Vehicle control device

Abstract

To provide a vehicle control device capable of performing automatic driving providing preferable riding feeling for occupants other than a driver.SOLUTION: A vehicle control device of the present invention can switch between automatic driving and manual driving, learns driving characteristics during the manual driving, and reflects learned values of the driving characteristics in control during the automatic driving. In the learned values of the driving characteristics, states of occupants other than a driver during the manual driving and the driving characteristics are associated with each other.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The present invention relates to a vehicle control device. [Background technology]

[0002] Patent Document 1 discloses a technology for learning the driving operations of a driver during manual driving in a vehicle capable of switching between manual driving and automatic driving, and applying the learning results to driving control for automatic driving. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] International Publication No. 2018 / 193536 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the technology disclosed in Patent Document 1 does not take into account the state of passengers other than the driver sitting in the back seat, etc., and therefore if the proportion of learning of driving operations during manual driving by the driver that are uncomfortable for passengers other than the driver is high, there is a risk that the ride will be uncomfortable for passengers other than the driver during autonomous driving if the learning results are applied to the driving control of the autonomous driving.

[0005] The present invention has been made in consideration of the above-mentioned problems, and its object is to provide a vehicle control device that can perform automatic driving that is comfortable for passengers other than the driver. [Means for solving the problem]

[0006] In order to solve the above-mentioned problems and achieve the objective, the vehicle control device of the present invention is a vehicle control device that is capable of switching between automatic driving and manual driving, learns driving characteristics during manual driving, and reflects the learned value of the driving characteristics in control during automatic driving, and is characterized in that the learned value of the driving characteristics is linked to the state of occupants other than the driver during the manual driving.

[0007] This makes it possible to implement automatic driving that is comfortable for passengers other than the driver by reflecting the learned values ​​of driving characteristics that take into account the state of passengers other than the driver during manual driving in the control of automatic driving.

[0008] In the above, the state of the occupant other than the driver during the manual driving may include at least the presence or absence of the occupant other than the driver.

[0009] This makes it possible to realize smooth automated driving that takes into consideration passengers other than the driver while reflecting the driver's driving preferences in the driving characteristics.

[0010] In addition, in the above, a vehicle interior state in which only the driver is present may be defined as a first vehicle interior state, and a vehicle interior state in which passengers other than the driver are present may be defined as a second vehicle interior state, and the learning value of the driving characteristics may be set so that the second vehicle interior state results in slower driving characteristics than the first vehicle interior state.

[0011] This makes it possible to realize automated driving that provides a comfortable ride for passengers.

[0012] In the above, the learned value of the driving characteristic may be further linked to a psychological state of the driver.

[0013] As a result, even during manual driving in the second vehicle interior state, if the driver's psychological state is in a hurry, the learned value of the driving characteristics at that time is not reflected, and the driver's psychological state is taken into account in the learning of the driving characteristics, making it possible to implement automatic driving that is more comfortable for occupants. Effect of the Invention

[0014] The vehicle control device of the present invention has the effect of being able to implement automatic driving that is comfortable for occupants other than the driver by reflecting learned values ​​of driving characteristics that take into account the state of occupants other than the driver during manual driving in the control of automatic driving. [Brief description of the drawings]

[0015] [Figure 1] FIG. 1 is a block diagram showing a functional configuration of a vehicle according to an embodiment. [Diagram 2] FIG. 2 is a flowchart showing a first example of control performed by the ECU. [Diagram 3] FIG. 3 is a diagram showing an example of the degree of steepness and gradualness for each of various items in the first and second operating characteristics. [Figure 4] FIG. 4 is a flowchart showing a second example of the control executed by the ECU. [Diagram 5] FIG. 5 is a flowchart showing a third example of the control executed by the ECU. [Figure 6] FIG. 6 is a diagram showing another example of setting the degree of steepness and gradualness for each of various items in the first and second operating characteristics. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0016] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of a vehicle control device according to the present invention will be described below. However, the present invention is not limited to the embodiment.

[0017] FIG. 1 is a block diagram showing a functional configuration of a vehicle 10 according to an embodiment.

[0018] The vehicle 10 shown in Fig. 1 includes an operation unit 11, a drive unit 12, an imaging unit 13, a sensor group 14, a battery 15, a car navigation system 16, a storage unit 17, a communication unit 18, and an ECU (Electronic Control Unit) 19. In the following, an electric vehicle capable of autonomous driving will be described as the vehicle 10, but the vehicle 10 is not limited to this. Furthermore, the vehicle 10 can automatically move toward a destination under the control of a center server or the ECU 19. Of course, the vehicle 10 can also be moved toward a destination desired by a user, such as a driver who has used the vehicle or a passenger who has boarded the vehicle, by operating a steering wheel or the like.

[0019] The operation unit 11 is configured using a steering wheel, an accelerator pedal, a brake pedal, etc. The operation unit 11 accepts operations by a driver (operator) who gets on the vehicle 10 or a passenger (passenger) other than the driver.

[0020] The drive unit 12 is configured using a motor, etc. Under the control of the ECU 19, the drive unit 12 supplies driving force to drive wheels of the vehicle 10 based on electric power supplied from the battery 15.

[0021] The imaging unit 13 is configured using an imaging device including one or more lenses, and a charge coupled device (CCD) image sensor or a complementary metal oxide semiconductor (CMOS) image sensor that captures an image of a subject focused by the lens. A plurality of imaging units 13 are arranged outside the vehicle 10 and inside the vehicle 10. For example, when the imaging units 13 are arranged inside the vehicle 10, they are arranged near the entrance of the vehicle 10, near the exit of the vehicle 10, near the seat of the vehicle 10, and near the driver's seat of the vehicle 10. When the imaging units 13 are arranged outside the vehicle 10, they are arranged in front of, behind, and on the sides of the vehicle 10. The imaging units 13 capture images under the control of the ECU 19, and output image data obtained by the capture to the ECU 19.

[0022] The sensor group 14 is configured using sensors for realizing automatic driving and sensors for detecting the remaining amount of the battery 15. Specifically, the sensor group 14 is configured using 3D-LiDAR, a millimeter wave sensor, an infrared sensor, a vehicle speed sensor, an angular velocity sensor, a gyro sensor, an acceleration sensor, and the like. Furthermore, the sensor group 14 is configured using sensors for detecting the driver's operation on the operation unit 11, and is configured using, for example, an accelerator pedal sensor, a brake pedal sensor, a steering sensor, a seating sensor, a seat belt sensor, and the like. In addition, the sensor group 14 is configured using a tester for detecting the remaining amount (SOC), temperature, SOH (State of Health), voltage value, and current value of the battery 15, and a temperature sensor, and the like. The sensor group 14 outputs various detection results to the ECU 19.

[0023] Battery 15 is configured using a rechargeable secondary battery such as a nickel-metal hydride battery or a lithium-ion battery. Battery 15 stores high-voltage DC power for driving vehicle 10. Battery 15 can be electrically connected to charging device 30 via a charging port (not shown), and is charged with external power supplied from charging device 30.

[0024] The car navigation system 16 includes a GPS (Global Positioning System) sensor 161 , a map database 162 , an alarm device 163 , and an input unit 164 .

[0025] The GPS sensor 161 receives signals from multiple GPS satellites or transmitting antennas, and calculates the position (longitude and latitude) of the vehicle 10 based on the received signals. The GPS sensor 161 is configured using a GPS receiving sensor, etc. In this embodiment, the orientation accuracy of the vehicle 10 may be improved by mounting multiple GPS sensors 161.

[0026] The map database 162 stores various map data and is configured using a storage medium such as a hard disk drive (HDD) or a solid state drive (SSD).

[0027] The notification device 163 has a display unit 163a that displays images, maps, videos, and text information, and an audio output unit 163b that generates sounds such as voices and alarm sounds. The display unit 163a is configured using a display such as a liquid crystal display or an organic EL (Electro Luminescence) display. The audio output unit 163b is configured using a speaker or the like.

[0028] The input unit 164 receives operation input, voice input, and the like from the user, and outputs signals according to the contents of the received various operations to the ECU 19. The input unit 164 is realized using a touch panel, buttons, switches, a jog dial, a microphone, and the like.

[0029] The car navigation system 16 configured in this manner overlays the current position of the vehicle 10 acquired by the GPS sensor 161 on a map corresponding to the map data stored in the map database 162, and notifies the user of information including the road on which the vehicle 10 is currently traveling and the driving route to the destination via the display unit 163a and the audio output unit 163b.

[0030] The storage unit 17 stores various information related to the vehicle 10. The vehicle information includes identification information (e.g., a vehicle ID) for identifying the vehicle 10, the vehicle model of the vehicle 10, and fuel efficiency information. The storage unit 17 also stores CAN data of the vehicle 10 input from the ECU 19, various programs executed by the ECU 19, and the like. The storage unit 17 is configured using a dynamic random access memory (DRAM), a read only memory (ROM), a flash memory, a hard disk drive (HDD), a solid state drive (SSD), and the like. The storage unit 17 also includes a program storage unit 171 executed by the vehicle 10, a learned model storage unit 172 that stores a learned model used by the ECU 19 when calculating the power consumption amount and the cruising range, a learned model used by the ECU 19 when calculating the driving characteristics during manual driving, and the like, and a vehicle information storage unit 173 that stores vehicle information for identifying the vehicle 10. Here, the trained model is formed, for example, by using a DNN (Deep Neural Network) as machine learning. The type of DNN network is not particularly limited, but may be, for example, a method in which teacher data or learning data that links the state of a passenger other than the driver during manual driving with the driving characteristics during manual driving is prepared, and the teacher data or learning data is input into a calculation model based on a multilayer neural network for learning. A method in which teacher data or learning data that links the vehicle model, fuel efficiency, speed, and distance of the vehicle 10 with the power consumption of the vehicle 10 is prepared, and the teacher data or learning data is input into a calculation model based on a multilayer neural network for learning. Furthermore, as a machine learning method, for example, a method based on DNN of a multilayer neural network such as CNN (Convolutional Neural Network) or 3D-CNN may be used.

[0031] The communication unit 18 transmits various data to the center server through the network NW under the control of the ECU 19, and receives various data from the center server. For example, the communication unit 18 acquires traffic information from the center server under the control of the ECU 19, and outputs the acquired traffic information to the ECU 19. The communication unit 18 is configured using a communication module capable of transmitting and receiving various information.

[0032] The ECU 19 is configured using a memory and a processor having hardware such as a CPU (Central Processing Unit). The ECU 19 controls each part of the vehicle 10. For example, when the driving mode of the vehicle 10 is set to an autonomous driving mode, the ECU 19 controls the drive unit 12 using the detection results of the sensor group 14, etc., to make the vehicle 10 run autonomously. The ECU 19 has an acquisition unit 191, a decision unit 192, a first calculation unit 193, a second calculation unit 194, an output control unit 195, a mode setting unit 196, and a determination unit 197. In this embodiment, the ECU 19 functions as a control device.

[0033] The acquisition unit 191 acquires the destination and the current position of the vehicle 10. Specifically, the acquisition unit 191 acquires the destination of the vehicle 10 input by the driver or a passenger other than the driver via the input unit 164, and acquires the current position of the vehicle 10 via the GPS sensor 161 and the map database 162.

[0034] The determination unit 192 selects from among a plurality of travel routes and determines a travel route based on the destination of the vehicle 10, the current position of the vehicle 10, and the map database 162. Specifically, the determination unit 192 selects from among the plurality of travel routes a travel route that provides the shortest distance between the destination of the vehicle 10 and the current position, and determines the travel route.

[0035] The first calculation unit 193 calculates the power consumption amount by predicting the power consumption of the battery 15 consumed on the driving route from the current position to the destination in each of the automatic driving mode and the manual driving mode based on the destination of the vehicle 10 and the current position of the vehicle 10. Specifically, the first calculation unit 193 calculates the power consumption amount by inputting the distance, gradient, and presence or absence of traffic congestion on the driving route from the current position to the destination as input data, and outputting the power consumption amount as output data, using the learned model stored in the learned model storage unit 172. In addition, the first calculation unit 193 calculates the cruising distance of the vehicle 10 in each of the automatic driving mode and the manual driving mode based on the current remaining amount of the battery 15 and the calculated predicted power consumption. Specifically, the first calculation unit 193 calculates the available driving distance in each of the automatic driving mode and the manual driving mode based on the current remaining charge of the battery 15 obtained via the sensor group 14, the calculated predicted power consumption, the distance of the driving route determined by the determination unit 192, the gradient of the driving route, the presence or absence of traffic congestion on the driving route, and the charging location (e.g., a charging station) of a charging device installed on the driving route.

[0036] The second calculation unit 194 learns the driving characteristics during manual driving based on learning data in which the states of passengers other than the driver during manual driving are linked to the driving characteristics during manual driving, using the learned model stored in the learned model storage unit 172 of the storage unit 17. Then, the second calculation unit 194 outputs the learned learning value and stores it in the storage unit 17.

[0037] The output control unit 195 outputs at least one of the predicted power consumption in each of the automatic driving mode and the manual driving mode, and the cruising distance in each of the automatic driving mode and the manual driving mode, calculated by the first calculation unit 193. Specifically, the output control unit 195 displays at least one of the predicted power consumption and the cruising distance in each of the automatic driving mode and the manual driving mode by outputting them to the display unit 163a. ​​In addition, when the determination unit 197 determines that congestion has occurred on the driving route on which the vehicle 10 is traveling, the output control unit 195 outputs at least one of the predicted power consumption in each of the automatic driving mode and the manual driving mode, and the cruising distance in each of the automatic driving mode and the manual driving mode, calculated by the first calculation unit 193.

[0038] The mode setting unit 196 sets the driving mode of the vehicle 10 to an automatic driving mode or a manual driving mode, or sets the drive mode (comfort, normal, sporty, etc.) in response to the operation of the input unit 164 by the driver or a passenger other than the driver.

[0039] The determination unit 197 determines whether or not a traffic jam has occurred on the route along which the vehicle 10 is traveling, based on the traffic information acquired by the acquisition unit 191. In addition, the determination unit 197 determines the state inside the vehicle and the mental state of the driver, based on the detection results of the sensor group 14.

[0040] In the vehicle 10 according to the embodiment, the manual driving state is classified from the viewpoint of the state of the vehicle 10 (presence or absence of passengers other than the driver, etc.) and psychological state (hurry, relaxed, etc.), and driving characteristics corresponding to each state of manual driving are learned and stored. During autonomous driving, the corresponding manual driving-based characteristics from the classification are applied as driving characteristics for autonomous driving. This makes it possible to realize smooth autonomous driving that is considerate of passengers while reflecting the driving preferences of the driver.

[0041] In addition, examples of driving characteristic items include items that consider passengers other than the driver, such as "acceleration and jerk during acceleration / deceleration," "timing of starting acceleration / deceleration," "distance between vehicles while following," "distance between vehicles when stopping," "longitudinal acceleration when starting," "vehicle speed entering a corner," "lateral acceleration during a corner," "trajectory of the corner," "lateral acceleration when changing lanes," and "cruising vehicle speed."

[0042] In addition, the in-vehicle state for which the manual driving-based characteristics should be individually stored includes the presence or absence of occupants other than the driver. For example, the in-vehicle state in which only the driver is present is defined as a first in-vehicle state, and the in-vehicle state in which occupants other than the driver are present is defined as a second in-vehicle state. Compared with the first driving characteristic, which is the learning value of the driving characteristic learned in the first in-vehicle state during manual driving, the second driving characteristic, which is the learning value of the driving characteristic learned in the second in-vehicle state during manual driving, is a slow (sluggish) driving characteristic that is considerate of the occupants.

[0043] In the vehicle 10 according to the embodiment, when the vehicle is being driven manually, the first driving characteristic and the second driving characteristic are calculated and stored as the characteristics based on the manual driving base based on the state of the vehicle interior (whether there is a passenger other than the driver, whether the passenger is seated or standing, and the direction of the passenger). When the vehicle is being driven automatically, it is determined whether the setting is such that the characteristics based on the manual driving base (the first driving characteristic and the second driving characteristic) are utilized, and when the characteristics based on the manual driving base are utilized, the first driving characteristic or the second driving characteristic is applied as the driving characteristic for the automatic driving based on the psychological state of the passenger. When the characteristics based on the manual driving are utilized, if no distinction is made based on the psychological state of the passenger, the second driving characteristic may be applied as the driving characteristic during the automatic driving. During the automatic driving, the movement expected by the driver may not match the movement of the vehicle, so the body of the driver during the automatic driving is easily shaken, like a passenger other than the driver during the manual driving. Therefore, it is preferable to apply the second driving characteristic, which is the characteristic based on the manual driving learned in the second vehicle interior state, as the normal driving characteristic during the automatic driving. On the other hand, when the occupant requests more aggressive automatic driving than the normal driving characteristic (second driving characteristic) during automatic driving, the first driving characteristic, which is steeper than the second driving characteristic, may be applied to the driving characteristic during automatic driving. In addition, to detect whether the occupant requests aggressive automatic driving as information on the psychological state of the occupant, for example, information such as hurry or relaxation read from the occupant's face or conversation by the sensor group 14 or the input unit 164, or the selected drive mode (comfort, normal, sporty, etc.) may be used.

[0044] Fig. 2 is a flowchart showing a first example of the control performed by the ECU 19. The control flow shown in Fig. 2 is repeatedly executed, for example, every several [ms]. Fig. 3 is a diagram showing an example of the degree of steepness and gradualness for each item in the first driving characteristic and the second driving characteristic.

[0045] First, the ECU 19 judges whether or not the vehicle is being manually driven (step S1). If the ECU 19 judges that the vehicle is being manually driven (Yes in step S1), it updates the vehicle interior state (step S2). Next, the ECU 19 judges whether or not the vehicle interior state is the driver only (step S3). If the ECU 19 judges that the vehicle interior state is the driver only (Yes in step S3), it calculates a first driving characteristic such that the degree of steepness and sluggishness is set for each item of the driving characteristic as shown in FIG. 3, and stores the calculated first driving characteristic in the storage unit 17 (step S4). After that, the ECU 19 ends the series of controls. On the other hand, in the process of step S3, if the ECU 19 determines that the vehicle interior state is not the driver alone, that is, that there are passengers other than the driver (No in step S3), it learns the driver's preferences from the driving data during manual driving, calculates second driving characteristics so that the degree of steepness and sluggishness is set for each item of the driving characteristics as shown in Fig. 3, and stores the calculated second driving characteristics in the storage unit 17 (step S5). After that, the ECU 19 ends the series of controls.

[0046] In addition, in the process of step S1, if the ECU 19 determines that the vehicle is not being driven manually, that is, that the vehicle is being driven automatically (No in step S1), the ECU 19 updates the setting of the driving characteristics during automatic driving (step S6). Next, the ECU 19 determines whether or not to utilize the characteristics based on manual driving, that is, the first driving characteristics or the second driving characteristics (step S7). If the ECU 19 determines that the characteristics based on manual driving are not to be utilized (No in step S7), the ECU 19 applies the default driving characteristics for automatic driving stored in the storage unit 17 in advance, and ends the series of controls. On the other hand, in the process of step S7, if the ECU 19 determines that the characteristics based on manual driving are to be utilized (Yes in step S7), the ECU 19 updates the passenger's psychological state or the drive mode (step S8). Next, the ECU 19 determines whether or not the passenger's psychological state is hurried or sporty (step S9). If the ECU 19 determines that the passenger's psychological state is hurried or sporty (Yes in step S9), the ECU 19 applies the first driving characteristics, which are the characteristics based on manual driving, (step S10). Then, the ECU 19 ends the series of controls. Also, in the process of step S9, if the ECU 19 determines that the passenger's psychological state is not in a hurry or sporty (No in step S9), the ECU 19 applies the second driving characteristic, which is a characteristic based on manual driving (step S11). Then, the ECU 19 ends the series of controls.

[0047] As described above, the ECU 19 reflects the first driving characteristic and the second driving characteristic, which are learned values ​​that are linked to the state of the occupants other than the driver during manual driving and the driving characteristics during manual driving, in the control of the automatic driving. This makes it possible to implement automatic driving that is comfortable for the occupants with driving characteristics that take into account the state of the occupants.

[0048] The presence or absence of passengers other than the driver has been mentioned as an in-vehicle state in which the manual driving-based characteristics should be stored separately. However, even in the second in-vehicle state in which passengers other than the driver are present during manual driving, the driver is likely to drive recklessly if he / she is in a hurry or wants to drive sporty. Therefore, it is preferable not to reflect the learning value learned when the driver's psychological state is in a hurry or sporty in the second in-vehicle state during manual driving in the second driving characteristic as the manual driving-based characteristic. Also, the learning value learned when the driver's psychological state is in a hurry or sporty in the second in-vehicle state during manual driving may be stored as the first driving characteristic. Then, when updating the setting of the driving characteristic during automatic driving to utilize the manual driving-based characteristics (the first driving characteristic and the second driving characteristic), the first driving characteristic or the second driving characteristic may be applied based on the psychological state of the passengers.

[0049] Fig. 4 is a flowchart showing a second example of the control executed by the ECU 19. Note that the control flow shown in Fig. 4 is repeatedly executed, for example, every several [ms].

[0050] First, the ECU 19 judges whether or not the vehicle is being driven manually (step S21). When the ECU 19 judges that the vehicle is being driven manually (Yes in step S21), it updates the vehicle interior state (step S22). Next, the ECU 19 judges whether or not the vehicle interior state is the driver alone (step S23). When the ECU 19 judges that the vehicle interior state is the driver alone (Yes in step S23), it learns the driver's preferences from the driving data during manual driving, calculates a first driving characteristic so that the degree of steepness and sluggishness is set for each item of the driving characteristic, and stores the calculated first driving characteristic in the storage unit 17 (step S24). After that, the ECU 19 ends a series of controls. On the other hand, in the process of step S23, when the ECU 19 judges that the vehicle interior state is not the driver alone, that is, there are passengers other than the driver (No in step S23), it judges whether or not the passenger's psychological state is hurried or sporty (step S25). When the ECU 19 determines that the passenger's psychological state is "hurry" or "sporty" (Yes in step S25), the ECU 19 learns the driver's preference from the driving data during manual driving, calculates a first driving characteristic so that the degree of steepness and slowness is set for each item of the driving characteristic, and stores the calculated first driving characteristic in the storage unit 17 (step S26). After that, the ECU 19 ends a series of controls. On the other hand, when the ECU 19 determines that the passenger's psychological state is not "hurry" or "sporty" in the process of step S25 (No in step S25), the ECU 19 learns the driver's preference from the driving data during manual driving, calculates a second driving characteristic so that the degree of steepness and slowness is set for each item of the driving characteristic, and stores the calculated second driving characteristic in the storage unit 17 (step S27). After that, the ECU 19 ends a series of controls.

[0051] In addition, in the process of step S21, if the ECU 19 determines that the vehicle is not being driven manually, that is, is being driven automatically (No in step S21), it updates the setting of the driving characteristics during automatic driving (step S28). Next, the ECU 19 determines whether or not to utilize the characteristics based on manual driving, that is, the first driving characteristics or the second driving characteristics (step S29). If the ECU 19 determines that the characteristics based on manual driving are not to be utilized (No in step S29), it applies the driving characteristics for the default automatic driving stored in the storage unit 17 in advance, and ends the series of controls. On the other hand, in the process of step S29, if the ECU 19 determines that the characteristics based on manual driving are to be utilized (Yes in step S29), it updates the psychological state of the occupant or the drive mode (step S30). Next, the ECU 19 determines whether or not the psychological state of the occupant is in a hurry or sporty (step S31). When the ECU 19 determines that the passenger's psychological state is either in a hurry or sporty (Yes in step S31), it applies the first driving characteristic, which is a characteristic based on manual driving (step S32). Then, the ECU 19 ends the series of controls. Also, when the ECU 19 determines in the processing of step S31 that the passenger's psychological state is not in a hurry or sporty (No in step S31), it applies the second driving characteristic, which is a characteristic based on manual driving (step S33). Then, the ECU 19 ends the series of controls.

[0052] As described above, even during manual driving in the second vehicle interior state, if the driver's psychological state is urgent or sporty, ECU 19 does not reflect the learned value of the driving characteristics at that time in the second driving characteristics, but takes the driver's psychological state into account in the learning of the driving characteristics, thereby enabling automatic driving that is more comfortable for the occupants.

[0053] Here, when the ECU 19 calculates the first and second driving characteristics, which are characteristics based on manual driving, so that the ECU 19 learns the driver's preferences from driving data during manual driving and sets the degree of steepness and sluggishness for each of the various items of the driving characteristics, the ECU 19 may set the degree of steepness and sluggishness for each of the various items in the calculated first and second driving characteristics to the closest level among multiple levels that are preset, and store the level in the memory unit 17 as the first and second driving characteristics.

[0054] Fig. 5 is a flowchart showing a third example of the control performed by the ECU 19. The control flow shown in Fig. 5 is repeatedly executed, for example, every several [ms]. Fig. 6 is a diagram showing another example of setting the degree of steepness and gradualness for each item in the first driving characteristic and the second driving characteristic.

[0055] First, the ECU 19 judges whether or not the vehicle is being driven manually (step S41). When the ECU 19 judges that the vehicle is being driven manually (Yes in step S41), the ECU 19 updates the vehicle interior state (step S42). Next, the ECU 19 judges whether or not the vehicle interior state is the driver only (step S43). When the ECU 19 judges that the vehicle interior state is the driver only (Yes in step S43), the ECU 19 calculates the first driving characteristic so that the degree of steepness and sluggishness is set for each of the various items of the driving characteristic (step S44). Next, the ECU 19 sets the degree of steepness and sluggishness for each of the various items in the calculated first driving characteristic to the closest level among the first level, the second level, and the third level, as shown in FIG. 6, and stores the level in the storage unit 17 as the first driving characteristic (step S45). After that, the ECU 19 ends the series of controls. On the other hand, in the process of step S43, when the ECU 19 determines that the vehicle interior state is not the driver only, that is, that there are passengers other than the driver (No in step S43), the ECU 19 learns the driver's preferences from the driving data during manual driving, and calculates the second driving characteristics so that the degree of steepness and sluggishness is set for each item of the driving characteristics (step S46). Next, the ECU 19 sets the degree of steepness and sluggishness for each item in the calculated second driving characteristics to the closest level among the first level, the second level, and the third level, as shown in FIG. 6, and stores it in the storage unit 17 as the second driving characteristics (step S47). After that, the ECU 19 ends the series of controls.

[0056] In addition, in the process of step S41, if the ECU 19 determines that the vehicle is not being driven manually, that is, is being driven automatically (No in step S41), it updates the setting of the driving characteristics during automatic driving (step S48). Next, the ECU 19 determines whether or not to utilize the characteristics based on manual driving, that is, the first driving characteristics or the second driving characteristics (step S49). If the ECU 19 determines that the characteristics based on manual driving are not to be utilized (No in step S49), it applies the driving characteristics for automatic driving that are stored in the storage unit 17 in advance, and ends the series of controls. On the other hand, in the process of step S49, if it determines that the characteristics based on manual driving are to be utilized (Yes in step S49), it updates the passenger's psychological state or the drive mode (step S50). Next, the ECU 19 determines whether or not the passenger's psychological state is in a hurry or sporty (step S51). When the ECU 19 determines that the passenger's psychological state is either in a hurry or sporty (Yes in step S51), it applies the first driving characteristic, which is a characteristic based on manual driving (step S52). Then, the ECU 19 ends the series of controls. Also, when the ECU 19 determines in the processing of step S51 that the passenger's psychological state is not in a hurry or sporty (No in step S51), it applies the second driving characteristic, which is a characteristic based on manual driving (step S53). Then, the ECU 19 ends the series of controls.

[0057] As a result, when learning the driver's preferences from driving data during manual driving in the first in-vehicle state or the second in-vehicle state, even if there is some variation in the degree of steepness and sluggishness for each item of driving characteristics in a similar driving situation, the driving characteristics during autonomous driving are prevented from changing significantly each time the settings of the driving characteristics during autonomous driving are updated, making it possible to implement autonomous driving that is more comfortable for occupants.

[0058] In addition, the vehicle interior state in which the ECU 19 should individually set the characteristics based on the manual driving may differ depending on the seating state of the occupants. Therefore, for example, the vehicle interior state in which only the driver is present may be the first vehicle interior state, the vehicle interior state in which occupants other than the driver are present and seated facing forward may be the second vehicle interior state, the vehicle interior state in which occupants other than the driver are present and seated facing backward may be the third vehicle interior state, and the vehicle interior state in which occupants other than the driver are present and seated standing may be the fourth vehicle interior state. Compared with the driving characteristics learned in the first vehicle interior state, the driving characteristics learned in the second vehicle interior state, the third vehicle interior state, and the fourth vehicle interior state are slow (sluggish) driving characteristics that are considerate of the occupants. In addition, since the directions of the forces acting on the occupants during acceleration and deceleration are opposite in the second vehicle interior state and the third vehicle interior state, the driving characteristics that better reflect the driver's preferences can be set by treating them as different vehicle interior states. It is preferable to exclude the fourth vehicle interior state when it is impossible to board the vehicle in a standing position. As the characteristics based on manual driving, the first driving characteristic, the second driving characteristic, the third driving characteristic, and the fourth driving characteristic, which are obtained by learning the driver's preferences from the driving data during manual driving in the first vehicle interior state, the second vehicle interior state, the third vehicle interior state, and the fourth vehicle interior state, respectively, may be selected based on the vehicle interior state during automatic driving. It is also preferable to correct the characteristics based on the gender, age, and health information of passengers other than the driver. [Explanation of symbols]

[0059] 10 Vehicles 11 Control section 12 Drive unit 13 Imaging unit 14 Sensor Group 15 Batteries 16 Car navigation system 17 Memory section 18 Communications Department 19 ECU 161 GPS Sensor 162 Map Database 163 Notification device 163a Display section 163b Audio output section 164 Input section 171 Program memory section 172 Trained model memory 173 Vehicle information storage unit 191 Acquisition Department 192 Decision Section 193 First Calculation Section 194 Second Calculation Section 195 Output control section 196 Mode setting section 197 Judgment Department

Claims

1. A control device for a vehicle that can switch between automatic driving and manual driving, learns driving characteristics during manual driving, and reflects a learned value of the driving characteristics in control during automatic driving, The learned value of the driving characteristic is linked to a state of a passenger other than the driver during the manual driving, and the driving characteristic, The state of the occupant other than the driver during the manual driving includes at least the presence or absence of the occupant other than the driver, a vehicle interior state in which only the driver is present is defined as a first vehicle interior state, and a vehicle interior state in which passengers other than the driver are present is defined as a second vehicle interior state, and the learned value of the driving characteristic is set so that the driving characteristic in the second vehicle interior state is slower than that in the first vehicle interior state, A vehicle control device characterized in that the degree of steepness and sluggishness for each of various items in a first driving characteristic, which is a learned value of the driving characteristic learned in the first in-vehicle state during manual driving, and a second driving characteristic, which is a learned value of the driving characteristic learned in the second in-vehicle state during manual driving, is set to the closest level among a plurality of preset levels.

2. 2. The vehicle control device according to claim 1, wherein the learned value of the driving characteristic is further linked to a psychological state of the driver.

Images