Vehicle control device and on-vehicle program

Abstract

A vehicle control device (10) mounted on a vehicle (101) comprises: a data acquisition unit (14) that acquires data relating to sensor information acquired by various sensors (20) mounted on the vehicle; a classification unit (15) that classifies the data, acquired by the data acquisition unit, for each scene in which the vehicle is traveling, the data being classified on the basis of the sensor information; a compression unit (16) that deletes one of the plurality of pieces of data classified into a predetermined scene by the classification unit or thins some components of the data, thereby compressing the data; and a transmission unit (17) that transmits the data compressed by the compression unit to a server (102) via a communication network (103).

Description

Vehicle control device and in-vehicle program CROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application is based on Japanese Application No. 2024-069041, filed on April 22, 2024, the contents of which are incorporated herein by reference.

[0002] The present disclosure relates to a vehicle control device and an in-vehicle program.

[0003] In recent years, a method has been adopted in which various data actually acquired from vehicles after they have been sold while they are being driven is collected on a server via a communication network, and the data collected on the server is analyzed and used in future vehicle development or to update the vehicle's control program.

[0004] As one example, a verification method called shadow mode is known, in which a vehicle control program to be verified is run while the vehicle is running after sales to verify the performance and safety of the vehicle control program. In verification using shadow mode, for example, the vehicle control program to be verified is run in the background, i.e., without being involved in vehicle control, and data related to the output values ​​is stored. The data related to the output values ​​is then collected by a server via an external network or the like. The collected data is then analyzed to verify the operation of the vehicle control program. Technology related to such shadow mode is described, for example, in Patent Document 1.

[0005] International Publication No. 2022 / 004324

[0006] However, when collecting data, if data on all driving conditions in all scenes for all vehicles is collected, the amount of data becomes enormous, which causes problems such as increased communication load, processing load, and analysis load.

[0007] The present disclosure has been made in consideration of the above circumstances, and has as its main object to provide a vehicle control device and an in-vehicle program that compress collected data.

[0008] A vehicle control device for solving the above problem is a vehicle control device mounted on a vehicle, and includes: a data acquisition unit that acquires data related to sensor information acquired by various sensors mounted on the vehicle; a classification unit that classifies the data acquired by the data acquisition unit for each scene in which the vehicle is traveling based on the sensor information; a compression unit that deletes any of the multiple data classified by the classification unit into a specified scene or compresses the data by thinning out some of the components of the data; and a transmission unit that transmits the data compressed by the compression unit to a server via a communication network.

[0009] According to the above configuration, data classified into a specific scene is compressed. This reduces the amount of data stored, prevents storage capacity pressure, and reduces communication and analysis loads. It also prevents duplicate collection of similar data for a specific scene.

[0010] The in-vehicle program for solving the above problem is an in-vehicle program executed by a vehicle control device mounted on a vehicle, and causes the vehicle control device to perform the following steps: a data acquisition step that causes the vehicle control device to acquire data related to sensor information acquired by various sensors mounted on the vehicle; a classification step that causes the vehicle control device to classify the data acquired in the data acquisition step for each scene in which the vehicle is traveling based on the sensor information; a compression step that deletes any of the multiple data classified into a specified scene in the classification step or compresses the data by thinning out some of the components of the data; and a transmission step that transmits the data compressed in the compression step to a server via a communication network.

[0011] According to the above configuration, data classified into a specific scene is compressed. This reduces the amount of data stored, prevents storage capacity pressure, and reduces communication and analysis loads. It also prevents duplicate collection of similar data for a specific scene.

[0012] The above and other objects, features, and advantages of the present disclosure will become more apparent from the following detailed description taken in conjunction with the accompanying drawings, in which Fig. 1 is a schematic diagram of a data collection system, Fig. 2 is a block diagram showing functions performed by a verification processing unit, Fig. 3 is a flowchart of a data acquisition process, Fig. 4 is a block diagram showing functions performed by a processing unit of a second embodiment, Fig. 5 is a flowchart of a data acquisition process of the second embodiment, and Fig. 6 is a flowchart of a data acquisition process of a modified example.

[0013] Hereinafter, embodiments of a vehicle control device and an on-board program according to the present disclosure will be described in detail with reference to the drawings. Note that, between the embodiments and modifications, the same or corresponding parts in the drawings are designated by the same reference numerals, and their description will not be repeated in principle.

[0014] 1 shows a data collection system 100 to which a vehicle control device 10 according to this embodiment is applied. The vehicle control device 10 is mounted on a vehicle 101, and controls the vehicle 101 and performs driving assistance.

[0015] As shown in Fig. 1, a data collection system 100 includes a server 102 and is capable of communicating with one or more vehicles 101 via a communication network 103 such as the Internet. Fig. 1 shows only one vehicle 101. The vehicle 101 includes a vehicle control device 10, a sensor 20, an actuator 30, and the like.

[0016] The sensor 20 includes various sensors for measuring the traveling conditions of the vehicle 101, such as a vehicle speed sensor 21, an acceleration sensor 22, and a yaw rate sensor 23. The sensors for measuring the traveling conditions of the vehicle 101 may include other sensors, or any of the vehicle speed sensor 21, the acceleration sensor 22, and the yaw rate sensor 23 may not be included.

[0017] The sensor 20 also includes various sensors for detecting other vehicles and obstacles, such as a camera 24 and a millimeter-wave radar 25. The sensor for detecting other vehicles and obstacles is not limited to the millimeter-wave radar 25, but may also be a laser radar (LiDAR), an ultrasonic sensor, or a combination of these. The camera 24 may also be a monocular camera or a compound camera. The camera 24 may also capture either still images or videos. The number, position, and type of the cameras 24 may be changed as desired. For example, the vehicle may include a front camera that captures the area in front of the vehicle, a right-side camera that captures the area on the right side of the vehicle, a left-side camera that captures the area on the left side of the vehicle, and a rear camera that captures the area behind the vehicle.

[0018] The sensor 20 also includes various sensors for detecting various amounts of operation by the driver, such as an accelerator sensor 26 that detects the amount of accelerator operation by the driver, a brake sensor 27 that detects the amount of brake operation, and a steering angle sensor 28 that detects the amount of steering (steering angle) of the steering wheel by the driver.

[0019] These sensors 20 are connected to the vehicle control device 10 wirelessly or by wire, and the measurement results (or detection results) of these sensors 20 are input to the vehicle control device 10 or the like as sensor information.

[0020] The actuators 30 include, for example, actuators for driving the vehicle 101, such as a motor that serves as the main engine of the vehicle 101. The actuators 30 may also include actuators for controlling the behavior of the vehicle 101, such as an actuator for operating a steering wheel, an actuator for operating a brake pedal, or an actuator for operating an accelerator pedal. The actuators 30 may also include devices for operating accessories of the vehicle 101, such as a display, a speaker, an indicator, and a headlight. The driving and operation of the vehicle 101 are controlled by the actuators 30.

[0021] The vehicle control device 10 is primarily composed of a microcomputer including a processing unit 10a such as a CPU and a storage unit 10b such as various types of memory. The functions provided by the microcomputer can be provided by software recorded in a physical memory device and a computer executing the software, software alone, hardware alone, or a combination thereof. For example, when the microcomputer is provided by electronic circuits, which are hardware, the functions can be provided by digital circuits including numerous logic circuits or analog circuits. For example, the processing unit 10a of the microcomputer executes programs stored in a non-transitory tangible storage medium (non-transitory tangible storage medium) that serves as the storage unit 10b. The programs include, for example, programs that realize functions shown in FIG. 2 . Execution of the programs results in the execution of methods corresponding to the programs. The storage unit 10b is, for example, a non-volatile memory. The programs stored in the storage unit 10b can be downloaded and updated via a communication network 103, such as the Internet, via over-the-air (OTA) or other means.

[0022] The vehicle control device 10 has various functions (application programs) for assisting the driving of the vehicle 101, and these functions control the actuator 30 based on sensor information input from the sensor 20.

[0023] Typical functions for assisting the driving of the vehicle 101 include, for example, an adaptive cruise control system (ACC), a forward collision warning (FCW), an advanced emergency braking system (AEBS), a night vision / pedestrian detection (NV / PD), a traffic sign recognition (TSR), a lane departure warning (LDW), a lane keeping assist system (LKAS), a rear cross traffic alert (RCTA), an adaptive front lighting system (AFS), and an advanced parking assist (APA). The vehicle 101 may be provided with all or some of these functions. Furthermore, the vehicle 101 may also be provided with other driving assistance functions. Furthermore, the vehicle 101 may also be provided with a function for realizing autonomous driving of the vehicle 101. These functions are realized by the arithmetic processing unit 10a executing a driving assistance control program stored in the storage unit 10b.

[0024] Furthermore, in order to verify the performance and safety of the driving assistance control program, the vehicle control device 10 has a function called a shadow mode in which a driving assistance control program to be verified (hereinafter referred to as a verification target program) is run while the vehicle 101 is running after being sold, that is, in an actual use case, and output values ​​are checked. In verification using the shadow mode, for example, the verification target program is run in the background, that is, in a manner not related to vehicle control, and data related to the output values ​​is stored, and the server 102 collects the data related to the output values ​​via the communication network 103. Note that the shadow mode is a type of data collection mode for collecting data.

[0025] The configuration and functions of the shadow mode according to this embodiment will be described below. The timing of switching to the shadow mode may be any timing. For example, the switching may be performed by an operation by the driver or by an instruction from the server 102. Alternatively, the switching to the shadow mode may be performed when the ignition switch is turned on.

[0026] In the following, the driving assistance control program that actually operates the vehicle 101 will be referred to as an "implemented program" to contrast it with the program to be verified. It will also be referred to as an "implemented program" in FIG. 1 . The vehicle control device 10 is equipped with a verification processing device 11 for executing the program to be verified, taking into account the processing load when executing the implemented program. The verification processing device 11 may have performance equivalent to or different from that of the processing device 10a, as long as it has the performance to execute the program to be verified. The program to be verified is stored in the storage unit 10b. A storage device dedicated to the shadow mode may also be provided.

[0027] Execution of the program to be verified executes various functions in the background to assist the driving of the vehicle 101. The functions implemented by execution of the program to be verified may be the same as the functions actually realized by the arithmetic processing device 10a, or some of the functions may be omitted. Furthermore, functions other than the functions actually realized by the arithmetic processing device 10a may also be implemented.

[0028] When the verification processing unit 11 is running the program to be verified in shadow mode, it receives sensor information from the various sensors 20, just like the processing unit 10a. Based on the received sensor information, the verification processing unit 11 then performs various functions and outputs various control signals for operating each actuator 30. These control signals (output results) are not actually input to the actuators 30, but are stored in the storage unit 10b as data related to the output results. At that time, the verification processing unit 11 also stores data related to the sensor information, which is an input value, in association with the data.

[0029] The verification processing unit 11 also receives the control signal output from the processing unit 10a after inputting sensor information as an input value and processing it based on the implementation program, and stores the control signal in the storage unit 10b as data related to the output result. That is, the verification processing unit 11 also stores the control signal output from the processing unit 10a after processing it based on the implementation program in order to compare and verify the output result of the implementation program with the output result of the program to be verified.

[0030] Furthermore, the verification processing device 11 may input sensor information (vehicle speed, yaw rate, acceleration amount, accelerator pedal operation amount, brake pedal operation amount, steering angle, etc.) detected when a control signal processed and output based on the implementation program is input to the actuator 30 and the vehicle 101 moves as a result, and store the information in the storage unit 10b. In other words, the sensor information related to the actual operation of the vehicle 101 for each scene, that is, the sensor information necessary to verify the correct operation, may also be stored.

[0031] The vehicle control device 10 uploads the data thus stored in the storage unit 10b to the server 102 via the communication network 103 at a predetermined transmission timing. The predetermined transmission timing may be any timing, for example, a timing when an upload instruction is issued from the server 102. Alternatively, the predetermined transmission timing may be, for example, a timing when the vehicle 101 is charging, when the vehicle is parked or stopped, or when the ignition switch is turned off.

[0032] However, there is a problem in that the storage capacity of the storage unit 10b is likely to be insufficient to store all data while the vehicle 101 is traveling. Also, if all the vehicles 101 upload all of the data they have stored, there is a risk that an excessive load will be placed on the communication network 103. Furthermore, there is also a problem in that the processing load on the server 102 will be too large if all of the uploaded data is analyzed by the server 102. There is also a problem in that there is a lot of waste in acquiring and analyzing all of the data in the first place.

[0033] For this reason, it is desirable to configure the system so that only the amount of data necessary for verification and analysis is stored and transmitted / received. Therefore, the vehicle control device 10 of this embodiment classifies data for each driving scene of the vehicle 101, and compresses or deletes data related to similar driving scenes to reduce the amount of data stored. This will be explained in detail below.

[0034] 2, the verification processing device 11 of the vehicle control device 10 has a function as an input unit 12, a function as a processing unit 13, a function as a data acquisition unit 14, a function as a classification unit 15, a function as a compression unit 16, and a function as a transmission unit 17. These functions are realized by the verification processing device 11 by executing an in-vehicle program stored in the storage unit 10b.

[0035] The input unit 12 inputs sensor information from the sensor 20. Then, the input unit 12 inputs part or all of the input sensor information to the processing unit 13 as input values ​​for the program to be verified. The input unit 12 also inputs part or all of the input sensor information to the data acquisition unit 14.

[0036] The processing unit 13 runs the program to be verified and performs processing based on various functions (application programs) realized by the program to be verified, based on input values ​​(sensor information) input from the input unit 12. The processing unit 13 then inputs control signals (control signals for the actuator 30) as the processing results to the data acquisition unit 14. Note that, as described above, these control signals are not input to the actuator 30.

[0037] The data acquisition unit 14 determines whether the acquisition condition is met based on at least one of the input value (sensor information) input from the input unit 12 and the output result (control signal) input from the processing unit 13.

[0038] The acquisition conditions may include, for example, thresholds for one or more parameters as components. The parameters of the acquisition conditions may be, for example, parameters included in sensor information such as vehicle speed, yaw rate, accelerator operation amount, brake operation amount, and steering amount, or parameters included in output results such as required torque and an output instruction signal to a display. The acquisition conditions may also include parameters calculated or estimated from sensor information or output results. For example, the acquisition condition parameters may include the relative distance to an obstacle (such as a preceding vehicle or pedestrian), the relative speed to the obstacle, and the time-to-collision (TTC) calculated from the recognition results of a camera image or the detection results of the millimeter-wave radar 25. The acquisition condition parameters may also include the difference between the output results based on the implemented program and the output results of the program to be verified. For example, the parameter may be the difference between the brake operation amount output by processing based on the implemented program and the brake operation amount output by processing based on the program to be verified. The threshold may be either the upper limit or lower limit of any of these parameters, or both.

[0039] Furthermore, a component of the acquisition condition may be whether or not the scene in which the vehicle 101 is traveling (hereinafter simply referred to as the scene) is a predetermined acquisition scene. The scene refers to various scenes that are expected when the vehicle 101 is traveling, such as a scene in which the vehicle overtakes a preceding vehicle, a scene in which the vehicle passes between vehicles, a scene in which the vehicle follows a preceding vehicle, a scene in which a pedestrian crosses in front of the vehicle 101 at night, a scene in which the vehicle 101 merges from an acceleration lane onto a main lane on a motorway, a scene in which the vehicle is parking or stopping, a scene in which the vehicle is waiting at a traffic light, and the like.

[0040] These scenes are estimated based on sensor information. For example, the vehicle control device 10 may recognize camera images or the like and estimate the scenes. More specifically, the sensor information such as camera images may be input to a machine-learned inference model such as a deep neural network to estimate the scenes. Note that image recognition does not have to be performed by the vehicle control device 10, and may be performed by an external device of the vehicle control device 10, such as an image recognition device, and the results may be input as sensor information.

[0041] Furthermore, among various functions (application programs) based on the program to be verified, an executed function (executed function) may be a component of the acquisition condition. For example, the acquisition condition may be satisfied when a collision damage mitigation braking control function is executed. Note that which function has been executed can be determined based on the output result (control signal) input from the processing unit 13.

[0042] In this embodiment, the acquisition condition is set by combining the acquisition scene, the execution function, and the parameter threshold (i.e., an AND condition). For example, the acquisition condition may be satisfied when the scene is following a preceding vehicle and the vehicle speed (a parameter of the acquisition condition) is equal to or greater than a threshold (50 km / h).

[0043] The combination of components of the acquisition condition may be an acquisition scene and an implementation function, an acquisition scene and a parameter threshold, or an implementation function and a parameter threshold. Furthermore, the components included in one acquisition condition may include two or more implementation functions, and in this case, the implementation functions may be an AND condition or an OR condition. For example, the condition may be that both the forward vehicle approach warning function and the collision damage mitigation braking control function are implemented, or that either one of them is implemented. Similarly, the parameter threshold may be a threshold for two or more types of parameters.

[0044] Furthermore, the acquisition condition is established when all of the conditions of the components that make up the acquisition condition are satisfied. For example, if the acquisition scene of the acquisition condition is "a scene of following a preceding vehicle," the implementation function of the acquisition condition is "a following driving function," and the threshold value of the parameter of the acquisition condition is "50 km / h or more," the acquisition condition is established when the following driving function is implemented in a scene of following a preceding vehicle and the vehicle speed (a parameter of the acquisition condition) is equal to or greater than the threshold value (50 km / h).

[0045] The number of acquisition conditions is not limited to one, and multiple acquisition conditions may be set. For example, a first acquisition condition may be a scene in which the vehicle is following a preceding vehicle and the vehicle speed is equal to or greater than a first threshold, and a second acquisition condition may be a scene in which a pedestrian is crossing in front of the vehicle 101, the distance to the pedestrian is equal to or less than a second threshold, and the amount of brake operation is equal to or greater than a third threshold.

[0046] When any of the acquisition conditions is satisfied, the data acquisition unit 14 stores data related to input values ​​and output results in the storage unit 10b. As described above, the input values ​​include, for example, sensor information input to the verification processing device 11. Furthermore, the output results include, for example, control signals processed and output based on the program to be verified, or control signals processed and output based on the implemented program. Furthermore, the output results may include sensor information related to the actual operation of the vehicle 101 for each scene. Furthermore, the output results may include a difference between the output results based on the implemented program and the output results of the program to be verified. The stored (acquired) data may be changed depending on the acquisition condition that is satisfied. For example, when an acquisition condition is satisfied in a scene in which the vehicle is following a preceding vehicle and the vehicle speed is equal to or greater than a first threshold, data related to the vehicle speed may be acquired. On the other hand, when an acquisition condition is satisfied in a scene in which a pedestrian is crossing in front of the vehicle 101 and the distance to the pedestrian is equal to or less than a second threshold and the brake operation amount is equal to or greater than a third threshold, data related to the brake operation amount may be acquired.

[0047] Next, the classification unit 15 will be described. The classification unit 15 classifies the data acquired (stored) by the data acquisition unit 14 for each scene in which the vehicle 101 is traveling, based on the sensor information input by the input unit 12. The scenes in which the vehicle 101 is traveling are the same as those described above. That is, the scenes refer to various possible scenes in which the vehicle 101 is traveling, such as a scene in which the vehicle overtakes a preceding vehicle, a scene in which the vehicle passes between vehicles, a scene in which the vehicle follows a preceding vehicle, a scene in which a pedestrian crosses in front of the vehicle 101 at night, a scene in which the vehicle 101 merges from an acceleration lane onto a main lane on a motorway, a scene in which the vehicle is parking or stopping, a scene in which the vehicle is waiting at a traffic light, and the like.

[0048] These scenes are estimated based on sensor information. For example, the vehicle control device 10 may recognize camera images or the like and estimate the scene. In this case, several reference scenes are assumed in advance, and sensor information indicating the characteristics of each scene is stored in advance. Then, the sensor information is compared, and the reference scene with the closest similarity between the sensor information among the multiple reference scenes is estimated as the current scene. More specifically, the sensor information such as the camera images may be input into a machine-learned inference model such as a deep neural network, and the scene may be estimated.

[0049] Note that image recognition does not have to be performed by the vehicle control device 10, but may be performed by an external device to the vehicle control device 10, such as an image recognition device, and the results may be input as sensor information.

[0050] When storing the data in the storage unit 10b, the data acquisition unit 14 stores the data in association with the scenes classified (estimated) by the classification unit 15. As a result, when the data is stored in the storage unit 10b, the data is classified by scene and stored.

[0051] Next, the compression unit 16 will be described. The compression unit 16 compresses the amount of data by deleting any of the multiple data classified into a predetermined scene or by thinning out some of the data components. Thinning out some of the data components means, for example, lowering the frame rate if the data is video data, or lowering the sampling rate if the data is audio data. In other words, if the data is detected in a time series at predetermined intervals, it means lengthening the detection interval to generate digital data with a reduced number of samples. Note that, hereinafter, deleting any of the multiple data or thinning out some of the data components will simply be referred to as "compression."

[0052] The timing and method of compression will be specifically described. The compression unit 16 of this embodiment compresses multiple pieces of data classified into predetermined scenes at a predetermined timing. The predetermined timing may be any timing, for example, a timing when the remaining storage capacity of the data in the storage unit 10b falls below a specified value. The predetermined timing may also be a timing specified by the server 102, or a timing when the processing load on the vehicle control device 10 is reduced, such as a timing when the vehicle 101 is stopped.

[0053] The predetermined scene may be any scene, but for example, a priority or urgency may be set for each scene in advance, and data classified as scenes with low priority or urgency may be deleted from the storage unit 10b. Furthermore, for example, the predetermined scene may be a scene designated by the server 102 (e.g., designated as unnecessary). Furthermore, the predetermined scene may be the scene with the largest amount of data among multiple scenes classified in the storage unit 10b.

[0054] The compression unit 16 may arbitrarily change which data among the multiple data included in a predetermined scene to compress. For example, the compression unit 16 may compress (delete or thin out) the first or last stored data among the multiple data included in a predetermined scene. Alternatively, the compression unit 16 may compress random data among the multiple data included in a predetermined scene.

[0055] In addition, the compression unit 16 may set priorities for multiple data classified into a specified scene in the order of specific parameters contained in the data, and compress (in this embodiment, delete) the multiple data included in the specified scene in order of lowest priority.

[0056] For example, the compression unit 16 sets a lower priority for data that includes a lower vehicle speed (specific parameter) among a plurality of data classified as a scene of passing between vehicles (predetermined scene).When deleting and compressing any of the plurality of data classified as a scene of passing between vehicles, the compression unit 16 preferentially deletes data with a lower vehicle speed.

[0057] When compressing data, the amount of data to be compressed may be set arbitrarily. For example, only a predetermined amount of data may be compressed. Also, for example, the amount of data to be compressed may be changed depending on the remaining amount of data storage capacity in the storage unit 10b. In other words, the smaller the remaining amount, the greater the amount of data to be compressed.

[0058] The transmitter 17 transmits the data acquired by the data acquisition unit 14 and stored in the storage unit 10b to the server 102 via the communication network 103 at a predetermined transmission timing. The predetermined transmission timing is as described above.

[0059] The flow of data acquisition in this embodiment will be described below with reference to FIG. 3. The flow of data acquisition shown below is the flow of data acquisition processing performed by the verification processing unit 11. This processing is performed after the shadow mode is set. The timing at which the shadow mode is set is arbitrary, but may be, for example, the timing at which the ignition switch is turned on.

[0060] First, the input unit 12 of the verification processing device 11 inputs sensor information from the sensor 20 (step S101). The processing unit 13 runs the program to be verified and performs processing based on various functions realized by the program to be verified, based on the input values ​​(sensor information) input from the input unit 12 (step S102). In step S102, the processing unit 13 inputs a control signal as a result of the processing to the data acquisition unit 14.

[0061] The data acquiring unit 14 determines whether or not the acquisition condition is met based on at least one of the input value (sensor information) and the output result (control signal, etc.) (step S103).

[0062] If the determination result is positive (if the acquisition condition is met), the classification unit 15 of the verification processing device 11 classifies the data related to the input values ​​and output results (step S104). Specifically, the classification unit 15 estimates the scene in which the vehicle 101 is traveling based on the sensor information input in step S101. In this embodiment, the classification unit 15 compares the sensor information and estimates the reference scene with the closest similarity between the sensor information among multiple reference scenes as the current scene. Then, the classification unit 15 classifies the data related to the input values ​​and output results into the estimated scene.

[0063] Then, the data acquisition unit 14 stores (acquires) data regarding the input values ​​and output results in the storage unit 10b (step S105). When storing the data, the data acquisition unit 14 stores the data so that the data regarding the input values ​​and output results is classified for the scenes classified (estimated) by the classification unit 15 in step S104. In this embodiment, the data to be stored is stored in association with tag information regarding the classified scenes. The data acquisition unit 14 also stores the acquisition conditions that have been met in association with the data. Then, the processing ends. On the other hand, if the determination result in step S103 is negative, the verification processing unit 11 ends the data acquisition process as it is. The data acquisition process is executed at regular intervals after the shadow mode is set.

[0064] The transmitting unit 17 transmits the data acquired by the data acquiring unit 14 and stored in the storage unit 10b to the server 102 via the communication network 103 at a predetermined transmission timing. At this time, the transmitting unit 17 also transmits information about the established acquisition conditions associated with the data. Tag information about the scenes classified by the classifying unit 15 may also be transmitted together with the data.

[0065] When the server 102 receives the data transmitted from the transmitter 17 of each vehicle 101, it stores the data in the storage device of the server 102. When storing the data, the data may be classified by scene based on tag information related to the scene received together with the data. The data may also be stored in association with information related to the acquisition conditions that were met when the data was acquired. In other words, after classifying the data by scene, the data may be further classified by the acquisition conditions and stored. This makes it easier to analyze the data because the data is grouped by scene.

[0066] According to the first embodiment, the following effects are achieved.

[0067] The compression unit 16 compresses the multiple pieces of data classified by the classification unit 15 into predetermined scenes. This prevents storage capacity from being overwhelmed and reduces communication loads, processing loads, analysis loads, and other burdens. Furthermore, since it is possible to change whether or not to compress for each scene, data can be collected without compression for scenes requiring a large amount of data. In other words, for scenes requiring less data, compressed data can be collected and analyzed efficiently. Furthermore, it is possible to prevent duplicate collection of similar data for a predetermined scene.

[0068] When selecting data to compress from a plurality of data classified into a predetermined scene, the compression unit 16 compresses data in order of decreasing priority based on the priority set in the order of specific parameters included in the data. This allows data with a high priority to be collected as much as possible to be retained, allowing for efficient analysis.

[0069] The classification unit 15 uses a deep neural network to estimate (recognize) similar scenes from among a plurality of predetermined reference scenes based on the sensor information input to the input unit 12, and classifies the data into the estimated scenes. Since the reference scenes are set in advance in this way, it is easy for the developer to recognize and analyze the expected scenes during analysis.

[0070] (Variation of the First Embodiment) In the first embodiment, it is not necessary to acquire the control signal (data related to the output result) that is processed and output based on the implementation program. On the other hand, after the acquisition condition is met, sensor information (vehicle speed, yaw rate, acceleration amount, accelerator pedal operation amount, brake pedal operation amount, steering angle, etc.) detected when the vehicle 101 is operating may be acquired until a predetermined time has elapsed. In other words, data related to this sensor information may be stored in the memory unit 10b.

[0071] In the first embodiment, the driving assistance function may not be implemented. In this case, sensor information (vehicle speed, yaw rate, acceleration amount, accelerator pedal operation amount, brake pedal operation amount, steering angle, etc.) detected when the vehicle 101 is operating due to an operation by the driver may be acquired until a predetermined time has elapsed after the acquisition condition is met. In other words, data related to this sensor information may be stored in the storage unit 10b to be collected as correct data.

[0072] In the first embodiment, the compression unit 16 prioritizes a plurality of data items classified into a predetermined scene in the order of specific parameters (e.g., vehicle speed) included in the data items. The specific parameters are not limited to vehicle speed and may be arbitrarily changed. For example, the specific parameters may include any of the following: vehicle speed, time of day, weather, road, type of detected target, shape of detected target, position of detected target, distance to detected target, speed of detected target, and time to collision until detected target. Since the specific parameters to be prioritized are likely to differ for each scene, the specific parameters may be changed depending on the scene.

[0073] In the first embodiment, the classification unit 15 classified the data by scene, but the data may be classified by the acquisition condition that is met. The compression unit 16 may then compress the data that is classified into a predetermined acquisition condition from among the acquisition conditions.

[0074] Similarly, the classification unit 15 classified the data by scene, but the data may be classified by executed function (application program) among the various functions realized by the program to be verified. The compression unit 16 may compress the data classified into a predetermined executed function among the realized functions.

[0075] In the first embodiment, the classification unit 15 estimated which of the reference scenes the data is similar to based on the input sensor information. As another example, the classification unit 15 may classify the data stored in the storage unit 10b into similar scenes. For example, the classification unit 15 extracts features using deep learning or the like based on the sensor information (e.g., image data) included in the data, and classifies the data into similar scenes based on the similarity of the features. The classification unit 15 then sorts the data into groups of similar scenes. That is, the classification unit 15 clusters the data based on the sensor information included in the data, and classifies the data into clusters consisting of similar scenes.

[0076] In the above embodiment, when storing data in the storage unit 10b, the data acquisition unit 14 may store the data by specifying an address in the storage unit 10b for each priority level of the data. The compression unit 16 may then automatically delete data stored in addresses with lower priority levels when the remaining storage capacity of the storage unit 10b becomes low, thereby freeing up data space and increasing storage capacity. This eliminates the need for compression instructions because the compression unit 16 deletes data based on the specified address when the remaining storage capacity becomes low, simplifying processing. Furthermore, fragmentation of the storage area can be prevented, effectively increasing storage capacity.

[0077] In the above embodiment, responsiveness or temporal resolution may be set in advance for each scene. A scene with high responsiveness indicates a scene in which data should be transmitted to the server 102 as soon as possible after acquisition, while a scene with low responsiveness indicates a scene in which data can be transmitted to the server 102 slowly after acquisition. For example, a scene in which there is a high possibility of an accident or a scene in which the automatic brakes are activated can be said to have high responsiveness. A scene with low temporal resolution indicates a scene in which there is little change over time, while a scene with high temporal resolution indicates a scene in which there is a large change over time. For example, a scene in which there is traffic congestion on a highway can be said to have low temporal resolution.

[0078] If the responsiveness or temporal resolution is set in advance for each scene, the transmitter 17 may thin out (compress) the data when transmitting data of a scene with low responsiveness or temporal resolution. The compressor 16 may compress data classified as scenes with low responsiveness or temporal resolution in order, depending on the remaining storage capacity of the storage unit 10b that stores the data.

[0079] Second Embodiment A second embodiment in which the vehicle control device 10 in the first embodiment is partially modified will be described.

[0080] The vehicle control device 10 in the second embodiment is configured to acquire only data related to sensor information and data related to output results based on the installed program without executing the program to be verified. In other words, in the fourth embodiment, a data collection mode is set in which the program to be verified is not executed.

[0081] The configuration and functions of the shadow mode according to the second embodiment will be described below. In the second embodiment, the verification processing unit 11 is not provided, and the processing unit 10a performs processing related to the shadow mode. As in the first embodiment, the verification processing unit 11 may be provided and may perform processing in place of the processing unit 10a. Furthermore, the verification target program is not stored.

[0082] 4, in the second embodiment, the arithmetic processing device 10a of the vehicle control device 10 has a function as an input unit 112, a function as a processing unit 113, a function as a data acquisition unit 114, a function as a classification unit 115, a function as a compression unit 116, and a function as a transmission unit 117. These functions are realized by the arithmetic processing device 10a as the arithmetic processing device 10a executes an in-vehicle program stored in the storage unit 10b.

[0083] The input unit 112 inputs sensor information from the sensor 20. The input unit 112 inputs some or all of the input sensor information to the processing unit 113 as input values ​​for the implementation program. The input unit 112 also inputs some or all of the input sensor information to the data acquisition unit 114.

[0084] The processing unit 113 runs the implementation program and performs processing based on various functions (application programs) realized by the implementation program, based on input values ​​(sensor information) input from the input unit 112. The processing unit 113 then inputs control signals (control signals for the actuator 30) as the processing results to the data acquisition unit 114. These control signals are also input to the actuator 30.

[0085] The data acquisition unit 114 determines whether or not an acquisition condition is met based on at least one of the input value (sensor information) input from the input unit 112 and the output result (control signal) input from the processing unit 13. The acquisition condition is the same as in the first embodiment, and therefore a description thereof will be omitted.

[0086] When the acquisition condition is met, the data acquisition unit 114 stores data related to the input values ​​and output results in the storage unit 10b. As described above, the input values ​​include, for example, sensor information input to the arithmetic processing device 10a. The output results include, for example, control signals processed and output based on the implementation program.

[0087] Furthermore, after the acquisition condition is satisfied, until a predetermined period of time has elapsed, the data acquisition unit 114 of the arithmetic processing device 10a may input sensor information (vehicle speed, yaw rate, acceleration amount, accelerator pedal operation amount, brake pedal operation amount, steering angle, etc.) detected when a control signal processed and output based on the implementation program is input to the actuator 30 and the vehicle 101 operates, and store the information in the storage unit 10b. In other words, the sensor information related to the actual operation of the vehicle 101 for each scene, that is, the sensor information necessary to verify the correct operation, may also be stored.

[0088] The classification unit 115, compression unit 116, and transmission unit 117 are similar to the classification unit 15, compression unit 16, and transmission unit 17 in the first embodiment, and therefore description thereof will be omitted.

[0089] The flow of data acquisition in this embodiment will be described below with reference to Fig. 5. The flow of data acquisition shown below is the flow of data acquisition processing performed by the arithmetic processing device 10a. This processing is performed after the shadow mode is set.

[0090] First, the input unit 112 of the arithmetic processing device 10a inputs sensor information from the sensor 20 (step S201). The processing unit 113 of the arithmetic processing device 10a runs an implementation program and performs processing based on various functions realized by the implementation program, based on the input values ​​(sensor information) input from the input unit 12 (step S202). In step S202, the processing unit 113 inputs control signals as the processing results to the actuator 30 and the data acquisition unit 114.

[0091] The data acquisition unit 114 determines whether or not an acquisition condition is met based on at least one of the input value (sensor information) and the output result (control signal, etc.) (step S203).

[0092] If the determination result is positive (if the acquisition condition is met), the classification unit 115 of the arithmetic processing device 10a classifies the data related to the input values ​​and output results (step S204). Specifically, the classification unit 115 estimates the scene in which the vehicle 101 is traveling based on the sensor information input in step S201. Then, the classification unit 115 classifies the data related to the input values ​​and output results into the estimated scene.

[0093] Then, the data acquisition unit 114 stores (acquires) data regarding the input values ​​and output results in the storage unit 10b (step S205). When storing the data, the data acquisition unit 114 stores the data so that the data regarding the input values ​​and output results is classified for the scenes classified (estimated) by the classification unit 115 in step S204. In this embodiment, the data to be stored is stored in association with tag information regarding the classified scenes. The data acquisition unit 114 also stores the acquisition conditions that were met in association with the data. Then, the processing ends. On the other hand, if the determination result in step S203 is negative, the arithmetic processing device 10a ends the processing as is.

[0094] These processes are executed at regular intervals after the shadow mode is set. The transmitter 117 transmits the data acquired by the data acquisition unit 114 and stored in the storage unit 10b to the server 102 via the communication network 103 at a predetermined transmission timing. At that time, the transmitter 117 also transmits tag information related to the scene associated with the data and information related to the acquisition conditions that have been met. The process of the server 102 is the same as in the first embodiment, and therefore will not be described.

[0095] According to the second embodiment, the following effects are achieved.

[0096] Since the program to be verified is not executed, the processing load can be reduced, and therefore the verification processing unit 11 does not need to be provided.

[0097] (Variation of the Second Embodiment) In the second embodiment, the data acquisition unit 114 acquires data related to the output results (control signals) based on the operation of the implementation program. However, it is not necessary to acquire data related to the output results based on the operation of the implementation program. In this case, it is also possible to acquire only sensor information that serves as an input value. Furthermore, it is also possible to acquire sensor information (vehicle speed, yaw rate, acceleration amount, accelerator pedal operation amount, brake pedal operation amount, steering angle, etc.) detected when the control signal processed and output based on the implementation program is input to the actuator 30 and the vehicle 101 operates.

[0098] In the second embodiment, the implementation program is executed to perform various driving assistance functions during the data collection mode, but the various driving assistance functions do not have to be executed during the data collection mode. In other words, during the data collection mode, sensor information (vehicle speed, yaw rate, acceleration amount, accelerator pedal operation amount, brake pedal operation amount, steering angle, etc.) detected when the vehicle 101 is operating may be acquired based on operations by the driver.

[0099] More specifically, the input unit 112 receives sensor information from the sensor 20 and inputs part or all of the received sensor information to the data acquisition unit 114 .

[0100] The data acquisition unit 114 determines whether or not an acquisition condition is met based on the input value (sensor information) input from the input unit 112. The acquisition condition is the same as in the first embodiment, and therefore a description thereof will be omitted.

[0101] When an acquisition condition is met, the data acquisition unit 114 stores data related to the input values ​​in the storage unit 10b. After the acquisition condition is met, the data acquisition unit 114 of the arithmetic processing device 10a inputs sensor information detected when the vehicle 101 is operating based on an operation by the driver via the input unit 112 or the like, and stores data related to the sensor information in the storage unit 10b. The sensor information detected when the vehicle 101 is operating includes vehicle speed, yaw rate, acceleration amount, accelerator pedal operation amount, brake pedal operation amount, steering angle, etc. After the acquisition condition is met, the data acquisition unit 114 inputs and stores the sensor information until a predetermined time has elapsed. The predetermined time may be changed depending on the type of acquisition condition that has been met.

[0102] The classification unit 115, compression unit 116, and transmission unit 117 are similar to the classification unit 15, compression unit 16, and transmission unit 17 in the first and second embodiments, and therefore description thereof will be omitted.

[0103] The flow of data acquisition in this modified example will be described below with reference to Fig. 6. The flow of data acquisition shown below is the flow of data acquisition processing performed by the arithmetic processing device 10a. This processing is performed after the shadow mode is set.

[0104] First, the input unit 112 of the arithmetic processing device 10a inputs sensor information from the sensor 20 (step S301). The data acquisition unit 114 determines whether an acquisition condition is met based on the input value (sensor information) (step S302).

[0105] If the determination result is positive (if the acquisition condition is met), the classification unit 115 of the arithmetic processing device 10a classifies the data related to the input values ​​(sensor information) (step S303). Specifically, the classification unit 115 estimates the scene in which the vehicle 101 is traveling based on the sensor information input in step S201. Then, the classification unit 115 classifies the data related to the input values ​​into the estimated scene.

[0106] Then, the data acquisition unit 114 stores data related to the input values ​​in the storage unit 10b (step S304). The data acquisition unit 114 also receives sensor information detected when the vehicle 101 is operating until a predetermined period of time has elapsed, and stores the data related to the sensor information in the storage unit 10b. When storing the data, the data acquisition unit 114 stores the data so that the data related to the input values ​​is classified into the scenes classified (estimated) by the classification unit 115 in step S303. In this embodiment, the data to be stored is stored in association with tag information related to the classified scenes. The data acquisition unit 114 also stores the fulfilled acquisition conditions in association with the data. Then, the processing ends. On the other hand, if the determination result is negative, the arithmetic processing device 10a ends the processing. The following description is the same as that of the second embodiment, and will not be repeated.

[0107] The controller and methods described herein may be implemented by a special-purpose computer configured with a processor and memory programmed to perform one or more functions embodied in a computer program. Alternatively, the controller and methods described herein may be implemented by a special-purpose computer configured with a processor configured with one or more dedicated hardware logic circuits. Alternatively, the controller and methods described herein may be implemented by one or more special-purpose computers configured with a processor and memory programmed to perform one or more functions in combination with a processor configured with one or more hardware logic circuits. Furthermore, the computer program may be stored as instructions executed by a computer on a computer-readable non-transitory storage medium.

[0108] The following describes technical ideas that can be derived from the above-described embodiment and modifications.

[0109] [Configuration 1] A vehicle control device (10) mounted on a vehicle (101), comprising: a data acquisition unit (14) that acquires data related to sensor information acquired by various sensors (20) mounted on the vehicle; a classification unit (15) that classifies the data acquired by the data acquisition unit for each scene in which the vehicle is traveling based on the sensor information; a compression unit (16) that deletes any of a plurality of data classified by the classification unit into a predetermined scene, or compresses the data by thinning out some of the components of the data; and a transmission unit (17) that transmits the data compressed by the compression unit to a server (102) via a communication network (103).

[0110] [Configuration 2] The vehicle control device is configured to be able to implement a shadow mode in which the program to be verified operates in a manner not related to the control of the vehicle, and the data acquisition unit uses sensor information acquired by various sensors mounted on the vehicle as input values, and when the program to be verified is executed or has been executed, acquires data related to the output results together with data related to the sensor information, or acquires data related to the output results instead of data related to the sensor information. This is the vehicle control device described in Configuration 1.

[0111] [Configuration 3] A vehicle control device according to configuration 1 or 2, wherein a plurality of data items classified into predetermined scenes and stored in a storage unit (10b) are prioritized in the order of specific parameters included in the data, and the compression unit compresses the plurality of data items included in the predetermined scenes in order of lowest priority, depending on the remaining storage capacity of the storage unit that stores the data.

[0112] [Configuration 4] The vehicle control device according to Configuration 3, wherein the specific parameters include any of vehicle speed, time of day when the vehicle is traveling, weather, road, type of detected target, shape of detected target, position of detected target, distance to detected target, speed of detected target, and time to collision until the detected target, and the specific parameters vary depending on the scene.

[0113] [Configuration 5] The vehicle control device according to Configuration 3, wherein the data acquisition unit, when storing acquired data in the storage unit, stores the data by specifying an address in the storage unit for each priority of the data, and the compression unit, when the remaining storage capacity of the storage unit is low, deletes data stored in an address with a low priority, thereby freeing up data space and increasing the storage capacity.

[0114] [Configuration 6] The vehicle control device according to any one of configurations 1 to 5, wherein a data responsiveness or a time resolution is set in advance for each of the scenes, and when transmitting data of a scene with low responsiveness or low time resolution, the transmission unit thins out the data before transmitting it.

[0115] [Configuration 7] A vehicle control device according to any one of configurations 1 to 6, wherein a data responsiveness or time resolution is set in advance for each of the scenes, and the compression unit compresses data classified into scenes with low responsiveness or low time resolution in accordance with the remaining storage capacity of a storage unit that stores the data.

[0116] [Configuration 8] The vehicle control device according to any one of Configurations 1 to 7, wherein the classification unit uses a deep neural network to recognize a similar scene from among a plurality of scenes already stored based on the sensor information, or recognize a similar scene from among a plurality of predetermined reference scenes, and classify the data into the recognized scene.

[0117] [Configuration 9] An on-board program executed by a vehicle control device (10) mounted on a vehicle (101), the on-board program causing the vehicle control device to perform the following steps: a data acquisition step of acquiring data related to sensor information acquired by various sensors (20) mounted on the vehicle; a classification step of classifying the data acquired in the data acquisition step for each scene in which the vehicle is traveling based on the sensor information; a compression step of deleting any of multiple data classified into a predetermined scene in the classification step or compressing the data by thinning out some of the components of the data; and a transmission step of transmitting the data compressed in the compression step to a server (102) via a communication network (103).

[0118] Although the present disclosure has been described with reference to the embodiments, it is understood that the present disclosure is not limited to the embodiments or structures. The present disclosure also encompasses various modifications and equivalent modifications. In addition, various combinations and forms, including only one element, more than one element, or less than one element, are also within the scope and spirit of the present disclosure.

Claims

1. A vehicle control device (10) mounted on a vehicle (101), comprising: a data acquisition unit (14) that acquires data relating to sensor information acquired by various sensors (20) mounted on the vehicle; a classification unit (15) that classifies the data acquired by the data acquisition unit for each scene in which the vehicle is traveling based on the sensor information; a compression unit (16) that deletes any of the multiple data classified by the classification unit into a predetermined scene or compresses the data by thinning out some of the components of the data; and a transmission unit (17) that transmits the data compressed by the compression unit to a server (102) via a communication network (103).

2. The vehicle control device is configured to be able to implement a shadow mode in which the program to be verified operates in a manner not related to the control of the vehicle, and the data acquisition unit uses sensor information acquired by various sensors mounted on the vehicle as input values ​​and acquires data regarding the output results when the program to be verified is executed or has been executed, together with data regarding the sensor information, or acquires data regarding the output results instead of data regarding the sensor information.

3. A vehicle control device as described in claim 1 or 2, wherein the priority of multiple data classified into a specified scene and stored in the memory unit (10b) is set in the order of specific parameters contained in the data, and the compression unit compresses the multiple data contained in the specified scene in order of lowest priority, depending on the remaining storage capacity of the memory unit that stores the data.

4. A vehicle control device as described in claim 3, wherein the specific parameters include any of the vehicle speed, time of day when the vehicle is traveling, weather, road, type of detected target, shape of detected target, position of detected target, distance to detected target, speed of detected target, and time to collision until the detected target, and the specific parameters differ for each scene.

5. A vehicle control device as described in claim 1 or 2, wherein when storing acquired data in the memory unit, the data acquisition unit stores the data by specifying an address in the memory unit for each priority of the data, and when the remaining storage capacity of the memory unit becomes low, the compression unit deletes data stored in addresses with low priority, freeing up data area and increasing storage capacity.

6. A vehicle control device as described in claim 1 or 2, wherein the data responsiveness or time resolution is set in advance for each of the scenes, and when transmitting data for scenes with low responsiveness or time resolution, the transmitting unit thins out the data before transmitting it.

7. A vehicle control device as described in claim 1 or 2, wherein the responsiveness or time resolution of data is set in advance for each scene, and the compression unit compresses data classified as scenes with low responsiveness or time resolution in order, depending on the remaining storage capacity of the storage unit that stores the data.

8. A vehicle control device as described in claim 1 or claim 2, wherein the classification unit uses a deep neural network to recognize similar scenes from among a plurality of scenes already stored based on the sensor information, or recognize similar scenes from among a plurality of predetermined reference scenes, and classify the data into the recognized scenes.

9. An on-board program executed by a vehicle control device (10) mounted on a vehicle (101), the on-board program causing the vehicle control device to perform the following steps: a data acquisition step for acquiring data relating to sensor information acquired by various sensors (20) mounted on the vehicle; a classification step for classifying the data acquired in the data acquisition step for each scene in which the vehicle is traveling based on the sensor information; a compression step for deleting any of the multiple data classified into a specified scene in the classification step or compressing the data by thinning out some of the components of the data; and a transmission step for transmitting the data compressed in the compression step to a server (102) via a communication network (103).

Images