Road Topology Research Articles

Obstacle detection to minimize delay and Q-learning to improve routing efficiency in VANET

Nowadays, several service providers in urban areas significantly consider vehicular ad hoc networks (VANET). VANETs can enhance road safety, prevent accidents, and grant passengers entertainment. Though in VANET, efficient routing has remained an open problem. VANET is dynamic; the frequent update in the situation originates through several aspects, such as traffic conditions and updates in the road topology, which demand a suitably adaptive routing. The existence of blocking obstacles degrades routing approaches and increases the failure of paths. These issues build an excessive amount of resource utilization and increase network delay. To solve these issues, obstacle detection to minimize delay and Q-learning to improve routing efficiency (ODQI) in VANET is proposed. This mechanism uses the spanning tree algorithm detects the obstacle. Clustering can be used to manage the topology in VANETs. The dingo algorithm selects the best cluster head (CH) based on vehicle bandwidth, speed, and link lifespan. Furthermore, the sender forwards the traffic information from the sender to the receiver by applying a Q-learning algorithm. This learning algorithm computes the award function to choose the forwarder, improving the routing efficiency. Simulation results demonstrate that the ODQI mechanism increases the CH lifetime and minimizes the network delay.

A homogeneous multi-vehicle cooperative group decision-making method in complicated mixed traffic scenarios

Connected and Automated Vehicles (CAVs) are expected to reshape the transportation system, and cooperative group intelligence of CAVs has great potential for improving transportation efficiency and safety. One challenge for CAV group driving is the decision-making under scenarios mixed with CAV and human-driven vehicles (HDV). Current studies mainly use methods based on single physical rules such as platoon driving or formation switch control, failing to reach a balanced and homogeneous state of optimal efficiency and risk in mixed traffic environments. In addition, most studies focus only on one specific type of scene, lacking the scene adaptability to various surrounding conditions. This paper proposes a homogeneous multi-vehicle cooperative group decision-making method targeting mixed traffic scenarios. A bi-level framework composed of behavior-level and trajectory-level decision-making is established to achieve balanced optimal cooperation. A region-driven behavioral decision mechanism is designed to decompose vehicle actions into a unified form of sequential target regions. Solutions are derived based on Cooperative Driving Safety Field, a risk assessment module inspired by field energy theory. The trajectory-level decision module takes the target regions as input and generates the control quantities of the CAVs through target point selection, conflict reconciliation, and dynamic constraint consideration. Experimental results on 19 various scenarios and continuous traffic flow scenes indicate that the proposed method significantly increases passing efficiency, reduces driving risk, and improves scene adaptability. In addition, experiments on multiple kinds of scenarios including intersections, ramps, bottlenecks, etc. prove that our method can adapt to various road topology structures. Feasibility is also verified through scaled physical platform validations and real-vehicle road tests.

Automatic road network selection method considering functional semantic features of roads with graph convolutional networks

Road network selection plays a key role in map generalization for creating multi-scale road network maps. Existing methods usually determine road importance based on road geometric and topological features, few evaluate road importance from the perspective of road utilization based on human travel data, ignoring the functional values of roads, which leads to a mismatch between the generated results and people’s needs. This paper develops two functional semantic features (i.e. travel path selection probability and regional attractiveness) to measure the functional importance of roads and proposes an automatic road network selection method based on graph convolutional networks (GCN), which models road network selection as a binary classification. Firstly, we create a dual graph representing the source road network and extract road features including six graphical and two functional semantic features. Then, we develop an extended GCN model with connectivity loss for generating multi-scale road networks and propose a refinement strategy based on the road continuity principle to ensure road topology. Experiments demonstrate the proposed model with functional features improves the quality of selection results, particularly for large and medium scale maps. The proposed method outperforms state-of-the-art methods and provides a meaningful attempt for artificial intelligence models empowering cartography.

One Size Fits All: A Unified Traffic Predictor for Capturing the Essential Spatial-Temporal Dependency.

Traffic prediction is a keystone for building smart cities in the new era and has found wide applications in traffic scheduling and management, environment policy making, public safety, and so on. Instead of creating a traffic predictor for each city, this article focuses on designing a unified network model that could be directly applied for traffic prediction in any city, by learning the essential spatial-temporal dependencies, i.e., the mutual relationship between traffic and the corresponding fine-grained road network. To achieve this goal, this article proposes a joint knowledge- and data-driven mechanism that novelly divides dependencies into three kinds of correlations, i.e., road segment, intra-intersection, and inter-intersection correlation, which capture the microcosmic, middle, and macroscopic dependencies between traffic and the road network, respectively. Specifically, we first construct traffic datasets that could cover all road segments from real-world trajectory datasets, which makes it possible to model the whole road network as a graph, with the help of fine-grained road topology. Then, we propose meta road segment learner, connection-aware spatial-temporal graph convolutional network (GCN), and multiscale residual networks for capturing the microcosmic, middle, and macroscopic dependencies, respectively. Our experiments on three real-world datasets demonstrate that our proposed method could: 1) achieve better prediction accuracy compared with several approaches and 2) capture the mutual relationship between traffic and the fine-grained road network since our model trained only using data from the source city achieves good performance when it is directly applied for traffic prediction in the target city, without any fine-tuning. The codes will be made publicly available.

A Review on End-to-End High-Definition Map Generation

Abstract. Autonomous driving offers benefits such as congestion mitigation, increased productivity through the reallocation of driving time, and decreased energy waste. However, achieving Level 4 and 5 autonomous driving remains a significant challenge for both academia and industry. Among the various modules of autonomous driving, High-Definition (HD) maps have become a crucial component due to their high precision in map elements, enabling accurate localization, scene interpretation, navigation, vehicle control and motion forecasting of trajectory of surrounding objects. Several map providers, including TomTom, HERE, Waymo, and NVIDIA, create HD maps for their specific purposes. However, most HD map datasets are not publicly available for individual researchers and companies to investigate the current trends in HD map generation. Furthermore, recent survey papers on HD map generation have tended to focus only on specific aspects, such as road topology or boundary extraction, rather than considering the overall end-to-end HD map generation process. Therefore, we begin with a brief definition, standards, and functionality of HD maps, followed by an exploration of different types of HD maps, including offline and online variants, highlighting their respective advantages and disadvantages. Finally, we will discuss the most recent end-to-end HD map generation architectures, along with various types of open-source HD map datasets and compare their performances.

An Efficient GPS Algorithm for Maximizing Electric Vehicle Range

Although the main purpose of conventional geographical positioning systems (GPSs) is to determine either the fastest path or the shortest distance to a destination, this function may not be enough for electric vehicles (EVs). This is simply because the fastest/shortest path may consume relatively higher energy when compared to other paths depending on the nature, speed limit, and topography of the road. This means that the driving range of the EV per charge decreases dramatically. This paper aims to develop a new algorithm and model dedicated for EV GPS which not only selects shortest/fastest routes, but also focuses on the most energy efficient route. This is achieved by considering many factors including aerodynamics, wind speed, topology of roads, with a clear objective of reducing the energy consumed from the battery. A MATLAB Simulink model is developed and validated with real-life case studies to ensure the results are realistic and accurate.

A methodology for optimal placement of energy hubs with electric vehicle charging stations and renewable generation

The use of electric vehicles and renewable energy sources can significantly contribute to the reduction of pollution levels, fostering a cleaner and more sustainable environment. In addition to their positive environmental impact, electric vehicles can also serve as energy storage units, enabling a bidirectional energy flow between the vehicles and the grid. Despite these promising prospects, a disjointed approach to charging infrastructure planning overlooks the synergies between the energy and transportation ecosystem. This calls for a holistic and coordinated approach to infrastructure development that harnesses the benefits emerging from the convergence of electric vehicles, renewable energy, and transport planning. This paper presents a methodology for the optimal placement of future Energy Hubs for electric vehicle charging and renewable generation. The methodology uses data from open-source datasets involving renewable energy sources, traffic density, charging patterns, road topology, and land use. The optimization problem is formulated as a multi-objective linear programming problem, with the objectives of minimizing the number of Energy Hub units, minimizing electric vehicles charging radius coverage and distance from power substations, and maximizing energy generation. The methodology is demonstrated through an application in Trondheim, Norway, which produces a Pareto front for decision-makers to evaluate the best trade-offs between objectives.

Multi-Source Information Fusion Graph Convolution Network for traffic flow prediction

As a fundamental technology in the field of intelligent transportation systems, traffic flow prediction has a wide range of applications. The utilization of Graph Convolutional Network (GCN) models is notable for capturing the complex spatial–temporal dependencies in traffic data, leading to a significant improvement in prediction accuracy. However, most existing graph construction methods overlook joint impact of auxiliary information such as weather and traffic speed on the road topology. Moreover, the research on interactions within time series at coarse temporal resolutions remains insufficiently explored, giving rise to unsatisfactory long-term prediction performance. In this study, we present a novel framework, namely Multi-Source Information Fusion Graph Convolution Network (MIFGCN), for spatial–temporal traffic flow prediction. Our key innovation lies in creating a dynamic graph that integrates weather, traffic speed, and global spatial information, effectively simulating significant traffic fluctuations caused by subtle ancillary information in the road network. Simultaneously, it captures the evolving hidden adjacency relationships between nodes over time. Furthermore, by combining with an attention-based temporal interaction module, MIFGCN learns multiscale temporal correlations at course temporal resolutions, enhancing the ability for long-term prediction. Experiments conducted on four real-world traffic datasets demonstrate that MIFGCN outperforms various state-of-the-art baselines, especially achieving a 10.50% average improvement on the PeMS08 dataset.

Multi-Camera Multi-Vehicle Tracking Guided by Highway Overlapping FoVs

Multi-Camera Multi-Vehicle Tracking (MCMVT) is a critical task in Intelligent Transportation Systems (ITS). Differently to in urban environments, challenges in highway tunnel MCMVT arise from the changing target scales as vehicles traverse the narrow tunnels, intense light exposure within the tunnels, high similarity in vehicle appearances, and overlapping camera fields of view, making highway MCMVT more challenging. This paper presents an MCMVT system tailored for highway tunnel roads incorporating road topology structures and the overlapping camera fields of view. The system integrates a Cascade Multi-Level Multi-Target Tracking strategy (CMLM), a trajectory refinement method (HTCF) based on road topology structures, and a spatio-temporal constraint module (HSTC) considering highway entry–exit flow in overlapping fields of view. The CMLM strategy exploits phased vehicle movements within the camera’s fields of view, addressing such challenges as those presented by fast-moving vehicles and appearance variations in long tunnels. The HTCF method filters static traffic signs in the tunnel, compensating for detector imperfections and mitigating the strong lighting effects caused by the tunnel lighting. The HSTC module incorporates spatio-temporal constraints designed for accurate inter-camera trajectory matching within overlapping fields of view. Experiments on the proposed Highway Surveillance Traffic (HST) dataset and CityFlow dataset validate the system’s effectiveness and robustness, achieving an IDF1 score of 81.20% for the HST dataset.

Fuzzy-AHP based optimal RSU deployment (Fuzzy-AHP-ORD) approach using road and traffic analysis in VANET

Vehicular Ad Hoc Network (VANET) is a proven technology in Intelligent Transportation Systems (ITS) that provides various safety and non-safety applications. The Roadside Unit (RSU) is one of the essential components of the VANET, which allows vehicles to disseminate and exchange safety and infotainment information in a broader range. RSUs are also valuable for offloading the internet data traffic of vehicular users from cellular networks. However, due to high deployment and maintenance costs and security overhead, it is essential to optimally deploy these RSUs and place them in prominent places to increase the overall network coverage and efficiency. The existing deployment strategies either analyzed the road network on one or a few topological parameters or vehicular traffic parameters and considered equal or random weights for each parameter. None of them deal with the uncertainty of parameter weightage. Thus, this paper proposes a Fuzzy-Analytic Hierarchy Process-based optimal RSU deployment (Fuzzy-AHP-ORD) approach to finding the highly influential intersection nodes for RSU deployment. The Fuzzy-AHP-ORD considers different static and dynamic parameters concerning road topology and the vehicle’s traffic behavior. The weights of the parameter are calculated through Fuzzy-AHP, then the various intersection nodes of the road networks are ranked using the TOPSIS (Technique for Order of Preference by Similarity to Ideal Solution) based MADM (Multiple Attribute Decision Making) method. The simulation results reveal the effectiveness of the proposed method in comparison to other benchmark methods in terms of coverage ratio, connection time, packet delivery ratio, and delay.

Design of urban road fault detection system based on artificial neural network and deep learning.

In urban traffic management, the timely detection of road faults plays a crucial role in improving traffic efficiency and safety. However, conventional methods often fail to fully leverage the information from road topology and traffic data. To address this issue, we propose an innovative detection system that combines Artificial Neural Networks (ANNs), specifically Graph Convolutional Networks (GCN), Bidirectional Gated Recurrent Units (BiGRU), and self-attention mechanisms. Our approach begins by representing the road topology as a graph and utilizing GCN to model it. This allows us to learn the relationships between roads and capture their structural dependencies. By doing so, we can effectively incorporate the spatial information provided by the road network. Next, we employ BiGRU to model the historical traffic data, enabling us to capture the temporal dynamics and patterns in the traffic flow. The BiGRU architecture allows for bidirectional processing, which aids in understanding the traffic conditions based on both past and future information. This temporal modeling enhances our system's ability to handle time-varying traffic patterns. To further enhance the feature representations, we leverage self-attention mechanisms. By combining the hidden states of the BiGRU with self-attention, we can assign importance weights to different temporal features, focusing on the most relevant information. This attention mechanism helps to extract salient features from the traffic data. Subsequently, we merge the features learned by GCN from the road topology and BiGRU from the traffic data. This fusion of spatial and temporal information provides a comprehensive representation of the road status. By employing a Multilayer Perceptron (MLP) as a classifier, we can effectively determine whether a road is experiencing a fault. The MLP model is trained using labeled road fault data through supervised learning, optimizing its performance for fault detection. Experimental evaluations of our system demonstrate excellent performance in road fault detection. Compared to traditional methods, our system achieves more accurate fault detection, thereby improving the efficiency of urban traffic management. This is of significant importance for city administrators, as they can promptly identify road faults and take appropriate measures for repair and traffic diversion.

Intelligent driving model considering vehicular dynamics and heterogeneous road environments

ABSTRACT Understanding vehicles’ movement in complex environments becomes cruical with the fast development of connected automated vehicles (CAVs). Current microscopic traffic flow models lack consideration for vehicle dynamics and complex road topologies. This study develops a model addressing these issues, retrieving vehicles’ maneuvers and predicting vehicles’ two-dimensional motion. It introduces a two-dimensional intelligent driving model utilizing steering angle and acceleration as control inputs. Intricate road topologies are represented with potential fields and a virtual boundary to capture the heterogeneous environment’s complexity. A driving potential field model is also developed for off-ramp areas. Model parameters are optimized with the dynamic time warping (DTW) and particle swarm optimization (PSO) algorithm. Furthermore, model predictive control (MPC) enhances the realism of the model’s output. Field validation results demonstrate that the proposed models can accurately describe vehicles’ two-dimensional movement in intricate environments, offering valuable support for research on heterogeneous traffic flows for CAVs and CVs.

A Distributed Scheme for the Taxi Cruising Route Recommendation Problem Using a Graph Neural Network

Despite considerable research efforts being devoted to the taxi cruising route recommendation (TCRR) problem, existing studies still have some shortcomings. To begin with, the competition and collaboration between taxis are not sufficiently taken into account. Furthermore, the TCRR is heavily reliant on potential taxi demand, which is time-variant and difficult to accurately predict due to the underlying spatiotemporal correlation and dynamic traffic patterns. Moreover, the consideration of competition and cooperation among taxis increases the complexity of the TCRR problem, making conventional centralized algorithms computationally expensive. In this paper, we first formulate TCRR as a biobjective optimization problem to balance the collaboration and competition between taxis. Subsequently, we forecast short-term taxi demand using the proposed long-short-term-memory-based graph convolutional network (LSTM-GCN), which considers diverse factors such as road topology, points of interest (POIs), and multiple time-scale features. Lastly, we propose a distributed algorithm based on a Lagrange dual decomposition. The experimental and simulation results demonstrate that our TCRR scheme performs better than any other counterpart, (i) resulting in a 3% reduction in idle taxis per hour, (ii) performing four times faster than the centralized algorithms to obtain the optimal solution, and (iii) resulting in a 7% increase in average profit.

Road Topology Extraction based on Point of Interest Guidance and Graph Convolutional Neural Network from High-resolution Remote Sensing Images

Road Topology Extraction based on Point of Interest Guidance and Graph Convolutional Neural Network from High-resolution Remote Sensing Images

Multiscale probability map guided index pooling with attention-based learning for road and building segmentation

Efficient road and building footprint extraction from satellite images are predominant in many remote sensing applications. However, precise segmentation map extraction is quite challenging due to the diverse building structures camouflaged by trees, similar spectral responses between the roads and buildings, and occlusions by heterogeneous traffic over the roads. Existing convolutional neural network (CNN)-based methods focus on either enriched spatial semantics learning for the building extraction or the fine-grained road topology extraction. The profound semantic information loss due to the traditional pooling mechanisms in CNN generates fragmented and disconnected road maps and poorly segmented boundaries for the densely spaced small buildings in complex surroundings. In this paper, we propose a novel attention-aware segmentation framework, Multi-Scale Supervised Dilated Multiple-Path Attention Network (MSSDMPA-Net), equipped with two new modules Dynamic Attention Map Guided Index Pooling (DAMIP) and Dynamic Attention Map Guided Spatial and Channel Attention (DAMSCA) to precisely extract the building footprints and road maps from remotely sensed images. DAMIP mines the salient features by employing a novel index pooling mechanism to retain important geometric information. On the other hand, DAMSCA simultaneously extracts the multi-scale spatial and spectral features. Besides, using dilated convolution and multi-scale deep supervision in optimizing MSSDMPA-Net helps achieve stellar performance. Experimental results over the seven benchmark building and road extraction datasets namely, Porto, Shanghai, Massachusetts Road, Massachusetts Building, Synthinel-1, WHU Satellite I and WHU aerial Imagery dataset, ensures MSSDMPA-Net as the state-of-the-art (SOTA) method for building and road extraction as our method beats the next best alternatives by 5.94%, 2.55%, 3.97%, 11.64%, 6.86%, 6.92%, 2.57% IOU and 3.98%, 1.90%, 2.43%, 7.17%, 3.98%, 4.99%, 1.37% F1 score, respectively, over the mentioned datasets. The code has been released in: https://github.com/shirshabose/MSSDMPA-Net.

Internet of Vehicles Based On Cellular-Vehicle-To-Everything (C-V2X)

In line with the development of automotive and traffic systems, high mobility and density in different road topologies cause scalability and delay issues due to frequent disconnection between communication nodes. From a safety aspect, Cellular-V2X (C-V2X) wireless technology was introduced by the Third Generation Partnership Project Organization (3GPP) to realise the transmission of emergency messages at critical times, anywhere. Specifically, Mode 4 C-V2X supports side-link communication without relying on a base station to provide network coverage. However, Mode 4 is susceptible to several limitations, which include half-duplex transmission, packet collision, and propagation errors that will cause intermittent connectivity issues. It is also difficult to determine appropriate parameter configurations that can increase the spectrum efficiency of dense networks to facilitate reliable and low-latency networks. The objective of this paper is to investigate the effectiveness of a Mode 4 C-V2X system under different road topologies and traffic scenarios. The study adopts a Krauss vehicular mobility model based on SUMO software to model normal and dense networks in a highway and a road intersection scenario, then perform simulation using OMNET++ software to analyse the impact of different physical layer (PHY) configurations such as modulation and coding scheme, packet size, number of resource block allocation, as well as the probability of resource reservation. The results show that the optimal configuration of parameters depends on the scenario. For highway scenarios, a lower MCS and a higher number of RBs are recommended. For road intersection scenarios, a higher MCS and a lower number of RBs are recommended. The packet size should also be in accordance with the requirements of the application used. The findings of this study can be used to assist in the design of an optimal intelligent transportation system using adaptive C-V2X parameters that can be automatically adjusted under different scenarios and network conditions.

Evolution of the Road Network Topology of Central European Housing Estates

The analysis of road network topology has attracted the attention of researchers in the past few decades. In this study, the road topology of housing estates in a few selected Central European countries (Hungary, Austria, Czech Republic, and Slovakia) was analysed. This research was carried out in three steps: (1) the road network topology of different decades from the 1950s to the 1980s was described, (2) the ratio of intersections and dead-ends was investigated, and (3) the connectivity indices were analysed and compared. The research was carried out using ESRI ArcGIS software. The results show that the design of road networks built in different countries is similar in the housing estates studied. When analysing the road networks over time, significant differences could be found in the case of Hungary for housing estates built after the 1960s. In general, connectivity has become more important, as it has gradually increased over time.

Swin-ResUNet+: An edge enhancement module for road extraction from remote sensing images

Road extraction from remote sensing images is very important in navigation, urban planning, traffic management and other fields. Deep learning methods have achieved great success in computer vision tasks. Therefore, road extraction from remote sensing images using deep learning methods can significantly improve the road extraction accuracy. However, these methods generally have problems such as low road extraction accuracy, slow training speed, high computational complexity, and poor road topology connectivity. In order to solve the above issues, we propose a Swin-ResUNet+ structure and use the new paradigm Swin-Transformer to extract roads in remote sensing images. Specifically, we construct an Edge Enhancement module based on residual connection and add this module to each stage of the encoder, which can obtain the edge information in remote sensing images. Based on the Edge Enhancement module, we propose a Swin-ResUNet+ structure in order to better capture the topology of roads. On the Massachusetts road dataset, our model has the least computational cost with only less than one percent accuracy decrease. On the DeepGlobe2018 road dataset, our model not only has the least computational complexity but also achieves the highest values of mIOU, mDC, mPA and F1-score. In a word, Swin-ResUNet+ obtains a much better trade-off between accuracy and efficiency than previous CNN-based and Transformer-based methods.

Stable dynamic feedback-based predictive clustering protocol for vehicular Ad hoc networks

Scalability presents a significant challenge in vehicular communication, particularly when there is no hierarchical structure in place to manage the increasing number of vehicles. As the number of vehicles increases, they may encounter the broadcast storm problem, which can cause network congestion and reduce communication efficiency. Clustering can solve these issues, but due to high vehicle mobility, clustering in vehicular ad hoc networks (VANET) suffers from stability issues. Most of the existing clustering protocols are optimized for highways only and some protocols are optimized for intersections only. The clusters that are created by the protocols which are optimized for highways breakdown at the intersections where clustering is needed more. On the other hand, the clusters that are created by the protocols optimized for intersections create extra clusters or break unnecessary on straight-roads which reduces cluster stability. Moreover, the lack of intelligent use of a combination of the mobility parameters, such as direction, movement, position, velocity, degree of vehicle, and movement at the intersection, also contributes to cluster stability problems. A dynamic clustering protocol that efficiently combines all the mobility parameters can resolve these issues in VANETs by providing stability in both intersections and highways. To achieve high stability in VANET clustering, a Stable Dynamic feedback-based Predictive Clustering (SDPC) protocol is proposed for VANET to ensure cluster stability in both highway and intersection scenarios. SDPC considers vehicle relative velocity, acceleration, position, distance, transmission range, moving direction at the intersection, and vehicle density to create a cluster. The cluster head is selected based on the future position of the vehicles, relative distance between vehicles, movement of vehicles at the intersection, degree of vehicles, and probable cluster head duration. The performance of SDPC is compared with four existing VANET clustering protocols in various road topologies, in terms of the average cluster head change rate, the average duration of cluster head, the average duration of cluster member, and the average clustering overhead. The simulation results show that SDPC outperforms the existing protocols, achieving higher clustering stability in terms of cluster head change rate (50%), cluster head duration (15%), cluster member duration (6%), and clustering overhead (35%).

Research on the Impact of Heavy Rainfall Flooding on Urban Traffic Network Based on Road Topology: A Case Study of Xi’an City, China

In recent years, the frequent occurrence of extreme emergencies represented by heavy rainfall has posed a significant impact on urban transportation networks and caused great inconvenience to people’s production and life. This paper examines the impact of heavy rainfall on the urban transportation network in Xi’an’s main urban area, models the map of urban road network in the main urban area of Xi’an by applying complex network theory, quantifies and analyzes the topological and geographic structural characteristics of the affected sections (interrupted by heavy rainfall) due to heavy rainfall, as well as the impact of heavy rainfall on the functional indexes of the road network such as access efficiency and accessibility, and, finally, analyzes its formation causes and proposes targeted management countermeasures. The findings of this study serve as a valuable reference for enhancing urban traffic emergency management capabilities and fostering sustainable urban development.