Road Conditions Research Articles

A new visual sensing system for motion state estimation of lateral localization of intelligent vehicles

Accurate lateral localization is the basis of intelligent vehicle decision making and control and one of the core problems of autonomous driving. In the process of vehicle driving, the vehicle body vibration, road bumps, and slope change will affect the motion parameters of the camera, which influences the localization accuracy. Therefore, we investigate a vehicle visual localization method based on the motion state estimation of vehicle camera by Gaussian Bayes sphere. This method uses Gaussian spherical crown sampling and maximum likelihood search to estimate the motion state of the vehicle camera in real time. Then, the real-time homography matrix between the sampling ground plane and the pixel plane is calculated according to the results to convert the coordinate points of the lane lines to the sampling ground plane for lateral localization of vehicles. Last, the localization results are restored to the real scale by the lane line width. The road experimental results show that the average error of the proposed method for lateral localization of vehicles is 5.7 cm under different road conditions on campus roads, and that under different road conditions on urban roads is 5.9 cm. At the same time, the localization accuracy of the proposed method is tested on the slope and under different weather conditions, and good results are obtained.

Objective Evaluation of Automatic Ambulance Performance and Weight Determination Through Analytic Hierarchy Process and Gray Correlation Theory

This paper proposes a comprehensive framework for testing and evaluating automatic ambulances, crucial for ensuring their reliability and safety in real-world scenarios. The framework includes designing test scenarios with varying complexity, covering environmental factors like road conditions, weather, and obstacles. An evaluation index system is introduced, comprising driving security, ride comfort, intelligence, and efficiency. Methodologies for calculating indicator weights, using the CRITIC and AHP methods, are presented to ensure fair evaluation. Additionally, evaluation methods including qualitative and quantitative techniques, such as grey correlation theory, are discussed. The test results show that the assessment results of the traditional fuzzy comprehensive evaluation method and the grey correlation theory evaluation method are highly consistent. The change in vehicle speed has less of an effect on accuracy during the real-time assessment process when the time interval is set to 0.1s, and the evaluation time of 0.098s can satisfy the requirement that the planning time of autonomous driving vehicles be shorter than 200 ms.

A SURVEY OF VERTEBRATES’ ROADKILL WITHIN A 10 KM RADIUS FROM THE CENTRE OF KUALA PILAH TOWN, NEGERI SEMBILAN

Assessing animal roadkill provides valuable insights into the diversity and abundance of different species within a particular area. This study has the potential to uncover factors influencing the occurrence of animal roadkill. However, there is a scarcity of studies focusing on animal roadkill in small, secluded areas such as the Kuala Pilah district, Negeri Sembilan. Thus, this study evaluates the composition and distribution of vertebrate roadkill within a 10 km radius from the centre of Kuala Pilah Town, with a focus on temporal (time of discovery), spatial (types of roads and types of surrounding areas), and environmental factors (the presence of streetlights). The road segments located within a 10 km radius from Kuala Pilah Town have been examined in ten weeks and the found carcasses were identified by their taxonomic groups and photographed. Further, their discovery location has been observed and marked with coordinates. A chi square test was then performed to evaluate the occurrence of animal roadkill with all recorded data. This study revealed 48 animal carcasses, with a taxonomic composition of 27.08% birds (13 individuals), 50% mammals (24 individuals), 18.75% reptiles (9 individuals), and 4.17% amphibians (2 individuals). The roadkill patterns showed that squirrels and cats as the most prevalent species found, with higher carcass rates found in plantation/forest areas and on state roads. Roadkill occurrences increased between 7 a.m. and 1 p.m., while streetlights had no noticeable impact on the numbers. Overall, mammals turned out to be the most frequent vertebrate class involved in roadkill with time being the only significant factor influencing the numbers. With a better understanding of the factors influencing vertebrate roadkill, mitigation strategies such as fencing, roadside vegetation clearance, and vehicle speed restrictions might be devised to minimize the adverse impacts of road infrastructure on local animal populations.

"Urban Mobility and Safety: Traffic Risks for Migrant Food Delivery Workers in Romania. Case Study: Cluj-Napoca Municipality "

The rapid expansion of the gig economy, particularly within the food delivery sector, has transformed urban mobility and employment landscapes globally. This study examines traffic incidents involving food delivery riders from Pakistan, Sri Lanka, and Bangladesh operating in Romania from 2017 to 2023. The research employs a mixed-method approach, using traffic incident records from the Romanian Traffic Police Directorate and a comprehensive survey conducted among delivery riders in Cluj-Napoca. The findings reveal a significant increase in traffic incidents, with notable fluctuations correlating with changes in behaviour and operational dynamics influenced by the COVID-19 pandemic. Key factors contributing to incidents include rider misconduct, inappropriate speed for road conditions, and high-pressure working environments. The study highlights the unsafe working conditions and elevated occupational risks faced by these gig economy workers, exacerbated by job demands and limited resources. The results advise policy recommendations aimed at improving the safety and working conditions of food delivery riders, emphasizing the need for enhanced educational campaigns, stricter enforcement of traffic laws, and infrastructure improvements.

Analyzing Road Images for Pothole Detection through Machine Learning Algorithms: A Comprehensive Review

The road accident prediction system leverages deep learning techniques, specifically YOLO (You Only Look Once), for the detection of potholes in road footage. By employing YOLO, the system can efficiently identify and localize potholes within video frames, enabling rapid and accurate detection. Furthermore, the system incorporates a severity prediction module that utilizes the dimensions and characteristics of detected potholes to assess their severity levels. This predictive capability empowers authorities and road maintenance teams to prioritize repair efforts and allocate resources effectively, ultimately contributing to the reduction of road accidents and ensuring safer road conditions for motorists and pedestrians alike. Through the seamless integration of pothole detection and severity prediction functionalities, the road accident prediction system offers a proactive approach to road maintenance and safety management, enhancing overall road infrastructure resilience and public safety.

Assessment of traffic sign retroreflectivity for autonomous vehicles: a comparison between handheld retroreflectometer and LiDAR data

This study investigates the critical role of retroreflectivity in traffic signs, particularly in the context of autonomous vehicles (AVs), where accurate detection is paramount for road safety. Retroreflectivity, influencing visibility and legibility, is essential for ensuring safe road conditions. The study aims to assess traffic sign retroreflectivity using handheld retroreflectometers and LiDAR data, offering a comprehensive comparison of results with a specific focus on the RA1 and RA2 traffic sign classes. In a real-world setting, an AV equipped with LiDAR sensors, GPS units, and a stereo camera collects data on traffic signs, including point cloud attributes such as intensity and density. Simultaneously, a handheld retroreflectometer measures retroreflectivity coefficients from identified traffic signs. While retroreflectometers provide precision, they face limitations regarding time-consuming measurements and handling large or elevated signs. In contrast, LiDAR systems efficiently evaluate retroreflective features for numerous signs without such constraints. Despite both methods consistently yielding accurate retroreflectivity, the study reveals a limited correlation between LiDAR point cloud data and handheld retroreflectivity coefficients. The implications of these findings are significant, particularly in the selection and maintenance of retroreflective materials in traffic signs, with direct repercussions on overall road safety. The results offer valuable insights into leveraging LiDAR technology to enhance AVs' detection capabilities. Recommendations for further research include exploring factors influencing LiDAR intensity, establishing a more accurate relationship between intensity and retroreflectivity, correcting the point cloud during intensity calibration, and testing empirical prediction models with a larger sample size. These endeavors aim to generate a robust regression graph and determine correlation coefficients, providing a more nuanced understanding of the intricate relationship between LiDAR data and handheld retroreflectivity coefficients in the context of traffic sign assessment.

Theoretical Considerations from the Modelling of the Interaction between Road Design and Fuel Consumption on Urban and Suburban Roadways

A roadway path is most commonly perceived as a 3-D element structure placed within its surrounding environment either within or outside urban areas. Design guidelines are usually strictly followed to ensure safe and comfort transportation of people and goods, but in full alignment with the terrain configuration and the available space, especially in urban and suburban areas. In the meantime, vehicles travelling along a roadway consume fuel and emit pollutants in a way that depends on both the driving attitude as well as the peculiar characteristics of road design and/or pavement surface condition. This study focuses on the environmental behavior of roadways in terms of fuel consumption, especially of heavy vehicles that mainly serve the purpose of freight transportation within urban areas. The impact of horizontal and vertical profiles of a roadway structure is theoretically considered through the parameters of speed and longitudinal slope, respectively. Based on theoretical calculations with an already developed model, it was found that the slope plays the most critical role, controlling the rate of fuel consumption increase, as an increase ratio of 2.5 was observed for a slope increase from 2% to 7%. The variation was less intense for a speed ranging from 25 to 45 km/h. The investigation additionally revealed useful discussion points for the need to consider the environmental impact of roadways during the operation phase for a more sustainable management of freight transportation procedures, thereby stimulating an ad hoc development of fuel consumption models based on actual measurements so that local conditions can be properly accounted for and used by road engineers and/or urban planners.

Multi-Agent System Based Cooperative Control for Speed Convergence of Virtually Coupled Train Formation.

This paper investigates the problem of spacing control between adjacent trains in train formation and proposes a distributed train-formation speed-convergence cooperative-control algorithm based on barrier Lyapunov function. Considering practical limitations such as communication distance and bandwidth constraints during operation, not all trains can directly communicate with the leader and obtain the expected trajectory it sends, making it difficult to maintain formation consistency as per the predetermined ideal state. Furthermore, to address the challenge of unknown external disturbances encountered by trains during operation, this paper designs a distributed observer deployed on each train in the formation. This observer can estimate and dynamically compensate for unknown reference trajectories and disturbances solely based on the states of adjacent trains. Additionally, to ensure that the spacing between adjacent trains remains within a predefined range, a safety hard constraint, this paper encodes the spacing hard constraint using barrier Lyapunov function. By integrating nonlinear adaptive control theory to handle model parameter uncertainties, a barrier Lyapunov function-based adaptive control method is proposed, which enables all trains to track the reference trajectory while ensuring that the spacing between them remains within the preset interval, therefore guaranteeing the asymptotic stability of the closed-loop system. Finally, a practical example using data from the Guangzhou Metro Line 22, specifically the route from Shiguang Road Station to Chentougang Station over three stations and two sections, is utilized to validate the effectiveness and robustness of the proposed algorithm.

O2SAT: Object-Oriented-Segmentation-Guided Spatial-Attention Network for 3D Object Detection in Autonomous Vehicles

Autonomous vehicles (AVs) strive to adapt to the specific characteristics of sustainable urban environments. Accurate 3D object detection with LiDAR is paramount for autonomous driving. However, existing research predominantly relies on the 3D object-based assumption, which overlooks the complexity of real-world road environments. Consequently, current methods experience performance degradation when targeting only local features and overlooking the intersection of objects and road features, especially in uneven road conditions. This study proposes a 3D Object-Oriented-Segmentation Spatial-Attention (O2SAT) approach to distinguish object points from road points and enhance the keypoint feature learning by a channel-wise spatial attention mechanism. O2SAT consists of three modules: Object-Oriented Segmentation (OOS), Spatial-Attention Feature Reweighting (SFR), and Road-Aware 3D Detection Head (R3D). OOS distinguishes object and road points and performs object-aware downsampling to augment data by learning to identify the hidden connection between landscape and object; SFR performs weight augmentation to learn crucial neighboring relationships and dynamically adjust feature weights through spatial attention mechanisms, which enhances the long-range interactions and contextual feature discrimination for noise suppression, improving overall detection performance; and R3D utilizes refined object segmentation and optimized feature representations. Our system forecasts prediction confidence into existing point-backbones. Our method’s effectiveness and robustness across diverse datasets (KITTI) has been demonstrated through vast experiments. The proposed modules seamlessly integrate into existing point-based frameworks, following a plug-and-play approach.

ANALYSIS OF THE SHORTEST ROUTE FROM CIKAMPEK TO PURWOKERTO USING ANT COLONY ALGORITHM

Finding the shortest path sometimes makes most people confused in choosing a path, especially if there are many paths that must be taken to reach one destination. Tracing various routes from Cikampek to Purwokerto is a challenge, with the risk of spending excessive time and money. To solve this problem, this research uses the Ant Colony Algorithm to determine the most efficient path. One of the problems that often arises is that the Cikampek area has 3 routes that can be used to reach Purwokerto, namely the Cikampek - Indramayu (Patrol), Cikampek - Subang, and Cikampek - Bandung routes. The purpose of determining the shortest path is to provide the shortest path solution to users so that they can reach their destination faster and save time and costs. In this study, we use Ant Algorithm because the route from Cikampek to Purwokerto depends on many road factors and other conditions that could change from time to time. For example, traffic congestion and road repairs are major factors. The ant algorithm has strong customization capabilities to determine the shortest path based on the pheromone trails left by ants during exploration. This means that the ant algorithm can work optimally even if there are many factors in road conditions. In addition, the ant algorithm has the ability to handle problems with a large number of nodes, so it can explore various possibilities efficiently. The ant algorithm is an appropriate choice for finding the shortest path in a journey involving complex and diverse routes. There are six steps required to complete the ant algorithm. The first step is initialization, the second step is path selection, and the third step is setting the ant trail and communication between the ants hit by the trail in path selection. The fourth step is to look for visibility, the fifth step is to stop the criterion until it reaches a certain condition, and the last step is to determine the path by calculating probabilities. The results of this study indicate that the ant algorithm can be used to determine the shortest path which is then displayed. This research aims to assist the community in making decisions and determining the location of the city that must be passed. This study took 8 location points with starting point A and destination point H. Based on the results of the discussion it can be concluded that the shortest route from Cikampek to Purwokerto is with 3 routes, namely first (A à D à E à F à H) with a distance of 355 KM, second (A à D à G à F à H) with a distance of 431 KM and the third (A à D à E àH) with a distance of 317 KM.

An ANALYSIS OF CONTRACTOR PERFORMANCE FOR ROAD REHABILITATION WORK USING SPECIAL ALLOCATION FUND OF 2022 IN MALANG REGENCY

Road is one of basic infrastructure playing crucial role in development process. Good condition of road creates properes transportation system. It, in turns ensures smooth movement of men and goods. Good transportation will make price of public goods cheap. So far, road rehabilitation works in Malang regency are conducted by usin Special Allocation Fund raising severeal problems such as late down payment, material queue and other. This study aims at analysisng performance of contractor of road rehabiitation using Special Allocation Fund of 2022 in Malang Regency. Customer Satisfaction Index analysis is used to analyse the contractors performance. In addition, Importance Performance Analysis is employed to find out performance variabel that should be improved or maintained. Then, simple linear regression analysis is used to find out the correlation between stakeholders’ level of satisfaction and performance importance on the part of contractors of road rehabilitation works using Special Allocation Fund of 2022 in Malang Regency. The findings shows that stakehoders are higly satisfied with performance of contractors of road rehabilitation works using Special Allocation Fund of 2022 in Malang Regency. It is shown by score of CSI 86,99%. It is also found that there is positive and significant correlation between stakeholders’ level of satisfaction and performance importance on the part of contractors of road rehabilitation works using Special Allocation Fund of 2022 in Malang Regency. However, there are some performance variables that should be improved by the contractors.

Pekerja Ekonomi Gig: Pengalaman Kerja Pengemudi Ojek Online Maxim dan Grab di Wilayah Timur Indonesia

This study aims to examine the work experience of online Ojek drivers in Kupang City who use the Maxim and Grab platforms. This research is motivated by the rapid development of online ojek services in Indonesia, including in Kupang City, as well as its important role in providing new economic opportunities. This research uses a qualitative approach with phenomenological methods to explore the subjective experiences of the drivers. In-depth interview techniques and participatory observation were used to collect data from 22 informants consisting of Maxim and Grab drivers. The results showed significant differences between the drivers' work experiences on the two platforms. Grab drivers prefer the strict Standard Operating Procedures (SOPs) that provide a sense of security, while Maxim drivers appreciate the flexibility of working hours offered. The main challenges faced by drivers include digital map inaccuracies, sudden order cancellations, accident risks, and poor road conditions. The rating system plays an important role in determining a driver's income, with high ratings increasing the number of orders. This research makes an important contribution to the literature by providing an in-depth comparative analysis of the work experience of online ojek drivers in a medium-sized city like Kupang. The findings also offer practical recommendations for online Ojek companies to improve driver welfare and provide useful data for policymakers in formulating regulations that support the welfare of online Ojek drivers.

RDD2022: A multi‐national image dataset for automatic road damage detection

AbstractThe data article describes the Road Damage Dataset, RDD2022, encompassing of 47,420 road images from majorly six countries, Japan, India, the Czech Republic, Norway, the United States, and China. The dataset incorporates over 55,000 instances of road damage, specifically longitudinal cracks, transverse cracks, alligator cracks, and potholes. Designed to facilitate the development of deep learning methodologies for automated road damage detection and classification, RDD2022 was unveiled as part of the Crowd sensing‐based Road Damage Detection Challenge (CRDDC'2022), with a major contribution from the challenge winners. This challenge garnered global participation, urging researchers to propose solutions for automatic road damage detection in multiple countries. A noteworthy outcome of CRDDC'2022 was the emergence of a top‐performing model achieving a remarkable F1 Score of 76.9% for road damage detection in all six countries using RDD2022. This success underscores the dataset's practical applicability for municipalities and road agencies, enabling low‐cost, automatic monitoring of road conditions. Beyond its immediate utility, RDD2022 stands as a valuable benchmark for researchers in computer vision, geoscience, and machine learning, offering a rich resource for algorithmic evaluation in diverse image‐based applications, including classification and object detection. The latest big data cup, Optimized Road Damage Detection Challenge (ORDDC'2024), is also based on RDD2022, underscoring its continued relevance and pivotal role in current research and development endeavors.

Evaluasi Kelayakan Geometrik Tikungan Pada Ruas Jalan Jenderal Ahmad Yani Km. 2 Kota Parepare

Jendral Ahmad Yani Km. 2 road is one of the land transportation accesses that connects between regions in improving the economy and standard of living of the community. This study aims to analyze the geometrics of road bends. The research method used is descriptive quantitative method of analysis using the standards of the Directorate of Highways. The results of the research from the geometric bend results that the road section includes a primary collector function class SCS type bend with provincial road status with type 2/2 UD. The existing geometric conditions of the road section are in accordance with the required standards where there is a vertical alignment of 8.1% and a stopping sight distance of 133.36m. Coordination of alignments that coincide does not obstruct visibility.

Urban Road Surface Condition Sensing from Crowd-Sourced Trajectories Based on the Detecting and Clustering Framework.

Roads play a crucial role in urban transportation by facilitating the movement of materials within a city. The condition of road surfaces, such as damage and road facilities, directly affects traffic flow and influences decisions related to urban transportation maintenance and planning. To gather this information, we propose the Detecting and Clustering Framework for sensing road surface conditions based on crowd-sourced trajectories, utilizing various sensors (GPS, orientation sensors, and accelerometers) found in smartphones. Initially, smartphones are placed randomly during users' travels on the road to record the road surface conditions. Then, spatial transformations are applied to the accelerometer data based on attitude readings, and heading angles are computed to store movement information. Next, the feature encoding process operates on spatially adjusted accelerations using the wavelet scattering transformation. The resulting encoding results are then input into the designed LSTM neural network to extract bump features of the road surface (BFRSs). Finally, the BFRSs are represented and integrated using the proposed two-stage clustering method, considering distances and directions. Additionally, this procedure is also applied to crowd-sourced trajectories, and the road surface condition is computed and visualized on a map. Moreover, this method can provide valuable insights for urban road maintenance and planning, with significant practical applications.

Analisis Kelayakan Penerapan Inklusivitas Kota Ramah Pejalan Kaki di Surabaya: Studi Komparatif dengan Kota Bandung dalam Teori Kepublikan

This research discusses the concept of a pedestrian-friendly city or Walkable City in Surabaya, relating it to Bandung. Based on the Most Liveable City Index (MLCI), Bandung ranks at the Average Tier City level, indicating it has the best city implementation in Indonesia. Similarities in city layout, road conditions, and the economic characteristics of the population suggest that Surabaya and Bandung have similar city identities. This research employs qualitative methods with content analysis techniques to analyze data and interpret the meaning behind data and information from social media users. The findings reveal that Jalan Braga retains a historical impression and features pedestrian-friendly sidewalks, including inclusive public spaces and street designs. However, the lighting on Jalan Braga is dim, causing visitors to feel anxious at night. In Surabaya, especially on Jalan Tunjungan, the walkable city conditions are similar to Jalan Braga. However, the crossing lights are ineffective, and the lack of canopies along the sidewalks discourages walking during the day due to the extreme heat, which is a drawback for implementing a walkable city on Jalan Tunjungan.This research suggests that to improve safety, resilience, and sustainability in inclusive road and urban traffic design comprehensively, the integration framework needs to be expanded beyond conventional views—limited to technology or products, business or economics, and infrastructure or platforms—to encompass space, speed, and priority. Each of these factors directly influences accessibility, security, and social usability and has a reciprocal and interdependent relationship with the others.

Efficient Method of Road Outlier Recognition Using Deep Learning Coupled with Data Augmentation Approach

In recent years, Closed-circuit Television (CCTV) cameras have been playing a vital role in the surveillance of both public and private areas. The primary objective of surveillance is to monitor human behavior and road conditions. In the real-world situation, detecting, and recognizing abnormal activities poses significant challenges due to the densely crowded environment and the complex nature of transportation systems. These factors make it difficult to automatically identify various anomalies that occur while traveling, leading to emergencies, and endangering human life and property. In response to these challenges, contemporary Road Outlier Recognition Surveillance Systems (RORSS) have been deployed to monitor and mitigate abnormalities on streets, highways, and roads. This research specifically investigated conventional as well as human-centered road anomalies encompassing snatching, accidents, fighting, and car fires. The proposed Real-time Road Outlier Recognition methodology is formulated as a classification task, involving the analysis and processing of real-time CCTV videos. The proposed study investigated different types of Convolutional Neural Network (CNN) pre-trained models with the Data Augmentation (DA) approach to address the frame variance problem in real-time videos. Furthermore, we introduced a benchmark real-world Road Outlier Dataset (ROD) containing roads, streets, and highways videos and images that presented different road anomalies performed by vehicles and humans. Experimentation using different pre-trained CNN models i.e., VGG19, InceptionV3, ResNet50, and DenseNet201 with a data augmentation approach has been performed on the ROD dataset. The experimental results demonstrated that the InceptionV3 model performed best with the augmentation approach as compared to other deep learning models that achieved the best accuracy of 98.80% in recognizing road anomalies

Road Traffic Accident and its Characteristics in Kathmandu Valley

Road Traffic Accident (RTA) is defined as an accident, which takes place on the road between two or more objects, in which one is any kind of moving vehicle and the other is another vehicle, pedestrian, animal, or stationary object. The major scope of this study is to analyze factors influencing road accident in Kathmandu Valley (i.e. Kathmandu, Bhaktapur and Lalitpur district), Nepal. Data used in this research were collected from Kathmandu Valley Traffic Police for FY 2070/71 to 2079/80 of the Nepalese Calendar. Both quantitative and qualitative analysis of data was performed. There were several variables used to analyze the collected data including age of driver, gender of driver, fatality rate, time of accident, reason of accident, type of vehicle involved in an accident. The result of analysis shows that 76752 accidents took place in FY 2070/71 to 2079/80. Vehicles most involved in accidents were motorcycle/scooters (54675) followed by car/jeep/van (46928) (both combining, contributing total of almost 75%). The number of male deaths was three times more than that of female death, (i.e. male death victims were 1360 and female were 409). Based on the age, 55% of total death victims were of age group 16-35 i.e. 969 deaths were of this age group. Largest number of accidents (31473) took place during 12:00-18:00 and the major cause of accidents was reckless driving. Other cause of road accident includes over speeding, alcohol consumption, pedestrian’s carelessness, road condition, physical and mental condition of driver. The objective of this research is to identify the trend of accident, investigate the possible causes of accidents, and suggest countermeasures for reducing road traffic accident.

Analysis of Fire Station Location and Road Condition on Service Response Time: A Study of Ogun West Senatorial District of Ogun State, Nigeria

Analysis of Fire Station Location and Road Condition on Service Response Time: A Study of Ogun West Senatorial District of Ogun State, Nigeria

A novel adaptive trajectory tracking control for complex environments based on accelerated back-propagation neural network

This work addresses the issue of trajectory tracking accuracy degradation for vehicle dynamics parameters and road conditions changing, an adaptive trajectory tracking controller is designed for the intelligent vehicle. Based on the yaw dynamics model, a model predictive controller (MPC) is developed for the trajectory tracking process. Meanwhile, the impacts of different control parameters on trajectory tracking at various speeds are compared. And the change rule between optimal control parameter values and reference speeds is determined by cubic polynomial fitting to ensure minimal error during the trajectory following process. Then, an estimator for vehicle tire cornering stiffness and road adhesion coefficient is designed and tested based on the accelerated back-propagation neural network (ABPNN) model, with its estimation values being compared to those obtained through recursive least square method. Last, a co-simulation platform combining MATLAB/Simulink and CarSim software is established to conduct the trajectory tracking experiment under variable working conditions. Experimental results show that the proposed adaptive controller not only exhibits high accuracy in trajectory tracking but also demonstrates excellent stability and adaptability under medium to low speed conditions, particularly when encountering changing road conditions.