Vehicle-road cooperative system, method and storage medium based on dual-intelligence private network

Abstract

The present application discloses a vehicle-road collaboration system, method and storage medium based on a dual-intelligence private network. The system includes: a vehicle-side subsystem, a roadside subsystem and a cloud platform subsystem installed in the vehicle; the roadside subsystem includes a base station applied to the dual-intelligence private network; the vehicle-side subsystem collects the driving data of vehicles in the road network in real time, and sends it to the cloud platform subsystem through the base station; the roadside subsystem collects the road perception information in the road network in real time, and sends it to the cloud platform subsystem through the base station; the cloud platform subsystem dynamically identifies the obstacle areas that affect the vehicle driving in the road network and the target vehicles passing through the obstacle areas based on the received driving data and road perception information, and creates the vehicle driving parameters of each target vehicle, and sends the vehicle driving parameters to the vehicle-side subsystem installed on each target vehicle through the base station. Therefore, by adopting the embodiments of the present application, vehicle-road collaboration can be applied to the field of unmanned driving, while reducing the risk of vehicle driving.

Description

Technical Field

[0001] The present application relates to the fields of intelligent transportation technology and computer technology, and in particular to a vehicle-road cooperative system, method and storage medium based on a dual-intelligent private network. Background Art

[0002] The dual-intelligence private network is an intelligent network system that integrates edge computing and cloud computing technologies, that is, a communication network under the edge-cloud unified heterogeneous technology architecture. Vehicle-road collaboration is a road traffic system that implements dynamic real-time information interaction between vehicles and roads in all directions. Vehicle-road collaboration carries out active vehicle safety control and road collaborative management based on the collection and integration of dynamic traffic information in all time and space, fully realizing effective collaboration between people, vehicles and roads, ensuring traffic safety and improving traffic efficiency.

[0003] In the related technologies, in the current vehicle-road collaborative safety communication technology of the Internet of Vehicles, the on-board unit (OBU) broadcasts its own safety beacon messages (such as location, speed, direction, etc.) through direct communication on the one hand, and needs to receive road conditions or safety beacon information broadcast by the road side unit (RSU) and other on-board units on the other hand; the road side unit also needs to collect safety beacon information broadcast by surrounding vehicles through direct communication on the one hand to obtain road condition information, and on the other hand, it also needs to periodically broadcast road condition information to the on-board unit.

[0004] On the one hand, the current on-board unit and roadside unit interact through direct communication. Due to the indirect delay and poor stability of the wired network or wireless network in the direct communication method, it is impossible to track the road perception information and driving data in a timely manner, and it is impossible to respond quickly to road problems and safety hazards. At the same time, in the field of unmanned driving, information cannot be transmitted in a timely manner, which increases the risk of vehicle driving.

[0005] On the other hand, with the rise of driverless cars, how to apply vehicle-road collaboration to driverless driving control and quickly perceive road sections with obstacles in advance to replan the path is an issue that needs to be solved urgently. The existing technology does not have a vehicle-road collaboration technology ecosystem under the driverless driving ecosystem. Summary of the invention

[0006] The embodiments of the present application provide a vehicle-road cooperative system, method and storage medium based on a dual-intelligence private network. In order to have a basic understanding of some aspects of the disclosed embodiments, a simple summary is given below. This summary is not a general review, nor is it intended to identify key / important components or describe the scope of protection of these embodiments. Its sole purpose is to present some concepts in a simple form as a preface to the detailed description that follows.

[0007] In a first aspect, an embodiment of the present application provides a vehicle-road cooperative system based on a dual-intelligence private network, the system comprising:

[0008] The vehicle-side subsystem, roadside subsystem and cloud platform subsystem are installed in the vehicle; the roadside subsystem includes a base station applied to the dual-intelligence private network; the cloud platform subsystem communicates with the vehicle-side subsystem and roadside subsystem through the base station;

[0009] The vehicle-side subsystem is used to create warning information for traffic warning based on the danger information existing in the vehicle driving process, and send it to the roadside subsystem through the base station; the roadside subsystem is used to broadcast the warning information to the vehicle-side subsystem installed on each vehicle within a preset range in combination with the base station based on the received warning information or the perception data from other perception devices; the vehicle-side subsystem is also used to display the received warning information, or control the vehicle driving based on the received warning information when in the automatic driving state;

[0010] The vehicle-side subsystem is also used to collect driving data of vehicles in the road network in real time and send it to the cloud platform subsystem through the base station; the roadside subsystem is also used to collect road perception information in the road network in real time and send it to the cloud platform subsystem through the base station; the cloud platform subsystem is used to dynamically identify obstacle areas in the road network that affect vehicle driving and target vehicles passing through obstacle areas based on the received driving data and road perception information, and create vehicle driving parameters for each target vehicle, and send the vehicle driving parameters to the vehicle-side subsystem installed on each target vehicle through the base station; the vehicle-side subsystem is also used to display the received vehicle driving parameters, or when in the automatic driving state, control the driving of the target vehicle based on the received vehicle driving parameters.

[0011] Optionally, the vehicle subsystem includes an autonomous driving unit, an on-board computing unit, a human-computer interaction component, an electronic auxiliary unit, and a communication component applied to the dual-intelligence private network; wherein,

[0012] The autonomous driving unit, the on-board computing unit, the human-computer interaction component, the electronic auxiliary unit, and the communication component applied to the dual-intelligence private network are electrically connected; wherein,

[0013] The vehicle-mounted computing unit is used to receive warning information sent from the roadside subsystem or receive vehicle driving parameters sent from the cloud platform subsystem;

[0014] An automatic driving unit, used to generate a driving route and a vehicle control strategy for the vehicle according to the warning information or the vehicle driving parameters, and to control the electronic auxiliary unit based on the driving route and the vehicle control strategy to realize automatic driving of the vehicle;

[0015] A human-computer interaction component for receiving vehicle control instructions;

[0016] The on-board computing unit is also used to create warning information for traffic warning based on the danger information existing during the vehicle's driving process, and send it to the roadside subsystem through the base station; or it is also used to collect driving data of vehicles in the road network in real time, and send it to the cloud platform subsystem through the base station.

[0017] Optionally, based on the received driving data and road perception information, dynamically identifying obstacle areas in the road network that affect vehicle driving and target vehicles passing through the obstacle areas, including:

[0018] Determine the vehicle density, average vehicle speed and traffic flow of each road section in the road network based on the received road perception information;

[0019] Calculate the congestion coefficient of each road section based on the vehicle density, average vehicle speed and traffic flow of each road section;

[0020] Determine whether the road congestion coefficient of each road section is greater than a preset congestion threshold, and determine whether the road section greater than the preset congestion threshold has an obstacle area that affects vehicle driving;

[0021] According to the received driving data, the target vehicle passing through the obstacle area is determined.

[0022] Optionally, the received road perception information includes a road condition image of each road section and traffic light control information;

[0023] Based on the received road perception information, determine the vehicle density, average vehicle speed and traffic flow of each road section in the road network, including:

[0024] According to the signal light control information, determine the total time required for the signal light to be in the green light phase;

[0025] Acquire a first road condition image corresponding to the start time of the green light phase and a second road condition image corresponding to the end time of the green light phase from the received road condition image of each road section;

[0026] marking the position and bounding box of the vehicle in the first road condition image, and marking the position and bounding box of the vehicle in the second road condition image;

[0027] Counting the total number of first vehicles in the first road condition image according to the positions and bounding boxes of the vehicles in the first road condition image;

[0028] Counting the total number of second vehicles in the second road condition image according to the positions and bounding boxes of the vehicles in the second road condition image;

[0029] The ratio between the sum of the first total number of vehicles, the second total number of vehicles and the total time required in the green light phase is used as the vehicle density of each road section under normal traffic conditions;

[0030] Optical flow tracking is performed based on the position and bounding box of the vehicle in the first road condition image and the position and bounding box of the vehicle in the second road condition image, the speed of the vehicle per unit time is calculated, and the average vehicle speed and traffic flow of each road section under normal traffic conditions are obtained.

[0031] Optionally, based on the vehicle density, average vehicle speed and traffic flow of each road section, the road congestion coefficient of each road section is calculated, including:

[0032] Calculate the speed ratio between the average vehicle speed of each road section and the preset optimal vehicle speed;

[0033] Calculate the difference between 1 and the speed ratio;

[0034] Calculate the product of vehicle density and difference for each road segment;

[0035] The sum of the product and the traffic flow of each road section is taken as the road section congestion coefficient of each road section; wherein, the calculation formula of the road section congestion coefficient of each road section is:

[0036] Congestion coefficient = vehicle density × (1-average vehicle speed / optimal speed) + traffic flow.

[0037] Optionally, the driving data includes the vehicle's position, speed, acceleration, and driving direction;

[0038] According to the received driving data, the target vehicle passing through the obstacle area is determined, including:

[0039] Obtain the road section identification to which the obstacle area belongs and the target position of the obstacle area;

[0040] Perform collision detection based on the vehicle's position and driving direction, road section signs, and target position to determine the initial vehicle passing through the obstacle area;

[0041] According to the initial vehicle speed and acceleration, determine the driving time for each vehicle to reach the obstacle area;

[0042] The obstacle type and driving time in the obstacle area are input into the pre-built obstacle dissipation portrait model to determine the obstacle dissipation probability of each initial vehicle when it reaches the obstacle area;

[0043] An initial vehicle whose obstacle dissipation probability is less than a preset probability threshold is determined as a target vehicle passing through the obstacle area.

[0044] Optionally, generate a pre-built obstacle dissipation model by following these steps, including:

[0045] Obtain historical obstacle areas within a preset time period in the road network;

[0046] Obtain the obstacle dissipation matrix corresponding to the entire life cycle of each obstacle event corresponding to each historical obstacle area; wherein the obstacle dissipation matrix expresses the spatiotemporal information of the entire life cycle of the obstacle area from its appearance to its end;

[0047] The obstacle dissipation matrix is ​​segmented according to a preset unit time to obtain segmented space-time slice information;

[0048] Constructing an obstacle dissipation model, which includes a convolutional neural network model;

[0049] Use the segmented space-time slice information to dissipate the obstacle model and output the model loss value;

[0050] When the model loss value reaches the minimum, a pre-built obstacle dissipation portrait model is generated.

[0051] In a second aspect, an embodiment of the present application provides a vehicle-road collaboration method based on a dual-intelligence private network, the method comprising:

[0052] The vehicle-side subsystem creates warning information for traffic warning based on the danger information existing in the vehicle driving process, and sends it to the roadside subsystem through the base station;

[0053] The roadside subsystem broadcasts warning information to the vehicle-side subsystem installed on each vehicle within a preset range in conjunction with the base station based on the received warning information or the sensing data from other sensing devices;

[0054] The vehicle-side subsystem displays the received warning information, or when in autonomous driving mode, controls the vehicle driving based on the received warning information.

[0055] In a fourth aspect, an embodiment of the present application provides a vehicle-road collaboration method based on a dual-intelligence private network, the method comprising:

[0056] The vehicle-to-vehicle subsystem collects driving data of vehicles in the road network in real time and sends it to the cloud platform subsystem through the base station;

[0057] The roadside subsystem collects road perception information in the road network in real time and sends it to the cloud platform subsystem through the base station;

[0058] The cloud platform subsystem dynamically identifies the obstacle areas that affect vehicle driving and the target vehicles passing through the obstacle areas in the road network based on the received driving data and road perception information, creates vehicle driving parameters for each target vehicle, and sends the vehicle driving parameters to the vehicle subsystem installed on each target vehicle through the base station;

[0059] The vehicle-subsystem displays the received vehicle driving parameters, or when in the automatic driving state, controls the driving of the target vehicle based on the received vehicle driving parameters.

[0060] In a third aspect, an embodiment of the present application provides a computer storage medium, which stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the above-mentioned method steps.

[0061] In a fourth aspect, an embodiment of the present application provides an electronic device, which may include: a processor and a memory; wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing the above-mentioned method steps.

[0062] The technical solution provided by the embodiments of the present application may have the following beneficial effects:

[0063] In the embodiment of the present application, on the one hand, the roadside subsystem and the cloud platform subsystem can send warning information or vehicle driving parameters to the vehicle subsystem through the roadside base station to realize information display or vehicle control in the automatic driving state. The roadside base station communicates based on the dual-intelligence private network. The dual-intelligence private network combines the advantages of edge computing and cloud computing, and can track road perception information and driving data in a timely manner, quickly respond to road problems and safety hazards, and can transmit information in a timely manner in the field of unmanned driving, thereby reducing the risk of vehicle driving. On the other hand, the cloud can identify the vehicle through the received driving data and the pre-built obstacle dissipation portrait model. The pre-built obstacle dissipation portrait model is generated based on the obstacle dissipation matrix corresponding to each obstacle event in the entire life cycle of each historical obstacle area. The obstacle dissipation matrix expresses the spatiotemporal information of the entire life cycle of the obstacle area from its appearance to its end, and can be prepared to characterize whether there is obstacle dissipation when the vehicle reaches the obstacle area, thereby improving the accuracy of identifying vehicles affected by the obstacle area.

[0064] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0066] Figure 1 Schematic diagram of the system architecture of a vehicle-road cooperative system based on a dual-intelligent private network provided in an embodiment of the present application;

[0067] Figure 2 It is a flowchart of a vehicle-road collaboration method based on a dual-intelligent private network provided in an embodiment of the present application;

[0068] Figure 3 A schematic diagram of a vehicle-road collaboration scenario is provided for an embodiment of the present application;

[0069] Figure 4 This is another schematic diagram of a vehicle-road collaboration scenario provided in an embodiment of the present application;

[0070] Figure 5 It is a flowchart of another vehicle-road collaboration method based on a dual-intelligent private network provided in an embodiment of the present application;

[0071] Figure 6 This is another schematic diagram of a vehicle-road collaboration scenario provided in an embodiment of the present application;

[0072] Figure 7 It is a flow chart of a model training method of an obstacle dissipation portrait model provided in an embodiment of the present application;

[0073] Figure 8 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0074] The following description and the accompanying drawings sufficiently illustrate specific embodiments of the present application to enable those skilled in the art to practice them.

[0075] It should be clear that the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0076] When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Instead, they are only examples of systems and methods consistent with some aspects of the present application as detailed in the attached claims.

[0077] In the description of the present application, it should be understood that the terms "first", "second", etc. are used for descriptive purposes only and should not be understood as indicating or implying relative importance. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to the specific circumstances. In addition, in the description of the present application, unless otherwise specified, "multiple" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects associated before and after are in an "or" relationship.

[0078] At present, in vehicle-road collaboration, in the current vehicle-road collaboration safety communication technology of the Internet of Vehicles, the on-board unit (OnBoard Unit, OBU) broadcasts its own safety beacon messages (such as location, speed, direction, etc.) through direct communication on the one hand, and on the other hand, it needs to receive road conditions or safety beacon information broadcast by the road side unit (Road Side Unit, RSU) and other on-board units; the road side unit also needs to collect safety beacon information broadcast by surrounding vehicles through direct communication on the one hand to obtain road conditions information, and on the other hand, it also needs to periodically broadcast road conditions information to the on-board unit.

[0079] The inventor of this application noticed that, on the one hand, the current on-board unit and the roadside unit interact through direct communication. Due to the indirect delay and poor stability of the wired or wireless network in the direct communication, it is impossible to track the road perception information and driving data in a timely manner, and it is impossible to respond quickly to road problems and safety hazards. At the same time, in the field of unmanned driving, information cannot be transmitted in a timely manner, which increases the risk of vehicle driving. On the other hand, with the rise of unmanned driving, how to apply vehicle-road collaboration to unmanned driving control and how to quickly perceive sections with obstacles in advance to replan the path are issues that need to be solved urgently. In the existing technology, there is no vehicle-road collaboration technology ecosystem under the unmanned driving ecosystem.

[0080] In order to solve the problem of timely tracking and monitoring as well as the problem of vehicle-road collaboration in the field of autonomous driving, the present application provides a vehicle-road collaboration system, method and storage medium based on a dual-intelligence private network to solve the problems existing in the above-mentioned related technical issues. In the technical solution provided by the present application, in the embodiment of the present application, on the one hand, the roadside subsystem and the cloud platform subsystem can send warning information or vehicle driving parameters to the vehicle-side subsystem through the roadside base station to realize information display or vehicle control in the state of autonomous driving. The roadside base station communicates based on the dual-intelligence private network. The dual-intelligence private network combines the advantages of edge computing and cloud computing, and can track road perception information and driving data in a timely manner, quickly respond to road problems and safety hazards, and can transmit information in a timely manner in the field of unmanned driving, thereby reducing vehicle driving risks. On the other hand, the cloud can identify the vehicle through the received driving data and the pre-built obstacle dissipation portrait model. The pre-built obstacle dissipation portrait model is generated based on the training of the obstacle dissipation matrix corresponding to the entire life cycle of each obstacle event corresponding to each historical obstacle area. The obstacle dissipation matrix expresses the spatiotemporal information of the entire life cycle of the obstacle area from its appearance to its end, and can be prepared to characterize whether there is obstacle dissipation when the vehicle reaches the obstacle area, thereby improving the accuracy of identifying vehicles affected by the obstacle area. An exemplary embodiment is used below to explain in detail.

[0081] See also Figure 1, which shows a schematic diagram of the structure of a vehicle-road cooperative system based on a dual-intelligent private network provided by an exemplary embodiment of the present application. The vehicle-road cooperative system based on the dual-intelligent private network includes: a vehicle-side subsystem, a roadside subsystem and a cloud platform subsystem installed in the vehicle; the roadside subsystem includes a base station applied to the dual-intelligent private network; the cloud platform subsystem is respectively connected to the vehicle-side subsystem and the roadside subsystem through the base station.

[0082] In one embodiment, the on-board subsystem is used to create warning information for traffic warning based on the danger information existing during the driving process of the vehicle, and send it to the roadside subsystem through the base station; the roadside subsystem is used to broadcast the warning information to the on-board subsystem installed on each vehicle within a preset range based on the received warning information or the perception data from other perception devices in combination with the base station; the on-board subsystem is also used to display the received warning information, or when in the automatic driving state, control the vehicle driving based on the received warning information.

[0083] In another embodiment, the vehicle-side subsystem is also used to collect driving data of vehicles in the road network in real time, and send it to the cloud platform subsystem through the base station; the roadside subsystem is also used to collect road perception information in the road network in real time, and send it to the cloud platform subsystem through the base station; the cloud platform subsystem is used to dynamically identify obstacle areas in the road network that affect vehicle driving and target vehicles passing through obstacle areas based on the received driving data and road perception information, and create vehicle driving parameters for each target vehicle, and send the vehicle driving parameters to the vehicle-side subsystem installed on each target vehicle through the base station; the vehicle-side subsystem is also used to display the received vehicle driving parameters, or when in the automatic driving state, control the driving of the target vehicle based on the received vehicle driving parameters.

[0084] In the system architecture of this application, the communication technical requirements of the dual-intelligence private network include the overall functional requirements of the intelligent transportation system business communication, such as high-priority business information delay: ≤10ms; packet loss rate ≤0.001%; ​​number of users per kilometer ≥1000; system bandwidth ≥200Mbps; switching success rate not less than 99.99%; communication distance ≥500m; supported vehicle speed range 0~130km / h.

[0085] The cloud platform subsystem specifically includes a private network management module, a cloud control platform, and a third-party platform (such as an intelligent information control platform, a video management platform, and a large-screen HMI display platform). The private network management module is used to manage the network configuration parameters of the dual-intelligence private network, the cloud control platform is used to implement information processing in the cloud, and the third-party platform is used to display relevant information.

[0086] In an embodiment of the present application, the vehicle-side subsystem includes an automatic driving unit, an on-board computing unit, a human-computer interaction component, an electronic auxiliary unit and a communication component applied to the dual-intelligence private network; wherein the automatic driving unit, the on-board computing unit, the human-computer interaction component, the electronic auxiliary unit and the communication component applied to the dual-intelligence private network are electrically connected; wherein the on-board computing unit is used to receive warning information sent from the roadside subsystem or receive vehicle driving parameters sent from the cloud platform subsystem; the automatic driving unit is used to generate the vehicle's driving route and vehicle control strategy based on the warning information or vehicle driving parameters, and control the electronic auxiliary unit based on the driving route and vehicle control strategy to realize automatic driving of the vehicle; the human-computer interaction component is used to receive vehicle control instructions; the on-board computing unit is also used to create warning information for traffic warning based on the danger information existing in the vehicle's driving process, and send it to the roadside subsystem through the base station; or it is also used to collect driving data of vehicles in the road network in real time, and send it to the cloud platform subsystem through the base station.

[0087] In an embodiment of the present application, the process of dynamically identifying obstacle areas that affect vehicle driving and target vehicles passing through obstacle areas in the road network based on received driving data and road perception information specifically includes the following steps: determining the vehicle density, average vehicle speed and traffic flow of each road section in the road network based on the received road perception information; calculating the section congestion coefficient of each road section based on the vehicle density, average vehicle speed and traffic flow of each road section; judging whether the section congestion coefficient of each road section is greater than a preset congestion threshold, and determining that the road sections greater than the preset congestion threshold have obstacle areas that affect vehicle driving; determining the target vehicles passing through the obstacle area based on the received driving data.

[0088] The received road perception information includes a road condition image of each road section and traffic light control information.

[0089] In an embodiment of the present application, the specific processing process of determining the vehicle density, average vehicle speed and traffic flow of each road section in the road network based on the received road perception information includes the following steps: determining the total time required for the signal light to be in the green light phase according to the signal light control information; obtaining a first road condition image corresponding to the start time of the green light phase and a second road condition image corresponding to the end time of the green light from the received road condition image of each road section; marking the position and bounding box of the vehicle in the first road condition image, and marking the position and bounding box of the vehicle in the second road condition image; counting the total number of first vehicles existing in the first road condition image according to the position and bounding box of the vehicle in the first road condition image; counting the total number of second vehicles existing in the second road condition image according to the position and bounding box of the vehicle in the second road condition image; taking the ratio between the sum of the total number of first vehicles and the total number of second vehicles and the total time required in the green light phase as the vehicle density of each road section under normal traffic conditions; performing optical flow tracking according to the position and bounding box of the vehicle in the first road condition image and the position and bounding box of the vehicle in the second road condition image, calculating the speed of the vehicle per unit time, and obtaining the average vehicle speed and traffic flow of each road section under normal traffic conditions.

[0090] In an embodiment of the present application, the process of calculating the section congestion coefficient of each road section based on the vehicle density, average vehicle speed and traffic flow of each road section includes the following steps: calculating the speed ratio of the average vehicle speed of each road section to the preset optimal speed; calculating the difference between 1 and the speed ratio; calculating the product of the vehicle density of each road section and the difference; taking the sum of the product and the traffic flow of each road section as the section congestion coefficient of each road section; wherein the calculation formula of the section congestion coefficient of each road section is: congestion coefficient = vehicle density × (1-average vehicle speed / optimal speed) + traffic flow.

[0091] The driving data includes the vehicle's position, speed, acceleration and driving direction.

[0092] In an embodiment of the present application, the process of determining a target vehicle passing through an obstacle area based on received driving data specifically includes the following processing steps: obtaining a road section identifier to which the obstacle area belongs and a target position of the obstacle area; performing collision detection based on the vehicle's position and driving direction, road section identifier, and target position to determine the initial vehicle passing through the obstacle area; judging the driving time for each vehicle to reach the obstacle area based on the speed and acceleration of the initial vehicle; inputting the obstacle type and driving time of the obstacle area into a pre-constructed obstacle dissipation portrait model to determine the obstacle dissipation probability of each initial vehicle when it reaches the obstacle area; and determining the initial vehicle whose obstacle dissipation probability is less than a preset probability threshold as a target vehicle passing through the obstacle area.

[0093] In an embodiment of the present application, the generation process of a pre-constructed obstacle dissipation portrait model includes the following steps: obtaining historical obstacle areas within a preset time period in the road network; obtaining an obstacle dissipation matrix corresponding to the entire life cycle of each obstacle event corresponding to each historical obstacle area; wherein the obstacle dissipation matrix expresses the spatiotemporal information of the entire life cycle of the obstacle area from its appearance to its end; segmenting the obstacle dissipation matrix according to a preset unit time to obtain segmented spatiotemporal slice information; constructing an obstacle dissipation model, the obstacle dissipation model including a convolutional neural network model; using the segmented spatiotemporal slice information on the obstacle dissipation model to output a model loss value; when the model loss value reaches a minimum, generating a pre-constructed obstacle dissipation portrait model.

[0094] The dual-intelligent private network is an intelligent network system that integrates edge computing and cloud computing technologies, that is, a communication network under the edge-cloud unified heterogeneous technology architecture. In this application, the dual-intelligent private network adopts the EUHT private network, which is a dedicated network built based on EUHT technology. EUHT (Enhanced Ultra High Throughput) technology is a high-speed wireless communication technology that aims to provide higher data transmission rates and better network performance than the current 4G LTE network. Starting from the basic principles of wireless communication, EUHT wireless network technology conducts full-system innovative design of frame structure, pilot, precoding, channel estimation, channel prediction, physical layer, MAC layer, protocol layer, synchronization, control, scheduling, etc. involved in wireless communication, and has the characteristics of "three highs and one low" - high throughput, high reliability, high-speed mobility, and low latency.

[0095] In the embodiment of the present application, on the one hand, the roadside subsystem and the cloud platform subsystem can send warning information or vehicle driving parameters to the vehicle subsystem through the roadside base station to realize information display or vehicle control in the automatic driving state. The roadside base station communicates based on the dual-intelligence private network. The dual-intelligence private network combines the advantages of edge computing and cloud computing, and can track road perception information and driving data in a timely manner, quickly respond to road problems and safety hazards, and can transmit information in a timely manner in the field of unmanned driving, thereby reducing the risk of vehicle driving. On the other hand, the cloud can identify the vehicle through the received driving data and the pre-built obstacle dissipation portrait model. The pre-built obstacle dissipation portrait model is generated based on the obstacle dissipation matrix corresponding to each obstacle event in the entire life cycle of each historical obstacle area. The obstacle dissipation matrix expresses the spatiotemporal information of the entire life cycle of the obstacle area from its appearance to its end, and can be prepared to characterize whether there is obstacle dissipation when the vehicle reaches the obstacle area, thereby improving the accuracy of identifying vehicles affected by the obstacle area.

[0096] See also Figure 2, a flow chart of a vehicle-road collaboration method based on a dual-intelligent private network is provided for an embodiment of the present application. As shown in the figure, the method of the embodiment of the present application may include the following steps:

[0097] S201, the vehicle-side subsystem creates warning information for traffic warning according to the danger information existing in the vehicle driving process, and sends it to the roadside subsystem through the base station;

[0098] Among them, the danger information is sent by the vehicle-side subsystem of the first vehicle when it detects a danger signal. The danger signal is, for example, a problem with the first vehicle's own condition or a problem with the condition of the vehicle in front. At this time, it is necessary to broadcast warning information to the rear vehicles.

[0099] In some embodiments, the vehicle uses various sensors (such as cameras, radars, lidars, etc.) to detect dangerous signals in the surrounding environment, such as sudden braking, sudden lane changes, etc. When a dangerous signal is detected, the vehicle needs to generate corresponding warning information based on the specific situation to alert the following vehicles to possible dangerous situations. Finally, the vehicle's on-board subsystem sends it to the roadside subsystem through the base station.

[0100] S202, the roadside subsystem broadcasts the warning information to the vehicle-side subsystem installed on each vehicle within a preset range in combination with the base station according to the received warning information or the sensing data from other sensing devices;

[0101] Among them, the perception data of other perception devices are, for example, abnormal information perceived by cameras deployed on traffic lights or ETC gantries.

[0102] In some embodiments, when the leading vehicle issues an early warning to nearby vehicles, the roadside subsystem that is shortest to the vehicle-to-vehicle subsystem of the leading vehicle can receive the early warning information broadcasted from the vehicle-to-vehicle subsystem of the leading vehicle. The roadside subsystem can use itself as the center of the circle, calculate the vehicles within a preset range, and in conjunction with the base station, broadcast the early warning information to the vehicle-to-vehicle subsystems installed on each vehicle within the preset range.

[0103] For example Figure 3 As shown, the system includes a front vehicle and a rear vehicle. The on-board computing unit of the front vehicle can broadcast information to the rear vehicle. The information is first transmitted to the roadside unit, and then forwarded by the roadside unit to the on-board computing unit in the vehicle-to-vehicle subsystem of the rear vehicle. The rear vehicle can perform scene calculations based on the broadcast information and determine the corresponding strategies that the vehicle needs to execute.

[0104] In other embodiments, for example Figure 4As shown in the figure, when the traffic lights or cameras deployed on the ETC gantries sense abnormal information, such as the presence of pedestrians on the highway, the roadside subsystem receives the perception data from other perception devices and broadcasts warning information to the vehicle-side subsystems installed on each vehicle within a preset range in conjunction with the base station.

[0105] S203, the vehicle terminal system displays the received warning information, or when in the automatic driving state, controls the vehicle driving based on the received warning information.

[0106] In an embodiment of the present application, after receiving the warning information, the on-board unit in the on-board subsystem can display the warning information, or when in the automatic driving state, control the vehicle driving based on the received warning information to achieve automatic driving.

[0107] In the embodiment of the present application, on the one hand, the roadside subsystem and the cloud platform subsystem can send warning information or vehicle driving parameters to the vehicle subsystem through the roadside base station to realize information display or vehicle control in the automatic driving state. The roadside base station communicates based on the dual-intelligence private network. The dual-intelligence private network combines the advantages of edge computing and cloud computing, and can track road perception information and driving data in a timely manner, quickly respond to road problems and safety hazards, and can transmit information in a timely manner in the field of unmanned driving, thereby reducing the risk of vehicle driving. On the other hand, the cloud can identify the vehicle through the received driving data and the pre-built obstacle dissipation portrait model. The pre-built obstacle dissipation portrait model is generated based on the obstacle dissipation matrix corresponding to each obstacle event in the entire life cycle of each historical obstacle area. The obstacle dissipation matrix expresses the spatiotemporal information of the entire life cycle of the obstacle area from its appearance to its end, and can be prepared to characterize whether there is obstacle dissipation when the vehicle reaches the obstacle area, thereby improving the accuracy of identifying vehicles affected by the obstacle area.

[0108] See also Figure 5 , a flow chart of a vehicle-road collaboration method based on a dual-intelligent private network is provided for an embodiment of the present application. As shown in the figure, the method of the embodiment of the present application may include the following steps:

[0109] S301, the vehicle subsystem collects driving data of vehicles in the road network in real time and sends it to the cloud platform subsystem through the base station;

[0110] S302, the roadside subsystem collects road perception information in the road network in real time and sends it to the cloud platform subsystem through the base station;

[0111] S303, the cloud platform subsystem dynamically identifies the obstacle areas that affect vehicle driving and the target vehicles passing through the obstacle areas in the road network based on the received driving data and road perception information, creates vehicle driving parameters for each target vehicle, and sends the vehicle driving parameters to the vehicle subsystem installed on each target vehicle through the base station;

[0112] In the embodiment of the present application, when dynamically identifying the obstacle area that affects vehicle driving and the target vehicle passing through the obstacle area in the road network based on the received driving data and road perception information, the vehicle density, average speed and traffic flow of each road section in the road network are determined based on the received road perception information; the road section congestion coefficient of each road section is calculated based on the vehicle density, average speed and traffic flow of each road section; it is determined whether the road section congestion coefficient of each road section is greater than a preset congestion threshold, and it is determined that the road section greater than the preset congestion threshold has an obstacle area that affects vehicle driving; according to the received driving data, the target vehicle passing through the obstacle area is determined. The driving data includes the position, speed, acceleration and driving direction of the vehicle.

[0113] In an embodiment of the present application, the specific processing process of determining the target vehicle passing through the obstacle area based on the received driving data includes the following steps: obtaining the section identification of the obstacle area and the target position of the obstacle area; performing collision detection based on the vehicle's position and driving direction, the section identification and the target position to determine the initial vehicle passing through the obstacle area; judging the driving time of each vehicle to reach the obstacle area based on the speed and acceleration of the initial vehicle; inputting the obstacle type and driving time of the obstacle area into a pre-constructed obstacle dissipation portrait model to determine the obstacle dissipation probability of each initial vehicle when it reaches the obstacle area; and determining the initial vehicle whose obstacle dissipation probability is less than a preset probability threshold as the target vehicle passing through the obstacle area.

[0114] S304, the vehicle-subsystem displays the received vehicle driving parameters, or when in the automatic driving state, controls the driving of the target vehicle based on the received vehicle driving parameters.

[0115] In some embodiments, for example Figure 6 As shown, the vehicle-to-vehicle subsystem collects driving data of vehicles in the road network in real time and sends it to the cloud platform through the base station. The roadside unit collects road perception information in the road network in real time and sends it to the cloud platform through the base station. After data fusion analysis, the cloud control platform can obtain the relevant control parameters of the vehicle and send them to the vehicle-to-vehicle subsystem through the MAP / RSI message body combined with the base station.

[0116] In the embodiment of the present application, on the one hand, the roadside subsystem and the cloud platform subsystem can send warning information or vehicle driving parameters to the vehicle subsystem through the roadside base station to realize information display or vehicle control in the automatic driving state. The roadside base station communicates based on the dual-intelligence private network. The dual-intelligence private network combines the advantages of edge computing and cloud computing, and can track road perception information and driving data in a timely manner, quickly respond to road problems and safety hazards, and can transmit information in a timely manner in the field of unmanned driving, thereby reducing the risk of vehicle driving. On the other hand, the cloud can identify the vehicle through the received driving data and the pre-built obstacle dissipation portrait model. The pre-built obstacle dissipation portrait model is generated based on the obstacle dissipation matrix corresponding to each obstacle event in the entire life cycle of each historical obstacle area. The obstacle dissipation matrix expresses the spatiotemporal information of the entire life cycle of the obstacle area from its appearance to its end, and can be prepared to characterize whether there is obstacle dissipation when the vehicle reaches the obstacle area, thereby improving the accuracy of identifying vehicles affected by the obstacle area.

[0117] See also Figure 7 , a flowchart of a pre-built obstacle dissipation portrait model training method is provided for an embodiment of the present application. As shown in the figure, the method of the embodiment of the present application may include the following steps:

[0118] S101, obtaining historical obstacle areas in a preset time period in the road network;

[0119] S102, obtaining an obstacle dissipation matrix corresponding to the entire life cycle of each obstacle event corresponding to each historical obstacle area; wherein the obstacle dissipation matrix expresses the spatiotemporal information of the entire life cycle of the obstacle area from appearance to end;

[0120] S103, segmenting the obstacle dissipation matrix according to a preset unit time to obtain segmented space-time slice information;

[0121] S104, constructing an obstacle dissipation model, where the obstacle dissipation model includes a convolutional neural network model;

[0122] S105, using the segmented space-time slice information to model the obstacle dissipation and outputting the model loss value;

[0123] S106, when the model loss value reaches the minimum, a pre-built obstacle dissipation portrait model is generated.

[0124] In an embodiment of the present application, the cloud can identify the vehicle through the received driving data and the pre-built obstacle dissipation portrait model. The pre-built obstacle dissipation portrait model is generated based on the training of the obstacle dissipation matrix corresponding to the entire life cycle of each obstacle event corresponding to each historical obstacle area. The obstacle dissipation matrix expresses the spatiotemporal information of the entire life cycle of the obstacle area from its appearance to its end, and can be prepared to characterize whether there is obstacle dissipation when the vehicle reaches the obstacle area, thereby improving the accuracy of identifying vehicles affected by the obstacle area.

[0125] The present application also provides a computer-readable medium having program instructions stored thereon, which, when executed by a processor, implement the vehicle-road collaboration method based on a dual-intelligence private network provided by the above-mentioned method embodiments.

[0126] The present application also provides a computer program product comprising instructions, which, when executed on a computer, enables the computer to execute the vehicle-road collaboration method based on a dual-intelligence private network of the above-mentioned various method embodiments.

[0127] See also Figure 8 , is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 8 As shown, the electronic device 1000 may include: at least one processor 1001 , at least one network interface 1004 , a user interface 1003 , a memory 1005 , and at least one communication bus 1002 .

[0128] The communication bus 1002 is used to realize the connection and communication between these components.

[0129] The user interface 1003 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 1003 may also include a standard wired interface and a wireless interface.

[0130] The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0131] Among them, the processor 1001 may include one or more processing cores. The processor 1001 uses various interfaces and lines to connect various parts of the entire electronic device 1000, and executes various functions and processes data of the electronic device 1000 by running or executing instructions, programs, code sets or instruction sets stored in the memory 1005, and calling data stored in the memory 1005. Optionally, the processor 1001 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 1001 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 1001, and it can be implemented separately through a chip.

[0132] Among them, the memory 1005 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 1005 includes a non-transitory computer-readable storage medium. The memory 1005 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 1005 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 1005 may also be optionally at least one storage system located away from the aforementioned processor 1001. As Figure 8 As shown, the memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module, and a vehicle-road collaborative application based on a dual-intelligence private network.

[0133] exist Figure 8In the electronic device 1000 shown, the user interface 1003 is mainly used to provide an input interface for the user and obtain data input by the user; and the processor 1001 can be used to call the dual-intelligence private network-based vehicle-road cooperative application stored in the memory 1005, and specifically perform the following operations:

[0134] Identify road damage based on the acquired road images, generate road damage information, and send the road damage information to the cloud through the roadside base station;

[0135] Alternatively, do the following:

[0136] The receiving edge computing module sends road damage information through the roadside base station, performs damage analysis based on the road damage information, generates road inspection results, and sends the road inspection results to the client for visual display.

[0137] In one embodiment, when the processor 1001 performs disease identification based on the acquired road image and generates road disease information, the following operations are specifically performed:

[0138] According to the received driving data and road perception information, dynamically identify the obstacle areas in the road network that affect vehicle driving and the target vehicles passing through the obstacle areas;

[0139] The vehicle driving parameters of each target vehicle are created, and the vehicle driving parameters are sent to the vehicle subsystem installed on each target vehicle through the base station.

[0140] In one embodiment, when the processor 1001 dynamically identifies the obstacle area that affects the vehicle driving and the target vehicle passing through the obstacle area in the road network according to the received driving data and road perception information, the processor 1001 specifically performs the following operations:

[0141] Determine the vehicle density, average vehicle speed and traffic flow of each road section in the road network based on the received road perception information;

[0142] Calculate the congestion coefficient of each road section based on the vehicle density, average vehicle speed and traffic flow of each road section;

[0143] Determine whether the road congestion coefficient of each road section is greater than a preset congestion threshold, and determine whether the road section greater than the preset congestion threshold has an obstacle area that affects vehicle driving;

[0144] According to the received driving data, the target vehicle passing through the obstacle area is determined.

[0145] In one embodiment, when the processor 1001 determines the vehicle density, the mean vehicle speed, and the traffic flow of each road section in the road network according to the received road perception information, the processor 1001 specifically performs the following operations:

[0146] According to the signal light control information, determine the total time required for the signal light to be in the green light phase;

[0147] Acquire a first road condition image corresponding to the start time of the green light phase and a second road condition image corresponding to the end time of the green light phase from the received road condition image of each road section;

[0148] marking the position and bounding box of the vehicle in the first road condition image, and marking the position and bounding box of the vehicle in the second road condition image;

[0149] Counting the total number of first vehicles in the first road condition image according to the positions and bounding boxes of the vehicles in the first road condition image;

[0150] Counting the total number of second vehicles in the second road condition image according to the positions and bounding boxes of the vehicles in the second road condition image;

[0151] The ratio between the sum of the first total number of vehicles, the second total number of vehicles and the total time required in the green light phase is used as the vehicle density of each road section under normal traffic conditions;

[0152] Optical flow tracking is performed based on the position and bounding box of the vehicle in the first road condition image and the position and bounding box of the vehicle in the second road condition image, the speed of the vehicle per unit time is calculated, and the average vehicle speed and traffic flow of each road section under normal traffic conditions are obtained.

[0153] In one embodiment, when the processor 1001 calculates the road congestion coefficient of each road section based on the vehicle density, the average vehicle speed and the traffic flow of each road section, the processor 1001 specifically performs the following operations:

[0154] Calculate the speed ratio between the average vehicle speed of each road section and the preset optimal vehicle speed;

[0155] Calculate the difference between 1 and the speed ratio;

[0156] Calculate the product of vehicle density and difference for each road segment;

[0157] The sum of the product and the traffic flow of each road section is taken as the road section congestion coefficient of each road section; wherein, the calculation formula of the road section congestion coefficient of each road section is:

[0158] Congestion coefficient = vehicle density × (1-average vehicle speed / optimal speed) + traffic flow.

[0159] In one embodiment, when the processor 1001 determines the target vehicle passing through the obstacle area according to the received driving data, the processor 1001 specifically performs the following operations:

[0160] Obtain the road section identification to which the obstacle area belongs and the target position of the obstacle area;

[0161] Perform collision detection based on the vehicle's position and driving direction, road section signs, and target position to determine the initial vehicle passing through the obstacle area;

[0162] According to the initial vehicle speed and acceleration, determine the driving time for each vehicle to reach the obstacle area;

[0163] The obstacle type and driving time in the obstacle area are input into the pre-built obstacle dissipation portrait model to determine the obstacle dissipation probability of each initial vehicle when it reaches the obstacle area;

[0164] An initial vehicle whose obstacle dissipation probability is less than a preset probability threshold is determined as a target vehicle passing through the obstacle area.

[0165] In one embodiment, when the processor 1001 generates a pre-built obstacle dissipation portrait model, the processor 1001 specifically performs the following operations:

[0166] Obtain historical obstacle areas within a preset time period in the road network;

[0167] Obtain the obstacle dissipation matrix corresponding to the entire life cycle of each obstacle event corresponding to each historical obstacle area; wherein the obstacle dissipation matrix expresses the spatiotemporal information of the entire life cycle of the obstacle area from its appearance to its end;

[0168] The obstacle dissipation matrix is ​​segmented according to a preset unit time to obtain segmented space-time slice information;

[0169] Constructing an obstacle dissipation model, which includes a convolutional neural network model;

[0170] Use the segmented space-time slice information to dissipate the obstacle model and output the model loss value;

[0171] When the model loss value reaches the minimum, a pre-built obstacle dissipation portrait model is generated.

[0172] In the embodiment of the present application, on the one hand, the roadside subsystem and the cloud platform subsystem can send warning information or vehicle driving parameters to the vehicle subsystem through the roadside base station to realize information display or vehicle control in the automatic driving state. The roadside base station communicates based on the dual-intelligence private network. The dual-intelligence private network combines the advantages of edge computing and cloud computing, and can track road perception information and driving data in a timely manner, quickly respond to road problems and safety hazards, and can transmit information in a timely manner in the field of unmanned driving, thereby reducing the risk of vehicle driving. On the other hand, the cloud can identify the vehicle through the received driving data and the pre-built obstacle dissipation portrait model. The pre-built obstacle dissipation portrait model is generated based on the obstacle dissipation matrix corresponding to each obstacle event in the entire life cycle of each historical obstacle area. The obstacle dissipation matrix expresses the spatiotemporal information of the entire life cycle of the obstacle area from its appearance to its end, and can be prepared to characterize whether there is obstacle dissipation when the vehicle reaches the obstacle area, thereby improving the accuracy of identifying vehicles affected by the obstacle area.

[0173] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing related hardware through a computer program, and the program of vehicle-road collaboration based on dual-intelligent private network can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the storage medium of the program of vehicle-road collaboration based on dual-intelligent private network can be a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0174] The above disclosure is only the preferred embodiment of the present application, which certainly cannot be used to limit the scope of rights of the present application. Therefore, equivalent changes made according to the claims of the present application are still within the scope covered by the present application.

Claims

1. A vehicle-road cooperative system based on dual-intelligence private network, characterized in that: The system comprises: The vehicle-side subsystem, roadside subsystem and cloud platform subsystem are installed in the vehicle; the roadside subsystem includes a base station applied to the dual-intelligence private network; the cloud platform subsystem is connected to the vehicle-side subsystem and the roadside subsystem through the base station; wherein, The on-board subsystem is used to create warning information for traffic warning according to the danger information existing in the driving process of the vehicle, and send it to the roadside subsystem through the base station; the roadside subsystem is used to broadcast the warning information to the on-board subsystem installed on each vehicle within a preset range in combination with the base station according to the received warning information or the perception data from other perception devices; the on-board subsystem is also used to display the received warning information, or control the driving of the vehicle based on the received warning information when in the automatic driving state; The vehicle-side subsystem is also used to collect driving data of vehicles in the road network in real time, and send it to the cloud platform subsystem through the base station; the roadside subsystem is also used to collect road perception information in the road network in real time, and send it to the cloud platform subsystem through the base station; the cloud platform subsystem is used to dynamically identify obstacle areas that affect vehicle driving in the road network and target vehicles passing through the obstacle areas based on the received driving data and road perception information, and create vehicle driving parameters for each target vehicle, and send the vehicle driving parameters to the vehicle-side subsystem installed on each target vehicle through the base station; the vehicle-side subsystem is also used to display the received vehicle driving parameters, or when in the automatic driving state, control the driving of the target vehicle based on the received vehicle driving parameters; wherein, The method of dynamically identifying obstacle areas in the road network that affect vehicle travel and target vehicles passing through the obstacle areas based on the received driving data and road perception information includes: Determine the vehicle density, vehicle speed average and traffic flow of each road section in the road network according to the received road perception information; Calculate the road congestion coefficient of each road section based on the vehicle density, the average vehicle speed and the traffic flow of each road section; Determine whether the road congestion coefficient of each road section is greater than a preset congestion threshold, and determine whether the road section greater than the preset congestion threshold has an obstacle area that affects vehicle driving; According to the received driving data, a target vehicle passing through the obstacle area is determined; wherein, The driving data includes the position, speed, acceleration and driving direction of the vehicle; The step of determining the target vehicle passing through the obstacle area according to the received driving data includes: Obtaining the road section identifier to which the obstacle area belongs and the target position of the obstacle area; Perform collision detection based on the position and driving direction of the vehicle, the road section mark and the target position to determine the initial vehicle passing through the obstacle area; Determining the driving time of each vehicle to reach the obstacle area according to the speed and acceleration of the initial vehicle; Inputting the obstacle type of the obstacle area and the driving duration into a pre-built obstacle dissipation portrait model to determine the obstacle dissipation probability of each initial vehicle when arriving at the obstacle area; Determine an initial vehicle whose obstacle dissipation probability is less than a preset probability threshold as a target vehicle passing through the obstacle area; The following steps are followed to generate a pre-built obstacle dissipation portrait model, including: Obtaining historical obstacle areas within a preset time period in the road network; Obtain the obstacle dissipation matrix corresponding to the entire life cycle of each obstacle event corresponding to each historical obstacle area; wherein the obstacle dissipation matrix expresses the spatiotemporal information of the entire life cycle of the obstacle area from its appearance to its end; Segmenting the obstacle dissipation matrix according to a preset unit time to obtain segmented space-time slice information; Constructing an obstacle dissipation model, wherein the obstacle dissipation model includes a convolutional neural network model; Using the segmented space-time slice information to dissipate the obstacle model, outputting the model loss value; When the model loss value reaches the minimum, a pre-built obstacle dissipation portrait model is generated.

2. The vehicle-road cooperative system based on dual-intelligence private network according to claim 1, characterized in that: The vehicle-side subsystem includes an autonomous driving unit, an on-board computing unit, a human-computer interaction component, an electronic auxiliary unit, and a communication component applied to the dual-intelligence private network; wherein, The autonomous driving unit, the on-board computing unit, the human-computer interaction component, the electronic auxiliary unit, and the communication component applied to the dual-intelligence private network are electrically connected; wherein, The vehicle-mounted computing unit is used to receive warning information sent from the roadside subsystem or receive vehicle driving parameters sent from the cloud platform subsystem; The automatic driving unit is used to generate a driving route and a vehicle control strategy of the vehicle according to the warning information or the vehicle driving parameters, and control the electronic assistance unit based on the driving route and the vehicle control strategy to realize automatic driving of the vehicle; The human-computer interaction component is used to receive vehicle control instructions; The on-board computing unit is also used to create warning information for traffic warning based on the danger information existing during the vehicle's driving process, and send it to the roadside subsystem through the base station; or it is also used to collect driving data of vehicles in the road network in real time, and send it to the cloud platform subsystem through the base station.

3. The system according to claim 1, characterized in that The received road perception information includes a road condition image of each road section and signal light control information; Determining the vehicle density, vehicle speed average, and traffic flow of each road section in the road network according to the received road perception information includes: Determining the total time required for the signal light to be in the green light phase according to the signal light control information; Acquire a first road condition image corresponding to the start time of the green light phase and a second road condition image corresponding to the end time of the green light phase from the received road condition image of each road section; marking the position and bounding box of the vehicle in the first road condition image, and marking the position and bounding box of the vehicle in the second road condition image; Counting the total number of first vehicles in the first road condition image according to the positions and bounding boxes of the vehicles in the first road condition image; Counting the total number of second vehicles in the second road condition image according to the positions and bounding boxes of the vehicles in the second road condition image; The ratio between the sum of the first total number of vehicles and the second total number of vehicles and the total time required in the green light phase is used as the vehicle density of each road section under normal traffic conditions; Optical flow tracking is performed based on the position and bounding box of the vehicle in the first road condition image and the position and bounding box of the vehicle in the second road condition image, the speed of the vehicle per unit time is calculated, and the average vehicle speed and traffic flow of each road section under normal traffic conditions are obtained.

4. The system according to claim 1, characterized in that The calculating of the road congestion coefficient of each road section based on the vehicle density, the mean vehicle speed and the traffic flow of each road section comprises: Calculating a speed ratio between the average vehicle speed of each road section and a preset optimal vehicle speed; Calculate the difference between 1 and the speed ratio; Calculating the product of the vehicle density of each road section and the difference; The sum of the product and the traffic flow of each road section is used as the road section congestion coefficient of each road section; wherein the road section congestion coefficient calculation formula of each road section is: Congestion coefficient = vehicle density × (1-average vehicle speed / optimal speed) + traffic flow.

5. A vehicle-road collaboration method based on a dual-intelligence private network implemented by the system according to any one of claims 1 to 4, characterized in that: The method comprises: The vehicle-side subsystem creates warning information for traffic warning according to the danger information existing in the vehicle driving process, and sends it to the roadside subsystem through the base station; The roadside subsystem broadcasts the warning information to the vehicle-side subsystem installed on each vehicle within a preset range in combination with the base station according to the received warning information or the sensing data from other sensing devices; The vehicle-side subsystem displays the received warning information, or when in autonomous driving mode, controls the vehicle driving based on the received warning information.

6. A vehicle-road collaboration method based on a dual-intelligence private network implemented by the system according to any one of claims 1 to 4, characterized in that: The method comprises: The vehicle subsystem collects the driving data of vehicles in the road network in real time and sends it to the cloud platform subsystem through the base station; The roadside subsystem collects road perception information in the road network in real time and sends it to the cloud platform subsystem through the base station; The cloud platform subsystem dynamically identifies the obstacle areas in the road network that affect vehicle driving and the target vehicles passing through the obstacle areas based on the received driving data and road perception information, creates vehicle driving parameters for each target vehicle, and sends the vehicle driving parameters to the vehicle subsystem installed on each target vehicle through the base station; The vehicle-subsystem displays the received vehicle driving parameters, or when in the automatic driving state, controls the driving of the target vehicle based on the received vehicle driving parameters.

7. A computer storage medium, characterized in that: The computer storage medium stores a plurality of instructions, which are suitable for being loaded by a processor and executing the method according to claim 5 or 6.

Images