Smart Road Research Articles

ANTi-JAM solutions for smart roads: Ant-inspired traffic flow rules under CAVs environment

ANTi-JAM solutions for smart roads: Ant-inspired traffic flow rules under CAVs environment

SIMULATING VEHICLE-TO-VEHICLE COMMUNICATION AT ROUNDABOUTS

Smart roads integrate advanced technology to enhance safety, effectiveness, and eco-friendliness, revolutionizing transportation systems. Within this framework, connectivity and automation work together to improve road mobility and energy efficiency. However, there are still uncertainties regarding their effect on road safety and traffic operations, as well as assessment methods, especially for intersections and roundabouts. Navigating roundabouts involves complex decision-making influenced by cooperative and competitive interactions between human-driven vehicles and connected and autonomous driving vehicles (CADVs), affecting gap-acceptance patterns. This research employs Aimsun Next software to simulate the rising market penetration percentages of CADVs by examining assumption-based behavior on single-lane roundabouts. It integrates CADV-based capacity modification factors from the Highway Capacity Manual 2022 and compares adapted capacity curves for CADVs, with simulated capacities for model calibration. Critical model parameters affecting CADVs; ability to enhance roundabout safety and throughput are identified, with a focus on the transition towards cooperative driving in the context of smart roads.

Self-powered asphalt-based sensors for smart roads

Monitoring traffic conditions and pavement structures is essential for intelligent transportation systems. However, conventional sensors have limitations, including poor compatibility with pavement and high maintenance costs. Here, we present the concept of transforming asphalt from a pavement structural component to a sensing component and demonstrate its application in smart road systems. The functional asphalt was customized by adding piezoelectric materials into the asphalt matrix. We optimized its piezoelectric properties by improving the fabrication process and measured the electrical performance of the asphalt-based sensors. In the traffic monitoring experiment, we developed a system incorporating data acquisition, signal processing, and wireless transmission functions to capture tire-ground contact information. The details, such as speed and wheelbase, are decoded by a feature extraction algorithm and input into a support vector machine (SVM) classification model for training and testing. The model reaches a test accuracy of 97 % in training a small-sample dataset. In addition, the self-powered asphalt-based sensor showed its feasibility and potential in the verification experiments of acoustic source localization (error = 2.4 %) and energy harvesting. Our work proposes a low-cost, environmentally friendly, multifunctional material suitable for road sensors, potentially facilitating the large-scale implementation of smart road networks.

Boundary Layer Modelling of Flow Acceleration and Energy Transfer Effects in Smart Pavement Design

The integration of remote technology into the construction industry has advanced the emergence of smart, self-learning infrastructure across all levels of land transportation design and development. However, energy harvesting capabilities for smart road ventilation purposes have not yet been fully researched as the world gravitates towards energy sustainability. This study thus presents a mathematical investigation of the self-draining design potentials of road pavements, leveraging on energy absorption and conversion to accelerate conductive and convective ventilation of these pavements during wet conditions, as a means of ensuring the skid resistance and safety of such pavements are not compromised. Applying numerical methods with the aid of commercial software code MATLAB®, the classical physics of fluid-surface interaction was used to model accelerated drainage of microflood off paved surfaces through methodical modification of the thickness of the boundary layer associated with the flow regime over the flat road surface. Results indicate significant influences of energy exchange, thermal, and viscous diffusivity on flow acceleration. Alterations in parameters such as the slip factor, thermally induced Brownian motion or phoretic characteristics of the fluid particles at the boundary induce accelerated flow at the surface of the pavement. The findings contribute to the advancement of smart infrastructure by offering practical insights into the potential benefits of integrating energy-harvesting technologies into road pavement systems. By optimizing flow acceleration mechanisms, smart pavements can play a crucial role in improving road safety and sustainability in urban environments.

Real-time joint recognition of weather and ground surface conditions by a multi-task deep network

Climate change and the occurrence of intense and unexpected weather events highlighted the need for real-time weather warning systems, especially in smart roads and isolated scenarios like rural areas. In this work, we propose to jointly recognize the weather and the ground surface conditions using existing video surveillance systems. Previous works separately tackled these two tasks even if they are correlated to each other. We propose a convolutional neural network with shared weights in the lower layers and two separate classification branches on top to exploit the correlation between the tasks and, at the same time, learn diverse high-level features for each task. Moreover, the network architecture implements attention mechanisms allowing the classification branches to focus on diverse image regions. The method is versatile and allows us to train the network on partially labeled data. The experimental analysis on real data demonstrate the effectiveness of the proposed method on both tasks, confirmed by the accuracy comparison with existing methods for the recognition of weather and ground surface conditions. The multi-task solution improves the inference speed (50 frames per second) and reduces the required memory (less than 1 GB) with respect to a system with two different single-task approaches; these results confirm that the proposed solution is ready for video surveillance applications to support smart cities.

자율주행 차량 사고 원인 분석을 통한 안전성 제고 방안

Although the convenience of drivers is maximizing due to the full-fledged self-driving service, complex problems are still emerging in various areas, including legal, ethical, and social aspects. As a result, social awareness and acceptability of self-driving cars have not been sufficiently formed, and efforts to improve stability are essential at this point. Therefore, in this study, only records of accidents while driving autonomously were selected among the accident data of autonomous vehicles provided by California DMV and the causes of accidents were analyzed for about 400 cases. As a result, main causes were verified as low recognition rate of parked vehicles, inability to grasp changes in vehicle size due to attachment of convenience goods, insufficient defense driving system, low recognition speed in special road conditions, etc. To mitigate these problems, it is expected to increase vehicle recognition rate, reconstruct safety area range, devise additional vehicle functionalities for defensive driving, and emphasize the importance of communication between self-driving cars and smart roads. These measures aim to enhance the safety of autonomous vehicles and contribute to increasing positive social perception and trust in autonomous driving.

Retraction Note: Machine learning and IoTs for forecasting prediction of smart road traffic flow

Retraction Note: Machine learning and IoTs for forecasting prediction of smart road traffic flow

Research on Urban Expressway Design Based on New Transportation Concepts

This article is based on the Suzhou Central Expressway project, adhering to the principles of "safety, comfort, ecology, wisdom, and harmony", adhering to the comprehensive, coordinated, and sustainable development concept, guided by the new concept of transportation construction of the Ministry of Transport, integrating the design concept of traffic safety first, resource conservation, environmental friendliness, technological innovation, and intelligent collaboration, and organically combining nature, culture, and roads. The design strives to achieve road aesthetic design, tolerant design, humanistic design, flexible design, and creative design, which is of great significance for the research of ecological smart road design, transportation industry, and sustainable development of nature and culture.

Advanced Sensor Technologies in CAVs for Traditional and Smart Road Condition Monitoring: A Review

This paper explores new sensor technologies and their integration within Connected Autonomous Vehicles (CAVs) for real-time road condition monitoring. Sensors like accelerometers, gyroscopes, LiDAR, cameras, and radar that have been made available on CAVs are able to detect anomalies on roads, including potholes, surface cracks, or roughness. This paper also describes advanced data processing techniques of data detected with sensors, including machine learning algorithms, sensor fusion, and edge computing, which enhance accuracy and reliability in road condition assessment. Together, these technologies support instant road safety and long-term maintenance cost reduction with proactive maintenance strategies. Finally, this article provides a comprehensive review of the state-of-the-art future directions of condition monitoring systems for traditional and smart roads.

Evaluation of the Implementation Status of the Nepal Rural Road Standards (NRRS) Concerning Geometrical Parameters: A Case Study of Morang District of Nepal

Maintaining the effectiveness of the transportation system is essential to economic growth. Poor road upgrading methods in many developing nations, however, are making it impossible for traffic to flow freely. Nepal developed the Nepal Rural Road Standards (NRRS) of 2055, District Transportation Master Plan (DTMP), and Municipality Transportation Master Plan (MTMP) to regulate the construction of rural road infrastructure. These guidelines provide guidelines for rural road planning, design, building, and maintenance, among other aspects. However, each geometric design has certain features, and parameter requirements depending on the region and location to be applied. This study aims to compare the geometrical features of the rural roads that have been built with the Nepal Rural Road Standards (NRRS) 2055, second revision (2071). Using a random sampling approach, six rural roads in the Morang district were selected for the data collection. To gather geometrical data, field observations and measurements were made at random chainages. This study evaluates various geometric parameters using linear and angular field measurements. Mapping conducted via smart road software ensures road geometry compliance, including aspects such as curve radius, shoulder width, gradient, sight distance, carriageway, and additional widening. The findings demonstrate that strict adherence to established standards substantially enhances road safety. Based on the results of the field observation, the geometric elements have been built according to design specifications, except for the additional widening at shoulder width and horizontal.

Enhanced building energy harvesting through integrated piezoelectric materials and smart road traffic routing

Enhanced building energy harvesting through integrated piezoelectric materials and smart road traffic routing

Investigating the impact of temporal instability in smart roadway retrofitting on terrain-related crash injury severity

The advancement of intelligent road systems in developing countries poses unique challenges in identifying risk factors and implementing safety strategies. The variability of factors affecting crash injury severity leads to different risks across levels of roadway smartness, especially in hazardous terrains, complicating the adaptation of smart technologies. Therefore, this study investigates the temporal instability of factors affecting injury severities in crashes across various terrains, with a focus on the evolution of road smartness. Crash data from selected complex terrain regions in Shaanxi Province during smart road adaptation were used, and categorized into periods before, during, and after smart road implementations. A series of mixed logit models were employed to account for unobserved heterogeneity in mean and variance, and likelihood ratio tests were conducted to assess the spatio-temporal instability of model parameters across different topographic settings and smart processes. Moreover, a comparison between partially constrained and unconstrained temporal modeling approaches was made. The findings reveal significant differences in injury severity determinants across terrain conditions as roadway intelligence progressed. On the other hand, certain factors like pavement damage, truck and pedestrian involvement were identified that had relatively stable effects on crash injury severities. Out-of-sample predictions further emphasize the need for modeling across terrain and roadway development stages. These insights are crucial for developing tailored safety measures for smart road retrofitting in different terrain conditions, thereby supporting the transition towards smarter road systems in developing regions.

Enhancing smart road safety with federated learning for Near Crash Detection to advance the development of the Internet of Vehicles

We introduce an innovative methodology for the identification of vehicular collisions within Internet of Vehicles (IoV) applications. This approach combines a knowledge base system with deep learning for model selection in an ensemble learning setting. It is designed to provide a general near-crash detection capability without relying on domain-specific knowledge, enabling the development of generic deep learning models. Our proposed methodology employs a novel deep learning approach, wherein multiple learning models are individually trained for each image. Subsequently, visual features are computed and stored for each trained image, along with the associated loss values from the training phase. This stored information is utilized to select the most suitable models for processing new image data during the testing phase. To facilitate efficient model selection, we employ a kNN (k Nearest Neighbors) strategy. To enhance both data and model security in IoV environments, we implement an intelligent federated learning (FL) strategy. Users are organized into clusters, and we employ two distinct aggregation methods, departing from conventional federated learning approaches. In the initial stage, we aggregate model data from all users to create a global model representing collective knowledge. In the subsequent stage, we aggregate models from each cluster to generate customized local models. Users are provided with both global and local models, allowing them to select the most suitable model for their specific crash detection needs. We test our approach, that we call Knowledge Guided Deep Learning for Near Crash Detection (KGDL-NCD), on well-known NCD benchmarks. The results demonstrate that KGDL-NCD surpasses baseline solutions, achieving an AUC (Area Under Curve) metric of 0.95.

A comparative review study on the electrified road structures: Performances, sustainability, and prospects

The electrified road (eRoad) technology, which allows for delivering electrical power to electric vehicles (EVs) in motion, has been under active development as a novel charging solution, with a great potential to eliminate EV’s range anxiety and to reduce the battery dependency. Three promising eRoad technologies, including pantograph, conductive rail, and the inductive power transfer (IPT), have gained momentum. In this review, the following studies are performed: (1) a comparative analysis of the three eRoad technologies is made by focusing on the working principles, performances as well as technology readiness levels (TRLs). (2) From the perspective of road infrastructure, the potential structural compatibility issues are extensively discussed; the recommendations and emerging research needs, which could improve the eRoads’ service lifetime, are further presented. (3) Life cycle sustainability potential for the three eRoad solutions are comparably analyzed, emphasizing as well the importance of integrating eRoad infrastructure into the full life cycle assessment on the use of EVs for clean transport. (4) In the context of the drastic development of smart road systems, potential synergistic development of eRoad with other novel technologies is envisioned.

Drivers’ Steering Behavior in Curve by Means of New Indicators

The design of road geometry is based on a rather elementary assumption that the user strictly follows the lane axis. Based on this hypothesis, the ideal trend of some factors related to the driver’s performance, such as steering angle and speed, can be derived to optimize the most appropriate design choices. In practice, driving behavior differs from the assumed one and produces trends in these variables, which are very different from the ideal functions. The purpose of this research is therefore to propose synthetic performance indicators useful for highlighting the real characteristics of users’ driving behavior during road travel. Toward this aim, some driving experiments along four different curves in a simulated environment were studied in order to evidence possible criticisms. The proposed indicators showed a remarkable ability to represent and synthesize even very complex performance function trends. The proposed performance indicators can have multiple uses, such as, for example, in statistical analyses—which are generally carried out at a later stage—or constitute sufficient information to guide the decisions of infrastructure managers. In the long term, in a “smart road” perspective, they can be used by road administrators for information exchange among users (with each other and with the infrastructure) to improve road operation and safety.

Smart Road Networks in Urban Freight Transport for Sustainable City Logistics

Smart Road Networks in Urban Freight Transport for Sustainable City Logistics

Effective Space Utilization System In Smart Cities Using IOT And Image Processing

In the world of Smart Cities, we're exploring new ways to improve our urban spaces using the Internet of Things (IoT). By using devices like Arduino, we're creating models for Smart City solutions, focusing on things like Smart Parking, Traffic Road Dividers, and Patrolling Vehicles.Our main goal is to make cities safer and better by using technology like IoT and image processing. For example, we're working on special road dividers that help manage traffic by separating cars going in different directions. These "Smart Road Dividers" are designed for cities and use sensors and technologies to adapt to how busy the roads are, helping traffic flow better and easing congestion.Cameras are being used on patrolling vehicles to spot cars parked in the wrong places. If they see something wrong, they quickly tell the right people so they can sort it out. This helps make sure that people park their cars properly and follow the rule.

Survey Paper on Road Damage Detection and Reporting System Using Fully Connected CNN

Many rural and metropolitan towns, as well as road authorities, encounter challenges in mapping surface damages resulting from numerous sources such strong rains, natural catastrophes, or other events that cause cracks and holes to emerge on the road surface. These organizations or private entities look out for solutions to implement automated methods of reporting damages on a surface of the road. The majority of the time, they lack the equipment needed to map the damage to the roadways. One of the main issues facing commuters is the numerous damaged road portions they must navigate. This causes riders to often reduce their pace, losing a great deal of time and energy and lengthening the time it takes them to reach their destinations. When driving at a faster speed and suddenly encountering a damaged section of the road, road damage can frequently be fatal. Furthermore, it is capable of identifying recurring bottlenecks, determining their cause, and suggesting remedies. The majority of the time, these traffic jams are brought on by road damage, which forces commuters to go far slower than is ideal. Keywords: Smart road damage detection, classification, Machine Learning, Image segmentation, CNN, fully connected CNNs, RDD System (Road Damage Detection System).

Reduction of the negative environmental impact of motor transport through the use of intelligent transport systems

The work investigates the anthropogenic impact of motor transport on the environment of urbanized areas, including emissions of pollutants into the air, noise and vibration effects. The efficiency of using intelligent transport systems (ITS) to solve various problems of the motor transport complex, including reduction of its negative environmental impact, is shown. The authors considered a local project of the intelligent transport system "Smart Road", implemented in the Kursk region. An assessment of the effectiveness of various ITS scenarios in terms of improving environmental performance on road sections and regulated intersections has been carried out. The following indicators of environmental safety have been studied: mass emission of pollutants contained in the exhaust gases of vehicles; noise level from traffic flow. A significant decrease in the emissions of pollutants from trucks at the site of ITS use has been established, as well as a decrease in the overall noise load from vehicles. At the same time, it is shown that there was no reduction in emissions from cars and minibuses. In this regard, it is proposed to develop scenarios for the functioning of ITS, ensuring the optimization of these types of vehicles.

Smart Roads: Roadside Perception, Vehicle-Road Cooperation and Business Model

Smart Roads: Roadside Perception, Vehicle-Road Cooperation and Business Model