精确的环境感知是实现自主代客泊车(automated valet parking,AVP)功能的基础,传统的AVP系统主要依赖于单车的感知,但随着场端智能技术的不断发展,车端与场端之间协同交互成为自主代客泊车落地的必然趋势。本文提出了一种基于V2X车场协...精确的环境感知是实现自主代客泊车(automated valet parking,AVP)功能的基础,传统的AVP系统主要依赖于单车的感知,但随着场端智能技术的不断发展,车端与场端之间协同交互成为自主代客泊车落地的必然趋势。本文提出了一种基于V2X车场协同的地下停车场全域感知方法,该方法将地下停车场的全域感知问题转化为大规模图模型的构建与优化问题。通过输入场端激光雷达、摄像头的传感器信息以及智能网联车的感知数据,以车辆位姿为节点,建立多种边约束关系。为了提高感知精度,本文提出了一种融合车道级地图信息的大规模图模型方法,通过将停放车辆作为半静态信息约束,并结合车道级地图信息构建横向约束,在求解过程中引入滑动窗口以减小图模型的规模,最终以地图形式输出感知结果供车端使用。通过仿真实验和在占地面积为2 500 m^(2)以上的地下停车场场景中进行实地实验,结果表明,该方法显著提升了在复杂停车场环境下的感知能力,实现了地下停车场的全域感知。展开更多
1 Introduction Amid escalating global climate change,the“dual carbon”goals of carbon peak and carbon neutrality have become a focal point of global attention and an important strategy for sustainable development[1]....1 Introduction Amid escalating global climate change,the“dual carbon”goals of carbon peak and carbon neutrality have become a focal point of global attention and an important strategy for sustainable development[1].With the rapid development of renewable energy technologies and the increasing public demand for environmental protection and low-carbon living,the adoption of new energy vehicles,particularly electric vehicles(EVs).展开更多
In Heterogeneous Vehicle-to-Everything Networks(HVNs),multiple users such as vehicles and handheld devices and infrastructure can communicate with each other to obtain more advanced services.However,the increasing num...In Heterogeneous Vehicle-to-Everything Networks(HVNs),multiple users such as vehicles and handheld devices and infrastructure can communicate with each other to obtain more advanced services.However,the increasing number of entities accessing HVNs presents a huge technical challenge to allocate the limited wireless resources.Traditional model-driven resource allocation approaches are no longer applicable because of rich data and the interference problem of multiple communication modes reusing resources in HVNs.In this paper,we investigate a wireless resource allocation scheme including power control and spectrum allocation based on the resource block reuse strategy.To meet the high capacity of cellular users and the high reliability of Vehicle-to-Vehicle(V2V)user pairs,we propose a data-driven Multi-Agent Deep Reinforcement Learning(MADRL)resource allocation scheme for the HVN.Simulation results demonstrate that compared to existing algorithms,the proposed MADRL-based scheme achieves a high sum capacity and probability of successful V2V transmission,while providing close-to-limit performance.展开更多
Driven by the global“dual-carbon”goals,hydrogen fuel cell electric vehicles(FCEVs)are being rapidly promoted as a zero-emission transportation solution.However,their large-scale application is constrained by issues ...Driven by the global“dual-carbon”goals,hydrogen fuel cell electric vehicles(FCEVs)are being rapidly promoted as a zero-emission transportation solution.However,their large-scale application is constrained by issues such as inefficient operation,poor information flow between vehicles and stations,and potential safety hazards,which are caused by insufficient intelligence of hydrogen refueling stations.This study aims to address these problems by deeply integrating Cellular Vehicle-to-Everything(C-V2X)technology with hydrogen refueling stations,thereby building a safe,efficient,and low-carbon hydrogen energy application ecosystem to promote the global transition to zero-carbon transportation.Firstly,through literature review and technical analysis,this study expounds on the core technologies and process flows of current hydrogen refueling stations,aswell as the technical architecture and development evolution of C-V2X technology.Then,based on the analysis of relevant literature,it proposes a“vehicle-road-station-cloud”collaborative architecture that integrates C-V2X with hydrogen refueling stations.Combined with 5G communication and big data technologies,it elaborates on the implementation path for achieving real-time data interaction among hydrogen refueling stations,hydrogen-powered vehicles,and road infrastructure.This interconnection mode enables hydrogen refueling stations to obtain real-time information of surrounding vehicles,which plays an important role in building a safe,efficient,and low-carbon hydrogen energy application ecosystem and promoting the global transition to zero-carbon transportation.Finally,the future development prospects and potential of this scheme are put forward.展开更多
With the advancement of Vehicle-to-Everything(V2X)technology,efficient resource allocation in dynamic vehicular networks has become a critical challenge for achieving optimal performance.Existing methods suffer from h...With the advancement of Vehicle-to-Everything(V2X)technology,efficient resource allocation in dynamic vehicular networks has become a critical challenge for achieving optimal performance.Existing methods suffer from high computational complexity and decision latency under high-density traffic and heterogeneous network conditions.To address these challenges,this study presents an innovative framework that combines Graph Neural Networks(GNNs)with a Double Deep Q-Network(DDQN),utilizing dynamic graph structures and reinforcement learning.An adaptive neighbor sampling mechanism is introduced to dynamically select the most relevant neighbors based on interference levels and network topology,thereby improving decision accuracy and efficiency.Meanwhile,the framework models communication links as nodes and interference relationships as edges,effectively capturing the direct impact of interference on resource allocation while reducing computational complexity and preserving critical interaction information.Employing an aggregation mechanism based on the Graph Attention Network(GAT),it dynamically adjusts the neighbor sampling scope and performs attention-weighted aggregation based on node importance,ensuring more efficient and adaptive resource management.This design ensures reliable Vehicle-to-Vehicle(V2V)communication while maintaining high Vehicle-to-Infrastructure(V2I)throughput.The framework retains the global feature learning capabilities of GNNs and supports distributed network deployment,allowing vehicles to extract low-dimensional graph embeddings from local observations for real-time resource decisions.Experimental results demonstrate that the proposed method significantly reduces computational overhead,mitigates latency,and improves resource utilization efficiency in vehicular networks under complex traffic scenarios.This research not only provides a novel solution to resource allocation challenges in V2X networks but also advances the application of DDQN in intelligent transportation systems,offering substantial theoretical significance and practical value.展开更多
The emission of heavy-duty vehicles has raised great concerns worldwide.The complex working and loading conditions,which may differ a lot from PEMS tests,raised new challenges to the supervision and control of emissio...The emission of heavy-duty vehicles has raised great concerns worldwide.The complex working and loading conditions,which may differ a lot from PEMS tests,raised new challenges to the supervision and control of emissions,especially during real-world applications.On-board diagnostics(OBD)technology with data exchange enabled and strengthened the monitoring of emissions from a large number of heavy-duty diesel vehicles.This paper presents an analysis of the OBD data collected from more than 800 city and highway heavy-duty vehicles in China using remote OBD data terminals.Real-world NO_(x)and CO_(2)emissions of China-6 heavy-duty vehicles have been examined.The results showed that city heavy-duty vehicles had higher NO_(x)emission levels,which was mostly due to longer time of low SCR temperatures below 180°C.The application of novel methods based on 3BMAWalso found that heavy-duty diesel vehicles tended to have high NO_(x)emissions at idle.Also,little difference had been found in work-based CO_(2)emissions,and this may be due to no major difference were found in occupancies of hot running.展开更多
随着自动驾驶技术的迅速发展,V2X(Vehicle to Everything)技术成为提升环卫车运行效率与安全性的关键。该技术能实现车辆与外部环境的广泛连接,优化自动驾驶系统的功能,增强车辆间的信息交流和决策支持。为此,详细探讨了V2X技术的组成...随着自动驾驶技术的迅速发展,V2X(Vehicle to Everything)技术成为提升环卫车运行效率与安全性的关键。该技术能实现车辆与外部环境的广泛连接,优化自动驾驶系统的功能,增强车辆间的信息交流和决策支持。为此,详细探讨了V2X技术的组成和工作原理、在自动驾驶系统中的集成,以及智能网联协同工作模式的构建。研究旨在剖析V2X技术在当前交通系统中的应用潜力及环卫车在实际环境中的效能。展开更多
矿山环境由于其复杂性往往会增加车辆事故发生的可能性。为提高矿山车辆预警系统的准确性,研究通过V2X(Vehicle to Everything)技术实现车辆信息共享,结合具备卡尔曼滤波器的神经网络与双向循环神经网络(KalmanNet-BRNN)模型对车辆状态...矿山环境由于其复杂性往往会增加车辆事故发生的可能性。为提高矿山车辆预警系统的准确性,研究通过V2X(Vehicle to Everything)技术实现车辆信息共享,结合具备卡尔曼滤波器的神经网络与双向循环神经网络(KalmanNet-BRNN)模型对车辆状态进行估计。研究结果中,在4种数据集上,研究方法的均方误差平均降低了7.60、1.70、11.01和3.19,动态时间规整平均降低了2.05 m、3.50 m、2.73 m和5.38 m。结果表明,融合V2X技术和KalmanNet-BRNN网络架构可用于矿山车辆的预警,同时研究方法在多个数据集上均方误差最低,动态时间规整值最小,表明了研究方法能够提升矿山车辆预警系统的准确性,同时预测的车辆状态信息更为接近车辆真实状态;研究不仅提高了矿山作业的安全性,同时可为矿山企业的运营效率的提升提供数据支撑。展开更多
文摘精确的环境感知是实现自主代客泊车(automated valet parking,AVP)功能的基础,传统的AVP系统主要依赖于单车的感知,但随着场端智能技术的不断发展,车端与场端之间协同交互成为自主代客泊车落地的必然趋势。本文提出了一种基于V2X车场协同的地下停车场全域感知方法,该方法将地下停车场的全域感知问题转化为大规模图模型的构建与优化问题。通过输入场端激光雷达、摄像头的传感器信息以及智能网联车的感知数据,以车辆位姿为节点,建立多种边约束关系。为了提高感知精度,本文提出了一种融合车道级地图信息的大规模图模型方法,通过将停放车辆作为半静态信息约束,并结合车道级地图信息构建横向约束,在求解过程中引入滑动窗口以减小图模型的规模,最终以地图形式输出感知结果供车端使用。通过仿真实验和在占地面积为2 500 m^(2)以上的地下停车场场景中进行实地实验,结果表明,该方法显著提升了在复杂停车场环境下的感知能力,实现了地下停车场的全域感知。
基金supported by Yunnan Provincial Basic Research Project(202401AT070344)National Natural Science Foundation of China(62263014).
文摘1 Introduction Amid escalating global climate change,the“dual carbon”goals of carbon peak and carbon neutrality have become a focal point of global attention and an important strategy for sustainable development[1].With the rapid development of renewable energy technologies and the increasing public demand for environmental protection and low-carbon living,the adoption of new energy vehicles,particularly electric vehicles(EVs).
基金funded in part by the National Key Research and Development of China Project (2020YFB1807204)in part by National Natural Science Foundation of China (U2001213 and 61971191)+1 种基金in part by the Beijing Natural Science Foundation under Grant L201011in part by the key project of Natural Science Foundation of Jiangxi Province (20202ACBL202006)。
文摘In Heterogeneous Vehicle-to-Everything Networks(HVNs),multiple users such as vehicles and handheld devices and infrastructure can communicate with each other to obtain more advanced services.However,the increasing number of entities accessing HVNs presents a huge technical challenge to allocate the limited wireless resources.Traditional model-driven resource allocation approaches are no longer applicable because of rich data and the interference problem of multiple communication modes reusing resources in HVNs.In this paper,we investigate a wireless resource allocation scheme including power control and spectrum allocation based on the resource block reuse strategy.To meet the high capacity of cellular users and the high reliability of Vehicle-to-Vehicle(V2V)user pairs,we propose a data-driven Multi-Agent Deep Reinforcement Learning(MADRL)resource allocation scheme for the HVN.Simulation results demonstrate that compared to existing algorithms,the proposed MADRL-based scheme achieves a high sum capacity and probability of successful V2V transmission,while providing close-to-limit performance.
基金supported in part by the Key Research and Development Program of Shandong Province under Grant 2022KJHZ002.
文摘Driven by the global“dual-carbon”goals,hydrogen fuel cell electric vehicles(FCEVs)are being rapidly promoted as a zero-emission transportation solution.However,their large-scale application is constrained by issues such as inefficient operation,poor information flow between vehicles and stations,and potential safety hazards,which are caused by insufficient intelligence of hydrogen refueling stations.This study aims to address these problems by deeply integrating Cellular Vehicle-to-Everything(C-V2X)technology with hydrogen refueling stations,thereby building a safe,efficient,and low-carbon hydrogen energy application ecosystem to promote the global transition to zero-carbon transportation.Firstly,through literature review and technical analysis,this study expounds on the core technologies and process flows of current hydrogen refueling stations,aswell as the technical architecture and development evolution of C-V2X technology.Then,based on the analysis of relevant literature,it proposes a“vehicle-road-station-cloud”collaborative architecture that integrates C-V2X with hydrogen refueling stations.Combined with 5G communication and big data technologies,it elaborates on the implementation path for achieving real-time data interaction among hydrogen refueling stations,hydrogen-powered vehicles,and road infrastructure.This interconnection mode enables hydrogen refueling stations to obtain real-time information of surrounding vehicles,which plays an important role in building a safe,efficient,and low-carbon hydrogen energy application ecosystem and promoting the global transition to zero-carbon transportation.Finally,the future development prospects and potential of this scheme are put forward.
基金Project ZR2023MF111 supported by Shandong Provincial Natural Science Foundation。
文摘With the advancement of Vehicle-to-Everything(V2X)technology,efficient resource allocation in dynamic vehicular networks has become a critical challenge for achieving optimal performance.Existing methods suffer from high computational complexity and decision latency under high-density traffic and heterogeneous network conditions.To address these challenges,this study presents an innovative framework that combines Graph Neural Networks(GNNs)with a Double Deep Q-Network(DDQN),utilizing dynamic graph structures and reinforcement learning.An adaptive neighbor sampling mechanism is introduced to dynamically select the most relevant neighbors based on interference levels and network topology,thereby improving decision accuracy and efficiency.Meanwhile,the framework models communication links as nodes and interference relationships as edges,effectively capturing the direct impact of interference on resource allocation while reducing computational complexity and preserving critical interaction information.Employing an aggregation mechanism based on the Graph Attention Network(GAT),it dynamically adjusts the neighbor sampling scope and performs attention-weighted aggregation based on node importance,ensuring more efficient and adaptive resource management.This design ensures reliable Vehicle-to-Vehicle(V2V)communication while maintaining high Vehicle-to-Infrastructure(V2I)throughput.The framework retains the global feature learning capabilities of GNNs and supports distributed network deployment,allowing vehicles to extract low-dimensional graph embeddings from local observations for real-time resource decisions.Experimental results demonstrate that the proposed method significantly reduces computational overhead,mitigates latency,and improves resource utilization efficiency in vehicular networks under complex traffic scenarios.This research not only provides a novel solution to resource allocation challenges in V2X networks but also advances the application of DDQN in intelligent transportation systems,offering substantial theoretical significance and practical value.
基金supported by the National Key Research and Development Project of China(No.2022YFC3701802)the National Natural Science Foundation of China(No.52272342)the Major Science and Technology Projects of Qinghai Province(No.2019-GX-A6).
文摘The emission of heavy-duty vehicles has raised great concerns worldwide.The complex working and loading conditions,which may differ a lot from PEMS tests,raised new challenges to the supervision and control of emissions,especially during real-world applications.On-board diagnostics(OBD)technology with data exchange enabled and strengthened the monitoring of emissions from a large number of heavy-duty diesel vehicles.This paper presents an analysis of the OBD data collected from more than 800 city and highway heavy-duty vehicles in China using remote OBD data terminals.Real-world NO_(x)and CO_(2)emissions of China-6 heavy-duty vehicles have been examined.The results showed that city heavy-duty vehicles had higher NO_(x)emission levels,which was mostly due to longer time of low SCR temperatures below 180°C.The application of novel methods based on 3BMAWalso found that heavy-duty diesel vehicles tended to have high NO_(x)emissions at idle.Also,little difference had been found in work-based CO_(2)emissions,and this may be due to no major difference were found in occupancies of hot running.
文摘随着自动驾驶技术的迅速发展,V2X(Vehicle to Everything)技术成为提升环卫车运行效率与安全性的关键。该技术能实现车辆与外部环境的广泛连接,优化自动驾驶系统的功能,增强车辆间的信息交流和决策支持。为此,详细探讨了V2X技术的组成和工作原理、在自动驾驶系统中的集成,以及智能网联协同工作模式的构建。研究旨在剖析V2X技术在当前交通系统中的应用潜力及环卫车在实际环境中的效能。
