WO2023213018A1 - 一种车辆跟驰控制方法和系统 - Google Patents

一种车辆跟驰控制方法和系统 Download PDF

Info

Publication number
WO2023213018A1
WO2023213018A1 PCT/CN2022/109003 CN2022109003W WO2023213018A1 WO 2023213018 A1 WO2023213018 A1 WO 2023213018A1 CN 2022109003 W CN2022109003 W CN 2022109003W WO 2023213018 A1 WO2023213018 A1 WO 2023213018A1
Authority
WO
WIPO (PCT)
Prior art keywords
vehicle
following
driver
following control
car
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2022/109003
Other languages
English (en)
French (fr)
Inventor
郑建颖
杨泽
郁树梅
孙荣川
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Suzhou University
Original Assignee
Suzhou University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Suzhou University filed Critical Suzhou University
Publication of WO2023213018A1 publication Critical patent/WO2023213018A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0125—Traffic data processing
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/052—Detecting movement of traffic to be counted or controlled with provision for determining speed or overspeed
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/123—Traffic control systems for road vehicles indicating the position of vehicles, e.g. scheduled vehicles; Managing passenger vehicles circulating according to a fixed timetable, e.g. buses, trains, trams

Definitions

  • This application relates to the field of intelligent transportation technology and vehicle control methods, and in particular to a vehicle following control method and system that considers the driver's willingness to overtake in urban road intersection scenarios.
  • the present invention proposes a vehicle following control method and system that considers the driver's overtaking intention at a road intersection.
  • the applicability of the GM model under different driving conditions is optimized, thereby prompting the vehicle to make a better car-following control strategy.
  • the technical solution provided by the present invention is a vehicle following control method that considers the driver's overtaking intention at a road intersection, which specifically includes the following steps:
  • S1 Collect and process road intersection traffic data, identify and extract vehicle following behavior
  • S2 Construct a 2D bounding box model of the vehicle and obtain high-resolution micro-traffic information, which includes the vehicle's instantaneous speed and following distance;
  • S3 Based on the high-resolution micro-traffic information, analyze the operating status of the target vehicle and the leading vehicle on the same lane, and at the same time analyze the vehicle's instantaneous speed and the curve of the following distance changing with time, and determine whether the driver of the target vehicle has the ability to overtake. Willingness;
  • the technical solution of the present invention has the following advantages: 1.
  • the data used for model parameter calibration and decision-making analysis of the present invention are all from real traffic scenes and can better reflect real traffic conditions.
  • the present invention can re-collect new data and calibrate new model parameters for different scenarios, and is suitable for various intersections.
  • the present invention takes the driver's personalized driving style into consideration, that is, in the process of vehicle following control, the driver's overtaking intention is taken into consideration, which greatly ensures the safety and comfort of driving.
  • Figure 1 is an overall flow chart of the vehicle following control method that considers the driver's intention to overtake in the present invention.
  • Figure 2 is a schematic diagram of the original point cloud data in the intersection scene.
  • Figure 3 shows the result after background filtering.
  • Figure 4 shows the vehicle target detection results.
  • Figure 5 shows the driving trajectory of the vehicle in the intersection scenario.
  • Figure 6 is a schematic diagram of the vehicle position relationship during car following.
  • Figure 7 is a schematic diagram of the vehicle 2D bounding box model.
  • Figure 8 shows the position coordinate relationship between the two workshops before and after the car-following process.
  • Figure 9 is a schematic diagram of the high-resolution microscopic database of the vehicle following process.
  • Figure 10(a) is a graph showing the variation of the following distance with the vehicle speed during the normal following process.
  • Figure 10(b) is a graph showing the variation of the following distance with the vehicle speed during the following process when the driver has the intention to overtake.
  • Figure 12 is a flow chart of the vehicle following control strategy that takes into account the driver’s willingness to overtake.
  • Figure 13(a) is a comparison chart between the velocity change curve output by the model and the real velocity curve
  • Figure 13(b) is a comparison chart between the displacement change curve output by the model and the real displacement curve.
  • Figure 14 shows a structural diagram of a vehicle following control system according to an embodiment of the present application.
  • Figure 15 shows a schematic structural diagram of an electronic device provided by an embodiment of the present application.
  • Figure 16 shows a schematic diagram of a storage medium provided by an embodiment of the present application.
  • an embodiment of the present invention provides a vehicle following control method that considers the driver's willingness to overtake in an urban road intersection scenario.
  • the method includes four major steps:
  • Step S1 Collect and process traffic data, identify and extract vehicle following behavior.
  • Step S2 Construct a 2D bounding box model to obtain high-resolution microscopic traffic information.
  • Step S3 Determine whether the target vehicle has the intention to overtake.
  • Step S4 According to different driver wishes, adopt corresponding vehicle following control methods.
  • step S1 The details of step S1 are described as follows: S101 to S105:
  • S101 Traffic data collection.
  • the present invention deploys laser radar in road testing to obtain traffic data in urban road intersection scenarios.
  • the lidar is placed at the corner of the intersection and close to the vehicle parking line. Since the lidar can scan the surrounding 360° range, the lidar can collect the complete driving trajectory of the vehicle passing through the intersection at this location. Placing the lidar on a 1.8-meter-high tripod on the roadside can not only prevent the problem of occlusion between traffic targets due to the position being too low, but also prevent the laser beam that can scan the target object from being reduced due to the position being too high. small, thereby reducing the problem of the number of target point clouds.
  • S102 Background filtering of point cloud data.
  • the background data In a large amount of data measured by lidar at a certain fixed orientation over a long period of time, the background data must be much more than the foreground data (in this field, the foreground data usually refers to traffic targets). Therefore, the distances (d 1 , d 2 , d 3 ,..., d n ) obtained from the statistics of all directions are gathered together, and the set of these points is the constructed background model.
  • S103 Traffic target detection.
  • the point cloud data after background filtering contains various traffic targets (motor vehicles, non-motor vehicles and pedestrians), as well as some unfiltered noise points. Since the point cloud of each traffic target is relatively concentrated, the DBSCAN clustering algorithm is selected to complete target detection based on the characteristics of the point cloud data. Because lidar returns signals by rotating 360° with 16 laser beams, for a traffic target, all its points are closer in the X and Y directions, but farther in the Z direction. Based on this feature Improve the Euclidean distance formula in the DBSCAN algorithm:
  • D new is the Euclidean distance
  • ⁇ x, ⁇ y, and ⁇ z are the coordinate differences of the two points on the traffic target in the X, Y, and Z directions.
  • clustering radius Eps clustering radius
  • MinPts minimum number of clustering points. If Eps is too large, it will cause different targets to be clustered into one target. If Eps is too small, it will cause the same target to be clustered into multiple targets. If MinPts is too large, it will cause traffic targets to be identified as noise points. If MinPts is too small, it will cause noise points to be identified as noise points. Traffic target, so after experiments, the clustering radius Eps is 1.2m and the minimum number of clustering points MinPts is 5.
  • S104 Obtain the vehicle trajectory. Use the traffic target tracking method based on historical frame data fusion to obtain vehicle driving trajectories, fuse two adjacent frames of data (n-1 and n frames) together, and then use the DBSCAN clustering method to classify the same vehicle target in the two frames of data.
  • the point clouds are clustered into a cluster, and these point clouds are identified as the same target, and then two adjacent frames of data (n and n+1 frames) are selected, and the same method is used for fusion, clustering and identification until processing After completing all the frame data in which the target vehicle appears, the target in these frames is fused together to obtain the running trajectory of the target vehicle.
  • This method uses the spatiotemporal correlation of point clouds to increase the spatiotemporal correlation of the target point cloud through the fusion of current frame and historical frame data, thereby improving the accuracy of target tracking.
  • Figure 5 shows the extracted vehicle running trajectory at the intersection.
  • occlusion between vehicles will cause the trajectory to be broken.
  • the driving trajectory of any vehicle target can be divided into three situations: complete, broken, and wrong. The broken tracks and wrong tracks are eliminated, and all complete vehicles extracted are Trajectories are used for subsequent processing.
  • S105 Recognition and extraction of car-following behavior.
  • the driving behavior of the following vehicle in the same lane will be stimulated and constrained by the instantaneous movement of the vehicle in front, that is, the vehicle's following behavior.
  • the obtained vehicle trajectory is identified, and based on the change of the X-Y coordinate position of the vehicle, the vehicle trajectory is divided into straight trajectory, lane change trajectory and turning trajectory, and then the straight vehicle is divided into free flow state and following state.
  • the extraction rules for vehicle following behavior are formulated, including the following: (1) following vehicle and leading vehicle Driving in the same lane; (2) The angle difference between the driving directions of the front and rear vehicles is less than 5°; (3) The distance between the front bumper of the following vehicle and the rear bumper of the preceding vehicle is less than 30m (that is, the following distance is less than 30m).
  • Figure 6 is a schematic diagram of vehicle position relationships during car following.
  • step S2 The details of step S2 are described as follows: S201 to S203:
  • S201 Build a 2D bounding box model of the vehicle. Since in actual traffic scenes, vehicles drive on the ground and their motion trajectories are parallel to the ground plane, the processed target point cloud is first projected onto the XOY plane to simplify the 3D problem into a 2D problem, and then the target point cloud is processed Convex hull point extraction, and the 2D bounding box model of the vehicle is constructed based on the principle of the minimum area method. Referring to Figure 7, by obtaining the four vertex coordinates of the vehicle bounding box model, the vehicle size and front position coordinates are calculated.
  • the target vehicle speed information can be calculated from the position information of adjacent frames before and after the target, (x i (k-1), y i (k-1)) and (x i (k), y i (k)) are respectively
  • the vehicle's front position coordinates at time t k-1 and time t k can be calculated through the following formula to obtain the instantaneous speed of the vehicle during travel.
  • S203 Calculate the vehicle following distance.
  • the distance information during vehicle following can be calculated from the position information of the preceding and following vehicles in the same frame.
  • (x p , y p ) and (x f , y f ) are the leading vehicle and the following vehicle respectively.
  • the front position coordinates of the vehicle, L p is the length of the leading vehicle, then the head distance D head and the following distance D gap are calculated respectively through the following formulas:
  • step S3 The details of step S3 are described as follows: S301 to S303:
  • S301 Integrate the high-resolution micro-traffic information obtained in S2 and establish a data table of vehicle following behavior information at urban road intersections in order to determine whether the driver has the intention to overtake and make appropriate control decisions.
  • the high-resolution microscopic data of the vehicle following process mainly includes the following information in Table 1:
  • S303 Determine whether the target vehicle is willing to overtake. Referring to Figure 11, through statistics of vehicle speeds, it is found that when vehicles pass through an intersection, they all accelerate, indicating that drivers always expect to pass through intersections at a faster speed while ensuring traffic safety. Analyze the relationship curve between the instantaneous speed of the target vehicle and the following distance between the vehicles in front. If the following distance decreases as the speed increases, it means that when the two vehicles are driving through the intersection, the following vehicle continues to catch up with the leading vehicle. vehicles, and the distance between the two vehicles is constantly decreasing. This behavior is the target vehicle’s preparation for overtaking. The driver hopes to shorten the distance from the leading vehicle at a faster speed so that he can quickly overtake when conditions are available. Change lanes to complete overtaking.
  • the driver can be considered to have the intention to overtake, and this behavior is called the driver's intention to overtake. Following behavior of overtaking intention. On the contrary, if the following distance of the target vehicle increases with the increase of speed, the driver has no intention to overtake.
  • a binary variable ⁇ is introduced to indicate whether the driver is willing to overtake.
  • step S4 The details of step S4 are described as follows: S401 to S403:
  • S401 First, transmit the data collected and analyzed by the road test detection equipment to the target vehicle through ZigBee network communication, so that the vehicle control system can perform vehicle following control based on this information and achieve vehicle-road collaboration.
  • a n (t+T) is the acceleration of the following vehicle at time t+T, which is the input of the model
  • v n (t+T) is the speed of the following vehicle at time t+T
  • ⁇ V(t) is the speed of the following vehicle at time t+T.
  • the speed difference between the leading vehicle and the leading vehicle at time t, ⁇ X(t) is the separation distance between the two vehicles at time t.
  • ⁇ N , m N , l N are the model parameters of the vehicle following control method under normal following conditions
  • ⁇ Y , m Y , l Y are the model parameters of the vehicle following control method that considers the driver's willingness to overtake.
  • Embodiment 1 is a car-following control method under normal car-following
  • Embodiment 2 is a car-following control method with overtaking. Desirable vehicle following control method.
  • Example 1 Since the driver's reaction time is usually less than 1 s, in order to simplify the difficulty of calibrating parameters, a representative T value is selected evenly in the range of 0 to 1 s, and the selected reaction time is regarded as a known parameter.
  • Coding method real number encoding, gene fragment is ( ⁇ , m, l); selection operator: roulette selection method; crossover operator: uniform crossover method, crossover rate is 0.8; mutation operator: normal distribution mutation, mutation rate is 0.1.
  • Coding method real number encoding, gene fragment is ( ⁇ , m, l); selection operator: roulette selection method; crossover operator: uniform crossover method, crossover rate is 0.8; mutation operator: normal distribution mutation, mutation rate is 0.1.
  • the driver When the driver is willing to overtake during the process of following, he must control the speed of the following vehicle to be greater than the speed of the leading vehicle, so that the distance between the driver and the leading vehicle can be continuously reduced to meet the overtaking conditions.
  • the following vehicle meets the conditions for overtaking and changing lanes at this time. If the left lane also meets the conditions for changing lanes and overtaking, that is, there is no vehicle influence in front of the left lane, then the control of the vehicle will be The strategy is switched from car-following control to lane-changing overtaking control, and the vehicle is controlled to change lanes and overtake to satisfy the driver's overtaking intention. If the left lane does not meet the lane change conditions, the vehicle will continue to perform following control until the lane change conditions are met.
  • Figure 13(a) is the predicted speed curve of the car-following vehicle
  • Figure 13(b) is the predicted vehicle displacement curve.
  • the top curve in the figure is the real curve of the leading vehicle
  • the middle curve is the real curve of the following vehicle
  • the lower curve is the predicted curve of the model control output.
  • the application embodiment provides a vehicle following control system, which is used to execute the vehicle following control method described in the above embodiment.
  • the system includes: a collection identification module 501 for collecting and processing Road intersection traffic data identifies and extracts vehicle following behavior; the microscopic traffic information acquisition module 502 is used to construct a 2D boundary box model of the vehicle and obtain high-resolution microscopic traffic information, which includes the instantaneous speed of the vehicle and Following distance; judging overtaking willingness module 503, used to analyze the operating status of the target vehicle and the leading vehicle in the same lane based on the high-resolution micro traffic information, and at the same time analyze the vehicle's instantaneous speed and the curve of the following distance changing with time , determine and analyze whether the driver of the target vehicle has the intention to overtake; the car-following control module 504 is used to use corresponding vehicle car-following control methods to control vehicle operation according to different driver wishes.
  • the vehicle following control system provided by the above embodiments of the application and the vehicle following control method provided by the embodiments of the application are based on the same inventive concept, and have the same beneficial effects as the methods adopted, run or implemented by their stored applications. .
  • An embodiment of the present application also provides an electronic device corresponding to the vehicle following control method provided in the foregoing embodiment, so as to execute the vehicle following control method.
  • the embodiments of this application are not limiting.
  • FIG. 15 shows a schematic diagram of an electronic device provided by some embodiments of the present application.
  • the electronic device 20 includes: a processor 200, a memory 201, a bus 202 and a communication interface 203.
  • the processor 200, the communication interface 203 and the memory 201 are connected through the bus 202; the memory 201 stores There is a computer program that can be run on the processor 200.
  • the processor 200 runs the computer program, it executes the vehicle following control method provided by any of the foregoing embodiments of this application.
  • the memory 201 may include high-speed random access memory (RAM: Random Access Memory), and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
  • RAM Random Access Memory
  • non-volatile memory such as at least one disk memory.
  • the communication connection between the system network element and at least one other network element is realized through at least one communication interface 203 (which can be wired or wireless), and the Internet, wide area network, local network, metropolitan area network, etc. can be used.
  • the bus 202 may be an ISA bus, a PCI bus, an EISA bus, etc.
  • the bus can be divided into address bus, data bus, control bus, etc.
  • the memory 201 is used to store a program. After receiving the execution instruction, the processor 200 executes the program.
  • the vehicle following control method disclosed in any of the embodiments of the present application can be applied to the processor 200 , or implemented by the processor 200.
  • the processor 200 may be an integrated circuit chip with signal processing capabilities.
  • each step of the above method can be completed by instructions in the form of hardware integrated logic circuits or software in the processor 200 .
  • the above-mentioned processor 200 can be a general-purpose processor, including a central processing unit (Central Processing Unit, referred to as CPU), a network processor (Network Processor, referred to as NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), off-the-shelf programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.
  • CPU Central Processing Unit
  • NP Network Processor
  • DSP digital signal processor
  • ASIC application-specific integrated circuit
  • FPGA off-the-shelf programmable gate array
  • a general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.
  • the steps of the method disclosed in conjunction with the embodiments of the present application can be directly implemented by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor.
  • the software module can be located in random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, registers and other mature storage media in this field.
  • the storage medium is located in the memory 201.
  • the processor 200 reads the information in the memory 201 and completes the steps of the above method in combination with its hardware.
  • the electronic device provided by the embodiments of the present application and the vehicle following control method provided by the embodiments of the present application are based on the same inventive concept, and have the same beneficial effects as the methods adopted, operated or implemented.
  • the embodiment of the present application also provides a computer-readable storage medium corresponding to the vehicle following control method provided in the previous embodiment. Please refer to Figure 16.
  • the computer-readable storage medium shown is an optical disk 30, on which is stored A computer program (i.e., a program product).
  • the computer program When the computer program is run by a processor, the computer program will execute the vehicle following control method provided by any of the foregoing embodiments.
  • examples of the computer-readable storage medium may also include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), and other types of random access memory.
  • PRAM phase change memory
  • SRAM static random access memory
  • DRAM dynamic random access memory
  • RAM random access memory
  • ROM read-only memory
  • EEPROM electrically erasable programmable read-only memory
  • flash memory or other optical and magnetic storage media will not be described in detail here.
  • the computer-readable storage medium provided by the above embodiments of the present application is based on the same inventive concept as the vehicle following control method provided by the embodiments of the present application, and has the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein. .

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Traffic Control Systems (AREA)

Abstract

一种车辆跟驰控制方法和系统，在城市道路交叉口场景下考虑驾驶人超车意愿，用以改善车辆个性化驾驶风格对交叉口交通安全的影响。方法包括以下步骤：1)采集城市道路交叉口的车辆行驶数据，识别并提取车辆跟驰行为；2)通过构建2D边界盒模型的方法，获取跟驰过程中的高分辨微观信息；3)分析同一车道上目标车辆与前导车辆的运行状态，速度及间距变化，判断目标车辆是否具有超车意愿；4)基于不同行驶状态下的跟驰模型，实时控制车辆加速度变化。车辆跟驰控制方法通过分析路测传感器获取的交通信息，进行车辆跟驰决策判断，避免交通事故，既提高了城市道路交叉口的通行效率，又保障了交叉口跟驰过程中车辆行驶的安全性。

Description

一种车辆跟驰控制方法和系统 技术领域
本申请涉及智能交通技术和车辆控制方法领域，尤其涉及一种城市道路交叉口场景下考虑驾驶人超车意愿的车辆跟驰控制方法和系统。
背景技术
随着现代城市的快速发展，城市机动车保有量不断增加，道路交通拥堵与安全问题日益严重，以智能交通系统为代表的信息化技术成为缓解交通拥堵及安全问题的新手段。车辆跟驰控制作为智能交通的关键技术之一，对揭示交通流演化的内在机理，缓解交通拥堵，保障车辆行驶的安全性有重要意义。城市道路交叉口作为城市路网的重要枢纽，不仅是交通冲突的密集区，更是交通事故高发区。同时，不同驾驶员的驾驶风格会影响跟驰控制的准确性，从而导致跟驰车辆在控制决策上产生误差，严重影响车辆运行的安全和驾驶舒适度。因此，针对城市道路交叉口车辆的驾驶行为分析，并在进行车辆跟驰控制的过程中考虑这种个性化的驾驶风格，有利于提高交叉口行车的安全性、舒适感和通行效率。
自1952年Pipes首次提出车辆跟驰模型开始，越来越多的交通学者开始研究车辆跟驰问题，相继提出了GM模型，最优速度(OV)模型，全速度差(FVD)模型和广义力(GF)模型等车辆跟驰模型。21世纪以来，随着计算机科学、导航技术和视频提取技术的不断进步，研究者们获取了大量真实的车辆微观运行轨迹数据，进一步促进了车辆跟驰模型研究的快速发展。经过对相关研究的调研中发现，虽然越来越多的扩展模型被广泛提出，然而现有的研究却很少考虑驾驶员的驾驶风格，更没有考虑到跟驰过程中驾驶人的超车意愿。因此，基于上述背景，针对城市道路交叉口场景，亟需考虑驾驶人的超车意愿，对传统的跟驰模型进行改进，提出更优的车辆跟驰控制方法。
发明内容
本发明基于上述背景问题，提出一种考虑道路交叉口驾驶人超车意愿的车辆跟驰控制方法和系统。通过分析路测传感器获取的交通信息，并考虑前后车辆的行驶参数，对GM模型进行不同行驶状态下的适用性优化，从而促使车辆做出更优的跟驰控制策略。
为了实现这一目标，本发明提供的技术方案为一种考虑道路交叉口驾驶人超车意愿的车辆跟驰控制方法，具体包括以下步骤：
S1：采集并处理道路交叉口交通数据，识别并提取车辆跟驰行为；
S2：构建车辆2D边界盒模型，获取高分辨率微观交通信息，所述高分辨率微观交通信息包括车辆的瞬时速度和跟驰间距；
S3：根据所述高分辨率微观交通信息，分析同一车道上目标车辆与前导车辆的运行状态，同时分析车辆的瞬时速度及跟驰间距随时间变化的曲线，判断分析目标车辆驾驶员是否具有超车意愿；
S4：针对不同驾驶员意愿，采用相应的车辆跟驰控制方法控制车辆运行。
相比现有技术，本发明的技术方案具有以下优点：1、本发明的进行模型参数标定与决策分析的数据均来自真实交通场景，更能反映真实的交通状况。2、本发明针对不同场景可以重新采集新的数据，标定新的模型参数，适用于各种不同的交叉口。3、本发明考虑了驾驶人的个性化驾驶风格，即在车辆跟驰控制的过程中，考虑了驾驶人的超车意愿，极大保障了行车的安全性和舒适度。
附图说明
在附图中，除非另外规定，否则贯穿多个附图相同的附图标记表示相同或相似的部件或元素。这些附图不一定是按照比例绘制的。应该理解，这些附图仅描绘了根据本申请公开的一些实施方式，而不应将其视为是对本申请范围的限制。
图1为本发明中考虑驾驶人超车意愿的车辆跟驰控制方法的总体流程图。
图2为交叉口场景下的原始点云数据示意图。
图3为经过背景滤除后的结果图。
图4为车辆目标检测结果图。
图5为交叉口场景下车辆的行驶轨迹图。
图6为跟驰过程中车辆位置关系示意图。
图7为车辆2D边界盒模型示意图。
图8为跟驰过程中前后两车间的位置坐标关系图。
图9为车辆跟驰过程的高分辨率微观数据库示意图。
图10(a)为常态跟驰过程中跟驰间距随车辆速度变化的曲线图，图10(b)为在驾驶员具有超车意愿的跟驰过程中跟驰间距随车辆速度变化的曲线图。
图11车辆通过交叉口的速度变化曲线图。
图12为考虑驾驶员超车意愿的车辆跟驰控制策略流程图。
图13(a)为模型输出的速度变化曲线与真实速度曲线的对比图，图13(b)为模型输出的位移变化曲线与真实位移曲线的对比图。
图14示出根据本申请实施例的车辆跟驰控制系统的构成图。
图15示出了本申请一实施例所提供的一种电子设备的结构示意图。
图16示出了本申请一实施例所提供的一种存储介质的示意图。
具体实施方式
下面结合附图和实施例对本申请作进一步的详细说明。可以理解的是，此处所描述的具体实施例仅用于解释相关发明，而非对该发明的限定。另外还需要说明的是，为了便于描述，附图中仅示出了与有关发明相关的部分。需要说明的是，在不冲突的情况下，本申请中的实施例及实施例中的特征可以相互组合。下面将参考附图并结合实施例来详细说明本申请。
参考图1所示，本发明实施例提供的城市道路交叉口场景下考虑驾驶人超车意愿的车辆跟驰控制方法，该方法包括四大步骤：
步骤S1：采集并处理交通数据，识别并提取车辆跟驰行为。
步骤S2：构建2D边界盒模型，获取高分辨微观交通信息。
步骤S3：判断目标车辆是否具有超车意愿。
步骤S4：针对不同驾驶员意愿，采用相应的车辆跟驰控制方法。
步骤S1的详细内容描述如下S101～S105：
S101：交通数据采集。本发明在路测部署激光雷达，从而获取城市道路交叉口场景下的交通数据。将激光雷达布置在交叉路口的转角处，且靠近车辆停车线一侧，由于激光雷达可扫描周围360°范围的环境，故激光雷达在此位置能够采集到车辆通过交叉口完整的行驶轨迹。将激光雷达布置在路侧1.8米高的三脚架上，既可以防止因为位置过低，造成的交通目标间遮挡的问题，又可以防止因为位置过高，导致能够扫描到目标物体上的激光束减小，从而减少目标点云数量的问题。
S102：点云数据背景滤除。本发明使用多帧数据叠加的方法构建背景。首先将同一场景下的大量帧数据叠加，然后统计每一个方位激光束(l 1,l 2,l 3,…,l n)返回的距离值及不同距离出现的频次，并找到其中出现频率最多的距离d i(i＝1,2,3,…,n)。由于在交通场景中由于交通目标的位置在不断改变，而交通背景的位置保持不变。在一段较长时间内，激光雷达在某一固定方位所测得的大量数据中，背景数据必然远多于前景数据(在本领域中，前景数据通常是指交通目标)。因此将所有方位统计得到的距离(d 1,d 2,d 3,…,d n)集合在一起，而这些点的集合即为构建出的背景模型。使用背景差分法将当前帧的点云数据与背景模型进行差分，设置阈值为0.05m，将当前帧每个方位点的距离(a 1,a 2,a 3,…,a n)与背景模型中该方位的距离(d 1,d 2,d 3,…,d n)进行差分，滤除所有差小于阈值0.05m的点，从而完成背景滤除。参考图2和图3所示，为交叉口场景下的原始点云数据和经过背景滤除后的结果。
S103：交通目标检测。经过背景滤除的点云数据，其中包含着各种交通目标(机动车、非机动车和行人)，同时也有一些未滤除掉的噪声点。由于每个交通目标的点云都比较集中分布，基于点云数据的特点选用DBSCAN聚类算法完成目标检测。因为激光雷达是通过16束激光旋转360°返回信号的，故对于一个交通目标而言，其所有点在X方向和Y方向上距离较近，而在Z方向上的距离较远，基于此特征对DBSCAN算法中的欧氏距离公式进行改进：
Figure PCTCN2022109003-appb-000001
其中D new为欧氏距离，Δx、Δy、Δz为交通目标上的两个点在X、Y、Z三个方向上的坐标差值。
根据激光雷达点云数据的特点和交通目标点云的空间排布规律，选定合适的DBSCAN算法参数：聚类半径Eps和最小聚类点个数MinPts。如果Eps过大会导致不同目标被聚类为一个目标，过小会导致同一目标被聚类成多个目标，如果MinPts过大会导致交通目标被识别为噪声点，过小会导致噪声点被识别为交通目标，因此经过试验选定参数聚类半径Eps为1.2m，最小聚类点个数MinPts为5。然后根据坐标关系清除所有道路空间之外区域的交通目标，再根据不同交通目标的点云特征差异，从所有目标中识别提取出车辆目标，并记录每个车辆目标在道路空间中的位置。参考图4所示为目标检测结果。
S104：车辆运行轨迹的获取。使用基于历史帧数据融合的交通目标跟踪方法获取车辆行驶轨迹，将相邻两帧数据(n-1与n帧)融合在一起，然后通过DBSCAN聚类的方法将同一车辆目标在两帧数据中的点云聚类成一个簇，并将这些点云标识为同一目标，然后另外选取相邻两帧数据(n与n+1帧)，使用同样的方法进行融合，聚类和标识，直到处理完该目标车辆出现的所有帧数据，将这些帧的该目标融合在一起，即得到了该目标车辆的运行轨迹。该方法利用点云的时空相关性，通过当前帧和历史帧数据融合，增加目标点云时空关联度，从而提高目标跟踪准确率，参考图5所示为提取到的交叉口车辆运行轨迹。另外，车辆运行之间的遮挡会导致轨迹的断裂，对于任意车辆目标的行驶轨迹，都可以分为完整、断裂和错误三种情况，剔除掉断裂轨迹和错误轨迹，将提取到的所有完整车辆轨迹用于后续的处理。
S105：跟驰行为的识别与提取。当机动车处于非自由流阶段，处于相同车道的后车驾驶行为会受到前车瞬时运动的刺激和约束作用，即车辆的跟驰行为。首先对获取的车辆轨迹进行识别，根据车辆的X-Y坐标位置变化，将车辆运行轨迹分为直行轨迹、变道轨迹和转弯轨迹，再将直行的车辆分为自由流状态和跟驰状态。由于本发明针对的是城市道路交叉口场景，所以根据交叉口的车辆行驶速度小，间隙距离小的特点，制定出车辆跟驰行为的提取规则包括以下内容：(1)跟驰车辆与前导车辆行驶在同一车道；(2)前后车行驶方向的角度差小于5°；(3)跟驰车辆的前保险杠到前车的后保险杠的距离小于30m(即跟驰间距小于30m)。参考图6所示，为跟驰过程中车辆位置关系示意图。
步骤S2的详细内容描述如下S201～S203：
S201：构建车辆2D边界盒模型。由于在实际交通场景中，车辆在地面上行驶，其运动轨迹平行于地平面，因此首先将处理后得到的目标点云投影至XOY平面，将3D问题简化为2D问题，然后对目标点云进行凸包点提取，根据最小面积法原理构建车辆的2D边界盒模型。参考图7所示，通过获得车辆边界盒模型的四个顶点坐标，计算得到车辆的尺寸和车头位置坐标。
S202：计算车辆行驶速度。目标车辆速度信息可以通过目标前后相邻帧的位置信息计算得到，(x i(k-1)，y i(k-1))和(x i(k)，y i(k))分别为车辆在t k-1时刻和t k时刻的车头位置坐标，则通过以下公式计算得到车辆行驶过程中的瞬时速度。
Figure PCTCN2022109003-appb-000002
S203：计算车辆跟驰间距。车辆跟驰过程中的间距信息可以通过同一帧前后辆车的位置信息计算得到，参考图8所示，(x p，y p)和(x f，y f)分别为前导车辆和跟驰车辆的车头位置坐标，L p为前导车辆的车长，则通过以下公式分别计算得到车头间距D head和跟驰间距D gap：
Figure PCTCN2022109003-appb-000003
D gap＝D head-L p          (10)
步骤S3的详细内容描述如下S301～S303：
S301：将S2中获取到的高分辨率微观交通信息整合，建立城市道路交叉口车辆跟驰行为信息数据表，以备进行驾驶员是否具有超车意愿的判定，做出合适的控制决策。参考图9所示，车辆跟驰过程的高分辨率微观数据主要包括如下表1信息：
表1车辆跟驰过程的高分辨率微观数据
Figure PCTCN2022109003-appb-000004
S302：基于交叉口车辆跟驰行为的高分辨率微观信息，以跟驰车辆的瞬时速度(FV-Velocity)为横坐标，以跟驰间距(Gap Distance)为纵坐标，统计分析在一个跟驰过程中，跟驰间距变化与跟驰车辆速度变化之间的关系。通过数据分析发现，在车辆行驶通过交叉口的整个过程中，只有两种行驶状况的跟驰行为，一种是跟驰间距随着跟驰车辆速度的增大而增大，另一种是跟驰间距随着跟驰车辆速度的增大而减小，分别参考图10(a)和图10(b)所示。
S303：判断目标车辆是否具有超车意愿。参考图11所示，通过对车辆速度的统计发现，当车辆行驶通过交叉口时，都是加速运动，说明驾驶员在确保交通安全的同时，总是期望以较快的速度通过交叉口。对目标车辆瞬时速度与前车间跟驰间距的关系曲线分析，若跟驰间距随着速度的增大而减小，即说明两车在行驶通过交叉口的过程中，跟驰车辆在持续追赶前导车辆，且两车间的距离在不断减小，此种行为是目标车辆为超车准备的预备工作，驾驶员希望以更快的速度拉进与前导车辆的距离，以便在具有超车条件的时刻能够快速变道，完成超车，因此在目标车辆做出具体超车行为前(即车辆开始变道前)的跟驰过程中，即可认为驾驶员是具有超车意愿的，同时将此行为称为驾驶员具有超车意愿的跟驰行为。反之，若目标车辆跟驰间距随着速度的增大而增大，则该驾驶员不具有超车意愿。
引入一个二进制变量θ，用来表示驾驶员是否具有超车意愿。
Figure PCTCN2022109003-appb-000005
步骤S4的详细内容描述如下S401～S403：
S401：首先通过ZigBee网络通讯，将路测检测设备采集及分析后得到的数据传输给目标车辆，从而使车辆控制系统可根据这些信息进行车辆跟驰控制，实现车路协同。
S402：基于改进的新模型来控制车辆的跟驰行为：
Figure PCTCN2022109003-appb-000006
其中a n(t+T)是跟驰车辆在t+T时刻的加速度，为模型的输入，v n(t+T)是跟驰车辆在t+T时刻的速度，ΔV(t)是跟驰车辆与前导车辆在t时刻的速度差，ΔX(t)是两车在t时刻的间隔距离。λ N，m N，l N为常态跟驰下的车辆跟驰控制方法的模型参数，λ Y，m Y，l Y为考虑驾驶员超车意愿的车辆跟驰控制方法的模型参数。
针对不同的驾驶员意愿，采用相应的跟驰控制方法对车辆的加速度进行控制，即可分为两种情况，实施例1是常态跟驰下的车辆跟驰控制方法，实施例2是具有超车意愿的车辆跟驰控制方法。
实施例1：由于驾驶员的反应时间通常小于1s，因此为了简化标定参数的难度，在0～1s范围内均衡地选取具有代表性的T值，将选取的反应时间视为已知参数。
使用遗传算法进行模型参数标定，遗传算法的设置如下，编码方式：实数编码，基因片段为(λ，m，l)；选择算子：轮盘选择法；交叉算子：均匀交叉法，交叉率为0.8；变异算子：正态分布突变，变异率为0.1。取500组样本数据进行标定，标定结果如表2所示：
表2模型参数标定结果
反应时间T 0s 0.1s 0.2s 0.3s 0.5s 0.8s 1.0s
λ 7.76 7.88 8.01 8.35 9.20 10.1 8.92
m 0.15 0.21 0.28 0.32 0.38 0.34 0.22
l 1.17 1.17 1.17 1.19 1.24 1.26 1.17
然后根据模型的加速度输出，计算车辆通过模型控制的速度及位移信息，并从这两个方面分析模型的预测误差，如表3所示。
表3模型预测误差
反应时间T 0s 0.1s 0.2s 0.3s 0.5s 0.8s 1.0s
速度误差(m/s) 0.232 0.153 0.299 0.344 0.434 0.453 0.472
位移误差(m) 0.376 0.171 0.345 0.447 0.556 0.694 0.983
因此，误差在反应时间T为0.1s时的误差最小，因此模型参数标定的最优结果为：T＝0.1s，λ N＝7.88，m N＝0.21，l N＝1.17。
实施例2：以实施例1相同的方法进行模型参数标定，得到在T＝0.1s情况下参数λ Y，m Y，l Y的最优结果。当驾驶员在跟驰的过程中具有超车意愿时，控制跟驰车辆速度大于前车速度，才能不断减小与前导车辆的间距，以满足超车的条件。
在进行考虑驾驶人超车意愿的车辆跟驰控制时，目标车辆与前车的跟驰间距也影响着控制决策。在这里引入两个距离参数：最小安全距离D safe和变道距离D change。
当跟驰间距D gap<D change时，跟驰车辆此时满足超车变道的条件，若左侧车道同时满足变道超车的条件，即左侧车道前方无车辆影响，此时将车辆的控制策略由跟驰控制切换到变道超车控制，控制车辆进行变道与超车，以满足驾驶员的超车意愿。若左侧车道不满足变道条件，则车辆继续进行跟驰控制，直到满足变道条件。
当跟驰间距D gap<D safe时，车辆此时已经无法满足安全行驶的条件，若碰到突发状况，很容易与前车追尾，发生交通事故。因此，当跟驰间距小于最小安全距离且不满足超车条件时，将控制车辆暂时放弃超车，即采用常态跟驰下的车辆跟驰控制方法，直到当D gap>D safe时再重新恢复具有超车意愿的跟驰控制方法。参考图12所示，是考虑驾驶员超车意愿的车辆跟驰控制策略流程图。
通过实验及统计分析，在城市道路交叉口场景下，最小安全距离D safe＝10m，变道距离D change＝15m。
S403：以前导车辆的整个行驶信息(包括位置和速度信息)和跟驰车辆的初始信息作为已知信息，通过计算可以获得模型的输入：t时刻的速度差ΔV(t)，t时刻的跟驰间距ΔX(t)，跟驰车辆在t+T时刻的速度v n(t+T)。输出跟驰车辆的瞬时加速度a n，通过控制车辆的加速度变化，计算车辆的跟驰速度，从而控制车辆的运行。
参考图13(a)、图13(b)是跟驰模型的预测结果，其中图13(a)是预测的跟驰车辆速度曲线，图13(b)是预测的车辆位移曲线。图中最上面的曲线为前导车辆的真实曲线，中间的曲线为跟驰车辆的真实曲线，下面的曲线为模型控制输出的预测曲线。
申请实施例提供了一种车辆跟驰控制系统，该系统用于执行上述实施例所述的车辆跟驰控制方法，如图14所示，该系统包括：采集识别模块501，用于采集并处理道路交叉口交通数据，识别并提取车辆跟驰行为；微观交通信息获取模块502，用于构建车辆2D边界盒模型，获取高分辨微观交通信息，所述高分辨微观交通信息包括车辆的瞬时速度和跟驰间距；判断超车意愿模块503，用于根据所述高分辨率微观交通信息，分析同一车道上目标车辆与前导车辆的运行状态，同时分析车辆的瞬时速度及跟驰间距随时间变化的曲线，判断分析目标车辆驾驶员是否具有超车意愿；跟驰控制模块504，用于针对不同驾驶员意愿，采用相应的车辆跟驰控制方法控制车辆运行。
本申请的上述实施例提供的车辆跟驰控制系统与本申请实施例提供的车辆跟驰控制方法出于相同的发明构思，具有与其存储的应用程序所采用、运行或实现的方法相同的有益效果。本申请实施方式还提供一种与前述实施方式所提供的车辆跟驰控制方法对应的电子设备，以执行上车辆跟驰控制方法。本申请实施例不做限定。
请参考图15，其示出了本申请的一些实施方式所提供的一种电子设备的示意图。如图15所示，所述电子设备20包括：处理器200，存储器201，总线202和通信接口203，所述处理器200、通信接口203和存储器201通过总线202连接；所述存储器201中存储有可在所述处理器200上运行的 计算机程序，所述处理器200运行所述计算机程序时执行本申请前述任一实施方式所提供的车辆跟驰控制方法。
其中，存储器201可能包含高速随机存取存储器(RAM：Random Access Memory)，也可能还包括非不稳定的存储器(non-volatile memory)，例如至少一个磁盘存储器。通过至少一个通信接口203(可以是有线或者无线)实现该系统网元与至少一个其他网元之间的通信连接，可以使用互联网、广域网、本地网、城域网等。总线202可以是ISA总线、PCI总线或EISA总线等。所述总线可以分为地址总线、数据总线、控制总线等。其中，存储器201用于存储程序，所述处理器200在接收到执行指令后，执行所述程序，前述本申请实施例任一实施方式揭示的所述车辆跟驰控制方法可以应用于处理器200中，或者由处理器200实现。处理器200可能是一种集成电路芯片，具有信号的处理能力。在实现过程中，上述方法的各步骤可以通过处理器200中的硬件的集成逻辑电路或者软件形式的指令完成。上述的处理器200可以是通用处理器，包括中央处理器(Central Processing Unit，简称CPU)、网络处理器(Network Processor，简称NP)等；还可以是数字信号处理器(DSP)、专用集成电路(ASIC)、现成可编程门阵列(FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件。可以实现或者执行本申请实施例中的公开的各方法、步骤及逻辑框图。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。结合本申请实施例所公开的方法的步骤可以直接体现为硬件译码处理器执行完成，或者用译码处理器中的硬件及软件模块组合执行完成。软件模块可以位于随机存储器，闪存、只读存储器，可编程只读存储器或者电可擦写可编程存储器、寄存器等本领域成熟的存储介质中。该存储介质位于存储器201，处理器200读取存储器201中的信息，结合其硬件完成上述方法的步骤。本申请实施例提供的电子设备与本申请实施例提供的车辆跟驰控制方法出于相同的发明构思，具有与其采用、运行或实现的方法相同的有益效果。
本申请实施方式还提供一种与前述实施方式所提供的车辆跟驰控制方法对应的计算机可读存储介质，请参考图16，其示出的计算机可读存储介质为光盘30，其上存储有计算机程序(即程序产品)，所述计算机程序在被处理器运行时，会执行前述任意实施方式所提供的车辆跟驰控制方法。
需要说明的是，所述计算机可读存储介质的例子还可以包括，但不限于相变内存(PRAM)、静态随机存取存储器(SRAM)、动态随机存取存储器(DRAM)、其他类型的随机存取存储器(RAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、快闪记忆体或其他光学、磁性存储介质，在此不再一一赘述。
本申请的上述实施例提供的计算机可读存储介质与本申请实施例提供的车辆跟驰控制方法出于相同的发明构思，具有与其存储的应用程序所采用、运行或实现的方法相同的有益效果。

Claims (10)

  1. 一种车辆跟驰控制方法，其特征在于，所述方法包括步骤：
    S1：采集并处理道路交叉口交通数据，识别并提取车辆跟驰行为；
    S2：构建车辆2D边界盒模型，获取高分辨率微观交通信息，所述高分辨率微观交通信息包括车辆的瞬时速度和跟驰间距；
    S3：根据所述高分辨率微观交通信息，分析同一车道上目标车辆与前导车辆的运行状态，同时分析车辆的瞬时速度及跟驰间距随时间变化的曲线，判断分析目标车辆驾驶员是否具有超车意愿；
    S4：针对不同驾驶员意愿，采用相应的车辆跟驰控制方法控制车辆运行。
  2. 根据权利要求1所述的车辆跟驰控制方法，其特征在于，步骤S1包括：交通数据采集，点云数据背景滤除，交通目标检测，车辆运行轨迹提取，跟驰行为识别与提取。
  3. 根据权利要求2所述的车辆跟驰控制方法，其特征在于，所述交通目标检测方法为DBSCAN聚类算法，首先根据激光雷达点云数据的特点和交通目标点云的空间排布规律，选定预设的聚类半径和最小聚类点个数，进行目标检测，然后根据坐标关系清除所有道路空间之外区域的交通目标，再根据不同交通目标的点云特征差异，从所有目标中识别提取出车辆目标，并记录每个车辆目标在道路空间中的位置。
  4. 根据权利要求1所述的车辆跟驰控制方法，其特征在于，步骤S2所述的构建车辆2D边界盒模型方法包括：首先将车辆目标点云投影至XOY平面，然后对目标点云进行凸包点提取，最后根据最小面积法原理构建边界盒模型。
  5. 根据权利要求1所述的车辆跟驰控制方法，其特征在于，步骤S2所述获取高分辨率微观交通信息的方法为：
    通过边界盒模型估计车辆的尺寸，并确定出车头的位置；比较相邻帧中车辆的位置变化，计算得到车辆的瞬时速度；比较跟驰过程中前后两车的位置关系，计算得到跟驰间距。
  6. 根据权利要求5所述的车辆跟驰控制方法，其特征在于，
    所述车辆的瞬时速度v i和跟驰间距D gap的计算方法如下：
    Figure PCTCN2022109003-appb-100001
    Figure PCTCN2022109003-appb-100002
    D gap＝D head-L p    (3)
    其中v i为目标车辆的瞬时速度，(x i(k-1)，y i(k-1))和(x i(k)，y i(k))分别为车辆在t k-1时刻和t k时刻的车头位置坐标，D head和D gap分别为两车的车头间距与跟驰间距，(x p，y p)和(x f，y f)分别为前导车辆和跟驰车辆的车头位置坐标，L p为前导车辆的车长。
  7. 根据权利要求1所述的车辆跟驰控制方法，其特征在于，步骤S3所述判断分析目标车辆驾驶员是否具有超车意愿的方法为：统计分析跟驰间距随车速变化的情况，若跟驰间距随着速度的增大而减小，则驾驶员具有超车意愿；若跟驰间距随着速度的增大而增大，则驾驶员不具超车意愿。
  8. 根据权利要求7所述的车辆跟驰控制方法，其特征在于，所述针对不同驾驶员意愿，采用相应的车辆跟驰控制方法控制车辆运行，包括：若判断目标车辆驾驶员具有超车意愿，则采用考虑驾驶人超车意愿的跟驰模型对目标车辆进行速度控制，否则采用常态情况下的车辆跟驰控制策略。
  9. 根据权利要求8所述的车辆跟驰控制方法，其特征在于，所述考虑驾驶人超车意愿的跟驰模型，具体包括：
    Figure PCTCN2022109003-appb-100003
    其中a n(t+T)是第n个跟驰车辆在t+T时刻的加速度，v n(t+T)是第n个跟驰车辆在t+T时刻的速度，ΔV(t)是第n个跟驰车辆与第n-1个车辆在t时刻的速度差，ΔX(t)是两车在t时刻的间隔距离；λ N，m N，l N为常态跟驰下的车辆跟驰控制方法的模型参数，λ Y，m Y，l Y为考虑驾驶员超车意愿的车辆跟驰控制方法的模型参数。
  10. 根据权利要求8所述的车辆跟驰控制方法，其特征在于，考虑驾驶员超车意愿的车辆跟驰控制在通过模型控制的同时，另外引入两个距离参数：最小安全距离D safe和变道距离D change；
    首先判断跟驰间距D gap与D change的大小，若D gap>D change，则继续执行考虑驾驶员超车意愿的车辆跟驰控制策略；若D gap<D change，接着判断左侧车道是否满足超车变道的条件；若满足条件，车辆执行变道超车的控制策略；若不满足条件，再判断跟驰间距D gap与D safe的大小；若D gap>D safe，则继续执行考虑驾驶员超车意愿的车辆跟驰控制策略；若D gap<D safe，车辆放弃超车意愿，执行常态跟驰下的车辆跟驰控制策略，直到满足D gap>D safe后，再重新执行考虑驾驶员超车意愿的车辆跟驰控制策略。
PCT/CN2022/109003 2022-05-06 2022-07-29 一种车辆跟驰控制方法和系统 Ceased WO2023213018A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210484862.0A CN114596712B (zh) 2022-05-06 2022-05-06 一种车辆跟驰控制方法和系统
CN202210484862.0 2022-05-06

Publications (1)

Publication Number Publication Date
WO2023213018A1 true WO2023213018A1 (zh) 2023-11-09

Family

ID=81820421

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/109003 Ceased WO2023213018A1 (zh) 2022-05-06 2022-07-29 一种车辆跟驰控制方法和系统

Country Status (2)

Country Link
CN (1) CN114596712B (zh)
WO (1) WO2023213018A1 (zh)

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117246333A (zh) * 2023-11-16 2023-12-19 北京航空航天大学 一种基于近场预知信息的车辆驱制动需求预测方法
CN117994987A (zh) * 2024-04-07 2024-05-07 东南大学 基于目标检测技术的交通参数提取方法及相关装置
CN118430306A (zh) * 2024-04-22 2024-08-02 福建理工大学 一种自动驾驶车辆智能选择跟驰车辆的方法及终端
CN118781840A (zh) * 2024-07-26 2024-10-15 同济大学 城市生态道路车联网混合交通流节碳驾驶策略
CN118953350A (zh) * 2024-10-15 2024-11-15 吉林大学 一种智能网联环境下基于前车作用的车辆跟驰控制系统
CN119283905A (zh) * 2024-11-12 2025-01-10 合肥工业大学 一种弯坡路段的车辆跟驰运动规划方法
CN119763348A (zh) * 2024-12-25 2025-04-04 北京交通大学 车联网环境下城市混合交通流基本图模型分析方法及系统
CN119863922A (zh) * 2024-12-06 2025-04-22 东南大学 一种考虑物理约束的车辆轨迹重构方法
CN120510714A (zh) * 2025-07-22 2025-08-19 新疆睿数云鼎信息科技有限公司 一种基于大数据的智慧交通监测系统
CN120781671A (zh) * 2025-06-27 2025-10-14 河北交通投资集团有限公司 一种理论-数据双驱动的车辆跟驰行为建模方法

Families Citing this family (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114596712B (zh) * 2022-05-06 2022-07-19 苏州大学 一种车辆跟驰控制方法和系统
CN115188184B (zh) * 2022-06-20 2024-03-19 海信集团控股股份有限公司 一种车辆限速处理方法、设备及装置
CN114822044B (zh) * 2022-06-29 2022-09-09 山东金宇信息科技集团有限公司 一种基于隧道的行车安全预警方法及设备
CN115147783B (zh) * 2022-07-15 2025-03-25 深圳大学 一种车辆计数方法、装置、电子设备及存储介质
CN115168810B (zh) * 2022-09-08 2022-11-29 南京慧尔视智能科技有限公司 一种交通数据的生成方法、装置、电子设备和存储介质
CN115384495A (zh) * 2022-09-22 2022-11-25 中国银行股份有限公司 一种车辆控制方法、装置、设备及介质
CN116089842B (zh) * 2023-02-23 2025-11-25 同济大学 一种视频轨迹数据集车道全域跟驰车对匹配及提取方法
CN116626649B (zh) * 2023-05-04 2026-03-10 苏州大学 一种基于激光雷达的航道船舶流量统计方法和系统
CN116543581B (zh) * 2023-05-10 2026-03-03 江苏大学 一种基于车路协同技术的信息辅助驾驶方法
CN118609416B (zh) * 2024-04-23 2025-01-28 武汉理工大学 一种移动式路侧行人交通冲突监测与预警装置及方法

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1719354A (zh) * 2005-05-08 2006-01-11 上海交通大学 车辆跟驰运动的加速度控制方法
JP2006259948A (ja) * 2005-03-16 2006-09-28 Clarion Co Ltd 安全車間距離表示装置
CN108682184A (zh) * 2018-04-25 2018-10-19 江苏大学 一种应用于双向两车道的车辆超车辅助控制方法及系统
CN110299004A (zh) * 2019-07-31 2019-10-01 山东理工大学 交叉口转弯车辆的跟驰模型建立及其稳定性分析方法
CN113487874A (zh) * 2021-05-27 2021-10-08 中汽研（天津）汽车工程研究院有限公司 一种跟驰行为场景数据采集、识别、分类提取系统及方法
CN114596712A (zh) * 2022-05-06 2022-06-07 苏州大学 一种车辆跟驰控制方法和系统

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106926844B (zh) * 2017-03-27 2018-10-19 西南交通大学 一种基于实时环境信息的动态自动驾驶换道轨迹规划方法
CN110597245B (zh) * 2019-08-12 2020-11-20 北京交通大学 基于二次型规划和神经网络的自动驾驶换道轨迹规划方法
CN110941901B (zh) * 2019-11-26 2023-06-30 北方工业大学 一种自主驾驶方法及其系统
CN111645692B (zh) * 2020-06-02 2021-08-24 中国科学技术大学先进技术研究院 基于混合策略博弈的驾驶人超车意图识别方法及系统
CN111994088A (zh) * 2020-09-02 2020-11-27 中国科学技术大学 基于混合策略博弈的驾驶人换道意图识别方法及系统

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2006259948A (ja) * 2005-03-16 2006-09-28 Clarion Co Ltd 安全車間距離表示装置
CN1719354A (zh) * 2005-05-08 2006-01-11 上海交通大学 车辆跟驰运动的加速度控制方法
CN108682184A (zh) * 2018-04-25 2018-10-19 江苏大学 一种应用于双向两车道的车辆超车辅助控制方法及系统
CN110299004A (zh) * 2019-07-31 2019-10-01 山东理工大学 交叉口转弯车辆的跟驰模型建立及其稳定性分析方法
CN113487874A (zh) * 2021-05-27 2021-10-08 中汽研（天津）汽车工程研究院有限公司 一种跟驰行为场景数据采集、识别、分类提取系统及方法
CN114596712A (zh) * 2022-05-06 2022-06-07 苏州大学 一种车辆跟驰控制方法和系统

Cited By (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117246333A (zh) * 2023-11-16 2023-12-19 北京航空航天大学 一种基于近场预知信息的车辆驱制动需求预测方法
CN117246333B (zh) * 2023-11-16 2024-01-16 北京航空航天大学 一种基于近场预知信息的车辆驱制动需求预测方法
CN117994987A (zh) * 2024-04-07 2024-05-07 东南大学 基于目标检测技术的交通参数提取方法及相关装置
CN117994987B (zh) * 2024-04-07 2024-06-11 东南大学 基于目标检测技术的交通参数提取方法及相关装置
CN118430306A (zh) * 2024-04-22 2024-08-02 福建理工大学 一种自动驾驶车辆智能选择跟驰车辆的方法及终端
CN118781840A (zh) * 2024-07-26 2024-10-15 同济大学 城市生态道路车联网混合交通流节碳驾驶策略
CN118953350A (zh) * 2024-10-15 2024-11-15 吉林大学 一种智能网联环境下基于前车作用的车辆跟驰控制系统
CN119283905A (zh) * 2024-11-12 2025-01-10 合肥工业大学 一种弯坡路段的车辆跟驰运动规划方法
CN119863922A (zh) * 2024-12-06 2025-04-22 东南大学 一种考虑物理约束的车辆轨迹重构方法
CN119763348A (zh) * 2024-12-25 2025-04-04 北京交通大学 车联网环境下城市混合交通流基本图模型分析方法及系统
CN120781671A (zh) * 2025-06-27 2025-10-14 河北交通投资集团有限公司 一种理论-数据双驱动的车辆跟驰行为建模方法
CN120510714A (zh) * 2025-07-22 2025-08-19 新疆睿数云鼎信息科技有限公司 一种基于大数据的智慧交通监测系统

Also Published As

Publication number Publication date
CN114596712B (zh) 2022-07-19
CN114596712A (zh) 2022-06-07

Similar Documents

Publication Publication Date Title
WO2023213018A1 (zh) 一种车辆跟驰控制方法和系统
US12254680B2 (en) Traffic flow machine-learning modeling system and method applied to vehicles
CN110632617B (zh) 一种激光雷达点云数据处理的方法及装置
CN110843789A (zh) 一种基于时序卷积网络的车辆换道意图预测方法
CN109101939B (zh) 车辆运动状态的确定方法、系统、终端及可读存储介质
CN112258893B (zh) 一种基于轨道预测的智能车辆换道碰撞概率评估方法
CN114973195A (zh) 基于多信息融合的车辆追踪方法、装置及系统
CN112614373A (zh) 一种基于BiLSTM周车换道意图预测方法
CN115292435A (zh) 高精地图的更新方法和装置、电子设备和存储介质
CN118025155A (zh) 一种跟车目标确定方法、设备、车辆及程序产品
WO2023087157A1 (zh) 一种智能驾驶方法及应用该方法的车辆
CN115482515A (zh) 自动驾驶车辆的可通行空间动态融合方法及装置
KR20210077043A (ko) 주행 차로 판단 장치 및 그의 주행 차로 판단 방법
WO2021170140A1 (zh) 一种车道结构检测方法及装置
CN119190001B (zh) 车辆避障轨迹规划方法、装置、计算机设备和存储介质
CN115909305A (zh) 一种车辆信息识别方法、装置、设备及存储介质
CN115431945B (zh) 目标筛选方法、装置、设备、介质及车辆
JP7532569B2 (ja) 歩行者の位置を決定する方法及び装置
CN116645808A (zh) 一种基于车辆运行状态的拥堵分析方法及系统
CN115482511A (zh) 一种基于平滑车辆运动数据的车辆轨迹生成方法及系统
CN115542250A (zh) 用于雷达数据处理的方法和系统
US12597244B2 (en) Method and device for improving object recognition rate of self-driving car
CN118941588B (zh) 障碍物信息处理方法、装置、车辆及程序产品
CN116129654B (zh) 一种车辆行驶数据预测方法、装置、电子设备及可读介质
Yang et al. An Improved Car-Following Model with Consideration of Driver's Overtaking Intention

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22940712

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 22940712

Country of ref document: EP

Kind code of ref document: A1