Vehicle control method and electronic device

Abstract

The application discloses a vehicle control method and electronic equipment, and belongs to the technical field of vehicles. Through the technical scheme provided by the embodiment of the application, the intersection passing parameters and intersection information of multiple intersections in a target area are acquired, so that the passing condition of the whole target area and the intersection attribute of each intersection in the target area are acquired. Based on the intersection passing parameters of multiple intersections, the intersection information of the multiple intersections, the vehicle driving parameters of the vehicles associated with each intersection, and a target constraint condition, the target passing speed of each intersection is determined, so that the full use of various data in the target area is realized. Based on the target passing speed and the vehicle passing parameters of the vehicles associated with each intersection, the vehicles associated with each intersection are controlled to pass through the corresponding intersection, so that the traffic control of the whole target area is realized, and the efficiency of vehicle passing in the target area is improved.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, and more specifically, to a vehicle control method and electronic device in the field of vehicle technology. Background Technology

[0002] With the rapid increase in the number of motor vehicles, traffic congestion has become one of the key factors restricting urban development. Implementing reasonable and effective traffic control measures is of great significance for alleviating traffic congestion and improving road efficiency.

[0003] In related technologies, traffic flow is often controlled and traffic congestion alleviated by adjusting the timing of traffic lights. However, many intersections in reality lack traffic lights, making effective traffic management impossible. Summary of the Invention

[0004] This application provides a vehicle control method and electronic device, which can improve the effectiveness of traffic management. The technical solution is as follows:

[0005] On the one hand, a vehicle control method is provided, the method comprising:

[0006] Obtain intersection traffic parameters and intersection information for multiple intersections within the target area. The intersection traffic parameters are used to indicate the traffic conditions at the intersections.

[0007] Based on the intersection traffic parameters of the multiple intersections, the intersection information of the multiple intersections, the vehicle driving parameters of the vehicles associated with each intersection, and the target constraints, the target traffic speed of each intersection is determined. The target constraints are used to constrain the vehicle driving parameters of the vehicles associated with each intersection, and the vehicle driving parameters are used to represent the driving state of the vehicles.

[0008] Based on the target traffic speed at each intersection and the vehicle driving parameters of the vehicles associated with each intersection, the vehicles associated with each intersection are controlled to pass through the corresponding intersection.

[0009] On one hand, a vehicle control device is provided, the device comprising:

[0010] The information acquisition module is used to acquire the intersection traffic parameters and intersection information of multiple intersections within the target area. The intersection traffic parameters are used to indicate the traffic conditions of the intersections.

[0011] The target traffic speed determination module is used to determine the target traffic speed of each intersection based on the intersection traffic parameters of the multiple intersections, the intersection information of the multiple intersections, the vehicle driving parameters of the vehicles associated with each intersection, and the target constraint conditions. The target constraint conditions are used to constrain the vehicle driving parameters of the vehicles associated with each intersection, and the vehicle driving parameters are used to represent the driving state of the vehicles.

[0012] The control module is used to control the vehicles associated with each intersection to pass through the corresponding intersection based on the target traffic speed of each intersection and the vehicle driving parameters of the vehicles associated with each intersection.

[0013] In one possible implementation, the intersection traffic parameters include the total travel time of the intersection, the average travel speed of the intersection, and the average distance between the vehicles associated with the intersection and the intersection. The information acquisition module is used to acquire, for any one of the plurality of intersections, the vehicle driving parameters of the vehicles associated with the intersection and the intersection information; and to determine the total travel time of the intersection, the average travel speed of the intersection, and the average distance between the vehicles associated with the intersection and the intersection based on the vehicle driving parameters of the vehicles associated with the intersection.

[0014] In one possible implementation, the vehicle driving parameters include vehicle speed, distance to the intersection, and time taken to pass through the intersection. The information acquisition module is used to accumulate the time taken for vehicles associated with the intersection to pass through the intersection to obtain the total travel time of the intersection; to determine the average speed of the intersection as the average travel speed of the intersection as the average travel speed of the intersection as the average distance between the vehicles associated with the intersection and ...

[0015] In one possible implementation, the intersection information includes intersection location and intersection speed limit. The target traffic speed determination module is used to construct an intersection map network of the target area based on the intersection traffic parameters, intersection speed limits, and intersection locations of the plurality of intersections. The intersection map network includes intersection nodes corresponding to each intersection. Based on the intersection map network of the target area, the vehicle driving parameters of the vehicles associated with each intersection, and target constraints, the module determines the target traffic speed of each intersection.

[0016] In one possible implementation, the target traffic speed determination module is used to create multiple intersection nodes, each corresponding to a plurality of intersections; determine the node characteristics of each intersection node as the intersection traffic parameters and intersection speed limits of the corresponding intersection; determine the adjacency relationship and distance between every two intersections based on the intersection locations of the plurality of intersections; and create connections between the multiple intersection nodes based on the adjacency relationship and distance between every two intersections to obtain the intersection graph network.

[0017] In one possible implementation, the vehicle driving parameters include vehicle speed and distance to the corresponding intersection. The target traffic speed determination module is used to update the intersection graph network with multiple candidate accelerations to obtain multiple prediction graph networks, where the candidate accelerations are the accelerations of vehicles associated with the corresponding intersections; perform graph convolution on the multiple prediction graph networks to obtain multiple candidate overall traffic durations for the target area; and determine the target traffic speed for each intersection based on the multiple candidate overall traffic durations, the multiple candidate accelerations, the vehicle driving parameters of vehicles associated with each intersection, and the target constraints.

[0018] In one possible implementation, the target traffic speed determination module is used to determine the predicted node features of the multiple intersection nodes based on the candidate acceleration and the node features of the multiple intersection nodes in the intersection graph network for any candidate acceleration among the multiple candidate accelerations; and update the node features of each intersection node using the predicted node features of the multiple intersection nodes to obtain the prediction graph network corresponding to the candidate acceleration.

[0019] In one possible implementation, the target traffic speed determination module is configured to: determine a first acceleration from among the plurality of candidate overall traffic durations based on the plurality of candidate overall traffic durations, wherein the candidate overall traffic duration corresponding to the first acceleration is the shortest among the plurality of candidate overall traffic durations; determine a first predicted vehicle driving parameter for each vehicle associated with each intersection based on the first acceleration and the vehicle driving parameters associated with each intersection; and determine the vehicle speed in the first predicted vehicle driving parameter as the target traffic speed if the first predicted vehicle driving parameter of each vehicle associated with each intersection meets the target constraint condition.

[0020] In one possible implementation, the target traffic speed determination module is further configured to: determine a second acceleration from the plurality of candidate accelerations, based on the condition that the first predicted vehicle driving parameters of the vehicles associated with any of the plurality of intersections do not meet the target constraint conditions, wherein the candidate overall travel time corresponding to the second acceleration is the second shortest among the plurality of candidate overall travel times; determine a second predicted vehicle driving parameter for the vehicles associated with each of the intersections based on the second acceleration and the vehicle driving parameters of the vehicles associated with each of the intersections; and determine the vehicle speed in the second predicted vehicle driving parameter as the target traffic speed if the second predicted vehicle driving parameters of the vehicles associated with each of the intersections meet the target constraint conditions.

[0021] In one possible implementation, the device further includes:

[0022] The condition discrimination module is used to determine the distance between vehicles associated with each intersection and the estimated collision duration based on the first predicted vehicle driving parameters of the vehicles associated with each intersection; and to determine whether the vehicle speed, the distance between vehicles associated with each intersection and the estimated collision duration in the first predicted vehicle driving parameters meet the target constraint conditions.

[0023] The target traffic speed determination module is further configured to determine the vehicle speed in the first predicted vehicle driving parameters as the target traffic speed if the vehicle speed in the first predicted vehicle driving parameters, the distance between vehicles associated with each intersection, and the expected collision duration meet the target constraint conditions.

[0024] In one possible implementation, the vehicle speed, the distance between vehicles associated with each of the intersections, and the estimated collision duration in the first predicted vehicle driving parameters meeting the target constraint conditions mean that:

[0025] The first predicted vehicle speed is less than or equal to the speed limit at the corresponding intersection.

[0026] The distance between vehicles associated with each of the aforementioned intersections is greater than or equal to a preset distance;

[0027] The expected collision duration between vehicles associated with each of the aforementioned intersections is greater than or equal to the preset collision duration.

[0028] In one possible implementation, the vehicle driving parameters include the distance to the corresponding intersection. The control module is used to determine the vehicle passage order of the vehicles associated with each intersection at the corresponding intersection based on the distance between the vehicles associated with each intersection and the corresponding intersection; and to send the target passage speed of each intersection to the target vehicles corresponding to each intersection, so that the vehicles associated with each intersection can pass through the corresponding intersection, with the target vehicles having the first passage order.

[0029] In one possible implementation, the control module is configured to, for any one of the plurality of intersections, arrange the vehicles associated with the intersection in ascending order of their distance from the intersection, thereby obtaining the vehicle passage order of the vehicles associated with the intersection at the intersection.

[0030] In one possible implementation, the vehicles associated with each of the intersections include vehicles that have already entered and those that will enter each of the intersections.

[0031] On one hand, an electronic device is provided, the electronic device including one or more processors and one or more memories, the one or more memories storing at least one piece of program code, the program code being loaded and executed by the one or more processors to implement the electronic device control method.

[0032] On one hand, a computer-readable storage medium is provided, wherein at least one piece of program code is stored in the computer-readable storage medium, the program code being loaded and executed by a processor to implement the vehicle control method.

[0033] The technical solution provided in this application obtains intersection traffic parameters and intersection information for multiple intersections within a target area, thereby acquiring the overall traffic situation and intersection attributes of each intersection within the target area. Based on the intersection traffic parameters, intersection information, vehicle driving parameters associated with each intersection, and target constraints, the target traffic speed for each intersection is determined, thus achieving full utilization of various types of data within the target area. Based on the target traffic speed and the vehicle traffic parameters associated with each intersection, the vehicles associated with each intersection are controlled to pass through the corresponding intersection, thereby achieving overall traffic control of the target area and improving the efficiency of vehicle traffic within the target area. Attached Figure Description

[0034] Figure 1 This is a schematic diagram of the implementation environment of a vehicle control method provided in an embodiment of this application;

[0035] Figure 2 This is a flowchart of a vehicle control method provided in an embodiment of this application;

[0036] Figure 3 This is a flowchart of another vehicle control method provided in an embodiment of this application;

[0037] Figure 4 This is a schematic diagram of a rotating projection provided in an embodiment of this application;

[0038] Figure 5 This is an architecture diagram of a vehicle control method provided in an embodiment of this application;

[0039] Figure 6 This is a schematic diagram of the structure of a vehicle control device provided in an embodiment of this application;

[0040] Figure 7 This is a schematic diagram of the structure of a vehicle provided in an embodiment of this application. Detailed Implementation

[0041] The technical solutions in this application will be clearly and thoroughly described below with reference to the accompanying drawings. In the description of the embodiments of this application, unless otherwise stated, " / " means "or," for example, A / B can mean A or B. "And / or" in the text is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Furthermore, in the description of the embodiments of this application, "multiple" refers to two or more than two.

[0042] In the following text, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of technical features reflected. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature.

[0043] An intersection is a point where two or more roads meet. It is a necessary route for vehicles and pedestrians to converge, turn, and disperse. Based on the number of intersecting roads, intersections can be classified as three-way intersections, four-way intersections, or multi-way intersections. Based on the method of intersection, they can be classified as at-grade intersections or grade-separated intersections.

[0044] Non-signalized intersections: intersections without traffic lights.

[0045] Intelligent Connected Vehicles (ICVs) refer to a new generation of automobiles that organically combine vehicle networking and intelligent vehicles, ultimately replacing human operation. ICVs are equipped with advanced onboard sensors, controllers, actuators, and other devices, integrating modern communication and network technologies to achieve intelligent information exchange and sharing between vehicles, people, roads, and backend systems. They are characterized by safety, comfort, energy efficiency, and high performance.

[0046] Edge computing refers to an open platform that integrates network, computing, storage, and application capabilities, located close to the source of objects or data, to provide services at the nearest edge. Applications originate at the edge, resulting in faster network service responses and meeting the industry's basic needs in real-time business, application intelligence, security, and privacy protection. Edge computing sits between physical entities and industrial connections, or at the top of physical entities. Cloud computing can still access historical data from edge computing.

[0047] The implementation environment of the embodiments of this application is described below. See also... Figure 1 The implementation environment of the vehicle control method provided in this application includes an on-board terminal 101, an intersection control device 102, and a cloud platform 103.

[0048] The vehicle terminal 101 is a terminal installed on the vehicle. The vehicle terminal 101 is connected to the cloud platform 103 via a wireless network. When the vehicle where the vehicle terminal 101 is located enters the control range of any intersection control device 102, the vehicle terminal 101 can connect to the intersection control device 102 via a wireless network to collect vehicle driving parameters and receive control commands from the intersection control device 102 or the cloud platform 103.

[0049] The intersection control device 102 is installed at an intersection to control vehicles associated with that intersection. The intersection control device 102 is connected to the cloud platform 103 via a wireless network, enabling data exchange between them. In some embodiments, the intersection control device 102 can remotely control the vehicle-mounted terminal 101, sending remote control commands to the vehicle-mounted terminal 101, which then executes the actions instructed by the remote control commands. The vehicle-mounted terminal 101 can also send information to the cloud platform 103 through the intersection control device 102.

[0050] Cloud platform 103 is a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery network (CDN), and big data and artificial intelligence platforms. In some embodiments, cloud platform 103 is also referred to as a TSP (Telematics Service Provider) platform.

[0051] After introducing the implementation environment of the embodiments of this application, the application scenarios of the technical solutions provided by the embodiments of this application are described below. The technical solutions provided by the embodiments of this application can be applied to scenarios of traffic control at non-signal-controlled intersections. After adopting the technical solutions provided by the embodiments of this application, the cloud platform can obtain the intersection traffic parameters and intersection information of multiple intersections within the target area. The intersection communication parameters are used to indicate the traffic status of the intersections. The target area is an area with non-signal-controlled intersections, and the intersections within the target area refer to non-signal-controlled intersections. Based on the intersection traffic parameters of the multiple intersections, the intersection information of the multiple intersections, the vehicle driving parameters of the vehicles associated with each intersection, and the target constraints, the cloud platform determines the target traffic speed of each intersection. The target constraints are used to constrain the vehicle driving parameters of the vehicles associated with each intersection, and the vehicle driving parameters are used to indicate the driving status of the vehicles. The cloud platform controls the passage of vehicles associated with each intersection through the corresponding intersection based on the target traffic speed of each intersection and the vehicle driving parameters of the vehicles associated with each intersection, thereby achieving overall traffic control of the target area.

[0052] After introducing the implementation environment and application scenarios of the embodiments of this application, the technical solutions provided by the embodiments of this application are described below. (See also...) Figure 2 Taking a cloud platform as the executing entity as an example, the method includes the following steps.

[0053] 201. The cloud platform obtains the intersection traffic parameters and intersection information of multiple intersections within the target area. These intersection traffic parameters are used to indicate the traffic conditions at the intersections.

[0054] The target area includes areas with non-signaled intersections; correspondingly, all of these intersections are non-signaled intersections. In terms of relative location, these intersections include both adjacent and non-adjacent intersections. Intersection information describes the intersection's attributes; for example, the intersection's location can be considered a type of intersection information. Traffic conditions provide a macroscopic description of how vehicles pass through the intersection.

[0055] 202. Based on the intersection traffic parameters of the multiple intersections, the intersection information of the multiple intersections, the vehicle driving parameters of the vehicles associated with each intersection, and the target constraints, the cloud platform determines the target traffic speed of each intersection. The target constraints are used to constrain the vehicle driving parameters of the vehicles associated with each intersection, and the vehicle driving parameters are used to represent the driving status of the vehicles.

[0056] The vehicles associated with the intersection include those already entering and those about to enter the intersection. These vehicles can be electric, hybrid, or gasoline-powered; this embodiment does not limit the specific types. Vehicle driving parameters represent the vehicle's driving state, which describes its operational status. Target constraints constrain the vehicle's driving parameters, i.e., constrain its driving state. In this embodiment, setting target constraints to constrain the vehicle's driving parameters ensures vehicle safety. The target traffic speed at the intersection controls the speed at which vehicles pass through the intersection; the target traffic speed may differ for different intersections.

[0057] 203. The cloud platform controls the vehicles associated with each intersection to pass through the corresponding intersection based on the target traffic speed of each intersection and the vehicle driving parameters of the vehicles associated with each intersection.

[0058] The technical solution provided in this application obtains intersection traffic parameters and intersection information for multiple intersections within a target area, thereby acquiring the overall traffic situation and intersection attributes of each intersection within the target area. Based on the intersection traffic parameters, intersection information, vehicle driving parameters associated with each intersection, and target constraints, the target traffic speed for each intersection is determined, thus achieving full utilization of various types of data within the target area. Based on the target traffic speed and the vehicle traffic parameters associated with each intersection, the vehicles associated with each intersection are controlled to pass through the corresponding intersection, thereby achieving overall traffic control of the target area and improving the efficiency of vehicle traffic within the target area.

[0059] It should be noted that steps 201-203 above are a simplified description of the vehicle control method provided in the embodiments of this application. The vehicle control method provided in the embodiments of this application will be described in more detail below with some examples. See [link to relevant documentation]. Figure 3 Taking a cloud platform as the executing entity as an example, the method includes the following steps.

[0060] It should be noted that the vehicle control method provided in this application embodiment will be executed repeatedly in multiple cycles. For ease of understanding, the following description will be based on one cycle.

[0061] 301. The cloud platform obtains the intersection traffic parameters and intersection information of multiple intersections within the target area. These intersection traffic parameters are used to indicate the traffic conditions at the intersections.

[0062] The target area includes areas with non-signaled intersections; correspondingly, all of these intersections are non-signaled intersections. In terms of relative location, these intersections include both adjacent and non-adjacent intersections. Intersection information describes the intersection's attributes; for example, the intersection's location can be considered a type of intersection information. Intersection traffic parameters represent the intersection's traffic conditions, providing a macroscopic description of how vehicles pass through the intersection. For example, traffic conditions reflect whether vehicle passage through the intersection is smooth and whether the intersection's traffic efficiency is high enough.

[0063] In one possible implementation, the intersection traffic parameters include the total travel time of the intersection, the average travel speed of the intersection, and the average distance between the intersection and the vehicles associated with the intersection. For any one of the plurality of intersections, the cloud platform obtains the vehicle driving parameters of the vehicles associated with the intersection and the intersection information. Based on the vehicle driving parameters of the vehicles associated with the intersection, the cloud platform determines the total travel time of the intersection, the average travel speed of the intersection, and the average distance between the intersection and the vehicles associated with the intersection.

[0064] The vehicles associated with an intersection include those already entering and those about to enter. An intersection can have one or more associated vehicles. When multiple vehicles are associated, their directions may be the same or different, but they are all moving towards the intersection. Vehicle driving parameters represent the vehicle's driving status, describing its operation. The total travel time at an intersection refers to the time required for all associated vehicles to pass through the intersection. The average travel speed at an intersection refers to the average speed of the associated vehicles. Because vehicle driving parameters may change at any time, the total travel time, average travel speed, and average distance between the associated vehicles and the intersection may differ at different times.

[0065] In this implementation, the intersection traffic parameters of each intersection can be determined by the vehicle driving parameters of the vehicles associated with each intersection. This achieves the aggregation of vehicle driving parameters at the vehicle level to intersection traffic parameters at the intersection level, making full use of vehicle driving parameters. The resulting intersection traffic parameters can more accurately reflect the traffic situation at the intersection.

[0066] To provide a clearer explanation of the above embodiments, the following description is divided into two parts.

[0067] Part 1: For any one of the multiple intersections, the cloud platform obtains the vehicle driving parameters of the vehicles associated with that intersection and the intersection information.

[0068] In one possible implementation, for any one of the plurality of intersections, the cloud platform obtains the vehicle driving parameters of the vehicles associated with the intersection and the intersection information of the intersection from the intersection control equipment set at the intersection.

[0069] The intersection control device is installed at any location within the intersection. Vehicles associated with the intersection establish a wireless connection with the control device, allowing it to acquire vehicle driving parameters. In some embodiments, the wireless communication range of the intersection control device is limited; only vehicles entering this range can establish a wireless connection. When a vehicle enters the wireless communication range, its onboard terminal can establish a wireless connection, enabling data exchange. The intersection control device stores intersection information, which the cloud platform can directly retrieve from the device.

[0070] In this implementation, the intersection control equipment can obtain the vehicle driving parameters of the vehicles associated with the intersection and the intersection information, which is highly efficient.

[0071] For example, for any one of the multiple intersections, the cloud platform sends an information retrieval request to the intersection control device installed at that intersection. Upon receiving the request, the intersection control device, in response, sends the vehicle driving parameters of the vehicles associated with that intersection and the intersection information to the cloud platform. The cloud platform then retrieves the vehicle driving parameters of the vehicles associated with that intersection and the intersection information.

[0072] It should be noted that the above description is based on the example of the cloud platform actively obtaining the vehicle driving parameters of the vehicles associated with the intersection and the intersection information from the intersection control equipment. In other possible implementations, the vehicle driving parameters of the vehicles associated with the intersection and the intersection information are actively sent to the cloud platform by the intersection control equipment. Since the vehicle driving parameters change in real time, the intersection control equipment can periodically send the vehicle driving parameters, while the intersection information does not change and only needs to be sent once.

[0073] Part Two: Based on the vehicle driving parameters of the vehicles associated with the intersection, the cloud platform determines the total travel time of the intersection, the average travel speed of the intersection, and the average distance between the vehicles associated with the intersection and the intersection.

[0074] In one possible implementation, the vehicle's driving parameters include its speed, distance to the intersection, and time taken to pass through the intersection. The cloud platform sums up the time taken by all vehicles associated with the intersection to obtain the total travel time at the intersection. The cloud platform determines the average speed of the intersection as the average travel speed of all vehicles associated with the intersection. The cloud platform also determines the average distance between the intersection and all vehicles associated with the intersection.

[0075] The time it takes for a vehicle to pass through the intersection is the time required for the vehicle to pass through the intersection from its current position. The distance between the vehicle and the intersection is the distance between the vehicle's current position and the center of the intersection, which refers to the geometric center of the intersection. The total travel time through the intersection, the average travel speed, and the average distance between the vehicle and the intersection provide a macroscopic reflection of the traffic situation at the intersection.

[0076] In addition to the above-described embodiments, this application also provides another embodiment of step 302.

[0077] In one possible implementation, the cloud platform obtains the intersection traffic parameters and intersection information of each intersection from the intersection control equipment of each intersection within the target area. The intersection traffic parameters of each intersection are determined by the intersection control equipment of each intersection based on the vehicle driving parameters of the vehicles associated with each intersection.

[0078] The method by which the intersection control device determines the intersection passage parameters based on the vehicle driving parameters of the vehicles associated with the intersection is the same inventive concept as the method described in the previous embodiment, whereby the cloud platform determines the intersection passage parameters based on the vehicle driving parameters of the vehicles associated with the intersection. Therefore, it will not be repeated here.

[0079] In this implementation, the cloud platform can directly obtain the intersection traffic parameters and intersection information from the intersection control equipment at each intersection. The cloud platform does not need to perform the process of determining the intersection traffic parameters; instead, the intersection control equipment performs the process of determining the intersection traffic parameters, thereby achieving the purpose of distributed computing and reducing the load on the cloud platform.

[0080] For example, there are long-term connections between the intersection control devices of multiple intersections in the target area of ​​the cloud platform. Each intersection control device can periodically send the corresponding intersection traffic parameters to the cloud platform. Since the intersection information of each intersection does not change, each intersection control device only needs to send the intersection information to the cloud platform once.

[0081] 302. Based on the intersection traffic parameters of the multiple intersections, the intersection information of the multiple intersections, the vehicle driving parameters of the vehicles associated with each intersection, and the target constraints, the cloud platform determines the target traffic speed of each intersection. The target constraints are used to constrain the vehicle driving parameters of the vehicles associated with each intersection, and the vehicle driving parameters are used to represent the driving status of the vehicles.

[0082] In this application, the vehicles associated with the intersections can be electric vehicles, hybrid vehicles, or gasoline-powered vehicles; this embodiment does not limit the specific types. Target constraints are used to constrain the vehicle's driving parameters, i.e., to constrain the vehicle's driving state. In this embodiment, setting target constraints to constrain the vehicle's driving parameters is to ensure vehicle safety. The target traffic speed at the intersection controls the speed at which vehicles pass through the intersection; the target traffic speed may differ at different intersections. Since the efficiency of vehicles passing through each intersection affects each other, when all vehicles associated with each intersection travel at the target traffic speed of the corresponding intersection, the traffic efficiency of these multiple intersections is high, meaning the traffic efficiency of the target area is high.

[0083] In one possible implementation, the intersection information includes the intersection location and the intersection speed limit. Based on the intersection traffic parameters, speed limits, and locations of these multiple intersections, the cloud platform constructs an intersection map network for the target area. This intersection map network includes intersection nodes corresponding to each intersection. Based on the intersection map network of the target area, the vehicle driving parameters associated with each intersection, and the target constraints, the cloud platform determines the target traffic speed for each intersection.

[0084] The intersection graph network describes the topological relationships and traffic characteristics of multiple intersections. It includes multiple intersection nodes and the relationships between them, which refer to their relative positions. Objective constraints are used to regulate the vehicle driving parameters associated with each intersection to ensure safe passage. These constraints are set by technicians based on actual conditions, and this embodiment does not impose such limitations.

[0085] In this implementation, an intersection map network for the target area is constructed using intersection traffic parameters, intersection speed limits, and intersection locations. The target traffic speed for each intersection is determined using the intersection map network, vehicle driving parameters associated with each intersection, and target constraints. This improves the traffic efficiency of vehicles within the target area while ensuring safety.

[0086] To provide a clearer explanation of the above embodiments, the following description will be divided into several parts.

[0087] Part 1: The cloud platform constructs an intersection map network for the target area based on the intersection traffic parameters, intersection speed limits, and intersection locations of these multiple intersections.

[0088] In one possible implementation, the cloud platform creates multiple intersection nodes, each corresponding one-to-one with a set of intersections. The cloud platform identifies the node characteristics of each intersection node as the intersection's traffic parameters and speed limits. Based on the intersection locations, the cloud platform determines the adjacency relationship and distance between every two intersections. Based on this adjacency relationship and distance, the cloud platform creates connections between the intersection nodes, thus obtaining the intersection graph network.

[0089] In this context, an intersection node is an abstract representation of an intersection, and its node features represent the characteristics of the corresponding intersection. A line connecting two intersection nodes indicates the adjacency relationship between the two intersections. This intersection graph network format provides a relatively intuitive display of multiple intersections within a target area. The location of an intersection can refer to either its center or the location of intersection control equipment; this embodiment does not impose such limitations.

[0090] In this implementation, the cloud platform creates multiple intersection nodes, and determines the intersection traffic parameters and speed limits of the corresponding intersection nodes as the node features. By using the intersection locations, connections are generated between the intersection nodes to obtain the intersection graph network. This fully utilizes the collected data, resulting in a high accuracy of the intersection graph network.

[0091] For example, the cloud platform creates intersection nodes corresponding to each intersection within the target area. The node identifier of each intersection node is the intersection identifier of the corresponding intersection. The cloud platform determines the node characteristics of each intersection node as the intersection traffic parameters and speed limits for the corresponding intersection. Based on the intersection locations of these multiple intersections, the cloud platform determines the adjacency relationship and distance between every two intersections. Based on this adjacency relationship, the cloud platform adds connections between adjacent intersection nodes. The weight of these connections is determined based on the distance between the intersections corresponding to adjacent intersection nodes, resulting in the intersection graph network. This weight is negatively correlated with distance.

[0092] For example, we can define an intersection graph network, which includes a set of vertices and a set of edges, that is, G =<V,E> Where G is the intersection graph network, V is the set of points, and E is the set of edges. V includes multiple intersection nodes and the node features of each intersection node, and E includes the connections between intersection nodes and the weights of the connections. In some embodiments, an adjacency matrix A can be used. ij Let E and A represent ij The determination method is as follows: formula (1).

[0093] (1)

[0094] in, For adjustment coefficients, and For the identification of intersection nodes, intersection node and intersection nodes The distance between them Indicates intersection node The maximum distance among all connected intersection nodes.

[0095] It should be noted that since the number and location of multiple intersections will not change, the number of intersection nodes, the connections, and the weights of the connections in the intersection graph network will also remain unchanged. In subsequent processing, only the node characteristics of the intersection nodes in the intersection graph network need to be adjusted.

[0096] Part Two: Based on the intersection map network of the target area, the vehicle driving parameters of the vehicles associated with each intersection, and the target constraints, the cloud platform determines the target traffic speed for each intersection.

[0097] In one possible implementation, the vehicle driving parameters include vehicle speed and distance to the corresponding intersection. The cloud platform updates the intersection graph network with multiple candidate accelerations to obtain multiple prediction graph networks. The candidate accelerations are the accelerations of vehicles associated with the corresponding intersections. The cloud platform performs graph convolution on these multiple prediction graph networks to obtain multiple candidate overall travel times for the target area. Based on these multiple candidate overall travel times, the multiple candidate accelerations, the vehicle driving parameters of vehicles associated with each intersection, and the target constraints, the cloud platform determines the target travel speed for each intersection.

[0098] The candidate accelerations are configured by technicians based on actual conditions. These candidate accelerations represent vehicle accelerations and can be either positive (indicating acceleration) or negative (indicating deceleration). This embodiment does not limit this. Updating the intersection graph network using candidate accelerations is to update the node features of the intersection nodes. Since node features include intersection traffic parameters and intersection speed limits, and the speed limits do not change, candidate accelerations are used to predict the traffic parameters for the next control cycle. Multiple candidate overall travel times correspond to multiple candidate accelerations, and one candidate overall travel time corresponds to one candidate acceleration. A candidate overall travel time is the overall travel time obtained after prediction using the corresponding candidate acceleration. The overall travel time refers to the total time required for all vehicles in the target area to pass through the intersection.

[0099] In this implementation, the intersection graph network is updated using multiple candidate accelerations to obtain multiple prediction graph networks. Graph convolution is performed on the multiple prediction graph networks to obtain multiple candidate overall travel times for the target area. Using these multiple candidate overall travel times, multiple candidate accelerations, vehicle driving parameters associated with each intersection, and target constraints, the target travel speed is determined, which more closely reflects the actual situation of the target area.

[0100] To provide a clearer explanation of the above embodiments, the following description will be divided into several parts.

[0101] A. The cloud platform updates the intersection graph network using multiple candidate accelerations, resulting in multiple prediction graph networks.

[0102] In one possible implementation, for any candidate acceleration among the plurality of candidate accelerations, the cloud platform determines the predicted node features of the plurality of intersection nodes based on the candidate acceleration and the node features of the plurality of intersection nodes in the intersection graph network. The cloud platform updates the node features of each intersection node using the predicted node features of the plurality of intersection nodes to obtain the prediction graph network corresponding to the candidate acceleration.

[0103] The prediction graph network is used to reflect the traffic situation in the target area after vehicle control is performed based on candidate acceleration.

[0104] In this implementation, candidate accelerations are used to update the node features of intersection nodes, thereby obtaining predicted node features. The predicted node features are then assigned to the corresponding intersection nodes to obtain a predictive graph network, which has high generation efficiency.

[0105] For example, node features include intersection traffic parameters and intersection speed limits. Intersection traffic parameters include the total travel time at the intersection, the average travel speed at the intersection, and the average distance between the intersection and the vehicles associated with it. Since the intersection speed limit does not change, updating node features actually updates the intersection traffic parameters, namely, the total travel time, the average travel speed, and the average distance between the intersection and the vehicles associated with it. When updating intersection traffic parameters using candidate acceleration, the conversion relationship between speed, acceleration, and distance is used to update speed and distance, thereby updating the total travel time, the average travel speed, and the average distance between the intersection and the vehicles associated with it.

[0106] B. The cloud platform performs graph convolution on the multiple prediction graph networks to obtain multiple candidate overall passage times for the target region.

[0107] In one possible implementation, for any one of the multiple prediction graph networks, the cloud platform performs graph convolution on the node features of the multiple intersection nodes based on the connections between the multiple intersection nodes in the prediction graph network to obtain the candidate overall travel time of the prediction graph network.

[0108] The overall candidate passage time refers to the time required for all vehicles in the target area to pass through the corresponding intersection after vehicle control is performed using the candidate acceleration corresponding to the prediction graph network.

[0109] For example, the cloud platform uses the following formula (2) to perform graph convolution on the prediction graph network to obtain the candidate overall passage time of the prediction graph network.

[0110] (2)

[0111] in, The overall passage time for candidates, intersection node Speed ​​limits at intersections intersection node The average speed of traffic, intersection node The average speed of traffic, intersection node The average distance between the vehicles associated with the corresponding intersection and the intersection itself.

[0112] C. The cloud platform determines the target speed for each intersection based on the overall travel time of the multiple candidates, the acceleration of the multiple candidates, the vehicle driving parameters of the vehicles associated with each intersection, and the target constraints.

[0113] In one possible implementation, the cloud platform determines a first acceleration from among the multiple candidate overall travel times, where the candidate overall travel time corresponding to the first acceleration is the shortest among the multiple candidate overall travel times. Based on the first acceleration and the vehicle driving parameters associated with each intersection, the cloud platform determines first predicted vehicle driving parameters for each intersection. If the first predicted vehicle driving parameters of the vehicles associated with each intersection meet the target constraint, the cloud platform determines the vehicle speed in the first predicted vehicle driving parameters as the target travel speed.

[0114] The vehicle driving parameters include vehicle speed, distance between the vehicle and the intersection, and time taken for the vehicle to pass through the intersection. The first acceleration can be used to update the vehicle speed, distance between the vehicle and the intersection, and time taken for the vehicle to pass through the intersection, thereby obtaining the first predicted vehicle driving parameters, which include the updated vehicle speed, distance between the vehicle and the intersection, and time taken for the vehicle to pass through the intersection.

[0115] For example, the cloud platform obtains the first predicted vehicle driving parameters using the following formulas (3)-(5).

[0116] (3)

[0117] (4)

[0118] (5)

[0119] in, The speed was before the update. For the updated vehicle speed, For the first acceleration, To control the duration, the settings are configured by technical personnel based on the actual situation. This represents the distance between the vehicle and the intersection before the update. This is the updated distance between the vehicle and the intersection. This represents the time it takes for vehicles to pass through the intersection after the update.

[0120] The method for determining whether the first predicted vehicle's driving parameters meet the target constraint is explained below.

[0121] In one possible implementation, the cloud platform determines the distances between vehicles associated with each intersection and the estimated collision duration based on first predicted vehicle driving parameters of the vehicles associated with each intersection. The cloud platform then determines whether the vehicle speed, the distances between vehicles associated with each intersection, and the estimated collision duration in the first predicted vehicle driving parameters meet the target constraint.

[0122] For example, the cloud platform uses the following formulas (6) and (7) to determine the distance between vehicles associated with each intersection and the estimated collision duration.

[0123] (6)

[0124] (7)

[0125] in, In a certain intersection, numbered The vehicle and the number The distance between vehicles In a certain intersection, numbered The vehicle and the number The estimated duration of a collision between vehicles.

[0126] In some embodiments, the vehicle speed, the distance between vehicles associated with each intersection, and the estimated collision duration in the first predicted vehicle driving parameters meet the target constraint condition if: the vehicle speed in the first predicted vehicle driving parameters is less than or equal to the speed limit of the corresponding intersection; the distance between vehicles associated with each intersection is greater than or equal to a preset distance; and the estimated collision duration between vehicles associated with each intersection is greater than or equal to a preset collision duration. An example of the target constraint condition is given in formula (8) below.

[0127] (8)

[0128] in, The minimum distance between two vehicles within the target area. To predict distance, The shortest estimated collision time between the two vehicles in front and behind within the target area. To preset the collision duration, The maximum speed of vehicles within the target area. Speed ​​limits at intersections.

[0129] Based on the above judgment, correspondingly, if the first predicted vehicle driving parameters of the vehicles associated with each intersection meet the target constraint conditions, determining the vehicle speed in the first predicted vehicle driving parameters as the target traffic speed includes:

[0130] If the vehicle speed, the distance between vehicles associated with each intersection, and the estimated collision duration in the first predicted vehicle driving parameters meet the target constraint conditions, the cloud platform determines the vehicle speed in the first predicted vehicle driving parameters as the target traffic speed.

[0131] Furthermore, the above explanation is based on the example that the first predicted vehicle driving parameters meet the target constraint. If any of the first predicted vehicle driving parameters does not meet the target constraint, the cloud platform will perform the following steps.

[0132] In one possible implementation, if the first predicted vehicle driving parameters of vehicles associated with any of the plurality of intersections do not meet the target constraint, the cloud platform determines a second acceleration from the plurality of candidate accelerations. The candidate overall travel time corresponding to this second acceleration is the second shortest among the plurality of candidate overall travel times. Based on this second acceleration and the vehicle driving parameters of vehicles associated with each intersection, the cloud platform determines the second predicted vehicle driving parameters of vehicles associated with each intersection. If the second predicted vehicle driving parameters of vehicles associated with each intersection meet the target constraint, the cloud platform determines the vehicle speed in the second predicted vehicle driving parameters as the target travel speed.

[0133] Optionally, if any of the second predicted vehicle driving parameters does not meet the target constraint, the cloud platform can also obtain a third acceleration from multiple candidate accelerations and determine the target passage speed based on the third acceleration. The implementation process is the same as the above-mentioned method of determining the target passage speed based on the second acceleration, and will not be described in detail here. The candidate overall passage time corresponding to the third acceleration is the third shortest among the multiple candidate overall passage times.

[0134] As can be seen from the above description, determining the target traffic speed may require multiple iterations. The purpose of using target constraints in determining the target traffic speed is to find the maximum traffic speed that satisfies these constraints. Since the target constraints limit vehicle speed, the distance between vehicles at various intersections, and the estimated collision duration—that is, to ensure vehicle safety—the resulting target traffic speed is the maximum traffic speed under the premise of ensuring vehicle safety. Using this target speed to control vehicles can improve traffic efficiency while ensuring vehicle safety.

[0135] 303. The cloud platform sends the target traffic speed to the control devices at each intersection within the target area.

[0136] 304. The control equipment at each intersection controls the vehicles associated with each intersection to pass through the corresponding intersection based on the target traffic speed at each intersection and the vehicle driving parameters of the vehicles associated with each intersection.

[0137] In one possible implementation, the vehicle driving parameters include the distance to the corresponding intersection. Each intersection control device determines the vehicle passage order at the corresponding intersection based on the distance between the vehicle associated with that intersection and the corresponding intersection. Each intersection control device sends the target passage speed for each intersection to the target vehicle corresponding to that intersection, so that the vehicle associated with each intersection passes through the corresponding intersection, with the target vehicle having the first passage order.

[0138] The target vehicle is the vehicle closest to the corresponding intersection.

[0139] In this implementation, an intersection corresponds to at least two roads, and vehicles on different roads enter the intersection from different directions. By using distance to uniformly plan the passage order of vehicles on different roads corresponding to an intersection, a two-dimensional or even multi-dimensional problem is transformed into a one-dimensional problem, which simplifies the control method and improves control efficiency.

[0140] For example, for any one of the plurality of intersections, the intersection control device arranges the vehicles associated with the intersection in ascending order of their distance from the intersection, thus obtaining the vehicle passage order for the vehicles associated with the intersection at that intersection. The intersection control device sends a target passage speed to the target vehicle corresponding to the intersection, so that the target vehicle passes through the intersection at the target passage speed. For other vehicles associated with the intersection, the target passage speed is obtained through the connection with the sensing system and the target vehicle, and vehicle control is performed to allow them to pass through the intersection in the specified passage order. In some embodiments, this method of vehicle control is also referred to as "rotational projection" control.

[0141] For example, see Figure 4 The intersection control device 401 introduces a virtual lane 403 that intersects the actual lanes at the intersection center 402. Specifically, it projects a circle with the intersection center 402 as the center and the distances of vehicles in each lane (lane 404 and lane 405) from the intersection center 402 as the radius onto the virtual lane, ultimately forming a one-dimensional virtual vehicle queue. This transforms a two-dimensional or multi-dimensional problem into a one-dimensional vehicle queue control problem, effectively organizing vehicles to pass through the intersection and improving intersection efficiency while ensuring traffic safety. Vehicles in this one-dimensional virtual queue are arranged according to their passage order.

[0142] To provide a clearer explanation of the technical solutions provided in the embodiments of the application, the following will be combined with... Figure 5 The technical solutions provided in the embodiments of this application will be described in conjunction with the above-described implementation methods.

[0143] See Figure 5The vehicle control method provided in this application embodiment can be divided into a decision layer 501, a scheduling and control layer 502, and an execution layer 503. The decision layer 501 is deployed on a cloud platform and is used to determine the target traffic speed for a target area. The scheduling and control layer 502 is deployed on the intersection control equipment at each intersection and is used to obtain vehicle driving parameters from the on-board terminals of associated vehicles, determine intersection traffic parameters based on the vehicle driving parameters, upload the intersection traffic parameters and intersection information to the cloud platform, and send the target traffic speed to the on-board terminals. The execution layer 503 is deployed on the on-board terminals and is used to upload vehicle driving parameters, obtain the target traffic speed, and control vehicles based on the target traffic speed.

[0144] All of the above-mentioned optional technical solutions can be combined in any way to form the optional embodiments of this application, and will not be described in detail here.

[0145] The technical solution provided in this application obtains intersection traffic parameters and intersection information for multiple intersections within a target area, thereby acquiring the overall traffic situation and intersection attributes of each intersection within the target area. Based on the intersection traffic parameters, intersection information, vehicle driving parameters associated with each intersection, and target constraints, the target traffic speed for each intersection is determined, thus achieving full utilization of various types of data within the target area. Based on the target traffic speed and the vehicle traffic parameters associated with each intersection, the vehicles associated with each intersection are controlled to pass through the corresponding intersection, thereby achieving overall traffic control of the target area and improving the efficiency of vehicle traffic within the target area.

[0146] Figure 6 This is a schematic diagram of the structure of a vehicle control device provided in an embodiment of this application. See also... Figure 6 The device includes: an information acquisition module 601, a target passage speed determination module 602, and a control module 603.

[0147] The information acquisition module 601 is used to acquire the intersection traffic parameters and intersection information of multiple intersections within the target area. The intersection traffic parameters are used to indicate the traffic situation of the intersection.

[0148] The target traffic speed determination module 602 is used to determine the target traffic speed of each intersection based on the intersection traffic parameters of the multiple intersections, the intersection information of the multiple intersections, the vehicle driving parameters of the vehicles associated with each intersection, and the target constraint conditions. The target constraint conditions are used to constrain the vehicle driving parameters of the vehicles associated with each intersection, and the vehicle driving parameters are used to represent the driving state of the vehicles.

[0149] The control module 603 is used to control the vehicles associated with each intersection to pass through the corresponding intersection based on the target traffic speed of each intersection and the vehicle driving parameters of the vehicles associated with each intersection.

[0150] In one possible implementation, the intersection traffic parameters include the total travel time of the intersection, the average travel speed of the intersection, and the average distance between the vehicles associated with the intersection and the intersection. The information acquisition module 601 is used to acquire, for any one of the plurality of intersections, the vehicle driving parameters of the vehicles associated with the intersection and the intersection information; and to determine the total travel time of the intersection, the average travel speed of the intersection, and the average distance between the vehicles associated with the intersection and the intersection based on the vehicle driving parameters of the vehicles associated with the intersection.

[0151] In one possible implementation, the vehicle driving parameters include vehicle speed, distance to the intersection, and time taken to pass through the intersection. The information acquisition module 601 is used to accumulate the time taken by vehicles associated with the intersection to pass through the intersection to obtain the total travel time of the intersection; to determine the average speed of vehicles associated with the intersection as the average travel speed of the intersection; and to determine the average distance between vehicles associated with the intersection and the intersection as the average distance between vehicles associated with the intersection and the intersection.

[0152] In one possible implementation, the intersection information includes the intersection location and the intersection speed limit. The target traffic speed determination module 602 is used to construct an intersection map network for the target area based on the intersection traffic parameters, intersection speed limits, and intersection locations of the multiple intersections. The intersection map network includes intersection nodes corresponding to each intersection. Based on the intersection map network of the target area, the vehicle driving parameters of the vehicles associated with each intersection, and the target constraints, the target traffic speed of each intersection is determined.

[0153] In one possible implementation, the target traffic speed determination module 602 is used to create multiple intersection nodes, each corresponding to a multiple intersection; determine the node characteristics of each intersection node as the intersection traffic parameters and intersection speed limit of the corresponding intersection; determine the adjacency relationship and distance between every two intersections based on the intersection locations of the multiple intersections; and create connections between the multiple intersection nodes based on the adjacency relationship and distance between every two intersections to obtain the intersection graph network.

[0154] In one possible implementation, the vehicle driving parameters include vehicle speed and distance to the corresponding intersection. The target traffic speed determination module 602 is used to update the intersection graph network with multiple candidate accelerations to obtain multiple prediction graph networks. The candidate accelerations are the accelerations of vehicles associated with the corresponding intersections. The multiple prediction graph networks are then subjected to graph convolution to obtain multiple candidate overall travel times for the target area. Based on the multiple candidate overall travel times, the multiple candidate accelerations, the vehicle driving parameters of vehicles associated with each intersection, and the target constraints, the target traffic speed for each intersection is determined.

[0155] In one possible implementation, the target traffic speed determination module 602 is used to determine the predicted node features of the multiple intersection nodes based on the candidate acceleration and the node features of the multiple intersection nodes in the intersection graph network for any candidate acceleration among the multiple candidate accelerations; and update the node features of each intersection node using the predicted node features of the multiple intersection nodes to obtain the prediction graph network corresponding to the candidate acceleration.

[0156] In one possible implementation, the target traffic speed determination module 602 is configured to determine a first acceleration from among the multiple candidate overall traffic durations based on the multiple candidate overall traffic durations, wherein the candidate overall traffic duration corresponding to the first acceleration is the shortest among the multiple candidate overall traffic durations; determine a first predicted vehicle driving parameter for each vehicle associated with each intersection based on the first acceleration and the vehicle driving parameters of each vehicle associated with each intersection; and determine the vehicle speed in the first predicted vehicle driving parameter as the target traffic speed if the first predicted vehicle driving parameter of each vehicle associated with each intersection meets the target constraint condition.

[0157] In one possible implementation, the target traffic speed determination module 602 is further configured to: determine a second acceleration from the plurality of candidate accelerations if the first predicted vehicle driving parameters of the vehicles associated with any of the plurality of intersections do not meet the target constraint conditions, wherein the candidate overall travel time corresponding to the second acceleration is the second shortest among the plurality of candidate overall travel times; determine a second predicted vehicle driving parameter for each vehicle associated with each intersection based on the second acceleration and the vehicle driving parameters of the vehicles associated with each intersection; and determine the vehicle speed in the second predicted vehicle driving parameter as the target traffic speed if the second predicted vehicle driving parameters of the vehicles associated with each intersection meet the target constraint conditions.

[0158] In one possible implementation, the device further includes:

[0159] The condition discrimination module is used to determine the distance between vehicles associated with each intersection and the estimated collision duration based on the first predicted vehicle driving parameters of the vehicles associated with each intersection; and to determine whether the vehicle speed, the distance between vehicles associated with each intersection and the estimated collision duration in the first predicted vehicle driving parameters meet the target constraint conditions.

[0160] The target traffic speed determination module 602 is further configured to determine the vehicle speed in the first predicted vehicle driving parameters as the target traffic speed when the vehicle speed in the first predicted vehicle driving parameters, the distance between vehicles associated with each intersection, and the expected collision duration meet the target constraint conditions.

[0161] In one possible implementation, the vehicle speed, the distance between vehicles associated with each intersection, and the estimated collision duration in the first predicted vehicle driving parameters meeting the target constraint means that:

[0162] The first predicted vehicle speed is less than or equal to the speed limit at the corresponding intersection.

[0163] The distance between vehicles associated with each intersection is greater than or equal to a preset distance;

[0164] The estimated collision duration between vehicles associated with each intersection is greater than or equal to the preset collision duration.

[0165] In one possible implementation, the vehicle driving parameters include the distance to the corresponding intersection. The control module 603 is used to determine the vehicle passage order of the vehicles associated with each intersection at the corresponding intersection based on the distance between the vehicles associated with each intersection and the corresponding intersection; and to send the target passage speed of each intersection to the target vehicles corresponding to each intersection so that the vehicles associated with each intersection pass through the corresponding intersection, with the target vehicles having the first passage order.

[0166] In one possible implementation, the control module 603 is used to arrange the vehicles associated with any of the plurality of intersections in ascending order of distance from the intersection, thereby obtaining the vehicle passage order of the vehicles associated with the intersection at the intersection.

[0167] In one possible implementation, the vehicles associated with each intersection include vehicles that have already entered and those that will enter each intersection.

[0168] It should be noted that the vehicle control device provided in the above embodiments is only illustrated by the division of the above functional modules when controlling the state of the vehicle. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device can be divided into different functional modules to complete all or part of the functions described above. In addition, the vehicle control device and the vehicle control method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be found in the method embodiments, which will not be repeated here.

[0169] The technical solution provided in this application obtains intersection traffic parameters and intersection information for multiple intersections within a target area, thereby acquiring the overall traffic situation and intersection attributes of each intersection within the target area. Based on the intersection traffic parameters, intersection information, vehicle driving parameters associated with each intersection, and target constraints, the target traffic speed for each intersection is determined, thus achieving full utilization of various types of data within the target area. Based on the target traffic speed and the vehicle traffic parameters associated with each intersection, the vehicles associated with each intersection are controlled to pass through the corresponding intersection, thereby achieving overall traffic control of the target area and improving the efficiency of vehicle traffic within the target area.

[0170] This application also provides an electronic device. Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0171] Typically, an electronic device 700 includes one or more processors 701 and one or more memories 702.

[0172] Processor 701 may include one or more processing cores, such as a quad-core processor, a seven-core processor, etc. Processor 701 may be implemented using at least one hardware form selected from DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). Processor 701 may also include a main processor and a coprocessor. The main processor, also known as a CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, processor 701 may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, processor 701 may also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.

[0173] The memory 702 may include one or more computer-readable storage media, which may be non-transitory. The memory 702 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In some embodiments, the non-transitory computer-readable storage media in the memory 702 are used to store at least one computer program, which is executed by the processor 701 to implement the electronic device control method provided in the method embodiments of this application.

[0174] Those skilled in the art will understand that Figure 7 The structure shown does not constitute a limitation on the electronic device 700, and may include more or fewer components than shown, or combine certain components, or use different component arrangements.

[0175] In addition, the device provided in the embodiments of this application may specifically be a chip, component or module. The chip may include a connected processor and a memory. The memory is used to store instructions. When the processor calls and executes the instructions, the chip can execute a vehicle control method provided in the above embodiments.

[0176] This embodiment also provides a computer-readable storage medium storing computer program code. When the computer program code is run on a computer, the computer executes the above-described related method steps to implement a vehicle control method provided in the above embodiment.

[0177] This embodiment also provides a computer program product that, when run on a computer, causes the computer to perform the aforementioned steps to implement a vehicle control method provided in the above embodiment.

[0178] In this embodiment, the device, computer-readable storage medium, computer program product, or chip are all used to execute the corresponding methods provided above. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects in the corresponding methods provided above, and will not be repeated here.

[0179] Through the above description of the embodiments, those skilled in the art will understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0180] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0181] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A vehicle control method, characterized in that, The method includes: Obtain intersection traffic parameters and intersection information for multiple intersections within the target area. The intersection traffic parameters are used to indicate the traffic conditions at the intersections. Based on the intersection traffic parameters of the multiple intersections, the intersection information of the multiple intersections, the vehicle driving parameters of the vehicles associated with each intersection, and the target constraints, the target traffic speed of each intersection is determined. The target constraints are used to constrain the vehicle driving parameters of the vehicles associated with each intersection, and the vehicle driving parameters are used to represent the driving state of the vehicles. Based on the target traffic speed at each intersection and the vehicle driving parameters of the vehicles associated with each intersection, control the vehicles associated with each intersection to pass through the corresponding intersection. The intersection information includes the intersection location and speed limit; the vehicle driving parameters include vehicle speed and distance to the corresponding intersection; and determining the target traffic speed for each intersection based on the intersection traffic parameters, the intersection information, the vehicle driving parameters associated with each intersection, and target constraints includes: Based on the intersection traffic parameters, intersection speed limits, and intersection locations of the multiple intersections, an intersection map network for the target area is constructed, and the intersection map network includes intersection nodes corresponding to each intersection. The intersection graph network is updated using multiple candidate accelerations to obtain multiple prediction graph networks, where the candidate accelerations are the accelerations of vehicles associated with the corresponding intersections; Graph convolution is performed on the multiple prediction graph networks to obtain multiple candidate overall passage times for the target region; Based on the multiple candidate overall travel times, the multiple candidate accelerations, the vehicle driving parameters of the vehicles associated with each intersection, and the target constraints, the target travel speed of each intersection is determined.

2. The method according to claim 1, characterized in that, The intersection traffic parameters include the total travel time at the intersection, the average travel speed at the intersection, and the average distance between the vehicles associated with the intersection and the intersection. Obtaining the intersection traffic parameters and intersection information for multiple intersections within the target area includes: For any one of the plurality of intersections, obtain the vehicle driving parameters of the vehicles associated with the intersection and the intersection information of the intersection; Based on the vehicle driving parameters of the vehicles associated with the intersection, the total travel time of the intersection, the average travel speed of the intersection, and the average distance between the vehicles associated with the intersection and the intersection are determined.

3. The method according to claim 1, characterized in that, The intersection traffic parameters include the total travel time at the intersection, the average travel speed at the intersection, and the average distance between the vehicles associated with the intersection and the intersection. Constructing the intersection map network of the target area based on the intersection traffic parameters, the speed limits at the intersections, and the locations of the intersections includes: Create multiple intersection nodes, each corresponding one-to-one with a multiple intersection; The node characteristics of each intersection node are determined as the intersection traffic parameters and intersection speed limits of the corresponding intersection. Based on the intersection locations of the multiple intersections, determine the adjacency relationship and distance between every two intersections. Based on the adjacency relationship and distance between each pair of intersections, a connection is created between the multiple intersection nodes to obtain the intersection graph network.

4. The method according to claim 1, characterized in that, The step of updating the intersection graph network using multiple candidate accelerations to obtain multiple prediction graph networks includes: For any candidate acceleration among the plurality of candidate accelerations, the predicted node features of the plurality of intersection nodes are determined based on the candidate acceleration and the node features of the plurality of intersection nodes in the intersection graph network. The node features of each intersection node are updated using the predicted node features of the multiple intersection nodes to obtain the prediction graph network corresponding to the candidate acceleration.

5. The method according to claim 1, characterized in that, The determination of the target traffic speed for each intersection based on the multiple candidate overall travel times, the multiple candidate accelerations, vehicle driving parameters of vehicles associated with each intersection, and target constraints includes: Based on the multiple candidate overall passage times, a first acceleration is determined from the multiple candidate accelerations, and the candidate overall passage time corresponding to the first acceleration is the shortest among the multiple candidate overall passage times; Based on the first acceleration and the vehicle driving parameters of the vehicles associated with each intersection, the first predicted vehicle driving parameters of the vehicles associated with each intersection are determined. If the first predicted vehicle driving parameters of the vehicles associated with each of the intersections meet the target constraint conditions, the vehicle speed in the first predicted vehicle driving parameters is determined as the target traffic speed.

6. The method according to claim 5, characterized in that, After determining the first predicted vehicle driving parameters of the vehicles associated with each intersection based on the first acceleration and the vehicle driving parameters of the vehicles associated with each intersection, the method further includes: If the first predicted vehicle driving parameters of the vehicle associated with any of the plurality of intersections do not meet the target constraint conditions, a second acceleration is determined from the plurality of candidate accelerations, and the candidate overall travel time corresponding to the second acceleration is the second shortest among the plurality of candidate overall travel times; Based on the second acceleration and the vehicle driving parameters of the vehicles associated with each of the intersections, the second predicted vehicle driving parameters of the vehicles associated with each of the intersections are determined. If the second predicted vehicle driving parameters of the vehicles associated with each of the intersections meet the target constraint conditions, the vehicle speed in the second predicted vehicle driving parameters is determined as the target traffic speed.

7. The method according to claim 5, characterized in that, Before determining the vehicle speed in the first predicted vehicle driving parameters as the target traffic speed when the first predicted vehicle driving parameters of the vehicles associated with each of the intersections meet the target constraint conditions, the method further includes: Based on the first predicted vehicle driving parameters of the vehicles associated with each of the intersections, the distance between the vehicles associated with each of the intersections and the estimated collision duration are determined; Determine whether the vehicle speed, the distance between vehicles associated with each intersection, and the estimated collision duration in the first predicted vehicle driving parameters meet the target constraints. The step of determining the vehicle speed in the first predicted vehicle driving parameters as the target traffic speed when the first predicted vehicle driving parameters of the vehicles associated with each of the intersections meet the target constraint conditions includes: If the vehicle speed in the first predicted vehicle driving parameters, the distance between vehicles associated with each intersection, and the expected collision duration meet the target constraint conditions, the vehicle speed in the first predicted vehicle driving parameters shall be determined as the target traffic speed.

8. An electronic device, characterized in that, include: Memory, used to store executable program code; A processor is configured to call and run the executable program code from the memory, causing the vehicle to perform the vehicle control method as described in any one of claims 1 to 7.

Images