have already discussed systems involving overlapping ACM. However, they did not discuss the implementation or periodicity of such a system in detail. This paper does cover the implementation and periodicity analysis of OACM and proposes a simple symmetric encryption system which uses OACM. The proposed encryption system is not as sophisticated or secure as other modern encryption schemes, since it is mainly intended as an initial test of OACM's utility. Histogram and sensitivity analyses did however indicate a level of security against various cryptographic attacks, and OACM performed reasonably in both the permutation and diffusion stages of the cryptosystem. [ABSTRACT FROM AUTHOR]

In fact, Computer Aided Design (CAD) offers powerful design tools to produce digital large scale topographic mapping that is considered the backbone for construction projects, urban planning and landscape architecture. Nowadays local agencies in small communities and developing countries are facing some difficulties in map to map transformation and handling discrepancies between the physical reality and represented spatial data due to the need for implementing high cost systems such as GIS and the experienced staff required. Therefore, the require for providing a low-cost tool based on the most common CAD system is very important to guarantee a quality and positional accuracy of features. The main aim of this study is to describe a mathematical relationship to fulfil the coordinate conversion between two different grid references applying two-dimensional conformal polynomial models built on control points and a least squares fitting algorithm. In addition, the automation of this model was performed in the Microsoft Visual Studio environment to calculate polynomial coefficients and convert the positional property of entities in AutoCAD by developing spatial CAD tool. To evaluate the proposed approach the extracted coordinates of check points from the interpolation surface are compared with the known ones. [ABSTRACT FROM AUTHOR]

Forest resources are one of the indispensable resources of the earth, which are the basis for the survival and development of human society. With the swift advancements in computer vision and artificial intelligence technology, the utilization of deep learning for smoke detection has achieved remarkable results. However, the existing deep learning models have poor performance in forest scenes and are difficult to deploy because of numerous parameters. Hence, we introduce an optimized forest fire smoke monitoring system for embedded edge devices based on a lightweight deep learning model. The model makes full use of the multi-scale variable attention mechanism of Transformer architecture to strengthen the ability of image feature extraction. Considering the needs of application scenarios, we propose an improved lightweight network model LCNet for feature extraction, which can reduce the parameters and enhance detecting ability. In order to improve running speed, a simple semi-supervised label knowledge distillation scheme is used to enhance the overall detection capability. Finally, we design and implement a forest fire smoke detection system on an embedded device, including the Jetson NX hardware platform, high-definition camera, and detection software system. The lightweight model is transplanted to the embedded edge device to achieve rapid forest fire smoke detection. Also, an asynchronous processing framework is designed to make the system highly available and robust. The improved model reduces three-fourths of the parameters and increases speed by 3.4 times with similar accuracy to the original model. This demonstrates that our system meets the precision demand and detects smoke in time. [ABSTRACT FROM AUTHOR]

In this paper, we propose a new approach for service robots to perform delivery tasks in indoor environments, including map-building and the automatic renewal of destinations for navigation. The first step involves converting the available floor plan (i.e., CAD drawing) of a new space into a grid map that the robot can navigate. The system then segments the space in the map and generates movable initial nodes through a generalized Voronoi graph (GVG) thinning process. As the second step, we perform room segmentation from the grid map of the indoor environment and classify each space. Next, when the delivery object is recognized while searching the set space using the laser and RGB-D sensor, the system automatically updates itself to a position that makes it easier to grab objects, taking into consideration geometric relationships with surrounding obstacles. Also, the system supports the robot to autonomously explore the space where the user's errand can be performed by hierarchically linking recognized objects and spatial information. Experiments related to map generation, estimating space from the recognized objects, and destination node updates were conducted from CAD drawings of buildings with actual multiple floors and rooms, and the performance of each stage of the process was evaluated. From the quantitative evaluation of each stage, the proposed system confirmed the potential of partial automation in performing location-based robot services. [ABSTRACT FROM AUTHOR]

Deep images can provide rich spatial structure information, which can effectively exclude the interference of illumination and road texture in road scene segmentation and make better use of the prior knowledge of road area. This paper first proposes a new cross‐modal feature maintenance and encouragement network. It includes a quantization statistics module as well as a maintenance and encouragement module for effective fusion between multimodal data. Meanwhile, for the problem that if the road segmentation is performed directly using a segmentation network, there will be a lack of supervised guidance with clear physical meaningful information and poor interpretability of learning features, this paper proposes two road segmentation models based on prior knowledge of deep image: disparity information and surface normal vector information. Then, a two‐branch neural network is used to process the colour image and the processed depth image separately, to achieve the full utilization of the complementary features of the two modalities. The experimental results on the KITTI road dataset and Cityscapes dataset show that the method in this paper has good road segmentation performance and high computational efficiency. [ABSTRACT FROM AUTHOR]

To eliminate blind spots in the field of vision and achieve a safe and collision‐free path, this paper proposes a path planning method based on multivehicle collaborative mapping in the context of vehicle networking. First, a multi vehicle map merging strategy based on the fireworks algorithm is proposed. In this strategy, a dissimilarity objective function based on the concept of grid map similarity is established and an improved fireworks algorithm is used to quickly search for the maximum overlap between local maps, achieving multivehicle collaborative mapping. Second, a real‐time path planning method based on artificial potential field theory is proposed. The information obtained from multivehicle collaborative mapping is first combined with the potential field model to form a multifield coupled road environment model. Then, the obstacle repulsion potential field model is improved to address the issues of traditional artificial potential field methods that target unreachability and poor dynamic response. The feasibility and effectiveness of the collaborative path planning method and single vehicle path planning method are tested through simulation analysis. This paper demonstrates through simulation analysis that the proposed path planning method can effectively achieve beyond line of sight perception and safely and comfortably guide vehicles to complete path planning. [ABSTRACT FROM AUTHOR]

Floods pose a significant threat to road networks globally, disrupting transportation, isolating communities, and causing economic losses. This study proposes a four-stage methodology (avoidance, endurance, recovery, and adaptability) to enhance the resilience of road networks. We combine analysis of constructed assets and asset system performance with multiple disaster scenarios (Reactive Flood Response, Proactive Resilience Planning, and Early Warning Systems). Advanced flood Geospatial-AI models and open data sources pinpoint high-risk zones affecting crucial routes. The study investigates how resilient assets and infrastructure scenarios improve outcomes within Urban Resilience Index (CRI) planning, integrating performance metrics with cost–benefit analysis to identify effective and economically viable solutions. A case study on the Lisbon Road network subjected to flood risk analyzes the effectiveness and efficiency of these scenarios, through loss and gain cost analysis. Scenario 2, Proactive Resilience Planning, demonstrates a 7.6% increase compared to Scenario 1, Reactive Flood Response, and a 3.5% increase compared to Scenario 3, Early Warning Systems Implementation. By considering asset performance, risk optimization, and cost, the study supports resilient infrastructure strategies that minimize economic impacts, while enabling communities to withstand and recover from flood events. Integrating performance and cost–benefit analysis ensures the sustainability and feasibility of risk reduction measures. [ABSTRACT FROM AUTHOR]

This article explores detecting and categorizing network traffic data using machine-learning (ML) methods, specifically focusing on the Domain Name Server (DNS) protocol. DNS has long been susceptible to various security flaws, frequently exploited over time, making DNS abuse a major concern in cybersecurity. Despite advanced attack, tactics employed by attackers to steal data in real-time, ensuring security and privacy for DNS queries and answers remains challenging. The evolving landscape of internet services has allowed attackers to launch cyber-attacks on computer networks. However, implementing Secure Socket Layer (SSL)-encrypted Hyper Text Transfer Protocol (HTTP) transmission, known as HTTPS, has significantly reduced DNS-based assaults. To further enhance security and mitigate threats like man-in-the-middle attacks, the security community has developed the concept of DNS over HTTPS (DoH). DoH aims to combat the eavesdropping and tampering of DNS data during communication. This study employs a ML-based classification approach on a dataset for traffic analysis. The AdaBoost model effectively classified Malicious and Non-DoH traffic, with accuracies of 75% and 73% for DoH traffic. The support vector classification model with a Radial Basis Function (SVC-RBF) achieved a 76% accuracy in classifying between malicious and non-DoH traffic. The quadratic discriminant analysis (QDA) model achieved 99% accuracy in classifying malicious traffic and 98% in classifying non-DoH traffic. [ABSTRACT FROM AUTHOR]