Citation: | GUO Yan-yong, LIU Pei, YUAN Quan, LIU Pan, XU Jin, ZHANG Hui. Review on research of road traffic safety of connected and automated vehicles[J]. Journal of Traffic and Transportation Engineering, 2023, 23(5): 19-38. doi: 10.19818/j.cnki.1671-1637.2023.05.002 |
The global road traffic safety situation is severe. According to a report by the World Health Organization, the annual number of traffic deaths worldwide exceeds 1.35 million, and about 50 million people are injured in road traffic accidents[1]The occurrence of road traffic accidents not only causes a large number of casualties, but also seriously affects economic development and social stability. The arrival of the intelligent era has provided many new ways to solve transportation problems. Connected and Automated Vehicles (CAVs), which integrate emerging technologies such as the Internet of Vehicles, intelligent vehicles, and real-time communication, are widely recognized as an effective solution to traffic problems.
Connected autonomous vehicles are equipped with advanced onboard sensors and other devices, relying on high-precision digital maps and integrating modern communication and network technologies to achieve real-time interaction and sharing of data information between vehicles and surrounding intelligent transportation facilities[2](Figure 1)It is currently an international research hotspot that can effectively improve safety and traffic efficiency, reduce energy consumption. The "Classification of Automotive Driving Automation" considers dynamic driving tasks, minimum risk states, and minimum risk strategies from multiple perspectives, and divides autonomous driving into levels 0-5[3]Relevant literature indicates that research on networked autonomous driving mainly includes the design of adaptive cruise control system algorithms[4-6]Optimization of Traffic Control Algorithms for Connected Vehicles[7-10]Analysis of the New Mixed Traffic Flow Model[11-12]Vehicle trajectory safety planning[13-16]Run security verification[17-18]And road traffic management[19-21]Wait. However, as more and more autonomous vehicles are put into operation, academia and industry are paying increasing attention to the many traffic safety issues exposed during the operation of networked autonomous vehicles on actual roads. Such as the 2016 Google Lexus autonomous vehicle and bus collision case[22]In 2018, an Uber connected autonomous vehicle on a public road in Arizona, USA, caused a fatal accident among pedestrians[23]In 2021, the NIO ES8 autonomous driving car in China caused a fatal accident on the highway[24]According to official statistics from the California Department of Vehicles, there were 543 accidents involving autonomous vehicles in the California region from 2014 to 2022. Conducting in-depth research and systematic analysis on the field of connected autonomous driving from the perspective of traffic safety, exploring the risks of autonomous driving traffic safety, and clarifying the future development direction of autonomous driving are key to improving autonomous driving traffic safety and promoting breakthroughs in technological bottlenecks. Therefore, it is of great significance to comprehensively summarize and review the research in the field of connected autonomous driving road traffic safety.
This article uses the Web of Science retrieval tool to search for relevant research papers on road traffic safety in the field of networked autonomous driving from 2010 to 2021, and uses bibliometrics and scientific knowledge graph methods to mine related topics. From a macro level, it analyzes and summarizes the development trends and source distribution of networked autonomous driving road traffic safety research, three research topics and main contents (micro traffic flow of networked autonomous driving, impact of networked autonomous driving on traffic systems, obstacle avoidance and traffic safety evaluation of networked autonomous driving), and three research hotspots (optimization and motion planning of networked autonomous driving traffic control, traffic safety analysis of new hybrid traffic flow of networked autonomous driving, micro behavior modeling and simulation safety evaluation of networked autonomous driving), And from five aspects (construction of intelligent networked data-driven simulation environment and deep testing platform under virtual reality, intelligent networked fleet group decision-making and formation control technology, performance evaluation system for driver takeover in the context of networked autonomous driving human-machine co driving, quantitative evaluation of traffic flow safety risks in networked autonomous driving, and formulation of multi-level automated vehicle policy and regulatory guarantees and management measures), the research on road traffic safety in networked autonomous driving is expected.
This study uses bibliometric and scientific knowledge graph methods to explore and analyze the research on road traffic safety in networked autonomous driving. In 1986, the University of California, Berkeley first proposed the concept of vehicle road coordination and focused on the theoretical research of vehicle following[25]Subsequently, Japan, China, and Europe all began research on vehicle road cooperative safe driving technology, with an early focus on the concept of vehicle road cooperative systems and vehicle following theory. The theoretical research and practical application exploration of road traffic safety in networked autonomous driving emerged around 2010. In order to fit the theme of road traffic safety in networked autonomous driving, a literature search was conducted using the Web of Science retrieval system. The search keywords were set as Connected and Automated (Autonomous) Vehicles, Connected (Autonomous) Vehicles, Traffic Safety (Accident, Crash, Collision, Conflict), and the retrieval logic strategy adopted was Connected and Automated (Autonomous) Vehicles or Connected (Autonomous) Vehicles and Traffic Safety or (Accident, Crash, Collision, Conflict). The retrieval time span was from 2010 to 2021. By selecting Article and Review as the literature types and Transportation as the search category, a total of 2130 domestic and foreign literature that met the screening criteria were retrieved. Add eligible literature to the tag list and select full records and references to export and save in text document format. Then import the file into VOSviewer software for analysis. The research method and process are described inFigure 2.
Bibliometrics uses statistical and other quantitative methods to process the elements of literature, analyze the distribution structure, variation patterns, and quantitative relationships of literature, and thus conduct disciplinary research summarization and dynamic analysis of development. The scientific knowledge graph is an important application of visualization technology in bibliometrics, which can mine, analyze, and classify literature knowledge. This article uses the scientific knowledge graph software VOSviewer to construct and visualize the relationships between scientific knowledge units obtained from literature, and uses co-occurrence matrices for layout to generate knowledge graphs. Its core principles include the construction of similarity matrices and the construction of knowledge graphs[26].
(1) Construction of similarity matrix
The construction of co-occurrence matrix is the foundation of cluster analysis, which normalizes the co-occurrence matrix to obtain a similarity matrix. VOSviewer uses association strength to cluster literature elements with high similarity and separate elements with low similarity. The literature element indicators in this study include literature attribution, keywords, etc., as well as elements in the scientific knowledge graphiandjThe similarity between themSijExpressed As
Sij=cijwiwj | (1) |
In the formula:cijinto elementsiandjThe co-occurrence frequency between them;wiandwjThey are elements respectivelyiandjThe frequency of occurrence.
(2) Construction of Scientific Knowledge Graph
To make the clustering effect more obvious, VOSviewer uses the spatial distance between elements to reflect their similarity. The closer the spatial distance, the higher the similarity between elements. The layout of the scientific knowledge graph is usually presented by minimizing the sum of weighted Euclidean distances of all elements in each cluster, where the distance between each cluster is represented as
E(x1,x2,⋯,xn)=∑i<jSij‖xi−xj‖2 | (2) |
2n(n−1)∑i<j‖xi−xj‖=1 | (3) |
In the formula:E(·) is the sum of weighted Euclidean distances for all elements in the cluster;nThe number of elements required for constructing a knowledge graph;xi、xjThey are elements respectivelyi、jPosition in two-dimensional space; ∥·∥ It is the Euclidean norm.
The distribution of publication years to a certain extent reflects the research status, level, and development speed of the field, and can also reflect the hot periods of research in the field during a certain period of time through charts and graphs[27]From 2010 to 2021, a total of 2130 relevant literature were included in the field of road traffic safety for connected autonomous driving, and their quantity varied over timeFigure 3The number of connected autonomous driving accidents and actual vehicle test mileage shown in the figure are from official statistics from the California Department of Vehicles in the United States.
(3) Rapid development stage (2017-2021). Due to the development and implementation of autonomous vehicles by brands such as Tesla, Uber, and Google, traffic safety issues have received increasing attention. The research on road traffic safety related to networked autonomous driving in this stage presents diversification, involving safety issues of mixed traffic flow in networked autonomous driving[43-44]Risk of vehicle communication network security attacks[45-46]Safety issues of networked autonomous driving vehicle formation[47-48]Stability and Safety Assessment of Adaptive Cruise Control System[49]Wait. Research methods and technologies are also becoming more diversified, such as using simulated driving and simulation experiments for safety avoidance modeling and data collection[50]The application of intelligent algorithms such as deep learning and reinforcement learning in improving autonomous driving planning, control, and safety enhancement[51-52]Using survey questionnaires and other forms to explore the public's acceptance of connected autonomous driving[53]Wait. The scope of this article includes road traffic safety of connected autonomous driving and safety related topics such as traffic control and traffic flow safety, but does not include content such as vehicle communication safety and traffic data securityFigure 5As shown.
The co-occurrence network of literature related to the research on road traffic safety in the field of networked autonomous driving belongs to countries and regionsFigure 6As shown in the figure, the color of the nodes in the network represents the research time, and the darker the color, the earlier the research time; The nodes in the network represent the number of articles published in that country or region, and the larger the radius of the nodes, the more related research articles are published[27]This article collects literature from 74 countries and regions, and conducts a visual analysis of the distribution of 40 countries with 5 or more relevant literature on road traffic safety research in the rapid development stage of networked autonomous driving in the time dimension.
causeFigure 6It can be seen that some Eurasian countries (such as Japan, France, Spain, etc.) are far ahead in terms of scientific and technological advancement and industrialization. Their research on intelligent connected traffic safety started earlier and has been deeply cultivated for many years with rich accumulation; Developed countries such as the United States, the United Kingdom, Germany, and Australia subsequently began to invest in relevant original scientific research, and the accumulation of achievements gradually took the dominant position; Countries such as Canada, South Korea, Italy, and Singapore are paying increasing attention to the field of road traffic safety through connected autonomous driving, and their research contributions are becoming more prominent; In recent years, countries such as China, the Netherlands, New Zealand, and Israel have also initiated research on intelligent connected traffic safety and achieved significant results. In terms of the volume of research results, the United States and China are the two largest research subjects in the world today, thanks to the fact that both have issued relevant policies at the national level to promote the safe implementation of autonomous driving, such as the one released by the US Department of TransportationPreparing for the Future of Transportation: Automated Vehicles3.0 prioritizes autonomous driving traffic safety, and the National Highway Traffic Safety Administration of the United States has also released regulations for autonomous drivingConceptual Framework: Safety Risk Management Stage for AVFocus on the risk management of autonomous driving traffic safety. The Chinese Ministry of Science and Technology, Ministry of Industry and Information Technology, and other departments have also vigorously invested in research on networked autonomous driving, and have successively promoted a number of key research and development projects such as the theory and testing verification of intelligent control of vehicle groups in the vehicle road collaborative environment (2018) and the simulation and digital twin testing evaluation tool chain for autonomous driving (2021), aiming to accelerate the practical application of networked autonomous driving. In addition, China has established 16 test sites for autonomous vehicle in Beijing, Shanghai, Chongqing, Wuxi and other places, providing a basis for studying the impact of autonomous driving on road traffic safety.
应用场景 | 相关文献 | 微观交通流研究内容 | 研究方法 |
微观跟驰 | [54] | 传统微观单车道模型、驾驶人辅助系统 | 智能驾驶模型 |
纵向控制 | [55]、[56] | 驾驶人辅助系统及其优化改进 | 自适应巡航控制系统协同自适应巡航控制 |
[11] | 研究不同ACC策略对交通流特性的影响 | 强化智能驾驶模型 | |
[57]、[58] | 研究CACC系统对智能网联交通流特性的影响 | 微观交通仿真模型 | |
横向控制 | [59] | 构建考虑相邻车辆运动状态的网联自动驾驶车道变换轨迹生成方法,应比较多种非线性变换曲线以评估选择最佳换道模型 | 交会引导技术 |
[60] | 考虑网联自动驾驶车辆横纵向运动之间的耦合效应,确定换道行为的最佳控制序列和碰撞规避及动态安全约束 | 非线性单轨车辆动力学模型多段变道过程模型 | |
编队换道 | [61] | 研究网联自动驾驶车队在拥挤车流中保证编队稳定性的同时提高变道成功率 | 协同自适应巡航车辆编队变道控制器 |
[62] | 提出能够仿真具有不同通信能力车辆安全跟驰行为的技术框架以解决车辆联通性和自动化区分不足的问题 | 多模型融合 | |
[63] | 开发计算自动驾驶车辆和常规车辆混合交通流通行能力的通用公式以根据需求确定跨车道的自动驾驶车辆分布 | 多目标优化 |
In terms of lane changing models and lateral control, Usman et al[59]A method for generating lane change trajectories in networked autonomous driving considering the motion status of adjacent vehicles has been constructed, thereby achieving safe lane changes. It is pointed out that lane change trajectories are different from linear programming in longitudinal control, and multiple nonlinear transformation curves should be compared to evaluate and select the best model[28]Liu et al[60]The optimal control sequence, collision avoidance, and dynamic safety constraints for lane changing behavior were determined by integrating nonlinear monorail vehicle dynamics models and multi-stage lane changing process models, and considering the coupling effects between longitudinal and lateral movements of networked autonomous vehicles. The proposed method was verified through simulation to have good real-time prediction ability, model fidelity, and computational feasibility, and can systematically mediate dynamic constraints in complex lane changing scenarios while maintaining lane changing safety. In addition, some scholars have studied lane changing strategies for networked autonomous driving formations, such as Wang et al[61]A collaborative adaptive cruise vehicle formation lane changing controller is proposed, which adopts a Back Looking (BL) collaborative adaptive cruise information topology structure. Simulation experiments have shown that the controller has enhanced lane changing ability under dense traffic capacity, and can improve the success rate of lane changing while ensuring formation stability. The above research indicates that the lane changing model of connected autonomous vehicles has been upgraded in terms of modeling technology and model form. It has gone through a process from single vehicle lane changing model to integrating surrounding environment lane changing model, and further evolved into a complex high-precision simulation model involving multiple variables and parameters. The modeling technology has also shifted from simple linear models to more advanced nonlinear models and multi-objective programming models.
Cluster A2 is the second largest cluster in the network, and its main content is the research on the impact of networked autonomous driving on traffic travel, traffic environment, traffic safety, etc., such asTable 2As shown, Fagnant et al. hold a high position in this cluster[64]PublishedThe Travel and Environmental Implications of Shared Autonomous Vehicles, Using Agent-Based Model ScenariosThe article proposes using an intelligent agent model to verify that networked autonomous driving can solve current obstacles to car sharing, reduce passenger waiting time, lower vehicle emissions and environmental impact, while also ensuring safe travel for shared car users, thus achieving overall maximization of benefits. Milakis et al[21]The concept of chain reaction was adopted to explore the potential impact of connected autonomous driving on social policies at different stages, including first-order (transportation, travel costs, and travel choices), second-order (vehicle ownership, location selection, land use, and transportation infrastructure), and third-order (energy consumption, air pollution, traffic safety, social equity, economy, and public health). It was pointed out that balancing the short-term benefits and long-term impacts of connected autonomous driving vehicles on society and policies can change traditional transportation modes and build a safer transportation environment. Scholars start from the perspective of studying the impact of connected autonomous vehicles on transportation systems, using control theory and traffic engineering theory to establish macroscopic and microscopic traffic models. They use car following models, intelligent agent models, and traffic simulation models to analyze vehicle behavior characteristics and road capacity, and explore the impact of connected autonomous driving on traffic travel, environment, and road safety.
应用领域 | 相关文献 | 对交通系统影响的相关研究内容 | 研究方法 |
交通环境交通安全 | [64] | 验证网联自动驾驶可解决汽车共享障碍,降低车辆排放对环境影响,保障共享车使用者安全出行,达到整体利益最大化 | 智能体模型 |
交通出行交通环境交通安全 | [21] | 探讨网联自动驾驶在一阶(交通、出行成本和出行选择),二阶(车辆所有权、地点选择和土地使用以及交通基础设施)和三阶(能源消耗、空气污染、交通安全、社会公平、经济和公共健康)对社会政策的潜在影响 | 连锁反应概念 |
公众态度 | [65] | 研究公众对网联自动驾驶的态度,确定用户接受程度和购买意愿,评估自动驾驶技术推广与个人变量的相关性 | 网络问卷调查 |
用户偏好 | [66] | 探究选择拥有和使用网联自动驾驶车辆的个人动机,开发网联自动驾驶车辆长期选择决策模型 | 陈述偏好问卷调查 |
应用领域 | 相关文献 | 主要研究内容 | 研究方法 |
运动规划、反馈控制 | [67] | 比较多种典型运动规划和反馈控制算法,分析优势和局限性 | 并列比较 |
安全避障 | [68] | 对决策过程分步骤进行算法复杂性和性能准确性的评估 | 批判性评估 |
轨迹规划 | [16] | 回顾智能驾驶车辆运动规划技术,指出研究目标应集中优化复杂驾驶环境下的运动轨迹规划,设置具有避障功能的导航系统 | 综合性分析 |
安全替代指标评估 | [69] | 系统总结安全替代指标在网联自动驾驶安全建模和评价中的应用,回顾不同安全替代指标的有效性和适用性 | 系统性总结 |
[70] | 提取碰撞时间TTC和制动次数BTN作为安全替代指标,基于极值理论估计事故频率以评估自动驾驶交通安全 | 极值模型 |
This cluster has a total of 27 keywords, including Safety, Autonomous Vehicles, Vehicles, Roads, Optimal Control, Predictive Control, Navigation, Algorithm, Collision Avoidance, Motion Planning, Trajectory Planning, Deep Learning, Machine Learning, etc. The visualization results of the cluster show that keywords such as control, planning, and algorithm are high-frequency co occurring words, reflecting that an important research topic in the field of road traffic safety in networked autonomous driving is traffic control and vehicle system algorithm optimization, such asTable 4As shown.
应用场景 | 相关文献 | 主要研究内容 |
高速公路 | [77] | 利用IDM模型评估不同渗透率条件下自动驾驶编队的纵向安全性 |
[75] | 构建自动驾驶时空波动率曲线以识别交通网络中的潜在危险并做出积极的驾驶决策 | |
[76] | 通过优化安全变道次数最大限度地减少混合交通流中断以提高吞吐量并减少拥堵 | |
信号交叉口 | [10] | 利用网联自动驾驶车辆作交叉口控制媒介通过预测微观模拟算法响应即时车辆需求 |
[78]、[79] | 基于启发式算法识别网联自动驾驶车辆轨迹以产生最佳安全性能的交通控制 | |
[8] | 使用交叉口周边交通状态数据进行实时自适应信号相位分配 | |
[80] | 开发适用于城市交通走廊的协作式信号控制算法 | |
[81] | 提出考虑车辆随机到达的两级控制模型,用于不同交通需求下多个网联自动驾驶车辆的交通信号配时设计和轨迹规划 | |
[82] | 构建根据不同交通状态指定合适信号控制方法的概念框架 | |
车道编队 | [47] | 基于行车环境势场和车辆动力学建模,结合模型预测控制中的优化算法完成编队车辆轨迹规划和控制,实现动态避障 |
[83] | 介绍Demo 2000协同驾驶系统中的自动驾驶和车间通信技术并提出多车道编队概念 | |
[84] | 基于协作式自适应巡航控制车辆跟驰算法,添加分层控制和信号交叉口优化控制模块,准确估计车辆状态、监控潜在碰撞风险进而优化车辆轨迹、调整信号配时 |
In addition to the vehicle road coordination function, networked autonomous vehicles can also share real-time information with other vehicles through wireless communication and sensing capabilities, accurately control their motion trajectories to form safe and stable formations, and shorten loss time through fast communication and longitudinal control of queue stability. Scholars have conducted relevant research on the formation problem of networked autonomous driving vehicles. Kato et al[83]Propose the concept of multi lane formation and use it to improve the safety of networked autonomous driving fleets; Huang et al[47]Based on the driving environment potential field and vehicle dynamics modeling, combined with optimization algorithms in model predictive control, the formation vehicle trajectory planning and control are completed to achieve dynamic obstacle avoidance; Guo et al[84]On the basis of the collaborative adaptive cruise control (PATH CACC) vehicle following algorithm, layered control and signal intersection optimization control modules have been added to accurately estimate vehicle status, monitor potential collision risks, optimize vehicle trajectories, and adjust signal timing.
The optimization of trajectory planning algorithms for networked autonomous driving is also crucial for safe operation, which helps to build obstacle avoidance mechanisms with higher safety performance, reduce collision risks, and minimize traffic accidents. Cheng et al[15]Based on the theory of virtual fluid dynamics, the upgraded lane keeping and obstacle avoidance control system optimizes the trajectory planning algorithm, ensuring the safety performance of smooth trajectories while avoiding obstacles; Khaitan et al[85]We use short-term prediction algorithms based on reachability analysis and long-term prediction algorithms using recursive least squares filters to build an obstacle avoidance framework that efficiently handles the uncertainty of dynamic obstacles in complex traffic environments and generates safe collision free trajectories in real time. With the development of complex nonlinear modeling techniques, machine learning and deep learning are gradually being applied to improve algorithms related to networked autonomous driving. Deguchi et al[86]Optimizing and upgrading the intelligent traffic sign detection system for connected autonomous vehicles based on adaptive learning methods to improve the accuracy of identifying signs and markings and reduce traffic safety hazards; Wang et al[87]Combining long short-term memory models and Bayesian inference to optimize lane change prediction algorithms for vehicle decision-making systems, in order to reduce driving perception errors; Grymin et al[88]Developed a locally greedy algorithm with efficient backtracking capability, optimized vehicle path planning and behavior control in complex traffic environments, and improved vehicle risk response capabilities; Xing et al[89]A driver behavior prediction model for multi-scale behavior recognition was established based on convolutional neural networks and recurrent neural networks to improve the driver behavior inference ability of intelligent vehicles. By learning the driving behavior of human drivers through artificial intelligence and enriching the perception scenarios of different modules of vehicles, networked autonomous vehicles can gain a comprehensive understanding of the physiological behavior of drivers and complex traffic environments[90]To enhance the performance of vehicle road safety, optimize vehicle path planning and behavior control, improve obstacle avoidance ability, improve the accuracy of intelligent traffic sign recognition, reduce driving perception errors, promote collaborative interaction with conventional vehicles, and reduce conflicts between humans and vehicle automation.
This cluster has a total of 26 keywords, including Automated Vehicles, Transportation, Impact, Security, Security, Risk, Mobility, Policy, Challenge, Privacy, Performance, Demand, etc. This cluster mainly focuses on the safety impact of autonomous vehicles on mixed traffic flow in an intelligent networked environment, as well as the security management challenges faced by autonomous vehicles in terms of technology, information, policies, and other aspects in practical applications, such asTable 5As shown.
应用领域 | 相关文献 | 主要研究内容 |
混合交通流运行效率 | [91] | 基于传统车辆与网联自动驾驶车辆的异质交通流模型分析不同渗透率下网联自动驾驶车辆对交通流量的影响 |
[92] | 通过驾驶模拟器研究网联自动驾驶车辆对常规车辆驾驶人交互行为影响 | |
[93] | 设计基于模糊规则的网联自动驾驶车辆运动控制系统促进与常规车辆的博弈合作 | |
[94] | 开发网联自动驾驶车辆情景感知安全控制模块解决城市交通网络中自动驾驶车辆和常规车辆交互冲突问题 | |
混合交通流事故分析 | [95] | 利用加利福尼亚州实车试验数据集分析网联自动驾驶车辆主要事故类型 |
[96] | 利用加利福尼亚州实车试验数据集探究影响自主驾驶模式脱离的影响因素 | |
其他方面安全管理问题 | [41]、[45] | 信息、性能、政策等安全管理挑战,包括法律保障、软件防护、隐私安全、城市发展 |
[97]、[98] |
In order to further explore the safety status of autonomous driving in actual traffic scenarios, multiple countries have allowed networked autonomous driving vehicles to conduct real vehicle tests on public roads. Some scholars have mined the road safety hazards of networked autonomous driving vehicles based on existing autonomous driving accident data. Arvin et al[95]The analysis of autonomous driving accidents in California shows that rear end collisions at intersections are the main type of accidents for connected autonomous vehicles, and the interaction and understanding between conventional vehicles and connected autonomous vehicles at intersections should be enhanced; Dixit et al[96]Using the California real vehicle test dataset to explore the factors affecting autonomous driving mode disengagement, it was found that human drivers' lack of trust in automatic disengagement of driving modes in emergency situations increases the likelihood of manually taking over the vehicle. As the vehicle's mileage increases, the level of trust increases and the response time to manual takeover also increases. In addition to operational safety issues in mixed traffic scenarios, connected autonomous vehicles also face security management challenges in terms of information, performance, policies, and software protection[45]Legal protection[41]Privacy and Security[97]Urban development[98].
应用场景 | 相关文献 | 主要研究内容 |
车辆交互 | [99] | 使用MATLAB构建仿真环境利用IDM模型模拟常规车辆跟驰行为、基于CACC跟驰机制确定自动驾驶车辆纵向决策操作,提出混合交通跟驰策略以识别整体机动性、安全性最佳的车队配置 |
[100] | 使用VISSIM构建微观仿真环境利用Wiedemann模型控制常规车辆跟车行为,基于规则控制算法对网联驾驶车辆行为部署,使用替代安全评估模块SSAM评估不同网联自动驾驶车辆渗透率对交通性能的影响 | |
[101] | 建立兼顾自动驾驶车辆平均车头时距和电子油门角度差的扩展跟驰模型,稳定自动驾驶车辆交通流、减少因交通流紊乱造成的车间冲突 | |
[102] | 综合考虑网联自动驾驶车辆轨迹控制、常规车辆跟驰和变道操作,添加自由变道约束设计基于变道感知轨迹优化的网联自动驾驶车辆跟驰模型,感知常规车辆轨迹变化以采取强制变道让步策略 | |
仿真测试 | [4]、[5]、[15] [103]、[104] | 基于仿真场景中车辆的微观驾驶行为和反馈信息对网联自动驾驶车辆进行自适应巡航控制、自动转向技术、避障轨迹规划、风险行为检测等安全系统设计 |
安全评估 | [12]、[105]~[110] | 虚拟测试和仿真模拟、数学建模与数字孪生、场景搭建和行为分析、驾驶模拟与试点测试等 |
人机共驾 | [111]~[117] | 人机共驾车辆控制权切换安全、接管能力评价指标选择、驾驶人接管能力影响因素、接管能力提升途径等 |
In addition to using micro simulation models to study vehicle interaction behavior, many scholars have used simulation methods to evaluate the safety of networked autonomous driving vehicles. Based on the micro driving behavior and feedback information of vehicles in simulation scenarios, adaptive cruise control has been applied to networked autonomous driving vehicles[4-5]Automatic steering technology[15]Obstacle avoidance trajectory planning[15]Risk behavior detection[103-104]Waiting for security system design. In the transitional stage of upgrading and deploying autonomous driving technology, the traditional method of judging the safety performance of networked autonomous vehicles based on travel and accident data is weak in feasibility. Developing safe and reliable alternative safety assessment methods, such as virtual testing and simulation, has gradually become a hot topic[12, 105-106]Mathematical Modeling and Digital Twin[107-108]Scene construction and behavior analysis[109]Driving simulation and pilot testing[110]Wait. The performance of driver takeover in the context of human-machine co driving is also a hot topic in this cluster, which integrates micro behavior modeling, traffic simulation, and driving simulation technologies for networked autonomous driving. The main content includes safe switching of control rights for human-machine co driving vehicles[111]Selection of evaluation indicators for takeover capability[112-113]Factors affecting the driver's ability to take over[114-115]Ways to enhance takeover capability[116-117]Wait. At present, research on takeover performance under human-machine co driving conditions mainly collects takeover behavior related data through driving simulators or traffic simulation experiments. The data sources and performance evaluation system need to be improved, and there is a lack of unified participant standards for the impact of driver attributes on takeover performance. The safety improvement methods for vehicle control switching still need to be considered from multiple aspects such as system design application scenarios, human-machine interaction forms, and driver takeover training standards.
(1) Construction of intelligent networked data-driven simulation environment and deep testing platform in virtual reality. The research on traffic flow safety and stability in both fully intelligent connected environments and human-machine hybrid driving environments still lacks sufficient real vehicle test data support, and the feasibility of relying on the traditional safety testing principle of "billions of vehicle kilometers" for road traffic safety research in intelligent connected autonomous driving is not highFigure 11The development process of the networked autonomous driving road traffic safety simulation environment and deep testing shown indicates that a key research direction in the future is to build an intelligent networked data-driven simulation environment and deep testing platform under virtual reality. In addition, the safety and stability of new hybrid macro micro traffic flow based on high-precision data-driven simulation and testing platforms is also a key research direction.
(2) Breakthrough in intelligent networked fleet group decision-making and formation control technology. The existing micro models of traffic flow are mainly based on the theoretical framework of traditional linear/nonlinear numerical analysis models, focusing on the risk analysis of autonomous driving single vehicle traffic accidents. They cannot accurately simulate the dynamic evolution law of the front and rear vehicles of networked autonomous driving vehicles in the new mixed traffic flow. Therefore, it is necessary to promote breakthroughs in group decision-making and formation control technology of networked autonomous driving fleets, build a new model of the correlation mechanism between micro driving behavior, traffic flow operation status, and accident risk in mixed traffic flow, optimize the existing vertical, same lane, and homogeneous fleet arrangement technology, deeply explore the theoretical methods of horizontal, multi lane, and heterogeneous fleet preparation, and improve the safety prediction effect of refined micro traffic flow models. Network attacks such as packet loss, signal blocking, and communication module damage will lead to the degradation of the communication topology of the fleet, and the stability of the vehicle formation will be affected. It is very important to integrate information security factors into the dynamic model of vehicle formation. In the future, targeted collaborative intelligent driving models will be developed to deal with different types of communication failures, dynamically adjust the weight of driving information, and enhance the safety of intelligent fleet operation.
(4) Quantitative assessment of traffic flow safety risks in networked autonomous driving. At present, the research on road traffic safety in connected autonomous driving lacks the support of accident databases. Most studies use simulation and data simulation methods, and focus on the risk assessment of single vehicle accidents in connected autonomous driving. The indicators used are the collision time TTC of traditional traffic conflicts and its derivative indicators, Time Exposed Time to Collision (TET) and Time Integrated Time to Collision (TIT)[118-120]Alternative security measures have been implemented, but the effectiveness of the indicators has not yet been verified. Therefore, it is urgent to verify the effectiveness and applicability of the indicators through large-scale data and experiments. In addition, there is a lack of quantitative conclusions for the macro/micro traffic flow safety risk assessment of connected autonomous driving. A key research direction in the future is to construct a quantitative indicator system and evaluation model and method to describe the traffic flow safety risks of connected autonomous driving.
(1) This article focuses on the issue of road traffic safety in networked autonomous driving. Based on the Web of Science database and relevant research at home and abroad in the past 10 years, using scientometric analysis methods and VOSviewer tools, a multi angle and complementary analysis of the research on road traffic safety in networked autonomous driving is conducted from the development context, research themes, and research hotspots. The scientific knowledge development process and structured network relationships related to international networked autonomous driving road traffic safety research in the past decade are described.
(3) The research on road traffic safety in connected autonomous driving includes three representative fields: micro behavior modeling and simulation of connected autonomous driving[69-70]Network connected autonomous driving traffic management and control, as well as system optimization[82-84]New hybrid traffic flow safety and risk management[92-94]After more than 10 years of rapid accumulation in both academic and industrial fields, remarkable achievements have been made in theoretical research, technological construction, and practical applications. Countries such as China, the United States, and Canada have also established large-scale testing bases with the goal of safe driving.
(4) In the early stage of the application of networked autonomous driving in the new mixed traffic stage, the virtual and real combination simulation of networked autonomous driving, the enhancement of vehicle road collaborative control system, the micro driving behavior model of swarm intelligence, and the operation control of heterogeneous traffic subject formation, etc[106-109]All of these are important research topics, and advanced technologies and methods such as big data modeling, artificial intelligence algorithms, and digital twins have shown broad application prospects in the study of road traffic safety in connected autonomous driving.
[1] |
ZHANG Ya-li. World health organization releases 2018 global status report on road safety[J]. Chinese Journal of Disaster Medicine, 2019, DOI:
|
[2] |
LI Ke-qiang, DAI Yi-fan, LI Sheng-bo, et al. State-of-the-art and technical trends of intelligent and connected vehicles[J]. Journal of Automotive Safety and Energy, 2017, 8(1): 1-14. (in Chinese) doi: 10.3969/j.issn.1674-8484.2017.01.001
|
[3] |
ZHANG Xing, SUN Hang. Analysis on taxonomy of driving automation for vehicles[J]. China Auto, 2022(5): 3-5, 7. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-CQGZ202205001.htm
|
[4] |
NAUS G J L, VUGTS R P A, PLOEG J, et al. String-stable CACC design and experimental validation: a frequency-domain approach[J]. IEEE Transactions on Vehicular Technology, 2010, 59(9): 4268-4279. doi: 10.1109/TVT.2010.2076320
|
[5] |
MILANES V, SHLADOVER S E, SPRING J, et al. Cooperative adaptive cruise control in real traffic situations[J]. IEEE Transactions on Intelligent Transportation Systems, 2013, 15(1): 296-305.
|
[6] |
PLOEG J, SHUKLA D P, VAN DE WOUW N, et al. Controller synthesis for string stability of vehicle platoons[J]. IEEE Transactions on Intelligent Transportation Systems, 2013, 15(2): 854-865.
|
[7] |
DRESNER K, STONE P. A multiagent approach to autonomous intersection management[J]. Journal of Artificial Intelligence Research, 2008, 31: 591-656. doi: 10.1613/jair.2502
|
[8] |
FENG Y, HEAD K L, KHOSHMAGHAM S, et al. A real-time adaptive signal control in a connected vehicle environment[J]. Transportation Research Part C: Emerging Technologies, 2015, 55: 460-473. doi: 10.1016/j.trc.2015.01.007
|
[9] |
GULER S I, MENENDEZ M, MEIER L. Using connected vehicle technology to improve the efficiency of intersections[J]. Transportation Research Part C: Emerging Technologies, 2014, 46: 121-131. doi: 10.1016/j.trc.2014.05.008
|
[10] |
GOODALL N J, SMITH B L, PARK B. Traffic signal control with connected vehicles[J]. Transportation Research Record, 2013(2381): 65-72.
|
[11] |
KESTING A, TREIBER M, HELBING D. Enhanced intelligent driver model to access the impact of driving strategies on traffic capacity[J]. Philosophical Transactions of the Royal Society A: Mathematical Physical and Engineering Sciences, 2010, 368(1928): 4585-4605. doi: 10.1098/rsta.2010.0084
|
[12] |
RAJU N, FARAH H. Evolution of traffic microsimulation and its use for modeling connected and automated vehicles[J]. Journal of Advanced Transportation, 2021, DOI: 10.1155/2021/2444363.
|
[13] |
CAO Xuan-hao, TIAN Yan-tao, JI Xue-wu, et al. Fault-tolerant controller design for path following of the autonomous vehicle under the faults in braking actuators[J]. IEEE Transactions on Transportation Electrification, 2021, 7(4): 2530-2540. doi: 10.1109/TTE.2021.3071725
|
[14] |
HANG Peng, CHEN Xin-bo, LUO Feng-mei. LPV/H-infinity controller design for path tracking of autonomous ground vehicles through four-wheel steering and direct yaw-moment control[J]. International Journal of Automotive Technology, 2019, 20(4): 679-691. doi: 10.1007/s12239-019-0064-1
|
[15] |
CHENG Shuo, LI Liang, LIU Yong-gang, et al. Virtual fluid-flow-model-based lane-keeping integrated with collision avoidance control system design for autonomous vehicles[J]. IEEE Transactions on Intelligent Transportation Systems, 2021, 22(10): 6232-6241. doi: 10.1109/TITS.2020.2990211
|
[16] |
GONZALEZ D, PEREZ J, MILANES V, et al. A review of motion planning techniques for automated vehicles[J]. IEEE Transactions on Intelligent Transportation Systems, 2015, 17(4): 1135-1145.
|
[17] |
VAN BRUMMELEN J, O'BRIEN M, GRUYER D, et al. Autonomous vehicle perception: the technology of today and tomorrow[J]. Transportation Research Part C: Emerging Technologies, 2018, 89: 384-406. doi: 10.1016/j.trc.2018.02.012
|
[18] |
BATSCH F, KANARACHOS S, CHEAH M, et al. A taxonomy of validation strategies to ensure the safe operation of highly automated vehicles[J]. Journal of Intelligent Transportation Systems, 2021, 26(1): 14-33. http://www.xueshufan.com/publication/3010764092
|
[19] |
BONNEFON J F, SHARIFF A, RAHWAN I. The social dilemma of autonomous vehicles[J]. Science, 2016, 352(6293): 1573-1576. doi: 10.1126/science.aaf2654
|
[20] |
LE V H, HARTOG J D, ZANNONE N. Security and privacy for innovative automotive applications: a survey[J]. Computer Communications, 2018, 132: 17-41. doi: 10.1016/j.comcom.2018.09.010
|
[21] |
MILAKIS D, VAN AREM B, VAN WEE B. Policy and society related implications of automated driving: a review of literature and directions for future research[J]. Journal of Intelligent Transportation Systems, 2017, 21(4): 324-348. doi: 10.1080/15472450.2017.1291351
|
[22] |
TEOH E R, KIDD D G. Rage against the machine? Google's self-driving cars versus human drivers[J]. Journal of Safety Research, 2017, 63: 57-60. doi: 10.1016/j.jsr.2017.08.008
|
[23] |
PENMETSA P, SHEINIDASHTEGOL P, MUSAEV A, et al. Effects of the autonomous vehicle crashes on public perception of the technology[J]. IATSS Research, 2021, 45(4): 485-492. doi: 10.1016/j.iatssr.2021.04.003
|
[24] |
LI Chong-sen, WANG Yao. The development of autonomous driving from NIO ES8 accident[J]. Auto Review, 2021(9): 8-13. (in Chinese) doi: 10.3969/j.issn.2095-1892.2021.09.002
|
[25] |
PETTY K F, NOEIMI H, SANWAL K, et al. The freeway service patrol evaluation project: database support programs, and accessibility[J]. Transportation Research Part C: Emerging Technologies, 1996, 4(2): 71-85. doi: 10.1016/0968-090X(96)00001-0
|
[26] |
VAN ECK N J, WALTMAN L. Software survey: VOSviewer, a computer program for bibliometric mapping[J]. Scientometrics, 2010, 84(2): 523-538. doi: 10.1007/s11192-009-0146-3
|
[27] |
CHENG Hui-rong, ZHANG Xiao-yang, SUN Tan, et al. A quantitative analysis of ontology research articles based on web of science[J]. Data Analysis and Knowledge Discovery, 2006(11): 46-50. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-XDTQ200611011.htm
|
[28] |
GLASER S, VANHOLME B, MAMMAR S, et al. Maneuver-based trajectory planning for highly autonomous vehicles on real road with traffic and driver interaction[J]. IEEE Transactions on Intelligent Transportation Systems, 2010, 11(3): 589-606. doi: 10.1109/TITS.2010.2046037
|
[29] |
REINA G, MILELLA A. FLane: an adaptive fuzzy logic lane tracking system for driver assistance[J]. Journal of Dynamic Systems, Measurement, and Control, 2011, 133(2): 1-11.
|
[30] |
MARKVOLLRAT H, SCHLEICHER S, GELAU C. The influence of cruise control and adaptive cruise control on driving behaviour—a driving simulator study[J]. Accident Analysis and Prevention, 2011, 43(3): 1134-1139. doi: 10.1016/j.aap.2010.12.023
|
[31] |
MILANES V, LLORCA D F, VILLAGRA J, et al. Intelligent automatic overtaking system using vision for vehicle detection[J]. Expert Systems with Applications, 2012, 39(3): 3362-3373. doi: 10.1016/j.eswa.2011.09.024
|
[32] |
FAJARDO D, AU T C, WALLER S T, et al. Automated intersection control: performance of future innovation versus current traffic signal control[J]. Transportation Research Record, 2011(2259): 223-232.
|
[33] |
VASIRANI M, OSSOWSKI S. Learning and coordination for autonomous intersection control[J]. Applied Artificial Intelligence, 2011, 25(3): 193-216. doi: 10.1080/08839514.2011.551318
|
[34] |
FURDA A, VLACIC L. Enabling safe autonomous driving in real-world city traffic using multiple criteria decision making[J]. IEEE Intelligent Transportation Systems Magazine, 2011, 3(1): 4-17. doi: 10.1109/MITS.2011.940472
|
[35] |
VERES S M, MOLNAR L, LINCOLN N K, et al. Autonomous vehicle control systems—a review of decision making[J]. Journal of Systems and Control Engineering, 2011, 225(2): 155-195.
|
[36] |
MILANES V, GONZALEZ C, NARANJO J E, et al. Electro-hydraulic braking system for autonomous vehicles[J]. International Journal of Automotive Technology, 2010, 11(1): 89-95. doi: 10.1007/s12239-010-0012-6
|
[37] |
KIM E, KIM J, SUNWOO M. Model predictive control strategy for smooth path tracking of autonomous vehicles with steering actuator dynamics[J]. International Journal of Automotive Technology, 2014, 15(7): 1155-1164. doi: 10.1007/s12239-014-0120-9
|
[38] |
KAMAL M A S, IMURA J, HAYAKAWA T, et al. Smart driving of a vehicle using model predictive control for improving traffic flow[J]. IEEE Transactions on Intelligent Transportation Systems, 2014, 15(2): 878-888. doi: 10.1109/TITS.2013.2292500
|
[39] |
LIN C F, JUANG J C, LI K R. Active collision avoidance system for steering control of autonomous vehicles[J]. IET Intelligent Transport Systems, 2014, 8(6): 550-557. doi: 10.1049/iet-its.2013.0056
|
[40] |
XU Li-jian, WANG Le-yi, YIN G, et al. Communication information structures and contents for enhanced safety of highway vehicle platoons[J]. IEEE Transactions on Vehicular Technology, 2014, 63(9): 4206-4220. doi: 10.1109/TVT.2014.2311384
|
[41] |
FAGNANT D J, KOCKELMAN K. Preparing a nation for autonomous vehicles: opportunities, barriers and policy recommendations[J]. Transportation Research Part A: Policy and Practice, 2015, 77: 167-181. doi: 10.1016/j.tra.2015.04.003
|
[42] |
LEVIN M W, BOYLES S D. Effects of autonomous vehicle ownership on trip, mode, and route choice[J]. Transportation Research Record, 2015(2493): 29-38.
|
[43] |
GHIASI A, HUSSAIN O, QIAN Z S, et al. A mixed traffic capacity analysis and lane management model for connected automated vehicles: a Markov chain method[J]. Transportation Research Part B: Methodological, 2017, 106: 266-292. doi: 10.1016/j.trb.2017.09.022
|
[44] |
BAGLOEE S A, SARVI M, PATRIKSSON M, et al. A mixed user-equilibrium and system-optimal traffic flow for connected vehicles stated as a complementarity problem[J]. Computer-Aided Civil and Infrastructure Engineering, 2017, 32(7): 562-580. doi: 10.1111/mice.12261
|
[45] |
PETIT J, SHLADOVER S E. Potential cyberattacks on automated vehicles[J]. IEEE Transactions on Intelligent Transportation Systems, 2014, 16(2): 546-556.
|
[46] |
PARKINSON S, WARD P, WILSON K, et al. Cyber threats facing autonomous and connected vehicles: future challenges[J]. IEEE Transactions on Intelligent Transportation Systems, 2017, 18(11): 2898-2915. doi: 10.1109/TITS.2017.2665968
|
[47] |
HUANG Zi-chao, CHU Duan-feng, WU Chao-zhong, et al. Path planning and cooperative control for automated vehicle platoon using hybrid automata[J]. IEEE Transactions on Intelligent Transportation Systems, 2019, 20(3): 959-974. doi: 10.1109/TITS.2018.2841967
|
[48] |
YANG Jun-ru, PENG Wei-feng, SUN Chuan. A learning control method of automated vehicle platoon at straight path with DDPG-based PID[J]. Electronics, 2021, DOI: 10.3390/electronics10212580.
|
[49] |
GUNTER G, GLOUDEMANS D, STERN R E, et al. Are commercially implemented adaptive cruise control systems string stable?[J]. IEEE Transactions on Intelligent Transportation Systems, 2021, 22(11): 6992-7003. doi: 10.1109/TITS.2020.3000682
|
[50] |
JIANG Xiao-bei, WANG Wu-hong, BENGLER K, et al. Analysis of drivers' performance in response to potential collision with pedestrians at urban crosswalks[J]. IET Intelligent Transport Systems, 2017, 11(9): 546-552. doi: 10.1049/iet-its.2016.0344
|
[51] |
HE Ying, ZHAO Nan, YIN Hong-xi. Integrated networking, caching, and computing for connected vehicles: a deep reinforcement learning approach[J]. IEEE Transactions on Vehicular Technology, 2017, 67(1): 44-55.
|
[52] |
CAI Xiu-zhang, GIALLORENZO M, SARABANDI K. Machine learning-based target classification for MMW radar in autonomous driving[J]. IEEE Transactions on Intelligent Vehicles, 2021, 6(4): 678-689. doi: 10.1109/TIV.2020.3048944
|
[53] |
DEB S, STRAWDERMAN L, CARRUTH D W, et al. Development and validation of a questionnaire to assess pedestrian receptivity toward fully autonomous vehicles[J]. Transportation Research Part C: Emerging Technologies, 2017, 84: 178-195. doi: 10.1016/j.trc.2017.08.029
|
[54] |
TREIBER M, HENNECKE A, HELBING D. Congested traffic states in empirical observations and microscopic simulations[J]. Physical Review E, 2000, 62(2): 1805-1824. doi: 10.1103/PhysRevE.62.1805
|
[55] |
Hoedemaeker D M. Driving with intelligent vehicles: driving behaviour with adaptive cruise control and the acceptance by individual drivers[D]. Delft: Delft University of Technology, 1999.
|
[56] |
GIRARD A R, DE SOUSA J B, MISENER J A, et al. A control architecture for integrated cooperative cruise control and collision warning systems[C]//IEEE. Proceedings of the 40th IEEE Conference on Decision and Control. New York: IEEE, 2001: 1491-1496.
|
[57] |
VAN AREM B, VAN DRIEL C J G, VISSER R. The impact of cooperative adaptive cruise control on traffic-flow characteristics[J]. IEEE Transactions on Intelligent Transportation Systems, 2006, 7(4): 429-436. doi: 10.1109/TITS.2006.884615
|
[58] |
SHLADOVER S E, SU D Y, LU X Y. Impacts of cooperative adaptive cruise control on freeway traffic flow[J]. Transportation Research Record, 2012(2324): 63-70.
|
[59] |
USMAN G, KUNWAR F. Autonomous vehicle overtaking-an online solution[C]//IEEE. 2009 IEEE International Conference on Automation and Logistics. New York: IEEE, 2009: 596-601.
|
[60] |
LIU Kai, GONG Jian-wei, KURT A, et al. Dynamic modeling and control of high-speed automated vehicles for lane change maneuver[J]. IEEE Transactions on Intelligent Vehicles, 2018, 3(3): 329-339. doi: 10.1109/TIV.2018.2843177
|
[61] |
WANG Hao-ran, LAI Jin-tao, ZHANG Xian-hong, et al. Make space to change lane: a cooperative adaptive cruise control lane change controller[J]. Transportation Research Part C: Emerging Technologies, 2022, 143: 103847. doi: 10.1016/j.trc.2022.103847
|
[62] |
TALEBPOUR A, MAHMASSANI H S. Influence of connected and autonomous vehicles on traffic flow stability and throughput[J]. Transportation Research Part C: Emerging Technologies, 2016, 71: 143-163. doi: 10.1016/j.trc.2016.07.007
|
[63] |
CHEN Dan-jue, AHN S, CHITTURI M, et al. Towards vehicle automation: roadway capacity formulation for traffic mixed with regular and automated vehicles[J]. Transportation Research Part B: Methodological, 2017, 100: 196-221. doi: 10.1016/j.trb.2017.01.017
|
[64] |
FAGNANT D J, KOCKELMAN K M. The travel and environmental implications of shared autonomous vehicles, using agent-based model scenarios[J]. Transportation Research Part C: Emerging Technologies, 2014, 40: 1-13. doi: 10.1016/j.trc.2013.12.001
|
[65] |
KYRIAKIDIS M, HAPPEE R, DE WINTER J C F. Public opinion on automated driving: results of an international questionnaire among 5 000 respondents[J]. Transportation Research Part F: Traffic Psychology and Behaviour, 2015, 32: 127-140. doi: 10.1016/j.trf.2015.04.014
|
[66] |
HABOUCHA C J, ISHAQ R, SHIFTAN Y. User preferences regarding autonomous vehicles[J]. Transportation Research Part C: Emerging Technologies, 2017, 78: 37-49. doi: 10.1016/j.trc.2017.01.010
|
[67] |
PADEN B, CAP M, YONG S Z, et al. A survey of motion planning and control techniques for self-driving urban vehicles[J]. IEEE Transactions on Intelligent Vehicles, 2016, 1(1): 33-55. doi: 10.1109/TIV.2016.2578706
|
[68] |
KATRAKAZAS C, QUDDUS M, CHEN W H, et al. Real-time motion planning methods for autonomous on-road driving: state-of-the-art and future research directions[J]. Transportation Research Part C: Emerging Technologies, 2015, 60: 416-442. doi: 10.1016/j.trc.2015.09.011
|
[69] |
WANG Chen, XIE Yuan-chang, HUANG He-lai, et al. A review of surrogate safety measures and their applications in connected and automated vehicles safety modeling[J]. Accident Analysis and Prevention, 2021, 157: 106157. doi: 10.1016/j.aap.2021.106157
|
[70] |
ASLJUNG D, NILSSON J, FREDRIKSSON J. Using extreme value theory for vehicle level safety validation and implications for autonomous vehicles[J]. IEEE Transactions on Intelligent Vehicles, 2017, 2(4): 288-297. doi: 10.1109/TIV.2017.2768219
|
[71] |
FERNANDES P, NUNES U. Multiplatooning leaders positioning and cooperative behavior algorithms of communicant automated vehicles for high traffic capacity[J]. IEEE Transactions on Intelligent Transportation Systems, 2014, 16(3): 1172-1187.
|
[72] |
WANG Huan-jie, YUAN Shi-hua, GUO Meng-yu, et al. A deep reinforcement learning-based approach for autonomous driving in highway on-ramp merge[J]. Journal of Automobile Engineering, 2021, 235(10/11): 2726-2739.
|
[73] |
WANG Xue-song, QIN Ding-ming, CAFISO S, et al. Operational design domain of autonomous vehicles at skewed intersection[J]. Accident Analysis and Prevention, 2021, 159: 106241. doi: 10.1016/j.aap.2021.106241
|
[74] |
CHEN Si-kai, DONG Ji-qian, HA P, et al. Graph neural network and reinforcement learning for multi-agent cooperative control of connected autonomous vehicles[J]. Computer-Aided Civil and Infrastructure Engineering, 2021, 36(7): 838-857. doi: 10.1111/mice.12702
|
[75] |
FU Xing, NIE Qi-fan, LIU Jun, et al. Constructing spatiotemporal driving volatility profiles for connected and automated vehicles in existing highway networks[J]. Journal of Intelligent Transportation Systems, 2022, 26(5): 1-14.
|
[76] |
DESIRAJU D, CHANTEM T, HEASLIP K. Minimizing the disruption of traffic flow of automated vehicles during lane changes[J]. IEEE Transactions on Intelligent Transportation Systems, 2014, 16(3): 1249-1258.
|
[77] |
RAHMAN M S, ABDEL-ATY M. Longitudinal safety evaluation of connected vehicles' platooning on expressways[J]. Accident Analysis and Prevention, 2018, 117: 381-391. doi: 10.1016/j.aap.2017.12.012
|
[78] |
ZHOU Fang, LI Xiao-peng, MA Jia-qi. Parsimonious shooting heuristic for trajectory design of connected automated traffic Part Ⅰ: theoretical analysis with generalized time geography[J]. Transportation Research Part B: Methodological, 2017, 95: 394-420. doi: 10.1016/j.trb.2016.05.007
|
[79] |
MA Jia-qi, LI Xiao-peng, ZHOU Fang, et al. Parsimonious shooting heuristic for trajectory design of connected automated traffic Part Ⅱ: computational issues and optimization[J]. Transportation Research Part B: Methodological, 2017, 95: 421-441. doi: 10.1016/j.trb.2016.06.010
|
[80] |
LEE J, PARK B B, MALAKORN K, et al. Sustainability assessments of cooperative vehicle intersection control at an urban corridor[J]. Transportation Research Part C: Emerging Technologies, 2013, 32: 193-206. doi: 10.1016/j.trc.2012.09.004
|
[81] |
JIANG Yang-sheng, ZHAO Bin, LIU Meng, et al. A two-level model for traffic signal timing and trajectories planning of multiple CAVs in a random environment[J]. Journal of Advanced Transportation, 2021, 2021: 1-13.
|
[82] |
GUO Qiang-qiang, LI Li, BAN X G. Urban traffic signal control with connected and automated vehicles: a survey[J]. Transportation Research Part C: Emerging Technologies, 2019, 101: 313-334. doi: 10.1016/j.trc.2019.01.026
|
[83] |
KATO S, TSUGAWA S, TOKUDA K, et al. Vehicle control algorithms for cooperative driving with automated vehicles and intervehicle communications[J]. IEEE Transactions on Intelligent Transportation Systems, 2002, 3(3): 155-161. doi: 10.1109/TITS.2002.802929
|
[84] |
GUO Yi, MA Jia-qi. DRL-TP3: a learning and control framework for signalized intersections with mixed connected automated traffic[J]. Transportation Research Part C: Emerging Technologies, 2021, 132: 103416. doi: 10.1016/j.trc.2021.103416
|
[85] |
KHAITAN S, LIN Q, DOLAN J M. Safe planning and control under uncertainty for self-driving[J]. IEEE Transactions on Vehicular Technology, 2021, 70(10): 9826-9837. doi: 10.1109/TVT.2021.3108525
|
[86] |
DEGUCHI D, SHIRASUNA M, DOMAN K, et al. Intelligent traffic sign detector: adaptive learning based on online gathering of training samples[C]//IEEE. 2011 IEEE Intelligent Vehicles Symposium (Ⅳ). New York: IEEE, 2011: 72-77.
|
[87] |
WANG Jing-hua, ZHANG Zhao, LU Guang-quan. A Bayesian inference based adaptive lane change prediction model[J]. Transportation Research Part C: Emerging Technologies, 2021, 132: 103363. doi: 10.1016/j.trc.2021.103363
|
[88] |
GRYMIN D J, NEAS C B, FARHOOD M. A hierarchical approach for primitive-based motion planning and control of autonomous vehicles[J]. Robotics and Autonomous Systems, 2014, 62(2): 214-228. doi: 10.1016/j.robot.2013.10.003
|
[89] |
XING Yang, LYU Chen, CAO Dong-pu, et al. Multi-scale driver behavior modeling based on deep spatial-temporal representation for intelligent vehicles[J]. Transportation Research Part C: Emerging Technologies, 2021, 130: 103288. doi: 10.1016/j.trc.2021.103288
|
[90] |
NAGAHAMA A, SAITO T, WADA T, et al. Autonomous driving learning preference of collision avoidance maneuvers[J]. IEEE Transactions on Intelligent Transportation Systems, 2020, 22(9): 5624-5634.
|
[91] |
YE Lan-hang, YAMAMOTO T, MORIKAWA T. Heterogeneous traffic flow dynamics under various penetration rates of connected and autonomous vehicle[C]//IEEE. 21st IEEE International Conference on Intelligent Transportation Systems (ITSC). New York: IEEE, 2018: 555-559.
|
[92] |
RAD S R, FARAH H, TAALE H, et al. The impact of a dedicated lane for connected and automated vehicles on the behaviour of drivers of manual vehicles[J]. Transportation Research Part F: Traffic Psychology and Behaviour, 2021, 82: 141-153. doi: 10.1016/j.trf.2021.08.010
|
[93] |
ONIEVA E, MILANES V, VILLAGRA J, et al. Genetic optimization of a vehicle fuzzy decision system for intersections[J]. Expert Systems with Applications, 2012, 39(18): 13148-13157. doi: 10.1016/j.eswa.2012.05.087
|
[94] |
KHAN S M, CHOWDHURY M. Situation-aware left-turning connected and automated vehicle operation at signalized intersections[J]. IEEE Internet of Things Journal, 2021, 8(16): 13077-13094. doi: 10.1109/JIOT.2021.3064041
|
[95] |
ARVIN R, KHATTAK A J, KAMRANI M, et al. Safety evaluation of connected and automated vehicles in mixed traffic with conventional vehicles at intersections[J]. Journal of Intelligent Transportation Systems, 2020, 25(2): 170-187.
|
[96] |
DIXIT V V, CHAND S, NAIR D J. Autonomous vehicles: disengagements, accidents and reaction times[J]. PlosOne, 2016, 11(12): 168054.
|
[97] |
CELINA K, FLORIAN K, TOBIAS V. Consequences of autonomous vehicles: ambivalent expectations and their impact on acceptance[J]. Transportation Research Part F: Traffic Psychology and Behaviour, 2021, 81: 282-294. doi: 10.1016/j.trf.2021.06.004
|
[98] |
NADAFIANSHAHAMABADI R, TAYARANI M, ROWANGOULD G. A closer look at urban development under the emergence of autonomous vehicles: traffic, land use and air quality impacts[J]. Journal of Transport Geography, 2021, 94: 103113. doi: 10.1016/j.jtrangeo.2021.103113
|
[99] |
SERAJ M, LI Jiang-chen, QIU Zhi-jun. Modeling microscopic car-following strategy of mixed traffic to identify optimal platoon configurations for multiobjective decision-making[J]. Journal of Advanced Transportation, 2018, DOI: 10.1155/2018/7835010.
|
[100] |
VIRDI N, GRZYBOWSKA H, WALLER S T, et al. A safety assessment of mixed fleets with connected and autonomous vehicles using the surrogate safety assessment module[J]. Accident Analysis and Prevention, 2019, 131: 95-111. doi: 10.1016/j.aap.2019.06.001
|
[101] |
CHEN Liang, ZHANG Yun, LI Kun, et al. Car-following model of connected and autonomous vehicles considering both average headway and electronic throttle angle[J]. Modern Physics Letters B, 2021, 35(15): 2150257. doi: 10.1142/S0217984921502572
|
[102] |
YAO Han-dong, LI Xiao-peng. Lane-change-aware connected automated vehicle trajectory optimization at a signalized i ntersection with multi-lane roads[J]. Transportation Research Part C: Emerging Technologies, 2021, 129: 103182. doi: 10.1016/j.trc.2021.103182
|
[103] |
RYAN C, MURPHY F, MULLINS M. End-to-end autonomous driving risk analysis: a behavioural anomaly detection approach[J]. IEEE Transactions on Intelligent Transportation Systems, 2021, 22(3): 1650-1662. doi: 10.1109/TITS.2020.2975043
|
[104] |
MATTAS K, MAKRIDIS M, BOTZORIS G, et al. Fuzzy surrogate safety metrics for real-time assessment of rear-end collision risk. A study based on empirical observations[J]. Accident Analysis and Prevention, 2020, 148: 105794. doi: 10.1016/j.aap.2020.105794
|
[105] |
KHASTGIR S, BIRRELL S, DHADYALLA G, et al. Development of a drive-in driver-in-the-loop fully immersive driving simulator for virtual validation of automotive systems[C]//IEEE. 2015 IEEE 81st Vehicular Technology Conference (VTC Spring). New York: IEEE, 2015: 1-4.
|
[106] |
XING Yang, LYU Chen, MO Xiao-yu, et al. Toward safe and smart mobility: energy-aware deep learning for driving behavior analysis and prediction of connected vehicles[J]. IEEE Transactions on Intelligent Transportation Systems, 2021, 22(7): 4267-4280. doi: 10.1109/TITS.2021.3052786
|
[107] |
OSMAN O A, ISHAK S. Prediction of travel time estimation accuracy in connected vehicle environments[C]//Springer. 2017 International Congress and Exhibition " Sustainable Civil Infrastructures: Innovative Infrastructure Geotechnology". Berlin: Springer, 2017: 72-87.
|
[108] |
LI Yang, WANG Jian-qiang, WU Jian. Model calibration concerning risk coefficients of driving safety field model[J]. Journal of Central South University, 2017, 24(6): 1494-1502. doi: 10.1007/s11771-017-3553-2
|
[109] |
WANG Hua, MENG Qiang, CHEN Shu-kai, et al. Competitive and cooperative behaviour analysis of connected and autonomous vehicles across unsignalised intersections: a game-theoretic approach[J]. Transportation Research Part B: Methodological, 2021, 149: 322-346. doi: 10.1016/j.trb.2021.05.007
|
[110] |
PAPAKOSTOPOULOS V, NATHANAEL D, PORTOULI E, et al. Effect of external HMI for automated vehicles (AVs) on drivers' ability to infer the AV motion intention: a field experiment[J]. Transportation Research Part F: Traffic Psychology and Behaviour, 2021, 82: 32-42. doi: 10.1016/j.trf.2021.07.009
|
[111] |
CASNER S M, HUTCHINS E L, NORMAN D. The challenges of partially automated driving[J]. Communications of the ACM, 2016, 59(5): 70-77. doi: 10.1145/2830565
|
[112] |
ALREFAIE M T, SUMMERSKILL S, JACKON T W. In a heart beat: using driver's physiological changes to determine the quality of a takeover in highly automated vehicles[J]. Accident Analysis and Prevention, 2019, 131: 180-190. doi: 10.1016/j.aap.2019.06.011
|
[113] |
VOGELPOHL T, KÜHN M, HUMMEL T, et al. Asleep at the automated wheel—sleepiness and fatigue during highly automated driving[J]. Accident Analysis and Prevention, 2019, 126: 70-84. doi: 10.1016/j.aap.2018.03.013
|
[114] |
YOON S H, KIM Y W, JI Y G. The effects of takeover request modalities on highly automated car control transitions[J]. Accident Analysis and Prevention, 2019, 123: 150-158. doi: 10.1016/j.aap.2018.11.018
|
[115] |
BRANDENBURG S, CHUANG L. Take-over requests during highly automated driving: how should they be presented and under what conditions?[J]. Transportation Research Part F: Traffic Psychology and Behaviour, 2019, 66: 214-225. doi: 10.1016/j.trf.2019.08.023
|
[116] |
ZEEB K, BUCHNER A, SCHRAUF M. What determines the take-over time? An integrated model approach of driver take-over after automated driving[J]. Accident Analysis and Prevention, 2015, 78: 212-221. doi: 10.1016/j.aap.2015.02.023
|
[117] |
SPORTILLO D, PALJIC A, OJEDA L. Get ready for automated driving using virtual reality[J]. Accident Analysis and Prevention, 2018, 118: 102-113. doi: 10.1016/j.aap.2018.06.003
|
[118] |
GUO Yan-yong, LIU Pan, WU Yao, et al. Safety evaluation of unconventional signalized intersection based on traffic conflict extreme model[J]. China Journal of Highway and Transport, 2022, 35(1): 85-92. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-ZGGL202201008.htm
|
[119] |
GUO Yan-yong, LIU Pan, WU Yao, et al. Bayesian traffic conflict model accounting for heterogeneity[J]. China Journal of Highway and Transport, 2018, 31(4): 296-303. (in Chinese) doi: 10.3969/j.issn.1001-7372.2018.04.034
|
[120] |
GUO Yan-yong, LIU Pan, WU Yao, et al. Traffic conflict model based on Bayesian multivariate Poisson-lognormal normal distribution[J]. China Journal of Highway and Transport, 2018, 31(1): 101-109. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-ZGGL201801013.htm
|
[1] | ZHU Xu, SUN Zhuo, ZHANG Ze-hua, YAN Mao-de. Stability of vehicle platoon control system with three types of delays[J]. Journal of Traffic and Transportation Engineering, 2024, 24(2): 254-266. doi: 10.19818/j.cnki.1671-1637.2024.02.018 |
[2] | CUI Jian-xun, YAO Jia, ZHAO Bo-yuan. Review on short-term traffic flow prediction methods based on deep learning[J]. Journal of Traffic and Transportation Engineering, 2024, 24(2): 50-64. doi: 10.19818/j.cnki.1671-1637.2024.02.003 |
[3] | HUANG He, LI Wen-long, YANG Lan, WANG Hui-feng, RU Feng, GAO Tao. Vehicle long-term target tracker optimized by improved carnivorous plant algorithm[J]. Journal of Traffic and Transportation Engineering, 2023, 23(6): 283-300. doi: 10.19818/j.cnki.1671-1637.2023.06.019 |
[4] | ZHAO Xiang-mo's team supported by the National Key Research and Development Program of China (2021YFB2501200). Research progress in testing and evaluation technologies for autonomous driving[J]. Journal of Traffic and Transportation Engineering, 2023, 23(6): 10-77. doi: 10.19818/j.cnki.1671-1637.2023.06.002 |
[5] | HAO Wei, ZHANG Zhao-lei, WU Qi-yu, YI Ke-fu. Lane-changing decision model of connected and automated vehicles driving off ramp[J]. Journal of Traffic and Transportation Engineering, 2023, 23(5): 242-252. doi: 10.19818/j.cnki.1671-1637.2023.05.017 |
[6] | PENG Jia-li, SHANGGUAN Wei, CHAI Lin-guo, QIU Wei-zhi. Car-following model and optimization strategy for connected and automated vehicles under mixed traffic environment[J]. Journal of Traffic and Transportation Engineering, 2023, 23(3): 232-247. doi: 10.19818/j.cnki.1671-1637.2023.03.018 |
[7] | QIN Yan-yan, LUO Qin-zhong, HE Zheng-bing. Management and control method of dedicated lanes for mixed traffic flows with connected and automated vehicles[J]. Journal of Traffic and Transportation Engineering, 2023, 23(3): 221-231. doi: 10.19818/j.cnki.1671-1637.2023.03.017 |
[8] | ZHU Xu, ZHANG Ze-hua, YAN Mao-de. Stability of PID control system for vehicle platoon with input delay and communication delay[J]. Journal of Traffic and Transportation Engineering, 2022, 22(3): 184-198. doi: 10.19818/j.cnki.1671-1637.2022.03.015 |
[9] | ZHANG Yi, PEI Hua-xin, YAO Dan-ya. Research review on cooperative decision-making for vehicle swarms in vehicle-infrastructure cooperative environment[J]. Journal of Traffic and Transportation Engineering, 2022, 22(3): 1-18. doi: 10.19818/j.cnki.1671-1637.2022.03.001 |
[10] | QU Xu, GAN Rui, AN Bo-cheng, LI Lin-heng, CHEN Zhi-jun, RAN Bin. Prediction of traffic swarm movement situation based on generalized spatio-temporal graph convolution network[J]. Journal of Traffic and Transportation Engineering, 2022, 22(3): 79-88. doi: 10.19818/j.cnki.1671-1637.2022.03.006 |
[11] | CHEN Ting, YAO Da-chun, GAO Tao, QIU Hui-hui, GUO Chang-xin, LIU Zhan-wen, LI Yong-hui, BIAN Hao-yi. A fused network based on PReNet and YOLOv4 for traffic object detection in rainy environment[J]. Journal of Traffic and Transportation Engineering, 2022, 22(3): 225-237. doi: 10.19818/j.cnki.1671-1637.2022.03.018 |
[12] | ZHAO Tong, SHANGGUAN Wei, CHAI Lin-guo, GUO Peng. Scenario factor analysis and test case generation for vehicle-infrastructure cooperative mixed traffic[J]. Journal of Traffic and Transportation Engineering, 2022, 22(3): 263-276. doi: 10.19818/j.cnki.1671-1637.2022.03.021 |
[13] | SHANGGUAN Wei, LI Xin, CHAI Lin-guo, CAO Yue, CHEN Jing-jing, PANG Hao-jie, RUI Tao. Research review on simulation and test of mixed traffic swarm in vehicle-infrastructure cooperative environment[J]. Journal of Traffic and Transportation Engineering, 2022, 22(3): 19-40. doi: 10.19818/j.cnki.1671-1637.2022.03.002 |
[14] | MA Yong-jie, CHENG Shi-sheng, MA Yun-ting, MA Yi-de. Review of convolutional neural network and its application in intelligent transportation system[J]. Journal of Traffic and Transportation Engineering, 2021, 21(4): 48-71. doi: 10.19818/j.cnki.1671-1637.2021.04.003 |
[15] | CHEN Xiao-bo, CHEN Cheng, CHEN Lei, WEI Zhong-jie, CAI Ying-feng, ZHOU Jun-jie. Interpolation method of traffic volume missing data based on improved low-rank matrix completion[J]. Journal of Traffic and Transportation Engineering, 2019, 19(5): 180-190. doi: 10.19818/j.cnki.1671-1637.2019.05.018 |
[16] | YANG Lin-jian, ZHAO Xiang-mo, HE Bing-hua, WEI Qiu-yue, AN Yi-sheng. An ant colony optimization algorithm of stochastic user equilibrium traffic assignment problem[J]. Journal of Traffic and Transportation Engineering, 2018, 18(3): 189-198. doi: 10.19818/j.cnki.1671-1637.2018.03.019 |
[17] | WU Chao-zhong, WU Hao-ran, LYU Neng-chao. Review of control switch and safety of human-computer driving intelligent vehicle[J]. Journal of Traffic and Transportation Engineering, 2018, 18(6): 131-141. doi: 10.19818/j.cnki.1671-1637.2018.06.014 |
[18] | LIU Hao-xue, ZHAO Wei-hua, LIU Kai-zheng, ZHANG Juan, ZHOU Jing. Cognitive regulation of space distance about drivers to genial tone obstacles in daytime dynamic environment[J]. Journal of Traffic and Transportation Engineering, 2009, 9(2): 105-109. doi: 10.19818/j.cnki.1671-1637.2009.02.019 |
[19] | WU Hua-jin, GUO Hai-long, YUAN Wang-fang, WEI Lang. Evaluating experiment of driving tensity[J]. Journal of Traffic and Transportation Engineering, 2009, 9(2): 100-104. doi: 10.19818/j.cnki.1671-1637.2009.02.018 |
[20] | PAN Ming-yang, YAN Fei, XIE Hai-yan. Intelligent traffic simulation based on agent and cellular automata[J]. Journal of Traffic and Transportation Engineering, 2006, 6(2): 70-74. |
1. | 周家宇,宋晓波,董家希,鄢春花,杜利芳. 基于AHP-熵权法的智轨车站选址研究. 内蒙古科技与经济. 2025(01): 35-39 . ![]() | |
2. | 杨贵永,张越垚,朱云尧,郑琪. 全球自动驾驶汽车应用现状与趋势. 汽车维护与修理. 2024(01): 62-65 . ![]() | |
3. | 黄志杰,杨广柱,方正. 智能汽车自动驾驶路径跟踪控制算法的应用分析. 汽车维修与保养. 2024(02): 77-78 . ![]() | |
4. | 李海舰,韩宗霖,郑金子,李宗典. 智能网联车辆组队与离队行为对混合交通流影响特性分析. 交通工程. 2024(06): 113-121 . ![]() | |
5. | 卢志刚,隋璐,蔡瑶,孔祥兴,程慧琳,刘东泽. 自动驾驶环境下交通-配电网协同优化运行. 电力自动化设备. 2024(09): 73-80 . ![]() | |
6. | 李继飞,钱春雨. 基于物联网的网联自动驾驶车端系统设计分析. 智能物联技术. 2024(04): 86-89 . ![]() | |
7. | 尹晨. 智能网联汽车发展背景下交通安全管理的挑战与应对. 湖北警官学院学报. 2024(04): 80-88 . ![]() | |
8. | 赵红专,张继康,潘佳雯,袁泉,许恩永,魏金占,周旦,刘承堃. 基于改进视觉算法的自动驾驶风险预判模型. 交通运输系统工程与信息. 2024(05): 79-90+139 . ![]() | |
9. | 赵欣,马佳宝,周姝含,袁旺. 城市道路网联混驾车辆分阶段动态轨迹控制方法. 重庆交通大学学报(自然科学版). 2024(11): 95-102+121 . ![]() | |
10. | 付丽,滕召波,张一帆,罗钧,王浩程. 基于TDA4VM的疲劳状态实时检测系统设计. 实验室研究与探索. 2024(11): 26-30+38 . ![]() | |
11. | 王正武,潘军良,陈涛,滑肖月. 单向三车道高速公路合流区智能网联车辆协同汇入控制. 交通运输工程学报. 2023(06): 270-282 . ![]() | |
12. | 杨广柱,龙泽链,李毅,王天生,黄绍信. 基于深度学习的交通标志识别技术研究进展. 西部交通科技. 2023(12): 194-197 . ![]() |
应用场景 | 相关文献 | 微观交通流研究内容 | 研究方法 |
微观跟驰 | [54] | 传统微观单车道模型、驾驶人辅助系统 | 智能驾驶模型 |
纵向控制 | [55]、[56] | 驾驶人辅助系统及其优化改进 | 自适应巡航控制系统协同自适应巡航控制 |
[11] | 研究不同ACC策略对交通流特性的影响 | 强化智能驾驶模型 | |
[57]、[58] | 研究CACC系统对智能网联交通流特性的影响 | 微观交通仿真模型 | |
横向控制 | [59] | 构建考虑相邻车辆运动状态的网联自动驾驶车道变换轨迹生成方法,应比较多种非线性变换曲线以评估选择最佳换道模型 | 交会引导技术 |
[60] | 考虑网联自动驾驶车辆横纵向运动之间的耦合效应,确定换道行为的最佳控制序列和碰撞规避及动态安全约束 | 非线性单轨车辆动力学模型多段变道过程模型 | |
编队换道 | [61] | 研究网联自动驾驶车队在拥挤车流中保证编队稳定性的同时提高变道成功率 | 协同自适应巡航车辆编队变道控制器 |
[62] | 提出能够仿真具有不同通信能力车辆安全跟驰行为的技术框架以解决车辆联通性和自动化区分不足的问题 | 多模型融合 | |
[63] | 开发计算自动驾驶车辆和常规车辆混合交通流通行能力的通用公式以根据需求确定跨车道的自动驾驶车辆分布 | 多目标优化 |
应用领域 | 相关文献 | 对交通系统影响的相关研究内容 | 研究方法 |
交通环境交通安全 | [64] | 验证网联自动驾驶可解决汽车共享障碍,降低车辆排放对环境影响,保障共享车使用者安全出行,达到整体利益最大化 | 智能体模型 |
交通出行交通环境交通安全 | [21] | 探讨网联自动驾驶在一阶(交通、出行成本和出行选择),二阶(车辆所有权、地点选择和土地使用以及交通基础设施)和三阶(能源消耗、空气污染、交通安全、社会公平、经济和公共健康)对社会政策的潜在影响 | 连锁反应概念 |
公众态度 | [65] | 研究公众对网联自动驾驶的态度,确定用户接受程度和购买意愿,评估自动驾驶技术推广与个人变量的相关性 | 网络问卷调查 |
用户偏好 | [66] | 探究选择拥有和使用网联自动驾驶车辆的个人动机,开发网联自动驾驶车辆长期选择决策模型 | 陈述偏好问卷调查 |
应用领域 | 相关文献 | 主要研究内容 | 研究方法 |
运动规划、反馈控制 | [67] | 比较多种典型运动规划和反馈控制算法,分析优势和局限性 | 并列比较 |
安全避障 | [68] | 对决策过程分步骤进行算法复杂性和性能准确性的评估 | 批判性评估 |
轨迹规划 | [16] | 回顾智能驾驶车辆运动规划技术,指出研究目标应集中优化复杂驾驶环境下的运动轨迹规划,设置具有避障功能的导航系统 | 综合性分析 |
安全替代指标评估 | [69] | 系统总结安全替代指标在网联自动驾驶安全建模和评价中的应用,回顾不同安全替代指标的有效性和适用性 | 系统性总结 |
[70] | 提取碰撞时间TTC和制动次数BTN作为安全替代指标,基于极值理论估计事故频率以评估自动驾驶交通安全 | 极值模型 |
应用场景 | 相关文献 | 主要研究内容 |
高速公路 | [77] | 利用IDM模型评估不同渗透率条件下自动驾驶编队的纵向安全性 |
[75] | 构建自动驾驶时空波动率曲线以识别交通网络中的潜在危险并做出积极的驾驶决策 | |
[76] | 通过优化安全变道次数最大限度地减少混合交通流中断以提高吞吐量并减少拥堵 | |
信号交叉口 | [10] | 利用网联自动驾驶车辆作交叉口控制媒介通过预测微观模拟算法响应即时车辆需求 |
[78]、[79] | 基于启发式算法识别网联自动驾驶车辆轨迹以产生最佳安全性能的交通控制 | |
[8] | 使用交叉口周边交通状态数据进行实时自适应信号相位分配 | |
[80] | 开发适用于城市交通走廊的协作式信号控制算法 | |
[81] | 提出考虑车辆随机到达的两级控制模型,用于不同交通需求下多个网联自动驾驶车辆的交通信号配时设计和轨迹规划 | |
[82] | 构建根据不同交通状态指定合适信号控制方法的概念框架 | |
车道编队 | [47] | 基于行车环境势场和车辆动力学建模,结合模型预测控制中的优化算法完成编队车辆轨迹规划和控制,实现动态避障 |
[83] | 介绍Demo 2000协同驾驶系统中的自动驾驶和车间通信技术并提出多车道编队概念 | |
[84] | 基于协作式自适应巡航控制车辆跟驰算法,添加分层控制和信号交叉口优化控制模块,准确估计车辆状态、监控潜在碰撞风险进而优化车辆轨迹、调整信号配时 |
应用领域 | 相关文献 | 主要研究内容 |
混合交通流运行效率 | [91] | 基于传统车辆与网联自动驾驶车辆的异质交通流模型分析不同渗透率下网联自动驾驶车辆对交通流量的影响 |
[92] | 通过驾驶模拟器研究网联自动驾驶车辆对常规车辆驾驶人交互行为影响 | |
[93] | 设计基于模糊规则的网联自动驾驶车辆运动控制系统促进与常规车辆的博弈合作 | |
[94] | 开发网联自动驾驶车辆情景感知安全控制模块解决城市交通网络中自动驾驶车辆和常规车辆交互冲突问题 | |
混合交通流事故分析 | [95] | 利用加利福尼亚州实车试验数据集分析网联自动驾驶车辆主要事故类型 |
[96] | 利用加利福尼亚州实车试验数据集探究影响自主驾驶模式脱离的影响因素 | |
其他方面安全管理问题 | [41]、[45] | 信息、性能、政策等安全管理挑战,包括法律保障、软件防护、隐私安全、城市发展 |
[97]、[98] |
应用场景 | 相关文献 | 主要研究内容 |
车辆交互 | [99] | 使用MATLAB构建仿真环境利用IDM模型模拟常规车辆跟驰行为、基于CACC跟驰机制确定自动驾驶车辆纵向决策操作,提出混合交通跟驰策略以识别整体机动性、安全性最佳的车队配置 |
[100] | 使用VISSIM构建微观仿真环境利用Wiedemann模型控制常规车辆跟车行为,基于规则控制算法对网联驾驶车辆行为部署,使用替代安全评估模块SSAM评估不同网联自动驾驶车辆渗透率对交通性能的影响 | |
[101] | 建立兼顾自动驾驶车辆平均车头时距和电子油门角度差的扩展跟驰模型,稳定自动驾驶车辆交通流、减少因交通流紊乱造成的车间冲突 | |
[102] | 综合考虑网联自动驾驶车辆轨迹控制、常规车辆跟驰和变道操作,添加自由变道约束设计基于变道感知轨迹优化的网联自动驾驶车辆跟驰模型,感知常规车辆轨迹变化以采取强制变道让步策略 | |
仿真测试 | [4]、[5]、[15] [103]、[104] | 基于仿真场景中车辆的微观驾驶行为和反馈信息对网联自动驾驶车辆进行自适应巡航控制、自动转向技术、避障轨迹规划、风险行为检测等安全系统设计 |
安全评估 | [12]、[105]~[110] | 虚拟测试和仿真模拟、数学建模与数字孪生、场景搭建和行为分析、驾驶模拟与试点测试等 |
人机共驾 | [111]~[117] | 人机共驾车辆控制权切换安全、接管能力评价指标选择、驾驶人接管能力影响因素、接管能力提升途径等 |
应用场景 | 相关文献 | 微观交通流研究内容 | 研究方法 |
微观跟驰 | [54] | 传统微观单车道模型、驾驶人辅助系统 | 智能驾驶模型 |
纵向控制 | [55]、[56] | 驾驶人辅助系统及其优化改进 | 自适应巡航控制系统协同自适应巡航控制 |
[11] | 研究不同ACC策略对交通流特性的影响 | 强化智能驾驶模型 | |
[57]、[58] | 研究CACC系统对智能网联交通流特性的影响 | 微观交通仿真模型 | |
横向控制 | [59] | 构建考虑相邻车辆运动状态的网联自动驾驶车道变换轨迹生成方法,应比较多种非线性变换曲线以评估选择最佳换道模型 | 交会引导技术 |
[60] | 考虑网联自动驾驶车辆横纵向运动之间的耦合效应,确定换道行为的最佳控制序列和碰撞规避及动态安全约束 | 非线性单轨车辆动力学模型多段变道过程模型 | |
编队换道 | [61] | 研究网联自动驾驶车队在拥挤车流中保证编队稳定性的同时提高变道成功率 | 协同自适应巡航车辆编队变道控制器 |
[62] | 提出能够仿真具有不同通信能力车辆安全跟驰行为的技术框架以解决车辆联通性和自动化区分不足的问题 | 多模型融合 | |
[63] | 开发计算自动驾驶车辆和常规车辆混合交通流通行能力的通用公式以根据需求确定跨车道的自动驾驶车辆分布 | 多目标优化 |
应用领域 | 相关文献 | 对交通系统影响的相关研究内容 | 研究方法 |
交通环境交通安全 | [64] | 验证网联自动驾驶可解决汽车共享障碍,降低车辆排放对环境影响,保障共享车使用者安全出行,达到整体利益最大化 | 智能体模型 |
交通出行交通环境交通安全 | [21] | 探讨网联自动驾驶在一阶(交通、出行成本和出行选择),二阶(车辆所有权、地点选择和土地使用以及交通基础设施)和三阶(能源消耗、空气污染、交通安全、社会公平、经济和公共健康)对社会政策的潜在影响 | 连锁反应概念 |
公众态度 | [65] | 研究公众对网联自动驾驶的态度,确定用户接受程度和购买意愿,评估自动驾驶技术推广与个人变量的相关性 | 网络问卷调查 |
用户偏好 | [66] | 探究选择拥有和使用网联自动驾驶车辆的个人动机,开发网联自动驾驶车辆长期选择决策模型 | 陈述偏好问卷调查 |
应用领域 | 相关文献 | 主要研究内容 | 研究方法 |
运动规划、反馈控制 | [67] | 比较多种典型运动规划和反馈控制算法,分析优势和局限性 | 并列比较 |
安全避障 | [68] | 对决策过程分步骤进行算法复杂性和性能准确性的评估 | 批判性评估 |
轨迹规划 | [16] | 回顾智能驾驶车辆运动规划技术,指出研究目标应集中优化复杂驾驶环境下的运动轨迹规划,设置具有避障功能的导航系统 | 综合性分析 |
安全替代指标评估 | [69] | 系统总结安全替代指标在网联自动驾驶安全建模和评价中的应用,回顾不同安全替代指标的有效性和适用性 | 系统性总结 |
[70] | 提取碰撞时间TTC和制动次数BTN作为安全替代指标,基于极值理论估计事故频率以评估自动驾驶交通安全 | 极值模型 |
应用场景 | 相关文献 | 主要研究内容 |
高速公路 | [77] | 利用IDM模型评估不同渗透率条件下自动驾驶编队的纵向安全性 |
[75] | 构建自动驾驶时空波动率曲线以识别交通网络中的潜在危险并做出积极的驾驶决策 | |
[76] | 通过优化安全变道次数最大限度地减少混合交通流中断以提高吞吐量并减少拥堵 | |
信号交叉口 | [10] | 利用网联自动驾驶车辆作交叉口控制媒介通过预测微观模拟算法响应即时车辆需求 |
[78]、[79] | 基于启发式算法识别网联自动驾驶车辆轨迹以产生最佳安全性能的交通控制 | |
[8] | 使用交叉口周边交通状态数据进行实时自适应信号相位分配 | |
[80] | 开发适用于城市交通走廊的协作式信号控制算法 | |
[81] | 提出考虑车辆随机到达的两级控制模型,用于不同交通需求下多个网联自动驾驶车辆的交通信号配时设计和轨迹规划 | |
[82] | 构建根据不同交通状态指定合适信号控制方法的概念框架 | |
车道编队 | [47] | 基于行车环境势场和车辆动力学建模,结合模型预测控制中的优化算法完成编队车辆轨迹规划和控制,实现动态避障 |
[83] | 介绍Demo 2000协同驾驶系统中的自动驾驶和车间通信技术并提出多车道编队概念 | |
[84] | 基于协作式自适应巡航控制车辆跟驰算法,添加分层控制和信号交叉口优化控制模块,准确估计车辆状态、监控潜在碰撞风险进而优化车辆轨迹、调整信号配时 |
应用领域 | 相关文献 | 主要研究内容 |
混合交通流运行效率 | [91] | 基于传统车辆与网联自动驾驶车辆的异质交通流模型分析不同渗透率下网联自动驾驶车辆对交通流量的影响 |
[92] | 通过驾驶模拟器研究网联自动驾驶车辆对常规车辆驾驶人交互行为影响 | |
[93] | 设计基于模糊规则的网联自动驾驶车辆运动控制系统促进与常规车辆的博弈合作 | |
[94] | 开发网联自动驾驶车辆情景感知安全控制模块解决城市交通网络中自动驾驶车辆和常规车辆交互冲突问题 | |
混合交通流事故分析 | [95] | 利用加利福尼亚州实车试验数据集分析网联自动驾驶车辆主要事故类型 |
[96] | 利用加利福尼亚州实车试验数据集探究影响自主驾驶模式脱离的影响因素 | |
其他方面安全管理问题 | [41]、[45] | 信息、性能、政策等安全管理挑战,包括法律保障、软件防护、隐私安全、城市发展 |
[97]、[98] |
应用场景 | 相关文献 | 主要研究内容 |
车辆交互 | [99] | 使用MATLAB构建仿真环境利用IDM模型模拟常规车辆跟驰行为、基于CACC跟驰机制确定自动驾驶车辆纵向决策操作,提出混合交通跟驰策略以识别整体机动性、安全性最佳的车队配置 |
[100] | 使用VISSIM构建微观仿真环境利用Wiedemann模型控制常规车辆跟车行为,基于规则控制算法对网联驾驶车辆行为部署,使用替代安全评估模块SSAM评估不同网联自动驾驶车辆渗透率对交通性能的影响 | |
[101] | 建立兼顾自动驾驶车辆平均车头时距和电子油门角度差的扩展跟驰模型,稳定自动驾驶车辆交通流、减少因交通流紊乱造成的车间冲突 | |
[102] | 综合考虑网联自动驾驶车辆轨迹控制、常规车辆跟驰和变道操作,添加自由变道约束设计基于变道感知轨迹优化的网联自动驾驶车辆跟驰模型,感知常规车辆轨迹变化以采取强制变道让步策略 | |
仿真测试 | [4]、[5]、[15] [103]、[104] | 基于仿真场景中车辆的微观驾驶行为和反馈信息对网联自动驾驶车辆进行自适应巡航控制、自动转向技术、避障轨迹规划、风险行为检测等安全系统设计 |
安全评估 | [12]、[105]~[110] | 虚拟测试和仿真模拟、数学建模与数字孪生、场景搭建和行为分析、驾驶模拟与试点测试等 |
人机共驾 | [111]~[117] | 人机共驾车辆控制权切换安全、接管能力评价指标选择、驾驶人接管能力影响因素、接管能力提升途径等 |