Data collection device, vehicle control device, and on-vehicle program

Abstract

A data collection device (102) that receives and collects data from vehicles (101) via a communication network (103) comprises: a clustering unit (51, 151) that ascertains the travel status of vehicles, performs clustering on the basis of the travel status, and sorts a plurality of vehicles having the same or similar travel status into one cluster; and a vehicle designation unit (52, 152) that designates some of the plurality of vehicles sorted into one cluster as vehicles for transmitting the data.

Description

Data collection device, vehicle control device and in-vehicle program CROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application is based on Japanese Application No. 2024-069047, filed on April 22, 2024, the contents of which are incorporated herein by reference.

[0002] The present disclosure relates to a data collection device, 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 a sold vehicle while it is in operation is collected in a server via a communication network, and the collected data is analyzed to be used in future vehicle development or to update the vehicle's control program. Such a technique is described, for example, in Patent Document 1.

[0004] Patent No. 7227358

[0005] However, when collecting data, if data on all driving conditions for all vehicles in all scenes is collected, the amount of data becomes enormous. When the amount of data becomes enormous, problems arise such as a heavy burden on communication, processing, and analysis. In addition, data that is not necessary for verification may be included, resulting in inefficiency.

[0006] The present disclosure has been made in consideration of the above circumstances, and has as its main object to provide a data collection device, a vehicle control device, and an in-vehicle program that can efficiently collect necessary data.

[0007] A data collection device that solves the above problem is a data collection device that receives and collects data from vehicles via a communication network, and is equipped with a clustering unit that grasps the driving conditions of each vehicle, performs clustering based on the driving conditions, and sorts multiple vehicles with the same or similar driving conditions into one cluster, and a vehicle designation unit that designates some of the multiple vehicles sorted into one cluster as vehicles that will transmit the data.

[0008] According to the above configuration, several vehicles among those with the same or similar driving conditions transmit data. This reduces the communication load on the communication network. It also reduces the amount of data stored in the data collection device, preventing storage capacity from being overwhelmed. Furthermore, because data from vehicles with the same or similar driving conditions, i.e., data that is likely to contain duplicate data, can be reduced, allowing for efficient data analysis.

[0009] A vehicle control device that solves the above problem is a vehicle control device that transmits data to a data collection device via a communication network, and is equipped with a driving control unit that cooperates with other vehicles belonging to the fleet to control the driving of the vehicle so that the vehicle drives as a fleet consisting of multiple vehicles, and a vehicle designation unit that designates some of the multiple vehicles belonging to the fleet as vehicles to which the data will be transmitted.

[0010] According to the above configuration, several vehicles among those with the same or similar driving conditions transmit data. This reduces the communication load on the communication network. It also reduces the amount of data stored in the data collection device, preventing storage capacity from being overwhelmed. Furthermore, because data from vehicles with the same or similar driving conditions, i.e., data that is likely to contain duplicate data, can be reduced, allowing for efficient data analysis.

[0011] The in-vehicle program that solves the above problem is an in-vehicle program executed by a vehicle control device that transmits data to a data collection device via a communication network, and causes the vehicle control device to perform a driving control step of controlling the driving of its own vehicle in cooperation with other vehicles belonging to the fleet so that the vehicle drives as a fleet unit consisting of multiple vehicles, and a vehicle designation step of designating some of the multiple vehicles belonging to the fleet as vehicles to which the data will be transmitted.

[0012] According to the above configuration, several vehicles among those with the same or similar driving conditions transmit data. This reduces the communication load on the communication network. It also reduces the amount of data stored in the data collection device, preventing storage capacity from being overwhelmed. Furthermore, because data from vehicles with the same or similar driving conditions, i.e., data that is likely to contain duplicate data, can be reduced, allowing for efficient data analysis.

[0013] 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 configuration diagram of a data collection system, Fig. 2 is a block diagram showing the functions of a vehicle control device, Fig. 3 is a flowchart showing the flow of data collection, Fig. 4 is a flowchart of data acquisition processing, Fig. 5 is a conceptual diagram showing a fleet driving mode, Fig. 6 is a block diagram showing the functions of a vehicle control device and a server in a second embodiment, Fig. 7 is a flowchart showing the flow of data collection in the second embodiment, Fig. 8 is a block diagram showing the functions of a vehicle control device and a server in a third embodiment, and Fig. 9 is a flowchart showing the flow of data collection in the third embodiment.

[0014] Hereinafter, embodiments of a data collection device, 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 equivalent parts in the drawings are designated by the same reference numerals, and their description will not be repeated in principle.

[0015] 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 each vehicle 101, and controls the vehicle 101 and performs driving assistance.

[0016] 1, the data collection system 100 includes a server 102 as a data collection device, and is capable of communicating with a plurality of vehicles 101 via a communication network 103 such as the Internet. Each vehicle 101 includes a vehicle control device 10, a sensor 20, an actuator 30, and the like.

[0017] The sensor 20 is used to measure the driving conditions of the vehicle 101. The sensor 20 includes various sensors for measuring the behavior of the vehicle 101 while it is driving. For example, the sensor 20 includes sensors for acquiring information about the behavior of the vehicle 101 while it is driving, such as a vehicle speed sensor 21, an acceleration sensor 22, and a yaw rate sensor 23. The sensors for acquiring information about the behavior of the vehicle 101 while it is driving 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.

[0018] Furthermore, for example, the sensor 20 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 be a laser radar (LiDAR), an ultrasonic sensor, or a combination of these. The camera 24 may be a monocular camera or a compound camera. The camera 24 may capture either still images or videos. The number, position, and type of the cameras 24 may be changed as desired. In this embodiment, the vehicle is provided with a front camera 24a whose imaging range is in front of the vehicle, a right side camera 24b whose imaging range is on the right side of the vehicle, a left side camera 24c whose imaging range is on the left side of the vehicle, and a rear camera 24d whose imaging range is on the rear of the vehicle.

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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.

[0025] 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 is running after sales, 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] The server 102 includes a server CPU 102a and a storage 102b serving as a storage device for storing data, etc. The functions provided by the server 102 can be provided by software recorded in a physical memory device and a computer that executes the software, software alone, hardware alone, or a combination of these. For example, the server CPU 102a executes a program stored in a non-transitory tangible storage medium serving as the storage 102b provided by the server 102. The program includes, for example, a program that realizes the functions shown in FIG. 2, etc. Execution of the program results in the execution of a method corresponding to the program. The program stored in the storage 102b can be downloaded and modified from an external device via the communication network 103.

[0034] The server 102 has a function of storing data received from the vehicle control device 10 via the communication network 103 in the storage 102b, and collecting data.

[0035] However, there is a problem in that the storage capacity of the storage unit 10b is likely to be insufficient to store all data of the vehicle 101 while it is traveling. Furthermore, if all vehicles 101 were to upload all of their stored data, there is a risk of placing an excessive burden on the communication network 103. Similarly, if the server 102 were to store data from all vehicles 101 in the storage 102b, there is a problem in that the storage capacity of the storage 102b would become enormous. Furthermore, there is also a problem in that the processing load on the analysis device would become too large if a dedicated analysis device were to analyze all of the uploaded data. Furthermore, there is also the problem that acquiring and analyzing all of the data in the first place would result in a lot of similar data, resulting in a lot of waste.

[0036] For this reason, it is desirable to store, transmit, and receive only the amount of data necessary for verification and analysis. Therefore, the number of vehicles 101 to which data is transmitted is limited. This will be explained in detail below.

[0037] 2, the verification processing device 11 of the vehicle control device 10 has a function as an input unit 12, a function as a verification unit 13, a function as a data acquisition unit 14, and a function as a transmission unit 15. These functions are realized by the verification processing device 11 by executing an in-vehicle program stored in the storage unit 10b.

[0038] 2, the server CPU 102a of the server 102 has a function as a clustering unit 51, a function as a vehicle designation unit 52, and a function as a collection unit 53. These functions are realized by the server CPU 102a by executing a data collection program stored in the storage 102b.

[0039] First, we will explain the functions realized by the verification processing device 11. The input unit 12 inputs sensor information from the sensor 20. Then, when the shadow mode starts, the input unit 12 transmits some or all of the input sensor information to the server 102 via the transmission unit 15.

[0040] Furthermore, when designated by a vehicle designation unit 52 (described later), the input unit 12 inputs part or all of the input sensor information to the verification unit 13 as input values ​​for the program to be verified. Furthermore, the input unit 12 inputs part or all of the input sensor information to the data acquisition unit 14.

[0041] When specified by a vehicle specification unit 52 (described later), the verification 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 verification 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.

[0042] When specified by the vehicle specification unit 52 described later, 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 verification unit 13.

[0043] 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.

[0044] 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.

[0045] 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.

[0046] 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 verification unit 13.

[0047] 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).

[0048] 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.

[0049] 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).

[0050] 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.

[0051] When the data acquisition unit 14 is designated by the vehicle designation unit 52 (described later) and one of the acquisition conditions is met, 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. The output results include, for example, control signals processed and output based on the program to be verified, and control signals processed and output based on the implemented program. The output results may also include sensor information related to the actual operation of the vehicle 101 for each scene. The output results may also include the difference between the output results based on the implemented program and the output results of the program to be verified. The data to be stored (acquired) may be changed depending on the acquisition conditions that are met. For example, in a scene where the vehicle is following a preceding vehicle and an acquisition condition is met that the vehicle speed is equal to or greater than a first threshold, data regarding the vehicle speed may be acquired, whereas in a scene where a pedestrian is crossing in front of the vehicle 101 and an acquisition condition is met that the distance between the pedestrian and the vehicle is equal to or less than a second threshold and the amount of brake operation is equal to or greater than a third threshold, data regarding the amount of brake operation may be acquired.

[0052] Furthermore, data related to sensor information, etc. acquired when an acquisition condition is met is stored in association with each other so that it is treated as a single set of data for each acquisition condition that is met. Specifically, data related to input values ​​and output results is assigned an ID and stored as a single set of data. Hereinafter, when simply referred to as data, this refers to this data.

[0053] When the shadow mode starts, the transmitter 15 transmits the sensor information input by the input unit 12 to the server 102 via the communication network 103. Furthermore, when designated by a vehicle designation unit 52 (described later), the transmitter 15 transmits the data acquired by the data acquisition unit 14 and stored in the memory unit 10b to the server 102 via the communication network 103 at a predetermined transmission timing. The predetermined transmission timing is as described above.

[0054] Next, various functions implemented in the server 102 will be described. When the shadow mode starts, the clustering unit 51 receives sensor information from each vehicle 101 and determines the driving conditions of each vehicle 101 based on the sensor information. Specifically, the driving position of the vehicle 101 and the road on which the vehicle is traveling are determined from sensor information such as a GPS (Global Positioning System) mounted on the vehicle 101. The time period in which the vehicle 101 is traveling is determined from the transmission time, etc. The scene is also estimated from image data of the camera 24 mounted on the vehicle 101. The scene estimation method is as described above. The weather is also estimated from the image data of the camera 24 mounted on the vehicle 101. In this embodiment, the driving conditions of the vehicle 101 can be identified by combining one or more elements such as the driving position, the road on which the vehicle is traveling, the time period in which the vehicle is traveling, the scene in which the vehicle is traveling, and the weather during the traveling.

[0055] The clustering unit 51 then performs clustering based on the determined driving conditions, and classifies multiple vehicles 101 with the same or similar driving conditions into one cluster. For example, multiple vehicles 101 traveling on the same road (e.g., National Route 1) based on their driving locations are identified and grouped into one cluster. Furthermore, for example, multiple vehicles 101 traveling late at night are identified and grouped into one cluster based on the time of day they are traveling. Furthermore, for example, multiple vehicles 101 traveling in the same or similar scene (e.g., a scene passing through a tunnel) are identified and grouped into one cluster. Furthermore, for example, multiple vehicles 101 traveling in rainy weather are identified and grouped into one cluster.

[0056] Clustering may be performed based on any of the viewpoints (elements constituting the driving conditions), or may be performed based on two or more viewpoints. For example, multiple vehicles 101 traveling on the same road late at night on a rainy day may be identified and grouped into one cluster. Furthermore, the similarity of the driving conditions may be scored based on two or more viewpoints, and vehicles with similarities may be grouped together and clustered.

[0057] Then, the vehicle designation unit 52 designates some of the vehicles 101 sorted into one cluster by the clustering unit 51 as vehicles 101 to transmit data. The number of vehicles 101 to designate may be a predetermined number, or may be determined as a percentage of the total number of vehicles 101 belonging to one cluster (for example, 50%). Furthermore, the vehicles 101 to designate may be determined randomly or based on the order of reception, etc.

[0058] The vehicle designation unit 52 designates the vehicle 101 to which data is to be transmitted via the communication network 103. When the verification processing device 11 receives the designation from the vehicle designation unit 52, the verification unit 13 executes the program to be verified, and the data acquisition unit 14 stores the data in the storage unit 10b, as described above. Then, the transmission unit 15 transmits the data stored in the storage unit 10b.

[0059] When the collection unit 53 receives data from the transmission unit 15, the collection unit 53 stores the data in the storage 102b. At this time, the collection unit 53 preferably classifies and stores the data by cluster. For example, the collection unit 53 stores the data by adding tag information indicating the cluster.

[0060] The flow of data collection in this embodiment will be described below with reference to Figures 3 and 4. When the shadow mode is started, as shown in Figure 3, the transmitter 15 transmits sensor information acquired by the sensor 20 to the server 102 via the input unit 12 (step S101). The timing at which the shadow mode is set is arbitrary, and may be, for example, the timing at which the ignition switch is turned on.

[0061] The clustering unit 51 of the server 102 grasps the driving conditions based on the sensor information from the vehicles 101 (step S102). Then, the clustering unit 51 performs clustering based on the driving conditions, and classifies multiple vehicles 101 having the same or similar driving conditions into one cluster (step S103).

[0062] Then, the vehicle designation unit 52 of the server 102 designates some of the vehicles 101 sorted into one cluster by the clustering unit 51 as vehicles 101 from which data is to be transmitted (step S104).

[0063] After the shadow mode is set, the verification processing unit 11 of each vehicle 101 executes the data acquisition process shown in Fig. 4 at predetermined intervals (step S105). The data acquisition process shown in Fig. 4 will now be described.

[0064] 4, after the data acquisition process is started, the verification processing unit 11 determines whether the vehicle 101 has been designated by the vehicle designation unit 52 as the vehicle 101 to which data is to be transmitted (step S201). If the determination result is negative, the verification processing unit 11 terminates the data acquisition process.

[0065] On the other hand, if the determination result in step S201 is positive, the input unit 12 of the verification processing device 11 inputs sensor information from the sensor 20 (step S202). The input sensor information is then input to the verification unit 13 as an input value for the program to be verified. The input sensor information is then input to the data acquisition unit 14.

[0066] The verification 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 S203). In step S203, the verification unit 13 inputs control signals as the processing results to the data acquisition unit 14.

[0067] 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 S204).

[0068] If the determination result is positive (if the acquisition condition is met), the data acquisition unit 14 stores (acquires) data regarding the input values ​​and output results in the storage unit 10b (step S205). The data acquisition process then ends. On the other hand, if the determination result in step S204 is negative, the verification processing unit 11 simply ends the data acquisition process. The data acquisition process is executed periodically after the shadow mode is set, if designated by the vehicle designation unit 52.

[0069] Returning to the description of Fig. 3, as shown in Fig. 3, the transmitting unit 15 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 (step S106).

[0070] When the collection unit 53 of the server 102 receives the data transmitted from the transmission unit 15 of each vehicle 101, the collection unit 53 stores the data in the storage device of the server 102 and collects the data (step S107). When storing the data, tag information indicating the cluster may be added to classify the data by cluster. This allows data that are assumed to have similar driving conditions to be grouped, making it easier to analyze the data.

[0071] According to the first embodiment, the following effects are achieved.

[0072] The clustering unit 51 grasps the driving conditions of each vehicle 101 from the sensor information received from each vehicle 101, performs clustering based on the driving conditions, and classifies multiple vehicles 101 with the same or similar driving conditions into one cluster. Then, the vehicle designation unit 52 designates some of the multiple vehicles 101 sorted into one cluster as vehicles 101 that will transmit data. The verification processing device 11 of the designated vehicle 101 executes a data acquisition process at predetermined intervals and stores the data in the memory unit 10b. The transmission unit 15 transmits the data stored in the memory unit 10b to the server 102 at a predetermined transmission timing. The collection unit 53 of the server 102 stores and collects the data transmitted from each vehicle 101 in the storage 102b.

[0073] As a result, only some of the vehicles 101 with the same or similar driving conditions execute the program to be verified, acquire data, and transmit the data. This reduces the communication load on the communication network 103. It also reduces the amount of data stored in the storage 102b, preventing storage capacity from being overwhelmed. Furthermore, since data from vehicles 101 with the same or similar driving conditions, i.e., data that is likely to be duplicated, is reduced, data analysis and the like can be performed efficiently. Furthermore, since the data is classified by cluster, data analysis can be performed efficiently.

[0074] (Variation of the First Embodiment) In the first embodiment, the verification processing unit 11 is provided, but as long as the processing unit 10a can run the program to be verified together with the implementation program, it is not necessary to provide the verification processing unit 11. In this case, it is sufficient if the processing unit 10a implements the various functions implemented by the verification processing unit 11.

[0075] In the first embodiment, the verification unit 13 may execute the program to be verified, and the data acquisition unit 14 may acquire data and store it in the storage unit 10b, even if the program is not designated by the vehicle designation unit 52. However, even in this case, the transmission unit 15 must not transmit data unless the vehicle designation unit 52 designates the data.

[0076] In the first embodiment, when specifying the vehicle 101 from which data is to be acquired, the vehicle designation unit 52 may also designate which sensor information is to be included in the data to be transmitted for each vehicle 101. For example, the sensor information to be acquired may differ depending on the driving conditions.

[0077] In the first embodiment, as shown in Fig. 2, the communication network 103 may have a function as a communication speed determination unit 54 that determines whether the communication speed in the communication network 103 is equal to or lower than a specified speed. The vehicle designation unit 52 may designate a vehicle 101 when the communication speed determination unit 54 determines that the communication speed is equal to or lower than the specified speed. This makes it possible to limit the amount of data only when the communication load increases.

[0078] In the first embodiment, the clustering unit 51 may gradually increase the number of vehicles 101 included in one cluster as time passes since the start of data collection. That is, if a long period of time, such as one year, has passed since the start of data collection, there is a high possibility that similar data will be acquired in duplicate. For this reason, even if the number of samples (the amount of data collected) is reduced, it is not expected that the data analysis will be significantly affected. Therefore, by gradually increasing the number of vehicles 101 included in one cluster as time passes since the start of data collection, the amount of data can be efficiently reduced, and the communication load and analysis load can be reduced.

[0079] Second Embodiment A second embodiment will be described in which the vehicle control device 10 in the first embodiment is partially modified. The clustering unit 51 in the first embodiment grasps the driving conditions from sensor information and performs clustering based on the grasped driving conditions, but the clustering unit 151 in the second embodiment classifies multiple vehicles 201 to 204 traveling in fleet units into one cluster because the driving conditions are the same or similar. This will be described in detail below.

[0080] As shown in Figure 5, in the second embodiment, multiple vehicles 201-204 (trailers in Figure 5) are configured to be able to travel in fleet units. Traveling in fleet units means that, as shown in Figure 5, each of the multiple vehicles (four vehicles in Figure 5) that make up the fleet travels as a group while maintaining a constant inter-vehicle distance from the other vehicles 201-204 that belong to the fleet at a predetermined travel position. In Figure 5, the vehicles travel in a single file in the order of vehicle 201 → vehicle 202 → vehicle 203 → vehicle 204. Hereinafter, traveling in fleet units will be referred to as fleet traveling.

[0081] In fleet driving, generally, only the lead vehicle 201 is manually driven, and the remaining vehicles 202 to 204 are automatically driven, or all of the vehicles 201 to 204 are automatically driven. In this embodiment, the description will be made on the assumption that the lead vehicle 201 is manually driven, and the remaining vehicles 202 to 204 are automatically driven. In this embodiment, the vehicle 201 is referred to as the lead vehicle 201, and the vehicles 202 to 204 are referred to as the following vehicles 202 to 204.

[0082] As shown in Fig. 6, in the lead vehicle 201, the arithmetic processing device 10a of the vehicle control device 10 has a function as a fleet setting unit 111 and a function as a driving control unit 112. These functions are realized by executing an in-vehicle program. Although not shown, the following vehicles 202 to 204 have the same functions.

[0083] The fleet setting unit 111 of the lead vehicle 201 communicates with the fleet setting units 111 (not shown) of the vehicle control devices 10 in the following vehicles 202 to 204 by using the communication network 103, short-range wireless communication, etc. At that time, the fleet setting unit 111 of the lead vehicle 201 transmits and receives setting information required for fleet traveling, such as identification information for identifying the vehicles 201 to 204 that make up the fleet and traveling positions in the fleet, between the fleet setting units 111 in the following vehicles 202 to 204.

[0084] Furthermore, the fleet setting unit 111 of the lead vehicle 201 transmits setting information related to the fleet to the server 102 via the communication network 103. Furthermore, the fleet setting unit 111 of each of the vehicles 201 to 204 inputs the setting information related to the fleet to the traveling control unit 112.

[0085] The traveling control unit 112 determines whether or not the vehicle is the lead vehicle 201 based on the setting information about the fleet input by the fleet setting unit 111. If the result of this determination is positive, the traveling control unit 112 executes traveling control for the lead vehicle 201.

[0086] In this embodiment, the lead vehicle 201 is manually driven, and therefore the driving of the lead vehicle 201 is controlled based on the driver's operation. That is, a control signal for controlling the driving of the lead vehicle 201 is generated based on the accelerator operation amount, brake operation amount, steering angle, etc. included in the sensor information input from the sensor 20, and input to the actuator 30. At this time, the driving control unit 112 may execute an implementation program and provide various driving assistance functions.

[0087] On the other hand, if it is determined that the following vehicles 202-204 are not the lead vehicle 201 but are the following vehicles 202-204, the driving control units 112 of the following vehicles 202-204 execute driving control so as to follow the lead vehicle 201. That is, the driving control unit 112 autonomously controls the vehicles 202-204 so as to drive while maintaining a predetermined driving position in the fleet based on setting information related to the fleet. Specifically, the driving control unit 112 controls driving so as to maintain a constant inter-vehicle distance from the other vehicles 201-204 input from the sensor 20, and to match the vehicle speed, steering angle, etc. to those of the other vehicles 201-204.

[0088] Next, various functions implemented in the server 102 in the second embodiment will be described. As shown in Fig. 6, the server CPU 102a of the server 102 in the second embodiment has a function as a clustering unit 151 and a function as a vehicle designation unit 152. These functions are implemented by the server CPU 102a by executing a data collection program stored in the storage 102b.

[0089] In the second embodiment, the clustering unit 151 receives fleet-related setting information from each vehicle 101 at the start of shadow mode (data collection mode), and based on the fleet-related setting information, sorts the vehicles 202 to 204 traveling in the fleet into one cluster as they have the same or similar driving conditions.

[0090] Then, the vehicle designation unit 152 in the second embodiment designates some of the vehicles 201-204 sorted into one cluster by the clustering unit 151 as the vehicles 201-204 from which data is to be transmitted. In the second embodiment, when designating the vehicles 201-204 from which data is to be transmitted from the vehicles 201-204 sorted into one cluster on a fleet-by-fleet basis, the vehicle designation unit 152 designates the vehicles 201-204 from which data is to be transmitted based on their traveling positions in the fleet. In this embodiment, the vehicle designation unit 152 designates the leading vehicle 201 and the trailing vehicle 204.

[0091] Furthermore, when specifying the vehicles 201-204 from which data is to be acquired, the vehicle designation unit 152 designates, for each of the vehicles 201-204, which sensor information is to be included in the data to be transmitted, depending on the traveling positions of the vehicles 201-204 when traveling as a fleet. Specifically, the vehicle designation unit 152 designates the last following vehicle 204 to include sensor information relating to the rear of the following vehicle 204 in the data to be transmitted. The sensor information relating to the rear of the following vehicle 204 is, for example, image data (sensor information) from the rear camera 24d and sensor information from a rear sensor (such as an ultrasonic sensor) that detects obstacles behind the following vehicle 204.

[0092] On the other hand, the vehicle designation unit 152 designates the lead vehicle 201 to include in the data to be transmitted sensor information other than the sensor information designated for the following vehicle 204. Specifically, the vehicle designation unit 152 designates that the data to be transmitted includes sensor information related to the front and sides of the lead vehicle 201, as well as sensor information such as vehicle speed, acceleration, yaw rate, accelerator operation amount, brake operation amount, and steering angle. The sensor information related to the front of the lead vehicle 201 is, for example, image data from the front camera 24a and sensor information from a front sensor (such as the millimeter-wave radar 25) that detects obstacles in front of the lead vehicle 201. Similarly, the sensor information related to the sides of the lead vehicle 201 is, for example, sensor information such as image data from the side cameras 24b and 24c.

[0093] In other words, when vehicles 201 to 204 are traveling in a fleet, it is highly likely that the information regarding the operation of the vehicles 201 to 204, such as vehicle speed, is the same or similar for all of the vehicles 201 to 204, so it is sufficient for one of the vehicles 201 to 204 traveling in the fleet to transmit data. For this reason, the lead vehicle 201 transmits all of this sensor information on behalf of the vehicles.

[0094] Furthermore, the leading vehicle 201 is obstructed by the following vehicles 202 to 204 and is therefore unable to properly acquire sensor information relating to the area behind the leading vehicle 201. Or, even if the sensor information is acquired, it is the same as or similar to the sensor information acquired by the following vehicles 202 to 204 and is not very valuable as information. On the other hand, the area ahead of the leading vehicle 201 is not obstructed by the following vehicles 202 to 204. For this reason, the leading vehicle 201 is specified not to transmit sensor information relating to the area behind the leading vehicle 201, while being specified to transmit sensor information relating to the area ahead of the leading vehicle 201.

[0095] Furthermore, the last following vehicle 204 is blocked by the vehicles 201 to 203 ahead of it, and is therefore unable to properly acquire sensor information relating to the area ahead of the following vehicle 204. Or, even if it were possible to acquire such information, it would be the same or similar to the sensor information acquired by the vehicles 201 to 203 ahead of it, and would not be of much value as information. On the other hand, the area behind the last following vehicle 204 is not blocked by the vehicles 201 to 203 ahead of it. For this reason, the last following vehicle 204 is instructed not to transmit sensor information relating to the area ahead of the last following vehicle 204, while being instructed to transmit sensor information relating to the area behind the last following vehicle 204.

[0096] Furthermore, it is highly likely that the information relating to the sides of the vehicles 201 to 204 is the same or similar for all of the vehicles 201 to 204. For this reason, the leading vehicle 201 is designated to transmit sensor information relating to the sides of the leading vehicle 201 as a representative.

[0097] After determining the vehicles 201, 204 to which data will be transmitted, the vehicle designation unit 152 designates the vehicles 201, 204 to transmit the data via the communication network 103. At that time, it also designates what sensor information should be included in the data to be transmitted. Upon receiving the designation from the vehicle designation unit 152, the verification processing device 11 executes the program to be verified by the verification unit 13, as described above, and stores the data in the storage unit 10b by the data acquisition unit 14. Then, the transmission unit 15 transmits the data stored in the storage unit 10b.

[0098] When the collection unit 53 receives the data from the transmission unit 15, the collection unit 53 stores the data in the storage 102b. Note that the input unit 12, the verification unit 13, the data acquisition unit 14, the transmission unit 15, and the collection unit 53 are the same as those in the first embodiment, and therefore detailed description thereof will be omitted.

[0099] The flow of data collection in the second embodiment will be described below with reference to Fig. 7. When the shadow mode is started, the arithmetic processing device 10a transmits setting information related to the fleet to the server 102 (step S301), as shown in Fig. 7. The timing at which the shadow mode is set is arbitrary, and may be, for example, when the fleet starts traveling.

[0100] The clustering unit 151 of the server 102 grasps the driving conditions based on the setting information related to the fleet, and classifies the vehicles 201 to 204 that are driving in the fleet into one cluster as having the same or similar driving conditions (step S302).

[0101] Then, the vehicle designation unit 152 of the server 102 designates some of the vehicles 201-204 sorted into one cluster by the clustering unit 151 as the vehicles 201-204 from which data should be transmitted (step S303). At this time, the vehicle designation unit 152 designates the vehicles 201-204 from which data should be transmitted based on the traveling position of the vehicles 201-204 in the fleet. At this time, the vehicle designation unit 152 also designates, for each of the vehicles 201-204, which sensor information should be included in the data to be transmitted based on the traveling position of the vehicles 201-204 when traveling as a fleet.

[0102] After starting the shadow mode setting, the verification processing device 11 of the vehicle 201, 204 specified by the vehicle specifying unit 152 executes the data acquisition process shown in Fig. 4 at predetermined intervals (step S304). The data acquisition process of step S304 is the same as the data acquisition process from step S105 onwards in the first embodiment, and therefore a description thereof will be omitted.

[0103] The transmitter 15 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 (step S305). At this time, the transmitter 15 transmits the data together with the sensor information designated by the vehicle designation unit 152. Upon receiving the data transmitted from the transmitters 15 of the vehicles 201 and 204, the collector 53 of the server 102 stores the data in the storage device of the server 102 and collects the data (step S306).

[0104] According to the second embodiment, the following effects are achieved.

[0105] The clustering unit 151 classifies the fleet of vehicles 201 to 204 into one cluster, assuming that the vehicles have the same or similar driving conditions. This makes it possible to reduce sensor information that is likely to contain duplicated content, thereby reducing various loads such as communication loads and preventing pressure on storage capacity.

[0106] Furthermore, when specifying vehicles 201-204 from a cluster into which multiple vehicles 201-204 traveling in a fleet are sorted, the vehicle specifying unit 152 specifies which sensor information to include in the data to be transmitted for each vehicle 201-204 according to the traveling positions of the vehicles 201-204 when traveling in a fleet. It is possible to reduce sensor information that is likely to have overlapping content or sensor information in which appropriate information has not been detected due to interference from other vehicles 201-204.

[0107] (Modification of the Second Embodiment) In the second embodiment, the number of vehicles 201 to 204 that make up the fleet may be changed as desired. Furthermore, the number of rows of vehicles 201 to 204 that are traveling as a fleet may be two or more.

[0108] In the second embodiment, the number of vehicles 201 to 204 that transmit data may be changed arbitrarily. For example, it may be one. Furthermore, in the second embodiment, the vehicle designation unit 152 changed whether or not to designate vehicles 201 to 204 that transmit data depending on the traveling position, but this may be changed arbitrarily. For example, the following vehicles 202 and 203 may transmit data. Similarly, although the sensor information included in the data differs depending on the traveling position, it may be the same. From the perspective of reducing the amount of data, it is better to have as few vehicles as possible, and it is also desirable to reduce sensor information that is likely to have the same or similar content.

[0109] In the second embodiment, information for verifying whether the fleet driving is being performed correctly, such as the inter-vehicle distance during fleet driving, may be included in the data transmitted to the server 102. In this case, unlike the second embodiment, image data of the other vehicles 201 to 204 that are also driving in the fleet may be required. In this case, the image data of the other vehicles 201 to 204 that are also driving in the fleet may be included in the data transmitted to the server 102.

[0110] In the second embodiment, the data acquisition unit 14 may store in the storage unit 10b only the sensor information specified by the vehicle specification unit 152. This reduces the amount of data stored in the storage unit 10b.

[0111] (Third Embodiment) A third embodiment will be described, in which the vehicle control device 10 in the first embodiment is partially modified. In the first and second embodiments, the server 102 determines the vehicles 101, 201 to 204 to which data is transmitted, but in the third embodiment, the vehicles 301 to 304 themselves determine whether or not to transmit data. This will be described in detail below.

[0112] Similar to the second embodiment, the vehicles 301 to 304 in the third embodiment are configured to be able to travel in a fleet in a single file in the order of vehicle 301 → vehicle 302 → vehicle 303 → vehicle 304. In this embodiment, vehicle 301 is referred to as the lead vehicle 301, and vehicles 302 to 304 are referred to as the following vehicles 302 to 304.

[0113] 8, in the lead vehicle 301, the arithmetic processing device 10a of the vehicle control device 10 has a function as a fleet setting unit 211, a function as a driving control unit 212, a function as a clustering unit 251, and a function as a vehicle designation unit 252. These functions are realized by executing an in-vehicle program stored in the storage unit 10b. Similarly, the following vehicles 302 to 304 have a function as a fleet setting unit 211 and a function as a driving control unit 212. Note that the following vehicles 302 to 304 do not necessarily have to have the clustering unit 251 and the vehicle designation unit 252.

[0114] The fleet setting unit 211 of the lead vehicle 301 communicates with the fleet setting units 211 (not shown) of the vehicle control devices 10 in the following vehicles 302 to 304 by using the communication network 103, short-range wireless communication, etc. At that time, the fleet setting unit 211 of the lead vehicle 301 transmits and receives setting information required for fleet traveling with the fleet setting units 211 in the following vehicles 302 to 304, as in the second embodiment.

[0115] Furthermore, the fleet setting unit 211 of the lead vehicle 301 inputs setting information about the fleet to the clustering unit 251. Furthermore, the fleet setting unit 211 of each of the vehicles 301 to 304 inputs setting information about the fleet to the traveling control unit 212.

[0116] The traveling control unit 212 determines whether or not the vehicle is the lead vehicle 301 based on the setting information about the fleet input from the fleet setting unit 211. If the result of this determination is positive, the traveling control unit 212 executes traveling control for the lead vehicle 301, as in the second embodiment.

[0117] On the other hand, if it is determined that the following vehicles 302 to 304 are not the leading vehicle 301, the driving control units 212 of the following vehicles 302 to 304 perform driving control so as to follow the leading vehicle 301, as in the second embodiment.

[0118] When the shadow mode starts, the clustering unit 251 inputs setting information about the fleet from the fleet setting unit 211, and if it determines that the vehicle is the lead vehicle 301, it sorts the vehicles 301 to 304 traveling in the fleet into one cluster based on the setting information about the fleet, assuming that the traveling conditions are the same or similar. Then, the clustering unit 251 inputs the result to the vehicle designation unit 252 of the lead vehicle 301.

[0119] The vehicle designation unit 252 of the lead vehicle 301 designates some of the vehicles 301 to 304 sorted into one cluster by the clustering unit 251 as the vehicles 301 to 304 from which data is to be transmitted. In this case, similar to the second embodiment, the vehicle designation unit 252 designates the lead vehicle 301 and the last following vehicle 304 as the vehicles 301 to 304 from which data is to be transmitted. Also, similar to the second embodiment, the vehicle designation unit 252 designates for each of the vehicles 301 to 304 which sensor information is to be included in the data to be transmitted depending on the traveling position of the vehicles when traveling as a fleet.

[0120] After determining the vehicles 301, 304 to which data will be transmitted, the vehicle designation unit 252 of the lead vehicle 301 designates the vehicle 301, 304, to which data will be transmitted, and then designates the vehicle designation unit 252 to that effect to the verification processing device 11 of the lead vehicle 301. At this time, the vehicle designation unit 252 also designates what sensor information should be included in the transmitted data according to the running position of the lead vehicle 301.

[0121] At the same time, the vehicle designation unit 252 of the lead vehicle 301 designates the last following vehicle 304 (vehicle 304 from which data is to be transmitted) to that effect via the communication network 103, etc. At that time, it also designates what sensor information should be included in the data to be transmitted, depending on the traveling position of the last following vehicle 304.

[0122] When the verification processing devices 11 of the leading vehicle 301 and the following vehicle 304 receive designation from the vehicle designation unit 252, as described above, the verification unit 13 executes the verification target program, and the data acquisition unit 14 stores the data in the storage unit 10b. Then, the transmission unit 15 transmits the data stored in the storage unit 10b. When the collection unit 53 of the server 102 receives the data from the transmission unit 15, it stores the data in the storage 102b. Note that the input unit 12, verification unit 13, data acquisition unit 14, transmission unit 15, and collection unit 53 are the same as those in the first embodiment, and therefore detailed description thereof will be omitted.

[0123] The flow of data collection in the third embodiment will be described below with reference to Fig. 9. When the shadow mode is started, as shown in Fig. 9, the processing unit 10a of the lead vehicle 301 transmits setting information related to the fleet to the following vehicles 302 to 304 (step S401). The start of the shadow mode is arbitrary, but may be, for example, the start of fleet driving.

[0124] The clustering unit 251 of the lead vehicle 301 classifies the vehicles 301 to 304 traveling in the fleet into one cluster based on the setting information related to the fleet, assuming that the traveling conditions are the same or similar (step S402).

[0125] Then, the vehicle designation unit 252 of the lead vehicle 301 designates some of the vehicles 301-304 sorted into one cluster by the clustering unit 251 as the vehicles 301-304 from which data should be transmitted (step S403). At this time, the vehicle designation unit 252 designates the vehicles 301, 304 from which data should be transmitted based on their traveling positions in the fleet. At this time, the vehicle designation unit 252 also designates for each vehicle 301, 304 which sensor information should be included in the data to be transmitted based on the traveling positions of the vehicles 301, 304 when traveling as a fleet.

[0126] After the shadow mode is set, the verification processing unit 11 of the leading vehicle 301 executes the data acquisition process shown in Fig. 4 at predetermined intervals (step S404). The data acquisition process of step S404 is the same as the data acquisition process of step S105 in the first embodiment, and therefore a description thereof will be omitted. Although not shown, the following vehicle 304 at the rear end also executes the same process.

[0127] The transmitter 15 of the leading vehicle 301 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 (step S405). At this time, the transmitter 15 transmits only the sensor information designated by the vehicle designation unit 252 in the data. The following vehicle 304 at the rear end performs the same process. When the collector 53 of the server 102 receives the data transmitted from the transmitters 15 of the vehicles 301 and 304, the collector 53 stores the data in the storage device of the server 102 and collects the data (step S406).

[0128] According to the third embodiment, the following effects are achieved.

[0129] The fleet-driving vehicles 301-304 perform clustering themselves, and then determine and designate the vehicles 301-304 from which data will be transmitted. This reduces the control load on the server 102. Furthermore, the use of short-range wireless communication also reduces the communication load on the communication network 103.

[0130] Furthermore, when specifying the vehicles 301 to 304 to which data is to be transmitted, the vehicle specification unit 252 of the lead vehicle 301 specifies the sensor information to be included in the data. This makes it possible to prevent the transmission of unnecessary sensor information and reduce the communication load.

[0131] (Variations of the Third Embodiment) In the third embodiment, the number of vehicles 301 to 304 constituting the fleet may be changed as desired. Furthermore, the number of vehicles 301 to 304 to which data is transmitted may be changed as desired. Furthermore, the vehicles 301 to 304 to which data is transmitted may not necessarily be determined based on the vehicle's location. Furthermore, although the sensor information included in the data differs depending on the vehicle's location, it may be the same.

[0132] In the third embodiment, the data transmitted to the server 102 may include information for verifying whether the fleet is traveling correctly, such as the vehicle-to-vehicle distance during fleet traveling.

[0133] In the third embodiment, the data acquisition unit 14 may store only the sensor information specified by the vehicle specification unit 152 in the storage unit 10b.

[0134] (Variations of each embodiment) In the above embodiment, a verification processing device 11 is provided, but if the processing device 10a executes various functions (such as the data acquisition unit 14) realized by the verification processing device 11, the verification processing device 11 may be eliminated.

[0135] In the above embodiment, the data acquisition unit 14 does not need to acquire the control signal (data related to the output result) processed and output based on the installed program. However, after the acquisition condition is met, the data acquisition unit 14 may acquire sensor information (vehicle speed, yaw rate, acceleration amount, accelerator pedal operation amount, brake pedal operation amount, steering angle, etc.) detected when the vehicles 101, 201 to 204, 301 to 304 are operating until a predetermined time has elapsed. In other words, data related to this sensor information may be stored in the storage unit 10b.

[0136] In the above embodiment, the verification unit 13 does not need to perform a function related to driving assistance. In other words, the verification unit 13 may not be necessary. In this case, after the acquisition condition is met, until a predetermined time has elapsed, sensor information (vehicle speed, yaw rate, acceleration amount, accelerator pedal operation amount, brake pedal operation amount, steering angle, etc.) detected when the vehicles 101, 201 to 204, 301 to 304 are operated by the driver may be acquired. In other words, data related to this sensor information may be stored in the memory unit 10b to be collected as correct answer data.

[0137] In the above embodiment, after the processing by the verification unit 13, the data acquisition unit 14 determines whether or not the acquisition condition is met. However, if the acquisition condition is met, the processing by the verification unit 13 may be executed. This makes it possible to reduce the processing load on the verification unit 13.

[0138] 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.

[0139] The following describes technical ideas that can be derived from the above-described embodiment and modifications.

[0140] [Configuration 1] A data collection device (102) that receives and collects data from vehicles (101, 201-204) via a communication network (103), the data collection device comprising: a clustering unit (51, 151) that grasps the driving conditions of each vehicle, performs clustering based on the driving conditions, and classifies multiple vehicles with the same or similar driving conditions into one cluster; and a vehicle designation unit (52, 152) that designates some of the multiple vehicles sorted into one cluster as vehicles that will transmit the data.

[0141] [Configuration 2] The data collection device according to Configuration 1, wherein each vehicle is provided with a plurality of sensors (20 to 28), the data received from the vehicle includes a plurality of pieces of sensor information acquired from the plurality of sensors, and when the vehicle designation unit designates a vehicle from which the data is to be acquired, the vehicle designation unit also designates, for each vehicle, which sensor information is to be included in the data to be transmitted.

[0142] [Configuration 3] The data collection device according to Configuration 1 or 2, further comprising a communication speed determination unit (54) that determines whether a communication speed in the communication network is equal to or lower than a specified speed, and the vehicle designation unit designates a vehicle when the communication speed determination unit determines that the communication speed is equal to or lower than the specified speed.

[0143] [Configuration 4] The data collection device according to any one of configurations 1 to 3, wherein the clustering unit gradually increases the number of vehicles included in one cluster as time elapses from the start of collection of the data.

[0144] [Configuration 5] The data collection device according to any one of Configurations 1 to 4, wherein the clustering unit classifies a plurality of vehicles traveling in a fleet unit, each of which is a group of a plurality of vehicles, into one cluster on the basis that the vehicles have the same or similar traveling conditions.

[0145] [Configuration 6] The data collection device of any of configurations 1 to 5, wherein each vehicle is provided with a plurality of sensors, and the data received from the vehicle includes a plurality of pieces of sensor information acquired from the plurality of sensors, and the clustering unit sorts a plurality of vehicles traveling in a fleet unit into one cluster on the assumption that the vehicles have the same or similar traveling conditions, and when designating a vehicle from which the data is to be acquired from the cluster into which the plurality of vehicles traveling in a fleet unit have been sorted, the vehicle designation unit designates for each vehicle which sensor information to be included in the data to be transmitted depending on the traveling position of the vehicle when traveling in the fleet unit.

[0146] [Configuration 7] A vehicle control device (10) that transmits data to a data collection device (102) via a communication network (103), comprising: a driving control unit (212) that controls driving of the vehicle in cooperation with other vehicles belonging to a fleet so that the vehicle drives as a fleet unit formed by grouping together multiple vehicles (301 to 304); and a vehicle designation unit (252) that designates some of the multiple vehicles belonging to the fleet as vehicles to which the data is to be transmitted.

[0147] [Configuration 8] The vehicle control device according to Configuration 7, wherein each vehicle is provided with a plurality of sensors (20 to 28), the data transmitted from the vehicle includes a plurality of pieces of sensor information acquired from the plurality of sensors, and when designating a vehicle from which the data is to be acquired, the vehicle designation unit designates, for each vehicle, which sensor information is to be included in the data to be transmitted depending on the traveling position of the vehicle when traveling as a fleet unit.

[0148] [Configuration 9] An in-vehicle program executed by a vehicle control device (10) that transmits data to a data collection device (102) via a communication network (103), the in-vehicle program causing the vehicle control device to execute: a driving control step of controlling the driving of the vehicle in cooperation with other vehicles belonging to the fleet so that the vehicle drives as a fleet unit formed by grouping multiple vehicles; and a vehicle designation step of designating some of the multiple vehicles belonging to the fleet as vehicles to which the data is to be transmitted.

[0149] 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 data collection device (102) that receives and collects data from vehicles (101, 201-204) via a communication network (103), comprising: a clustering unit (51, 151) that grasps the driving conditions of each vehicle, performs clustering based on the driving conditions, and classifies multiple vehicles with the same or similar driving conditions into one cluster; and a vehicle designation unit (52, 152) that designates some of the multiple vehicles sorted into one cluster as vehicles that will transmit the data.

2. The data collection device according to claim 1, wherein each vehicle is provided with a plurality of sensors (20-28), the data received from the vehicle includes a plurality of pieces of sensor information acquired from the plurality of sensors, and when the vehicle designation unit designates the vehicle from which the data is to be acquired, it also designates for each vehicle which sensor information is to be included in the data to be transmitted.

3. A data collection device as described in claim 1 or 2, further comprising a communication speed determination unit (54) that determines whether the communication speed in the communication network is equal to or less than a specified speed, and wherein the vehicle designation unit designates a vehicle when the communication speed determination unit determines that the communication speed is equal to or less than the specified speed.

4. The data collection device according to claim 1 or 2, wherein the clustering unit gradually increases the number of vehicles included in one cluster as time passes from the start of data collection.

5. The data collection device according to claim 1 or 2, wherein the clustering unit classifies multiple vehicles traveling in fleet units into one cluster, assuming that the vehicles have the same or similar driving conditions.

6. The data collection device of claim 1, wherein each vehicle is equipped with multiple sensors, and the data received from the vehicle includes multiple sensor information acquired from the multiple sensors, and the clustering unit sorts multiple vehicles traveling in a fleet into a single cluster on the assumption that they have the same or similar driving conditions, and when designating a vehicle from which to acquire the data from among the clusters into which multiple vehicles traveling in a fleet have been sorted, the vehicle designation unit designates for each vehicle which sensor information to be included in the data to be transmitted depending on the vehicle's driving position when traveling in the fleet.

7. A vehicle control device (10) that transmits data to a data collection device (102) via a communication network (103), comprising: a driving control unit (212) that controls the driving of the vehicle in cooperation with other vehicles belonging to a fleet so that the vehicle drives as a fleet unit formed by grouping multiple vehicles (301 to 304); and a vehicle designation unit (252) that designates some of the multiple vehicles belonging to the fleet as vehicles to which the data is to be transmitted.

8. A vehicle control device as described in claim 7, wherein each vehicle is provided with a plurality of sensors (20 to 28), the data transmitted from the vehicle includes a plurality of pieces of sensor information acquired from the plurality of sensors, and when the vehicle designation unit designates the vehicle from which the data is to be acquired, it designates for each vehicle which sensor information is to be included in the data to be transmitted depending on the traveling position of the vehicle when traveling as a fleet unit.

9. An in-vehicle program executed by a vehicle control device (10) that transmits data to a data collection device (102) via a communication network (103), the in-vehicle program causing the vehicle control device to execute: a driving control step of controlling the driving of the vehicle in cooperation with other vehicles belonging to the fleet so that the vehicle drives as a fleet unit consisting of multiple vehicles; and a vehicle designation step of designating some of the multiple vehicles belonging to the fleet as vehicles to which the data will be transmitted.

Images