Driving control method and apparatus, computer device, and storage medium

Abstract

A driving control method and apparatus, a computer device, and a storage medium. The method comprises: S101, when receiving an intelligent driving starting instruction, in response to a target vehicle receiving a driving control instruction, generating first prompt information corresponding to the driving control instruction; S102, inputting the first prompt information into a generative target planning model, so as to generate a global driving strategy corresponding to the first prompt information, the global driving strategy being used for satisfying a driving requirement corresponding to the driving control instruction; and S103, on the basis of the global driving strategy, performing intelligent driving control on the target vehicle. Applying the generative target planning model to intelligent driving control can achieve end-to-end intelligent driving control.

Description

Driving control method, device, computer equipment and storage medium

[0001] This disclosure claims priority to a Chinese patent application filed with the Patent Office of China on December 12, 2023, with application number 2023117078159 and application name “A driving control method, device, computer equipment and storage medium,” all of which are incorporated by reference into this disclosure. Technical Field

[0002] The present disclosure relates to the field of intelligent driving technology, and more specifically, to a driving control method, apparatus, computer equipment, and storage medium. Background Art

[0003] With the rapid development of artificial intelligence technology, smart vehicles with autonomous driving functions have gradually entered people's daily lives, and smart vehicles can achieve more and more intelligent driving functions.

[0004] In related technologies, in the process of realizing intelligent driving functions, intelligent vehicles often need to use functional models corresponding to the intelligent driving functions. Since the functional model may contain multiple functional modules, different functional modules may produce errors, which causes the to-be-processed data corresponding to the intelligent driving function to accumulate errors after being processed by multiple functional modules in the functional model, thereby affecting the user's intelligent driving experience.

[0005] Summary of the Invention

[0006] The embodiments of the present disclosure at least provide a driving control method, apparatus, computer equipment, and storage medium.

[0007] In a first aspect, an embodiment of the present disclosure provides a driving control method, comprising:

[0008] After receiving the intelligent driving start instruction, in response to the target vehicle receiving the driving control instruction, generating first prompt information corresponding to the driving control instruction;

[0009] Inputting the first prompt information into a generative goal programming model to generate a global driving strategy corresponding to the first prompt information; wherein the global driving strategy is used to meet the driving demand corresponding to the driving control instruction;

[0010] Based on the global driving strategy, intelligent driving control is performed on the target vehicle.

[0011] In a possible implementation manner, the driving control instruction includes instruction content for indicating a driving task objective;

[0012] The step of generating first prompt information corresponding to the driving control instruction in response to the target vehicle receiving the driving control instruction includes:

[0013] In response to the target vehicle receiving the driving control instruction, first prompt information corresponding to the driving task target is generated according to the driving task target and a first prompt template for instructing generation of global driving information.

[0014] In one possible implementation, inputting the first prompt information into a generative goal programming model to generate a global driving strategy corresponding to the first prompt information includes:

[0015] Inputting the first prompt information into a generative goal programming model to generate information values ​​corresponding to various pieces of global driving information under the driving conditions corresponding to the driving task goal;

[0016] Based on the information values ​​corresponding to each item of global driving information, a global driving strategy corresponding to the first prompt information is determined.

[0017] In one possible implementation, the driving control instruction includes instruction content for indicating a driving task objective, and the method further includes:

[0018] In response to a preset real-time driving strategy determination condition being met, generating second prompt information based on a second prompt template for instructing to obtain real-time driving assistance parameters and the driving task objective, and inputting the second prompt information into the generative goal programming model to obtain parameter values ​​corresponding to each of the real-time driving assistance parameters;

[0019] generating third prompt information based on a third prompt template for instructing generation of a real-time driving strategy and parameter values ​​corresponding to each real-time driving assistance parameter, and inputting the third prompt information into the generative goal programming model to generate a real-time driving strategy;

[0020] Based on the real-time driving strategy, intelligent driving control is performed on the target vehicle.

[0021] In a possible implementation manner, the method further includes:

[0022] In response to the target vehicle receiving a speed adjustment instruction during the intelligent driving process, generating fourth prompt information based on a fourth prompt template for instructing generation of a driving path matching the speed adjustment instruction and the speed adjustment instruction;

[0023] The fourth prompt information is input into the generative target programming model to generate a speed regulation driving strategy that matches the speed adjustment instruction; wherein the speed regulation driving strategy includes a first driving path corresponding to the target vehicle when the speed adjustment command is executed.

[0024] In a possible implementation manner, the method further includes:

[0025] In response to the target vehicle receiving an overtaking instruction during the intelligent driving process, generating fifth prompt information based on a fifth prompt template for instructing generation of a driving path matching the overtaking instruction and the overtaking instruction;

[0026] The fifth prompt information is input into the generative target programming model to generate an overtaking driving strategy that matches the overtaking instruction; wherein the overtaking driving strategy includes a second driving path corresponding to the target vehicle when the overtaking instruction is executed.

[0027] In one possible implementation, the method further includes training the generative goal programming model according to the following steps:

[0028] Obtaining historical driving control instructions corresponding to the target vehicle and historical driving records corresponding to the historical driving control instructions;

[0029] Determining a sample driving strategy corresponding to the historical driving record based on the historical driving record and the target planning model to be trained;

[0030] determining a target loss value based on the sample driving strategy and the historical driving control instructions;

[0031] The network parameters of the target programming model to be trained are adjusted based on the target loss value, and the output result of the target programming model after adjusting the network parameters matches the vehicle driving habits corresponding to the historical driving control instructions.

[0032] In a second aspect, an embodiment of the present disclosure further provides a driving control device, comprising:

[0033] A first generating module is configured to generate, after receiving the intelligent driving start instruction, first prompt information corresponding to the driving control instruction in response to the target vehicle receiving the driving control instruction;

[0034] a second generation module, configured to input the first prompt information into a generative goal programming model to generate a global driving strategy corresponding to the first prompt information; wherein the global driving strategy is configured to satisfy the driving demand corresponding to the driving control instruction;

[0035] A control module is used to perform intelligent driving control on the target vehicle based on the global driving strategy.

[0036] In a possible implementation manner, the driving control instruction includes instruction content for indicating a driving task objective;

[0037] The first generating module, in response to the target vehicle receiving the driving control instruction, generates first prompt information corresponding to the driving control instruction, for:

[0038] In response to the target vehicle receiving the driving control instruction, first prompt information corresponding to the driving task target is generated according to the driving task target and a first prompt template for instructing generation of global driving information.

[0039] In one possible implementation, the second generation module, when inputting the first prompt information into a generative goal programming model to generate a global driving strategy corresponding to the first prompt information, is configured to:

[0040] Inputting the first prompt information into a generative goal programming model to generate information values ​​corresponding to various pieces of global driving information under the driving conditions corresponding to the driving task goal;

[0041] Based on the information values ​​corresponding to each item of global driving information, a global driving strategy corresponding to the first prompt information is determined.

[0042] In one possible implementation, the driving control instruction includes instruction content for indicating a driving task objective, and the second generating module is further configured to:

[0043] In response to a preset real-time driving strategy determination condition being met, generating second prompt information based on a second prompt template for instructing to obtain real-time driving assistance parameters and the driving task objective, and inputting the second prompt information into the generative goal programming model to obtain parameter values ​​corresponding to each of the real-time driving assistance parameters;

[0044] generating third prompt information based on a third prompt template for instructing generation of a real-time driving strategy and parameter values ​​corresponding to each real-time driving assistance parameter, and inputting the third prompt information into the generative goal programming model to generate a real-time driving strategy;

[0045] Based on the real-time driving strategy, intelligent driving control is performed on the target vehicle.

[0046] In a possible implementation manner, the second generation module is further configured to:

[0047] In response to the target vehicle receiving a speed adjustment instruction during the intelligent driving process, generating fourth prompt information based on a fourth prompt template for instructing generation of a driving path matching the speed adjustment instruction and the speed adjustment instruction;

[0048] The fourth prompt information is input into the generative target programming model to generate a speed regulation driving strategy that matches the speed adjustment instruction; wherein the speed regulation driving strategy includes a first driving path corresponding to the target vehicle when the speed adjustment command is executed.

[0049] In a possible implementation manner, the second generation module is further configured to:

[0050] In response to the target vehicle receiving an overtaking instruction during the intelligent driving process, generating fifth prompt information based on a fifth prompt template for instructing generation of a driving path matching the overtaking instruction and the overtaking instruction;

[0051] The fifth prompt information is input into the generative target programming model to generate an overtaking driving strategy that matches the overtaking instruction; wherein the overtaking driving strategy includes a second driving path corresponding to the target vehicle when the overtaking instruction is executed.

[0052] In one possible implementation, the control module is further configured to train the generative goal programming model according to the following steps:

[0053] Obtaining historical driving control instructions corresponding to the target vehicle and historical driving records corresponding to the historical driving control instructions;

[0054] Determining a sample driving strategy corresponding to the historical driving record based on the historical driving record and the target planning model to be trained;

[0055] determining a target loss value based on the sample driving strategy and the historical driving control instructions;

[0056] The network parameters of the target programming model to be trained are adjusted based on the target loss value, and the output result of the target programming model after adjusting the network parameters matches the vehicle driving habits corresponding to the historical driving control instructions.

[0057] In a third aspect, an embodiment of the present disclosure further provides a computer device comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the computer device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the steps of the above-mentioned first aspect or any possible implementation of the first aspect are performed.

[0058] In a fourth aspect, an embodiment of the present disclosure further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned first aspect or any possible implementation of the first aspect are executed.

[0059] The driving control method, apparatus, computer equipment, and storage medium provided by the embodiments of the present disclosure, after receiving an intelligent driving start instruction, generate a first prompt message corresponding to the driving control instruction in response to the target vehicle receiving the driving control instruction, and input the first prompt message that meets the input requirements of the generative target planning model into the target planning model, thereby performing intelligent driving control on the target vehicle based on the global driving strategy generated by the target planning model to meet the driving requirements corresponding to the driving control instruction. In this way, by applying the generative target planning model to intelligent driving control and converting the driving control instruction into prompt information that is more suitable for the generative target planning model input, end-to-end intelligent driving control can be achieved, which can effectively solve the problem of error accumulation caused by the large number of functional modules in related technologies and improve the user's intelligent driving experience.

[0060] In order to make the above-mentioned objectives, features and advantages of the present disclosure more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following briefly introduces the drawings required for use in the embodiments. The drawings herein are incorporated into and constitute a part of the specification. These drawings illustrate embodiments consistent with the present disclosure and, together with the specification, are used to illustrate the technical solutions of the present disclosure. It should be understood that the following drawings only illustrate certain embodiments of the present disclosure and should not be regarded as limiting the scope. For those of ordinary skill in the art, other relevant drawings can be obtained based on these drawings without inventive effort.

[0062] FIG1 shows a flow chart of a driving control method provided by an embodiment of the present disclosure;

[0063] FIG2 shows an architecture diagram corresponding to the driving control method provided in an embodiment of the present disclosure;

[0064] FIG3 shows a schematic diagram of the architecture of a driving control device provided by an embodiment of the present disclosure;

[0065] FIG4 shows a schematic structural diagram of a computer device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0066] In order to make the purpose, technical solutions and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. The components of the embodiments of the present disclosure generally described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present disclosure provided in the drawings is not intended to limit the scope of the disclosure for which protection is sought, but merely represents selected embodiments of the present disclosure. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present disclosure.

[0067] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings.

[0068] The term "and / or" herein simply describes an association relationship, indicating that three relationships can exist. For example, A and / or B can represent the existence of A alone, the simultaneous existence of A and B, and the existence of B alone. In addition, the term "at least one" herein refers to any combination of at least two of any one or more of a plurality of items. For example, "at least one of A, B, and C" can represent any one or more elements selected from the set consisting of A, B, and C.

[0069] Research has found that in the process of realizing intelligent driving functions, intelligent vehicles often need to use functional models corresponding to the intelligent driving functions. Since the functional model may contain multiple functional modules, different functional modules may produce errors, which causes the unprocessed data corresponding to the intelligent driving function to accumulate errors after being processed by multiple functional modules in the functional model, thereby affecting the user's intelligent driving experience.

[0070] Based on the above research, the present disclosure provides a driving control method, apparatus, computer equipment and storage medium. After receiving an intelligent driving start instruction, in response to the target vehicle receiving the driving control instruction, a first prompt information corresponding to the driving control instruction is generated, and the first prompt information that meets the input requirements of the generative target planning model is input into the target planning model, so that the target vehicle can be intelligently driven based on the global driving strategy generated by the target planning model to meet the driving needs corresponding to the driving control instruction. In this way, by applying the generative target planning model to intelligent driving control and converting the driving control instruction into prompt information that is more suitable for the generative target planning model input, end-to-end intelligent driving control can be achieved, which can effectively solve the problem of error accumulation caused by the large number of functional modules in the related technology and improve the user's intelligent driving experience.

[0071] To facilitate understanding of this embodiment, a driving control method disclosed in an embodiment of the present disclosure is first described in detail. The driving control method provided in the embodiment of the present disclosure is generally executed by a target vehicle that is equipped with a computer device having a certain computing capability. The computer device may include, for example, a terminal device, a server, or other processing device. The terminal device may be a user equipment (UE), a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (PDA), a handheld device, a computing device, an in-vehicle device, a wearable device, etc. In some possible implementations, the driving control method may be implemented by a processor invoking computer-readable instructions stored in a memory.

[0072] 1 , which is a flow chart of a driving control method according to an embodiment of the present disclosure, includes steps S101 to S103 , wherein:

[0073] S101: After receiving an intelligent driving start instruction, in response to the target vehicle receiving a driving control instruction, generating first prompt information corresponding to the driving control instruction.

[0074] S102: Inputting the first prompt information into a generative goal programming model to generate a global driving strategy corresponding to the first prompt information; wherein the global driving strategy is used to meet the driving requirements corresponding to the driving control instructions.

[0075] S103: Based on the global driving strategy, perform intelligent driving control on the target vehicle.

[0076] The following is a detailed description of the above steps.

[0077] With respect to S101, the intelligent driving start instruction is used to start the intelligent driving function of the target vehicle. The intelligent driving function may include an automatic driving or assisted driving function such as adaptive cruise control (ACC) and integrated adaptive cruise control (IACC). After the intelligent driving function of the target vehicle is triggered, intelligent driving control can be performed according to the driving control instruction. The intelligent driving start instruction may be generated by the user through voice, triggering a corresponding button, etc. The driving control instruction may include instruction content for indicating a driving task objective. The driving task objective may include a departure point, a destination, safety requirements, a departure time, etc. The driving task objective may be, for example, "from point A to point B, departure time is time C, and complete this journey in the safest way." The first prompt information may be a prompt information Prompt input into the generative model. By inputting the Prompt corresponding to the driving control instruction into the generative model, the generative model can output an output result that is more adapted to the driving requirement corresponding to the driving control instruction.

[0078] In one possible embodiment, when generating the first prompt information corresponding to the driving control instruction, the first prompt information corresponding to the driving task target can be generated in response to the target vehicle receiving the driving control instruction, according to the driving task target and the first prompt template for indicating the generation of global driving information.

[0079] Here, the first prompt template is used to enrich the contextual information of the driving task objective so that the first prompt information generated based on the first prompt template can contain richer semantics, so that after the first prompt information is input into the generative goal planning model, the goal planning model can better understand the driving requirements indicated by the driving task objective and perform planning based on this understanding.

[0080] Among them, the first prompt template may include a strategy acquisition instruction corresponding to the driving task objective, and the strategy acquisition instruction is used to obtain global driving information corresponding to the driving task objective. The global driving information is used to characterize the driving information that needs to be used globally when the target vehicle performs the driving task objective, that is, the driving information used from a global perspective; the global driving information may include: navigation information used to characterize the destination included in reaching the driving task objective, the risk factor when the target vehicle drives according to the driving task objective, the remaining resource amount corresponding to each driving node during the target vehicle's driving according to the driving task objective (the remaining resource amount can be, for example, the remaining power of the target vehicle), the map required when the target vehicle drives according to the driving task objective, etc.

[0081] Specifically, when generating the first prompt information corresponding to the driving task target according to the driving task target and the first prompt template for indicating the generation of global driving information, the driving task target and the first prompt template for indicating the generation of global driving information can be spliced ​​to generate the first prompt information corresponding to the driving task target.

[0082] For example, taking the first prompt template as "According to driving task objective XXXX, obtain the vehicle's navigation information, risk factor, and remaining battery power," after receiving the driving task objective "From point A to point B, departure time is time C, complete this journey in the safest way," the driving task objective "From point A to point B, departure time is time C, complete this journey in the safest way" and the first prompt template for instructing the generation of global driving information "According to driving task objective XXXX, obtain the vehicle's navigation information, risk factor, and remaining battery power" can be spliced ​​to generate the first prompt information corresponding to the driving task objective "According to the driving task objective 'From point A to point B, departure time is time C, complete this journey in the safest way', obtain the vehicle's navigation information, risk factor, and remaining battery power."

[0083] For S102 and S103,

[0084] Here, the network type of the generative goal programming model may be, for example, a generative pre-trained Transformer (GPT) model.

[0085] In one possible implementation, when the first prompt information is input into a generative goal programming model to generate a global driving strategy corresponding to the first prompt information, the following steps A1 to A2 may be performed:

[0086] A1: Input the first prompt information into a generative goal planning model to generate information values ​​corresponding to various global driving information under the driving conditions corresponding to the driving task objectives.

[0087] Continuing with the above example, taking the global driving information as the vehicle's navigation information, risk coefficient, and remaining power as an example, the information values ​​obtained for each item of global driving information can be the specific navigation content of the vehicle's navigation information, the specific value of the risk coefficient, and the specific power corresponding to the remaining power.

[0088] Among them, the navigation information in the global driving information can be used to characterize the global path planning, so as to subsequently obtain the global driving strategy based on the global path planning; the remaining power in the global driving information can be used to characterize whether it is necessary to set the power saving function, whether it is necessary to plan the charging path, etc.; the risk coefficient in the global driving information is used to judge whether the trip is possible this time, so as to improve the safety of the generated global driving strategy.

[0089] In this way, by generating global driving information in multiple dimensions and using the global driving information in multiple dimensions when subsequently generating a global driving strategy, the final global driving strategy can take into account user needs in terms of driving safety, power usage, etc.

[0090] A2: Determine a global driving strategy corresponding to the first prompt information based on information values ​​corresponding to each item of global driving information.

[0091] Here, when determining the global driving strategy corresponding to the first prompt information based on the information values ​​corresponding to each item of global driving information, the information values ​​corresponding to the global driving information can be displayed, and a driving strategy determination instruction initiated by the user for the information values ​​corresponding to the displayed global driving information can be received, and the driving strategy selected by the user can be used as the global driving strategy; or, based on the information values ​​corresponding to each item of global driving information, a global navigation path that meets the driving needs corresponding to the driving control instruction can be determined from the navigation information contained in the global driving information, and the determined global navigation path can be used as the target driving strategy.

[0092] In another possible implementation, the target vehicle may be intelligently driven and controlled by the following steps B1 to B3:

[0093] B1: In response to satisfying a preset real-time driving strategy determination condition, a second prompt message is generated based on a second prompt template for indicating the acquisition of real-time driving assistance parameters and the driving task goal, and the second prompt message is input into the generative target planning model to obtain parameter values ​​corresponding to each of the real-time driving assistance parameters.

[0094] Here, the real-time driving assistance parameters are parameters used to assist in determining the real-time driving strategy, and may include vehicle positioning information, vehicle speed information, vehicle acceleration information, etc.; the second prompt information may be prompt information input into the generative model; the second prompt template is used to enrich the context information of the driving task goal, so that the second prompt information generated based on the second prompt template can contain richer semantics, so that after the second prompt information is input into the generative goal planning model, the parameter values ​​corresponding to each of the real-time driving assistance parameters used to generate the real-time driving strategy are obtained; the satisfaction of the preset real-time driving strategy determination condition may be at least one of the following situations:

[0095] Case 1: It is detected that the time interval from the last determination of the real-time driving strategy reaches the preset time interval.

[0096] Here, the preset time interval may be any time interval, such as 30s.

[0097] For example, taking the preset time interval of 30 seconds as an example, when it is detected that the time interval from the last determination of the real-time driving strategy reaches 30 seconds, it can be determined that the preset real-time driving strategy determination conditions are met, and the real-time driving strategy is generated according to subsequent processing steps to perform intelligent driving control on the target vehicle based on the real-time driving strategy.

[0098] Case 2: Receive real-time driving instructions.

[0099] Here, the real-time driving instructions may include speed adjustment instructions, overtaking instructions, etc. The specific contents of the speed adjustment instructions and overtaking instructions will be described in detail below and will not be elaborated here.

[0100] Specifically, when a real-time driving instruction is received, it can be determined whether the preset real-time driving strategy determination conditions are met, and a real-time driving strategy is generated according to subsequent processing steps to perform intelligent driving control on the target vehicle based on the real-time driving strategy.

[0101] Case 3: It is detected that the environmental information around the target vehicle meets the preset environmental conditions.

[0102] Among them, the environmental information around the target vehicle can be collected by sensors deployed on the target vehicle, and the environmental information may include the position, speed, acceleration and other information corresponding to vehicles, obstacles and other objects around the target vehicle; the preset environmental condition can be that there are vehicles or obstacles within 5 meters around the target vehicle.

[0103] For example, taking the preset environmental condition that there is a vehicle or obstacle 5 meters around the target vehicle as an example, when it is detected that there is a vehicle or obstacle 5 meters around the target vehicle, it can be determined that the preset real-time driving strategy determination conditions are met, and a real-time driving strategy can be generated according to subsequent processing steps to perform intelligent driving control on the target vehicle based on the real-time driving strategy.

[0104] B2: Generate third prompt information based on the third prompt template for instructing the generation of the real-time driving strategy and the parameter values ​​corresponding to each real-time driving assistance parameter, and input the third prompt information into the generative target programming model to generate the real-time driving strategy.

[0105] Here, the third prompt information may be prompt information Prompt input into the generative model; the real-time driving strategy may include a real-time driving path.

[0106] For example, taking the third prompt template as "Based on the parameter values ​​corresponding to the currently known real-time driving assistance parameters A, real-time driving assistance parameters B, and real-time driving assistance parameters C, which of the current planned paths can be?", after inputting the second prompt information into the generative target planning model and obtaining the parameter values ​​corresponding to each of the real-time driving assistance parameters used to generate the real-time driving strategy, the parameter values ​​corresponding to each of the real-time driving assistance parameters can be spliced ​​with the third prompt template to generate a real-time driving strategy.

[0107] B3: Based on the real-time driving strategy, perform intelligent driving control on the target vehicle.

[0108] Here, when intelligent driving control is performed on the target vehicle based on the real-time driving strategy, multiple real-time driving paths included in the real-time driving information can be displayed, and a driving path determination instruction initiated by the user for any of the displayed real-time driving paths can be received, and intelligent driving control is performed on the target vehicle based on the real-time driving path indicated by the user.

[0109] Furthermore, in the above process of determining the real-time driving strategy, it is necessary to generate prompt information twice and use the generative target planning model twice. In order to reduce the number of times prompt information is generated and improve the efficiency of using the generative target planning model, it is also possible to generate sixth prompt information in response to meeting the preset real-time driving strategy determination conditions, based on the sixth prompt template for indicating the generation of the real-time driving strategy, the driving task goal, and the parameter values ​​corresponding to each of the real-time driving assistance parameters, and input the sixth prompt information into the generative target planning model to generate the real-time driving strategy.

[0110] Here, the sixth prompt information can be the prompt information Prompt input into the generative model; the sixth prompt template can be "Based on the driving task goal XXXX, and the currently known parameter values ​​corresponding to the real-time driving assistance parameter A, the real-time driving assistance parameter B, and the real-time driving assistance parameter C, what are the current planned paths? ", so that the sixth prompt template, the driving task goal, and the parameter values ​​corresponding to each of the real-time driving assistance parameters can be spliced ​​to generate the sixth prompt information for input into the generative target planning model to obtain the real-time driving strategy.

[0111] In this way, compared with obtaining the parameter values ​​of the real-time driving assistance parameters through the target planning model and then using the target planning model again to determine the real-time driving strategy, by adding the parameter values ​​of the directly obtained real-time driving assistance parameters to the prompt information, the real-time driving strategy can be generated by calling the target planning model only once, thereby realizing the end-to-end integrated generation of the real-time driving strategy during the driving process of the target vehicle.

[0112] In one possible implementation, the target vehicle can receive different real-time commands during intelligent driving. Each received real-time command can be detected for its type and then, based on the command type, generated a different real-time driving strategy that matches the global driving strategy, thereby meeting the user's diverse real-time driving needs.

[0113] The instruction type of the real-time instruction may include at least one of the following:

[0114] Instruction type 1: Speed ​​adjustment instruction

[0115] Here, in response to the target vehicle receiving a speed adjustment instruction during the intelligent driving process, fourth prompt information can be generated based on a fourth prompt template for indicating the generation of a driving path matching the speed adjustment instruction and the speed adjustment instruction, and the fourth prompt information is input into the generative target planning model to generate a speed adjustment driving strategy matching the speed adjustment instruction.

[0116] Among them, the speed regulation driving strategy includes a first driving path corresponding to the target vehicle when executing the speed adjustment command; the fourth prompt information can be a prompt information Prompt input into the generative model; the fourth prompt template can be "Based on the driving task objective XXXX, and the currently known parameter values ​​corresponding to the real-time driving assistance parameters A, real-time driving assistance parameters B, and real-time driving assistance parameters C, among the current several planned paths, which path matches the instruction content XXXX corresponding to the speed adjustment instruction?", that is, the fourth prompt template can be, on the basis of the sixth prompt template used to obtain the real-time driving strategy, adding the instruction content corresponding to the speed adjustment instruction, so that the generative target planning model can, on the basis of obtaining the real-time driving strategy, output a speed regulation driving strategy that meets the speed adjustment requirements corresponding to the speed adjustment instruction according to the speed adjustment instruction.

[0117] For example, the instruction content corresponding to the speed adjustment instruction is "You are driving too slowly, hurry up", and the fourth prompt template can be "According to the driving task target XXXX, and the currently known parameter values ​​corresponding to the real-time driving assistance parameters A, real-time driving assistance parameters B, and real-time driving assistance parameters C, which path among the currently planned paths matches the instruction content XXXX corresponding to the speed adjustment instruction?". After splicing the fourth prompt template and the instruction content corresponding to the speed adjustment instruction, the fourth prompt information "According to the driving task target XXXX, and the currently known parameter values ​​corresponding to the real-time driving assistance parameters A, real-time driving assistance parameters B, and real-time driving assistance parameters C, which path matches the instruction content 'You are driving too slowly, hurry up' corresponding to the speed adjustment instruction?" can be obtained.

[0118] In this way, by using the fourth prompt template and the speed adjustment instruction to generate the fourth prompt information, the generative goal programming model can generate a speed adjustment driving strategy that meets the speed adjustment requirements corresponding to the speed adjustment instruction according to the fourth prompt information, thereby improving the user's intelligent driving experience.

[0119] Instruction type 2: Overtaking instruction

[0120] Here, in response to the target vehicle receiving an overtaking instruction during the intelligent driving process, fifth prompt information can be generated based on a fifth prompt template for indicating the generation of a driving path matching the overtaking instruction and the overtaking instruction; and the fifth prompt information can be input into the generative target planning model to generate an overtaking driving strategy matching the overtaking instruction.

[0121] Among them, the overtaking driving strategy includes a second driving path corresponding to the target vehicle when executing the overtaking instruction; the fifth prompt information can be a prompt information Prompt input into the generative model; the fifth prompt template can be "Based on the driving task objective XXXX, and the currently known parameter values ​​corresponding to the real-time driving assistance parameters A, real-time driving assistance parameters B, and real-time driving assistance parameters C, among the current several planned paths, which path matches the instruction content XXXX corresponding to the overtaking instruction?", that is, the fifth prompt template can be, on the basis of the sixth prompt template used to obtain the real-time driving strategy, adding the instruction content corresponding to the overtaking instruction, so that the generative target planning model can, on the basis of obtaining the real-time driving strategy, output an overtaking driving strategy that meets the overtaking requirements corresponding to the speed adjustment instruction according to the overtaking instruction.

[0122] For example, the instruction content corresponding to the overtaking instruction is "overtake the large truck in front", and the fifth prompt template can be "According to the driving task target XXXX, and the currently known parameter values ​​corresponding to the real-time driving assistance parameters A, real-time driving assistance parameters B, and real-time driving assistance parameters C, which path among the currently planned paths matches the instruction content XXXX corresponding to the overtaking instruction?". After splicing the fifth prompt template and the instruction content corresponding to the overtaking instruction, the fifth prompt information "According to the driving task target XXXX, and the currently known parameter values ​​corresponding to the real-time driving assistance parameters A, real-time driving assistance parameters B, and real-time driving assistance parameters C, which path matches the instruction content corresponding to the overtaking instruction 'overtake the large truck in front'?" can be obtained.

[0123] Furthermore, if the real-time driving path corresponding to the real-time driving strategy does not include a driving path that meets the overtaking requirement corresponding to the overtaking instruction, a corresponding prompt message can be generated to indicate that the overtaking instruction cannot be completed; alternatively, the real-time driving path corresponding to the real-time driving strategy can be regenerated, and a driving path that meets the overtaking requirement corresponding to the overtaking instruction can be determined from the regenerated implementation driving path.

[0124] In this way, by using the fifth prompt template and the overtaking instruction to generate the fifth prompt information, the generative goal programming model can generate an overtaking driving strategy that meets the overtaking requirements corresponding to the overtaking instruction according to the fifth prompt information, thereby improving the user's intelligent driving experience.

[0125] In practical applications, the target planning model can also be subjected to reinforcement learning so that the output of the target planning model can match the user's driving habits. The following is an exemplary introduction to one of the reinforcement learning training methods:

[0126] In one possible implementation, the generative goal programming model may be trained through the following steps C1 to C4:

[0127] C1: Acquire historical driving control instructions corresponding to the target vehicle and historical driving records corresponding to the historical driving control instructions.

[0128] Here, the historical driving record may include parameter values ​​corresponding to real-time driving assistance parameters for generating a real-time driving strategy corresponding to each driving moment.

[0129] C2: Based on the historical driving records and the target planning model to be trained, determine a sample driving strategy corresponding to the historical driving records.

[0130] Here, for any driving moment, a sample driving strategy corresponding to the historical driving record can be generated based on the parameter values ​​of the real-time driving assistance parameters corresponding to the driving moment and the target planning model to be trained.

[0131] The detailed description of generating the sample driving strategy can refer to the above-mentioned content related to generating the real-time driving strategy, which will not be repeated here.

[0132] C3: Determine a target loss value based on the sample driving strategy and the historical driving control instructions.

[0133] C4: adjusting the network parameters of the target programming model to be trained based on the target loss value, so that the output result of the target programming model after adjusting the network parameters matches the vehicle driving habits corresponding to the historical driving control instructions.

[0134] Here, for any driving moment, the historical driving control instructions corresponding to the driving moment can be used as supervision data of the sample driving strategy at the driving moment to determine the target loss value.

[0135] Among them, for the real-time strategy adjustment scenarios corresponding to different real-time instructions (such as speed adjustment instructions, overtaking instructions, etc.), the loss values ​​can be calculated separately, and based on the loss values ​​determined in each real-time strategy adjustment scenario, the network parameters of the target planning model to be trained are adjusted so that the output results of the target planning model can match the user's vehicle driving habits in different driving scenarios.

[0136] It should be noted that the above-mentioned training method is only an exemplary reinforcement learning method. In actual applications, other reinforcement learning methods can be used to perform reinforcement learning on the target planning model so that the output results of the target planning model can match the user's vehicle driving habits in different driving scenarios. The embodiment of the present disclosure does not limit how to perform reinforcement learning on the target planning model, so as to improve the model performance of the target planning model.

[0137] Below, the architecture diagram corresponding to the driving control method provided by the embodiment of the present disclosure will be introduced in conjunction with the architecture diagram. The architecture diagram corresponding to the driving control method provided by the embodiment of the present disclosure can be shown in Figure 2. In Figure 2, the input is a driving control instruction, and Prompt represents the prompt information input to the target planning model after processing the driving control instruction using the corresponding template; according to the stage division of the input content of the target planning model, it can be divided into global Prompt and real-time Prompt, and according to whether it is generated according to user instructions, it can be divided into user Prompt and system Prompt (that is, not generated by user instructions); among which, the relevant content of the global Prompt contained in the system Prompt can refer to the relevant content of the first prompt information mentioned above, and will not be repeated here; about the user Prompt For the relevant content of the real-time Prompt contained in rompt, please refer to the relevant content of the fourth prompt information and the fifth prompt information mentioned above, which will not be repeated here; for the relevant content of the end-to-end Prompt (belonging to the real-time Prompt) contained in the system Prompt, please refer to the relevant content of the sixth prompt information mentioned above, which will not be repeated here; for the relevant content of the perception Prompt (belonging to the real-time Prompt) and cognitive Prompt (belonging to the real-time Prompt) contained in the system Prompt, please refer to the relevant content of the second prompt information and the third prompt information mentioned above, which will not be repeated here. The perception Prompt and cognitive Prompt contained in the dotted line can achieve the same effect as the end-to-end Prompt, and the dotted line indicates that using them simultaneously can achieve the same effect as the end-to-end Prompt.

[0138] The driving control method provided by the embodiment of the present disclosure, after receiving an intelligent driving start instruction, generates a first prompt message corresponding to the driving control instruction in response to the target vehicle receiving the driving control instruction, and inputs the first prompt message that meets the input requirements of the generative target planning model into the target planning model, thereby performing intelligent driving control on the target vehicle based on the global driving strategy generated by the target planning model to meet the driving requirements corresponding to the driving control instruction. In this way, by applying the generative target planning model to intelligent driving control and converting the driving control instruction into prompt messages that are more suitable for the input of the generative target planning model, end-to-end intelligent driving control can be achieved, which can effectively solve the problem of error accumulation caused by the large number of functional modules in related technologies and improve the user's intelligent driving experience.

[0139] Those skilled in the art will understand that in the above-mentioned method of the specific implementation method, the writing order of each step does not mean a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of each step should be determined by its function and possible internal logic.

[0140] Based on the same inventive concept, a driving control device corresponding to the driving control method is also provided in the embodiment of the present disclosure. Since the principle of solving the problem by the device in the embodiment of the present disclosure is similar to the above-mentioned driving control method in the embodiment of the present disclosure, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0141] 3 , which is a schematic diagram of the architecture of a driving control device provided by an embodiment of the present disclosure, the device includes: a first generating module 301 , a second generating module 302 , and a control module 303 ; wherein,

[0142] The first generating module 301 is configured to generate first prompt information corresponding to the driving control instruction in response to the target vehicle receiving the driving control instruction after receiving the intelligent driving start instruction;

[0143] A second generating module 302 is configured to input the first prompt information into a generative goal programming model to generate a global driving strategy corresponding to the first prompt information; wherein the global driving strategy is configured to satisfy the driving demand corresponding to the driving control instruction;

[0144] The control module 303 is configured to perform intelligent driving control on the target vehicle based on the global driving strategy.

[0145] In a possible implementation manner, the driving control instruction includes instruction content for indicating a driving task objective;

[0146] The first generating module 301, in response to the target vehicle receiving the driving control instruction, generates first prompt information corresponding to the driving control instruction, for:

[0147] In response to the target vehicle receiving the driving control instruction, first prompt information corresponding to the driving task target is generated according to the driving task target and a first prompt template for instructing generation of global driving information.

[0148] In one possible implementation, the second generation module 302, when inputting the first prompt information into a generative goal programming model to generate a global driving strategy corresponding to the first prompt information, is configured to:

[0149] Inputting the first prompt information into a generative goal programming model to generate information values ​​corresponding to various pieces of global driving information under the driving conditions corresponding to the driving task goal;

[0150] Based on the information values ​​corresponding to each item of global driving information, a global driving strategy corresponding to the first prompt information is determined.

[0151] In a possible implementation, the driving control instruction includes instruction content for indicating a driving task objective, and the second generating module 302 is further configured to:

[0152] In response to a preset real-time driving strategy determination condition being met, generating second prompt information based on a second prompt template for instructing to obtain real-time driving assistance parameters and the driving task objective, and inputting the second prompt information into the generative goal programming model to obtain parameter values ​​corresponding to each of the real-time driving assistance parameters;

[0153] generating third prompt information based on a third prompt template for instructing generation of a real-time driving strategy and parameter values ​​corresponding to each real-time driving assistance parameter, and inputting the third prompt information into the generative goal programming model to generate a real-time driving strategy;

[0154] Based on the real-time driving strategy, intelligent driving control is performed on the target vehicle.

[0155] In a possible implementation manner, the second generating module 302 is further configured to:

[0156] In response to the target vehicle receiving a speed adjustment instruction during the intelligent driving process, generating fourth prompt information based on a fourth prompt template for instructing generation of a driving path matching the speed adjustment instruction and the speed adjustment instruction;

[0157] The fourth prompt information is input into the generative target programming model to generate a speed regulation driving strategy that matches the speed adjustment instruction; wherein the speed regulation driving strategy includes a first driving path corresponding to the target vehicle when the speed adjustment command is executed.

[0158] In a possible implementation manner, the second generating module 302 is further configured to:

[0159] In response to the target vehicle receiving an overtaking instruction during the intelligent driving process, generating fifth prompt information based on a fifth prompt template for instructing generation of a driving path matching the overtaking instruction and the overtaking instruction;

[0160] The fifth prompt information is input into the generative target programming model to generate an overtaking driving strategy that matches the overtaking instruction; wherein the overtaking driving strategy includes a second driving path corresponding to the target vehicle when the overtaking instruction is executed.

[0161] In a possible implementation, the control module 303 is further configured to train the generative goal programming model according to the following steps:

[0162] Obtaining historical driving control instructions corresponding to the target vehicle and historical driving records corresponding to the historical driving control instructions;

[0163] Determining a sample driving strategy corresponding to the historical driving record based on the historical driving record and the target planning model to be trained;

[0164] determining a target loss value based on the sample driving strategy and the historical driving control instructions;

[0165] The network parameters of the target programming model to be trained are adjusted based on the target loss value, and the output result of the target programming model after adjusting the network parameters matches the vehicle driving habits corresponding to the historical driving control instructions.

[0166] The driving control method and apparatus provided in the embodiment of the present disclosure, after receiving an intelligent driving start instruction, generates a first prompt message corresponding to the driving control instruction in response to the target vehicle receiving the driving control instruction, and inputs the first prompt message that meets the input requirements of the generative target planning model into the target planning model, thereby performing intelligent driving control on the target vehicle based on a global driving strategy generated by the target planning model to meet the driving requirements corresponding to the driving control instruction. In this way, by applying the generative target planning model to intelligent driving control and converting the driving control instruction into prompt messages that are more suitable for the input of the generative target planning model, end-to-end intelligent driving control can be achieved, which can effectively solve the problem of error accumulation caused by the large number of functional modules in related technologies and improve the user's intelligent driving experience.

[0167] For descriptions of the processing flow of each module in the device and the interaction flow between each module, reference can be made to the relevant descriptions in the above method embodiment, which will not be described in detail here.

[0168] Based on the same technical concept, the embodiment of the present disclosure also provides a computer device. Referring to Figure 4, it is a structural diagram of the computer device 400 provided in the embodiment of the present disclosure, including a processor 401, a memory 402, and a bus 403. Among them, the memory 402 is used to store execution instructions, including a memory 4021 and an external memory 4022; the memory 4021 here is also called an internal memory, which is used to temporarily store the calculation data in the processor 401, as well as the data exchanged with the external memory 4022 such as a hard disk. The processor 401 exchanges data with the external memory 4022 through the memory 4021. When the computer device 400 is running, the processor 401 communicates with the memory 402 through the bus 403, so that the processor 401 executes the following instructions:

[0169] After receiving the intelligent driving start instruction, in response to the target vehicle receiving the driving control instruction, generating first prompt information corresponding to the driving control instruction;

[0170] Inputting the first prompt information into a generative goal programming model to generate a global driving strategy corresponding to the first prompt information; wherein the global driving strategy is used to meet the driving demand corresponding to the driving control instruction;

[0171] Based on the global driving strategy, intelligent driving control is performed on the target vehicle.

[0172] In a possible implementation manner, in the instructions of the processor 401, the driving control instructions include instruction content for indicating a driving task objective;

[0173] The step of generating first prompt information corresponding to the driving control instruction in response to the target vehicle receiving the driving control instruction includes:

[0174] In response to the target vehicle receiving the driving control instruction, first prompt information corresponding to the driving task target is generated according to the driving task target and a first prompt template for instructing generation of global driving information.

[0175] In one possible implementation, the instructions of the processor 401, inputting the first prompt information into a generative goal programming model to generate a global driving strategy corresponding to the first prompt information, include:

[0176] Inputting the first prompt information into a generative goal programming model to generate information values ​​corresponding to various pieces of global driving information under the driving conditions corresponding to the driving task goal;

[0177] Based on the information values ​​corresponding to each item of global driving information, a global driving strategy corresponding to the first prompt information is determined.

[0178] In a possible implementation, in the instructions of the processor 401, the driving control instructions include instruction content for indicating a driving task objective, and further include:

[0179] In response to a preset real-time driving strategy determination condition being met, generating second prompt information based on a second prompt template for instructing to obtain real-time driving assistance parameters and the driving task objective, and inputting the second prompt information into the generative goal programming model to obtain parameter values ​​corresponding to each of the real-time driving assistance parameters;

[0180] generating third prompt information based on a third prompt template for instructing generation of a real-time driving strategy and parameter values ​​corresponding to each real-time driving assistance parameter, and inputting the third prompt information into the generative goal programming model to generate a real-time driving strategy;

[0181] Based on the real-time driving strategy, intelligent driving control is performed on the target vehicle.

[0182] In a possible implementation manner, the instruction of the processor 401 further includes:

[0183] In response to the target vehicle receiving a speed adjustment instruction during the intelligent driving process, generating fourth prompt information based on a fourth prompt template for instructing generation of a driving path matching the speed adjustment instruction and the speed adjustment instruction;

[0184] The fourth prompt information is input into the generative target programming model to generate a speed regulation driving strategy that matches the speed adjustment instruction; wherein the speed regulation driving strategy includes a first driving path corresponding to the target vehicle when the speed adjustment command is executed.

[0185] In a possible implementation manner, the instruction of the processor 401 further includes:

[0186] In response to the target vehicle receiving an overtaking instruction during the intelligent driving process, generating fifth prompt information based on a fifth prompt template for instructing generation of a driving path matching the overtaking instruction and the overtaking instruction;

[0187] The fifth prompt information is input into the generative target programming model to generate an overtaking driving strategy that matches the overtaking instruction; wherein the overtaking driving strategy includes a second driving path corresponding to the target vehicle when the overtaking instruction is executed.

[0188] In a possible implementation, the instructions of the processor 401 further include training the generative goal programming model according to the following steps:

[0189] Obtaining historical driving control instructions corresponding to the target vehicle and historical driving records corresponding to the historical driving control instructions;

[0190] Determining a sample driving strategy corresponding to the historical driving record based on the historical driving record and the target planning model to be trained;

[0191] determining a target loss value based on the sample driving strategy and the historical driving control instructions;

[0192] The network parameters of the target programming model to be trained are adjusted based on the target loss value, and the output result of the target programming model after adjusting the network parameters matches the vehicle driving habits corresponding to the historical driving control instructions.

[0193] The present disclosure also provides a computer-readable storage medium having a computer program stored thereon. When executed by a processor, the computer program executes the steps of the driving control method described in the above method embodiment. The storage medium may be a volatile or non-volatile computer-readable storage medium.

[0194] The embodiments of the present disclosure also provide a computer program product, which carries a program code. The instructions included in the program code can be used to execute the steps of the driving control method described in the above method embodiment. For details, please refer to the above method embodiment, which will not be repeated here.

[0195] The computer program product may be implemented in hardware, software, or a combination thereof. In one embodiment, the computer program product is implemented as a computer storage medium. In another embodiment, the computer program product is implemented as a software product, such as a software development kit (SDK).

[0196] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems and devices described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. In the several embodiments provided in the present disclosure, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0197] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0198] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0199] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present disclosure, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present disclosure. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0200] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present disclosure, which are used to illustrate the technical solutions of the present disclosure, rather than to limit them. The scope of protection of the present disclosure is not limited thereto. Although the present disclosure has been described in detail with reference to the above-described embodiments, those skilled in the art should understand that any person skilled in the art can modify or easily conceive of changes to the technical solutions described in the above-described embodiments within the technical scope disclosed in the present disclosure, or replace some of the technical features therein with equivalents. Such modifications, changes, or replacements do not deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure, and should be included in the scope of protection of the present disclosure. Therefore, the scope of protection of the present disclosure shall be subject to the scope of protection of the claims.

Claims

1. A driving control method, characterized in that: Applied to target vehicles, including: After receiving the intelligent driving start instruction, in response to the target vehicle receiving the driving control instruction, generating first prompt information corresponding to the driving control instruction; Inputting the first prompt information into a generative target programming model to generate a global driving strategy corresponding to the first prompt information; wherein the global driving strategy is used to meet the driving demand corresponding to the driving control instruction; Based on the global driving strategy, intelligent driving control is performed on the target vehicle.

2. The method according to claim 1, characterized in that The driving control instruction includes instruction content for indicating a driving task target; In response to the target vehicle receiving the driving control instruction, generating first prompt information corresponding to the driving control instruction includes: In response to the target vehicle receiving the driving control instruction, first prompt information corresponding to the driving task target is generated according to the driving task target and a first prompt template for instructing to generate global driving information.

3. The method according to claim 2, characterized in that The step of inputting the first prompt information into a generative target programming model to generate a global driving strategy corresponding to the first prompt information includes: Inputting the first prompt information into a generative target planning model to generate information values ​​corresponding to each item of global driving information under the driving conditions corresponding to the driving task target; Based on the information values ​​corresponding to each item of global driving information, a global driving strategy corresponding to the first prompt information is determined.

4. The method according to claim 1, characterized in that: The driving control instruction includes instruction content for indicating a driving task target, and the method further includes: In response to satisfying a preset real-time driving strategy determination condition, generating second prompt information based on a second prompt template for indicating acquisition of real-time driving assistance parameters and the driving task goal, and inputting the second prompt information into the generative goal planning model to obtain parameter values ​​corresponding to each of the real-time driving assistance parameters; generating third prompt information based on a third prompt template for indicating generation of a real-time driving strategy and parameter values ​​corresponding to each real-time driving assistance parameter, and inputting the third prompt information into the generative target programming model to generate a real-time driving strategy; Based on the real-time driving strategy, intelligent driving control is performed on the target vehicle.

5. The method according to claim 1, characterized in that The method further comprises: In response to the target vehicle receiving a speed adjustment instruction during the intelligent driving process, generating fourth prompt information based on a fourth prompt template for indicating generation of a driving path matching the speed adjustment instruction and the speed adjustment instruction; The fourth prompt information is input into the generative target planning model to generate a speed regulation driving strategy that matches the speed adjustment instruction; wherein the speed regulation driving strategy includes a first driving path corresponding to the target vehicle when the speed adjustment command is executed.

6. The method according to claim 1, characterized in that The method further comprises: In response to the target vehicle receiving an overtaking instruction during the intelligent driving process, generating fifth prompt information based on a fifth prompt template for instructing to generate a driving path matching the overtaking instruction and the overtaking instruction; The fifth prompt information is input into the generative target programming model to generate an overtaking driving strategy that matches the overtaking instruction; wherein the overtaking driving strategy includes a second driving path corresponding to the target vehicle when the overtaking instruction is executed.

7. The method according to claim 1, characterized in that The method further comprises training the generative goal programming model according to the following steps: Acquire historical driving control instructions corresponding to the target vehicle, and historical driving records corresponding to the historical driving control instructions; Determining a sample driving strategy corresponding to the historical driving record based on the historical driving record and the target planning model to be trained; Determining a target loss value based on the sample driving strategy and the historical driving control instructions; The network parameters of the target programming model to be trained are adjusted based on the target loss value, and the output result of the target programming model after the network parameters are adjusted matches the vehicle driving habits corresponding to the historical driving control instructions.

8. A driving control device, characterized in that: Applied to target vehicles, including: A first generating module is used for generating first prompt information corresponding to the driving control instruction in response to the target vehicle receiving the driving control instruction after receiving the intelligent driving start instruction; a second generating module, configured to input the first prompt information into a generative target programming model to generate a global driving strategy corresponding to the first prompt information; wherein the global driving strategy is used to meet the driving demand corresponding to the driving control instruction; A control module is used to perform intelligent driving control on the target vehicle based on the global driving strategy.

9. A computer device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the computer device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the steps of the driving control method as described in any one of claims 1 to 7 are performed.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the driving control method as claimed in any one of claims 1 to 7 are executed.

Images