Browse Topic: Intelligent transportation systems

Items (448)
Heavy-duty commercial vehicles (HDCVs) are the key mobile nodes in intelligent transportation systems (ITS). However, their complex operating conditions and the diversity of data sources (such as road conditions, driver behavior, traffic signals, and on-board sensors) present considerable difficulties for accurately estimating the state and perceiving the environment using a single modality of data. This requires effective multi-modal data fusion to enhance the control and decision-making capabilities of HDCVs. This paper addresses this need by proposing a customized multi-modal intelligent transportation data fusion framework for intelligent HDCVs. This paper presents a solution for establishing a multi-modal intelligent transportation data collection platform, including real-scene collection methods and simulation scene collection methods based on the SUMO-MATLAB joint simulation platform. Through three representative case studies, the application methods of multi-modal traffic data
Chen, ZhengxianWang, ShaoqiJiang, HuimingZhou, FojinWang, MingqiangLi, Jun
In the context of intelligent transportation systems and applications such as autonomous driving, it is essential to predict a vehicle’s immediate future states to enable precise and timely prediction of vehicles’ movements. This article proposes a hybrid short-term kinematic vehicle prediction framework that integrates a novel object detection model, You Only Look Once version 11 (YOLOv11), with an unscented Kalman filter (UKF), a reliable state estimation technique. This study provides a unique method for real-time detection of vehicles in traffic scenes, tracking and predicting their short-term kinematics. Locating the vehicle accurately and classifying it in a range of dynamic scenarios is achievable by the enhanced detection capabilities of YOLOv11. These detections are used as inputs by the UKF to estimate and predict the future positions of the vehicles while considering measurement noise and dynamic model errors. The focus of this work is on individual vehicle motion prediction
Pahal, SudeshNandal, Priyanka
Use Decision Making Trial and Evaluation Laborator (DEMATEL) and Analytic Hierarchy Process (AHP) to jointly analysis and determine the key factors of Guangzhou intelligent logistics. Through the questionnaire survey of 92 logistics enterprises in Guangzhou, it is concluded that Information infrastructure, big data, Internet of Things, artificial intelligence, Logistics dynamic updates, and Smart warehousing have a great impact on intelligent logistics. Combining practical engineering with theory to make the implementation of Guangzhou’s smart logistics project more scientific, It is characterized by a higher degree of scientificity. Moreover, it is of great warning value, which can alert relevant parties to potential issues. Meanwhile, it provides essential guidance for the implementation of the smart city project in Guangzhou, facilitating a more efficient and well - directed execution process. This study is limited to logistics business respondents in Guangzhou and may limit the
Zhang, ShuangshuangChen, NingKhaw, Khai WahLiu, ChenxiJin, Lili
Based on the similarity analysis of Intelligent Connected Vehicles (ICVs), a distributed V2X hardware-in-the-loop test system for ICVs is designed, including the PanoSim autonomous driving simulation engine, GNSS simulator, V2X simulator, and management and cooperative control software. The system integrates the major technologies of distributed interaction, including operation management, time synchronization, coordinate conversion, and data preprocessing, and realizes the spatial and temporal consistency of each simulation node. 89 V2X first-stage application scenarios (e.g., FCW, RLVW) and 5 V2X second-stage application scenarios (e.g., CLC) use case experimental results have proved the reliability of the system. The FCW use case experiment results show that its simulation results pass with high confidence. The study emphasizes the value of the system in reducing development costs, improving safety, and accelerating the deployment of V2X applications, while identifying future
Gao, TianfangZhang, XingHuiChen, LiangHuang, ZhichenNi, Dong
The adhesion condition of the road surface is an important factor in the driving decision-making, and the lower the adhesion coefficient of the road, the greater the risk of safety. In order to study the development and progress in the research of the substances, a comparative analysis of Chinese and foreign references was carried out. The sensitive factors to the adhesion coefficient and influence of adhesion condition on driving were summarized. Then two main strategies to avoid a collision were presented, including longitudinal braking and lateral lane change. A detailed description of three methods used in automotive decision-making processes was offered, including rule-based method, supervised learning method, and reinforcement learning method, each characterized with certain attributes. Topics in the field of driving decision-making considering adhesion condition for intelligent connected vehicles were pointed out and future-oriented research formulations were provided. These
Wang, HongHou, De-Zao
This thesis explores strategies for controlling traffic signals at intersections within the context of ITS., emphasizing the role of DRL in optimizing traffic flow. In recent years, urbanization and the rapid increase in vehicle numbers in China have exacerbated traffic congestion, significantly hindering urban development. This study explores innovative approaches to alleviating traffic congestion, focusing on smart traffic signal systems that adjust according to real-time traffic conditions. The research reviews fundamental concepts in traffic signal control, including traffic flow, signal phases, and signal cycles, and investigates how DRL can dynamically adjust traffic light cycles to optimize intersection performance. The findings suggest that DRL provides an effective method for managing complex and unpredictable traffic environments, as it enables systems to self-learn and continuously refine their strategies based on environmental changes. The adoption of this technology holds
Liu, JunaoZuo, Tingyou
This article presents a path planning and control method for a cost-effective autonomous sweeping vehicle operating in enclosed campus. First, to address the challenges from perception, an effective obstacle filtering algorithm is proposed, considering the elimination of false detection and correction of object position. Based on it, the adaptive sampling–based path planner and pure pursuit controller are developed. Not only an adaptive cost-weighting mechanism is introduced by TOPSIS algorithm to determine the desired trajectory as a multi-objective optimization problem, but also the adaptive preview distance is designed according to the trajectory curvature and vehicle state. The real-vehicle tests are implemented in typical scenario. The results show that the 87.8% effective edge-following rate is achieved in curved paths, and 22.93% cleaning coverage is improved for cleaning coverage. Therefore, the proposed method is effective and reliable for cost-effective autonomous sweeping
Lei, WuKunYang, BoPei, XiaofeiZhang, YangZhou, HongLong
Perception is a key component of automated vehicles (AVs). However, sensors mounted to the AVs often encounter blind spots due to obstructions from other vehicles, infrastructure, or objects in the surrounding area. While recent advancements in planning and control algorithms help AVs react to sudden object appearances from blind spots at low speeds and less complex scenarios, challenges remain at high speeds and complex intersections. Vehicle-to-infrastructure (V2I) technology promises to enhance scene representation for connected and automated vehicles (CAVs) in complex intersections, providing sufficient time and distance to react to adversary vehicles violating traffic rules. Most existing methods for infrastructure-based vehicle detection and tracking rely on LIDAR, RADAR, or sensor fusion methods, such as LIDAR–camera and RADAR–camera. Although LIDAR and RADAR provide accurate spatial information, the sparsity of point cloud data limits their ability to capture detailed object
Saravanan, Nithish KumarJammula, Varun ChandraYang, YezhouWishart, JeffreyZhao, Junfeng
Autonomous vehicle motion planning and control are vital components of next-generation intelligent transportation systems. Recent advances in both data- and physical model-driven methods have improved driving performance, yet current technologies still fall short of achieving human-level driving in complex, dynamic traffic scenarios. Key challenges include developing safe, efficient, and human-like motion planning strategies that can adapt to unpredictable environments. Data-driven approaches leverage deep neural networks to learn from extensive datasets, offering promising avenues for intelligent decision-making. However, these methods face issues such as covariate shift in imitation learning and difficulties in designing robust reward functions. In contrast, conventional physical model-driven techniques use rigorous mathematical formulations to generate optimal trajectories and handle dynamic constraints. Hybrid Data- and Physical Model-Driven Safe and Intelligent Motion Planning and
Zheng, Ling
We present DISRUPT, a research project to develop a cooperative traffic perception and prediction system based on networked infrastructure and vehicle sensors. Decentralized tracking and prediction algorithms are used to estimate the dynamic state of road users and predict their state in the near future. Compared to centralized approaches, which currently dominate traffic perception, decentralized algorithms offer advantages such as greater flexibility, robustness and scalability. Mobile sensor boxes are used as infrastructure sensors and the locally calculated state estimates are communicated in such a way that they can augment local estimates from other sensor boxes and/or vehicles. In addition, the information is transferred to a cloud that collects the local estimates and provides traffic visualization functionalities. The prediction module then calculates the future dynamic state based on neurocognitive behavior models and a measure of a road user's risk of being involved in
Beutenmüller, FrankBrostek, LukasDoberstein, ChristianHan, LongfeiKefferpütz, KlausObstbaum, MartinPawlowski, AntoniaRössert, ChristianSas-Brunschier, LucasSchön, ThiloSichermann, Jörg
With the increasing distribution of smart mobility systems, automated & connected vehicles are more and more interacting with each other and with smart infrastructure using V2X-communication. Hereby, the vehicles’ position, driving dynamics data, or driving intention are exchanged. Previous research has explored graph-based cooperation strategies for automated vehicles in mixed traffic environments based on current V2X-communication standards. Thereby, the focus is set on cooperation optimization and maneuver negotiation. These strategies can be implemented through both centralized and decentralized computational approaches and are conflict-free by design. To enhance these previously established cooperation models, real-world traffic data is used to derive vehicle trajectories, providing a more accurate representation of actual traffic scenarios in order to enhance the practical application of the described methodology. Additionally, machine learning algorithms are employed to train
Flormann, MaximilianMeyer, FelixHenze, Roman
The road network is a critical component of modern urban mobility systems, with signalized traffic intersections playing a pivotal role. Traditionally, traffic light phase timings and durations at intersections are designed by transportation engineers using historical traffic data. Some modern intersections employ trigger-based mechanisms to improve traffic flow; however, these systems often lack global awareness of traffic conditions across multiple intersections within a network. With the increasing availability of traffic data and advancements in machine learning, traffic light systems can be enhanced by modeling them as agents operating in an environment. This paper proposes a Reinforcement Learning (RL) based approach for multi-agent traffic light systems within a simulation environment. The simulation is calibrated using real-world traffic data, enabling RL agents to learn effective control strategies based on realistic scenarios. A key advantage of using a calibrated simulation
Kalra, VikhyatTulpule, PunitGiuliani, Pio Michele
The escalating complexity at intersections challenges the safety of the interaction between vehicles and pedestrians, especially for those with mobility impairments. Traditional traffic control systems detect pedestrians through costly technologies such as LiDAR and radar, limiting their adoption due to high costs and static programming. Therefore, the article proposes a customized signalized intersection control (CSIC) algorithm for pedestrian safety enhancement. This algorithm integrates advanced computer vision (CV) algorithms to detect, track, and predict pedestrian movements in real time, enhancing safety at a signalized intersection while remaining economically viable and easily integrated into existing infrastructure. Implemented at a key intersection in Bellevue, the CSIC system achieves a 100% pedestrian passing rate while simultaneously minimizing the average remaining walk time after crossings. The algorithm used in this study demonstrates the potential of combining CV with
Xia, RongjingFang, HongchaoZhang, Chenyang
This article introduces a comprehensive cooperative navigation algorithm to improve vehicular system safety and efficiency. The algorithm employs surrogate optimization to prevent collisions with cooperative cruise control and lane-keeping functionalities. These strategies address real-world traffic challenges. The dynamic model supports precise prediction and optimization within the MPC framework, enabling effective real-time decision-making for collision avoidance. The critical component of the algorithm incorporates multiple parameters such as relative vehicle positions, velocities, and safety margins to ensure optimal and safe navigation. In the cybersecurity evaluation, the four scenarios explore the system’s response to different types of cyberattacks, including data manipulation, signal interference, and spoofing. These scenarios test the algorithm’s ability to detect and mitigate the effects of malicious disruptions. Evaluate how well the system can maintain stability and avoid
Khan, Rahan RasheedHanif, AtharAhmed, Qadeer
The transportation industry is transforming with the integration of advanced data technologies, edge devices, and artificial intelligence (AI). Intelligent transportation systems (ITS) are pivotal in optimizing traffic flow and safety. Central to this are transportation management centers, which manage transportation systems, traffic flow, and incident responses. Leveraging Advanced Data Technologies for Smart Traffic Management explores emerging trends in transportation data, focusing on data collection, aggregation, and sharing. Effective data management, AI application, and secure data sharing are crucial for optimizing operations. Integrating edge devices with existing systems presents challenges impacting security, cost, and efficiency. Ultimately, AI in transportation offers significant opportunities to predict and manage traffic conditions. AI-driven tools analyze historical data and current conditions to forecast future events. The importance of multidisciplinary approaches and
Ercisli, Safak
Conflicts between vehicles and pedestrians at unsignalized intersections occur frequently and often result in serious consequences. In order to alleviate traffic flow congestion at unsignalized intersections caused by accidents, reduce vehicle congestion time and waiting time, and improve intersection safety as well as intersection access efficiency, a speed guidance algorithm based on pedestrian-to-vehicle (P2V) and vehicle-to-pedestrian (V2P) communication technologies is proposed. The method considers the heading angle (direction of motion) of vehicles and pedestrians and combines the post encroachment time (PET) and time to collision (TTC) to determine whether there is a risk of collision, so as to guide the speed of vehicles. Network simulator NS3 and traffic flow simulation software SUMO are used to verify the effectiveness of the speed guidance strategy proposed in this article. The experimental findings demonstrate that the speed guidance strategy introduced in this article
Sun, YuanyuanWang, KanLiu, WeizhenLi, Wenli
Letter from the Guest Editors
Liang, CiTörngren, Martin
The existing variable speed limit (VSL) control strategies rely on variable message signs, leading to slow response times and sensitivity to driver compliance. These methods struggle to adapt to environments where both connected automated vehicles (CAVs) and manual vehicles coexist. This article proposes a VSL control strategy using the deep deterministic policy gradient (DDPG) algorithm to optimize travel time, reduce collision risks, and minimize energy consumption. The algorithm leverages real-time traffic data and prior speed limits to generate new control actions. A reward function is designed within a DDPG-based actor-critic framework to determine optimal speed limits. The proposed strategy was tested in two scenarios and compared against no-control, rule-based control, and DDQN-based control methods. The simulation results indicate that the proposed control strategy outperforms existing approaches in terms of improving TTS (total time spent), enhancing the throughput efficiency
Ding, XibinZhang, ZhaoleiLiu, ZhizhenTang, Feng
New mobility concepts with smart infrastructure have led to enhanced customer driving experience. The potential to develop safe cars with minimal driver intervention is a great need of the future. The cusp for fully autonomous driving has produced much technical talk, which has led to faster transition and adoption. One of the features that global OEMs have tried to focus on, is Human Machine Interface (HMI) solutions, popularly called display screens. The touchscreen HMIs are common in all mid-range budget cars. They offer driver support beyond just streaming music, including inputs for navigation, parking assistance, in-car technologies, Advanced Driver Assistance Systems (ADAS), and infotainment. Poor display screen visibility is a phenomenon observed when a vehicle is driven over different road surfaces. This paper presents a user-centric approach for the right design & development of the HMI for a vibration free driving experience. The mounting strategies for the display screens
Adil, MD ShahzadC M, MithunMohammed, RiyazuddinR, Prasath
This article reviews the key physical parameters that need to be estimated and identified during vehicle operation, focusing on two key areas: vehicle state estimation and road condition identification. In the vehicle state estimation section, parameters such as longitudinal vehicle speed, sideslip angle, and roll angle are discussed, which are critical for accurately monitoring road conditions and implementing advanced vehicle control systems. On the other hand, the road condition identification section focuses on methods for estimating the tire–road friction coefficient (TRFC), road roughness, and road gradient. The article first reviews a variety of methods for estimating TRFC, ranging from direct sensor measurements to complex models based on vehicle dynamics. Regarding road roughness estimation, the article analyzes traditional methods and emerging data-driven approaches, focusing on their impact on vehicle performance and passenger comfort. In the section on road gradient
Chen, ZixuanDuan, YupengWu, JinglaiZhang, Yunqing
Coyner, KelleyBittner, Jason
Dedicated lanes provide a simpler operating environment for ADS-equipped vehicles than those shared with other roadway users including human drivers, pedestrians, and bicycles. This final report in the Automation and Infrastructure series discusses how and when various types of lanes whether general purpose, managed, or specialty lanes might be temporarily or permanently reserved for ADS-equipped vehicles. Though simulations and economic analysis suggest that widespread use of dedicated lanes will not be warranted until market penetration is much higher, some US states and cities are developing such dedicated lanes now for limited use cases and other countries are planning more extensive deployment of dedicated lanes. Automated Vehicles and Infrastructure: Dedicated Lanes includes a review of practices across the US as well as case studies from the EU and UK, the Near East, Japan, Singapore, and Canada. Click here to access the full SAE EDGETM Research Report portfolio.
Coyner, KelleyBittner, Jason
Traffic flow prediction is very important in traffic-related fields, and increasing prediction accuracy is the primary goal of traffic prediction research. This study proposes a new traffic flow prediction method, which uses the CNN–BiLSTM model to extract features from traffic data, further models these features through GBRT, and uses Optuna to tune important hyperparameters of the overall model. The main contribution of this study is to propose a new combination model with better performance. The model integrates two deep learning models that are widely used in this field and creatively uses GBRT to process the output features of the front-end model. On this basis, the optimal hyperparameters and the robustness of the model are deeply explored, providing an effective and feasible solution to the difficult problems in traffic flow prediction. This model is experimentally studied using three different data transformation methods (original data, wavelet transform, Fourier transform
Ma, ChangxiJin, Renzhe
With the development of intelligent transportation systems and the increasing demand for transportation, traffic congestion on highways has become more prominent. So accurate short-term traffic flow prediction on these highways is exceedingly crucial. However, because of the complexity, nonlinearity, and randomness of highway traffic flows, short-term prediction of its flows can be difficult to achieve the desired accuracy and robustness. This article presents a novel architectural model that harmoniously fuses bidirectional long–short-term memory (BiLSTM), bidirectional gated recurrent unit (BiGRU), and multi-head attention (MHA) components. Bayesian optimization (BO) is also used to determine the optimal set of hyperparameters. Based on the PeMS04 dataset from California, USA, we evaluated the performance of the proposed model across various prediction intervals and found that it performs best within a 5-min prediction interval. In addition, we have conducted comparison and ablation
Chen, PengWang, TaoMa, ChangxiChen, Jun
With the rapid development of intelligent connected vehicles, their open and interconnected communication characteristics necessitate the use of in-vehicle Ethernet with high bandwidth, real-time performance, and reliability. DDS is expected to become the middleware of choice for in-vehicle Ethernet communication. The Data Distribution Service (DDS), provided by the Object Management Group (OMG), is an efficient message middleware based on the publish/subscribe model. It offers high real-time performance, flexibility, reliability, and scalability, showing great potential in service-oriented in-vehicle Ethernet communication. The performance of DDS directly impacts the stable operation of vehicle systems, making accurate evaluation of DDS performance in automotive systems crucial for optimizing system design. This paper proposes a latency decomposition method based on DDS middleware, aiming to break down the overall end-to-end latency into specific delays at each processing stage
Yu, YanhuaLuo, FengRen, YiHou, Yongping
Intelligent transportation systems and connected and automated vehicles (CAVs) are advancing rapidly, though not yet fully widespread. Consequently, traditional human-driven vehicles (HDVs), CAVs, and human-driven connected and automated vehicles (HD-CAVs) will coexist on roads for the foreseeable future. Simultaneously, car-following behaviors in equilibrium and discretionary lane-changing behaviors make up the most common highway operations, which seriously affect traffic stability, efficiency and safety. Therefore, it’s necessary to analyze the impact of CAV technologies on both longitudinal and lateral performance of heterogeneous traffic flow. This paper extends longitudinal car-following models based on the intelligent driver model and lateral lane-changing models using the quintic polynomial curve to account for different vehicle types, considering human factors and cooperative adaptive cruise control. Then, this paper incorporates CAV penetration rates, shared autonomy rates
Wang, TianyiGuo, QiyuanHe, ChongLi, HaoXu, YimingWang, YangyangJiao, Junfeng
Connected and automated vehicle (CAV) technology is a rapidly growing area of research as more automakers strive towards safer and greener roads through its adoption. The addition of sensor suites and vehicle-to-everything (V2X) connectivity gives CAVs an edge on predicting lead vehicle and connected intersection states, allowing them to adjust trajectory and make more fuel-efficient decisions. Optimizing the energy consumption of longitudinal control strategies is a key area of research in the CAV field as a mechanism to reduce the overall energy consumption of vehicles on the road. One such CAV feature is autonomous intersection navigation (AIN) with eco-approach and departure through signalized intersections using vehicle-to-infrastructure (V2I) connectivity. Much existing work on AIN has been tested using model-in-loop (MIL) simulation due to being safer and more accessible than on-vehicle options. To fully validate the functionality and performance of the feature, additional
Hamilton, KaylaMisra, PriyashrabaOrd, DavidGoberville, NickCrain, TrevorMarwadi, Shreekant
Real-time traffic event information is essential for various applications, including travel service improvement, vehicle map updating, and road management decision optimization. With the rapid advancement of Internet, text published from network platforms has become a crucial data source for urban road traffic events due to its strong real-time performance and wide space-time coverage and low acquisition cost. Due to the complexity of massive, multi-source web text and the diversity of spatial scenes in traffic events, current methods are insufficient for accurately and comprehensively extracting and geographizing traffic events in a multi-dimensional, fine-grained manner, resulting in this information cannot be fully and efficiently utilized. Therefore, in this study, we proposed a “data preparation - event extraction - event geographization” framework focused on traffic events, integrating geospatial information to achieve efficient text extraction and spatial representation. First
Hu, ChenyuWu, HangbinWei, ChaoxuChen, QianqianYue, HanHuang, WeiLiu, ChunFu, TingWang, Junhua
Roadside perception technology is an essential component of traffic perception technology, primarily relying on various high-performance sensors. Among these, LiDAR stands out as one of the most effective sensors due to its high precision and wide detection range, offering extensive application prospects. This study proposes a voxel density-nearest neighbor background filtering method for roadside LiDAR point cloud data. Firstly, based on the relatively fixed nature of roadside background point clouds, a point cloud filtering method combining voxel density and nearest neighbor is proposed. This method involves voxelizing the point cloud data and using voxel grid density to filter background point clouds, then the results are processed through a neighbor point frame sequence to calculate the average distance of the specified points and compare with a distance threshold to complete accurate background filtering. Secondly, a VGG16-Pointpillars model is proposed, incorporating a CNN
Liu, ZhiyuanRui, Yikang
This SAE Technical Information Report identifies use cases for AI technology applications to ground vehicles and transportation infrastructure. Whenever applicable, functional definitions and noted issues and concerns are provided in consistent with the current industry mobility practices and published peer-reviewed literature.
Artificial Intelligence
Introducing connectivity and collaboration promises to address some of the safety challenges for automated vehicles (AVs), especially in scenarios where occlusions and rule-violating road users pose safety risks and challenges in reconciling performance and safety. This requires establishing new collaborative systems with connected vehicles, off-board perception systems, and a communication network. However, adding connectivity and information sharing not only requires infrastructure investments but also an improved understanding of the design space, the involved trade-offs and new failure modes. We set out to improve the understanding of the relationships between the constituents of a collaborative system to investigate design parameters influencing safety properties and their performance trade-offs. To this end we propose a methodology comprising models, analysis methods, and a software tool for design space exploration regarding the potential for safety enhancements and requirements
Fornaro, GianfilippoTörngren, MartinGaspar Sánchez, José Manuel
At present, 77GHz millimeter-wave (MMW) radar has become a critical sensor in intelligent transportation systems due to its all-weather detection capability, which enables it to resist complex weather and light interference. Radar cross section (RCS) is a significant characteristic of radar, greatly impacting the detection quality of traffic targets across various traffic scenarios. RCS is usually measured in an anechoic chamber to establish a model of the RCS of typical traffic participants. However, due to large target fluctuations and multi-angle scattering centers of targets, representing the RCS characteristics of typical traffic participants with a single point is challenging. Taking global vehicle target (GVT), pedestrian target and cyclist target as examples, this paper proposes a method for measuring and modeling the RCS features of typical traffic participants. For the static RCS features of targets, we measured the RCS of the target under different viewing angles in an
Liu, TengyuShi, WeigangTong, PanpanBi, Xin
To facilitate the construction of a robust transport infrastructure, it is essential to implement a digital transformation of the current highway system. The concept of digital twins, which are virtual replicas of physical assets, offers a novel approach to enhancing the operational efficiency and predictive maintenance capabilities of highway networks. The present study begins with an exhaustive examination of the demand for the smart highway digital twin model, underscoring the necessity for a comprehensive framework that addresses the multifaceted aspects of digital transformation. The framework, as proposed, is composed of six integral components: spatiotemporal data acquisition and processing, multidimensional model development, model integration, application layer construction, model iteration, and model governance. Each element is critical in ensuring the fidelity and utility of the digital twin, which must accurately reflect the dynamic nature of highway systems. The
Zhang, YawenCai, Xianhua
In the context of intelligent transportation vehicle perception, embedded computing devices serve as the primary computing platform, facing the challenge of the traditional visual SLAM(Simultaneous Localization and Mapping) framework's high computational demands for environmental feature points. To address issues such as point cloud drift errors in long-term, large-scale road traffic perception tasks and the high mismatch rate of feature point tracking in traffic scenes with numerous dynamic objects, this work proposes an optimized feature point mismatch elimination method for the visual odometry module based on the ORB-SLAM3 framework. Additionally, an efficient visual vector dictionary loading and matching algorithm for repetitive keyframes is designed for the loop closure detection module. In the feature point mismatch elimination calculation of the visual odometry module, a feature confidence index is introduced to eliminate mismatched feature points of dynamic traffic objects
Weichao, ZhangShi, Xiaomeng
The transition from manual to autonomous driving introduces new safety challenges, with road obstacles emerging as a prominent threat to driving safety. However, existing research primarily focuses on vehicle-to-vehicle risk assessment, often overlooking the significant risks posed by static or dynamic road obstacles. In this context, developing a system capable of real-time monitoring of road conditions, accurately identifying obstacle positions and characteristics, and assessing their associated risk levels is crucial. To address these gaps, this study proposes a comprehensive process for rapid obstacle identification and risk quantification, composed of three main components: road obstacle event detection and feature extraction, risk quantification and level assessment, and output of warning information and countermeasures. First, a rapid detection method suited for highway scenarios is proposed based on the YOLOv5 model, enabling fast detection and classification of obstacles in
Chen, TingtingChen, LeileiYu, WenluChen, Daoxie
In intelligent transportation systems (ITS), traffic flow prediction is a necessary tool for effective traffic management. By identifying and extracting key nodes in the network, it is possible to achieve efficient traffic flow prediction of the whole network using “partial” nodes, as the key nodes contain essential information about changes in the state of the traffic network. This paper proposes a key node identification method based on revised penalty local structure entropy (RPLE) for specific traffic networks. This method takes into account the influence of node distance and traffic flow on identifying important nodes within the traffic network. By introducing a modified penalty term and a comprehensive weight, it achieves a certain level of accuracy in traffic flow prediction using data from key nodes in the network. We compared the RPLE method with different key node identification methods and combined it with different prediction models to compare the traffic flow prediction
Shu, XinRan, Bin
Intelligent Structural Health Monitoring (SHM) of bridge is a technology that utilizes advanced sensor technology along with professional bridge engineering knowledge, coupled with machine vision and other intelligent methods for continuously monitoring and evaluating the status of bridge structures. One application of SHM technology for bridges by way of machine learning is in the use of damage detection and quantification. In this way, changes in bridge conditions can be analyzed efficiently and accurately, ensuring stable operational performance throughout the lifecycle of the bridge. However, in the field of damage detection, although machine vision can effectively identify and quantify existing damages, it still lacks accuracy for predicting future damage trends based on real-time data. Such shortfall l may lead to late addressing of potential safety hazards, causing accelerated damage development and threatening structural safety. To tackle this problem, this study designs a deep
Xu, WeidongCai, C.S.Xiong, WenZhu, Yanjie
Intelligent transportation has emerged as a critical paradigm in the transportation sector, underscoring the growing significance of digital information. The extent to which travelers comprehend transportation network information fundamentally influences the dynamics of traffic flow evolution. Traditional random user equilibrium models assume that travelers possess knowledge of segment flow information; however, they fail to account for route flow information. To date, research has yet to investigate how travelers’ decision-making behaviors are altered following the acquisition of route flow information. When endowed with such information, travelers frequently demonstrate behaviors influenced by the bandwagon effect, adjusting their routes to conform to the choices of the majority. This behavioral modification disrupts the existing equilibrium, resulting in a continued evolution of traffic flow until a new stable state is achieved. To examine the implications of transportation network
Zhou, BojianYu, YaofengLi, ShihaoLi, Kangjiao
This work aims to design an ecological driving strategy for connected and automated vehicles (CAVs) at an isolated signalized intersection in a mixed traffic flow of CAVs and human-driven vehicles (HVs). Actually, from existing experiments and theories, we can obtain that stochasticity of HVs plays a nontrivial role in traffic flow, including the drivers’ driving personality style and the interaction between HV and CAV. To consider the uncertainty of HVs, we propose driver acceptance to describe the interaction between HV and CAV with the increase of CAV market penetration rate (MPR). Then, to estimate the arrival time of CAV accurately, we propose an improved LWR method integrating the vehicle to V2X data and detector data. The problem is formulated as a multi-objective optimization model and solved by NSGA-II. Our study indicates that multi-objective performance benefits depend on inflow rate, the MPR, and the drivers’ acceptance towards CAVs. The results show that traffic efficiency
Wang, XiaoliangMa, ShufangYu, QinSong, WenPeng, HongruiHu, Yiming
Segment with lane drops are very important in freeway systems since they are major constrains to traffic flow and safety. The frequency of capacity reductions and higher safety risks is proportional to an increase in lane-changing actions, which worsen traffic congestion, decrease road capacity, and increase the risk of an accident. Traditional traffic management strategies that rely on physical structures and driver’s decision making often fail under such conditions. This paper provides a detailed lane change control strategy specific to freeway segments with lane reduction in the connected and autonomous vehicle (CAV) environment. The strategy combines both centralized and decentralized techniques to improve the vehicle’s lane-changing behavior and density. A cellular transmission model of lane-level is proposed for the centralized control of the linked vehicles based on the ratio of the driver compliance. The model derives the density equation and transforms the lane-changing
Ma, YuhengGuo, XiuchengZhang, YimingCao, Jieyu
This paper presents a novel variable speed limit control strategy based on an Improved METANET model aimed at addressing traffic congestion in the bottleneck areas of expressways while considering the impact of an intelligent connected environment. Traffic flow simulation software was employed to compare the outcomes of the traditional variable speed limit model with those derived from the proposed strategy. The results indicated that under three scenarios—main road, ramp, and lane closure—with a 100% penetration rate of intelligent connected vehicles, the average delay for vehicles utilizing the new model decreased by 9.37%, 11.11%, and 7.22%, respectively. This study offers an innovative approach to highway variable speed limits under an intelligent connected environment.
Qi, TianchengQu, XinhuiGu, HaiyanSang, ZhemingNing, Fangyue
The practice of vehicle platooning for managing mixed traffic can greatly enhance safety on the roads, augment overall traffic flow, and boost fuel efficiency, garnering considerable focus in transportation. Existing research on vehicle platoon control of mixed traffic has primarily focused on using the state information of the leading or head vehicle as control input for following vehicles without accounting for the driving variability of Human-driven Vehicles (HDVs), which does not conform to the driving conditions of vehicles in reality. Inspired by this, this paper presents a car-following model for Connected and Automated Vehicles (CAVs) that utilizes communication with multiple preceding vehicles in mixed traffic. The study further investigates the impact of parameters such as the speed and acceleration of preceding vehicles on the car-following behavior of CAVs, as well as the overall effect of different CAV penetration rates on mixed traffic flow. Firstly, a mixed-vehicle
Peng, FukeHuang, Xin
Tunnels play a crucial role in urban transportation, yet they frequently encounter various incidents during operation. Manual video inspections and sensor-based systems are inefficient and limited in accurately detecting and addressing these issues. The emergence of artificial intelligence has led to the development of object detection models such as YOLO, which have shown promise in real-time anomaly detection. However, these single-modality models achieve suboptimal results when dealing with complex events. Multi-modal large language models (LLMs) offer a potential solution, with their ability to process and understand information from different modalities. This paper develops a novel tunnel traffic anomaly detection method that combines single-modal models and multi-modal LLMs. The proposed system first employs YOLO for an initial detection round and then utilizes a specially designed LLM with an effective prompt and a data filtering strategy tailored for traffic tunnel scenarios
Liu, HongyuZhou, RuohanBai, JiayangLi, Yuanqi
Items per page:
1 – 50 of 448