Vehicle control system and vehicle control method

Abstract

The vehicle control system of the present application is provided with a sensor section, a vehicle control device having a vehicle control application, and a server. In the vehicle control device, difference data between a vehicle behavior prediction value and an actual vehicle behavior value calculated based on a sensor value is calculated, in the case where the difference data is large, upload data is uploaded to the server, and the vehicle control application and the vehicle model are updated to information distributed from the server. In the server, the vehicle model is improved based on the upload data so that the vehicle behavior prediction value approaches the actual vehicle behavior value, and the vehicle control application is developed based on the upload data, and the improved vehicle model and the developed vehicle control application are distributed to the vehicle control device.

Description

Technical Field

[0001] This invention relates to vehicle control systems and vehicle control methods. Background Technology

[0002] In recent years, the increasing sophistication of advanced driver assistance systems and the introduction of autonomous driving have led to the advancement of automotive intelligence, with vehicles being controlled by software. Patent document 1 discloses a technology for updating the software used to control a vehicle.

[0003] Patent Document 1 describes a software update system comprising: a vehicle data acquisition unit that acquires data about the vehicle's state, including data about a specified performance of the vehicle; an effect prediction unit that, based on the data acquired by the vehicle data acquisition unit, predicts the effect that can be obtained when software update data used in the vehicle to improve the specified performance is applied to the vehicle; and a distribution unit that distributes the update data to the vehicle if the effect predicted by the effect prediction unit meets a specified standard, and suspends the distribution of the update data to the vehicle if the effect predicted by the effect prediction unit does not meet the specified standard.

[0004] Existing technical documents

[0005] Patent documents

[0006] Patent Document 1: Japanese Patent Application Publication No. 2023-43528 Summary of the Invention

[0007] The problem the invention aims to solve

[0008] In the prior art described in the aforementioned Patent Document 1, since it is configured to upload data according to a request from the vehicle data acquisition unit, it is possible to upload data that is not originally needed and is therefore useless.

[0009] The present invention was made in view of the following situation, and its object is to provide a vehicle control system and a vehicle control method that can avoid uploading useless data by collecting and uploading only the data of the parts that really need improvement.

[0010] Problem-solving methods

[0011] The vehicle control system of the present invention, which solves the above-mentioned problems, comprises: a sensor unit that collects vehicle information; a vehicle control device that calculates control command values ​​based on sensor values ​​from the sensor unit and predicted values ​​from a vehicle model; and a server. Furthermore, the vehicle control device comprises: a vehicle behavior prediction unit that calculates predicted vehicle behavior values ​​from environmental information calculated based on control command values ​​and sensor values, and predicted values ​​from a vehicle model; a comparison unit that calculates differential data by comparing the predicted vehicle behavior values ​​with actual vehicle behavior values ​​based on sensor values; an upload judgment unit that uploads upload data including the vehicle model, sensor values, control command values, and actual vehicle behavior values ​​to the server if the differential data is greater than a predetermined threshold; and a vehicle software update unit that updates the vehicle control application and vehicle model to the vehicle control application and vehicle model distributed from the server. In addition, the server includes: a vehicle model improvement department, which improves the vehicle model based on uploaded data so that the predicted vehicle behavior value is close to the actual vehicle behavior value; a vehicle control application development and verification department, which develops the vehicle control application for the vehicle control device based on uploaded data; and a vehicle software distribution department, which distributes the improved vehicle model and the developed vehicle control application to the vehicle control device.

[0012] Furthermore, the vehicle control method of the present invention, used to solve the above-mentioned problems, is applied in a vehicle control system comprising: a sensor unit that collects vehicle information; a vehicle control device having a vehicle control application that calculates control command values ​​based on sensor values ​​from the sensor unit and predicted values ​​from a vehicle model; and a server. In the vehicle control device, the following steps are performed: calculating a vehicle behavior prediction value from environmental information calculated based on control command values ​​and sensor values, and a predicted value from a vehicle model; calculating differential data by comparing the predicted vehicle behavior value with actual vehicle behavior values ​​based on sensor values; uploading uploaded data including the vehicle model, sensor values, control command values, and actual vehicle behavior values ​​to the server if the differential data is larger than a predetermined threshold; and updating the vehicle control application and vehicle model to vehicle control applications and vehicle models distributed from the server. In the server, the following processes are performed: improving the vehicle model based on the uploaded data to make the predicted vehicle behavior value closer to the actual vehicle behavior value; developing a vehicle control application for the vehicle control device based on the uploaded data; and distributing the improved vehicle model and the developed vehicle control application to the vehicle control device.

[0013] Invention Effects

[0014] According to the present invention, by uploading data based on the difference between the information of the sensor unit that collects information about the vehicle and the information of the vehicle model, it is possible to collect and upload only the data of the parts that truly need improvement, thus avoiding useless uploading.

[0015] Other problems, structures, and effects not described above will become clear through the following description of the manner in which the invention is carried out (hereinafter referred to as the implementation method). Attached Figure Description

[0016] Figure 1 This is a block diagram illustrating an overall configuration example of a vehicle control system according to one embodiment of the present invention.

[0017] Figure 2 This is a block diagram used to explain the functions of each functional unit and each program in a vehicle control system according to one embodiment of the present invention.

[0018] Figure 3 This is a flowchart illustrating an example of the processing of a vehicle behavior prediction unit in a vehicle control system according to an embodiment of the present invention.

[0019] Figure 4 This is a flowchart illustrating an example of the processing of a vehicle control application in a vehicle control system according to an embodiment of the present invention.

[0020] Figure 5 This is a flowchart illustrating an example of the processing of a comparison unit in a vehicle control system according to an embodiment of the present invention.

[0021] Figure 6 This is a flowchart illustrating an example of the processing of an upload determination unit in a vehicle control system according to an embodiment of the present invention.

[0022] Figure 7 This is a flowchart illustrating an example of the processing of a vehicle software update unit in a vehicle control system according to an embodiment of the present invention.

[0023] Figure 8 This is a flowchart illustrating an example of the processing of a vehicle model improvement unit in a vehicle control system according to an embodiment of the present invention.

[0024] Figure 9 This is a flowchart illustrating an example of the specific processing of a vehicle model improvement unit in a vehicle control system according to an embodiment of the present invention.

[0025] Figure 10 This is a flowchart illustrating an example of the processing of a vehicle control application development and verification unit in a vehicle control system according to an embodiment of the present invention.

[0026] Figure 11 This is a flowchart illustrating an example of a specific process in the vehicle control application development and verification unit of a vehicle control system according to an embodiment of the present invention.

[0027] Figure 12 This is a flowchart illustrating an example of the processing of a vehicle software distribution unit in a vehicle control system according to an embodiment of the present invention. Detailed Implementation

[0028] Hereinafter, the embodiments (methods) for carrying out the invention will be described with reference to the accompanying drawings. In this specification and the drawings, constituent elements having substantially the same function or structure are given the same reference numerals, and repeated descriptions are omitted.

[0029] <One embodiment of the present invention>

[0030] [System Configuration Example]

[0031] Figure 1 This is a block diagram illustrating an overall configuration example of a vehicle control system according to one embodiment of the present invention. The vehicle control system 1 according to this embodiment is configured to include an ECU (Electronic Control Unit) 10, a server 20, a sensor unit 30, and other ECUs 40, which are examples of vehicle control devices.

[0032] ECU 10 is a system installed in vehicles such as automobiles, and it connects to server 20, sensor unit 30, and other ECUs 40, enabling communication via a network. Server 20 resides in the cloud and operates collaboratively with ECU 10 installed in the vehicle. Sensor unit 30 includes one or more sensors, such as Radar, LiDAR, camera, and gyroscope sensors, used to collect vehicle information. Sensor unit 30 outputs status information from various sensors to ECU 10. Other ECUs 40 are ECUs that include one or more actuators for operating accelerators, brakes, steering systems, etc. Other ECUs 40 control the vehicle based on input control information from ECU 10.

[0033] [ECU (Vehicle Control Unit)]

[0034] As an example of a vehicle control device, the ECU 10 includes a memory 11 and a CPU 12. The memory 11 is, for example, RAM (Random Access Memory), SSD (Solid State Drive), or HDD (Hard Disk Drive), and stores the program and necessary information executed by the CPU 12. The CPU 12 includes a CPU (Central Processing Unit) and an accelerator, and executes various processes according to the program stored in the memory 11.

[0035] (Memory)

[0036] The memory 11 stores sensor values ​​110, vehicle model 111, environmental information 112, control command values ​​113, differential data 114, vehicle behavior prediction values ​​115, actual vehicle behavior values ​​116, vehicle behavior prediction unit 117, vehicle control application 118, comparison unit 119, upload judgment unit 120, and vehicle software update unit 121.

[0037] Sensor values ​​110, environmental information 112, control command values ​​113, differential data 114, vehicle behavior prediction values ​​115, and actual vehicle behavior values ​​116 are time-series data, maintaining data for a certain period that includes the latest values.

[0038] The vehicle model 111, vehicle behavior prediction unit 117, vehicle control application 118, comparison unit 119, upload judgment unit 120, and vehicle software update unit 121 are programs.

[0039] The functions of the vehicle behavior prediction unit 117, the vehicle control application 118, the comparison unit 119, the upload judgment unit 120, and the vehicle software update unit 121 will be described later.

[0040] Furthermore, in the following description, for convenience, the program is sometimes described as the subject of the action, but the actual subject of execution is the CPU12 that executes the program.

[0041] [server]

[0042] Server 20 includes memory 21 and CPU 22. Memory 21, such as RAM, SSD, or HDD, stores programs and necessary information executed by CPU 22. CPU 22 performs various processes according to the programs stored in memory 21.

[0043] (Memory)

[0044] The memory 21 stores the programs for the vehicle model storage unit 211, the data upload unit 212, the vehicle model improvement unit 213, the vehicle control application development and verification unit 214, and the vehicle software distribution unit 215. The functions of each program will be described later.

[0045] Furthermore, in the following description, for convenience, the program is sometimes described as the subject of the action, but the actual subject of execution is the CPU22 that executes the program.

[0046] [Regarding the functions of each functional department and program]

[0047] Figure 2 This is a block diagram used to explain the functions of each functional unit and each program in a vehicle control system according to one embodiment of the present invention.

[0048] (ECU)

[0049] In ECU 10, vehicle control application 118 calculates control command value 113 based on sensor value 110 from sensor unit 30 and predicted value from vehicle model 111. Here, control command value refers to information such as throttle opening and steering input.

[0050] The vehicle behavior prediction unit 117 calculates a vehicle behavior prediction value 115 based on environmental information calculated from control command values ​​and sensor values ​​110 in the vehicle control application 118, as well as prediction values ​​from the vehicle model 111. Here, environmental information includes, for example, information about the state of the road surface.

[0051] The comparison unit 119 compares the predicted vehicle behavior value 115 and the actual vehicle behavior value 116, and uses the calculated difference between the two as the difference data 114. Here, the predicted vehicle behavior value is, for example, the value of the main vehicle's position information, speed, etc. The actual vehicle behavior value 116 is the value calculated based on the sensor value 110 of the sensor unit 30.

[0052] If the difference data 114 between the predicted vehicle behavior value 115 and the actual vehicle behavior value 116 is greater than a specified threshold, the upload judgment unit 120 determines that it needs to be uploaded and uploads the upload data containing the vehicle model 111, sensor value 110, control command value 113 and actual vehicle behavior value 116 to the server 20.

[0053] The vehicle software update unit 121 updates the vehicle control application 118 and the vehicle model 111 to the vehicle control application and vehicle model distributed from the server 20.

[0054] (server)

[0055] In the memory 21 of the server 20, the vehicle model improvement unit 213 updates the vehicle model 111 based on the uploaded data 212 from the ECU 10 so that the vehicle behavior prediction value 115 is close to the actual vehicle behavior value 116.

[0056] The vehicle control application development and verification unit 214 updates the vehicle control application 118 based on the uploaded data 212 from the ECU 10.

[0057] The vehicle software distribution unit 215 distributes the improved vehicle model (improved vehicle model) in the vehicle model improvement unit 213 and the developed vehicle control application (developed vehicle model) in the vehicle control application development and verification unit 214 to the ECU 10.

[0058] [Processing Examples for Each Functional Department]

[0059] Next, processing examples of each functional unit in the ECU10, including the vehicle behavior prediction unit 117, vehicle control application 118, comparison unit 119, upload judgment unit 120, and vehicle software update unit 121, as well as processing examples of each functional unit in the server 20, including the vehicle model improvement unit 213, vehicle control application development and verification unit 214, and vehicle software distribution unit 215, will be explained.

[0060] (Processing example from the vehicle behavior prediction department)

[0061] The processing of the vehicle behavior prediction unit 117 is, for example, the process of calculating where the vehicle will move to in the next moment based on the control command value of the autonomous driving control application. This function is achieved by the vehicle behavior prediction unit 117 executing the function under the control of the CPU 12 of the ECU 10. Figure 3 This is a flowchart illustrating an example of the processing of a vehicle behavior prediction unit 117 in a vehicle control system 1 according to an embodiment of the present invention.

[0062] CPU 12 acquires the latest values ​​of sensor values ​​110, environmental information 112, and control command values ​​113 (step S11). Then, based on the acquired data, it uses the latest vehicle model stored in vehicle model 111 to predict the vehicle behavior at the next moment and calculates the predicted vehicle behavior value (step S12). Next, CPU 12 outputs the predicted vehicle behavior value calculated in step S12 to vehicle behavior prediction value 115 (step S13).

[0063] Furthermore, in the processing of step S11, the data obtained may not be the latest value; for example, it may be time series data from a certain period since the latest value.

[0064] (Processing example for vehicle control applications)

[0065] The processing of the vehicle control application 118 is achieved by the vehicle control application 118 executing the function under the control of the CPU 12 of the ECU 10. Figure 4 This is a flowchart illustrating an example of the processing of a vehicle control application 118 in a vehicle control system 1 according to an embodiment of the present invention.

[0066] CPU 12 acquires the latest values ​​of sensor value 110, environmental information 112, and control command value 113 (step S21), and then calculates the control command value based on the acquired data (step S22). Next, CPU 12 outputs the control command value calculated in step S22 to control command value 113 (step S23).

[0067] Furthermore, in step S21, the acquired data may not be the latest value; for example, it could be time-series data from a certain period since the latest value. Additionally, in step S22, the calculation of the control command value can be performed, for example, using a mathematical model based on control theory or a machine learning model. Furthermore, when the vehicle model is successively optimized using model predictive control, snapshots of the vehicle model can be taken and maintained at regular intervals.

[0068] (Example of the comparison section)

[0069] The processing of the comparison unit 119 is carried out by the comparison unit 119 under the control of the CPU 12 of the ECU 10. Figure 5 This is a flowchart illustrating an example of the processing of the comparison unit 119 in a vehicle control system 1 according to an embodiment of the present invention.

[0070] CPU 12 obtains the latest vehicle behavior prediction value from vehicle behavior prediction value 115 (step S31), and then obtains the latest actual vehicle behavior value from actual vehicle behavior value 116 (step S32). Next, CPU 12 calculates the difference between the latest vehicle behavior prediction value and the latest actual vehicle behavior value (step S33), and then outputs the calculated difference to difference data 114 (step S34).

[0071] Furthermore, the data obtained in steps S32 and S33 may not be the latest values; for example, it could be time series data from a certain period since the latest values. Additionally, the difference calculation in step S33 could be, for example, the error between the predicted vehicle behavior value and the actual vehicle behavior value, or the square error. In the case of time series data, it could also be the average error or the average square error.

[0072] (Example of upload judgment process)

[0073] The processing of the upload judgment unit 120 is achieved by the upload judgment unit 120 executing the function under the control of the CPU 12 of the ECU 10. Figure 6 This is a flowchart illustrating an example of the processing of the upload determination unit 120 in a vehicle control system 1 according to an embodiment of the present invention.

[0074] CPU12 defines an analysis period based on the difference data 114, obtains the difference data within that analysis period (step S41), and then performs statistical analysis on the obtained difference data to calculate statistical values ​​(e.g., mean and variance) (step S42). Next, CPU12 determines whether the calculated statistical value is above a threshold (step S43).

[0075] In step S43, CPU12 determines that data needs to be uploaded due to large errors, such as a significant deviation of the average from 0 or a variance greater than the threshold. That is, if CPU12 determines that the calculated statistical value is above the threshold (YES in S43), it uploads the differential data within the analysis period defined in step S41 (step S44), and then determines whether the termination condition is met (step S45).

[0076] In step S44, CPU 12 retrieves sensor values ​​110, vehicle model 111 parameters, environmental information 112, control command values ​​113, differential data 114, vehicle behavior prediction values ​​115, and actual vehicle behavior values ​​116. It then assigns tags such as vehicle ID and time to the differential data within the analysis period defined in step S41 and uploads it. Additionally, in step S43, if the calculated statistical value is determined not to be above the threshold (S43 NO), CPU 12 proceeds to step S45.

[0077] In step S45, if the CPU 12 determines that the termination condition has been met (S45 YES), it ends the series of processes of the upload determination unit 120. If the CPU 12 determines that the termination condition has not been met (S45 NO), it returns to step S41, sets a different analysis period than before, and performs the process again. Here, the situation where the termination condition is not met includes, for example, the case where there is still unanalyzed data remaining in the differential data.

[0078] In step S41, the differential data within the analysis period could be, for example, data from one hour, one day, or one week. Alternatively, it could be discontinuous, such as only nighttime data for one week. In step S42, the statistical analysis could involve parameters of the approximate curve of the time series data of the differential data, or analysis using machine learning models (NN, SVM, Bayesian inference). In step S43, the tags assigned to the uploaded data could be, for example, information specific to the user or passenger.

[0079] (Example of a vehicle software update process)

[0080] The processing of the vehicle software update unit 121 is achieved by the vehicle software update unit 121 performing the function under the control of the CPU 12 of the ECU 10. Figure 7 This is a flowchart illustrating an example of the processing of the vehicle software update unit 121 in a vehicle control system 1 according to an embodiment of the present invention.

[0081] CPU12 downloads a new version of the vehicle model (step S51), and then downloads a new version of the vehicle control application (step S52). Next, CPU12 replaces the current vehicle model with the new version of the vehicle model (step S53), and then replaces the current vehicle control application with the new version of the vehicle control application (step S54).

[0082] (Example of processing by the Vehicle Model Improvement Department)

[0083] The processing of the vehicle model improvement unit 213 is achieved by the vehicle model improvement unit 213 performing the function under the control of the CPU 22 of the server 20. Figure 8 This is a flowchart illustrating an example of the processing of the vehicle model improvement unit 213 in a vehicle control system 1 according to an embodiment of the present invention.

[0084] The CPU 22 selects the vehicle equipped with the vehicle model that should be updated as the target vehicle (step S61). Then, it reads the parameters, environmental information, control command values, differential data, actual vehicle behavior values, and vehicle behavior prediction values ​​of the target vehicle's vehicle model from the uploaded data 212 (step S62). Next, the CPU 22 improves the vehicle model based on the data read in step S62 (step S63), and then saves the improved vehicle model in the vehicle model storage unit 211 (step S64).

[0085] Furthermore, in step S61, the selected vehicle is not limited to a single vehicle; for example, it can be multiple vehicle groups, users, or user groups. Additionally, in step S62, for example, previously uploaded data and uploaded data from other vehicles can be additionally read. Furthermore, in step S63, the parameters of the vehicle model can be optimized, and the construction of the vehicle model can be modified.

[0086] exist Figure 9 The diagram schematically illustrates an example of the specific processing flow of the vehicle model improvement unit 213 executed under the control of CPU 22. From the uploaded data 212, CPU 22 (1) extracts input / output data and comparison difference data for the vehicle model as learning data, and (2) extracts the parameters of the vehicle model. Furthermore, CPU 22 (3) creates a basic vehicle model based on the vehicle model's parameters, and (4) uses a training dataset to adjust and verify the parameters of the basic vehicle model. The verification simulator model and the vehicle control application model are output to the vehicle control application development verification unit 214.

[0087] (Processing example from the Vehicle Control Application Development and Verification Department)

[0088] The processing of the vehicle control application development and verification unit 214 is achieved by the vehicle control application development and verification unit 214 executing the function under the control of the CPU 22 of the server 20. Figure 10 This is a flowchart illustrating an example of the processing of the vehicle control application development and verification unit 214 in a vehicle control system 1 according to an embodiment of the present invention.

[0089] The CPU 22 selects the vehicle equipped with the vehicle control application that should be updated as the target vehicle (step S71). Then, it retrieves the updated vehicle model associated with the target vehicle from the vehicle model storage unit 211, and reads the environmental information, control command value, differential data, actual vehicle behavior value and vehicle behavior prediction value associated with the vehicle from the uploaded data 212 (step S72).

[0090] Next, the CPU 22 improves the vehicle control application based on the data read in step S72 (step S73). Then, it performs simulation verification using the improved vehicle control application, the improved vehicle model, and the uploaded data (step S74). Finally, the CPU 22 sends the improved vehicle control application to the vehicle software distribution unit 215 (step S75).

[0091] Furthermore, in the process of step S71, the selected vehicle is not limited to a single vehicle; for example, it can be multiple vehicle groups, or users or user groups.

[0092] exist Figure 11 The diagram schematically illustrates an example of the specific processing flow of the vehicle control application development verification unit 214, which is executed under the control of CPU 22. CPU 22 (1) improves the vehicle control application and (2) improves the verification simulator. In addition, CPU 22 (3) extracts the input data to the vehicle control application as verification data. Furthermore, CPU 22 (4) verifies the updated vehicle control application using the updated simulator.

[0093] (Processing example from the vehicle software distribution department)

[0094] The processing of the vehicle software distribution unit 215 is achieved by the vehicle software distribution unit 215 executing the function under the control of the CPU 22 of the server 20. Figure 12 This is a flowchart illustrating an example of the processing of the vehicle software distribution unit 215 in a vehicle control system 1 according to an embodiment of the present invention.

[0095] CPU 22 selects a vehicle equipped with the vehicle control application that should be updated (step S81), and then retrieves the vehicle model corresponding to the vehicle control application that should be updated from the vehicle model storage unit 211 (step S82). Furthermore, CPU 22 sends the improved vehicle control application and the corresponding improved vehicle model program data to the target vehicle (step S83).

[0096] [The function and effects of this implementation method]

[0097] As described above, in the vehicle control system (vehicle control method) according to this embodiment, differential data between the sensor values ​​(actual vehicle behavior) of the sensor unit 30 that collects vehicle information and the vehicle model is recorded, and data is uploaded based on this differential data. Therefore, since only the data that truly needs improvement can be collected and uploaded, useless uploads can be avoided. Furthermore, because the data is uploaded based on differential data, boundary conditions that could not be anticipated beforehand can also be collected.

[0098] Furthermore, since the vehicle model is improved on the cloud-side server 20, data from multiple vehicles can be used to improve the vehicle model. This avoids localized solutions that should not have been optimized, such as fault states.

[0099] Furthermore, by comparing the sensor values ​​(actual vehicle behavior) from sensor unit 30 with the vehicle model, a large difference indicates that the accuracy of the vehicle model is deteriorating. Based on such a scenario of accuracy deterioration, vehicle data can be collected to improve the vehicle model. Additionally, since the system is configured to determine whether to upload data when the difference is large, it can include scenarios not anticipated beforehand, automatically detecting and collecting only data associated with previous scenarios of vehicle model accuracy deterioration. Because this method can be applied to multiple vehicles to collect diverse data, this data can be used to improve the accuracy of the vehicle model.

[0100] <Variation Example>

[0101] The present invention is not limited to the embodiments described above and shown in the accompanying drawings, and various modifications can be made without departing from the spirit of the invention as set forth in the claims. Furthermore, the above embodiments are detailed descriptions provided for ease of understanding of the invention and are not limited to having all the described configurations.

[0102] Furthermore, in the above embodiment, the upload judgment unit is configured to upload data to the server when the difference between the predicted vehicle behavior value and the actual vehicle behavior value is greater than a predetermined threshold. However, it can also be configured to upload data to the server when the difference is statistically large. Here, "statistically large difference" refers to, for example, a large absolute value of the average of the difference data and a large variance. By adopting this configuration, the upload judgment unit 120 performs statistical processing on the time series data and judges whether there is a difference within a certain interval, thereby filtering out outliers such as noise. As a result, useless uploads based on instantaneous differences such as noise can be avoided.

[0103] In addition to the configuration described above, the processing of the vehicle model and vehicle behavior prediction unit can also be configured to run separately from these vehicle models and vehicle behavior prediction units in the background, unrelated to vehicle control. By adopting this configuration, even components under development with insufficient safety verification can be executed within the vehicle, thus enabling data upload based on the difference between the predicted vehicle behavior value and the actual vehicle behavior value. As a result, data from scenarios where the developing vehicle model is not well-suited can be uploaded using real-world vehicle data and execution environment.

[0104] Symbol Explanation

[0105] 1…Vehicle Control System, 10…ECU, 11…Memory, 12…CPU, 20…Server, 30…Sensor Unit, 40…Other ECUs, 110…Sensor Values, 111…Vehicle Model, 112…Environmental Information, 113…Control Command Values, 114…Differential Data, 115…Vehicle Behavior Prediction Values, 116…Actual Vehicle Behavior Values, 117…Vehicle Behavior Prediction Unit, 118…Vehicle Control Application, 119…Comparison Unit, 120…Upload Judgment Unit, 121…Vehicle Software Update Unit, 211…Vehicle Model Storage Unit, 212…Upload Data, 213…Vehicle Model Improvement Unit, 214…Vehicle Control Application Development and Verification Unit, 215…Vehicle Software Distribution Unit.

Claims

1. A vehicle control system comprising: a sensor unit for acquiring vehicle information; a vehicle control device having a vehicle control application for calculating control command values ​​based on sensor values ​​from the sensor unit and predicted values ​​from a vehicle model; and a server, characterized in that, The vehicle control device includes: The vehicle behavior prediction unit calculates vehicle behavior prediction values ​​from environmental information calculated based on the control command values ​​and the sensor values, and the prediction values ​​of the vehicle model. The comparison unit calculates differential data by comparing the predicted vehicle behavior value with the actual vehicle behavior value based on the sensor value; The upload judgment unit uploads the upload data, which includes the vehicle model, the sensor values, the control command values, and the actual vehicle behavior values, to the server when the differential data is greater than a specified threshold. as well as The vehicle software update department updates the vehicle control application and the vehicle model to the vehicle control application and vehicle model distributed from the server. The server has the following features: The vehicle model improvement unit improves the vehicle model based on the uploaded data to make the predicted vehicle behavior value closer to the actual vehicle behavior value. The Vehicle Control Application Development and Verification Department develops vehicle control applications for the vehicle control device based on the uploaded data. and The vehicle software distribution department distributes the improved vehicle model and the developed vehicle control application to the vehicle control device.

2. The vehicle control system according to claim 1, characterized in that, If the difference in statistical data is large, the upload judgment unit will upload the data, including the vehicle model, the sensor values, the control command values, and the actual vehicle behavior values, to the server.

3. A vehicle control method for use in a vehicle control system, the vehicle control system comprising: a sensor unit for acquiring vehicle information; a vehicle control device having a vehicle control application for calculating control command values ​​based on sensor values ​​from the sensor unit and predicted values ​​from a vehicle model; and a server, characterized in that, In the vehicle control device, the following processes are performed: The steps for calculating vehicle behavior prediction values ​​from environmental information calculated based on the control command values ​​and the sensor values, and the prediction values ​​of the vehicle model; The step of calculating differential data by comparing the predicted vehicle behavior value with the actual vehicle behavior value based on the sensor value; When the differential data is greater than a specified threshold, the step of uploading the data containing the vehicle model, the sensor values, the control command values, and the actual vehicle behavior values ​​to the server is as follows: as well as The step of updating the vehicle control application and the vehicle model to the vehicle control application and vehicle model distributed from the server. The following processes are performed on the server: The step of improving the vehicle model based on the uploaded data so that the predicted vehicle behavior value is close to the actual vehicle behavior value; The steps for developing a vehicle control application for the vehicle control device based on the uploaded data; as well as The step of distributing the improved vehicle model and the developed vehicle control application to the vehicle control device.

Images