Vehicle control method and device, computer equipment, readable storage medium and program product

Abstract

The invention relates to a vehicle control method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises: obtaining decision information of one or more levels, the decision information at least comprising first decision information of at least one level issued by a server or the decision information comprising the first decision information of at least one level issued by the server and second decision information generated by a vehicle terminal, wherein the first decision information is generated based on vehicle control data corresponding to a server, roadside equipment and a vehicle terminal, and the second decision information is generated based on the vehicle control data corresponding to the vehicle terminal; determining target decision information based on the priority of the acquired decision information of each level; and controlling the operation of the vehicle based on the target decision information. By adopting the method, the decision-making efficiency and accuracy can be improved.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to a vehicle control method, apparatus, computer equipment, computer-readable storage medium, and computer program product. Background Art

[0002] With the development of autonomous driving technology, vehicle-to-everything (V2X), big data and cloud computing, intelligent connected transportation systems have become an important direction for future transportation. Traditional intelligent transportation technologies mostly rely on single-vehicle intelligence, that is, vehicles rely on their own sensors (such as cameras, radars, lidars, etc.) to perceive the environment and make decisions. Although this method has achieved autonomous driving to a certain extent, it has limitations, especially when facing complex and changing traffic environments, single-vehicle intelligence is difficult to respond efficiently and safely.

[0003] In order to solve the above problems, vehicle-road-cloud integration has proposed a new intelligent transportation solution. Through the collaborative operation of vehicle-road-cloud and combined with vehicle networking technology, it organically combines vehicles, road infrastructure (such as roadside units RSU), and cloud platforms to build a system of information sharing and real-time collaboration.

[0004] However, the current vehicle-road-cloud system needs to process and integrate massive amounts of data from vehicles, road infrastructure, and the cloud in real time, which places extremely high demands on the stability of the decision-making system. Especially in the face of emergencies, how to make quick decisions in complex road conditions is a difficult problem. Summary of the invention

[0005] Based on this, it is necessary to provide a vehicle control method, device, computer equipment, computer-readable storage medium and computer program product that can improve decision-making efficiency in response to the above technical problems.

[0006] In a first aspect, the present application provides a vehicle control method, applied to a vehicle terminal, the method comprising:

[0007] Obtaining one or more levels of decision information, the decision information at least including first decision information of at least one level sent by a server, or the decision information including first decision information of at least one level sent by a server and second decision information generated by the vehicle terminal, wherein the first decision information is generated based on the server, the roadside equipment and the vehicle control data corresponding to the vehicle terminal, and the second decision information is generated based on the vehicle control data corresponding to the vehicle terminal;

[0008] Determine target decision information based on the priorities of the obtained decision information at each level;

[0009] The vehicle operation is controlled based on the target decision information.

[0010] In one embodiment, the second decision information is generated in a manner including:

[0011] Obtain information about events that affect vehicle operation;

[0012] When the place where the event corresponding to the event information occurs is on the same road as the vehicle and the place where the event occurs is located in front of the vehicle, second decision information is generated based on the event and at least one of the road section corresponding to the vehicle, the number of lanes corresponding to the road section, the lane position and the number of vehicles on the lane.

[0013] In one embodiment, generating the second decision information based on the event and at least one of the road section corresponding to the vehicle, the number of lanes corresponding to the road section, the lane position, and the number of vehicles on the lane includes:

[0014] In any of the following cases, the second decision information is generated based on the number of vehicles in the adjacent lane of the vehicle:

[0015] The road section corresponding to the place where the event occurs is the same as the road section corresponding to the vehicle, the number of lanes of the road section corresponding to the place where the event occurs is the same as the number of lanes of the road section corresponding to the vehicle, and the lane position corresponding to the place where the event occurs is the same as the lane position corresponding to the vehicle;

[0016] The road section corresponding to the place where the event occurs and the road section corresponding to the vehicle are adjacent road sections, the number of lanes of the road section corresponding to the place where the event occurs is the same as the number of lanes of the road section corresponding to the vehicle, and the lane position corresponding to the place where the event occurs is the same as the lane position corresponding to the vehicle;

[0017] The road section corresponding to the place where the event occurred and the road section corresponding to the vehicle are adjacent sections, the number of lanes of the road section corresponding to the place where the event occurred is different from the number of lanes of the road section corresponding to the vehicle, and the lane position corresponding to the place where the event occurred is the same as the lane position corresponding to the vehicle.

[0018] In one embodiment, the first decision information includes global dynamic path planning decision information and intersection decision information; the priority of the second decision information is higher than the priority of the intersection decision information, and the priority of the intersection decision information is higher than the global dynamic path planning decision information;

[0019] The determining the target decision information based on the priority of the first decision information and the priority of the second decision information at least one level includes:

[0020] In the case where the second decision information exists, taking the second decision information as the target decision information;

[0021] In the case where the second decision information does not exist and the intersection decision information exists, using the intersection decision information as the target decision information;

[0022] In the absence of the second decision information and the intersection decision information, the global dynamic path planning decision information is used as the target decision information.

[0023] In one embodiment, the first decision information includes global dynamic path planning decision information; the global dynamic path planning decision information is generated by the server based on first vehicle control data, the first vehicle control data includes static data and intention data in dynamic data, or the first vehicle control data includes historical data, at least one of road condition data in quasi-static data and intention data in the static data and dynamic data, wherein the historical data is static data, quasi-static data and dynamic data obtained before the current time; the static data, quasi-static data and dynamic data are classified based on the real-time nature of the vehicle control data.

[0024] In one of the embodiments, when the intention data indicates that the path planning intention is the shortest path, global dynamic path planning decision information is obtained based on the road condition data and the navigation map in the static data;

[0025] When the intention data represents the path planning intention as the shortest time, the traffic flow speed observed by vehicles on the historical path and the number of vehicles on the historical path are determined based on the historical data; based on the traffic flow speed observed by vehicles on the historical path, the number of vehicles on the historical path, the road condition data and the navigation map in the static data, global dynamic path planning decision information is obtained.

[0026] In one of the embodiments, the intersection decision information is generated based on the vehicle request and traffic signal data in the dynamic data, the navigation map in the static data, and the vehicle travel speed in the corresponding scenario in the historical data.

[0027] In a second aspect, the present application further provides a vehicle control method, applied to a server, the method comprising:

[0028] Obtain vehicle control data corresponding to the server, roadside equipment and vehicle terminal;

[0029] Generate at least one level of first decision information based on the server, the roadside equipment and the vehicle control data corresponding to the vehicle terminal;

[0030] The first decision information is sent to a vehicle terminal, and the vehicle terminal is used to obtain decision information of one or more levels, and determine target decision information based on the priority of the acquired decision information of each level, and control the vehicle operation based on the target decision information, wherein the decision information includes first decision information of at least one level issued by a server or the decision information includes first decision information of at least one level issued by a server and second decision information generated by the vehicle terminal, and the second decision information is generated based on vehicle control data corresponding to the vehicle terminal.

[0031] In one embodiment, after obtaining the vehicle control data corresponding to the server, the roadside equipment and the vehicle terminal, the method further includes:

[0032] Based on the real-time nature of the vehicle control data, the vehicle control data is grouped to obtain static data, quasi-static data and dynamic data;

[0033] The generating of at least one level of first decision information based on the vehicle control data corresponding to the server, the roadside equipment and the vehicle terminal includes:

[0034] At least one level of first decision information is generated based on the static data, the quasi-static data and the dynamic data.

[0035] In one embodiment, the first decision information includes global dynamic path planning decision information; the generating of at least one level of first decision information based on the static data, quasi-static data and dynamic data includes:

[0036] Global dynamic path planning decision information is generated based on first vehicle control data, wherein the first vehicle control data includes the static data and intention data in the dynamic data, or the first vehicle control data includes historical data, at least one of the road condition data in the quasi-static data and the intention data in the static data and the dynamic data, wherein the historical data is the static data, quasi-static data and dynamic data obtained before the current time.

[0037] In one embodiment, generating global dynamic path planning decision information based on the first vehicle control data includes:

[0038] When the intention data indicates that the path planning intention is the shortest path, obtaining global dynamic path planning decision information based on the road condition data and the navigation map in the static data;

[0039] When the intention data represents the path planning intention as the shortest time, the traffic flow speed observed by vehicles on the historical path and the number of vehicles on the historical path are determined based on the historical data; based on the traffic flow speed observed by vehicles on the historical path, the number of vehicles on the historical path, the road condition data and the navigation map in the static data, global dynamic path planning decision information is obtained.

[0040] In one embodiment, the first decision information includes intersection decision information; the generating of at least one level of first decision information based on the static data, quasi-static data and dynamic data includes:

[0041] Based on the vehicle request and traffic signal data in the dynamic data, the navigation map in the static data, and the vehicle travel speed in the corresponding scene in the historical data, the intersection decision information is obtained.

[0042] In one embodiment, the second decision information is generated based on the event and at least one of the road section corresponding to the vehicle, the number of lanes corresponding to the road section, the lane position, and the number of vehicles on the lane, when the event occurs on the same road as the vehicle and the event occurs in front of the vehicle, wherein the event is obtained based on the event information affecting the operation of the vehicle obtained by the vehicle terminal.

[0043] In one of the embodiments, in any of the following cases, the vehicle terminal generates second decision information based on the number of vehicles in the adjacent lanes of the vehicle:

[0044] The road section corresponding to the place where the event occurs is the same as the road section corresponding to the vehicle, the number of lanes of the road section corresponding to the place where the event occurs is the same as the number of lanes of the road section corresponding to the vehicle, and the lane position corresponding to the place where the event occurs is the same as the lane position corresponding to the vehicle;

[0045] The road section corresponding to the place where the event occurs and the road section corresponding to the vehicle are adjacent road sections, the number of lanes of the road section corresponding to the place where the event occurs is the same as the number of lanes of the road section corresponding to the vehicle, and the lane position corresponding to the place where the event occurs is the same as the lane position corresponding to the vehicle;

[0046] The road section corresponding to the place where the event occurred and the road section corresponding to the vehicle are adjacent sections, the number of lanes of the road section corresponding to the place where the event occurred is different from the number of lanes of the road section corresponding to the vehicle, and the lane position corresponding to the place where the event occurred is the same as the lane position corresponding to the vehicle.

[0047] In one embodiment, the first decision information includes global dynamic path planning decision information and intersection decision information; the method for generating the target decision information includes: when the second decision information exists, the second decision information is used as the target decision information; when the second decision information does not exist and the intersection decision information exists, the intersection decision information is used as the target decision information; when the second decision information and the intersection decision information do not exist, the global dynamic path planning decision information is used as the target decision information.

[0048] In one embodiment, the first decision information of the at least one level is generated by a model based on the vehicle control data corresponding to the server, the roadside equipment and the vehicle terminal; the method further includes:

[0049] The model is modified based on the historical data.

[0050] In a third aspect, the present application further provides a vehicle control device, applied to a vehicle terminal, the device comprising:

[0051] A decision information acquisition module, used to acquire one or more levels of decision information, wherein the decision information at least includes first decision information of at least one level issued by a server or the decision information includes first decision information of at least one level issued by a server and second decision information generated by the vehicle terminal, wherein the first decision information is generated based on the server, the roadside equipment and the vehicle control data corresponding to the vehicle terminal, and the second decision information is generated based on the vehicle control data corresponding to the vehicle terminal;

[0052] A target decision information determination module, used to determine the target decision information based on the priority of the acquired decision information at each level;

[0053] A control module is used to control the operation of the vehicle based on the target decision information.

[0054] In a fourth aspect, the present application further provides a vehicle control device, applied to a server, the device comprising:

[0055] A control data acquisition module is used to acquire vehicle control data corresponding to the server, roadside equipment and vehicle terminal;

[0056] A first decision information generating module, configured to generate at least one level of first decision information based on the vehicle control data corresponding to the server, the roadside equipment and the vehicle terminal;

[0057] A sending module is used to send the first decision information to a vehicle terminal, and the vehicle terminal is used to obtain decision information of one or more levels, and determine target decision information based on the priority of the acquired decision information of each level, and control the vehicle operation based on the target decision information, wherein the decision information includes first decision information of at least one level issued by a server or the decision information includes first decision information of at least one level issued by a server and second decision information generated by the vehicle terminal, and the second decision information is generated based on vehicle control data corresponding to the vehicle terminal.

[0058] In a fifth aspect, the present application further provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0059] In a sixth aspect, the present application also provides a computer-readable storage medium having a computer program stored thereon, and the computer program implements the steps of the above method when executed by a processor.

[0060] In a seventh aspect, the present application also provides a computer program product, including a computer program, which implements the steps of the above method when executed by a processor.

[0061] The above-mentioned vehicle control method, device, computer equipment, computer-readable storage medium and computer program product obtain one or more levels of decision information, wherein the decision information at least includes at least one level of first decision information issued by the server or the decision information includes at least one level of first decision information issued by the server and second decision information generated by the vehicle terminal, wherein the first decision information is generated based on the server, the roadside equipment and the vehicle control data corresponding to the vehicle terminal, and the second decision information is generated based on the vehicle control data corresponding to the vehicle terminal, and then the target decision information is determined based on the priority of the decision information; the vehicle operation is controlled based on the target decision information, different decision information is generated at different terminals, and decisions are made in layers, which can improve the efficiency of generating decision information, and determining the target decision information based on the priority of different decision information also improves the accuracy of the decision. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0063] FIG1 is an application environment diagram of a vehicle control method according to an embodiment;

[0064] FIG2 is a schematic flow chart of a vehicle control method in one embodiment;

[0065] FIG3 is a schematic diagram of a second decision information generating step in one embodiment;

[0066] FIG4 is a flow chart of a second decision information generating step in one embodiment;

[0067] FIG5 is a schematic flow chart of a vehicle control method in another embodiment;

[0068] FIG6 is a schematic diagram of a step of generating global dynamic path planning decision information in an optional embodiment;

[0069] FIG7 is a schematic diagram of a step of generating intersection decision information in an optional embodiment;

[0070] FIG8 is a flow chart of a vehicle control method in yet another embodiment;

[0071] FIG9 is a block diagram of a vehicle control device according to an embodiment;

[0072] FIG10 is a block diagram of a vehicle control device according to another embodiment;

[0073] FIG. 11 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0074] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0075] The vehicle control method provided in the embodiment of the present application can be applied in the application environment as shown in FIG1 . The server, roadside equipment and vehicle terminal are all used to collect vehicle control data. For example, the server is used to statically obtain high-precision map data. The roadside equipment is used to obtain traffic flow data, road condition data and traffic data. The vehicle terminal is used to obtain instant vehicle requests, that is, vehicle intention data.

[0076] The roadside equipment and the vehicle terminal both communicate with the server through the network to send the collected vehicle control data to the server, and the vehicle terminal can also receive the first decision information sent by the server.

[0077] Specifically, the vehicle terminal can obtain one or more levels of decision information, wherein the decision information at least includes the first decision information of at least one level issued by the server, or the decision information includes the first decision information of at least one level issued by the server and the second decision information generated by the vehicle terminal, wherein the first decision information is generated based on the server, the roadside equipment and the vehicle control data corresponding to the vehicle terminal, and the second decision information is generated based on the vehicle control data corresponding to the vehicle terminal. The vehicle terminal determines the target decision information based on the priority of the first decision information of at least one level and the priority of the second decision information; and controls the vehicle operation based on the target decision information. In this way, different decision information is generated at different terminals, and decisions are made in layers, which can improve the efficiency of generating decision information, and determining the target decision information based on the priority of different decision information also improves the accuracy of the decision.

[0078] The server can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services. The server can be based on multi-access edge computing. MEC (MEC, Multi-access Edge Computing) is a distributed computing architecture that moves computing power from the central cloud to the edge of the network (such as roadside units RSU, base stations, etc.). In vehicle-road collaboration, MEC can help vehicles obtain real-time computing services and data processing in a low-latency environment.

[0079] Among them, the road side unit (RSU) is a communication device deployed at the edge of the road, usually used to support vehicle-to-infrastructure (V2I) communication in the vehicle-to-everything (V2X) network.

[0080] The vehicle-to-everything (V2X) involved in this application is a communication technology used for intelligent transportation and autonomous driving, which enables vehicles to exchange real-time information with various entities in the surrounding environment, enhancing driving safety, efficiency and traffic management.

[0081] In an exemplary embodiment, as shown in FIG2 , a vehicle control method is provided, which is described by taking the method applied to the vehicle terminal in FIG1 as an example, and includes the following steps S202 to S206 . Among them:

[0082] S202: Obtain one or more levels of decision information, the decision information at least including first decision information of at least one level issued by the server, or the decision information includes first decision information of at least one level issued by the server and second decision information generated by the vehicle terminal, wherein the first decision information is generated based on the server, the roadside equipment and the vehicle control data corresponding to the vehicle terminal, and the second decision information is generated based on the vehicle control data corresponding to the vehicle terminal.

[0083] The decision information includes one or more levels. Optionally, the decision information includes at least one level of first decision information issued by the server. In other embodiments, the decision information includes at least one level of first decision information issued by the server and second decision information generated by the vehicle terminal. The first decision information is generated based on the vehicle control data corresponding to the server, the roadside equipment and the vehicle terminal, wherein the vehicle terminal feeds back the vehicle control data such as the driving status to the server and the roadside equipment in real time, and the roadside equipment feeds back the vehicle control data such as the road condition to the server in real time. The first decision information may include at least one level. In some optional embodiments, the first decision information includes two levels of global dynamic path planning decision information and intersection decision information, and the priority of the corresponding level of the global dynamic path planning decision information is lower than the priority of the corresponding level of the intersection decision information. The second decision information is generated by the vehicle terminal based on the vehicle control data corresponding to the vehicle terminal, and the priority of the second decision information is higher than the priority of each first decision information.

[0084] In one of the optional embodiments, the first decision information includes global dynamic path planning decision information; the global dynamic path planning decision information is generated by the server based on the first vehicle control data, the first vehicle control data includes static data and intention data in dynamic data, or the first vehicle control data includes historical data, at least one of road condition data in quasi-static data and intention data in static data and dynamic data, wherein the historical data is static data, quasi-static data and dynamic data obtained before the current time; the static data, quasi-static data and dynamic data are classified based on the real-time nature of the vehicle control data.

[0085] In one of the optional embodiments, when the intention data represents that the path planning intention is the shortest path, global dynamic path planning decision information is obtained based on the road condition data and the navigation map in the static data; when the intention data represents that the path planning intention is the shortest time, the traffic flow speed observed by vehicles on the historical path and the number of vehicles on the historical path are determined based on the historical data; global dynamic path planning decision information is obtained based on the traffic flow speed observed by vehicles on the historical path, the number of vehicles on the historical path, the road condition data and the navigation map in the static data.

[0086] In one optional embodiment, the intersection decision information is generated based on vehicle requests and traffic signal data in dynamic data, navigation maps in static data, and vehicle travel speeds in corresponding scenarios in historical data.

[0087] Among them, the limitations on the specific generation process of the above-mentioned global dynamic path planning decision information and intersection decision information can be found below.

[0088] After generating the first decision information, the server sends the first decision information to the vehicle terminal, and the vehicle terminal can obtain the decision information of each level to make an inner decision.

[0089] In the case where there are multiple connected vehicles, the server can generate first decision information for each connected vehicle respectively, and send the first decision information to the vehicle terminal of the corresponding connected vehicle.

[0090] S204: Determine target decision information based on the priorities of the acquired decision information at each level.

[0091] The priority of the decision information is preset, and each level corresponds to one decision information. In the case of high-priority decision information, the high-priority decision information is used first.

[0092] When making a decision, the vehicle terminal determines one or more pieces of decision information obtained, and then determines target decision information based on the priority of one or more levels of decision information.

[0093] For ease of understanding, in one of the optional embodiments, the first decision information includes global dynamic path planning decision information and intersection decision information, the priority of the second decision information is higher than the priority of the intersection decision information, and the priority of the intersection decision information is higher than the priority of the global dynamic path planning decision information. The second decision information is lane-level trajectory decision information.

[0094] Based on the priority of the first decision information and the priority of the second decision information of at least one level, the target decision information is determined, including: when the second decision information exists, the second decision information is used as the target decision information; when the second decision information does not exist and there is intersection decision information, the intersection decision information is used as the target decision information; when the second decision information and intersection decision information do not exist, the global dynamic path planning decision information is used as the target decision information.

[0095] S206: Control vehicle operation based on the target decision information.

[0096] After the target decision information is determined, the vehicle terminal controls the operation of the vehicle based on the target decision information. For example, the vehicle terminal performs corresponding operations, such as executing actual driving behavior, adjusting speed, and optimizing the path to ensure efficient and safe driving. Among them, executing actual driving behavior may include accelerating, decelerating, changing lanes, or continuing to maintain the existing driving trajectory, etc., and the actual driving behavior may be determined based on the second decision information. Adjusting the speed may include adjusting the speed before entering the intersection, and the speed before entering the intersection may be determined based on the intersection decision information; optimizing the path may include optimizing the overall planned path, and the overall planned path may be determined based on the global dynamic path planning decision information.

[0097] The above-mentioned vehicle control method obtains one or more levels of decision information, and the decision information at least includes first decision information of at least one level issued by the server, or the decision information includes first decision information of at least one level issued by the server and second decision information generated by the vehicle terminal, wherein the first decision information is generated based on the server, the roadside equipment and the vehicle control data corresponding to the vehicle terminal, and the second decision information is generated based on the vehicle control data corresponding to the vehicle terminal, and then the target decision information is determined based on the priority of the first decision information of at least one level and the priority of the second decision information; the vehicle operation is controlled based on the target decision information, different decision information is generated at different terminals, and decisions are made in layers, which can improve the efficiency of generating decision information, and determining the target decision information based on the priority of different decision information also improves the accuracy of the decision.

[0098] In one of the optional embodiments, the method for generating the second decision information includes: obtaining event information that affects the operation of the vehicle; when the event corresponding to the event information occurs on the same road as the vehicle and the event occurs in front of the vehicle, generating the second decision information based on the event and at least one of the road section corresponding to the vehicle, the number of lanes corresponding to the road section, the lane position, and the number of vehicles on the lane.

[0099] Specifically, in conjunction with FIG. 3, FIG. 3 is a schematic diagram of the second decision information generation step in an embodiment, in which the event information affecting the operation of the vehicle includes environmental vehicles and road blocking events. The environmental vehicles include the observation environmental vehicles observed by the vehicle terminal and the environmental vehicles determined by the roadside equipment and the server. The road blocking event is generally a road blocking event determined by the roadside equipment and the server.

[0100] When the place where the event corresponding to the event information occurs and the vehicle is on the same road, and the place where the event occurs is located in front of the vehicle, it is necessary to generate corresponding second decision information. If the place where the event corresponding to the relevant information occurs and the vehicle is not on the same road, or the place where the event occurs is located behind the vehicle, it will not affect the operation of the vehicle, so it will not be processed, that is, there is no need to generate second decision information.

[0101] In some optional embodiments, the vehicle terminal first obtains the function information of the current lane and the planned path provided by the navigation system before generating the second decision information. The function information of the current lane may include whether the lane can be changed and the lane width. The generated second decision information is used to prompt the vehicle terminal to perform the required operation, such as changing lanes to the left, changing lanes to the right, or keeping the original lane.

[0102] In one optional embodiment, second decision information is generated based on the event and at least one of the road section corresponding to the vehicle, the number of lanes corresponding to the road section, the lane position and the number of vehicles on the lane, including: in any of the following cases, second decision information is generated based on the number of vehicles on the adjacent lanes of the vehicle: the road section corresponding to the place where the event occurred is the same as the road section corresponding to the vehicle, the number of lanes of the road section corresponding to the place where the event occurred is the same as the number of lanes of the road section corresponding to the vehicle, and the lane position corresponding to the place where the event occurred is the same as the lane position corresponding to the vehicle; the road section corresponding to the place where the event occurred is adjacent to the road section corresponding to the vehicle, the number of lanes of the road section corresponding to the place where the event occurred is the same as the number of lanes of the road section corresponding to the vehicle, and the lane position corresponding to the place where the event occurred is the same as the lane position corresponding to the vehicle; the road section corresponding to the place where the event occurred is adjacent to the road section corresponding to the vehicle, the number of lanes of the road section corresponding to the place where the event occurred is different from the number of lanes of the road section corresponding to the vehicle, and the lane position corresponding to the place where the event occurred is the same as the lane position corresponding to the vehicle.

[0103] Before explaining the second decision information generation step in detail, several definitions introduced are explained first, where a road is, for example, a road with a name, a road section is a different section of the road, each road section includes multiple lanes, each lane corresponds to a lane position, and the lane position can be represented by a lane number.

[0104] The conditions for generating the second decision information may include the event corresponding to the event information, where the event is in front, that is, if the vehicle detects an event (such as an accident, congestion) ahead, the route will be adjusted according to the lane conditions of different road sections. The environment vehicle is in front, that is, if there is an environment vehicle blocking the front, the vehicle terminal will choose whether to change lanes according to the conditions of the target lane, or choose to pass or keep the lane according to the road width.

[0105] Optionally, the conditions for generating the second decision information may also include the judgment of the road section. Among them, the lane cannot be changed, that is, if it is in a single lane and cannot change lanes, the vehicle will slow down or maintain the distance according to the current speed and the event ahead. No processing means that when the lane cannot be changed and there is no feasible operation, the system maintains the current decision state.

[0106] Optionally, the condition for generating the second decision information may also include lane determination. In the same road section, if the number of lanes is the same, that is, if the current lane and the target lane are the same, the vehicle terminal makes dynamic adjustments according to events or obstacles ahead, such as slowing down or changing lanes in advance. If the number of lanes is different, that is, if the number of lanes of the target lane is different, it is necessary to further determine the specific lane change strategy.

[0107] Optionally, the condition for generating the second decision information may also include the judgment of the lane number. In the case of multiple lanes, the vehicle terminal needs to select the best lane according to the current lane number and the feasibility of the left or right lane.

[0108] Combined with Figure 4, Figure 4 is a flowchart of the second decision information generation step in an embodiment. In this embodiment, it is first determined whether the place where the event corresponding to the relevant information occurs and the vehicle are on the same road. If they are not on the same road, no processing is performed, that is, no new second decision information is generated.

[0109] If the place where the event corresponding to the relevant information occurs is on the same road as the vehicle, it is necessary to determine whether the place where the event corresponding to the relevant information occurs is in front of the vehicle. If the place where the event corresponding to the relevant information occurs is not in front of the vehicle, it will not be processed, that is, no new second decision information will be generated.

[0110] If the event corresponding to the relevant information occurs in front of the vehicle, it is necessary to determine whether the event corresponding to the relevant information and the vehicle are in the same section of road. If they are in different sections of road, no processing will be done, that is, no new second decision information will be generated.

[0111] If the event corresponding to the relevant information occurs in front of the vehicle, and the event corresponding to the relevant information and the vehicle are on the same road section, the lane information is judged; if the road section is a single lane or the lane cannot be changed, it is not processed, that is, no new second decision information is generated.

[0112] If the location of the event corresponding to the relevant information is in front of the vehicle, and the location of the event corresponding to the relevant information is on the same road section as the vehicle, and the number of lanes of the road section corresponding to the location of the event is the same as the number of lanes of the road section corresponding to the vehicle, then the lane number is determined. If the lane numbers are different, no processing is performed, that is, no new second decision information is generated. If the lane numbers are the same, the second decision information is generated based on the number of vehicles on the relevant lanes of the vehicle.

[0113] If the event corresponding to the relevant information occurs in front of the vehicle, and the event corresponding to the relevant information is on an adjacent road section to the vehicle, and the road section is a single lane or a non-changeable lane, it will not be processed, that is, no new second decision information will be generated.

[0114] If the location of the event corresponding to the relevant information is in front of the vehicle, and the location of the event corresponding to the relevant information is in an adjacent section of the road to the vehicle, and the number of lanes of the section corresponding to the location of the event is the same as the number of lanes of the section corresponding to the vehicle, then the lane number is determined. If the lane numbers are different, no processing is performed, that is, no new second decision information is generated. If the lane numbers are the same, the second decision information is generated based on the number of vehicles on the relevant lanes of the vehicle.

[0115] If the location of the event corresponding to the relevant information is in front of the vehicle, and the location of the event corresponding to the relevant information is in an adjacent section of the road to the vehicle, and the number of lanes of the section corresponding to the location of the event is different from the number of lanes of the section corresponding to the vehicle, then the lane number is determined. If the lane numbers are different, no processing is performed, that is, no new second decision information is generated. If the lane numbers are the same, the second decision information is generated based on the number of vehicles on the relevant lanes of the vehicle.

[0116] The generating of the second decision information based on the number of vehicles on the lanes related to the vehicle may include selecting the best lane according to the current lane number and the feasibility of the left or right lanes. Specifically, if there are more lanes on the left, then changing lanes to the left is preferred. If there are more lanes on the right, then changing lanes to the right is preferred. If the number of lanes is different, further decision making is made according to the availability and number of the lanes.

[0117] The lane change mentioned above means that if the vehicle is in a single lane and cannot change lanes, the vehicle will slow down or maintain the distance according to the current speed and the events ahead. The no processing mentioned above means that when the lane cannot be changed and there is no feasible operation, the system maintains the current decision state.

[0118] In the above embodiment, the generation of the second decision information utilizes the vehicle observation results and the networked vehicle information to make a lane change decision beyond visual range, thereby ensuring accuracy. In addition, after the decision is executed, the vehicle terminal synchronizes the current state to the server to facilitate the next decision optimization.

[0119] In some optional embodiments, the vehicle terminal will feed back real-time data such as driving status and road conditions to the server and roadside equipment for the system to perform the next round of decision optimization.

[0120] In an exemplary embodiment, as shown in FIG5 , a vehicle control method is provided, which is described by taking the method applied to the server in FIG1 as an example, and includes the following steps 502 to 506. Among them:

[0121] S502: Obtain vehicle control data corresponding to the server, roadside equipment and vehicle terminal.

[0122] The roadside equipment and vehicle terminal can upload the vehicle control data collected by each of them to the server in real time, and the server will integrate the vehicle control data in the vehicle terminal, roadside equipment and server.

[0123] In one of the optional embodiments, after obtaining the vehicle control data corresponding to the server, roadside equipment and vehicle terminal, it also includes: based on the real-time nature of the vehicle control data, grouping the vehicle control data to obtain static data, quasi-static data and dynamic data.

[0124] Among them, static data (or macro data) includes high-precision map data; quasi-static data (or quasi-macro data) includes traffic flow data, road condition information data, and background vehicle intention data; dynamic data (or micro data) includes traffic signal data and instant vehicle requests.

[0125] In other optional embodiments, after the vehicle control data is grouped, the vehicle control data may be preprocessed, and the preprocessing may be performed based on the data grouping. The preprocessing of static data and quasi-static data includes: parsing high-precision map data (ground element information), establishing a navigation map (topological structure), and adding a traffic flow status and road condition status mapping table. The dynamic data preprocessing includes: updating the road signal light status and establishing a real-time signal light query table.

[0126] S504: Generate at least one level of first decision information based on the server, the roadside equipment and the vehicle control data corresponding to the vehicle terminal.

[0127] The server may generate at least one level of first decision information based on the server, the roadside equipment, and the vehicle control data corresponding to the vehicle terminal, for example, based on static data, quasi-static data, and dynamic data. Optionally, the server processes the current data and also fully processes the historical data as the decision information input. Both the historical data and the current data include the above-mentioned static data, quasi-static data, and dynamic data.

[0128] The first decision information may include at least one level. In some optional embodiments, the first decision information includes global dynamic path planning decision information and intersection decision information, and the priority of the global dynamic path planning decision information is lower than the priority of the intersection decision information.

[0129] It should be noted that the first decision information in the present application at least includes global dynamic path planning decision information. In the case of encountering an intersection, the first decision information also includes intersection decision information.

[0130] S506: Send the first decision information to the vehicle terminal, the vehicle terminal is used to obtain one or more levels of decision information, and determine the target decision information based on the priority of the acquired decision information at each level, and control the vehicle operation based on the target decision information, wherein the decision information includes the first decision information of at least one level issued by the server, or the decision information includes the first decision information of at least one level issued by the server and the second decision information generated by the vehicle terminal, and the second decision information is generated based on the vehicle control data corresponding to the vehicle terminal.

[0131] The server sends the first decision information to the vehicle terminal, and the vehicle terminal can make a decision based on the first decision information sent by the server.

[0132] The second decision information is generated based on the event and at least one of the road section corresponding to the vehicle, the number of lanes corresponding to the road section, the lane position, and the number of vehicles on the lane, when the event occurs on the same road as the vehicle and in front of the vehicle, and the event is obtained based on event information affecting the operation of the vehicle acquired by the vehicle terminal.

[0133] Optionally, in any of the following cases, the vehicle terminal generates second decision information based on the number of vehicles on the adjacent lanes of the vehicle: the road section corresponding to the place where the event occurred is the same as the road section corresponding to the vehicle, the number of lanes of the road section corresponding to the place where the event occurred is the same as the number of lanes of the road section corresponding to the vehicle, and the lane position corresponding to the place where the event occurred is the same as the lane position corresponding to the vehicle; the road section corresponding to the place where the event occurred is adjacent to the road section corresponding to the vehicle, the number of lanes of the road section corresponding to the place where the event occurred is the same as the number of lanes of the road section corresponding to the vehicle, and the lane position corresponding to the place where the event occurred is the same as the lane position corresponding to the vehicle; the road section corresponding to the place where the event occurred is adjacent to the road section corresponding to the vehicle, the number of lanes of the road section corresponding to the place where the event occurred is different from the number of lanes of the road section corresponding to the vehicle, and the lane position corresponding to the place where the event occurred is the same as the lane position corresponding to the vehicle.

[0134] The first decision information includes global dynamic path planning decision information and intersection decision information; the method of generating the target decision information includes: when the second decision information exists, the second decision information is used as the target decision information; when the second decision information does not exist and the intersection decision information exists, the intersection decision information is used as the target decision information; when the second decision information and the intersection decision information do not exist, the global dynamic path planning decision information is used as the target decision information.

[0135] The process by which the vehicle terminal determines the target decision information based on the acquired decision information can be found above and will not be repeated here.

[0136] In the above embodiment, the process of generating global dynamic path planning decision information, that is, when performing path control, uses static map information, quasi-static traffic flow information, and connected vehicle observation information to make comprehensive decisions; in the process of generating intersection decision information, the current dynamic traffic light data, vehicle position, and historical vehicle driving experience under the same state are simultaneously referred to to make comprehensive decisions; the second decision information generation process simultaneously uses vehicle observation results and connected vehicle information to make beyond-visual-range lane change decisions; the strategy execution process dynamically compares the decision results of the above three levels, and executes according to the priority of second decision information > intersection decision information > global dynamic path planning decision information; after the decision is executed, the connected vehicle synchronizes the current state to the cloud to optimize the decision; the above embodiment can be applied to scenarios such as autonomous driving, smart traffic management, and smart logistics, significantly improving traffic efficiency, driving safety, and overall driving experience.

[0137] In one of the optional embodiments, the first decision information includes global dynamic path planning decision information; generating at least one level of first decision information based on static data, quasi-static data and dynamic data, including: generating global dynamic path planning decision information based on first vehicle control data, the first vehicle control data including static data and intention data in dynamic data, or the first vehicle control data including historical data, at least one of road condition data in quasi-static data and intention data in static data and dynamic data, wherein the historical data is static data, quasi-static data and dynamic data obtained before the current time.

[0138] In conjunction with FIG. 6 , FIG. 6 is a schematic diagram of a step of generating global dynamic path planning decision information in an optional embodiment. The global dynamic path planning decision information is generated based on historical data and real-time macro data. When the server performs global dynamic path planning, the server performs path planning based on dynamic road conditions and reported intentions:

[0139] The goal of path planning is to select a reasonable path P={e1, e2, …, e n} to minimize the path travel cost:

[0140]

[0141] Among them, T is the current planning time, and w() is the path travel cost calculation method.

[0142] In one of the optional embodiments, global dynamic path planning decision information is generated based on the first vehicle control data, including: when the intention data represents that the path planning intention is the shortest path, based on the road condition data and the navigation map in the static data, the global dynamic path planning decision information is obtained; when the intention data represents that the path planning intention is the shortest time, based on the historical data, the traffic flow speed observed by the vehicle on the historical path and the number of vehicles on the historical path are determined; based on the traffic flow speed observed by the vehicle on the historical path, the number of vehicles on the historical path, the road condition data and the navigation map in the static data, the global dynamic path planning decision information is obtained.

[0143] In the case where the intention data is the shortest path, then:

[0144]

[0145] in, is a coefficient related to the road condition data, such as when a road blockage occurs is infinite, dis() calculates the Euclidean distance between two nodes, which is obtained based on the navigation map in the static data.

[0146] When the intention data is the shortest time, that is, the fastest passing intention, then:

[0147]

[0148] Among them, k1 and k2 are coefficients, dis() calculates the Euclidean distance between two nodes, which is obtained based on the navigation map in the static data, v is the traffic flow speed observed by the connected vehicle on the current path, count(P T ) calculates the number of connected vehicles on the current path, that is, it is considered that the more connected vehicles there are, the more reliable the observed speed is. random is a random number with a (0,1] distribution, that is, the introduction of a random term avoids simultaneously introducing different vehicles into the same path. In other embodiments, count(P T ) can also be obtained based on the number of connected vehicles on the historical path.

[0149] In the above embodiments, when performing path control, static map information, quasi-static traffic flow information, and connected vehicle observation information are used to make comprehensive decisions and improve accuracy.

[0150] In one of the optional embodiments, the first decision information includes intersection decision information; at least one level of first decision information is generated based on static data, quasi-static data and dynamic data, including: obtaining intersection decision information based on vehicle requests and traffic signal data in dynamic data, navigation maps in static data, and vehicle traffic speeds in corresponding scenarios in historical data.

[0151] Among them, the intersection decision information is mainly the local speed recommendation within the short road range. As shown in Figure 7, when the vehicle enters a specific section of road, the server will make further optimization decisions based on the real-time traffic conditions of the current section and quasi-static data. The intersection information includes the countdown of the traffic light in the direction of the intersection ahead and the distance to the nearest vehicle in front. If the current light is green, the recommended speed v s for:

[0152]

[0153] Among them, k3 and k4 are coefficients, Calculate the distance from the current vehicle to the intersection, which is based on the navigation map in the static data. is the remaining time of the green light, which is also the dynamic data. It is the historical travel speed of connected vehicles in the current scenario, that is, historical data is introduced.

[0154] In the above embodiment, the current dynamic traffic light data, the vehicle position, and the historical vehicle driving experience under the same state are simultaneously referred to, and a comprehensive decision is made to improve the accuracy of the decision.

[0155] In one of the optional embodiments, at least one level of first decision information is generated by a model based on vehicle control data corresponding to the server, roadside equipment and vehicle terminal; the above method also includes: correcting the model based on historical data.

[0156] In this application, historical data can also be processed. For example, the server processes the accumulated historical driving trajectories, historical road conditions, and long-term, macro data such as manual driving experience, and uses this to correct the model. Specifically, the server analyzes and corrects the historical data to generate a prediction model, which provides a basis for the generation of subsequent first decision information. Model correction and update includes continuously correcting and updating the global traffic model based on new data input to improve the accuracy of the prediction.

[0157] The prediction model here refers to the model involved in the generation process of the first decision information, including but not limited to the generation model of global dynamic path planning decision information, the generation model of intersection decision information, the specific coefficients involved in each model, etc., and no specific limitation is made here.

[0158] For ease of understanding, in conjunction with FIG8 , FIG8 is a flow chart of a vehicle control method in another embodiment, wherein the server can obtain vehicle control data collected by the server, roadside equipment, and vehicle terminal, and then make an outer decision based on the vehicle control data to generate global dynamic path planning decision information. Based on the vehicle control data, a middle-level decision is made to generate intersection decision information, and the generated global dynamic path planning decision information and intersection decision information are sent to the vehicle terminal. The vehicle terminal makes an inner-level decision to generate the second decision information, and then selects the target decision information based on the priority of the decision information, and executes the target decision information. Finally, the vehicle terminal synchronizes the status to the server. The server can process these historical data to update the model, and send the updated model to the vehicle terminal. In addition, these historical data can also be used to generate the first decision information and the second decision information.

[0159] Through the above steps, the decision-making and control process of the vehicle-road-cloud integrated technology realizes a complete closed loop from global path planning to local dynamic control, ensuring that the vehicle can obtain the optimal driving strategy and control suggestions during driving.

[0160] One thing that needs to be explained is that autonomous vehicles can achieve safer and more efficient driving by coordinating with roadside infrastructure and cloud platforms through vehicle-road-cloud technology. Vehicles not only rely on their own sensors, but also receive real-time information from the road and other vehicles to make more accurate decisions.

[0161] This application uses the autonomous driving scenario as an example for explanation. The vehicle control method in this application can also be applied to other scenarios, such as smart city traffic management scenarios. The traffic management system in the smart city can use vehicle-road-cloud integration technology to monitor and optimize urban traffic flow in real time. By analyzing traffic data across the city, the system can dynamically adjust traffic signals, optimize bus routes, and divert vehicle traffic to improve the overall traffic efficiency of the city. Specifically, the vehicle control method is applied to intelligent traffic signal control systems, urban traffic integrated management platforms, and traffic monitoring and dispatching systems.

[0162] The emergency vehicle priority passage system can provide priority passage support for emergency vehicles such as ambulances and fire trucks through vehicle-road-cloud technology. When the emergency vehicle is driving, the system can automatically adjust the traffic signal to ensure that the emergency vehicle has green lights along the way and notify other vehicles to give way in time. Specifically, the vehicle control method is applied to the emergency vehicle priority passage management system and the intelligent traffic signal control system.

[0163] Complex intersection management, where at complex intersections, vehicle-road-cloud technology can analyze traffic conditions in real time through roadside infrastructure (such as traffic lights, sensors, etc.) and cloud systems, dynamically adjust traffic plans, and reduce collision risks and congestion. Specifically, the vehicle control method is applied to intelligent intersection management systems and vehicle-road cooperative traffic lights.

[0164] Shared travel services, including shared cars, shared electric vehicles and other products, can achieve more accurate scheduling and management through vehicle-road-cloud integration technology. The platform can dynamically adjust the distribution and routes of vehicles based on real-time traffic data and user needs to optimize travel service efficiency. Specifically, the vehicle control method is applied to shared car scheduling platforms and smart travel service apps.

[0165] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0166] Based on the same inventive concept, the embodiment of the present application also provides a vehicle control device for implementing the vehicle control method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more vehicle control device embodiments provided below can refer to the limitations on the vehicle control method above, and will not be repeated here.

[0167] In an exemplary embodiment, as shown in FIG9 , a vehicle control device is provided, including: a decision information acquisition module 901, a target decision information determination module 902 and a control module 903, wherein:

[0168] A decision information acquisition module 901 is used to acquire one or more levels of decision information, wherein the decision information at least includes first decision information of at least one level sent by the server or the decision information includes first decision information of at least one level sent by the server and second decision information generated by the vehicle terminal, wherein the first decision information is generated based on the server, the roadside equipment and the vehicle control data corresponding to the vehicle terminal, and the second decision information is generated based on the vehicle control data corresponding to the vehicle terminal;

[0169] A target decision information determination module 902, for determining target decision information based on the priorities of the decision information at each level of Hu Qingou;

[0170] The control module 903 is used to control the vehicle operation based on the target decision information.

[0171] In one of the optional embodiments, the above-mentioned device also includes: a second decision information generating module, used to obtain event information affecting the operation of the vehicle; when the occurrence place of the event corresponding to the event information is on the same road as the vehicle, and the occurrence place of the event is located in front of the vehicle, the second decision information is generated based on the event and at least one of the road section corresponding to the vehicle, the number of lanes corresponding to the road section, the lane position and the number of vehicles on the lane.

[0172] In one of the optional embodiments, the above-mentioned second decision information generation module is specifically used to generate second decision information based on the number of vehicles on the adjacent lanes of the vehicle in any of the following situations: the road section corresponding to the place where the event occurred is the same as the road section corresponding to the vehicle, the number of lanes of the road section corresponding to the place where the event occurred is the same as the number of lanes of the road section corresponding to the vehicle, and the lane position corresponding to the place where the event occurred is the same as the lane position corresponding to the vehicle; the road section corresponding to the place where the event occurred is adjacent to the road section corresponding to the vehicle, the number of lanes of the road section corresponding to the place where the event occurred is the same as the number of lanes of the road section corresponding to the vehicle, and the lane position corresponding to the place where the event occurred is the same as the lane position corresponding to the vehicle; the road section corresponding to the place where the event occurred is adjacent to the road section corresponding to the vehicle, the number of lanes of the road section corresponding to the place where the event occurred is different from the number of lanes of the road section corresponding to the vehicle, and the lane position corresponding to the place where the event occurred is the same as the lane position corresponding to the vehicle.

[0173] In one of the optional embodiments, the first decision information includes global dynamic path planning decision information and intersection decision information, the priority of the second decision information is higher than the priority of the intersection decision information, and the priority of the intersection decision information is higher than the global dynamic path planning decision information; the above-mentioned target decision information determination module 902 is specifically used to use the second decision information as the target decision information when the second decision information exists; when the second decision information does not exist and there is intersection decision information, use the intersection decision information as the target decision information; when the second decision information and intersection decision information do not exist, use the global dynamic path planning decision information as the target decision information.

[0174] In some optional embodiments, the first decision information includes global dynamic path planning decision information; the global dynamic path planning decision information is generated by the server based on the first vehicle control data, the first vehicle control data includes static data and intention data in dynamic data, or the first vehicle control data includes historical data, at least one of road condition data in quasi-static data and intention data in static data and dynamic data, wherein the historical data is static data, quasi-static data and dynamic data obtained before the current time; the static data, quasi-static data and dynamic data are classified based on the real-time nature of the vehicle control data.

[0175] In some optional embodiments, when the intention data characterizes that the path planning intention is the shortest path, global dynamic path planning decision information is obtained based on the road condition data and the navigation map in the static data; when the intention data characterizes that the path planning intention is the shortest time, the traffic flow speed observed by vehicles on the historical path and the number of vehicles on the historical path are determined based on historical data; global dynamic path planning decision information is obtained based on the traffic flow speed observed by vehicles on the historical path, the number of vehicles on the historical path, the road condition data and the navigation map in the static data.

[0176] In some optional embodiments, the intersection decision information is generated based on the vehicle request and traffic signal data in the dynamic data, the navigation map in the static data, and the vehicle travel speed in the corresponding scenario in the historical data.

[0177] In an exemplary embodiment, as shown in FIG10 , a vehicle control device is provided, including: a control data acquisition module 1001, a first decision information generation module 1002 and a sending module 1003, wherein:

[0178] The control data acquisition module 1001 is used to acquire the vehicle control data corresponding to the server, the roadside equipment and the vehicle terminal;

[0179] A first decision information generating module 1002, configured to generate at least one level of first decision information based on the server, the roadside equipment and the vehicle control data corresponding to the vehicle terminal;

[0180] The sending module 1003 is used to send the first decision information to the vehicle terminal, and the vehicle terminal is used to obtain one or more levels of decision information, and determine the target decision information based on the priority of the acquired decision information at each level, and control the vehicle operation based on the target decision information, wherein the decision information includes the first decision information of at least one level issued by the server, or the decision information includes the first decision information of at least one level issued by the server and the second decision information generated by the vehicle terminal, and the second decision information is generated based on the vehicle control data corresponding to the vehicle terminal.

[0181] In one of the optional embodiments, the above device further includes:

[0182] A grouping module, for grouping the vehicle control data into static data, quasi-static data and dynamic data based on the real-time nature of the vehicle control data;

[0183] The first decision information generating module 1002 is specifically configured to generate at least one level of first decision information based on static data, quasi-static data and dynamic data.

[0184] In one of the optional embodiments, the first decision information includes global dynamic path planning decision information; the above-mentioned first decision information generation module 1002 is specifically used to generate global dynamic path planning decision information based on the first vehicle control data, the first vehicle control data includes static data and intention data in dynamic data, or the first vehicle control data includes historical data, at least one of road condition data in quasi-static data and intention data in static data and dynamic data, wherein the historical data is static data, quasi-static data and dynamic data obtained before the current time.

[0185] In one of the optional embodiments, the above-mentioned first decision information generation module 1002 is specifically used to obtain global dynamic path planning decision information based on road condition data and navigation maps in static data when the intention data represents that the path planning intention is the shortest path; when the intention data represents that the path planning intention is the shortest time, determine the traffic flow speed observed by vehicles on the historical path and the number of vehicles on the historical path based on historical data; obtain global dynamic path planning decision information based on the traffic flow speed observed by vehicles on the historical path, the number of vehicles on the historical path, road condition data and navigation maps in static data.

[0186] In one of the optional embodiments, the first decision information includes intersection decision information; the above-mentioned first decision information generation module 1002 is specifically used to obtain intersection decision information based on vehicle requests and traffic signal data in dynamic data, navigation maps in static data, and vehicle traffic speeds in corresponding scenarios in historical data.

[0187] In one of the optional embodiments, the second decision information is generated based on the event and at least one of the road section corresponding to the vehicle, the number of lanes corresponding to the road section, the lane position, and the number of vehicles on the lane, when the event occurs on the same road as the vehicle and the event occurs in front of the vehicle, wherein the event is obtained based on the event information affecting the operation of the vehicle obtained by the vehicle terminal.

[0188] In one of the optional embodiments, in any of the following cases, the vehicle terminal generates the second decision information based on the number of vehicles in the adjacent lanes of the vehicle:

[0189] The road section corresponding to the place where the incident occurs is the same as the road section corresponding to the vehicle, the number of lanes of the road section corresponding to the place where the incident occurs is the same as the number of lanes of the road section corresponding to the vehicle, and the lane position corresponding to the place where the incident occurs is the same as the lane position corresponding to the vehicle;

[0190] The road section corresponding to the place where the incident occurs and the road section corresponding to the vehicle are adjacent road sections, the number of lanes of the road section corresponding to the place where the incident occurs and the number of lanes of the road section corresponding to the vehicle are the same, and the lane position corresponding to the place where the incident occurs and the lane position corresponding to the vehicle are the same;

[0191] The road section corresponding to the place where the incident occurred and the road section corresponding to the vehicle are adjacent road sections, the number of lanes of the road section corresponding to the place where the incident occurred is different from the number of lanes of the road section corresponding to the vehicle, and the lane position corresponding to the place where the incident occurred is the same as the lane position corresponding to the vehicle.

[0192] In one of the optional embodiments, the first decision information includes global dynamic path planning decision information and intersection decision information; the method of generating the target decision information includes: when the second decision information exists, the second decision information is used as the target decision information; when the second decision information does not exist and there is intersection decision information, the intersection decision information is used as the target decision information; when the second decision information and intersection decision information do not exist, the global dynamic path planning decision information is used as the target decision information.

[0193] In one of the optional embodiments, the first decision information of at least one level is generated by a model based on vehicle control data corresponding to a server, roadside equipment and a vehicle terminal; the above-mentioned device also includes: a model correction module, which is used to correct the model based on historical data.

[0194] Each module in the above vehicle control device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each module.

[0195] In an exemplary embodiment, a computer device is provided, which may be a terminal or a server, wherein the internal structure diagram of the terminal may be shown in FIG11. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, the memory, and the input / output interface are connected via a system bus, and the communication interface, the display unit, and the input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner may be implemented through WIFI, a mobile cellular network, near field communication (NFC) or other technologies. When the computer program is executed by the processor, a vehicle control method is implemented. The display unit of the computer device is used to form a visually visible picture, which may be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0196] Those skilled in the art will understand that the structure shown in FIG. 11 is merely a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0197] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0198] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0199] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0200] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0201] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0202] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0203] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A vehicle control method, characterized in that: Applied to a vehicle terminal, the method comprises: Obtaining one or more levels of decision information, the decision information at least including first decision information of at least one level sent by a server, or the decision information including first decision information of at least one level sent by a server and second decision information generated by the vehicle terminal, wherein the first decision information is generated based on the server, the roadside equipment and the vehicle control data corresponding to the vehicle terminal, and the second decision information is generated based on the vehicle control data corresponding to the vehicle terminal; Determine target decision information based on the priorities of the obtained decision information at each level; The vehicle operation is controlled based on the target decision information.

2. The method according to claim 1, characterized in that The method for generating the second decision information includes: Obtain information about events that affect vehicle operation; When the place where the event corresponding to the event information occurs is on the same road as the vehicle and the place where the event occurs is located in front of the vehicle, second decision information is generated based on the event and at least one of the road section corresponding to the vehicle, the number of lanes corresponding to the road section, the lane position and the number of vehicles on the lane.

3. The method according to claim 2, characterized in that The generating the second decision information based on the event and at least one of the road section corresponding to the vehicle, the number of lanes corresponding to the road section, the lane position, and the number of vehicles on the lane comprises: In any of the following cases, the second decision information is generated based on the number of vehicles in the adjacent lane of the vehicle: The road section corresponding to the place where the event occurs is the same as the road section corresponding to the vehicle, the number of lanes of the road section corresponding to the place where the event occurs is the same as the number of lanes of the road section corresponding to the vehicle, and the lane position corresponding to the place where the event occurs is the same as the lane position corresponding to the vehicle; The road section corresponding to the place where the event occurs and the road section corresponding to the vehicle are adjacent road sections, the number of lanes of the road section corresponding to the place where the event occurs is the same as the number of lanes of the road section corresponding to the vehicle, and the lane position corresponding to the place where the event occurs is the same as the lane position corresponding to the vehicle; The road section corresponding to the place where the event occurred and the road section corresponding to the vehicle are adjacent sections, the number of lanes of the road section corresponding to the place where the event occurred is different from the number of lanes of the road section corresponding to the vehicle, and the lane position corresponding to the place where the event occurred is the same as the lane position corresponding to the vehicle.

4. The method according to any one of claims 1 to 3, characterized in that: The first decision information includes global dynamic path planning decision information and intersection decision information; the priority of the second decision information is higher than the priority of the intersection decision information, and the priority of the intersection decision information is higher than the global dynamic path planning decision information; The determining the target decision information based on the priority of the first decision information and the priority of the second decision information at least one level includes: In the case where the second decision information exists, taking the second decision information as the target decision information; In the case where the second decision information does not exist and the intersection decision information exists, using the intersection decision information as the target decision information; In the absence of the second decision information and the intersection decision information, the global dynamic path planning decision information is used as the target decision information.

5. The method according to claim 4, characterized in that The first decision information includes global dynamic path planning decision information; the global dynamic path planning decision information is generated by the server based on the first vehicle control data, the first vehicle control data includes static data and intention data in dynamic data, or the first vehicle control data includes historical data, at least one of road condition data in quasi-static data and intention data in the static data and dynamic data, wherein the historical data is static data, quasi-static data and dynamic data obtained before the current time; the static data, quasi-static data and dynamic data are classified based on the real-time nature of the vehicle control data.

6. The method according to claim 5, characterized in that When the intention data indicates that the path planning intention is the shortest path, obtaining global dynamic path planning decision information based on the road condition data and the navigation map in the static data; In the case where the intention data represents that the path planning intention is the shortest time, determining the traffic flow speed observed by vehicles on the historical path and the number of vehicles on the historical path based on the historical data; Based on the traffic flow speed observed by vehicles on the historical path, the number of vehicles on the historical path, the road condition data and the navigation map in the static data, global dynamic path planning decision information is obtained.

7. The method according to claim 5, characterized in that The intersection decision information is generated based on the vehicle request and traffic signal data in the dynamic data, the navigation map in the static data, and the vehicle travel speed in the corresponding scene in the historical data.

8. A vehicle control method, characterized in that: Applied to a server, the method comprises: Obtain vehicle control data corresponding to the server, roadside equipment and vehicle terminal; Generate at least one level of first decision information based on the server, the roadside equipment and the vehicle control data corresponding to the vehicle terminal; The first decision information is sent to a vehicle terminal, and the vehicle terminal is used to obtain decision information of one or more levels, and determine target decision information based on the priority of the acquired decision information of each level, and control the vehicle operation based on the target decision information, wherein the decision information includes first decision information of at least one level issued by a server or the decision information includes first decision information of at least one level issued by a server and second decision information generated by the vehicle terminal, and the second decision information is generated based on vehicle control data corresponding to the vehicle terminal.

9. The method according to claim 8, characterized in that After obtaining the vehicle control data corresponding to the server, the roadside equipment and the vehicle terminal, the method further includes: Based on the real-time nature of the vehicle control data, the vehicle control data is grouped to obtain static data, quasi-static data and dynamic data; The generating of at least one level of first decision information based on the vehicle control data corresponding to the server, the roadside equipment and the vehicle terminal includes: At least one level of first decision information is generated based on the static data, the quasi-static data and the dynamic data.

10. The method according to claim 9, characterized in that The first decision information includes global dynamic path planning decision information; the generating of at least one level of first decision information based on the static data, quasi-static data and dynamic data includes: Global dynamic path planning decision information is generated based on first vehicle control data, wherein the first vehicle control data includes the static data and intention data in the dynamic data, or the first vehicle control data includes historical data, at least one of the road condition data in the quasi-static data and the intention data in the static data and the dynamic data, wherein the historical data is the static data, quasi-static data and dynamic data obtained before the current time.

11. The method according to claim 10, characterized in that The generating of global dynamic path planning decision information based on the first vehicle control data includes: When the intention data indicates that the path planning intention is the shortest path, obtaining global dynamic path planning decision information based on the road condition data and the navigation map in the static data; When the intention data represents the path planning intention as the shortest time, the traffic flow speed observed by vehicles on the historical path and the number of vehicles on the historical path are determined based on the historical data; based on the traffic flow speed observed by vehicles on the historical path, the number of vehicles on the historical path, the road condition data and the navigation map in the static data, global dynamic path planning decision information is obtained.

12. The method according to claim 9, characterized in that The first decision information includes intersection decision information; the generating of at least one level of first decision information based on the static data, quasi-static data and dynamic data includes: Based on the vehicle request and traffic signal data in the dynamic data, the navigation map in the static data, and the vehicle travel speed in the corresponding scene in the historical data, the intersection decision information is obtained.

13. The method according to claim 8, characterized in that The second decision information is generated based on the event and at least one of the road section corresponding to the vehicle, the number of lanes corresponding to the road section, the lane position, and the number of vehicles on the lane, when the event occurs on the same road as the vehicle and the event occurs in front of the vehicle, wherein the event is obtained based on event information affecting the operation of the vehicle acquired by the vehicle terminal.

14. The method according to claim 13, characterized in that In any of the following cases, the vehicle terminal generates second decision information based on the number of vehicles in the adjacent lanes of the vehicle: The road section corresponding to the place where the event occurs is the same as the road section corresponding to the vehicle, the number of lanes of the road section corresponding to the place where the event occurs is the same as the number of lanes of the road section corresponding to the vehicle, and the lane position corresponding to the place where the event occurs is the same as the lane position corresponding to the vehicle; The road section corresponding to the place where the event occurs and the road section corresponding to the vehicle are adjacent road sections, the number of lanes of the road section corresponding to the place where the event occurs is the same as the number of lanes of the road section corresponding to the vehicle, and the lane position corresponding to the place where the event occurs is the same as the lane position corresponding to the vehicle; The road section corresponding to the place where the event occurred and the road section corresponding to the vehicle are adjacent sections, the number of lanes of the road section corresponding to the place where the event occurred is different from the number of lanes of the road section corresponding to the vehicle, and the lane position corresponding to the place where the event occurred is the same as the lane position corresponding to the vehicle.

15. The method according to claim 8, characterized in that The first decision information includes global dynamic path planning decision information and intersection decision information; The method for generating the target decision information includes: when the second decision information exists, using the second decision information as the target decision information; when the second decision information does not exist and there is intersection decision information, using the intersection decision information as the target decision information; when the second decision information and the intersection decision information do not exist, using the global dynamic path planning decision information as the target decision information.

16. The method according to claim 10, characterized in that The first decision information of at least one level is generated by a model based on the vehicle control data corresponding to the server, the roadside equipment and the vehicle terminal; the method further includes: The model is modified based on the historical data.

17. A vehicle control device, characterized in that: Applied to a vehicle terminal, the device comprises: A decision information acquisition module, used to acquire one or more levels of decision information, wherein the decision information at least includes first decision information of at least one level issued by a server or the decision information includes first decision information of at least one level issued by a server and second decision information generated by the vehicle terminal, wherein the first decision information is generated based on the server, the roadside equipment and the vehicle control data corresponding to the vehicle terminal, and the second decision information is generated based on the vehicle control data corresponding to the vehicle terminal; A target decision information determination module, used to determine the target decision information based on the priority of the acquired decision information at each level; A control module is used to control the operation of the vehicle based on the target decision information.

18. A vehicle control device, characterized in that: Applied to a server, the device comprises: A control data acquisition module is used to acquire vehicle control data corresponding to the server, roadside equipment and vehicle terminal; A first decision information generating module, configured to generate at least one level of first decision information based on the vehicle control data corresponding to the server, the roadside equipment and the vehicle terminal; A sending module is used to send the first decision information to a vehicle terminal, and the vehicle terminal is used to obtain decision information of one or more levels, and determine target decision information based on the priority of the acquired decision information of each level, and control the vehicle operation based on the target decision information, wherein the decision information includes first decision information of at least one level issued by a server or the decision information includes first decision information of at least one level issued by a server and second decision information generated by the vehicle terminal, and the second decision information is generated based on vehicle control data corresponding to the vehicle terminal.

19. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 16 are implemented.

20. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 16 are implemented.

21. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 16 are implemented.

Images