CN115423303A - V2X dynamic electronic lane planning method and device based on dynamic traffic flow - Google Patents

V2X dynamic electronic lane planning method and device based on dynamic traffic flow Download PDF

Info

Publication number
CN115423303A
CN115423303A CN202211055960.9A CN202211055960A CN115423303A CN 115423303 A CN115423303 A CN 115423303A CN 202211055960 A CN202211055960 A CN 202211055960A CN 115423303 A CN115423303 A CN 115423303A
Authority
CN
China
Prior art keywords
lane
dynamic
neural network
width
network model
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.)
Pending
Application number
CN202211055960.9A
Other languages
Chinese (zh)
Inventor
宦涣
闫学亮
孙亚风
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.)
Yunkong Zhihang Shanghai Automotive Technology Co ltd
Original Assignee
Yunkong Zhihang Shanghai Automotive Technology Co ltd
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 Yunkong Zhihang Shanghai Automotive Technology Co ltd filed Critical Yunkong Zhihang Shanghai Automotive Technology Co ltd
Priority to CN202211055960.9A priority Critical patent/CN115423303A/en
Publication of CN115423303A publication Critical patent/CN115423303A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/26—Government or public services
    • 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
    • G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
    • G08G1/012—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from other sources than vehicle or roadside beacons, e.g. mobile networks
    • 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
    • G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
    • 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
    • G08G1/065—Traffic control systems for road vehicles by counting the vehicles in a section of the road or in a parking area, i.e. comparing incoming count with outgoing count

Landscapes

  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Theoretical Computer Science (AREA)
  • Tourism & Hospitality (AREA)
  • Chemical & Material Sciences (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Educational Administration (AREA)
  • Marketing (AREA)
  • Development Economics (AREA)
  • Analytical Chemistry (AREA)
  • General Business, Economics & Management (AREA)
  • Health & Medical Sciences (AREA)
  • Game Theory and Decision Science (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Primary Health Care (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Computational Linguistics (AREA)
  • Software Systems (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Traffic Control Systems (AREA)

Abstract

The application relates to the technical field of intelligent management and control system application, in particular to a V2X dynamic electronic lane planning method and device based on dynamic traffic flow. The method comprises the step of based on X 0 And the average number of vehicles per lane per time sliceAnd average vehicle speed, constructing an input feature vector
Figure DDA0003824952470000011
Constructing output characteristic vector based on width proportion of manually divided lanes
Figure DDA0003824952470000012
Constructing a training set, a verification set and a test set based on historical traffic data of a preset period of manually dividing lanes; constructing a shallow neural network model, including an activation function Softmax and a loss function D (P, Y); performing iterative training on the shallow neural network model parameters; testing the neural network model which completes parameter training; and if the test reaches the preset accuracy, deploying to a dynamic electronic lane planning environment. The electronic lane planning method and device based on the high-precision GNSS positioning and the roadside device information dynamically adjust the electronic lane planning of the current traffic environment in real time, and achieve the electronic lane effects of flexibility, easiness in maintenance and multiple available scenes.

Description

V2X dynamic electronic lane planning method and device based on dynamic traffic flow
Technical Field
The application relates to the technical field of intelligent management and control system application, in particular to a V2X dynamic electronic lane planning method and device based on dynamic traffic flow.
Background
In order to make road traffic smooth, traffic control departments may divide lanes of a road, and commonly divide opposing lanes, fast and slow lanes, and the like according to a driving direction and a driving speed. Conventionally, traffic management departments plan lanes of roads in advance, and use special paint on physical road surfaces to divide lanes so as to distinguish functions and use permissions of different areas of the same road surface. The lane division not only meets the traffic standard, but also meets the traffic flow requirement of the actual road section. When the vehicle runs on the road divided into fixed lanes according to the principle, the blindness of traffic flow simplification and traffic jam and traffic accident avoidance can be achieved indirectly according to the preset design targets (driving direction limitation and driving speed limitation) of the lanes.
Although the traditional fixed lane scheme has achieved a more obvious effect, the traditional fixed lane scheme still has shortcomings. The main performance is as follows: 1) The lane lines are printed on the surface of the road, and special persons are required to regularly check and maintain to ensure the usability of the lane lines, so that the maintenance cost is high; 2) In the actual situation, the optimal lane marking method is different according to different factors such as weather conditions and traffic flow timeliness, and the traditional lane fixing mode is inconvenient for dynamically adjusting the lane marking method, namely the position, to meet the requirement of road condition change in a short time; 3) In some special occasions, such as grasslands, rural roads and the like, which are not suitable for dividing fixed lanes by using paint and require the fixed lanes to provide assistance for drivers in practical use, the traditional lane lines also cannot effectively play a role.
Therefore, it is desirable to provide a method and a device for planning a dynamic V2X electronic lane based on a dynamic traffic flow, which are implemented by integrating high-precision satellite positioning information GNSS, lane trace information described by the V2X communication method, and road side equipment to recognize the sensed traffic states near the lane in real time, such as the driving states of all traffic participants, the average speed, the average number of vehicles, and the like. The method dynamically adjusts the trace point GNSS coordinate position of the central lines of a plurality of lanes in the road in the MAP message in the V2X communication mechanism according to the road condition and the traffic condition, and broadcasts the trace point GNSS coordinate position to the vehicles with V2X communication capability at the periphery so as to realize the effect of presenting dynamic electronic lanes for the vehicles.
Disclosure of Invention
According to a first aspect of some embodiments of the present application, there is provided a dynamic traffic flow-based V2X dynamic electronic lane planning method applied in a terminal (e.g., an internet-connected vehicle, etc.), which may include S1: obtaining the total width X of the road 0 And the number m of lanes, and setting a time slice interval n; based on X 0 And the average vehicle number and the average vehicle speed of each lane in each time slice to construct an input feature vector
Figure BDA0003824952450000021
Includes 2m +1 attribute values; constructing output characteristic vector based on width proportion of manually divided lanes
Figure BDA0003824952450000022
Comprises m attribute values; s2: extracting information of each line according to the S1 field based on historical traffic data of a preset period of manually dividing lanes, and constructing a training set, a verification set and a test set; s3: constructing a shallow neural network model, wherein an activation function Softmax is used for determining that the sum of the lane width distribution proportions is 1, a loss function D (P,y) Lane width based prediction
Figure BDA0003824952450000025
Cross entropy in proportion to manual partitioning; s4: performing iterative training on the shallow neural network model parameters based on the training set constructed in the S2 and the loss function of the S3 to determine the optimal weights and offset parameters of the Wr and br parameters, and performing overfitting verification based on the verification set constructed in the S2; s5: testing the neural network model which completes parameter training based on the test set constructed in the S2, and returning to the S4 training if the test does not reach the preset accuracy; s6: and if the test reaches the preset accuracy, deploying to a dynamic electronic lane planning environment.
In some embodiments, road traffic data is collected in real time according to road side sensing equipment, an input feature vector is constructed, and a trained neural network model is input to obtain the prediction of the real-time division ratio of the electronic lane; distributing the total width of the current road to each lane according to a prediction proportion, and calculating the center line trace coordinates of each lane based on the GNSS road center line trace coordinates; and updating the MAP message of the V2X communication message according to the width of each lane and the center line trace coordinate information, and broadcasting the message as dynamic electronic lane information to the networked vehicles within a preset distance after coding the message.
In some embodiments, when the number of lanes m =3, specifically including obtaining the average number of vehicles passing by lane 1 per n second time slice X 1 Average speed X of lane 1 in n second time slices 2 Average number of vehicles passing through lane 2 in n second time slice 3 Average speed X of lane 2 in n second time slice 4 Average number of vehicles passing through lane 3 in n-second time slice 5 Average speed X of lane 3 in n second time slice 6 Constructing an input eigenvector X = [ X ] 0 ,X 1 ,X 2 ,X 3 ,X 4 ,X 5 ,X 6 ](ii) a Lane 1, lane 2 and lane 3 width proportion Y based on manual division 0 、Y 1 、Y 2 Constructing an output eigenvector Y = [ Y ] 0 ,Y 1 ,Y 2 ]Wherein
Figure BDA0003824952450000023
In some embodiments, the constructing the shallow neural network model specifically includes:
Figure BDA0003824952450000024
wherein, X 0 To X 6 For the input feature vector, P, defined in S1 with a strong correlation with the lane width division ratio 0 、P 1 、P 2 Is a target lane width distribution, w ij For using real-time traffic characteristics X j Calculating the ith lane width P i Weight coefficient required for time, b i To calculate the offset to be added for the ith lane width, w ij ，b i Determined by training.
In some embodiments, the activating function Softmax specifically includes:
Figure BDA0003824952450000031
wherein the activation function Softmax is used for determining that the sum of the distribution proportions of the lane widths is 1,Z i Is the output value of the ith node of the last layer of the neural network.
In some embodiments, features P having the form of a probability distribution are output according to the model 0 +P 1 +P 2 =1, the loss function D (P, Y) specifically includes:
Figure BDA0003824952450000032
wherein the loss function D (P, Y) is based on lane width prediction
Figure BDA0003824952450000033
Cross entropy in proportion to artificial division, Y i Is the actual width ratio of the road i, P i Obtained for the road i by model predictionWidth ratio.
In some embodiments, the iteratively training the shallow neural network model parameters specifically includes iteratively training the neural network model parameters on a high performance server based on the training set and the loss function by using a BP algorithm.
In some embodiments, the step of testing whether the neural network model completing the parameter training reaches a preset accuracy includes randomly extracting data in a preset period from a test set and dividing the data into 4 groups according to traffic flow conditions, wherein the 4 groups include no congestion, light congestion, moderate congestion and heavy congestion, and 1000 pieces of data are fixed in each group; predicting each data in the 4 groups of data by using a neural network model which completes parameter training, and if the corresponding probability maximum item in the predicted guide lane use probability distribution is the same as the use of a lane actually planned by an artificial driver, determining that the prediction is correct; if not, determining that the prediction is wrong; respectively counting the accuracy of the prediction results of the 4 groups of data, wherein the accuracy is the ratio of the number of correct times of prediction of each group to the total number of test data of each group, and if the accuracy is respectively greater than a preset threshold corresponding to each group, determining that the actual use requirement is met; if not, the actual use requirement is not met.
In some embodiments, the accuracy is greater than a preset threshold corresponding to each group, specifically including 70% of no congestion, 75% of light congestion, 80% of moderate congestion, and 85% of heavy congestion.
According to a second aspect of some embodiments of the present application, there is provided a dynamic traffic flow-based V2X dynamic electronic lane planning apparatus, comprising a memory configured to store data and instructions; a processor in communication with the memory, wherein the processor, when executing instructions in the memory, is configured to: s1: obtaining the total width X of the road 0 And the number m of lanes, and setting a time slice interval n; based on X 0 And the average vehicle number and the average vehicle speed of each lane in each time slice to construct an input feature vector
Figure BDA0003824952450000034
Includes 1 attribute value of 2m +; constructing output characteristic vector based on width proportion of manually divided lanes
Figure BDA0003824952450000035
Comprises m attribute values; s2: extracting information of each line according to the S1 field based on historical traffic data of a preset period of manually dividing lanes, and constructing a training set, a verification set and a test set; s3: constructing a shallow neural network model, wherein an activation function Softmax is used for determining that the sum of the lane width distribution proportions is 1, and a loss function D (P, Y) is predicted based on the lane width
Figure BDA0003824952450000036
Cross entropy in proportion to manual partitioning; s4: performing iterative training on the shallow neural network model parameters based on the training set constructed in the S2 and the loss function of the S3 to determine the optimal weights and offset parameters of the Wr and br parameters, and performing overfitting verification based on the verification set constructed in the S2; s5: testing the neural network model which completes parameter training based on the test set constructed in the S2, and returning to the S4 training if the test does not reach the preset accuracy; s6: and if the test reaches the preset accuracy, deploying to a dynamic electronic lane planning environment.
Therefore, according to some embodiments of the present application, a method and an apparatus for V2X dynamic electronic lane planning based on dynamic traffic flow provide an automatic dynamic electronic lane division method and apparatus by fusing high-precision satellite positioning information GNSS, lane trace information described based on the V2X communication method, and roadside devices to recognize the sensed traffic states near the lane in real time, such as the driving states of all the traffic participants, the average vehicle speed, the average number of vehicles, etc. The method automatically and dynamically adjusts the trace point GNSS coordinate position used for the center lines of a plurality of lanes in the road in the MAP message in the V2X communication mechanism according to the road condition and the traffic condition, and broadcasts the trace point GNSS coordinate position to the vehicles with V2X communication capability at the periphery so as to realize the effect of presenting dynamic electronic lanes.
Drawings
For a better understanding and appreciation of some embodiments of the present application, reference will now be made to the description of embodiments taken in conjunction with the accompanying drawings, in which like reference numerals designate corresponding parts in the figures.
Fig. 1 is an exemplary schematic diagram of a dynamic traffic flow based V2X dynamic electronic lane planning system provided in accordance with some embodiments of the present application.
Fig. 2 is an exemplary flow diagram of a dynamic traffic flow based V2X dynamic electronic lane planning method provided in accordance with some embodiments of the present application.
Detailed Description
The following description, with reference to the accompanying drawings, is provided to facilitate a comprehensive understanding of various embodiments of the application as defined by the claims and their equivalents. These embodiments include various specific details for ease of understanding, but these are to be considered exemplary only. Accordingly, those skilled in the art will appreciate that various changes and modifications may be made to the various embodiments described herein without departing from the scope and spirit of the present application. In addition, descriptions of well-known functions and constructions will be omitted herein for brevity and clarity.
The terms and phrases used in the following specification and claims are not to be limited to the literal meaning, but are merely for the clear and consistent understanding of the application. Therefore, it will be understood by those skilled in the art that the description of the various embodiments of the present application is provided for illustration only and not as a limitation of the application defined by the appended claims and their equivalents.
The technical solutions in the embodiments of the present application will be described clearly and completely with reference to the drawings in some embodiments of the present application, and it is obvious that the described embodiments are only some embodiments of the present application, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It is to be understood that the terminology used in the embodiments of the present application is for the purpose of describing particular embodiments only, and is not intended to be limiting of the application. As used in the examples of this application and the appended claims, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items. The expressions "first", "second", "said first" and "said second" are used for modifying the corresponding elements without regard to order or importance and are only used for distinguishing one element from another element without limiting the corresponding elements.
Terminals according to some embodiments of the present application may be intelligent terminals, platforms, equipment and/or electronic devices, etc.; the intelligent terminal can comprise a positioning device and the like. The platform can comprise a cloud platform and the like, and the platform can comprise a system platform consisting of one or more electronic devices; the equipment may include Intelligent networked vehicles (ICV); the electronic device may include one or a combination of a personal computer (PC, e.g., tablet, desktop, notebook, netbook, PDA), a client device, a virtual reality device (VR), an augmented reality device (AR), a mixed reality device (MR), an XR device, a renderer, a smartphone, a mobile phone, an e-book reader, a Portable Multimedia Player (PMP), an audio/video player (MP 3/MP 4), a camera, a wearable device, and so forth. According to some embodiments of the present application, the wearable device may include an accessory type (e.g., watch, ring, bracelet, glasses, or Head Mounted Device (HMD)), an integrated type (e.g., electronic garment), a decorative type (e.g., skin pad, tattoo, or built-in electronic device), and the like, or a combination of several. In some embodiments of the present application, the electronic device may be flexible, not limited to the above devices, or may be a combination of one or more of the above devices. In this application, the term "user" may indicate a person using an electronic device or a device using an electronic device (e.g., an artificial intelligence electronic device).
The embodiment of the application provides a V2X dynamic electronic lane planning method and device based on dynamic traffic flow. In order to facilitate understanding of the embodiments of the present application, the embodiments of the present application will be described in detail below with reference to the accompanying drawings.
Fig. 1 is an exemplary schematic diagram of a dynamic traffic flow based V2X dynamic electronic lane planning system provided in accordance with some embodiments of the present application. As shown in fig. 1, the dynamic traffic flow-based V2X dynamic electronic lane planning system 100 may include a network 110, an information terminal 120, a user terminal 130, a server 140, and the like. Specifically, the information end 120 and the user end 130 establish communication through a network, for example, the information end 120 and the user end 130 can communicate in the same local area network (e.g., the network environment of the same router, etc.). Further, the information terminal 120 may be connected to the network 110 in a wired (e.g., network cable, etc.) or wireless (e.g., cloud server, etc.), and the user terminal 130 may establish a communication connection with the network 110 in a wired or wireless (e.g., WIFI, etc.) manner. In some embodiments, the user terminal 130 may send high-precision satellite positioning information GNSS to the information terminal 120, the server 140, and the like. Further, the information terminal 120 and the server 140 may feed back dynamic electronic lane information and the like to the user terminal 130. For example, the server 140 and/or the information terminal 120 may acquire data such as GNSS road center line trace coordinates based on a roadside device, or collect road traffic data in real time according to a roadside sensing device. The roadside apparatus (RSU) may sense road environment information, obstacle information, etc. through sensors, which may include, but are not limited to, a camera, a lidar, a millimeter wave radar, etc.
According to some embodiments of the present application, the information end 120 and the user end 130 may be the same or different terminal devices, and the like. The terminal device may include, but is not limited to, a smart terminal, a cloud platform, a mobile terminal, a computer, and the like. In a dynamic electronic lane scenario, the information terminal 120 may include road side equipment and the like, and the user terminal 130 may include a positioning device and the like. In some embodiments, the information end 120 and the user end 130 may be integrated into one device, such as a positioning device integrated with a sensor. In some embodiments, server 140 is one type of computer that has the advantages of running faster, being more heavily loaded, etc. than a normal computer, and being correspondingly more expensive. In a network environment, a server may provide computing or application services to other clients (e.g., terminals such as PCs, smart phones, ATMs, and large appliances such as transportation systems). The server has high-speed CPU computing capability, long-time reliable operation, strong I/O external data throughput capability and better expansibility. The services that the server may provide include, but are not limited to, the ability to undertake responding to service requests, undertake services, secure services, and the like. The server, as an electronic device, has an extremely complex internal structure, including an internal structure similar to that of a general computer, and the like, and for example, the internal structure of the server may include a Central Processing Unit (CPU), a hard disk, a memory, a system bus, and the like.
In some embodiments of the present application, the dynamic traffic flow-based V2X dynamic electronic lane planning system 100 may omit one or more elements, or may further include one or more other elements. As an example, the dynamic traffic flow based V2X dynamic electronic lane planning system 100 may include a plurality of clients 130, such as a plurality of networked vehicles, and the like. As another example, the dynamic traffic flow-based V2X dynamic electronic lane planning system 100 may include one or more information terminals 120. As another example, the dynamic traffic flow-based V2X dynamic electronic lane planning system 100 may include a plurality of servers 140, or the like. In some embodiments, the dynamic traffic flow-based V2X dynamic electronic lane planning system 100 may include, but is not limited to, a dynamic electronic lane scene planning-based system. The Network 110 may be any type of communication Network, which may include a computer Network (e.g., a Local Area Network (LAN) or Wide Area Network (WAN)), the internet and/or a telephone Network, etc., or a combination of several. In some embodiments, the network 110 may be other types of wireless communication networks. The wireless communication may include microwave communication and/or satellite communication, among others. The Wireless communication may include cellular communication, such as Global System for Mobile Communications (GSM), code Division Multiple Access (CDMA), third Generation Mobile communication (3G, the 3rd Generation communication), fourth Generation Mobile communication (4G), fifth Generation Mobile communication (5G), sixth Generation Mobile communication (6G), long Term Evolution (LTE-a), LTE-Advanced, wideband Code Division Multiple Access (WCDMA, wideband Code Division Multiple Access), universal Mobile Telecommunications System (UMTS), wireless Broadband (Broadband ), and the like, or a combination of several or more. In some embodiments, the user terminal 130 may be other equipment and/or electronic devices with equivalent functional modules, and the equipment and/or electronic devices may include one or a combination of several of a virtual reality device (VR), a rendering machine, a personal computer (PC, such as a tablet computer, a desktop computer, a notebook, a netbook, a PDA, a smart phone, a mobile phone, an e-book reader, a Portable Multimedia Player (PMP), an audio/video player (MP 3/MP 4), a camera, and a wearable device.
In some embodiments, the WIFI may be other types of wireless communication technologies. According to some embodiments of the present application, the Wireless Communication may include Wireless local Area Network (WiFi), bluetooth Low Energy (BLE), zigBee (ZigBee), near Field Communication (NFC), magnetic security transmission, radio frequency and Body Area Network (BAN), or the like, or a combination of several. According to some embodiments of the present application, the wired communication may include a Global Navigation Satellite System (Global Navigation Satellite System), a Global Positioning System (GPS), a beidou Navigation Satellite System, a galileo (european Global Satellite Navigation System), or the like. The wired communication may include a Universal Serial Bus (USB), a High-Definition Multimedia Interface (HDMI), a recommended Standard 232 (RS-232, recommended Standard 232), and/or Plain Old Telephone Service (POTS), etc., or a combination of several.
It should be noted that the above description of the dynamic traffic flow based V2X dynamic electronic lane planning system 100 is only for convenience of description and is not intended to limit the scope of the present application to the illustrated embodiments. It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the principles of the system, which may be combined in any manner or combined with other elements to form a subsystem for use in a field of application in which the method and system described above is practiced. For example, the server 140 and/or the information terminal 120 may collect road traffic data in real time through a roadside sensing device or the like. Also for example, the information end 120/user end 130 may be integrated in a networked vehicle, or the like. Such variations are within the scope of the present application.
Fig. 2 is an exemplary flow diagram of a dynamic traffic flow based V2X dynamic electronic lane planning method provided in accordance with some embodiments of the present application. As illustrated in fig. 2, the process 200 may be implemented by the dynamic traffic flow-based V2X dynamic electronic lane planning system 100. In some embodiments, the dynamic traffic flow-based V2X dynamic electronic lane planning method 200 may be initiated automatically or by instruction. The instructions may include system instructions, device instructions, user instructions, action instructions, etc., or a combination of several.
At 201, S1: obtaining the total width X of the road 0 And the number m of lanes, and setting a time slice interval n; based on X 0 And the average vehicle number and the average vehicle speed of each lane in each time slice to construct an input feature vector
Figure BDA0003824952450000071
Includes 2m +1 attribute values; constructing output characteristic vector based on width proportion of manually divided lanes
Figure BDA0003824952450000081
Including m attribute values. Operation 201 may be implemented by the server 140 of the dynamic traffic flow-based V2X dynamic electronic lane planning system 100. In some embodiments, the user terminal 130 may transmit high-precision satellite positioning information GNSS based on high-precision GNSS positioning. In some embodiments, the server 140 may construct input feature vectors and output feature vectors, and the like. For example, the number of lanes m is equal to or greater than2, in this embodiment, m =3 is taken as an example. As an example, when the number of lanes m =3, it may include:
acquiring the average number X of vehicles passing through the lane 1 in each n-second time slice 1 Average speed X of lane 1 in n second time slices 2 Average number of vehicles passing through lane 2 in n second time slice 3 Average speed X of lane 2 in n second time slice 4 Average number of vehicles passing through lane 3 per n second time slice X 5 Average speed X of lane 3 in n second time slice 6 Constructing an input feature vector X = [ X ] 0 ,X 1 ,X 2 ,X 3 ,X 4 ,X 5 ,X 6 ](ii) a The time slice interval n may be set according to the traffic flow, and for example, includes a time slice interval of 10 seconds to 240 seconds, for example, 20 seconds, 60 seconds, and the like.
Lane 1, lane 2, lane 3 width ratio Y based on manual division 0 、Y 1 、Y 2 Constructing an output eigenvector Y = [ Y ] 0 ,Y 1 ,Y 2 ]Wherein
Figure BDA0003824952450000082
At 202, S2: based on historical traffic data of manually divided lanes in a preset period, extracting information of each line according to the S1 field, and constructing a training set, a verification set and a test set. Operation 202 may be implemented by the information terminal 120, the server 140 of the dynamic traffic flow based V2X dynamic electronic lane planning system 100. In some embodiments, the information terminal 120 and the server 140 may extract fields such as total road width, average vehicle number per lane, average vehicle speed, width ratio of manually divided lanes, and the like, extract historical traffic data, and construct a training set, a verification set, and a test set.
In some embodiments, the preset period may include a time range of 1 month to 24 months, e.g., 6 months, 12 months, etc. For example, based on 12-month historical traffic data of manually divided lanes, information of each line is extracted according to the S1 field, and a training set, a verification set, a test set, and the like are constructed.
At 203, S3: constructing a superficial neural networkA network model, wherein the activation function Softmax is used to determine that the sum of the lane width allocation proportions is 1, and the loss function D (P, Y) is based on the lane width prediction
Figure BDA0003824952450000083
Cross entropy in proportion to manual partitioning. Operation 203 may be implemented by the server 140 of the dynamic traffic flow-based V2X dynamic electronic lane planning system 100. In some embodiments, the server 140 may build a shallow neural network model.
For example, the constructing the shallow neural network model may include:
Figure BDA0003824952450000084
wherein, X 0 To X 6 For the input feature vector, P, defined in S1 with a strong correlation with the lane width division ratio 0 、P 1 、P 2 Is a target lane width distribution, w ij For using real-time traffic characteristics X j Calculating the ith lane width P i Weight coefficient required for time, b i To calculate the offset required to be added for the ith lane width, w ij ，b i Determined by training.
According to some embodiments of the application, the activation function Softmax may comprise:
Figure BDA0003824952450000091
wherein the activation function Softmax is used for determining that the sum of the distribution proportions of the lane widths is 1,Z i The output value of the ith node of the last layer of the neural network.
According to some embodiments of the application, the feature P having the form of a probability distribution is output according to the model 0 +P 1 +P 2 =1, the loss function D (P, Y) may include:
Figure BDA0003824952450000092
wherein the loss function D (P, Y) is based on lane width prediction
Figure BDA0003824952450000093
Cross entropy in proportion to artificial division, Y i Is the actual width ratio of the road i, P i The width ratio of the road i obtained through model prediction is obtained.
At 204, S4: and performing iterative training on the shallow neural network model parameters based on the training set constructed in the S2 and the loss function of the S3 to determine the optimal weights and offset parameters of the Wr and br parameters, and performing overfitting verification based on the verification set constructed in the S2. Operation 204 may be implemented by the server 140 of the dynamic traffic flow-based V2X dynamic electronic lane planning system 100. In some embodiments, the server 140 may iteratively train the shallow neural network model parameters to determine the optimal weights for the Wr, br parameters and the offset parameters.
According to some embodiments of the present application, the iteratively training the shallow neural network model parameters may include iteratively training the neural network model parameters on a high performance server based on the training set and the loss function by using a BP algorithm.
At 205, S5: and (3) testing the neural network model which completes the parameter training based on the test set constructed in the S2, and returning to the S4 training if the test does not reach the preset accuracy. Operation 205 may be implemented by the information terminal 120, the server 140 of the dynamic traffic flow based V2X dynamic electronic lane planning system 100. In some embodiments, the server 140 may test the neural network model that completes the parameter training.
As an example, the testing whether the neural network model completing the parameter training reaches the preset accuracy may include randomly extracting data in a preset period from a test set and dividing the data into 4 groups according to traffic flow conditions, where the 4 groups include no congestion, light congestion, moderate congestion, and heavy congestion, and each group has 1000 pieces of fixed data; predicting each data in the 4 groups of data by using a neural network model which completes parameter training, and if the maximum corresponding probability item in the predicted application probability distribution of the guide lane is the same as the application of the lane actually planned by manpower, determining that the prediction is correct; if not, determining that the prediction is wrong; respectively counting the accuracy of the prediction results of the 4 groups of data, wherein the accuracy is the ratio of the number of correct times of prediction of each group to the total number of test data of each group, and if the accuracy is respectively greater than a preset threshold corresponding to each group, determining that the actual use requirement is met; if not, determining that the actual use requirement is not met. The accuracy is respectively greater than the preset threshold corresponding to each group, and may include 70% of no congestion, 75% of light congestion, 80% of moderate congestion, and 85% of severe congestion.
At 206, S6: and if the test reaches the preset accuracy, deploying to a dynamic electronic lane planning environment. Operation 205 may be implemented by the information terminal 120, the server 140 of the dynamic traffic flow based V2X dynamic electronic lane planning system 100. In some embodiments, the information terminal 120, the server 140 may deploy the trained neural network model to a dynamic electronic lane planning environment.
According to some embodiments of the present application, the process 200 may further include constructing the input feature vector according to the road side sensing device collecting road traffic data in real time
Figure BDA0003824952450000101
Inputting the trained neural network model to obtain the prediction of the real-time division ratio of the electronic lane
Figure BDA0003824952450000102
(ii) a Distributing the total width of the current road to each lane according to a prediction proportion, and calculating the center line trace coordinates of each lane based on the GNSS road center line trace coordinates; and updating the MAP message of the V2X communication message according to the width of each lane and the center line trace coordinate information, and broadcasting the message as dynamic electronic lane information to the networked vehicles and the like within a preset distance after coding the message.
Specifically, in an actual application scene, road side sensing equipment (such as a camera, a laser radar and the like) connected with the road side device collects road traffic conditions in real time, and the dynamic electronic lane planning device constructs input feature vectors from the obtained data according to fields listed in S1 and inputs the input feature vectors into a trained model algorithm integrated in the device S7, so that the prediction of real-time lane division proportion is obtained; further, distributing the current total road width M to a lane 1, a lane 2 and a lane 3 according to a proportion, and calculating the center line trace coordinates of the lane 1, the lane 2 and the lane 3 by taking the known road center line GNSS trace coordinates as reference; and updating the MAP message in the V2X communication message according to the width information and the center line trace coordinate information of each lane determined by calculation, and broadcasting the message as dynamic electronic lane information to peripheral networked vehicles through a PC5 interface V2X communication channel after the message is coded, thereby finally realizing the function of dynamic electronic lane planning information service.
According to some embodiments of the present application, the dynamic electronic lane information may be displayed in a User Interface (UI) of the user terminal 130, and the scene of displaying the dynamic electronic lane information may include, but is not limited to, displaying the scene in any one or a combination of VR, AR, MR, XR. As an example, the networked vehicle user may obtain electronic lane information based on any one or combination of VR, AR, MR, XR, etc.
According to some embodiments of the present application, only 3 lanes can be set in a road as an example, and the present application embodiments can also be applied to other number of lanes, and a corresponding special neural network model is constructed and trained for the adjusted input and output vectors by adjusting the corresponding feature vector form and output vector form.
It should be noted that the above description of the process 200 is for convenience only and is not intended to limit the scope of the present application. It will be understood by those skilled in the art that various modifications and changes in form or detail of the functions implementing the procedures and operations described above may be made by any combination of the individual operations or by a combination of the constituent sub-procedures and other operations without departing from the principles of the present system. For example, the process 200 may further include the operations of allocating the total width of the current link to each lane according to a prediction ratio, calculating centerline coordinates of each lane based on the GNSS road centerline coordinates, and the like. For another example, the process 200 may further include updating a MAP message of the V2X communication message according to the width of each lane and the center line trace coordinate information, and broadcasting the encoded message as dynamic electronic lane information to networked vehicles within a preset distance. Such variations are within the scope of the present application.
According to some embodiments of the present application, there is provided a dynamic traffic flow based V2X dynamic electronic lane planning apparatus, comprising a memory configured to store data and instructions; a processor in communication with the memory, wherein the processor, when executing instructions in the memory, is configured to: s1: obtaining the total width X of the road 0 And the number m of lanes, and setting a time slice interval n; based on X 0 And the average vehicle number and the average vehicle speed of each lane in each time slice to construct an input feature vector
Figure BDA0003824952450000111
Including 2m +1 attribute values; constructing output characteristic vector based on width proportion of manually divided lanes
Figure BDA0003824952450000112
M attribute values; s2: extracting information of each line according to the S1 field based on historical traffic data of a preset period of manually dividing lanes, and constructing a training set, a verification set and a test set; s3: constructing a shallow neural network model, wherein an activation function Softmax is used for determining that the sum of the lane width distribution proportions is 1, and a loss function D (P, Y) is predicted based on the lane width
Figure BDA0003824952450000113
Cross entropy in proportion to manual partitioning; s4: performing iterative training on the shallow neural network model parameters based on the training set constructed in the S2 and the loss function of the S3 to determine the optimal weights and offset parameters of the Wr and br parameters, and performing overfitting verification based on the verification set constructed in the S2; s5:testing the neural network model which completes parameter training based on the test set constructed in the S2, and returning to the S4 training if the test does not reach the preset accuracy; s6: and if the test reaches the preset accuracy, deploying to a dynamic electronic lane planning environment.
In some embodiments, the spatial location information of the networked vehicle user is acquired by a high-precision positioning scheme, and other information can be acquired from the road side equipment RSU through short-range V2X communication based on a PC5 interface, wherein the road side equipment RSU serves as a broadcast sharing device and can provide information data service for a large number of positioning devices within hundreds of meters around. The method has the advantages that the support of the MAP MAP message in the current V2X technology is applied to the dynamic electronic lane. In some embodiments, the wireless communication between the information end 120 and the user end 130 of the present application may include V2X end-to-end short-range wireless direct communication based on a PC5 interface, and may be different from a wireless communication manner such as 4G-based long-range wireless communication (including a 4G module, a 4G SIM card, and a 4G antenna) in the prior art.
In summary, according to the V2X dynamic electronic lane planning method and apparatus based on dynamic traffic flow in the embodiment of the present application, an automatic dynamic electronic lane division method and apparatus are provided by fusing high-precision satellite positioning information GNSS, lane trace point information described based on the V2X communication method, and roadside devices to recognize the sensed traffic states near the lane in real time, such as the driving states of all traffic participants, average vehicle speed, average vehicle number, and the like. The method automatically and dynamically adjusts the trace point GNSS coordinate position used for the center lines of a plurality of lanes in the road in the MAP message in the V2X communication mechanism according to the road condition and the traffic condition, and broadcasts the trace point GNSS coordinate position to the vehicles with V2X communication capability at the periphery so as to realize the effect of presenting dynamic electronic lanes.
It is to be noted that the above-described embodiments are merely examples, and the present application is not limited to such examples, but various changes may be made.
It should be noted that, in the present specification, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrases "comprising one of 8230; \8230;" 8230; "does not exclude the presence of additional like elements in a process, method, article, or apparatus that comprises the element.
Finally, it should be noted that the series of processes described above includes not only processes performed in time series in the order described herein but also processes performed in parallel or individually, rather than in time series.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above may be implemented by hardware associated with computer program instructions, and the program may be stored in a computer readable storage medium, and when executed, may include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
While the invention has been described with reference to a number of illustrative embodiments, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention.

Claims (10)

1. A V2X dynamic electronic lane planning method based on dynamic traffic flow is characterized by comprising the following steps:
s1: obtaining the total width X of the road 0 And the number m of lanes, and setting a time slice interval n; based on X 0 And the average vehicle number and the average vehicle speed of each lane in each time slice to construct an input feature vector
Figure FDA0003824952440000011
Includes 1 attribute value of 2m +; based onManually dividing the width proportion of the lane and constructing an output characteristic vector
Figure FDA0003824952440000012
Comprises m attribute values;
s2: extracting information of each line according to the S1 field based on historical traffic data of a preset period of manually dividing lanes, and constructing a training set, a verification set and a test set;
s3: constructing a shallow neural network model, wherein an activation function Softmax is used for determining that the sum of the lane width distribution proportions is 1, and a loss function D (P, Y) is predicted based on the lane width
Figure FDA0003824952440000013
Cross entropy in proportion to manual partitioning;
s4: performing iterative training on the shallow neural network model parameters based on the training set constructed in the S2 and the loss function of the S3 to determine the optimal weights and offset parameters of the Wr and br parameters, and performing overfitting verification based on the verification set constructed in the S2;
s5: testing the neural network model which completes the parameter training based on the test set constructed in the S2, and returning to the S4 training if the test does not reach the preset accuracy rate;
s6: and if the test reaches the preset accuracy, deploying to a dynamic electronic lane planning environment.
2. The dynamic traffic flow-based V2X dynamic electronic lane planning method according to claim 1, specifically comprising:
according to the road side sensing equipment, road traffic data are collected in real time, and input feature vectors are constructed
Figure FDA0003824952440000014
Inputting the trained neural network model to obtain the prediction of the real-time division ratio of the electronic lane
Figure FDA0003824952440000015
Distributing the total width of the current road to each lane according to a prediction proportion, and calculating the center line trace coordinates of each lane based on the GNSS road center line trace coordinates;
and updating the MAP message of the V2X communication message according to the width of each lane and the center line point trace coordinate information, and broadcasting the message after coding as dynamic electronic lane information to the networked vehicles within a preset distance.
3. The dynamic traffic flow-based V2X dynamic electronic lane planning method according to claim 1, when the number of lanes m =3, specifically comprising:
acquiring the average number X of vehicles passing through the lane 1 in each n-second time slice 1 Average speed X of lane 1 in n second time slices 2 Average number of vehicles passing through lane 2 in n second time slice 3 Average speed X of lane 2 in n second time slice 4 Average number of vehicles passing through lane 3 per n second time slice X 5 Average speed X of lane 3 in n second time slice 6 Constructing an input feature vector X = [ X ] 0 ,X 1 ,X 2 ,X 3 ,X 4 ,X 5 ,X 6 ]；
Lane 1, lane 2 and lane 3 width proportion Y based on manual division 0 、Y 1 、Y 2 Constructing an output eigenvector Y = [ Y ] 0 ,Y 1 ,Y 2 ]Wherein
Figure FDA0003824952440000021
4. The dynamic traffic flow-based V2X dynamic electronic lane planning method according to claim 3, wherein the constructing of the shallow neural network model specifically comprises:
Figure FDA0003824952440000022
wherein, X 0 To X 6 Is the width of the lane defined in S1Input feature vector with strong correlation in degree division ratio, P 0 、P 1 、P 2 Is a target lane width distribution, w ij For using real-time traffic characteristics X j Calculating the width P of the ith lane i Weight coefficient required for time, b i To calculate the offset to be added for the ith lane width, w ij ，b i Determined by training.
5. The dynamic traffic flow-based V2X dynamic electronic lane planning method according to claim 4, wherein the activation function Softmax specifically comprises:
Figure FDA0003824952440000023
wherein the activation function Softmax is used for determining that the sum of the distribution proportions of the lane widths is 1,Z i The output value of the ith node of the last layer of the neural network.
6. The dynamic traffic flow-based V2X dynamic electronic lane planning method according to claim 5, wherein the feature P having a probability distribution form is output according to a model 0 +P 1 +P 2 =1, the loss function D (P, Y) specifically includes:
Figure FDA0003824952440000024
wherein the loss function D (P, Y) is based on lane width prediction
Figure FDA0003824952440000025
Cross entropy, Y, proportional to artificial division i Is the actual width ratio of the road i, P i The width ratio of the road i obtained through model prediction.
7. The dynamic traffic flow-based V2X dynamic electronic lane planning method according to claim 6, wherein the iterative training of the shallow neural network model parameters specifically comprises:
and utilizing a BP algorithm to iteratively train the neural network model parameters on a high-performance server based on the training set and the loss function.
8. The dynamic traffic flow-based V2X dynamic electronic lane planning method according to claim 7, wherein the step of testing whether the neural network model completing the parameter training reaches a preset correct rate specifically comprises:
randomly extracting data in a preset period from the test set, and dividing the data into 4 groups according to traffic flow conditions, wherein the 4 groups comprise no congestion, slight congestion, moderate congestion and severe congestion, and 1000 pieces of data are fixed in each group;
predicting each data in the 4 groups of data by using a neural network model which completes parameter training, and if the corresponding probability maximum item in the predicted guide lane use probability distribution is the same as the use of a lane actually planned by an artificial driver, determining that the prediction is correct; if not, determining that the prediction is wrong;
respectively counting the correct rate of the prediction results of 4 groups of data, wherein the correct rate is the ratio of the correct times of prediction of each group to the total number of the test data of each group, and if the correct rate is respectively greater than a preset threshold corresponding to each group, determining that the actual use requirement is met; if not, the actual use requirement is not met.
9. The V2X dynamic electronic lane planning method based on the dynamic traffic flow according to claim 8, wherein the accuracy is respectively greater than a preset threshold corresponding to each group, and specifically includes 70% of no congestion, 75% of light congestion, 80% of moderate congestion, and 85% of severe congestion.
10. A V2X dynamic electronic lane planning device based on dynamic traffic flow is characterized by comprising:
a memory configured to store data and instructions;
a processor in communication with the memory, wherein the processor, when executing instructions in the memory, is configured to:
s1: obtaining the total width X of the road 0 And the number m of lanes, and setting a time slice interval n; based on X 0 And the average vehicle number and the average vehicle speed of each lane in each time slice to construct an input feature vector
Figure FDA0003824952440000031
Includes 2m +1 attribute values; constructing output characteristic vector based on width proportion of manually divided lanes
Figure FDA0003824952440000032
Comprises m attribute values;
s2: extracting information of each line according to the S1 field based on historical traffic data of a preset period of manually dividing lanes, and constructing a training set, a verification set and a test set;
s3: constructing a shallow neural network model, wherein an activation function Softmax is used for determining that the sum of the lane width distribution proportions is 1, and a loss function D (P, Y) is predicted based on the lane width
Figure FDA0003824952440000033
Cross entropy in proportion to manual partitioning;
s4: performing iterative training on the shallow neural network model parameters based on the training set constructed in the S2 and the loss function of the S3 to determine the optimal weights and offset parameters of the Wr and br parameters, and performing overfitting verification based on the verification set constructed in the S2;
s5: testing the neural network model which completes parameter training based on the test set constructed in the S2, and returning to the S4 training if the test does not reach the preset accuracy;
s6: and if the test reaches the preset accuracy, deploying to a dynamic electronic lane planning environment.
CN202211055960.9A 2022-08-30 2022-08-30 V2X dynamic electronic lane planning method and device based on dynamic traffic flow Pending CN115423303A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211055960.9A CN115423303A (en) 2022-08-30 2022-08-30 V2X dynamic electronic lane planning method and device based on dynamic traffic flow

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211055960.9A CN115423303A (en) 2022-08-30 2022-08-30 V2X dynamic electronic lane planning method and device based on dynamic traffic flow

Publications (1)

Publication Number Publication Date
CN115423303A true CN115423303A (en) 2022-12-02

Family

ID=84200600

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211055960.9A Pending CN115423303A (en) 2022-08-30 2022-08-30 V2X dynamic electronic lane planning method and device based on dynamic traffic flow

Country Status (1)

Country Link
CN (1) CN115423303A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115798215A (en) * 2023-02-03 2023-03-14 江苏天一航空工业股份有限公司 Method for testing cooperative behavior capability of vehicle and road in civil aviation airport

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115798215A (en) * 2023-02-03 2023-03-14 江苏天一航空工业股份有限公司 Method for testing cooperative behavior capability of vehicle and road in civil aviation airport
CN115798215B (en) * 2023-02-03 2023-06-09 江苏天一航空工业股份有限公司 Method for testing cooperative behavior capability of civil aviation airport road

Similar Documents

Publication Publication Date Title
JP6506460B2 (en) System and method for managing service supply status
CN106205114B (en) A kind of Freeway Conditions information real time acquiring method based on data fusion
JP2020173856A (en) Systems and methods for determining predicted distribution of future transportation service time points
CN109769207A (en) A kind of mobile device dynamic group net shares the System and method for of calculation power
CN103200238A (en) Geography fencing intelligent network information system
WO2016164892A1 (en) Methods and systems for unmanned aircraft system (uas) traffic management
CN115423303A (en) V2X dynamic electronic lane planning method and device based on dynamic traffic flow
CN115148026A (en) Data-driven traffic safety risk assessment and variable speed limit control algorithm and system
CN104636966A (en) Method and equipment for sending order
CN117453843A (en) Data processing method and device, storage medium and electronic equipment
Gui et al. Vehicle Movement Analyses Considering Altitude Based on Modified Digital Elevation Model and Spherical Bilinear Interpolation Model: Evidence from GPS‐Equipped Taxi Data in Sanya, Zhengzhou, and Liaoyang
Saputra et al. Selective federated learning for on-road services in internet-of-vehicles
CN115412473B (en) Method and terminal for detecting data consistency of intelligent internet-connected broadcast signals of vehicles in real time
CN115116226A (en) Highway freight car flow prediction algorithm, software and device based on deep reinforcement learning model
KR20240046793A (en) Positioning method and apparatus, and device and storage medium
Doucek et al. Internet of Things or Surveillance of Things?
Ordóñez-Hurtado et al. An assessment on the use of stationary vehicles to support cooperative positioning systems
CN108038993A (en) The recommendation method and terminal of a kind of shared billboard
Duan et al. Traffic Flow Sensing Using Wireless Signals.
CN113936453B (en) Information identification method and system based on headway
Palviainen et al. Approach for simulating vehicle-based supply of sellable data products in smart cities–Parking space data as a use case
Loo et al. Improved Path Loss Simulation Incorporating Three‐Dimensional Terrain Model Using Parallel Coprocessors
Zhu et al. A Privacy‐Preserving Incentive Mechanism for Data Offloading in Satellite‐Terrestrial Crowdsensing
CN106855979A (en) Data correlation System and method for
CN113936454B (en) Information processing method and system based on track fusion

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination