Vehicle control device

Abstract

To make it possible to easily and appropriately acquire driving preference values of a driver.SOLUTION: A control device includes: a storage unit for storing a first function; and a processor. The first function is specified in advance on the basis of driving data on a plurality of drivers, and indicates a relation of an inter-vehicular preference value with respect to inter-vehicular information and an own vehicle speed. In accordance with the first function, the processor calculates the inter-vehicular preference value of a driver according to the inter-vehicular information and the own vehicle speed that are acquired during follow-up traveling in manual driving by the driver. On the basis of the calculated inter-vehicular preference value, the processor calculates a remaining driving preference value indicating a preference of the driver for at least one of acceleration, deceleration, deceleration timing, and acceleration timing of an own vehicle during the follow-up traveling. On the basis of the calculated remaining driving preference value, the processor calculates a control target value for the at least one of the acceleration, deceleration, deceleration timing, and acceleration timing in automated driving while the driver is riding in a vehicle.SELECTED DRAWING: Figure 4

Description

Technical Field

[0001] The present disclosure relates to a control device for a vehicle capable of switching between manual driving and automatic driving.

Background Art

[0002] Patent Document 1 discloses an automatic driving control device for a vehicle. During manual driving by the driver, the automatic driving control device learns the preferences of the driver regarding the driving method of the vehicle for each driver. Then, the automatic driving control device controls vehicle driving based on the results of the learning.

Prior Art Document

Patent Document

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In order to more appropriately reflect the driver's driving preferences in following driving during automatic driving, it is desirable to acquire a plurality of driving preference values for a larger number of automatic driving parameters (such as inter-vehicle time and acceleration). And it is required that such a plurality of driving preference values can be easily learned and acquired during the driver's manual driving when the driving preferences are to be acquired.

[0005] The present disclosure has been made in view of the above problems, and an object thereof is to provide a control device for a vehicle that can easily and appropriately acquire the driver's driving preference value regarding the following driving of the host vehicle with respect to the preceding vehicle.

Means for Solving the Problems

[0006] The vehicle control device according to the present disclosure is a control device that controls a host vehicle capable of switching between manual driving and automatic driving, and includes a storage device that stores a first function, and a processor. The first function is specified in advance based on the driving data of a plurality of drivers, and shows the relationship between the inter-vehicle information and the inter-vehicle preference value with respect to the host vehicle speed. The inter-vehicle information is the inter-vehicle time or the inter-vehicle distance of the host vehicle with respect to the preceding vehicle. The inter-vehicle preference value indicates the driver's preference regarding the inter-vehicle information. The processor calculates the driver's inter-vehicle preference value corresponding to the inter-vehicle information and the host vehicle speed obtained during following driving in manual driving by the driver according to the first function. The processor calculates the remaining driving preference value indicating the driver's preference for at least one of the acceleration, deceleration, deceleration timing, and acceleration timing of the host vehicle during following driving based on the calculated inter-vehicle preference value. Then, the processor executes a target value calculation process for calculating at least one control target value of the acceleration, deceleration, deceleration timing, and acceleration timing in the automatic driving during the driver's ride based on the calculated remaining driving preference value. Additionally, the first function may be specified using machine learning.

Effect of the Invention

[0007] According to the present disclosure, it becomes possible to easily and appropriately acquire the driver's driving preference value regarding the following driving of the host vehicle with respect to the preceding vehicle.

Brief Description of the Drawings

[0008]

Figure 1

Figure 2

Figure 3

Figure 4

Mode for Carrying Out the Invention

[0009] The embodiments of the present disclosure will be described together with the accompanying drawings.

[0010] 1. Configuration of the vehicle FIG. 1 is a diagram schematically showing an example of the configuration of a vehicle 1 according to an embodiment. The vehicle 1 includes a vehicle control system 10. The vehicle control system 10 is mounted on the vehicle 1 and controls the running of the vehicle 1. The vehicle control system 10 includes a vehicle state sensor 12, a recognition sensor 14, a position sensor 16, a communication device 18, a running device 20, an electronic control unit (ECU) 22, an operation switching switch 24, and a driver monitor 26.

[0011] The vehicle state sensor 12 detects the state of the vehicle 1. The vehicle state sensor 12 includes, for example, a vehicle speed sensor, a longitudinal and lateral acceleration sensor, an accelerator pedal sensor, a brake pedal sensor, and a steering angle sensor. The recognition sensor 14 recognizes (detects) the situation around the vehicle 1. The recognition sensor 14 includes, for example, a camera. The position sensor 16 detects the position and orientation of the vehicle 1. The position sensor 16 includes, for example, a GNSS (Global Navigation Satellite System) receiver.

[0012] The communication device 18 communicates with the outside of the vehicle 1. The communication device 18 communicates with an external system, for example, and acquires various information. The information includes, for example, map information and traffic information. The map information includes road information such as road gradients. The traffic information includes, for example, information regarding traffic jams.

[0013] The running device 20 is a device that operates the vehicle 1. For example, the running device 20 includes a driving device, a braking device, and a steering device. The driving device includes, for example, at least one of an electric motor and an internal combustion engine for driving (accelerating) the vehicle 1. The braking device includes a brake actuator for braking (decelerating) the vehicle 1. The steering device includes, for example, a steering motor for steering the vehicle 1.

[0014] The ECU 22 is a computer that controls the vehicle 1 and corresponds to an example of the "vehicle control device" according to the present disclosure. The ECU 22 includes a processor 28 and a storage device 30. The processor 28 executes various processes. The various processes include processes related to vehicle driving control described later. The storage device 30 stores various information necessary for the processes by the processor 28. By the processor 28 executing a computer program, the various processes by the ECU 22 are realized. The computer program is stored in the storage device 30. Alternatively, the computer program may be recorded on a computer-readable recording medium. Note that the ECU 22 may be configured by combining a plurality of ECUs.

[0015] The vehicle control system 10 is configured to be able to execute an automatic driving control that controls the automatic driving of the vehicle 1. This automatic driving control has a following driving function of driving the vehicle 1 so as to follow the preceding vehicle while controlling the inter-vehicle time T or the inter-vehicle distance D of the vehicle (own vehicle) 1 with respect to the preceding vehicle. More specifically, the automatic driving here corresponds to, for example, level 3 or higher automatic driving in the definition of the Society of Automotive Engineers (SAE) of the United States, but is not necessarily limited to level 3 or higher automatic driving. That is, the automatic driving control only needs to have the above-mentioned following driving function, and may be, for example, Adaptive Cruise Control (ACC). Known techniques are applied to such automatic driving control. Therefore, the description of the details of the automatic driving control is omitted.

[0016] The driving mode switch 24 is operated by the driver 2 and is used to switch the driving of the vehicle 1 between manual driving by the driver 2 and automatic driving. That is, the vehicle 1 is configured to be able to switch between manual driving and automatic driving. Manual driving is performed by the driver 2 operating the accelerator pedal, the brake pedal, and the steering wheel according to his or her own will.

[0017] The driver monitor 26 includes, for example, a camera installed in the vehicle interior 1 so as to image the driver 2. By analyzing the image obtained by this camera, the driver 2 (individual) can be identified, and the state and operation of the driver 2 can be detected.

[0018] 2. Vehicle driving control In the present embodiment, in order to more appropriately reflect the driving preferences of the driver 2 in the following distance driving during automated driving, the ECU 22 executes the "first preference value calculation process PR1", "second preference value calculation process PR2", and "target value calculation process PR3" described later.

[0019] More specifically, in order to evaluate the driving preferences of the driver 2, a driving preference value PV indicating the driving preferences of the driver 2 is used. The driving preference value PV indicates, for example, the driving characteristics of the driver 2 during following distance driving. More specifically, as an example, the driving preference value PV is specified by a numerical value (for example, a percentile value) corresponding to the driving characteristics during following distance driving (see, for example, FIG. 3 described later).

[0020] In the present embodiment, as the driving preference value PV, a following distance preference value PV1, an acceleration preference value PV2, a deceleration preference value PV3, a deceleration timing preference value PV4, and an acceleration timing preference value PV5 are used. Each of the driving preference values PV1 to PV5 is calculated using the following functions f1 to f9 during manual driving by the driver 2. Each of the functions f1 to f9 is specified in advance based on driving data DD (so-called big data) collected during following distance driving in manual driving by a plurality of drivers. Each of the calculated driving preference values PV1 to PV5 is reflected in the automated driving control during following distance driving in automated driving performed while the driver 2 is in the vehicle.

[0021] 2-1. First preference value calculation process PR1 In the first preference value calculation process (or simply the calculation process) PR1, the ECU 22 calculates the inter-vehicle preference value PV1 using the function f1 (the first function). The inter-vehicle preference value PV1 is a value indicating the preference of the driver 2 regarding the "inter-vehicle information". FIG. 2 is a diagram for explaining the inter-vehicle information used in the embodiment. Here, the inter-vehicle information referred to is, as shown in FIG. 2, the inter-vehicle time T or the inter-vehicle distance D of the host vehicle 1 with respect to the preceding vehicle during following driving. The following description will be given by taking the inter-vehicle time T as an example, but the same applies to the inter-vehicle distance D.

[0022] As shown in the following formula (1), the function f1 shows the relationship of the inter-vehicle preference value PV1 with respect to the inter-vehicle time T and the host vehicle speed (vehicle speed V). The function f1 is specified in advance based on the data of the inter-vehicle time T and the vehicle speed V included in the driving data DD of multiple drivers. The function f1 is stored in the storage device 30 as a relational expression, for example, as in formula (1). Alternatively, the function f1 may be stored as a map (table). PV1 = f1(T, V) ···(1)

[0023] The inter-vehicle preference value PV1 indicates the driving characteristics of the driver 2 regarding the inter-vehicle time T during following driving. More specifically, for example, the inter-vehicle preference value PV1 is the percentile value of the inter-vehicle time T at each vehicle speed V based on the data (big data) of the inter-vehicle time T and the vehicle speed V collected for multiple drivers. That is, the inter-vehicle preference value PV1 takes values from 0 to 100. Here, as an example, it is assumed that the inter-vehicle preference value PV1 is the percentile value when the data of the inter-vehicle time T at each vehicle speed V is arranged in descending order of numerical value. For this reason, the shorter the inter-vehicle time T, the larger the percentile value (i.e., the inter-vehicle preference value PV1). Therefore, the larger the value of the inter-vehicle preference value PV1, the more aggressive the driver is regarding the setting (selection) of the inter-vehicle time T. According to the function f1, the inter-vehicle preference value PV1 thus specified can be calculated from the inter-vehicle time T and the vehicle speed V.

[0024] The calculation process PR1 is executed during the following driving in manual driving by the driver 2. In the calculation process PR1, the ECU 22 calculates the inter-vehicle preference value PV1 of the driver 2 according to the inter-vehicle time T and the vehicle speed V obtained during the following driving according to the function f1. According to the calculation process PR1, the inter-vehicle preference value PV1 is calculated as the learning value of the driving preference of the driver 2 for the inter-vehicle time T.

[0025] 2-2. Second preference value calculation process PR2 The second preference value calculation process (or simply the calculation process) PR2 corresponds to the process of calculating the remaining driving preference values PV2 to PV5.

[0026] (Acceleration preference value PV2) First, the acceleration preference value PV2 indicates the preference of the driver 2 for the acceleration Gxa of the host vehicle 1 during the following driving. More specifically, the acceleration Gxa corresponds to the acceleration when accelerating the host vehicle 1 in response to the acceleration of the preceding vehicle during the following driving. In the calculation process PR2, the ECU 22 calculates the acceleration preference value PV2 based on the inter-vehicle preference value PV1 calculated by the calculation process PR1. The storage device 30 stores each of the functions f2 and f3 related to the acceleration preference value PV2 as a relational expression or a map.

[0027] As shown in the following formula (2), the function f2 shows the relationship of the acceleration preference value PV2 with respect to the relative speed ΔV, the acceleration Gxa, and the inter-vehicle time T. The relative speed ΔV corresponds to the difference between the vehicle speed V of the host vehicle and the speed of the preceding vehicle. The function f2 is specified in advance based on the data of the relative speed ΔV, the acceleration Gxa, and the inter-vehicle time T included in the driving data DD of multiple drivers. PV2=f2(ΔV,Gxa,T) ···(2)

[0028] The acceleration preference value PV2 indicates the driving characteristics of driver 2 regarding the acceleration Gxa during following driving. More specifically, for example, the acceleration preference value PV2 is the percentile value of the acceleration Gxa at each relative speed ΔV and each time headway T based on the data (big data) of the relative speed ΔV, acceleration Gxa, and time headway T collected for a plurality of drivers. That is, the acceleration preference value PV2 takes values from 0 to 100. Here, as an example, it is assumed that the acceleration preference value PV2 is the percentile value when the data of the acceleration Gxa at each relative speed ΔV and each time headway T are arranged in ascending order of numerical value. Therefore, the higher the acceleration Gxa, the larger the percentile value (i.e., the acceleration preference value PV2). Thus, the acceleration preference value PV2 indicates that the higher its value, the more aggressive the driver is regarding the requirement (selection) of the acceleration Gxa. According to the function f2, the acceleration preference value PV2 thus specified can be calculated from the relative speed ΔV, acceleration Gxa, and time headway T.

[0029] As shown in the following formula (3), the function f3 indicates the relationship between the acceleration preference value PV2 and the time headway preference value PV1. PV2 = f3(PV1) ···(3)

[0030] The function f3 is specified in advance based on the driving data DD of a plurality of drivers, the function f1, and the function f2. FIG. 3 is a graph showing the relationship of each driving preference value PV for each driver. In FIG. 3, the relationships of the acceleration preference value PV2 and the deceleration preference value PV3 with respect to the time headway preference value PV1 are shown for nine drivers as an example. Each driving preference value PV1 to PV3 in FIG. 3 is calculated for each driver according to the above-mentioned functions f1 and f2 and the following function f4 based on the driving data DD of the nine drivers. It should be noted that the same applies to the following deceleration timing preference value PV4 and acceleration timing preference value PV5.

[0031] As shown in Fig. 3, when looking at each driving preference value PV for each driver, it can be seen that the driving preference values PV2 and PV3 take values close to the inter-vehicle preference value PV1 of the same driver. That is, from the analysis result of the driving data DD, it can be seen that a high correlation is recognized between the inter-vehicle preference value PV1 and the other driving preference values PV2 and PV3. In this embodiment, based on this finding, from the relationship between the inter-vehicle preference value PV1 and the acceleration preference value PV2 obtained from the functions f1 and f2 respectively using the driving data DD of multiple drivers, an approximate function is pre-specified as the function f3.

[0032] By using the above-mentioned function f3, once the inter-vehicle preference value PV1 of driver 2 is calculated (acquired) under a certain inter-vehicle time T and a certain vehicle speed V during following driving, the acceleration preference value PV2 can be calculated from the inter-vehicle preference value PV1 and the function f3. That is, during following driving by driver 2, it is not necessary to obtain the relative speed ΔV corresponding to the argument of the function f2 and the acceleration Gxa (excluding the inter-vehicle time T acquired as the argument of the function f1), and the acceleration preference value PV2 can be calculated from the inter-vehicle preference value PV1. Thus, according to the function f3, if the value of the inter-vehicle preference value PV1 of a certain driver is known, the preference for the acceleration Gxa of the said driver can be grasped from the inter-vehicle preference value PV1. This also applies to the other driving preference values PV3 to PV5 described later. Thus, according to this embodiment, while simplifying the processing for learning driving preferences during following driving in manual driving, each driving preference value PV can be obtained.

[0033] (Deceleration preference value PV3) Next, the deceleration preference value PV3 indicates the preference of driver 2 regarding the deceleration Gxb of the host vehicle 1 during following driving. More specifically, the deceleration Gxb corresponds to the deceleration when decelerating the host vehicle 1 in response to the deceleration of the preceding vehicle during following driving. In the calculation process PR2, the ECU22 calculates the deceleration preference value PV3 based on the inter-vehicle preference value PV1 calculated by the calculation process PR1. The storage device 30 stores each of the functions f4 and f5 related to the deceleration preference value PV3 as a relational expression or a map.

[0034] As shown in the following formula (4), the function f4 shows the relationship of the deceleration preference value PV3 with respect to the relative speed ΔV, the deceleration Gxb, and the inter-vehicle time T. The function f4 is specified in advance based on the data of the relative speed ΔV, the deceleration Gxb, and the inter-vehicle time T included in the driving data DD of multiple drivers. PV3 = f4(ΔV, Gxb, T) ···(4)

[0035] The deceleration preference value PV3 indicates the driving characteristics of Driver 2 regarding the deceleration Gxb during following driving. The details of the deceleration preference value PV3 are the same as those of the acceleration preference value PV2, except that the deceleration Gxb is targeted instead of the acceleration Gxa. Therefore, although the detailed description is omitted, for example, the larger the value of the deceleration preference value PV3, the more aggressive the driver is regarding the requirement (selection) of the deceleration Gxb.

[0036] As shown in the following formula (5), the function f5 shows the relationship of the deceleration preference value PV3 with respect to the inter-vehicle preference value PV1. The correlation between the inter-vehicle preference value PV1 and the deceleration preference value PV3 is as described together with FIG. 3. In the present embodiment, based on this finding, an approximation function is specified in advance as the function f5 from the relationship between the inter-vehicle preference value PV1 and the deceleration preference value PV3 respectively obtained from the functions f1 and f4 using the driving data DD of multiple drivers. PV3 = f5(PV1) ···(5)

[0037] (Deceleration timing preference value PV4) Next, the deceleration timing preference value PV4 is a value indicating the driver 2's preference regarding the deceleration timing TMb of the host vehicle 1 during following driving. More specifically, the deceleration timing TMb corresponds to, for example, the time (response time) from the deceleration start point of the preceding vehicle to the deceleration start point of the host vehicle 1 when decelerating the host vehicle 1 in response to the deceleration of the preceding vehicle during following driving. In the calculation process PR2, the ECU 22 calculates the deceleration timing preference value PV4 based on the inter-vehicle preference value PV1 calculated by the calculation process PR1. The storage device 30 stores each of the functions f6 and f7 related to the deceleration timing preference value PV4 as a relational expression or a map.

[0038] As shown in the following formula (6), the function f6 shows the relationship of the deceleration timing preference value PV4 with respect to the relative speed ΔV, the deceleration timing TMb, and the inter-vehicle time T. The function f6 is specified in advance based on the data of the relative speed ΔV, the deceleration timing TMb, and the inter-vehicle time T included in the driving data DD of a plurality of drivers. PV4 = f6(ΔV, TMb, T) ···(6)

[0039] The deceleration timing preference value PV4 indicates the driving characteristics of the driver 2 regarding the deceleration timing TMb during following driving. The details of the deceleration timing preference value PV4 are the same as those of the acceleration preference value PV2, except that the deceleration timing TMb is targeted instead of the acceleration Gxa. Therefore, although the detailed description thereof is omitted, for example, the earlier the deceleration timing TMb is, that is, the shorter the above response time is, the more aggressive the driver is regarding the setting (selection) of the deceleration timing TMb.

[0040] As shown in the following formula (7), function f7 shows the relationship between the deceleration timing preference value PV4 and the inter-vehicle preference value PV1. Similar to the relationship shown in Figure 3, a high correlation is also recognized between the inter-vehicle preference value PV1 and the deceleration timing preference value PV4. In this embodiment, based on this finding, an approximate function is specified in advance as function f7 from the relationships between the inter-vehicle preference value PV1 and the deceleration timing preference value PV4 respectively obtained from functions f1 and f6 using the driving data DD of multiple drivers. PV4 = f7(PV1) ···(7)

[0041] (Acceleration timing preference value PV5) Next, the acceleration timing preference value PV5 is a value indicating the preference of driver 2 regarding the acceleration timing TMa of the host vehicle 1 during following driving. More specifically, the acceleration timing TMa corresponds to, for example, the time (response time) from the acceleration start point of the preceding vehicle to the acceleration start point of the host vehicle 1 when accelerating the host vehicle 1 in response to the acceleration of the preceding vehicle during following driving. In the calculation process PR2, the ECU22 calculates the acceleration timing preference value PV5 based on the inter-vehicle preference value PV1 calculated by the calculation process PR1. The storage device 30 stores each of functions f8 and f9 related to the acceleration timing preference value PV5 as a relational expression or a map.

[0042] As shown in the following formula (8), function f8 shows the relationship between the relative speed ΔV, the acceleration timing TMa, and the acceleration timing preference value PV5 with respect to the inter-vehicle time T. Function f9 is specified in advance based on the data of the relative speed ΔV, the acceleration timing TMa, and the inter-vehicle time T included in the driving data DD of multiple drivers. PV5 = f8(ΔV, TMa, T) ···(8)

[0043] The acceleration timing preference value PV5 indicates the driving characteristics of driver 2 regarding the acceleration timing TMa during following driving. The details of the acceleration timing preference value PV5 are the same as those of the acceleration preference value PV2, except that the acceleration timing TMa is targeted instead of the acceleration Gxa. Therefore, although the detailed description thereof is omitted, for example, the earlier the acceleration timing TMa, that is, the shorter the above response time, the more aggressive the driver is regarding the setting (selection) of the acceleration timing TMa.

[0044] As shown in the following formula (9), the function f9 indicates the relationship between the acceleration timing preference value PV5 and the inter-vehicle preference value PV1. Similar to the relationship shown in FIG. 3, a high correlation is also recognized between the inter-vehicle preference value PV1 and the acceleration timing preference value PV5. In the present embodiment, based on this finding, an approximation function is specified in advance as the function f9 from the relationships between the inter-vehicle preference value PV1 and the acceleration timing preference value PV5 respectively obtained from the functions f1 and f8 using the driving data DD of multiple drivers. PV5 = f9(PV1) ···(9)

[0045] 2-3. Target value calculation process PR3 In the target value calculation process (or simply the calculation process) PR3, the ECU22 calculates the control target values of the acceleration Gxa, deceleration Gxb, deceleration timing TMb, and acceleration timing TMa respectively used during following driving in the automatic driving while driver 2 is in the vehicle.

[0046] Specifically, the ECU22 calculates the target value Gxat of the acceleration Gxa as the control target value based on the acceleration preference value PV2 calculated by the calculation process PR2. More specifically, for the calculation of the target value Gxat, the acceleration preference value PV2 calculated according to the above function f3, the current relative speed ΔV, and the inter-vehicle time T are used. Then, the target value Gxat corresponding to the acceleration preference value PV2, the current relative speed ΔV, and the inter-vehicle time T is calculated according to the function f2.

[0047] In the calculation process PR3, the target values Gxbt, TMbt, and TMat of the deceleration Gxb, deceleration timing Tmb, and acceleration timing Tma are also calculated in the same way as the target value Gxat. That is, functions f4 and f5 are used to calculate the target value Gxbt according to the deceleration preference value PV3. Functions f6 and f7 are used to calculate the target value TMbt according to the deceleration timing preference value PV4. And functions f8 and f9 are used to calculate the target value TMat according to the acceleration timing preference value PV5.

[0048] 2-4. Flow of the process Figure 4 is a flowchart showing an example of a process related to vehicle driving control according to the embodiment. The process of this flowchart is repeatedly executed during the startup of the vehicle control system 10. Additionally, when the vehicle control system 10 starts up, the ECU 22 executes a process of identifying the driver 2 currently on board the vehicle 1 using the driver monitor 26. Alternatively, the identification of the driver 2 may be executed, for example, every time the driving mode is switched between manual driving and automatic driving during the startup of the vehicle control system 10.

[0049] In step S100, the ECU 22 (processor 28) determines whether the vehicle 1 is in manual driving or automatic driving. This determination can be made, for example, based on the operation state of the driving mode switch 24.

[0050] If the vehicle 1 is in manual driving (step S100; Yes), the process proceeds to step S102. In step S102, the ECU 22 determines whether the inter-vehicle preference learning condition is satisfied. The inter-vehicle preference learning condition is a condition for executing the calculation (learning) of the inter-vehicle preference value PV1 of the currently identified driver 2. The learning condition is, for example, the presence of a preceding vehicle, the absolute value of the moving average value of the relative speed ΔV for a predetermined period (e.g., 5 seconds) being within a predetermined threshold (e.g., 2 km / h), the vehicle speed V of the host vehicle 1 being higher than a predetermined threshold (e.g., 1 km / h), and the absolute value of the longitudinal acceleration Gx of the host vehicle 1 being within a predetermined threshold (e.g., 0.2 m / s 2being less than, and including that these four conditions hold for a predetermined time (e.g., 4 seconds) or more.

[0051] When the inter-vehicle preference learning condition does not hold (step S102; No), the process proceeds to the return. On the other hand, when the inter-vehicle preference learning condition holds (step S102; Yes), the process proceeds to step S104.

[0052] In step S104, the ECU 22 acquires the current inter-vehicle time T and the current vehicle speed V. The vehicle speed V is detected using the vehicle state sensor 12. The inter-vehicle time T is calculated based on the detected vehicle speed V and the inter-vehicle distance D acquired using, for example, the recognition sensor 14. Thereafter, the process proceeds to step S106.

[0053] In step S106, the ECU 22 calculates the inter-vehicle preference value PV1 of the driver 2 currently performing following driving as a learning value. The inter-vehicle preference value PV1 is calculated from the inter-vehicle time T and the vehicle speed V acquired in step S104 and the function f1. The calculated inter-vehicle preference value PV1 is stored in the storage device 30. Note that each of the inter-vehicle time T and the vehicle speed V used to calculate the inter-vehicle preference value PV1 using the function f1 may be, for example, the average value or the median value of the values acquired a plurality of times in step S104 each time the inter-vehicle preference learning condition holds. In FIG. 4, the processes of steps S104 and S106 correspond to the "first preference value calculation process PR1".

[0054] In step S108 following step S106, the ECU 22 calculates the remaining driving preference values PV2 to PV5 from the calculated inter-vehicle preference value PV1 using the functions f3, f5, f7, and f9. That is, the ECU 22 executes the second preference value calculation process PR2. The calculated driving preference values PV2 to PV5 are stored in the storage device 30.

[0055] On the other hand, when the vehicle 1 is in the process of automatic driving (step S100; No), the ECU 22 executes the above-described automatic driving control, and the process proceeds to step S110. In step S110, the ECU 22 determines whether the preference learning has been completed. Specifically, in step S110, the ECU 22 determines whether the process has advanced to step S108 during manual driving and whether the current driving preference values PV2 to PV5 of the driver 2 have been acquired and stored together with the inter-vehicle preference value PV1.

[0056] If the determination result in step S110 is No, the process returns. On the other hand, if the determination result is Yes, the process proceeds to step S112. In step S112, the ECU 22 reflects each driving preference value PV1 to PV5 on each control target value of the following driving. Specifically, the ECU 22 calculates the target value Tt of the inter-vehicle time T from the inter-vehicle preference value PV1 calculated in step S106, the current vehicle speed V, and the function f1. Further, the ECU 22 executes the above-described target value calculation process PR3 to calculate the respective target values Gxat, Gxbt, TMbt, and TMat of the remaining driving preference values PV2 to PV5.

[0057] 3. Effects As described above, according to the present embodiment, during the following driving in manual driving by the driver 2, the inter-vehicle preference value PV1 of the driver 2 is calculated from the inter-vehicle time T (inter-vehicle information) and the vehicle speed V. Then, the remaining driving preference values PV2 to PV5 are calculated (derived) from the inter-vehicle preference value PV1. That is, each driving preference value PV1 to PV5 of the driver 2 can be calculated from the inter-vehicle time T and the vehicle speed V. Thus, according to the present embodiment, the driving preference values PV1 to PV5 of the driver 2 regarding the following driving can be easily and appropriately acquired. And the following driving in which each driving preference value PV1 to PV5 is reflected can be performed during automatic driving.

[0058] Incidentally, in the above-described embodiments, for the calculation of each driving preference value PV1 to PV5, functions f1 to f9 specified in advance according to a statistical method are used with the driving data DD of a plurality of drivers. Instead of such an example, the functions f1 to f9 may be specified in advance using machine learning with the driving data DD of a plurality of drivers.

[0059] Also, in step S108 described above, the driving preference values PV2 to PV5 are calculated from the inter-vehicle preference value PV1 using the functions f3, f5, f7, and f9. Instead of such an example, based on the findings described with FIG. 3, the same value as the inter-vehicle preference value PV1 may be calculated (set) as each driving preference value PV2 to PV5.

[0060] Also, the remaining driving preference values PV calculated from the inter-vehicle preference value PV1 may be a plurality that are not any one or all of the acceleration preference value PV2, the deceleration preference value PV3, the deceleration timing preference value PV4, and the acceleration timing preference value PV5.

[0061] In the above-described embodiments, the storage device 30 and the processor 28, which are examples of the "storage device" and "processor" according to the present disclosure, are mounted on the vehicle 1. As another example, at least a part of the "storage device" according to the present disclosure may be provided in an external system communicable with the vehicle 1. The external system is, for example, a management server on the cloud. Similarly, at least a part of the processing by the "processor" according to the present disclosure may be executed by a processor provided in the external system.

Description of Reference Numerals

[0062] 1 Vehicle, 2 Driver, 10 Vehicle Control System, 12 Vehicle State Sensor, 14 Recognition Sensor, 16 Position Sensor, 18 Communication Device, 20 Travel Device, 22 Electronic Control Unit (ECU), 24 Driving Switch, 26 Driver Monitor, 28 Processor, 30 Storage Device

Claims

1. A control device for controlling a host vehicle capable of switching between manual driving and automatic driving, a storage device that stores a first function that is specified in advance based on driving data of a plurality of drivers and shows the relationship between inter-vehicle information and an inter-vehicle preference value with respect to the host vehicle speed, a processor, and is provided with, wherein the inter-vehicle information is the inter-vehicle time or the inter-vehicle distance of the host vehicle with respect to a preceding vehicle, the inter-vehicle preference value indicates the driver's preference for the inter-vehicle information, the processor, calculates the driver's inter-vehicle preference value corresponding to the inter-vehicle information and the host vehicle speed acquired during following driving in the manual driving by the driver according to the first function, calculates a remaining driving preference value indicating the driver's preference for at least one of the acceleration, deceleration, deceleration timing, and acceleration timing of the host vehicle during the following driving based on the calculated inter-vehicle preference value, and executes a target value calculation process for calculating a control target value of at least one of the acceleration, the deceleration, the deceleration timing, and the acceleration timing in the automatic driving during the driver's ride based on the calculated remaining driving preference value for a vehicle control device.

2. The storage device, stores a second function that is specified in advance based on the driving data of the plurality of drivers and shows the relationship between the relative speed between the preceding vehicle speed and the host vehicle speed, the acceleration, and the acceleration preference value with respect to the inter-vehicle information, and a third function that is specified in advance based on the driving data of the plurality of drivers, the first function, and the second function and shows the relationship between the acceleration preference value with respect to the inter-vehicle preference value, and stores, wherein the acceleration preference value is one of the remaining driving preference values, the processor, calculates the acceleration preference value corresponding to the inter-vehicle preference value according to the third function, and in the target value calculation process, calculates the target value of the acceleration corresponding to the acceleration preference value calculated according to the third function, the relative speed, and the inter-vehicle information as the control target value according to the second function for the vehicle control device according to Claim 1.

3. The storage device, stores a fourth function that is specified in advance based on the driving data of the plurality of drivers and shows the relationship between the relative speed between the preceding vehicle speed and the host vehicle speed, the deceleration, and the deceleration preference value with respect to the inter-vehicle information, A fifth function that is specified in advance based on the driving data of the plurality of drivers, the first function, and the fourth function, and that indicates the relationship between the deceleration preference value and the inter-vehicle preference value store it The deceleration preference value is one of the remaining driving preference values The processor calculates the deceleration preference value corresponding to the inter-vehicle preference value according to the fifth function In the target value calculation process, calculate the target value of the deceleration as the control target value according to the fourth function based on the deceleration preference value calculated according to the fifth function, the relative speed, and the inter-vehicle information The vehicle control device according to claim 1

4. The storage device A sixth function that is specified in advance based on the driving data of the plurality of drivers, and that indicates the relationship between the relative speed between the preceding vehicle speed and the host vehicle speed, the deceleration timing, and the deceleration timing preference value with respect to the inter-vehicle information A seventh function that is specified in advance based on the driving data of the plurality of drivers, the first function, and the sixth function, and that indicates the relationship between the deceleration timing preference value and the inter-vehicle preference value store them The deceleration timing preference value is one of the remaining driving preference values The processor calculates the deceleration timing preference value corresponding to the inter-vehicle preference value according to the seventh function In the target value calculation process, calculate the target value of the deceleration timing as the control target value according to the sixth function based on the deceleration timing preference value calculated according to the seventh function, the relative speed, and the inter-vehicle information The vehicle control device according to claim 1

5. The storage device An eighth function that is specified in advance based on the driving data of the plurality of drivers, and that indicates the relationship between the relative speed between the preceding vehicle speed and the host vehicle speed, the acceleration timing, and the acceleration timing preference value with respect to the inter-vehicle information A ninth function that is specified in advance based on the driving data of the plurality of drivers, the first function, and the eighth function, and that indicates the relationship between the acceleration timing preference value and the inter-vehicle preference value store them The acceleration timing preference value is one of the remaining driving preference values The processor calculates the acceleration timing preference value corresponding to the inter-vehicle preference value according to the ninth function In the target value calculation process, calculate the target value of the acceleration timing as the control target value according to the eighth function, based on the acceleration timing preference value calculated according to the ninth function, the relative speed, and the inter-vehicle information. The vehicle control device according to claim 1.

Images