Vehicle control devices and onboard programs

By setting characteristic information in the vehicle control device and changing the data acquisition conditions, only necessary sensor information and output results are collected and transmitted, solving the load problem caused by the large amount of data in the prior art and realizing efficient data collection and analysis.

CN123125634APending Publication Date: 2026-11-17DENSO CORP
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202580029126.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Priority Date
2024-04-22
Filing Date
2025-04-08
Publication Date
2026-11-17

Smart Images

  • Figure CN123125634A_ABST
    Figure CN123125634A_ABST
Patent Text Reader

Abstract

The vehicle control device (10) of the present invention includes: a characteristic setting unit (15) that acquires at least one of information related to the vehicle itself, information related to the owner of the vehicle, information related to the driving status of the vehicle, and information related to the area where the vehicle is driven, and sets characteristic information of the vehicle during driving based on this information; a data acquisition unit (14) that, when data acquisition conditions are met, acquires data related to sensor information acquired by various sensors mounted on the vehicle; and a transmission unit (17) that transmits the data acquired by the data acquisition unit to a server via a communication network. Based on the characteristic information, at least one of the acquisition conditions and the data acquired by the data acquisition unit is changed.
Need to check novelty before this filing date? Find Prior Art

Description

[0001] Cross-references to related applications

[0002] This application is based on Japanese Patent Application No. 2024-069040, filed on April 22, 2024, the contents of which are incorporated herein by reference. Technical Field

[0003] This disclosure relates to vehicle control devices and onboard programs. Background Technology

[0004] In recent years, various data collected from vehicles after they are sold are sent to servers via communication networks. The data collected from these servers is then analyzed and effectively used for future vehicle development or to update the vehicle's control programs.

[0005] As an example, to verify the performance and safety of a program, a known verification method, known as shadow mode, involves activating the program of the verification object while the vehicle is in operation after sale to confirm the output value. In shadow mode-based verification, for example, the program of the verification object is activated in the background, that is, in a manner independent of vehicle control, and data related to the output value is stored. This data is then collected by a server via a communication network or similar means. The collected data is then analyzed to verify the operation of the program of the verification object. Such shadow mode-related techniques are described, for example, in Patent Document 1.

[0006] Patent document 1: International Publication No. 2022 / 004324.

[0007] Furthermore, collecting data from all vehicles across all scenarios and related to all driving conditions presents a massive data burden. The data volume increases further when verifying all procedures. Such a large data volume leads to increased communication, processing, and analysis loads. Additionally, the inclusion of data unnecessary for verification also reduces efficiency. Summary of the Invention

[0008] This disclosure was made in view of the above circumstances, and its main purpose is to provide a vehicle control device and on-board program capable of efficiently collecting the required data.

[0009] The first vehicle control device for solving the above-mentioned problems includes, in a vehicle control device mounted on a vehicle: a characteristic setting unit that acquires at least one of the following: information related to the vehicle itself, information related to the owner of the vehicle, information related to the driving status of the vehicle, and information related to the area where the vehicle is driving, and sets characteristic information of the vehicle during driving based on this information; a data acquisition unit that, when data acquisition conditions are met, acquires data related to sensor information acquired by various sensors mounted on the vehicle; and a transmission unit that transmits the data acquired by the data acquisition unit to a server via a communication network, and changes at least one of the acquisition conditions and the data acquired by the data acquisition unit according to the characteristic information.

[0010] The second vehicle control device for solving the above-mentioned problem is mounted on a vehicle and configured to implement a shadow mode in which the verification target program operates in a manner independent of the control of the vehicle. The vehicle control device includes: a characteristic setting unit that acquires at least one of the following: information related to the vehicle itself, information related to the owner of the vehicle, information related to the driving status of the vehicle, and information related to the location where the vehicle is driving, and sets characteristic information of the vehicle during driving based on this information; a modification unit that modifies part or all of the verification target program according to the characteristic information; a data acquisition unit that takes sensor information acquired by various sensors mounted on the vehicle as input values, and acquires data related to the output result and data related to the sensor information when the verification target program is implemented or has already been implemented, provided that the data acquisition conditions are met, or acquires data related to the output result instead of data related to the sensor information; and a transmission unit that transmits the data acquired by the data acquisition unit to a server via a communication network.

[0011] The first vehicle-mounted program for solving the above-mentioned problem is a vehicle-mounted program implemented by a vehicle control device installed in the vehicle, which causes the vehicle control device to perform: a characteristic setting step, which acquires at least one of the following: information related to the vehicle itself, information related to the owner of the vehicle, information related to the driving status of the vehicle, and information related to the area where the vehicle is driving, and sets the characteristic information of the vehicle during driving based on this information; a data acquisition step, which, when the data acquisition conditions are met, acquires data related to sensor information acquired by various sensors installed in the vehicle; and a transmission step, which transmits the data acquired by the data acquisition step to a server via a communication network, and changes at least one of the acquisition conditions and the data acquired by the data acquisition step according to the characteristic information.

[0012] The second vehicle-mounted program for solving the aforementioned problem is an in-vehicle program implemented by a vehicle control device mounted on a vehicle. This vehicle control device is configured to implement a shadow mode that allows the verification target program to operate in a manner independent of vehicle control. The in-vehicle program causes the vehicle control device to perform the following steps: a characteristic setting step, acquiring at least one of the following: information related to the vehicle itself, information related to the vehicle's owner, information related to the vehicle's driving status, and information related to the region where the vehicle is driving; setting characteristic information of the vehicle during driving based on this information; a modification step, modifying part or all of the verification target program according to the aforementioned characteristic information; a data acquisition step, using sensor information acquired by various sensors mounted on the vehicle as input values, acquiring data related to the output result and data related to the sensor information, or acquiring data related to the output result instead of the data related to the sensor information, provided that the data acquisition conditions are met, when implementing or having already implemented the verification target program; and a transmission step, transmitting the data acquired in the data acquisition step to a server via a communication network. Attached Figure Description

[0013] The above-mentioned objects, as well as other objects, features, and advantages of this disclosure, will become more apparent from the accompanying drawings and from the following detailed description. The accompanying drawings are as follows:

[0014] Figure 1 This is a simplified structural diagram of the data collection system.

[0015] Figure 2 This is a block diagram representing the functionality of the verification-based computing device.

[0016] Figure 3 It is a diagram used to illustrate basic information.

[0017] Figure 4 It is a diagram used to illustrate characteristic information.

[0018] Figure 5 This is a diagram used to illustrate the method for changing the acquisition conditions.

[0019] Figure 6 This is a diagram used to illustrate the method for changing the acquisition conditions.

[0020] Figure 7 This is a diagram used to illustrate the method for changing the acquisition conditions.

[0021] Figure 8 This is a flowchart of data acquisition and processing.

[0022] Figure 9This is a flowchart of the data acquisition and processing in the second embodiment.

[0023] Figure 10 This is a flowchart of the data acquisition and processing in the third embodiment.

[0024] Figure 11 This is a block diagram illustrating the functions of the arithmetic processing device based on the fourth embodiment.

[0025] Figure 12 This is a flowchart of the data acquisition and processing in the fourth embodiment.

[0026] Figure 13 This is a flowchart of the data acquisition and processing in the variant example. Detailed Implementation

[0027] Hereinafter, embodiments of the vehicle control device and on-board program in this disclosure will be described in detail with reference to the accompanying drawings. Furthermore, in principle, the same or equivalent parts in the drawings will be labeled with the same reference numerals between embodiments and variations, and their descriptions will not be repeated.

[0028] (First Implementation)

[0029] Figure 1 This refers to the data collection system 100 of the vehicle control device 10 used in this embodiment. The vehicle control device 10 is mounted on the vehicle 101 and performs vehicle 101 control and driving assistance.

[0030] like Figure 1 As shown, the data collection system 100 includes a server 102 and can communicate with one or more vehicles 101 via a communication network 103, such as the Internet. Figure 1 The image shows only one vehicle 101. Vehicle 101 includes a vehicle control device 10, sensors 20, and actuators 30, etc.

[0031] Sensor 20 includes various sensors used to determine the driving status of vehicle 101, such as vehicle speed sensor 21, acceleration sensor 22, and yaw rate sensor 23. The sensors used to determine the driving status of vehicle 101 may include other sensors, or may not include any one of vehicle speed sensor 21, acceleration sensor 22, and yaw rate sensor 23.

[0032] In addition, sensor 20 includes various sensors such as camera 24 and millimeter-wave radar 25 for detecting other vehicles and obstacles. The sensors used to detect other vehicles and obstacles are not limited to millimeter-wave radar 25; they can also be LiDAR, ultrasonic sensors, etc., and multiple combinations of these can be used. Furthermore, camera 24 can be a single-lens camera or a compound-lens camera. Additionally, camera 24 can capture either still images or moving images. Furthermore, the number, position, and type of camera 24 can be arbitrarily changed. For example, it can include a front camera that captures the area in front of the vehicle, a right-side camera that captures the area to the right of the vehicle, a left-side camera that captures the area to the left of the vehicle, and a rear camera that captures the area behind the vehicle.

[0033] In addition, the sensor 20 includes various sensors for detecting various amounts of driver input, such as an accelerator sensor 26 for detecting the amount of accelerator input based on the driver, a brake sensor 27 for detecting the amount of brake input, and a steering angle sensor 28 for detecting the amount of steering input (steering angle) based on the driver's handle (steering wheel).

[0034] These sensors 20 are connected to the vehicle control unit 10 wirelessly or via wired connection, and the measurement results (or detection results) of these sensors 20 are input into the vehicle control unit 10 as sensor information.

[0035] The actuator 30 may include, for example, a motor that serves as the main unit of the vehicle 101 and is used to drive the vehicle 101. It may also include actuators for controlling the movement of the vehicle 101, such as actuators for operating the steering wheel, the brake pedal, and the accelerator pedal. Furthermore, the actuator 30 may include devices for activating accessories of the vehicle 101, such as displays, speakers, indicators, and headlights. The driving and movement of the vehicle 101 are controlled by this actuator 30.

[0036] The vehicle control unit 10 is primarily composed of a microcomputer equipped with a processing unit 10a such as a CPU and a storage unit 10b such as various memories. The functions provided by the microcomputer can be provided by software recorded in a physical storage device and a computer executing that software, software only, hardware only, or a combination thereof. For example, when the microcomputer is provided by electronic circuitry as hardware, it can be provided by digital circuitry or analog circuitry containing multiple logic circuits. For example, the processing unit 10a of the microcomputer executes a program stored in a non-transitory tangible storage medium, which is its own storage unit 10b. The program, for example, includes implementations... Figure 2The program, as shown, performs the functions described above. By executing the program, the corresponding methods are executed. The storage unit 10b is, for example, non-volatile memory. Furthermore, the program stored in the storage unit 10b can be downloaded and updated via communication networks 103 such as OTA (Over-The-Air) or the Internet.

[0037] The vehicle control unit 10 has various functions (applications) for assisting in driving the vehicle 101, and through these functions, controls the actuator 30 based on sensor information input from the sensor 20.

[0038] Representative functions used to assist the driving of Vehicle 101 include, for example, Adaptive Cruise Control (ACC), Forward Collision Warning (FCW), Advanced Emergency Braking System (AEBS), Night Vision / Pedestrian Detection (NV / PD), Traffic Sign Recognition (TSR), Lane Departure Warning (LDW), Lane Keeping Assist System (LKAS), Rear Cross Traffic Alert (RCTA), Adaptive Frontlighting System (AFS), and Advanced Parking Assist (APA). Vehicle 101 may possess all of these functions or only some of them. Additionally, it may also possess other driving assistance functions. Furthermore, it may include functions for achieving autonomous driving of Vehicle 101. Furthermore, these functions are implemented by the arithmetic processing unit 10a executing the driving assistance control program stored in the storage unit 10b.

[0039] Furthermore, to verify the performance and safety of the driver assistance control program, the vehicle control device 10 has a function called "shadow mode" that enables the driver assistance control program (hereinafter referred to as the verification object program) to operate during the driving of the vehicle after it has been sold, that is, in actual use cases, to verify the output value. In shadow mode-based verification, for example, the verification object program is operated in the background, that is, in a manner unrelated to vehicle control, and data related to the output value is stored, etc., and the server 102 collects the data related to the output value via the communication network 103. In addition, shadow mode is a data collection mode used for collecting data.

[0040] The following describes the structure and functions related to the shadow mode in this embodiment. The switching to shadow mode can occur at any time. For example, it can be switched based on the driver's operation or by an instruction from the server 102. Alternatively, it can switch to shadow mode simultaneously with the ignition switch being turned on.

[0041] Furthermore, in order to compare the driver assistance control program that actually enables vehicle 101 to operate with the verification target program, the following is an installation procedure. Additionally, in Figure 1 The term "installation program" is also used. Considering the processing burden during the installation process, the vehicle control unit 10 includes a verification processing unit 11 for implementing the verification target program. The verification processing unit 11 only needs to have the performance required for implementing the verification target program; it may have the same performance as the processing unit 10a, or it may be different. The verification target program is stored in the storage unit 10b. Alternatively, a storage unit dedicated to shadow mode may be provided.

[0042] By executing the verification object program, various functions for assisting the driving of vehicle 101 are implemented in the background. The functions implemented by executing the verification object program may be the same as the functions actually implemented by the arithmetic processing unit 10a, or some may be omitted. In addition, functions other than those actually implemented by the arithmetic processing unit 10a may also be implemented.

[0043] When the verification processing unit 11 operates the verification target program in shadow mode, it receives sensor information from various sensors 20, similar to the processing unit 10a. Then, based on the input sensor information, the verification processing unit 11 performs various functions and outputs various control signals to activate each actuator. 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 this time, the verification processing unit 11 also establishes an association with the data related to the sensor information that is the input value.

[0044] Furthermore, the verification processing unit 11 inputs sensor information as input values ​​to the processing unit 10a, and also inputs control signals processed and output by the installation program. These control signals are stored in the storage unit 10b as data related to the output results. In other words, in order to compare and verify the output results in the installation program and the output results in the verification target program, the control signals processed and output by the installation program are also stored.

[0045] Furthermore, the verification processing unit 11 can also input control signals processed and output based on the installation procedure to the actuator 30. As a result, sensor information detected when the vehicle 101 performs an action (vehicle speed, yaw rate, acceleration, accelerator pedal operation, brake pedal operation, steering angle, etc.) is input and stored in the storage unit 10b. In other words, sensor information related to the actual action of the vehicle 101 for each scenario can also be stored at the same time, that is, sensor information required to verify the action as correct.

[0046] The vehicle control unit 10 uploads the data stored in the storage unit 10b to the server 102 via the communication network 103 at a predetermined transmission time. The predetermined transmission time is arbitrary, for example, when an upload instruction is received from the server 102. Alternatively, it could be when the vehicle 101 is charging, when the vehicle is parked, or when the ignition switch is turned off, etc.

[0047] Furthermore, there is a high possibility that the storage capacity of the storage unit 10b may be insufficient in order to store all the data from the movement of vehicle 101. Additionally, if all vehicles 101 upload all the stored data, there is a concern that this would place an excessive burden on the communication network 103. Moreover, if the server 102 were to analyze all the uploaded data, there is also a problem that the processing load on the server 102 would become too heavy. Furthermore, acquiring and analyzing all the data in the first place would also be quite wasteful.

[0048] Therefore, it is preferable to configure the system to store and transmit only the amount of data required for verification and analysis. Furthermore, to facilitate analysis by the server 102, it is preferable to include metadata (tag information) in the data. Thus, the vehicle control device 10 of this embodiment is configured to identify which state of the vehicle 101 acquired the data, and to store and transmit only the data acquired by the vehicle 101 in the specified state. A detailed description will follow.

[0049] like Figure 2As shown, the verification processing unit 11 of the vehicle control device 10 has the functions of an input unit 12, a processing unit 13, a data acquisition unit 14, a characteristic setting unit 15, a modification unit 16, and a transmission unit 17. These functions are implemented by the verification processing unit 11 by executing the on-board program stored in the storage unit 10b.

[0050] Input unit 12 inputs sensor information from sensor 20. Then, input unit 12 inputs part or all of the input sensor information as input values ​​for the verification target program to processing unit 13. In addition, input unit 12 inputs part or all of the input sensor information to data acquisition unit 14.

[0051] The processing unit 13 causes the verification target program to operate, and performs processing based on the input values ​​(sensor information) input from the input unit 12, performing various functions (application programs) implemented by the verification target program. Then, the processing unit 13 inputs control signals (control signals of the actuator 30) as the result of its processing to the data acquisition unit 14. Furthermore, as mentioned above, these control signals are not input to the actuator 30.

[0052] The data acquisition unit 14 determines whether the acquisition condition (also called the trigger 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.

[0053] Acquisition conditions may include thresholds of one or more parameters as constituent elements. Parameters for acquisition conditions may, for example, be any one of the parameters contained in sensor information such as vehicle speed, yaw rate, accelerator operation amount, brake operation amount, and steering input, or any parameter contained in output results such as requested torque and output indication signals to the display. Additionally, parameters calculated or inferred based on sensor information and output results may be included. For example, the relative distance to obstacles (vehicles ahead, pedestrians, etc.), the relative speed relative to obstacles, and the time-to-collision (TTC) calculated based on the recognition results of camera images and the detection results of millimeter-wave radar 25 may be set as parameters for acquisition conditions. Furthermore, the difference between the output results based on the installer and the output results based on the verification object program may be set as a parameter for acquisition conditions. For example, the difference between the brake operation amount output by the processing based on the installer and the brake operation amount output by the processing based on the verification object program may be set as a parameter. The threshold may be one of the upper and lower limits of any of these parameters, or both.

[0054] Alternatively, whether the scenario in which vehicle 101 is driving (hereinafter referred to as the scenario) is a pre-determined acquisition scenario can also be used as a constituent element of the acquisition conditions. A scenario refers to various scenarios envisioned when vehicle 101 is driving, such as a scenario of overtaking a vehicle in front, a scenario of passing between vehicles, a scenario of following a vehicle in front, a scenario of pedestrians crossing in front of vehicle 101 at night, a scenario of vehicle 101 merging from the acceleration lane to the main lane on a dedicated motor vehicle road, a scenario of stopping, a scenario of waiting at a signal, etc.

[0055] These scenes are inferred based on sensor information. For example, the vehicle control unit 10 can recognize camera images and infer the scene. More specifically, sensor information such as camera images can be input into a machine learning-completed inference model such as a deep neural network to infer the scene. Furthermore, image recognition does not need to be performed by the vehicle control unit 10; it can be performed by an external device of the vehicle control unit 10, such as an image recognition device, and its results can be used as sensor information input.

[0056] Alternatively, implemented functions (implemented functions) from various functions (application programs) of the verification object program can also be used as components of the acquisition conditions. For example, if a collision damage mitigation braking control function is implemented, the acquisition conditions can also be met. Furthermore, which function has been implemented can be determined based on the output result (control signal) input from the processing unit 13.

[0057] In this embodiment, the acquisition conditions are set by combining the acquisition scenario, the implemented function, and the threshold of the parameter (i.e., AND condition). For example, in the scenario of following the vehicle in front, if the vehicle speed (the parameter of the acquisition condition) is above the threshold (50km / h), the acquisition condition can also be set to be true.

[0058] Furthermore, the combination of components of an acquisition condition can be an acquisition scenario and an implemented function, an acquisition scenario and a parameter threshold, or an implemented function and a parameter threshold. Additionally, as a component of an acquisition condition, there can be two or more implemented functions; in this case, the implemented functions can be AND conditions or OR conditions. For example, both the forward vehicle approach warning function and the collision damage mitigation braking control function can be implemented as conditions, or either one can be implemented as a condition. Similarly, the parameter threshold can be the threshold of two or more parameters.

[0059] Furthermore, the acquisition condition being met refers to the situation where all the constituent elements constituting the acquisition condition are satisfied. For example, if the acquisition scenario of the acquisition condition is "following the vehicle in front", the implementation function of the above acquisition condition is "following driving function", and the threshold of the parameter of the above acquisition condition is "above 50km / h", then in the scenario of following the vehicle in front, if the following driving function is implemented and the vehicle speed (the parameter of the acquisition condition) is above the threshold (50km / h), then the above acquisition condition is met.

[0060] Furthermore, the acquisition conditions are not limited to one; multiple acquisition conditions can be set. For example, the first acquisition condition could be a scenario where the vehicle is following the vehicle in front and the vehicle speed is above a first threshold. The second acquisition condition could be a scenario where a pedestrian crosses in front of the vehicle 101, and the distance between the vehicle and the pedestrian is below a second threshold and the braking amount is above a third threshold.

[0061] When any one of the acquisition conditions is met, the data acquisition unit 14 stores the data related to the input value and the output result in the storage unit 10b. As described above, the input value includes, for example, sensor information input to the verification processing device 11. The output result includes, for example, control signals processed and output based on the verification object program, and control signals processed and output based on the installation program. Additionally, the output result may also include sensor information related to the actual movement of the vehicle 101 for each scenario. Furthermore, the output result may also include the difference between the output result of the installation program and the output result of the verification object program. Moreover, the stored (acquired) data can change depending on the acquisition conditions that are met. For example, when the acquisition condition is met in a scenario where the vehicle is following another vehicle and the vehicle speed is at or above a first threshold, data related to the vehicle speed is acquired. On the other hand, when the acquisition condition is met in a scenario where a pedestrian is crossing in front of the vehicle 101 and the distance between the vehicle and the pedestrian is at or below a second threshold, and the brake operation amount is at or above a third threshold, data related to the brake operation amount can also be acquired.

[0062] Next, the characteristic setting unit 15 will be described. The characteristic setting unit 15 acquires at least one of the following: information related to the vehicle 101 itself, information related to the owner (purchaser) of the vehicle 101, information related to the driving status of the vehicle 101, and information related to the location where the vehicle 101 is located, and sets the characteristic information of the vehicle 101 when it is in motion based on this information. In addition, the driving time is not limited to actual driving time, but also includes driving time when the vehicle is parked, as long as the ignition switch is turned on (the power is turned on). In addition, sometimes the information related to the vehicle 101 itself, the information related to the owner (purchaser) of the vehicle 101, the information related to the driving status of the vehicle 101, and the information related to the location where the vehicle 101 is located are collectively represented as basic information.

[0063] Reference Figure 3 The basic information is described in more detail. Information related to the vehicle 101 itself includes, for example, information related to the number, location, and type of sensors 20 mounted on the vehicle 101. In addition to this, information related to the vehicle 101 itself may also include vehicle model, width, height, size, shape, style, and weight. Information related to the vehicle 101 itself may be pre-stored in the storage unit 10b, or it may be input to the vehicle control device 10 and stored in the storage unit 10b by an input device (e.g., a touch panel display) from a dealer or the like.

[0064] Information related to the owner (purchaser) of vehicle 101 includes, for example, the owner's place of residence, family composition, gender, and age. Information related to vehicle 101 itself is input into the vehicle control device 10 by input devices such as dealers, and stored in the storage unit 10b.

[0065] Information related to the driving status of vehicle 101 includes information such as weather, time of travel, and road conditions. Road conditions refer to information about the road itself, such as whether it is a dedicated road for motor vehicles, a winding mountain road, or an urban road. This information is identified in real-time from camera images using image recognition technology employing deep neural networks and input into the vehicle control unit 10. Additionally, weather information can be identified and input via a rain sensor, or the time of travel can be identified and input via a clock mounted on vehicle 101. Furthermore, road conditions can also be identified and input via a navigation system.

[0066] Information related to the location where vehicle 101 is located includes, for example, the country (Japan, etc.) where vehicle 101 is located, the region (Kanto region, etc.) where vehicle 101 is located, and the city (Tokyo, etc.) where vehicle 101 is located. Additionally, it may include, for example, climate zone (temperate, heavy snow zone, rainstorm zone, dry zone, etc.). This information related to the location where vehicle 101 is located can be input into the vehicle control device 10 by a dealer or similar entity, and stored in the storage unit 10b. Alternatively, it can be identified and input in real time via a navigation system. In other words, the location information of vehicle 101 can be detected via GPS (Global Positioning System), and based on this location information, the country and region where vehicle 101 is located can be identified and input into the vehicle control device 10.

[0067] The characteristic setting unit 15 extracts and abstracts the necessary information from these basic information, or performs either extraction and abstraction, and converts it into one or more characteristic parameters representing the characteristics of the vehicle 101 when it is in motion, and sets them as characteristic information.

[0068] To store Figure 3 Based on the basic information K1 shown, the method for setting characteristic information will be explained in detail. First, the case where characteristic information is represented by three characteristic parameters: "age group", "presence or absence of cohabiting family member", and "country name" will be explained. In addition, in the following, characteristic information composed of multiple characteristic parameters such as "age group", "presence or absence of cohabiting family member", and "country name" will sometimes be represented as the first characteristic information.

[0069] The characteristic setting unit 15 extracts information from the basic information according to predetermined rules, abstracts the extracted information, and thus sets the first characteristic information. For example, such as Figure 4 As shown, the feature setting unit 15 extracts the "age" information from the basic information and abstracts it according to the rule of classifying those under 30 years old as "youth", those aged 31 to 60 as "middle-aged and elderly", and those aged 61 and above as "elderly", converting it into an "age class" that constitutes one of the feature parameters of the first feature information. For example, in the basic information K1, the "age" is "25 years old", so the feature setting unit 15 sets "youth" as one of the feature parameters of the feature information as the "age class".

[0070] Furthermore, in the basic information K1, "Regional Classification" is "Kanto Region," therefore, the feature setting unit 15 extracts the information for "Kanto Region" from the basic information K1 and abstracts it according to the rules for "Country Name." In this case, such as Figure 4 As shown, the feature setting unit 15 sets "Japan" as one of the feature parameters constituting the first feature information, which is the "country name".

[0071] Furthermore, in the basic information K1, "family composition" is "single," therefore, the feature setting unit 15 extracts the "single" information from the basic information K1 and abstracts it according to the rules in "presence or absence of cohabiting family members." In this case, such as Figure 4 As shown, the feature setting unit 15 is set to "none", which is one of the feature parameters constituting the first feature information, namely "the presence or absence of cohabiting family members".

[0072] Furthermore, extraction and abstraction can be rule-based, but they can also utilize inference models such as neural networks trained through machine learning to infer characteristic information from basic information. Additionally, extraction and abstraction are not always necessary; basic information can be directly used as characteristic information. This is especially true when the amount of basic information is limited.

[0073] Furthermore, the type of characteristic information can be arbitrarily set. For example, it can also be set to indicate more specific driving conditions. For instance, it could be set to characteristics indicating specific driving conditions such as "a sports car driven by a single person on a mountain road during a sunny day" or "a family car driven with family members in the city during a rainy night." Several specific driving conditions can be prepared in advance, and the most suitable driving condition can be selected based on the basic information. Additionally, in the following text, the characteristic information indicating specific driving conditions will sometimes be referred to as the second characteristic information.

[0074] The determination of second-characteristic information can be based on rules or inferential models. For example, Figure 4 As shown, the feature setting unit 15 can also input all the basic information K1 into the inference model, thereby inferring "when it is sunny during the day, a single person's sports car is driving on a mountain road", and setting it as the second feature information.

[0075] Alternatively, clustering based on basic information can be performed, and the resulting clusters can be used as characteristic information. For example, if a dataset consisting of multiple basic information items is pre-stored and clustered using a prescribed method, it can be divided into multiple predetermined clusters. Furthermore, if basic information such as owner information is included in the input dataset, and clustering is performed using a prescribed method, the dataset can be divided into any one of the predetermined clusters based on the similarity of the basic information. The clusters resulting from the division of the input basic information are then used as characteristic information. Additionally, in the following, the characteristic information determined by clustering may sometimes be referred to as third characteristic information.

[0076] For example, such as Figure 4 As shown, when the basic information K1 is included in the dataset for clustering and the result is classified as the first cluster, the feature setting unit 15 can also set the first cluster as the third feature information.

[0077] In this embodiment, the feature setting unit 15 may also use feature information of any one of the first feature information, the second feature information, and the third feature information.

[0078] The modification unit 16 modifies the acquisition conditions based on the characteristic information set by the characteristic setting unit 15. That is, it modifies the acquisition scenario and the threshold values ​​of the parameters in the acquisition conditions. The case where the first characteristic information is used will be explained. For example, such as... Figure 5 As shown, based on the first characteristic information T1 of the basic information K1 (where the characteristic parameters are "youth", "no family", and "Japan"), the acquisition scenario can be limited to "parking scenario", changing the acquisition conditions so that acquisition is not performed in other scenarios. Additionally, as... Figure 6 As shown, based on the first characteristic information T2 of the basic information K2 (where each characteristic parameter is "middle-aged and elderly", "has family members", or "USA"), it can also be changed to the case where the acquisition scenario is set to "following the vehicle in front" and the "vehicle speed" is above 50km / h, when the acquisition condition is met.

[0079] Furthermore, when using second characteristic information representing specific driving conditions, it is sufficient to change whether the condition is true or false according to each type of second characteristic information. For example, such as Figure 7 As shown, the condition can be met when the second characteristic information is "a single person's sports car is driving on a mountain road on a sunny day", but the condition cannot be met under other characteristic parameters (such as "a family car with family members is driving in the city on a rainy night").

[0080] Furthermore, when using third-characteristic information determined by clustering, the condition can be changed to true / false for each cluster. For example, the condition can be determined to be true if the third-characteristic information represents the first cluster, and false if the condition is not true in other clusters.

[0081] Furthermore, the information regarding how to change the acquisition conditions based on the characteristic information can be pre-stored in the storage unit 10b. Alternatively, it can be downloaded from an external device such as a server 102 via the communication network 103.

[0082] The sending unit 17 sends 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 sending time. The predetermined sending time is as described above.

[0083] The following is for reference Figure 8The data acquisition process in this embodiment will be described. The data acquisition process shown below is a verification process of the data acquisition processing implemented by the computing processing unit 11. These processes are performed after the shadow mode is set. The timing of setting the shadow mode is arbitrary, for example, when the ignition switch is turned on.

[0084] The characteristic setting unit 15 of the verification processing unit 11 acquires basic information and sets the characteristic information of the vehicle 101 during driving based on this basic information (step S101). Next, the modification unit 16 of the verification processing unit 11 modifies the acquisition conditions according to the characteristic information set by the characteristic setting unit 15 (step S102). Then, the input unit 12 of the verification processing unit 11 inputs sensor information from the sensor 20 (step S103).

[0085] The processing unit 13 activates the verification target program and performs processing based on the input values ​​(sensor information) input from the input unit 12, performing various functions implemented by the verification target program (step S104). In step S104, the processing unit 13 inputs a control signal, which is its processing result, to the data acquisition unit 14.

[0086] The data acquisition unit 14 determines whether the acquisition condition is met based on at least one of the input value (sensor information) and the output result (control signal, etc.) (step S105). Furthermore, the acquisition condition in step S105 is the acquisition condition modified according to the characteristic information in step S102.

[0087] If the determination result is positive (the acquisition condition is met), the data acquisition unit 14 stores (acquires) the data related to the input value and the output result in the storage unit 10b (step S106). When storing the data, the data acquisition unit 14 also establishes and stores the characteristic information and the met acquisition condition accordingly. Then, the process ends. On the other hand, if the determination result is negative, the verification processing device 11 directly ends the process.

[0088] These processes are executed at regular intervals after the shadow mode is set. In addition, after the shadow mode is set, the processes in steps S101 and S102 can be skipped in subsequent data acquisition processes.

[0089] At a predetermined transmission time, the transmitting unit 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 the same time, the transmitting unit 17 also transmits characteristic information corresponding to the data establishment and information related to the established acquisition conditions.

[0090] If server 102 receives data sent from the transmitting unit 17 of each vehicle 101, it stores the data in the storage device of server 102. When storing data, characteristic information received along with the data is used to establish corresponding data storage. In other words, data is categorized and stored based on characteristic information. Additionally, information related to the acquisition conditions that are met when the data is acquired can also be stored accordingly. That is, after categorizing by characteristic information, the data can be further categorized and stored based on acquisition conditions. Thus, data with similar premises such as driving conditions are grouped together, making data analysis easier.

[0091] According to the first embodiment described above, the following effects are achieved.

[0092] The modification unit 16 sets the characteristic information of the vehicle 101 during operation based on the basic information, and modifies the data acquisition conditions based on this characteristic information. Therefore, data can be acquired only for vehicles 101 with predetermined characteristic information. This reduces the burden on communication load, processing load, and analysis load.

[0093] Based on the characteristic information, the threshold values ​​of the parameters constituting the acquisition conditions and the acquisition scenario are changed. Therefore, by changing the acquired driving conditions based on the characteristic information, data can be acquired, and data more suitable for the characteristic information can be obtained.

[0094] The feature setting unit 15 uses GPS to obtain the location information of the vehicle 101, which is related to the area where the vehicle 101 is traveling. Therefore, the trouble of inputting information can be eliminated.

[0095] The feature setting unit 15 uses a deep neural network to identify at least one of the following from the camera images of the camera 24: the time period during which the vehicle 101 is traveling, the weather, and the road conditions, and sets it as information related to the driving conditions of the vehicle 101. Therefore, the hassle of input can be eliminated. Furthermore, the basic information can be changed in real time and reflected in the feature information.

[0096] The feature setting unit 15 uses a deep neural network to identify the road on which the vehicle 101 is traveling from the camera images of the camera 24, and sets it as information related to the area on which the vehicle 101 is traveling. Therefore, the hassle of input can be eliminated. In addition, the basic information can be changed in real time and reflected in the feature information.

[0097] The characteristic setting unit 15 extracts and abstracts necessary information from the basic information, or performs either extraction or abstraction, to convert it into one or more characteristic parameters representing the characteristics of the vehicle 101 during driving, and sets them as characteristic information. Therefore, compared with the basic information, the amount of information in the characteristic information can be reduced, and it is easy to process as parameters.

[0098] Furthermore, when setting characteristic information based on basic information according to rules, the characteristic setting unit 15 can set characteristic information that further reflects the designer's ideas. On the other hand, when setting characteristic information using inference models or clustering, the characteristic setting unit 15 does not need to determine detailed rules, thus reducing development hassles.

[0099] (A variation of the first embodiment)

[0100] In the first embodiment described above, it is also possible not to acquire the control signals (data related to the output results) processed and output by the installation program. On the other hand, it is also possible to acquire sensor information (vehicle speed, yaw rate, acceleration, accelerator pedal operation, brake pedal operation, steering angle, etc.) detected when the vehicle 101 moves after a predetermined time has elapsed after the acquisition conditions are met.

[0101] In the first embodiment described above, the functions related to driving assistance may not be implemented. In this case, after the conditions are met and a predetermined time has elapsed, sensor information detected when the vehicle 101 moves (vehicle speed, yaw rate, acceleration, accelerator pedal operation, brake pedal operation, steering angle, etc.) can be acquired based on the driver's operation.

[0102] In the first embodiment described above, a verification processing unit 11 is provided. However, as long as the processing unit 10a can make the verification target program operate together with the installation program, the verification processing unit 11 may not be provided.

[0103] (Second Implementation)

[0104] A second embodiment, which modifies a portion of the vehicle control device 10 in the first embodiment, will be described.

[0105] In the second embodiment, the modification unit 16 modifies the data acquired by the data acquisition unit 14 based on the characteristic information set by the characteristic setting unit 15. That is, the modification unit 16 modifies the quantity and type of data acquired by the data acquisition unit 14 based on the characteristic information.

[0106] For example, the modification unit 16 can also change whether to acquire only the data related to the sensor information input to the verification processing device 11, or to acquire both the data related to the sensor information and the output result simultaneously, based on the characteristic information.

[0107] Furthermore, the modification unit 16 can also change the quantity and type of data related to the sensor information based on the characteristic information. For example, the modification unit 16 can also change whether to acquire data related to vehicle speed from the sensor information, data related to vehicle speed and yaw rate, or data related to accelerator operation amount and steering operation amount, etc., based on the characteristic information.

[0108] Furthermore, the modification unit 16 can also change the quantity and type of data related to the acquired output results based on the characteristic information. To explain in more detail, the modification unit 16 can also change the data acquisition function and the non-data acquisition function in multiple functions (application programs) implemented by the verification object program based on the characteristic information. For example, the modification unit 16 can also change whether to acquire data related to the output results based on the follow-driving function, data related to the output results based on the collision damage mitigation braking control function, or data related to the output results based on the automatic headlight beam adjustment function, etc.

[0109] The following is for reference Figure 9 The data acquisition process in the second embodiment will be described. If data acquisition processing begins, steps S101 to S102 are performed in the same manner as in the first embodiment.

[0110] Then, the modification unit 16 of the second embodiment modifies the data acquired by the data acquisition unit 14 according to the characteristic information set by the characteristic setting unit 15 (step S201). Then, steps S103 to S105 are performed.

[0111] Then, if the determination result in step S105 is positive (if the acquisition condition is met), the data acquisition unit 14 of the second embodiment acquires the data set in step S201 from the data related to the input value and the output result, and stores it in the storage unit 10b (step S202). Then, the process ends. The following description is the same as that of the first embodiment, so it is omitted.

[0112] Furthermore, in the second embodiment, the acquisition conditions can be changed in the same way as in the first embodiment, or they can remain unchanged. That is, the processing in step S102 can be omitted.

[0113] According to the second embodiment described above, the following effects are achieved.

[0114] The modification unit 16 modifies the data obtained based on the characteristic information. More specifically, the modification unit 16 modifies at least one of the quantity and type of data obtained based on the characteristic information. As a result, only the necessary data can be obtained based on the characteristic information, reducing the burden on communication load, processing load, analysis load, etc.

[0115] For example, when using the second characteristic information, it can be modified so that, if the second characteristic information indicates "a single person's sports car is driving on a mountain road during a sunny day," data related to the output result based on the follow-drive function is acquired, while data related to other output results is not acquired. On the other hand, if the second characteristic information indicates "a family car with family members is driving in the city during a rainy night," data related to the output result based on the automatic headlight axis adjustment function is acquired, while data related to other output results is not acquired. Thus, it is possible to appropriately modify the data related to the output result of the desired function based on the characteristic information.

[0116] Furthermore, when using the first feature information, for example, it can be modified so that if the "country name" parameter in the first feature information is "Japan", data related to the output result based on rear cross-traffic alert is acquired, and data related to other output results is not acquired. On the other hand, if it is "United States", data related to the output result based on traffic sign recognition function is acquired, and data related to other output results is not acquired. Thus, based on the feature information, data related to the output result of the desired function can be acquired efficiently.

[0117] (Third Implementation)

[0118] A third embodiment, which modifies a portion of the vehicle control device 10 in the first embodiment, will be described.

[0119] The modification unit 16 in the third embodiment modifies part or all of the verification target program based on the characteristic information set by the characteristic setting unit 15. For example, if multiple verification target programs are stored in the storage unit 10b, the modification unit 16 may modify them to either the first verification target program or the second verification target program based on the characteristic information.

[0120] Additionally, for example, it is possible to change whether one of the various functions (applications) implemented by the verification object program is implemented. Specifically, the modification unit 16 can also change whether to implement the follow-driving function, whether to implement the forward vehicle approach warning function, etc., based on characteristic information.

[0121] Alternatively, the content of the function (application) implemented by the verification object program can be changed. For example, the modification unit 16 can also store multiple modes of follow-drive function (application), and change which mode of follow-drive function is implemented based on the characteristic information.

[0122] In addition, parameters such as thresholds within various functions can be changed based on characteristic information. For example, in the follow-driving function, the modification unit 16 can also change whether to follow the vehicle in front at a distance of 30m or at a distance of 40m based on characteristic information.

[0123] The following is for reference Figure 10 The data acquisition process in the third embodiment will be described. If data acquisition processing begins, steps S101 to S102 will be performed in the same manner as in the first embodiment.

[0124] Then, the modification unit 16 of the third embodiment modifies part or all of the verification target program according to the characteristic information set by the characteristic setting unit 15 (step S301). Then, the processing after step S103 is performed. The flow of the subsequent processing is the same as that of the first embodiment, so it is omitted.

[0125] Furthermore, in the third embodiment, the acquisition conditions can be changed in the same way as in the first embodiment, or they can remain unchanged. That is, the processing in step S102 can be omitted. Alternatively, the third embodiment and the second embodiment can be combined. That is, in the third embodiment, the acquired data can also be changed.

[0126] According to the third embodiment described above, the following effects are achieved.

[0127] The modification unit 16 modifies part or all of the verification target program based on the characteristic information. This allows for modification of the verification content to obtain the required data, reducing communication, processing, and analysis loads. Furthermore, by modifying the content of the verification target program to create functionality corresponding to the characteristic information, the required output results can be obtained. Therefore, various verifications can be performed.

[0128] (Fourth Implementation)

[0129] A fourth embodiment, which modifies a portion of the vehicle control device 10 in the first embodiment, will be described.

[0130] In the vehicle control device 10 of the fourth embodiment, it is configured to acquire and collect only data related to sensor information and data related to the output results based on the installation program, without implementing the verification object program. In other words, in the fourth embodiment, a data collection mode is set without implementing the verification object program.

[0131] The structure and functions related to the data collection mode in the fourth embodiment will be described below. In the fourth embodiment, the verification processing unit 11 is not provided, and the processing unit 10a performs the processing related to the data collection mode. Alternatively, the verification processing unit 11 may be provided instead of the processing unit 10a, similar to the first embodiment. In addition, the verification target program is not stored.

[0132] To explain in more detail, such as Figure 11 As shown, in the fourth embodiment, the arithmetic processing unit 10a of the vehicle control device 10 has the functions of an input unit 112, a processing unit 113, a data acquisition unit 114, a characteristic setting unit 115, a modification unit 116, and a transmission unit 117. These functions are implemented by the arithmetic processing unit 10a executing the vehicle program stored in the storage unit 10b.

[0133] Input unit 112 inputs sensor information from sensor 20. Input unit 112 inputs part or all of the input sensor information as input values ​​for the installation program to processing unit 113. In addition, input unit 112 inputs part or all of the input sensor information to data acquisition unit 114.

[0134] The processing unit 113 activates the installation program by performing processing based on the input values ​​(sensor information) input from the input unit 112, performing various functions (application programs) implemented by the installation program. Furthermore, the processing unit 113 inputs control signals (control signals for the actuator 30) as the result of its processing to the data acquisition unit 114. These control signals are also input to the actuator 30.

[0135] The data acquisition unit 114 determines whether the 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, therefore, a description is omitted.

[0136] When the acquisition conditions are met, the data acquisition unit 114 stores the data related to the input value and the output result in the storage unit 10b. As described above, the input value includes, for example, sensor information input to the arithmetic processing device 10a. Furthermore, the output result includes, for example, control signals processed and output based on the installation program.

[0137] Furthermore, the data acquisition unit 114 of the processing unit 10a can also input control signals processed and output by the installation program to the actuator 30, input sensor information detected when the vehicle 101 moves (vehicle speed, yaw rate, acceleration, accelerator pedal operation amount, brake pedal operation amount, steering angle, etc.), and store it in the storage unit 10b. In other words, it can also store sensor information related to the actual movement of the vehicle 101 for each scenario, that is, sensor information required to verify the correct movement.

[0138] The feature setting unit 115, the modification unit 116, and the sending unit 117 are the same as those in the first embodiment, so their description is omitted.

[0139] The following is for reference Figure 12 The data acquisition process in this embodiment will be described. The data acquisition process shown below is the data acquisition process implemented by the computing processing device 10a. These processes are performed after a data collection mode is set. The timing of setting the data collection mode is the same as that of setting the shadow mode in the first embodiment.

[0140] The characteristic setting unit 115 of the processing unit 10a acquires basic information and sets the characteristic information of the vehicle 101 during driving based on this basic information (step S401). Next, the modification unit 116 of the processing unit 10a modifies the acquisition conditions according to the characteristic information set by the characteristic setting unit 115 (step S402). Then, the input unit 112 of the processing unit 10a inputs sensor information from the sensor 20 (step S403).

[0141] The processing unit 113 of the arithmetic processing device 10a activates the installation program and performs processing based on the input values ​​(sensor information) input from the input unit 12, performing various functions implemented by the installation program (step S404). In step S404, the processing unit 113 inputs control signals as its processing results to the actuator 30 and the data acquisition unit 114.

[0142] The data acquisition unit 114 determines whether the acquisition condition is met based on at least one of the input value (sensor information) and the output result (control signal, etc.) (step S405). Furthermore, the acquisition condition in step S405 is the acquisition condition modified according to the characteristic information in step S402.

[0143] If the determination result is positive (the acquisition condition is met), the data acquisition unit 114 stores the data related to the input value and the output result in the storage unit 10b (step S406). When storing the data, the data acquisition unit 114 also stores the characteristic information and the met acquisition condition accordingly. Then, the process ends. On the other hand, if the determination result is negative, the arithmetic processing device 10a directly ends the process.

[0144] These processes are executed at regular intervals after the shadow mode is set. In addition, after the shadow mode is set, the processes in steps S401 and 402 can be skipped in subsequent data acquisition processes.

[0145] The sending unit 117 sends 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 sending time. At this time, the sending unit 17 also sends characteristic information corresponding to the data establishment and information related to the establishment of the acquisition conditions. The processing of the server 102 is the same as in the first embodiment, and therefore is omitted.

[0146] According to the fourth embodiment described above, the following effects are achieved.

[0147] Since the verification object procedure is not implemented, the processing burden can be reduced. As a result, the verification processing unit 11 can also be omitted, which simplifies the structure.

[0148] (A variation of the fourth embodiment)

[0149] In the fourth embodiment described above, the modification unit 116 may also modify the acquired data based on the characteristic information, similar to the second embodiment. In this case, the acquisition conditions may not need to be changed.

[0150] The data acquisition unit 114 of the fourth embodiment described above acquires data related to the output result (control signal) of the operation based on the installation program, but it may not acquire data related to the output result of the operation based on the installation program. In this case, only sensor information set as input values ​​may be used. Alternatively, the control signal processed and output by the installation program may be input to the actuator 30 to acquire sensor information detected when the vehicle 101 is in motion (vehicle speed, yaw rate, acceleration, accelerator pedal operation amount, brake pedal operation amount, steering angle, etc.).

[0151] In the fourth embodiment described above, the installation program is implemented in the data collection mode, and various functions related to driving assistance are implemented. However, it is also possible that various functions related to driving assistance are not implemented in the data collection mode. That is, it is also possible that in the data collection mode, sensor information detected when the vehicle 101 moves (vehicle speed, yaw rate, acceleration, accelerator pedal operation, brake pedal operation, steering angle, etc.) is acquired based on the driver's operation.

[0152] To explain in detail, the input unit 112 inputs sensor information from the sensor 20 and inputs part or all of the input sensor information to the data acquisition unit 114.

[0153] The data acquisition unit 114 determines whether the acquisition conditions are met based on the input value (sensor information) input from the input unit 112. The acquisition conditions are the same as in the first embodiment, therefore, a description is omitted.

[0154] When the acquisition conditions are met, the data acquisition unit 114 stores the data related to the input value in the storage unit 10b. Furthermore, after the acquisition conditions are met, the data acquisition unit 114 of the arithmetic processing device 10a, via the input unit 112 and the like, inputs sensor information detected during vehicle 101 operation based on the driver's input, and stores the data related to this sensor information in the storage unit 10b. The sensor information detected during vehicle 101 operation includes vehicle speed, yaw rate, acceleration amount, accelerator pedal operation amount, brake pedal operation amount, steering angle, etc. Additionally, after the acquisition conditions are met, the data acquisition unit 114 inputs and stores the aforementioned sensor information until a predetermined time has elapsed. The predetermined time can also be varied depending on the type of acquisition conditions that are met.

[0155] The feature setting unit 115, the modification unit 116, and the sending unit 117 are the same as those in the first embodiment and the fourth embodiment, so their description is omitted.

[0156] The following is for reference Figure 13 The data acquisition process in this variant example will be described. The data acquisition process shown below is the data acquisition process implemented by the computing processing unit 10a. These processes are implemented after the data collection mode is set.

[0157] The characteristic setting unit 115 of the computing processing device 10a acquires basic information and sets the characteristic information of the vehicle 101 during driving based on this basic information (step S501). Next, the modification unit 116 of the computing processing device 10a changes the acquisition conditions according to the characteristic information set by the characteristic setting unit 115 (step S502).

[0158] Then, the input unit 112 of the processing unit 10a inputs sensor information from the sensor 20 (step S503). The data acquisition unit 114 determines whether the acquisition condition is met based on the input value (sensor information) (step S504). Furthermore, the acquisition condition in step S504 is the acquisition condition modified according to the characteristic information in step S502.

[0159] If the determination result is positive (the acquisition condition is met), the data acquisition unit 114 stores the data related to the input value in the storage unit 10b (step S505). Additionally, the data acquisition unit 114 inputs sensor information detected during vehicle 101 operation up to a predetermined period and stores the data related to that sensor information in the storage unit 10b. When storing data, the data acquisition unit 114 also correspondingly stores characteristic information and the met acquisition conditions. Then, the process ends. On the other hand, if the determination result is negative, the arithmetic processing device 10a directly ends the process. The following description is the same as in the fourth embodiment and is therefore omitted.

[0160] Furthermore, in this modified example, the modification unit 116 can also modify the acquired data based on the characteristic information, just like in the second embodiment. In this case, the acquisition conditions may not need to be changed.

[0161] The control unit and method described in this disclosure can also be implemented using a dedicated computer, which is provided by comprising a processor and memory programmed to perform one or more functions embodied in a computer program. Alternatively, the control unit and method described in this disclosure can also be implemented using a dedicated computer provided by employing one or more dedicated hardware logic circuits to construct a processor. Alternatively, the control unit and method described in this disclosure can also be implemented using one or more dedicated computers, which are composed of a combination of a processor and memory programmed to perform one or more functions, and a processor composed of one or more hardware logic circuits. Furthermore, the computer program can also be stored as instructions to be executed by the computer on a computer-readable non-transferable tangible recording medium.

[0162] The following describes the technical ideas that can be derived from the above embodiments and variations.

[0163] [Structure 1]

[0164] A vehicle control device, comprising a vehicle control device (10) mounted on a vehicle (101), including:

[0165] The feature setting unit (15) acquires at least one of the following: information related to the vehicle itself, information related to the owner of the vehicle, information related to the driving status of the vehicle, and information related to the area where the vehicle is driving, and sets the feature information of the vehicle when driving based on this information.

[0166] The data acquisition unit (14), when the data acquisition conditions are met, acquires data related to sensor information obtained by various sensors mounted on the aforementioned vehicle; and

[0167] The sending unit (17) sends the data acquired by the data acquisition unit to the server via the communication network.

[0168] Based on the aforementioned characteristic information, at least one of the aforementioned acquisition conditions and the data acquired by the aforementioned data acquisition unit is changed.

[0169] [Structure 2]

[0170] According to the vehicle control device described in Structure 1, wherein,

[0171] The aforementioned vehicle control device is configured to implement a shadow mode that enables the verification target program to perform actions in a manner independent of the control of the aforementioned vehicle.

[0172] The data acquisition unit takes the sensor information as input value and, when implementing or in the process of implementing the verification object program, acquires data related to the output result and data related to the sensor information, or acquires data related to the output result instead of data related to the sensor information.

[0173] [Structure 3]

[0174] A vehicle control device, mounted on a vehicle (101), is configured to implement a shadow mode that causes a verification object program to operate in a manner independent of the vehicle's control, wherein...

[0175] The vehicle control device (10) described above includes:

[0176] The feature setting unit (15) acquires at least one of the following: information related to the vehicle itself, information related to the owner of the vehicle, information related to the driving status of the vehicle, and information related to the area where the vehicle is driving, and sets the feature information of the vehicle when driving based on this information.

[0177] The modification department (16) modifies part or all of the above-mentioned verification object program based on the above-mentioned characteristic information;

[0178] The data acquisition unit (14) takes sensor information acquired by various sensors mounted on the vehicle as input values. When implementing the verification object procedure or when the verification object procedure has already been implemented, and provided the data acquisition conditions are met, it acquires data related to the output result and data related to the sensor information, or acquires data related to the output result instead of data related to the sensor information; and

[0179] The sending unit (17) sends the data acquired by the data acquisition unit to the server via the communication network.

[0180] [Structure 4]

[0181] According to the vehicle control device described in Structure 3, wherein,

[0182] Based on the aforementioned characteristic information, the aforementioned modification unit further modifies at least one of the aforementioned acquisition conditions and the data acquired by the aforementioned data acquisition unit.

[0183] [Structure 5]

[0184] According to the vehicle control device described in any one of structures 1 to 4, wherein,

[0185] The aforementioned feature setting unit uses GPS to obtain the vehicle's location information, which is information related to the area where the vehicle is traveling.

[0186] [Structure 6]

[0187] According to the vehicle control device described in any one of structures 1 to 5, wherein,

[0188] The aforementioned feature setting unit uses a deep neural network to identify at least one of the time period during which the vehicle was driving, the weather, and the road conditions from the camera images of the vehicle-mounted camera, and sets it as information related to the driving conditions of the vehicle.

[0189] [Structure 7]

[0190] According to the vehicle control device described in any one of structures 1 to 6, wherein,

[0191] The aforementioned feature setting unit uses a deep neural network to identify the road the vehicle is traveling on from the camera images of the vehicle-mounted camera and sets it as information related to the region where the vehicle is traveling.

[0192] [Structure 8]

[0193] According to the vehicle control device described in any one of structures 1 to 7, wherein,

[0194] The aforementioned characteristic setting unit inputs at least one of the following into the inference model: information related to the vehicle itself, information related to the owner of the vehicle, information related to the driving status of the vehicle, and information related to the region where the vehicle is driving, and outputs the aforementioned characteristic information based on this information.

[0195] [Structure 9]

[0196] According to the vehicle control device described in any one of structures 1 to 7, wherein,

[0197] The aforementioned feature setting unit defines the clusters formed by clustering information that includes at least one of the following: information related to the vehicle itself, information related to the owner of the vehicle, information related to the driving status of the vehicle, and information related to the region where the vehicle is driving, as the aforementioned feature information.

[0198] [Structure 10]

[0199] An in-vehicle program is an in-vehicle program implemented by a vehicle control device (10) mounted on a vehicle (101), wherein,

[0200] To enable the above vehicle control device to function:

[0201] The characteristic setting step involves obtaining at least one of the following: information related to the vehicle itself, information related to the owner of the vehicle, information related to the driving status of the vehicle, and information related to the region where the vehicle is driving; and setting the characteristic information of the vehicle during driving based on this information.

[0202] The data acquisition step, under the condition that the data acquisition conditions are met, acquires data related to sensor information obtained by various sensors mounted on the aforementioned vehicle; and

[0203] The sending step involves transmitting the data acquired by the aforementioned data acquisition unit to the server via a communication network.

[0204] The acquisition conditions and at least one of the data acquired by the data acquisition unit may change based on the aforementioned characteristic information.

[0205] [Structure 11]

[0206] An in-vehicle program is an in-vehicle program implemented by a vehicle control device (10), which is mounted on a vehicle (101) and configured to implement a shadow mode that enables the verification target program to operate in a manner independent of the control of the vehicle.

[0207] The above-mentioned vehicle-mounted program enables the above-mentioned vehicle control device to perform:

[0208] The characteristic setting step involves obtaining at least one of the following: information related to the vehicle itself, information related to the owner of the vehicle, information related to the driving status of the vehicle, and information related to the region where the vehicle is driving; and setting the characteristic information of the vehicle during driving based on this information.

[0209] The modification steps involve modifying part or all of the above-mentioned verification object program based on the aforementioned characteristic information.

[0210] The data acquisition step takes sensor information acquired by various sensors mounted on the aforementioned vehicle as input values. When implementing the aforementioned verification object program, or when the aforementioned verification object program has already been implemented, and provided the data acquisition conditions are met, it acquires data related to the output result and data related to the aforementioned sensor information, or acquires data related to the output result in place of the data related to the aforementioned sensor information; and

[0211] In the sending step, the data acquired by the aforementioned data acquisition unit is sent to the server via a communication network.

[0212] This disclosure is described based on embodiments, but it should be understood that this disclosure is not limited to those embodiments or constructions. This disclosure also includes various modifications and equivalent variations. Furthermore, various combinations and methods, including only one element, one or more, or one or fewer of these elements, are also included in the scope and spirit of this disclosure.

Claims

1. A vehicle control device, comprising, in a vehicle control device (10) mounted on a vehicle (101): The feature setting unit (15) acquires at least one of the following: information related to the vehicle itself, information related to the owner of the vehicle, information related to the driving status of the vehicle, and information related to the area where the vehicle is driving, and sets the feature information of the vehicle when driving based on this information. The data acquisition unit (14), when the data acquisition conditions are met, acquires data related to sensor information obtained by various sensors mounted on the vehicle; and The sending unit (17) sends the data acquired by the data acquisition unit to the server via the communication network. Based on the characteristic information, at least one of the acquisition conditions and the data acquired by the data acquisition unit is changed.

2. The vehicle control device according to claim 1, wherein, The vehicle control device is configured to implement a shadow mode that enables the verification object program to perform actions in a manner independent of the control of the vehicle. When the data acquisition unit executes the verification object program with the sensor information as input value, it acquires data related to the output result and data related to the sensor information, or acquires data related to the output result instead of data related to the sensor information.

3. A vehicle control device, mounted on a vehicle (101), configured to implement a shadow mode that causes a verification object program to perform program actions in a manner independent of the control of the vehicle, wherein, The vehicle control device (10) includes: The feature setting unit (15) acquires at least one of the following: information related to the vehicle itself, information related to the owner of the vehicle, information related to the driving status of the vehicle, and information related to the area where the vehicle is driving, and sets the feature information of the vehicle when driving based on this information. The modification unit (16) modifies part or all of the verification object program according to the characteristic information; The data acquisition unit (14) takes sensor information acquired by various sensors mounted on the vehicle as input value. When the verification object program is implemented or the verification object program has been implemented, if the data acquisition conditions are met, it acquires data related to the output result and data related to the sensor information, or acquires data related to the output result instead of acquiring data related to the sensor information. as well as The sending unit (17) sends the data acquired by the data acquisition unit to the server via the communication network.

4. The vehicle control device according to claim 3, wherein, The modification unit further modifies at least one of the acquisition conditions and the data acquired by the data acquisition unit based on the characteristic information.

5. The vehicle control device according to any one of claims 1 to 4, wherein, The feature setting unit uses GPS to obtain the vehicle's location information, which is information related to the area where the vehicle is traveling.

6. The vehicle control device according to any one of claims 1 to 4, wherein, The feature setting unit uses a deep neural network to identify at least one of the time period, weather, and road conditions from the camera images of the vehicle-mounted camera, and sets it as information related to the vehicle's driving conditions.

7. The vehicle control device according to any one of claims 1 to 4, wherein, The feature setting unit uses a deep neural network to identify the road the vehicle is traveling on from the camera images of the vehicle-mounted camera and set it as information related to the region where the vehicle is traveling.

8. The vehicle control device according to any one of claims 1 to 4, wherein, The characteristic setting unit inputs at least one of the following into the inference model: information related to the vehicle itself, information related to the owner of the vehicle, information related to the driving status of the vehicle, and information related to the region where the vehicle is driving, and outputs the characteristic information based on this information.

9. The vehicle control device according to any one of claims 1 to 4, wherein, The feature setting unit defines the clusters formed by clustering information that includes at least one of the following: information related to the vehicle itself, information related to the vehicle owner, information related to the vehicle's driving status, and information related to the region where the vehicle is driving.

10. An in-vehicle program implemented by a vehicle control device (10) mounted on a vehicle (101), wherein, The vehicle control device shall perform the following steps: The characteristic setting step involves acquiring at least one of the following: information related to the vehicle itself, information related to the owner of the vehicle, information related to the driving status of the vehicle, and information related to the region where the vehicle is driving; and setting the characteristic information of the vehicle during driving based on this information. The data acquisition step involves acquiring data related to sensor information obtained by various sensors mounted on the vehicle, provided that the data acquisition conditions are met. as well as The sending step involves sending the data acquired in the data acquisition step to the server via a communication network. The acquisition conditions and at least one of the data acquired by the data acquisition steps are changed according to the characteristic information.

11. An in-vehicle program implemented by a vehicle control device (10), the vehicle control device (10) being mounted on a vehicle (101), configured to implement a shadow mode that causes the verification object program to operate in a manner independent of the control of the vehicle, wherein, The onboard program causes the vehicle control device to perform the following steps: The characteristic setting step involves acquiring at least one of the following: information related to the vehicle itself, information related to the owner of the vehicle, information related to the driving status of the vehicle, and information related to the region where the vehicle is driving; and setting the characteristic information of the vehicle during driving based on this information. The modification step involves modifying part or all of the verification object program based on the aforementioned characteristic information. The data acquisition step takes sensor information acquired by various sensors mounted on the vehicle as input values. When implementing the verification object program or when the verification object program has been implemented, if the data acquisition conditions are met, data related to the output result and data related to the sensor information are acquired, or data related to the output result is acquired instead of data related to the sensor information. as well as The sending step involves sending the data acquired in the data acquisition step to the server via a communication network.

Citation Information

Patent Citations

  • Stone structure and rotation mechanism

    JP2024069040A

  • Vehicle control device

    WO2022004324A1