Road Surface Conditions Research Articles

Joint Estimation of Driving State and Road Surface Adhesion Coefficient of a Four-Wheel Independent and Steering-Drive Electric Vehicle

Vehicle running state parameters and road surface state are crucial to the stability of four-wheel independent drive and steering electric vehicle control. Therefore, this study explores the estimation of vehicle driving state parameters and road surface adhesion coefficients using a combination of federal Kalman filtering and an intelligent bionic antlion optimization algorithm. Firstly, according to the research purpose of the paper and the focus on the accuracy of the establishment of the three degrees of freedom dynamics model, fully considering the road conditions, the paper adopts the Dugoff tire model and finally completes the establishment of the vehicle state estimation model. Secondly, the drive state estimation algorithm is developed utilizing the principles of federal Kalman filtering and volume Kalman filtering. At the same time, robust estimation theory is introduced into the sub-filter, and the antlion optimization module is designed at the lower layer of the main filter to enhance the accuracy of estimates. It is easy to see that the design of the Antlion federal Kalman travel state estimation algorithm has noticeably enhanced accuracy and traceability, according to the result. Thirdly, a joint estimation algorithm of state estimation and road surface adhesion coefficient has been devised to enhance the stability and precision of the estimation process. Finally, the results showed that the joint estimation algorithm has high accuracy in estimating vehicle driving state parameters such as the center of mass lateral deflection angle and road surface adhesion coefficient by simulation.

Snow‐ or ice‐covered road detection in winter road surface conditions using deep neural networks

AbstractTraffic accidents occur frequently in cold and snow‐ or ice‐covered regions due to weather changes that occur during the winter season. To detect the snow‐ or ice‐covered roads in road surface conditions, road surface images captured using fixed‐point cameras installed along the route are sufficient. This paper proposes a snow‐ or ice‐covered road detection method that uses the deep convolutional autoencoding Gaussian mixture model (DCAGMM) with structural similarity (SSIM). The DCAGMM method, which is an unsupervised anomaly detection method, is unaffected by imbalance in the training data. In addition, the end‐to‐end convolutional neural network implemented in the DCAGMM enables the capture of the unique characteristics of the road surface images. Finally, by reconstructing the input images as normal images, the comparison of the input and reconstructed images enables identification of snow‐ or ice‐covered road areas without requiring pixel‐level annotations. Furthermore, the road surface images include complex characteristics for reconstruction, and the SSIM‐based reconstruction error allows us to preserve the image quality of the reconstructed image. Experimental results obtained on real‐world road surface images demonstrate the effectiveness of the proposed method.

Multimodal Transformer Model Using Time-Series Data to Classify Winter Road Surface Conditions.

This paper proposes a multimodal Transformer model that uses time-series data to detect and predict winter road surface conditions. For detecting or predicting road surface conditions, the previous approach focuses on the cooperative use of multiple modalities as inputs, e.g., images captured by fixed-point cameras (road surface images) and auxiliary data related to road surface conditions under simple modality integration. Although such an approach achieves performance improvement compared to the method using only images or auxiliary data, there is a demand for further consideration of the way to integrate heterogeneous modalities. The proposed method realizes a more effective modality integration using a cross-attention mechanism and time-series processing. Concretely, when integrating multiple modalities, feature compensation through mutual complementation between modalities is realized through a feature integration technique based on a cross-attention mechanism, and the representational ability of the integrated features is enhanced. In addition, by introducing time-series processing for the input data across several timesteps, it is possible to consider the temporal changes in the road surface conditions. Experiments are conducted for both detection and prediction tasks using data corresponding to the current winter condition and data corresponding to a few hours after the current winter condition, respectively. The experimental results verify the effectiveness of the proposed method for both tasks. In addition to the construction of the classification model for winter road surface conditions, we first attempt to visualize the classification results, especially the prediction results, through the image style transfer model as supplemental extended experiments on image generation at the end of the paper.

An Investigation in the Control Effectiveness of the Driving Wheel Slip Prevention System of a Diesel Engine Dump Truck

<div>This article proposes the structure and algorithm to design a PID controller for the driving wheel slip prevention system (DWSPs) of a dump truck using a diesel engine, which is equipped just only with a traditional high-pressure pump (HPP) under low-adhesion coefficient conditions. First, a longitudinal dynamic model, and a dynamic model of the wheel and powertrain of a dump truck are, respectively, established, and an experiment in the torque determination of a diesel engine is set up to investigate longitudinal vehicle dynamics as well. Then, a control system structure of the DWSPs for a dump truck using a diesel engine with a high-pressure inline fuel pump is proposed. Finally, based on performance analysis of other types of controllers, a PID controller is selected to control actual load level of a diesel engine. The criteria representing the vehicle’s acceleration such as the vehicle speed, vehicle acceleration, total slip time, and time to reach vehicle speed are selected to examine the effectiveness of the proposed controller when vehicles are being operated under the road surface conditions with low values of adhesion coefficient. The obtained results show that the proposed controller has greatly limited the driving wheel slipping phenomenon and increased the acceleration of the original dump truck. In addition, these findings can be used as a theoretical basis for the improvement of the wheel slip controllers in trucks using diesel engines.</div>

Evaluation of data representation techniques for vibration based road surface condition classification

The accurate classification of road surface conditions plays a vital role in ensuring road safety and effective maintenance. Vibration-based techniques have shown promise in this domain, leveraging the unique vibration signatures generated by vehicles to identify different road conditions. In this study, we focus on utilizing vehicle-mounted vibration sensors to collect road surface vibrations and comparing various data representation techniques for classifying road surface conditions into four classes: normal road surface, potholes, bad road surface, and speedbumps. Our experimental results reveal that the combination of multiple data representation techniques results in higher performance, with an average accuracy of 93.4%. This suggests that the integration of deep neural networks and signal processing techniques can produce a high-level representation better suited for challenging multivariate time series classification issues.

Enhancing Tire Condition Monitoring through Weightless Neural Networks Using MEMS-Based Vibration Signals

Tire pressure monitoring system (TPMS) has a critical role in safeguarding vehicle safety by monitoring tire pressure levels. Keeping the accurate tire pressure is necessary for confirming comfortable driving and safety, and improving fuel consumption. Tire problems can result from various factors, such as road surface conditions, weather changes, and driving activities, emphasizing the importance of systematic tire checks. This study presents a novel method for tire condition monitoring using weightless neural networks (WNN), which mimic neural processes using random-access memory (RAM) components, supporting fast and precise training. Wilkes, Stonham, and Aleksander Recognition Device (WiSARD), a type of WNN, stands out for its capability in classification and pattern recognition, gaining from its ability to avoid repetitive training and residual formation. For vibration data acquisition from tires, cost-effective micro-electro-mechanical system (MEMS) sensors are employed, offering a more economical solution than piezoelectric sensors. This approach yields a variety of features, such as autoregressive moving average (ARMA), statistical and histogram features. The J48 decision tree algorithm plays a critical role in selecting essential features for classification, which are subsequently divided into training and testing sets, crucial for assessing the WiSARD classifier’s efficacy. Hyperparameter optimization of the WNN leads to improved classification accuracy and shorter computation times. In practical tests, the WiSARD classifier, when optimally configured, achieved an impressive 97.92% accuracy with histogram features in only 0.008 seconds, showcasing the capability of WNN to enhance tire technology and the accuracy and efficiency of tire monitoring and maintenance.

Improving Driving Style in Connected Vehicles via Predicting Road Surface, Traffic, and Driving Style

This paper investigates the application of ensemble learning in improving the accuracy and reliability of predictions in connected vehicle systems, focusing on driving style, road surface quality, and traffic conditions. Our study’s central methodology is the voting classifier ensemble method, which integrates predictions from multiple machine learning models to improve overall predictive performance. Specifically, the ensemble method combines insights from random forest, decision tree, and K-nearest neighbors models, leveraging their individual strengths while compensating for their weaknesses. This approach resulted in high accuracy rates of 94.67% for driving style, 99.10% for road surface, and 98.80% for traffic predictions, demonstrating the robustness of the ensemble technique. Additionally, our research emphasizes the importance of model explanation ability, employing the tree interpreter tool to provide detailed insights into how different features influence predictions. This paper proposes a model based on the algorithm GLOSA for sharing data between connected vehicles and the algorithm CTCRA for sending road information to navigation application users. Based on prediction results using ensemble learning and similarity in driving styles, road surface conditions, and traffic conditions, an ensemble learning approach is used. This not only contributes to the predictions’ transparency and trustworthiness but also highlights the practical implications of ensemble learning in improving real-time decision-making and vehicle safety in intelligent transportation systems. The findings underscore the significant potential of advanced ensemble methods for addressing complex challenges in vehicular data analysis.

Dynamic Load Analysis of Mine-Truck Using Multibody Dynamic Analysis Method

Abstract: Vehicle load distributed on front & rear axle assembly during various working conditions is one of the most important factors influencing working performance and service life of drive axle assembly. The dynamic load on axle assembly is higher compared to the rated load because of variations in vehicle speed and road surface conditions. Early failure of structural components is caused because of higher dynamic reaction forces due to uneven road profiles. The dynamic load calculation of axle assembly is presented in this paper for a Mine-truck with various road conditions and vehicle speeds. The road load conditions consist of grade, bump & path hole. Mine-truck with payload capacities of 63 Ton is considered for the study. The behaviour of vertical force is calculated for different vehicle speeds (3 - 12 km/hr.) of the machine on the front & rear axle assembly during running conditions. Multi-body dynamic Analysis tool ADAMS is used for this study. ADAMS helps to study the dynamics of moving parts and load distribution throughout mechanical systems during motion. The Mine-truck3D model was created with the help of computer-aided design (CAD) software. Major units of Mine trucks are considered to prepare 3D models like Cabin-engine mass, Bucket, front axle assembly, rear Axle assembly & tires. Multi-body vehicle models are prepared in simulation software ADAMS by importing 3D models prepared by computer-aided design (CAD) software. This provides guidelines for selecting dynamic load factors while designing structural parts of the vehicle.

Detection of Lane & Speed Breakers for Autonomous Vehicles using CNN

Abstract: The advancement of autonomous vehicles necessitates robust systems for real-time detection of lane markings and speed breakers to ensure safe and efficient navigation. In this paper, we propose a novel approach for lane and speed breaker detection utilizing Convolutional Neural Networks (CNN). Our method achieves remarkable accuracy in identifying lane markings and speed breakers from input images captured by onboard cameras. By leveraging the capabilities of CNN, our system demonstrates superior performance in diverse environmental conditions, including varying lighting, weather, and road surface conditions. We present a comprehensive analysis of the CNN architecture employed in our system, highlighting its ability to extract meaningful features from raw image data and make accurate predictions. The training process involves a large dataset comprising annotated images of lane markings and speed breakers, enabling the CNN to learn discriminative patterns for effective detection. Furthermore, we evaluate the performance of our proposed system through extensive experimentation, quantifying its accuracy, precision, and recall rates across different scenarios. The results indicate the effectiveness and reliability of our approach in real-world settings, showcasing its potential for integration into autonomous vehicle platforms. Overall, this paper contributes to the field of autonomous driving by presenting a robust and efficient solution for lane and speed breaker detection, leveraging the power of machine learning algorithms, specifically CNN, to enhance the safety and autonomy of vehicles on the road.

Characteristics of Skid Resistance for Pavements with Black Ice

Korea experiences a four-season climate, leading to significant fluctuations in seasonal road surface conditions and contributing to numerous traffic accidents. Over the period of five years since 2016, approximately 4,800 traffic accidents have been attributed to icy and frosty road conditions, with a fatality rate 1.5 times higher than that of general traffic accidents. This study aims to analyze the skid resistance properties of domestic asphalt pavements as an initial step toward establishing indicators to mitigate and manage traffic accidents caused by black ice. In this study, the BPN was measured using BPT equipment specified in the ASTM and KS standards. The road pavement surface conditions were assessed under three categories: dry, wet, and frozen (black ice). The recorded BPN values decreased in the following order: dry, wet, and frozen conditions. Under wet conditions, a comparative analysis was performed between dense asphalt pavements and drainable pavements. Furthermore, the evaluation under frozen conditions revealed no significant disparity between the types of road pavement. Notably, the exposure of the road pavement aggregate owing to freezing and the resultant surface roughness had a minimal impact on the skid resistance.

A Study on Power Transmission Control for Applying MR Fluid Multi-Plate Clutch to Automobile Power Distribution Device

The aim of this study is to design and manufacture a multi-plate clutch system that uses magnetorheological (MR) fluid control to allow for a variable power transmission ratio in power distribution systems. MR fluid is a smart material that enables presenting a solution to the shocks and power loss that occur due to mechanical problems in power distribution systems. As such, the longitudinal and lateral dynamic properties of 4WD (four-wheel drive) vehicles were examined and analyzed to develop an algorithm to control the front/rear power distribution according to the road surface state and driving conditions. To verify the algorithm, the CarSim vehicle dynamics simulation program was adopted to perform experiments to understand the vehicle’s dynamic performance improvements and turning stability via a HILS (Hardware in the Loop) system. In this study, an MR fluid, multi-plate clutch was used that combines a dry clutch and a wet clutch using the characteristics of the MR fluid. Such a clutch was designed to enable continuous and smooth torque transmission by utilizing the strengths of each of the dry and wet clutches. The CarSim vehicle dynamics program was used to conduct the experiments, which were conducted by linking to the manufactured MR fluid clutch experimental device. The experiments investigated the dynamic performance based on the power distribution ratio by performing longitudinal flat, inclined driving and lateral DLC (double lane change) driving. In summary, this study found that it is possible to perform power transmission by applying a current to an MR fluid and forming a magnetic field to change the flow properties of the fluid to control the torque transmission ratio that occurs in an MR fluid clutch.

An efficient safest route prediction-based route discovery mechanism for drivers using improved golden tortoise beetle optimizer

ABSTRACT Several commercialised route recommendation systems only consider the metrics like cost, time, and distance. The essential metric ‘safety’ is neglected by the existent systems. It suggests only the short way and doesn’t include any safety information, such as crime awareness, road availability. This paper describes an inventive ideology to discover the safest route with minimal risk score for security of the road travellers. Hence, a new safety route navigation mechanism is developed to solve the challenges in the traditional route discovery approaches using deep learning. In the developed route discovery mechanism, the examination of the safest roads is done by the developed deep learning network, where the network is trained with the inputs obtained from the roads, such as road surface conditions, Road users, weather conditions, traffic conditions, accidental cases, and crime areas. The availability of the safest route will be determined by the ‘Long Short-Term Memory with Attention Mechanism’ (LSTM-AM). The route discovery is done with the help of a developed ‘Fitness-based Golden Tortoise Beetle Optimizer’ (FGTBO) with multi-objective constraints like distance, time, and road availability. The implementation outcome of the developed route discovery scheme will be validated with the traditional route discovery approaches concerning various measures.

Vehicle–Bridge Coupling Vibration of Long-Span Concrete-Filled Steel Tubular Arch Bridge

An increase in the nonlinearity of the bridge will lead to a more obvious vehicle–bridge interaction effect and affect the vehicle response and driving comfort as the span increases. This paper establishes a refined finite element model of vehicle–bridge coupling for the 575 m long-span concrete-filled steel tubular arch bridge, Pingnan Third Bridge. Coupling vibration responses under different vehicle speeds, vehicle weights and road conditions of this bridge is analyzed. Then its comfort is assessed according to the comfort criterion. The results show that the vehicle–bridge coupling model has good agreement with the field test. The dynamic response of the bridge within the speed limit has no significant linear relationship with the magnitude of the vehicle speed without considering the pavement class. When the vehicle exceeds the speed limit, the dynamic response increases sharply with the increase in speed. The increase in vehicle weight leads to an increase in the maximum dynamic deflection of the bridge and a decrease in the impact coefficient, but the actual total response of the bridge does not decrease. The worse the road surface condition, the more dramatic the dynamic response of the bridge structure, taking into account the road surface level.

Weather event characterization: a catalyst for improved spatial mapping and benefit quantification in winter road maintenance

Monitoring winter road surface conditions (RSC) is essential for optimizing winter road maintenance operations and ensuring public traffic safety and mobility. However, many existing RSC estimation methods focus primarily on local or site-specific conditions, thus lacking effectiveness in comprehensive spatial mapping under varying winter weather events. Additionally, the potential financial benefits these methods could provide to maintenance authorities remain largely unexplored. This study addresses these gaps by introducing a refined methodology that harnesses the K-Means algorithm to characterize various weather events – a significant stride towards improving the generalizability and accuracy of road surface temperature (RST) estimations. The study also incorporates regression kriging (RK), a renowned geostatistical technique, as an integral component of a system for constructing an extensive spatial map of RSC across large highway networks. This strategy maximizes the use of data from existing road weather information systems (RWIS) to bridge their large spatial gaps. This study further quantifies the potential savings derived from optimally placing RWIS stations and reducing traffic collisions. The efficacy of these methods is validated through a real-world case study on two major interstate highways in Iowa, US, with RST estimation discrepancies as low as 0.619 °C. The findings also indicate potential cost savings by conserving up to 10 RWIS stations, which can be further translated into monetary savings of RWIS capital costs, traffic collisions prevention, enhanced traffic mobility and savings in maintenance material usage.

Cooperative truck platooning trial on Canadian public highway under commercial operation in winter driving conditions

Cooperative truck platooning, a convoy of trucks driving together while communicating and coordinating with each other, represents a technology-driven approach to improve energy conversion efficiency, lower greenhouse gas emissions, and enhance road safety. Despite numerous studies have explored these potentials, there is a scarcity of empirical investigations into on-road cooperative truck platooning during commercial operations, particularly in winter driving conditions. This paper presents the findings of an experimental study on the first commercially focused truck platooning implementation on a Canadian public highway in the winter season, using two SAE level 2 class 8 trucks. The on-road trials took place on the Queen Elizabeth II Highway, between Calgary and Edmonton, with ambient temperatures ranging from −27°C to 12°C, and truck weights spanning 16–39 tons. Nine well-trained and experienced drivers conducted 41 incident-free (platooning and baseline) test trips, covering a distance of 22,855 km. The experimental results confirmed the feasibility of operating commercial truck platooning with 3–5 s time gaps on public roads during the Canadian winter season including various road surface conditions. The results also show that the platooning engagement ratio reached up to 88.9%, with an average of 61.6% across 25 platooning trips. Furthermore, the follower truck achieved a 1.6% fuel savings on flat road sections during platooning, but its freight transportation specific fuel consumption was higher than that of the lead truck on hilly terrain. Test results indicate the lighter truck exhibited higher specific nitrogen oxides (NOx) emissions. Moreover, the frequent engagement and disengagement of the cooperative truck platooning system had adverse effects on the powertrain system of the truck, leading to increased fuel consumption and engine-out NOx emissions. This study provides real-world data to identify limitations and needed areas for improvement in adapting cooperative truck platooning technology to commercial operations on public roads.

Analysis of crash severity in rear-end and angle collisions on an urban roundabout in heterogeneous non-lane-based traffic conditions

ABSTRACT This study examines crash risk factors and develops a severity model for rear-end and angle collisions in roundabouts and its vicinity in non-lane-based heterogeneous traffic. The rear-end severity is primarily influenced by posted speed limits, violation type, collision partner, single-vehicle collision, and vehicle age. Whereas type of violation, collision partner, and presence of road surface condition are the critical influencing factors for determining the severity outcomes of angle collision. The marginal effects of angle collision results indicated that the probability of fatal injury increased by 28% due to heavy-vehicle-vulnerable road user collisions. In the rear-end case, risk factors such as collision partners (heavy vehicles-vulnerable road users) increased by 18% and single-vehicle collisions increased by 25%, highly influencing the severity of fatal injury at roundabouts. Notably, rear-end collisions exhibit higher severity compared to angle collisions. This study provides valuable insights for developing strategies to mitigate roundabout collision severity.

Bridge Damage Identification Based on LSTM Network and Contact Point Response

In this study, a bridge damage identification method based on the Long Short-Term Memory (LSTM) network and the contact point response is proposed, which utilizes the time behavior of the contact point response. The contact point response serving as the input to the LSTM network is obtained by calculating the vehicle-bridge interaction motion equation. A new bridge damage indicator titled the Euclidean Distance Damage Index (EDDI) is developed based on the difference between the actual and predicted values of the contact point response. Under ideal road surface conditions, the EDDI calculated in the healthy state of the bridge remains below 0.16, while exceeding 1.0 in the damaged state. When road roughness is considered, the EDDI is calculated to be less than 0.12 in the healthy state of the bridge and higher than 0.65 in the damaged state. The results show that the EDDI is more effective in distinguishing between the damaged and the healthy states of the bridge. Meanwhile, road roughness has a negative effect on the damage sensitivity of EDDI.

Augmenting roadway safety with machine learning and deep learning: Pothole detection and dimension estimation using in-vehicle technologies

Detection and estimation of pothole dimensions is an essential step in road maintenance. Aging, heavy rainfall, traffic, and weak underlying layers may cause pavement potholes. Potholes can cause accidents when drivers lose control after hitting or swerving to avoid them, which may lead to injuries or fatal crashes. Also, potholes may result in property damages, such as flat tires, scrapes, dents, and leaks. Additionally, potholes are costly; for example, in the United States, potholes cost drivers about $3 Billion annually. Traditional ways of attending to potholes involve field surveys carried out by skilled personnel to determine their sizes for quantity and cost estimates. This process is expensive, prone to errors, subjectivity, unsafe, and time-consuming. Some authorities use sensor vehicles to carry out the surveys, a method that is accurate, safer, and faster than the traditional approach but much more expensive; therefore, not all authorities can afford them. To avoid these challenges, a modern, real-time, cost-effective approach is proposed to ensure the efficient and fast process of pothole maintenance. This paper presents a Deep Learning model trained using the You Only Look Once (YOLO) algorithm to capture potholes and estimate their dimensions and locations using only built-in vehicle technologies. The model attained 93.0 % precision, 91.6 % recall, 87.0 % F1-score, and 96.3 % mAP. A statistical analysis of the on-site test results indicates that the results are significant at a 5 % level, with a p-value of 0.037. This approach provides an economical and faster way of monitoring road surface conditions.

Vehicle Sideslip Angle estimation under critical road conditions via nonlinear Kalman filter-based state-dependent Interacting Multiple Model approach

The knowledge of Vehicle Sideslip Angle (VSA) can play an essential role in active safety vehicle control systems. However, due to the high costs of sensing instruments, this information is difficult to be directly measured onboard of series production vehicles, restricting de facto its application in practice. It follows that there is a need for online VSA estimation methods only based on available measurements from low-cost sensors. From this perspective, this work proposes a strategy based on Interacting Multiple Model (IMM) filters, which does not require tyre–road friction coefficient knowledge. By integrating the available onboard sensor data, the IMM estimates relevant information in different driving conditions leveraging a 2-Degrees Of Freedom (DOF) single-track vehicle model embedding a Dugoff tyre representation. Two alternative IMM algorithms based on the Extended (EKF) and Unscented Kalman filter (UKF) are developed. Moreover, while usually the transition probabilities among models in classical IMMs are fixed and set on prior information and/or dedicated analysis, here these conservative hypotheses are relaxed introducing a state-dependent Markov transition matrix based on a novel model switching algorithm. The effectiveness of the new proposed methods is evaluated on extensive non-trivial simulation scenarios through a Monte Carlo analysis exploiting an accurate 15-DOF vehicle model via a purposely designed high-fidelity co-simulation platform embedding the dSPACE software Automotive Simulation Model (ASM). Results provide a meaningful comparative performance analysis between the IMMEKF and IMMUKF solutions, as well as with respect to traditional IMM based on constant probabilities transition matrix, blue in both the EKF and UKF configuration. Finally, the developed IMM-based estimation strategy is tested in two realistic driving scenarios to assess the VSA estimation accuracy in case of abrupt changes in road surface conditions.

Selected aspects of the solididfication process in a moist granular bed

This work presents issues related to the solidification process taking place in moist granular porous media in which water undergoes a phase change as a result of low temperatures. The characteristics of porous materials are also presented, as well as the description and method of determining the basic parameters related to solidification in porous granular deposits. Moreover, as part of the theoretical analysis of the solidification process in a granular bed, a simplified theoretical model of a wet porous material was presented, enabling the development of appropriate theoretical formulas describing the solidification phenomenon. In order to verify the theoretical solutions to the problem, a description and construction of a research stand for conducting experimental research were presented. Using defined dimensionless quantities and formulas, presented in detail in the works of other researchers, charts were developed and illustrated in the work. The entire study is summarized with conclusions that concern the great practical importance of the presented issues, especially for the technical condition of road surfaces