Road Network Research Articles

An Indoor-Outdoor Layered HD Map Construction for Unmanned Ground Vehicles

Abstract. High-Definition Maps (HD Maps) are lane-level 3-dimensional road network models that ensure the safe operation of autonomous vehicles and drive the continuous advancement of autonomous driving technology to higher levels. However, HD Maps currently face challenges regarding limited coverage and description of indoor environments (e.g. underground parking), as well as the lack of uniformity between indoor and outdoor map formats. Therefore, this paper proposes a Layered HD Map model for both indoor and outdoor environments. The map model consists of 6 layers, allowing effective representation of indoor and outdoor environments, as well as transitional areas. The paper also establishes an Unmanned Ground Vehicle (UGV) to collect and update map data using LiDAR (Light Detection and Ranging) SLAM (Simultaneous Localization and Mapping) and autonomous exploration technology, aiming to enhance the efficiency and automation of HD Map acquisition. In order to verify the validity of the proposed map model, this paper conducted a navigation experiment in a double decker parking lot containing entrances and exits. The results of the experiments demonstrate that the Layered HD Map generated through autonomous LiDAR SLAM can effectively describe the indoor and outdoor environments, and enable successful navigation of UGVs.

Urban heterogeneity of the trade-offs between exposure to greenery and walking distance in children's home–school routes

Greenery fosters sustainable outdoor environments and promotes walking and healthy lifestyles. Greening children's home–school routes can be seen as an environmentally sustainable solution that enhances their daily interaction with nature. However, the uneven distribution of greenery and route networks within cities results in varied opportunities for pedestrians, including children, to experience greenery.This study evaluates the urban heterogeneity of trade-offs between exposure to greenery and route length. We focus on the shortest and greenest hypothetical home–school routes for all children in the city. For this purpose, we conducted a spatial analysis using multiple spatially explicit data sets on primary schoolchildren, pedestrian street networks, and high-resolution urban green space maps, with Łódź (Poland) as the case study city.Children who opt for the greenest hypothetical routes instead of the shortest could increase their exposure to greenery by 18%. However, maximizing exposure to greenery requires choosing routes 9.5% (46 m) longer than the shortest alternative. The trade-off between the shortest and greenest home–school routes is more pronounced for children in the urban core area compared to other city zones. This urban heterogeneity should be considered when allocating new greenery to support active transportation.

Bound-preserving OEDG schemes for Aw–Rascle–Zhang traffic models on networks

Physical solutions to the widely used Aw–Rascle–Zhang (ARZ) traffic model and the adapted pressure ARZ model should satisfy the positivity of density, the minimum and maximum principles with respect to the velocity v and other Riemann invariants. Many numerical schemes suffer from instabilities caused by violating these bounds, and the only existing bound-preserving (BP) numerical scheme (for ARZ model) is random, only first-order accurate, and not strictly conservative. This paper introduces arbitrarily high-order provably BP discontinuous Galerkin (DG) schemes for these two models, preserving all the aforementioned bounds except the maximum principle of v, which has been rigorously proven to conflict with the consistency and conservation of numerical schemes. Although the maximum principle of v is not directly enforced, we find that the strictly preserved maximum principle of another Riemann invariant w actually enforces an alternative upper bound on v. At the core of this work, analyzing and rigorously proving the BP property is a particularly nontrivial task: the Lax–Friedrichs (LF) splitting property, usually expected for hyperbolic conservation laws and employed to construct BP schemes, does not hold for these two models. To overcome this challenge, we formulate a generalized version of the LF splitting property, and prove it via the geometric quasilinearization approach (Wu and Shu, 2023 [47]). To suppress spurious oscillations in the DG solutions, we incorporate the oscillation-eliminating technique, recently proposed in (Peng et al., 2024 [34]), which is based on the solution operator of a novel damping equation. Several numerical examples are included to demonstrate the effectiveness, accuracy, and BP properties of our schemes, with applications to traffic simulations on road networks.

Nature positive infrastructure - habitat connectivity structures, a call to arms

‘Linear infrastructure, including the Strategic Road Network, fragments habitats and landscapes creating impassable barriers for flora and fauna. Where populations of animals can’t move from their home ranges they become isolated and vulnerable to local extinction through disease, extreme events and inbreeding. Isolation of habitats also makes them increasingly vulnerable to extinction from climate change. In the UK habitat connectivity structures that restore species movement and physical connection of habitats, such as green-bridges, mammal tunnels and underpasses are rare. Although, they are becoming increasingly common due to planning consent requirements. Nevertheless, on the 4,500 miles of Strategic Road Infrastructure in England habitat connectivity features are still few and far between. Mass restoration of habitat connectivity across a Strategic Nature Network and using wildlife crossing structures would be transformative for the UK public as well as our ecosystems. The UK is decades behind other nations in the application of habitat defragmentation structures. In the last 15 years the Dutch transport authority have built approximately 70 large green bridges and approximately 200 smaller interventions across its road and rail network, at time of writing National Highways have built 2. Designing and constructing structures for wildlife, as well as people, on a scale that will make meaningful difference to UK nature will require our industry to unite and innovate to deliver a lasting legacy of nature restoration.‘

АНАЛИЗ ФУНКЦИОНАЛЬНЫХ ИНДИКАТОРОВ ИНТЕЛЛЕКТУАЛЬНЫХ ТРАНСПОРТНЫХ СИСТЕМ КАК ПОКАЗАТЕЛЕЙ ПОВЫШЕНИЯ ЭКОЛОГИЧЕСКОЙ БЕЗОПАСНОСТИ АВТОМОБИЛЬНОГО ТРАНСПОРТА В КУРСКОЙ ОБЛАСТИ

The article presents an analysis of modern research in the field of assessing the anthropogenic impact of motor transport, including emissions of pollutants into the air, noise and vibration impact. When implementing measures aimed at reducing the negative impact of motor transport, considerable attention is paid to the development and implementation of intelligent transport systems (ITS). To assess the effectiveness of using ITS elements in the Kursk region in terms of improving environmental performance, the authors analyzed the following functional indicators of ITS: mass emissions of pollutants contained in vehicle exhaust gases; noise level from traffic flow; CO and NOx concentration values. The conducted field studies and calculations indicate the high efficiency of ITS implementation to reduce the environmental load on sections of the road network.

Ecological niche assessment and conservation status of colocolo pampas cat Leopardus colocola (Molina 1782)

Until 2021, Leopardus colocola was considered a species distributed across much of South America. However, recent studies have shown that it is a monotypic species, apparently restricted in its distribution to the central-northern region of Chile, distinct from other felines of the same genus. This change in its classification and distribution has sparked debate regarding its conservation status, which now requires a detailed assessment. In this study, we analyzed the species’ geographic distribution using ecological niche modeling and evaluated its conservation status according to the guidelines of the International Union for Conservation of Nature, considering the impact of mining concessions and Chile's road network. Presence records of the species were systematized, and a new ecological niche model was developed. Additionally, the Extent of Occurrence (EOO) and the Area of Occupancy (AOO) were calculated. The fragmentation and projected reduction of the niche model, along with the EOO and AOO, place the species under the Criteria B2ab (i, ii, iii), leading to its classification as “Endangered.” This study provides an updated view of the species' geographic distribution and conservation status in Chile. The results are crucial for future conservation efforts and offer a solid foundation for effective management strategies.

Deep spatial-temporal information fusion dynamic graph convolutional network for traffic flow prediction

Abstract Predicting traffic flow is vital for advancing intelligent transportation systems, but achieving precise forecasts remains challenging. To deeply explore the complex and diverse dynamic spatio-temporal correlation of traffic data, this study proposes a multi-information fusion spatio-temporal dynamic graph convolution model for traffic flow prediction. In the model construction, firstly, a dynamic graph generation module is designed to fully capture the complex spatial correlation of the traffic network and model the changing spatio-temporal interaction; secondly, the spatial self-attention mechanism is used to dynamically focus on the spatial relationship between different nodes, and combined with the dynamic graph convolution network to extract the spatial dynamic correlation features of the road network to study deep spatiotemporal information; Finally, existing models rarely consider other traffic information related to traffic flow, and a spatiotemporal information fusion module is designed to enhance the ability of the model to perceive information, thereby improving the performance of traffic flow prediction models. Experiments are conducted on four real traffic datasets using three performance evaluation metrics and 18 baseline models. The results show that the model has higher prediction accuracy.

The Fifth Milestation from Tiberias: A Newly Discovered Milestone in the Gennesaret Valley Illumines the Roman Arterial Network

ABSTRACT Through the prism of a fairly recent discovery of a milestone, the present article sheds light on the Roman road in the Gennesaret Valley, particularly the span connecting Tiberias to Julias. Building on Zvi Ilan's initiative in the 1980s, the author will emphasise two milestones: IMC 694 and IMC 847. Dating to 120 ce, the latter stone’s inscription not only divulges the role of Emperor Hadrian in the artery’s construction, but establishes Tiberias as its caput viae. By delving into historical sources, contemporary research, and the broader context of Hadrian's infrastructure initiatives throughout the province of Judaea, the paper explicates the road network’s purpose and strategic importance during the Roman era.

TrafficPro: A road speed prediction framework for urban signal-controlled road networks

In view of the problem that traditional deep learning models do not consider the active time-varying characteristics of traffic flow (signal control information) when predicting the speed of urban road networks, and have low prediction accuracy, this paper proposes a speed prediction framework based on generative adversarial networks and graph neural networks. In this framework, the generator network simultaneously encodes the road network traffic flow and signal control information through active and passive prediction modules to generate prediction results, and then uses the discriminator network to improve the generalization of the prediction results. This framework can obtain higher prediction accuracy than traditional time series models and deep learning models. In the real road network speed prediction scenario, this framework can reduce the prediction error compared to the best benchmark model 3%-4%.

Forecasting Daily Air Quality Index and Early Warning System for Estimating Ambient Air Pollution on Road Networks Using Gaussian Dispersion Model with Deep Learning Algorithm

The rapid growth of the vehicle population is a major factor in heavy air pollution and public health issues. Traffic-related air pollutants (TRAPs) on roads are often much higher than ambient values, leading to high exposure levels in vehicles. This research proposes a hybrid forecasting model for early detection and early warning systems (EWS) of road networks during real-world travels. Data is collected from Kannur, Calicut, Palakkad, and Coimbatore using real-time sensors, including surrounding discussion information, activity information, vehicle speed, and stopping events. The study predicts ambient air quality (AAQ) levels on the road network using the Gaussian Dispersion model (GDM) and measures the risk sensitivity of PM10 and PM2.5 in selected regions. This helps formulate powerful prevention strategies and prevent negative health impacts. The air pollution module for predicting concentration has an innovative hybridization model that combines an improved cuckoo search (CS) and differential evolution (DE) algorithm with a stacked LSTM model to increase forecasting accuracy of six major environmental pollution levels. This model predicts the AAQ level and is effective and robust for warning one day before the pollutant event occurs based on the risk level of an ambient air pollutant from the RN.

Enhancing assessment of direct and indirect exposure of settlement-transportation systems to mass movements by intergraph representation learning

Abstract Amidst the intensifying extreme rainfall patterns due to climate change, global early warning systems for mass movements (e.g. landslides, avalanches) need to provide not only the coarsely aggregated danger reports, but also the necessary fine details to understand its potential implications on critical infrastructures such as transportation systems. In this study, we introduce a novel ‘intergraph’ method that enhances the exposure information using a graph-based machine learning implementation on the hydrological and geological characteristics of mass movements and the underlying connectivity of settlement-transportation systems. Demonstrating the entire country of Norway and the 2020 Gjerdrum quick clay incident as a case study, we integrated the assessment of both direct and indirect exposure information of settlement-transportation systems and their daily 1 km-by-1 km susceptibility map, which were derived from the 68 934 mass movement incidents since 1957 and the connectivity information of 4778 settlements and 257 000 km road networks. Our findings achieved 86.25% accuracy, providing a distribution of improved susceptibility estimates and identifying critical settlements in near-real-time. By interacting the graphical representations of the shared causal drivers of susceptibility and the settlement-transportation system connectivity, our study extends our understanding of the exposure of multiple interacting settlements with a high granularity degree in a unified approach.

Autonomous trajectory planning method for aircraft based on ripple diffusion algorithm

Aiming at the problem that route optimization in dynamic continuous airspace (non-discrete road network) is difficult to ensure optimality and has low computational efficiency, a non-circular ripple diffusion algorithm is proposed. Firstly, considering the influence of time-varying airflow and obstacle area in dynamic airspace, the airspace wind speed model, route network and dynamic network weight model are established, and 6 airspace environments and 4 road network structures with the influence of time-varying airflow and obstacle area are constructed. Then, the effects of traditional dynamic path optimization algorithm, co-evolutionary path optimization algorithm and non-circular ripple diffusion algorithm on route optimization are compared in 1000 experiments, taking the optimized path length, flight time and calculation time as indicators. The simulation results show that the traditional dynamic path optimization algorithm has the worst effect under the three indicators, and the calculation time of non-circular ripple diffusion algorithm is significantly less than that of the other two algorithms, which effectively improves the engineering calculation efficiency.

Traffic speed prediction of regional complex road network based on CapsNet and D-BiLSTM

Accurate and efficient short-term traffic prediction is of great significance in the study of regional traffic network. However, the complex and dynamic spatiotemporal correlation of traffic patterns makes the existing methods insufficient in learning traffic evolution in terms of structural depth and prediction scale. Therefore, this paper proposes a deep learning model combining capsule network (CapsNet) and deep bidirectional LSTM (D-BiLSTM). CapsNet is used to identify the spatial topological structure of the road network and extract spatial features, and D-BiLSTM network is integrated. The forward and backward dependencies of traffic states are considered at the same time, and the bidirectional temporal correlation of different historical periods is captured to predict the traffic of large-scale complex road networks in the target area. Experiments on real traffic network speed datasets show that the prediction accuracy of the proposed model is improved by more than 10% on average , which is better than other methods. It has high prediction accuracy and good robustness in traffic prediction of regional complex road networks.

Long-Term Evolution of Ecologically Fragile Waterside Rural Areas and Strategies for Local Spatial Planning: An Empirical Study in Baiyangdian, China

Under the dynamics of urbanization and counterurbanization, rural areas in China face both challenges and opportunities with the government’s new-town policy. A comprehensive analysis is essential for developing effective strategies. Characterized by traditional water settlements and high ecological sensitivity, Anxin County, which encompasses 50% of Baiyangdian Lake, was selected as a case study. Anxin County was incorporated into the National New Area in 2017, and it served as an experimental site for green ecological development. This study aims to provide insights into the sustainable spatial planning of Anxin County’s settlements by examining their long-term evolution and locational differences, modeling the driving mechanisms, and proposing differentiated spatial planning strategies based on predictive outcomes. Our research findings indicate the folllowing: (1) Anxin County’s settlements have expanded significantly in the past, with a notable surge between 1975 and 1996. Initially, semi-waterside settlements experienced the fastest growth before the 1970s, followed by land settlements. (2) Natural and socio-economic factors are modeled as independent variables to explain the evolution of settlement areas. The results indicate a decreasing impact of natural factors and an increasing influence of socio-economic factors over time. Furthermore, the evolution of settlements in water areas is relatively straightforward and random, whereas land settlements are influenced by a complex array of factors. (3) Utilizing the model to predict settlement growth, the study identifies settlements requiring relocation, and it proposes the most suitable relocation targets for them. A total of 23 villages, including Bei Tianzhuang and Cai Putai, are identified for relocation, while villages such as Ma Village, Bian Village, and Liu Lizhuang have strong capacities for accepting in-migrants. The study also offers recommendations for enhancing waterfront landscapes, flexible land use, road network systems, and internal construction.

Graffiti Writers Choose Locations That Optimize Exposure

We investigate the spatial decision-making of graffiti writers when selecting target locations, examining how street segment characteristics influence exposure. Extending the rational choice perspective to expressive offending, we collected data through Systematic Social Observation in Ghent’s city center in November 2017, covering 12,655 graffiti instances across 2,233 street segments. The SSO involved counting graffiti items and public facilities likely to attract crowds, and measuring street network centrality. Conditional logit models assessed the impact of these characteristics on graffiti location choices. Results show that street network centrality and the presence of bars, night shops, residential units, and schools significantly increased graffiti writers’ preferences. Our findings suggest that graffiti writers aim to maximize exposure, highlighting the rational choice perspective’s relevance for expressive offending.

Urban Emergency Evacuation Path Optimization Based on Uncertain Environments to Enhance Response for Symmetric and Asymmetric Evacuation Problems

Background: Serious secondary disasters caused by extreme natural weather conditions occur frequently, making it essential to establish a scientific and efficient modern emergency management system to maximize life-saving efforts. Methods: This study focuses on the uncertain environment of urban road networks and employs fuzzy theory to construct a 0–1 integer programming model for emergency evacuation paths that minimizes the average expected travel time. Results: We enhanced the neighborhood search strategy of the traditional ACO_time by incorporating the 2-opt and 3-opt perturbation mechanisms from the SA algorithm. Additionally, we utilized improved ant-volume and ant-perimeter models, along with their combinations, in the pheromone-updating mechanism of the basic ACO. The heuristic principles of the A* algorithm were integrated, introducing the joint influence of path and time into the heuristic function of the ACO algorithm. Conclusions: The IACO3 algorithm was tested on the Sioux Falls network and the Berlin Heisenheimer Center network. The computation time of the improved IACO3 algorithm was reduced by up to 20% compared to the original IACO3 algorithm in relation to the SA algorithm, with only a 4–5% increase in computation time compared to the ACO_time algorithm, which translates to an increase of merely 4–5 s. This demonstrates the superior solution efficiency of the IACO3 algorithm.

Influence of Transport Process Management on Exceeding Permitted Load Weights in Transport Companies

Poland is the leader in the performance of international transport in the EU, serving more than half of its market. The most common branch of transport is road transport, predominantly heavy goods transport, which contributes to the strain on road infrastructure. Furthermore, around one-fifth of those vehicles may exceed the permissible total mass. In this respect, the increasing demand for road transport further complicates the slowdown and prevention of road network degradation. Overloads have significant consequences for road infrastructure, economics, and traffic safety. Load management in transport companies is crucial for eliminating overloads. This article aims to assess how companies conducting freight transport manage the cargo weighing process in the context of potential overloads. Data from a survey among transport industry companies in Poland were analysed. Using non-parametric U Mann-Whitney and Kruskal-Wallis tests, the influence between propensity for cargo overloading and the method of cargo weighing was examined. The results indicated that the propensity for cargo overloading in TSL industry companies is significantly associated with both the occurrence of the weighing process and its method, as well as the responsibility for this process among individual participants in the transport process.

Real-Time Monitoring of Road Networks for Pavement Damage Detection Based on Preprocessing and Neural Networks

This paper presents a novel multi-initialization model for recognizing road surface damage, e.g. potholes and cracks, on video using convolutional neural networks (CNNs) in real-time for fast damage recognition. The model is trained by the latest Road Damage Detection dataset, which includes four types of road damage. In addition, the CNN model is updated using pseudo-labeled images from semi-learned methods to improve the performance of the pavement damage detection technique. This study describes the use of the YOLO architecture and optimizes it according to the selected parameters, demonstrating high efficiency and accuracy. The results obtained can enhance the safety and efficiency of road pavement and, hence, its traffic quality and contribute to decision-making for the maintenance and restoration of road infrastructure.

An Optimal Road Network Extraction Methodology for an Autonomous Driving-Based Demand-Responsive Transit Service Considering Operational Design Domains

In addition to addressing the labor shortage due to an aging population, the transition to autonomous vehicle (AV)-based mobility services offers enhanced efficiency and operational flexibility for public transportation. However, much of the existing focus has been on improving AV safety without fully considering road conditions and real-world service demand. This study contributes to the literature by proposing a comprehensive framework for efficiently integrating AV-based mobility services at the network level, addressing these gaps. The framework analyzes and optimizes service networks by incorporating actual demand patterns, quantifying road segment difficulty from an AV perspective, and developing an optimization model based on these factors. The framework begins by quantifying the operational difficulty of road segments through an evaluation of Operational Design Domains (ODDs), providing a precise measure of AV suitability under varying road conditions. It then introduces a quantitative metric to assess operational feasibility, considering factors such as the service margin, costs, and safety risks. Using these metrics alongside Genetic Algorithms (GAs), the framework identifies an optimal service network that balances safety, efficiency, and profitability. By analyzing real-world data from different mobility services, such as taxis, Demand-Responsive Transport (DRT), and Special Transportation Services (STSs), this study highlights the need for service-specific strategies to optimize AV deployment. The findings show that optimal networks vary with demand patterns and road difficulty, demonstrating the importance of tailored network designs. This research provides a scalable, data-driven approach for integrating AV services into public transportation systems and lays the foundation for further improvements by incorporating dynamic factors and broader urban contexts.

Real-Time Monitoring and Forecasting Ice Layer Thickness Growth Rate and Grip Loss on a Road Network During Winter Storm Events

Real-Time Monitoring and Forecasting Ice Layer Thickness Growth Rate and Grip Loss on a Road Network During Winter Storm Events