Vehicle intelligent fault-tolerant optimization method and system based on preset time

Abstract

The invention relates to a vehicle intelligent fault-tolerant optimization method and system based on preset time. The method comprises the following steps: acquiring environmental parameters, and inputting the environmental parameters into a local model preset at a vehicle end to obtain a first control instruction generated by the vehicle end model; uploading the environmental parameters to a cloud, so that the cloud inputs the environmental parameters to a cloud model preset in the cloud and obtains a second control instruction; waiting and acquiring a receiving timestamp of completely receiving the environmental parameters fed back by the cloud, and judging whether an event from completing the receiving of the event corresponding to the timestamp to uploading the timestamp event of the environmental parameters is greater than a preset time threshold value or not; if yes, lowering the priority of a second driving instruction fed back by the cloud; obtaining a third control instruction obtained by the in-vehicle hardware; and comparing the priorities of the first control instruction, the second control instruction and the third control instruction, and obtaining the control instruction with the highest priority as an actual control instruction and outputting the actual control instruction.

Description

Technical Field

[0001] This application relates to the field of vehicle automatic control technology, and in particular to a vehicle intelligent fault-tolerant optimization method, system, computer equipment, storage medium and computer program product based on preset time. Background Technology

[0002] With the rapid development of new energy vehicles towards intelligence, increasingly comprehensive driver assistance and autonomous driving technologies are steadily moving towards driverless operation. However, as the number of input sources that can control the vehicle gradually increases, how to coordinate the input commands from these sources to ensure the smooth and safe driving of the vehicle has become a hot issue of concern in the industry.

[0003] Chinese patent application CN120161852A discloses an autonomous driving system based on 5G IoT, including an image acquisition device, a cloud server platform, and a central control center. The image acquisition device includes sensors such as LiDAR and cameras for acquiring road images. The cloud server platform processes the image information and performs intelligent recognition to obtain road identification results. The central control center makes decisions and controls the driving behavior of the autonomous vehicle based on the data processing results. Through the image processing technology of the cloud server platform, the acquired road condition information, especially potholes and icy roads, is intelligently identified, and decisions are made for autonomous driving based on the road conditions. The method described in this invention can accurately identify potholes and control speed on icy roads, achieving precise control of autonomous vehicles in complex road conditions and improving the accuracy of identifying poor road conditions and the accuracy of unmanned driving control.

[0004] However, this system relies on real-time data interaction between the vehicle and the cloud. When communication is interfered with by environmental factors, the vehicle will be in a dangerous state where it is difficult to cope with emergencies. Therefore, there is an urgent need for a vehicle control method that can optimize the cooperative relationship between multiple control sources and perform fault-tolerant control of the vehicle to meet the needs of autonomous driving in areas with poor signal. Summary of the Invention

[0005] Therefore, it is necessary to provide a vehicle intelligent fault-tolerant optimization method, device, computer equipment, computer-readable storage medium, and computer program product based on a preset time to address the above-mentioned technical problems and reduce the communication quality requirements between the vehicle and the cloud.

[0006] Firstly, this application provides a vehicle intelligent fault-tolerant optimization method based on a preset time, the method comprising: Obtain environmental parameters and input them into the local model preset on the vehicle to obtain the first control command generated by the vehicle model; Upload environmental parameters to the cloud so that the cloud can input the environmental parameters into the cloud model preset in the cloud and obtain the second control command; Wait for and obtain the receiving timestamp of the complete receiving environment parameters from the cloud, and determine whether the timetamp between the event corresponding to the completed receiving timestamp and the timetamp of the uploaded environment parameters is greater than a preset time threshold. If so, then lower the priority of the second driving command fed back from the cloud; If not, then increase the priority of the second driving command fed back from the cloud; Acquire third control commands obtained from the vehicle's hardware; Compare the priorities of the first, second, and third control instructions, and select the one with the highest priority as the actual control instruction and output it.

[0007] In one embodiment, the specific steps for waiting for and obtaining the complete acceptance timestamp of the environment parameters from the cloud, and determining whether the timetamp between the event corresponding to the completion acceptance timestamp and the timetamp of uploading the environment parameters is greater than a preset time threshold include: Obtain the timestamp of the environmental parameters uploaded to the cloud, with the timestamp accurate to at least the microsecond level; Wait for and obtain the received timestamp, which is at least accurate to the microsecond level; Calculate the timestamp difference between the sending timestamp and the receiving timestamp, and determine whether the timestamp difference is greater than a preset time threshold; If so, then lower the priority of the second driving instruction; If not, then increase the priority of the second driving instruction.

[0008] In one embodiment, the receiving timestamp is the time when the complete environmental parameters are obtained from the cloud, and the method for determining the receiving time specifically includes: The cloud records the timestamp information of the received environmental parameters; Verify the integrity of the environmental parameters. If the environmental parameters pass the integrity verification, use the timestamp information as the receiving time and send it to the vehicle.

[0009] In one embodiment, priority levels are represented by numerical values, with higher values ​​indicating higher priority. The first, second, and third control commands all have preset priority levels. The priority level of the first control command is set to 3, the second control command to 4, and the third control command to 1. The specific steps for lowering the priority of the second driving command include: Determine if the current priority of the second driving instruction is less than 3; If so, then the priority level of the second control command remains unchanged; If not, halve the priority of the second control command; The specific steps for raising the priority of a second driving instruction include: Determine if the current priority of the second driving instruction is greater than 3; If so, then the priority level of the second control command remains unchanged; If not, double the priority of the second control command.

[0010] In one embodiment, the specific steps of comparing the priorities of the first control instruction, the second control instruction, and the third control instruction, and obtaining the one with the highest priority as the actual control instruction and outputting it include: Determine whether the specific instruction content of the first control instruction and the second control instruction matches at the current moment; If so, the first control command will be used as the actual control command and output. If not, the priorities of the first, second, and third control instructions will be read, and the control instruction with the highest priority value will be selected as the actual control instruction and output.

[0011] In one embodiment, the vehicle intelligent fault-tolerant optimization method based on a preset time further includes: waiting for and obtaining the execution result of the actual control command, and determining whether an accident has occurred; If not, then determine whether the actual control instruction is the first control instruction; If not, the actual control commands and environmental parameters will be used as positive training samples, and the positive training samples will be input into the cloud model to complete the cloud model training.

[0012] Secondly, this application also provides a vehicle intelligent fault-tolerant optimization system based on a preset time, the system comprising: The environmental parameter acquisition module, including an image sensor and millimeter-wave radar, is used to collect environmental parameters; The vehicle-side control module is used to store and run the local model to generate the first control command based on environmental parameters; The cloud control module is used to store and run cloud models to generate second control commands based on environmental parameters; A communication module is installed in both the vehicle-side control module and the cloud-side control module to enable data and information exchange between them. The hardware control module is used to generate third control commands based on the specific actions of the passengers in operating the in-vehicle hardware. The instruction fusion module compares the priorities of the first control instruction, the second control instruction, and the third control instruction, and selects the one with the highest priority as the actual control instruction and outputs it.

[0013] Thirdly, this application also provides a computer device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to perform the following steps: Obtain environmental parameters and input them into the local model preset on the vehicle to obtain the first control command generated by the vehicle model; Upload environmental parameters to the cloud so that the cloud can input the environmental parameters into the cloud model preset in the cloud and obtain the second control command; Wait for and obtain the receiving timestamp of the complete receiving environment parameters from the cloud, and determine whether the timetamp between the event corresponding to the completed receiving timestamp and the timetamp of the uploaded environment parameters is greater than a preset time threshold. If so, then lower the priority of the second driving command fed back from the cloud; If not, then increase the priority of the second driving command fed back from the cloud; Acquire third control commands obtained from the vehicle's hardware; Compare the priorities of the first control instruction, the second control instruction, and the third control instruction, and select the one with the highest priority as the actual control instruction and output it. Wait for and obtain the execution results of the actual control commands to determine whether an accident has occurred; If not, then determine whether the actual control instruction is the first control instruction; If not, the actual control commands and environmental parameters will be used as positive training samples, and the positive training samples will be input into the cloud model to complete the cloud model training.

[0014] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps: Obtain environmental parameters and input them into the local model preset on the vehicle to obtain the first control command generated by the vehicle model; Upload environmental parameters to the cloud so that the cloud can input the environmental parameters into the cloud model preset in the cloud and obtain the second control command; Wait for and obtain the receiving timestamp of the complete receiving environment parameters from the cloud, and determine whether the timetamp between the event corresponding to the completed receiving timestamp and the timetamp of the uploaded environment parameters is greater than a preset time threshold. If so, then lower the priority of the second driving command fed back from the cloud; If not, then increase the priority of the second driving command fed back from the cloud; Acquire third control commands obtained from the vehicle's hardware; Compare the priorities of the first control instruction, the second control instruction, and the third control instruction, and select the one with the highest priority as the actual control instruction and output it. Wait for and obtain the execution results of the actual control commands to determine whether an accident has occurred; If not, then determine whether the actual control instruction is the first control instruction; If not, the actual control commands and environmental parameters will be used as positive training samples, and the positive training samples will be input into the cloud model to complete the cloud model training.

[0015] Fifthly, this application also provides a computer program product comprising a computer program that, when executed by a processor, performs the following steps: Obtain environmental parameters and input them into the local model preset on the vehicle to obtain the first control command generated by the vehicle model; Upload environmental parameters to the cloud so that the cloud can input the environmental parameters into the cloud model preset in the cloud and obtain the second control command; Wait for and obtain the receiving timestamp of the complete receiving environment parameters from the cloud, and determine whether the timetamp between the event corresponding to the completed receiving timestamp and the timetamp of the uploaded environment parameters is greater than a preset time threshold. If so, then lower the priority of the second driving command fed back from the cloud; If not, then increase the priority of the second driving command fed back from the cloud; Acquire third control commands obtained from the vehicle's hardware; Compare the priorities of the first control instruction, the second control instruction, and the third control instruction, and select the one with the highest priority as the actual control instruction and output it. Wait for and obtain the execution results of the actual control commands to determine whether an accident has occurred; If not, then determine whether the actual control instruction is the first control instruction; If not, the actual control commands and environmental parameters will be used as positive training samples, and the positive training samples will be input into the cloud model to complete the cloud model training.

[0016] The aforementioned vehicle intelligent fault-tolerant optimization method, system, computer equipment, storage medium, and computer program product based on preset time, by setting up an instruction fusion module, selectively receives the first, second, and third control instructions obtained in the actual scenario. When communication signals are blocked, the priority of the second control instruction is reduced, so that the vehicle can rely on the first or third control instructions generated locally to achieve smooth operation, thereby reducing the requirements of autonomous vehicles on signal conditions in the driving environment. Attached Figure Description

[0017] Figure 1 This is a structural topology diagram of a vehicle intelligent fault-tolerant optimization system based on a preset time in one embodiment; Figure 2 This is a system architecture diagram of a vehicle intelligent fault-tolerant optimization system based on a preset time in one embodiment; Figure 3 This is a flowchart illustrating a vehicle intelligent fault-tolerant optimization method based on a preset time in one embodiment; Figure 4 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0019] In one embodiment, such as Figure 1 As shown, a vehicle intelligent fault-tolerant optimization system based on a preset time is provided. The hardware control module includes: an environmental parameter acquisition module, a vehicle-side control module, a cloud-based control module, a communication module, a hardware control module, and an instruction fusion module, wherein: The environmental parameter acquisition module is used to collect environmental parameters. Specifically, it includes various sensor and / or map data for collecting road surface environment data. Taking sensors as an example, the environmental parameter acquisition module includes, but is not limited to, image sensors and millimeter-wave radar. The vehicle-side control module is used to store and run the local model to generate the first control command based on environmental parameters. Specifically, the vehicle-side control module may include a local intelligent driving chip installed on the vehicle, peripheral circuits, and a local model installed thereon. It is used to generate local intelligent driving commands, i.e., the first control command, based on environmental parameters. The cloud control module is used to store and run the cloud model to generate second control commands based on environmental parameters. Specifically, the cloud control module may include a cloud server computing unit, a processor or server, and a cloud model installed on it. The cloud model is more complex than the local model, and the second control command it generates contains more predictions of road conditions and corresponding strategies compared to the first control command. In terms of time alone, the duration of the second control command is longer than that of the first control command. A communication module is installed in both the vehicle-side control module and the cloud-side control module to enable data and information exchange between them. Specifically, in this embodiment, the communication module uses 5G or other low-latency wireless communication protocols. The hardware control module is used to generate third control commands based on the specific actions of the driver and passengers in operating the in-vehicle hardware. Specifically, the in-vehicle hardware includes, but is not limited to, hardware devices such as the steering wheel, brake pedal, accelerator pedal, and gear lever that allow the driver to control the vehicle's driving status. The instruction fusion module compares the priorities of the first control instruction, the second control instruction, and the third control instruction, and selects the one with the highest priority as the actual control instruction and outputs it.

[0020] In this embodiment, the hardware control module, including the steering wheel, brake pedal, accelerator pedal, and gear lever, is decoupled from its corresponding steering, braking, and power systems and connected through the command fusion module. That is, during vehicle operation, if intelligent driving or autonomous driving mode is activated, the vehicle's driving state is controlled by the command fusion module through the selective execution of the first, second, and third control commands, thereby achieving autonomous driving or human-vehicle co-driving. When human-driving mode is activated, the command fusion module primarily executes the third control command. The vehicle acquires environmental parameters of the road environment through the environmental parameter acquisition module to determine whether a sudden event has occurred during driving. If a sudden event occurs, the first control command is output to successfully trigger functions such as AEB and ABS, thereby ensuring vehicle driving safety.

[0021] Based on the same inventive concept, this application also provides a preset-time vehicle intelligent fault-tolerant optimization method for implementing the preset-time vehicle intelligent fault-tolerant optimization system described above. The solution provided by this method is similar to the implementation described in the above method. Therefore, the specific limitations in one or more preset-time vehicle intelligent fault-tolerant optimization method embodiments provided below can be found in the limitations of the preset-time vehicle intelligent fault-tolerant optimization system described above, and will not be repeated here.

[0022] In one embodiment, such as Figure 2 As shown, a vehicle intelligent fault-tolerant optimization method based on a preset time is provided, including the following steps: Step S100: Obtain environmental parameters and input the environmental parameters into the local model preset on the vehicle to obtain the first control command generated by the vehicle model.

[0023] Among them, the environmental parameters are various types of environmental information acquired by the environmental parameter acquisition module, including but not limited to road condition image data acquired by image sensors, environmental point cloud data acquired by millimeter-wave radar, vehicle distance or distance data acquired by ultrasonic sensors and / or infrared sensors, location information acquired by GPS modules or Beidou positioning modules, and map data. By inputting some or all of the above environmental parameters into the vehicle-side model, the first control command can be obtained. The first control command is generated in real time by the local model on the vehicle side and output to the command fusion module.

[0024] Step S200: Upload the environmental parameters to the cloud so that the cloud can input the environmental parameters into the cloud model preset in the cloud and obtain the second control command.

[0025] The second control command contains more predictions about road conditions and corresponding strategies compared to the first control command. In terms of time, the second control command is longer than the first control command. In a preferred embodiment, the two second control commands generated successively have overlapping time periods. When the communication signal is blocked during vehicle operation, affecting the successful reception of subsequent second control commands, the previous second control command is used as the current second control command to be referenced. If the communication signal is not blocked and the new second control command is successfully received by the command fusion module, the latest received second control command is used as the current second control command to be referenced.

[0026] Step S300: Wait for and obtain the receiving timestamp of the complete receiving environment parameters from the cloud, and determine whether the timetamp between the event corresponding to the completion of the receiving timestamp and the timetamp of the uploaded environment parameters is greater than the preset time threshold.

[0027] The preset time threshold is used as a criterion for judging whether the communication between the cloud and the vehicle is smooth and whether the delay is too large. In a specific embodiment, the specific steps of step S300 include: Step S310: Obtain the sending timestamp when the environmental parameters are uploaded to the cloud. The sending timestamp should be accurate to at least the microsecond level.

[0028] Step S320: Wait for and obtain the received timestamp, which is at least accurate to the microsecond level.

[0029] The receiving timestamp represents the time when the complete environmental parameters are obtained from the cloud. The specific methods for determining the receiving time include: Step S321: The cloud records the timestamp information of the received environmental parameters; Step S322: Verify the integrity of the environmental parameters. If the environmental parameters pass the integrity verification, the timestamp information is used as the receiving time and sent to the vehicle terminal.

[0030] Through steps S321 and S322, the timestamp information of the received environmental parameters is first stored, and then its integrity is verified. After the data integrity verification is passed, the temporarily stored timestamp information is used as the received information. Since the time occupied by the data integrity verification is not included, a more accurate data transmission time can be calculated.

[0031] Step S330: Calculate the timestamp difference between the sending timestamp and the receiving timestamp, and determine whether the timestamp difference is greater than a preset time threshold.

[0032] Step S410: If so, reduce the priority of the second driving command fed back from the cloud; Step S420: If not, increase the priority of the second driving command fed back from the cloud.

[0033] In one embodiment, priority levels are all represented by numerical values. The larger the numerical value representing the priority level, the higher the priority level. The first control instruction, the second control instruction, and the third control instruction all have preset priority levels. The priority level of the first control instruction is set to 3, the priority level of the second control instruction is set to 4, and the priority level of the third control instruction is set to 1. The specific steps of step S410 include: Step S411: Determine whether the current priority of the second driving instruction is less than 3; Step S412: If yes, then keep the priority level of the second control instruction unchanged; Step S413: If not, halve the priority of the second control command.

[0034] Similarly, the specific steps of step S420 include: Step S421: Determine whether the current priority of the second driving instruction is greater than 3; Step S422: If yes, then keep the priority level of the second control instruction unchanged; Step S423: If not, double the priority of the second control command.

[0035] The purpose of setting the first, second, and third control commands as described above is that, during vehicle operation, both the vehicle-side control module and the hardware control module are capable of making decisions based on real-time road conditions and generating corresponding first and third control commands. However, the delivery of the second control command from the cloud control module is affected by many factors, such as the stability of the communication signal and the timely generation of the second control command by the cloud computing power, thus affecting the timeliness of the second control command. Therefore, it is necessary to flexibly adjust the execution priority of the second control command according to the actual situation during driving to ensure vehicle safety. It is precisely because of the need to adjust the priority of the second control command in real time that the values ​​of the first and third control commands are set as fixed quantities, while the second control command is set as a variable. The numerical relationship between the first, second, and third control commands can be adjusted through simple mathematical operations. The specific priority values ​​given in this embodiment, such as 1, 2, 3, and 4, are only used to clearly illustrate the meaning of steps S410 and S420 and are not intended to limit the scope of protection of this application.

[0036] Step S500: Obtain the third control command obtained from the vehicle hardware.

[0037] The third control command is generated by the driver's specific actions through in-vehicle hardware. In-vehicle hardware includes, but is not limited to, hardware devices such as the steering wheel, brake pedal, accelerator pedal, and gear lever that allow the driver to control the vehicle's driving status. The corresponding third control command corresponds to the driver's actions such as pressing or releasing the brake pedal, accelerator pedal, or turning the steering wheel, controlling the vehicle's acceleration, deceleration, and steering wheel rotation. The third control command differs from the first and second control commands in that the first and second control commands are control commands generated by the autonomous driving model to control the vehicle to execute at a specific time in the next period of time, and they have a certain predictive or pre-input nature. However, the third control command is an immediate command, that is, the command fusion module receives the third control command corresponding to the driver's operation as soon as the driver actively controls the vehicle.

[0038] Step S600: Compare the priorities of the first control instruction, the second control instruction, and the third control instruction, and obtain the one with the highest priority as the actual control instruction and output it.

[0039] The specific steps of step S600 include: Step S610: Determine whether the specific instruction content of the first control instruction and the second control instruction at the current moment matches.

[0040] Step S620: If yes, then the first control instruction is used as the actual control instruction and output.

[0041] Step S630: If not, the priorities of the first control instruction, the second control instruction, and the third control instruction will be read, and the control instruction with the highest priority value will be obtained as the actual control instruction and output.

[0042] Step S700: Wait for and obtain the execution result of the actual control command, and determine whether an accident has occurred; Step S810: If not, determine whether the actual control instruction is the first control instruction; Step S820: If not, use the actual control commands and environmental parameters as training positive samples, and input the training positive samples into the cloud model to complete the cloud model training.

[0043] Through steps S700 to S820, the correct decisions made by the vehicle-side control module can be summarized and output to the cloud for cloud model iteration, thereby completing the model reinforcement training and realizing the function of cloud model self-iteration.

[0044] However, 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, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0045] In another optional embodiment, the user can select an autonomous driving mode (or a human-vehicle co-driving mode) or a driver-active driving mode when starting or driving the vehicle. When the autonomous driving mode (or human-vehicle co-driving mode) is activated, the vehicle executes steps S100 to S820 to achieve human-vehicle co-driving. When the driver-active driving mode is activated, the vehicle stops sending sensor data to the cloud, but the vehicle still acquires sensor and map data in real time. However, it only outputs a second control command to deal with the emergency when a sudden situation occurs (such as a vehicle slowing down or stopping on a highway, or a pedestrian appearing at an intersection when driving to an intersection). After receiving the second control command, the command fusion module executes the second control command first because the preset priority of the second control command is higher than the preset priority of the third control command, thereby ensuring that functions such as AEB are successfully triggered and thus dealing with the emergency.

[0046] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0047] The modules in the aforementioned vehicle intelligent fault-tolerant optimization system based on a preset time can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0048] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 4 As shown, the computer device includes a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a vehicle intelligent fault-tolerant optimization method based on a preset time. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, or external buttons, a trackball, or a touchpad.

[0049] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0050] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps: Step S100: Obtain environmental parameters and input the environmental parameters into the local model preset on the vehicle to obtain the first control command generated by the vehicle model; Step S200: Upload the environmental parameters to the cloud so that the cloud can input the environmental parameters into the cloud model preset in the cloud and obtain the second control command; Step S300: Wait for and obtain the receiving timestamp of the complete receiving environment parameters from the cloud, and determine whether the timetamp between the event corresponding to the completion of the receiving timestamp and the timetamp of the uploaded environment parameters is greater than the preset time threshold. Step S410: If so, reduce the priority of the second driving command fed back from the cloud; Step S420: If not, increase the priority of the second driving command fed back from the cloud; Step S500: Obtain a third control command representing the information obtained from the vehicle's hardware; Step S600: Compare the priorities of the first control instruction, the second control instruction, and the third control instruction, and obtain the one with the highest priority as the actual control instruction and output it; Step S700: Wait for and obtain the execution result of the actual control command, and determine whether an accident has occurred; Step S810: If not, determine whether the actual control instruction is the first control instruction; Step S820: If not, use the actual control commands and environmental parameters as training positive samples, and input the training positive samples into the cloud model to complete the cloud model training.

[0051] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor: Step S100: Obtain environmental parameters and input the environmental parameters into the local model preset on the vehicle to obtain the first control command generated by the vehicle model; Step S200: Upload the environmental parameters to the cloud so that the cloud can input the environmental parameters into the cloud model preset in the cloud and obtain the second control command; Step S300: Wait for and obtain the receiving timestamp of the complete receiving environment parameters from the cloud, and determine whether the timetamp between the event corresponding to the completion of the receiving timestamp and the timetamp of the uploaded environment parameters is greater than the preset time threshold. Step S410: If so, reduce the priority of the second driving command fed back from the cloud; Step S420: If not, increase the priority of the second driving command fed back from the cloud; Step S500: Obtain a third control command representing the information obtained from the vehicle's hardware; Step S600: Compare the priorities of the first control instruction, the second control instruction, and the third control instruction, and obtain the one with the highest priority as the actual control instruction and output it; Step S700: Wait for and obtain the execution result of the actual control command, and determine whether an accident has occurred; Step S810: If not, determine whether the actual control instruction is the first control instruction; Step S820: If not, use the actual control commands and environmental parameters as training positive samples, and input the training positive samples into the cloud model to complete the cloud model training.

[0052] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps: Step S100: Obtain environmental parameters and input the environmental parameters into the local model preset on the vehicle to obtain the first control command generated by the vehicle model; Step S200: Upload the environmental parameters to the cloud so that the cloud can input the environmental parameters into the cloud model preset in the cloud and obtain the second control command; Step S300: Wait for and obtain the receiving timestamp of the complete receiving environment parameters from the cloud, and determine whether the timetamp between the event corresponding to the completion of the receiving timestamp and the timetamp of the uploaded environment parameters is greater than the preset time threshold. Step S410: If so, reduce the priority of the second driving command fed back from the cloud; Step S420: If not, increase the priority of the second driving command fed back from the cloud; Step S500: Obtain a third control command representing the information obtained from the vehicle's hardware; Step S600: Compare the priorities of the first control instruction, the second control instruction, and the third control instruction, and obtain the one with the highest priority as the actual control instruction and output it; Step S700: Wait for and obtain the execution result of the actual control command, and determine whether an accident has occurred; Step S810: If not, determine whether the actual control instruction is the first control instruction; Step S820: If not, use the actual control commands and environmental parameters as training positive samples, and input the training positive samples into the cloud model to complete the cloud model training.

[0053] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile 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. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0054] The technical features of the above embodiments can be combined in any way. For the sake of brevity, 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 specification.

[0055] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A vehicle intelligent fault-tolerant optimization method based on a preset time, characterized in that, include: Obtain environmental parameters and input the environmental parameters into a local model preset on the vehicle to obtain the first control command generated by the vehicle model; The environmental parameters are uploaded to the cloud so that the cloud can input the environmental parameters into a cloud model preset in the cloud and obtain a second control command; Wait for and obtain the receiving timestamp of the complete receiving environment parameters from the cloud, and determine whether the timetamp between the event corresponding to the completion receiving timestamp and the timetamp of uploading the environment parameters is greater than a preset time threshold; If so, then lower the priority of the second driving command fed back from the cloud; If not, then increase the priority of the second driving command fed back from the cloud; Acquire third control commands obtained from the vehicle's hardware; The priorities of the first control instruction, the second control instruction, and the third control instruction are compared, and the one with the highest priority is selected as the actual control instruction and output.

2. The vehicle intelligent fault-tolerant optimization method based on a preset time according to claim 1, characterized in that, The specific steps for waiting for and obtaining the complete acceptance timestamp of the environment parameters from the cloud, and determining whether the timetamp between the event corresponding to the completion acceptance timestamp and the timetamp of uploading the environment parameters is greater than a preset time threshold, include: The timestamp of the environmental parameters being uploaded to the cloud is obtained, and the timestamp is accurate to at least the microsecond level. Wait for and obtain the received timestamp, which is at least accurate to the microsecond level; Calculate the timestamp difference between the sending timestamp and the receiving timestamp, and determine whether the timestamp difference is greater than the preset time threshold; If so, then lower the priority of the second driving command; If not, then increase the priority of the second driving instruction.

3. The vehicle intelligent fault-tolerant optimization method based on a preset time according to claim 2, characterized in that, The received timestamp is the time when the complete environmental parameters are obtained from the cloud, and the method for determining the received time specifically includes: The cloud records the timestamp information of the received environmental parameters; The integrity of the environmental parameters is verified. If the environmental parameters pass the integrity verification, the timestamp information is used as the receiving time and sent to the vehicle.

4. The vehicle intelligent fault-tolerant optimization method based on a preset time according to claim 2, characterized in that, The priority levels are all represented by numerical values, with higher values ​​indicating higher priority levels. The first, second, and third control commands each have preset priority levels. The priority level of the first control command is set to 3, the priority level of the second control command is set to 4, and the priority level of the third control command is set to 1. The specific steps for lowering the priority of the second driving command include: Determine whether the current priority of the second driving instruction is less than 3; If so, then the priority level of the second control command remains unchanged; If not, halve the priority of the second control command; The specific steps for raising the priority of the second driving instruction include: Determine whether the current priority of the second driving instruction is greater than 3; If so, then the priority level of the second control command remains unchanged; If not, double the priority of the second control command.

5. The vehicle intelligent fault-tolerant optimization method based on a preset time according to claim 3, characterized in that, The specific steps of comparing the priorities of the first control command, the second control command, and the third control command, and obtaining the highest priority one as the actual control command and outputting it include: Determine whether the specific instruction content of the first control instruction and the second control instruction at the current moment matches; If so, the first control instruction will be used as the actual control instruction and output. If not, the priorities of the first control instruction, the second control instruction, and the third control instruction will be read, and the control instruction with the highest priority value will be selected as the actual control instruction and output.

6. The vehicle intelligent fault-tolerant optimization method based on a preset time according to any one of claims 1-5, characterized in that... It also includes: waiting for and obtaining the execution result of the actual control command to determine whether an accident has occurred; If not, then determine whether the actual control instruction is the first control instruction; If not, the actual control command and the environmental parameters are used as positive training samples, and the positive training samples are input into the cloud model to complete the training of the cloud model.

7. A vehicle intelligent fault-tolerant optimization system based on a preset time, characterized in that... include: The environmental parameter acquisition module, including an image sensor and millimeter-wave radar, is used to collect environmental parameters; The vehicle-side control module is used to store and run the local model to generate the first control command based on environmental parameters; The cloud control module is used to store and run cloud models to generate second control commands based on environmental parameters; A communication module is provided in the vehicle-side control module and the cloud-side control module to realize data and information exchange between the vehicle-side control module and the cloud-side control module; The hardware control module is used to generate third control commands based on the specific actions of the passengers in operating the in-vehicle hardware. The instruction fusion module compares the priorities of the first control instruction, the second control instruction, and the third control instruction, and obtains the one with the highest priority as the actual control instruction and outputs it.

8. 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, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images