Vehicle control device, vehicle control computer program, and vehicle control method

Abstract

To provide a vehicle control device that can transfer operation of a vehicle into an operation mode in which degrees of involvement of a driver in operation are much higher, before reliability on a sensor is deteriorated due to rain.SOLUTION: A vehicle control device is provided with: an estimating part 231 that estimates rainfall amounts per unit time, on the basis of a sound signal obtained from a sound sensor mounted on a vehicle 10; a deciding part 232 that decides whether a current operation mode of the vehicle 10 is a first operation mode in which degrees of involvement of a driver in operation are low or a second operation mode in which degrees of the driver in operation are higher than in the first operation mode; and a determining part 233 that when the operation mode of the vehicle 10 is the first operation mode, determines a first time during which the operation mode of the vehicle 10 is transferred from the first operation mode into the second operation mode, on the basis of the rainfall amounts.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The present disclosure relates to a vehicle control device, a computer program for controlling a vehicle, and a vehicle control method. Regarding. [Background technology]

[0002] An automatic control system installed in a vehicle has, for example, an automatic driving mode in which the automatic control system takes the lead in driving the vehicle, and a manual driving mode in which the driver takes the lead in driving the vehicle (see, for example, Patent Document 1).

[0003] In the autonomous driving mode, some or all of the driving operations required for the vehicle to run are performed automatically, so the degree of driver involvement in driving is low. On the other hand, in the manual driving mode, the types of driving operations that are performed automatically are fewer or none than in the autonomous driving mode, so the degree of driver involvement in driving is high.

[0004] In autonomous driving mode, the autonomous control system generates a driving plan for the vehicle while detecting the environment around the vehicle using sensors such as an image sensor or LiDAR sensor mounted on the vehicle. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] JP 2019-167116 A Summary of the Invention [Problem to be solved by the invention]

[0006] When it rains, the reliability of the sensor may gradually decrease due to the adhesion of raindrops, etc. When the reliability of the sensor decreases, the automatic control system determines that the vehicle cannot be driven safely and shifts the driving of the vehicle from the automatic driving mode to the manual driving mode.

[0007] When the driving of the vehicle is shifted from the autonomous driving mode to the manual driving mode, the automatic control system notifies the driver of a control shift request to shift the driving of the vehicle from the autonomous driving mode to the manual driving mode. The driver starts driving the vehicle after performing an approval action to approve the control shift request.

[0008] If the reliability of the sensors decreases due to rain, the automatic control system will transition the vehicle's driving from automatic to manual driving mode, but it will take time for the driver to perform a specified action before the transition is complete.

[0009] Until the transition is completed, the reliability of the sensors is reduced, and during that time, there is a risk that the operation plan generated by the automatic control system will become unstable.

[0010] The present disclosure has an object to provide a vehicle control device that can transition the operation of the vehicle to a driving mode in which the driver is more involved in driving before the reliability of the sensors decreases due to rain. [Means for solving the problem]

[0011] (1) According to one embodiment, a vehicle control device is provided, which includes an estimation unit that estimates a rainfall amount per unit time based on a sound signal acquired from a sound sensor mounted on the vehicle, a determination unit that determines whether a current driving mode of the vehicle is a first driving mode in which the driver is less involved in driving, or a second driving mode in which the driver is more involved in driving than the first driving mode, and a determination unit that determines a first time until the driving mode of the vehicle is shifted from the first driving mode to the second driving mode based on the rainfall amount when the determination unit determines that the driving mode of the vehicle is the first driving mode.

[0012] (2) In the vehicle control device of (1), it is preferable that the determination unit calculates a second time period until the reliability of detecting the environment around the vehicle by another sensor that detects the environment around the vehicle falls below a predetermined standard reliability level based on the amount of rainfall, and determines the first time period so that it is shorter than the second time period.

[0013] (3) In the vehicle control device of (2), it is preferable that the determination unit determines the second time period based on an amount of rainfall and a speed of the vehicle.

[0014] (4) In the vehicle control device of (2), it is preferable that the determination unit determines the second time period based on an amount of rainfall and an orientation of the other sensor.

[0015] (5) In any of the vehicle control devices of (2) to (4), it is preferable that the determination unit determines the first time so that the first time is shorter than the second time by at least the time required for the driver to approve the transition of the vehicle's driving mode from the first driving mode to the second driving mode.

[0016] (6) In any of the vehicle control devices of (1) to (5), it is preferable to have a notification control unit that notifies the driver via the notification unit that the vehicle's driving mode is scheduled to be transitioned from the first driving mode to the second driving mode after the first time has elapsed.

[0017] (7) According to another embodiment, a computer program for controlling a vehicle is provided, which causes a processor to execute a process including estimating a rainfall amount per unit time based on a sound signal acquired from a sound sensor mounted on the vehicle, determining whether the driving mode is a first driving mode in which the driver is less involved in driving, or a second driving mode in which the driver is more involved in driving than the first driving mode, and determining a first time until the driving mode of the vehicle is shifted from the first driving mode to the second driving mode based on the rainfall amount when the driving mode of the vehicle is determined to be the first driving mode.

[0018] (8) According to yet another embodiment, a vehicle control method is provided, which is characterized in that a vehicle control device executes the following: estimating a rainfall amount per unit time based on a sound signal acquired from a sound sensor mounted on the vehicle, determining whether the driving mode is a first driving mode in which the driver is less involved in driving, or a second driving mode in which the driver is more involved in driving than the first driving mode, and determining a first time until the driving mode of the vehicle is shifted from the first driving mode to the second driving mode based on the rainfall amount, when the driving mode of the vehicle is determined to be the first driving mode. Effect of the Invention

[0019] The vehicle control device according to the present disclosure can transition the driving of the vehicle to a driving mode in which the driver is more involved in driving before the reliability of the sensors decreases due to rain. [Brief description of the drawings]

[0020] [Figure 1] 1 is a diagram illustrating an overview of an operation of a vehicle control system having a driving mode control device according to an embodiment of the present invention. [Diagram 2] 1 is a schematic configuration diagram of a vehicle in which a driving mode control device according to an embodiment of the present invention is implemented; [Diagram 3] 4 is an example of an operational flowchart relating to an operation mode control process of the operation mode control device of the present embodiment. [Figure 4] 5 is an example of an operational flowchart relating to a time calculation process of the operation mode control device of the present embodiment. [Diagram 5] 11 is a diagram illustrating an example of a relationship between sensor performance and total rainfall amount. FIG. [Figure 6] 5 is an example of an operational flowchart relating to another operation mode control process of the operation mode control device of the present embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0021] Fig. 1 is a diagram for explaining an outline of the operation of the driving mode control device 12 of this embodiment. Below, an outline of the operation related to the driving mode control process of the driving mode control device 12 disclosed in this specification will be explained with reference to Fig. 1. The driving mode control device 12 is an example of a vehicle control device.

[0022] The vehicle 10 has a user interface (UI) 5, an automatic control device 11, and a driving mode control device 12. The automatic control device 11 controls the operation of the vehicle 10 according to a plurality of driving modes that have different degrees of involvement of the driver 40 in driving. The vehicle 10 may be an automatically driven vehicle.

[0023] For example, the automatic control device 11 has an automatic driving mode (e.g., a driving mode of levels 3 to 5) in which the automatic control device 11 takes the lead in driving the vehicle 10, and a manual driving mode (e.g., a driving mode of levels 0 to 2) in which the driver 40 takes the lead in driving the vehicle 10.

[0024] In the autonomous driving mode, the autonomous control device 11 generates a driving plan for the vehicle 10 while detecting the environment around the vehicle 10 using a sensor such as a forward camera 2 mounted on the vehicle 10.

[0025] When it rains, raindrops may adhere to the front camera 2, which may prevent accurate detection of road features and the like shown in the captured camera image. This reduces the reliability of the front camera 2.

[0026] Therefore, the driving mode control device 12 estimates the amount of rainfall per unit time based on a sound signal acquired from the sound sensor 4 mounted on the vehicle 10. In the example shown in Fig. 1, it is raining outside the vehicle 10. The sound sensor 4 inputs sounds generated by raindrops hitting the outer surface of the vehicle 10, and outputs the sounds to the driving mode control device 12 as a sound signal.

[0027] The driving mode control device 12 determines the driving mode of the vehicle 10 based on the mode information notified from the automatic control device 11. Specifically, the driving mode control device 12 determines whether the driving mode of the vehicle 10 is an automatic driving mode in which the driver 40 is less involved in driving, or a manual driving mode in which the driver 40 is more involved in driving than in the automatic driving mode.

[0028] When the driving mode of the vehicle 10 is the autonomous driving mode, the reliability of the front camera 2 may decrease due to the influence of rain, and the vehicle may not be able to be driven safely.

[0029] Therefore, when the driving mode of the vehicle 10 is the autonomous driving mode, the driving mode control device 12 determines a first time T1 until the driving mode of the vehicle 10 is shifted from the autonomous driving mode to the manual driving mode based on the amount of rainfall. The first time T1 can be determined so as to be shorter than the time between the current time and the time when the reliability of the front camera 2 is reduced due to rain and the vehicle 10 cannot be driven safely.

[0030] After the first time T1 has elapsed, the automatic control device 11 notifies the driver 40 of a control transition request to transition the driving of the vehicle 10 from the automatic driving mode to the manual driving mode via the UI 5. The driver 40 starts driving the vehicle 10 after performing an approval action to approve the control transition request.

[0031] As described above, the driving mode control device 12 can shift the driving of the vehicle 10 to a driving mode in which the driver 40 is more involved in driving before the reliability of the front camera 2 is reduced due to rain. This allows the driver 40 to start driving the vehicle 10 in a driving mode in which the driver 40 is more involved in driving, while the automatic control device 11 is safely driving the vehicle 10, before the reliability of the front camera 2 is reduced.

[0032] 2 is a schematic configuration diagram of a vehicle 10 in which a vehicle control system 1 having a driving mode control device 12 of this embodiment is implemented. The vehicle control system 1 has a forward camera 2, a LiDAR sensor 3, a sound sensor 4, a user interface (UI) 5, an automatic control device 11, a driving mode control device 12, and the like.

[0033] The forward camera 2, the LiDAR sensor 3, the sound sensor 4, the UI 5, the automatic control device 11, and the driving mode control device 12 are communicatively connected via an in-vehicle network 13 that complies with a standard such as a controller area network.

[0034] The front camera 2 is an example of an image sensor provided on the vehicle 10. The front camera 2 is attached to the outer surface of the vehicle 10 so as to face the front of the vehicle 10. The front camera 2 captures a camera image showing the environment of a predetermined area in front of the vehicle 10 at a camera image capture time set at a predetermined cycle, for example. The camera image may show a road included in the predetermined area in front of the vehicle 10 and road features such as lane markings on the road surface. The camera image is an example of environmental information showing the environment around the vehicle 10. The front camera 2 has a two-dimensional detector composed of an array of photoelectric conversion elements sensitive to visible light, such as CCD or C-MOS, and an imaging optical system that forms an image of the area to be captured on the two-dimensional detector. Since the front camera 2 is attached to the outer surface of the vehicle 10, raindrops may adhere to the light receiving portion (for example, a lens, etc.) of the front camera 2.

[0035] Every time the front camera 2 captures a camera image, it outputs the camera image and the time the camera image was captured to the automatic control device 11 and the like via the in-vehicle network 13. The camera image is used by the automatic control device 11 in a process of detecting other objects around the vehicle 10.

[0036] The LiDAR sensor 3 is attached, for example, to the outer surface of the vehicle 10 so as to face the front of the vehicle 10. The LiDAR sensor 3 emits a laser to scan the front of the vehicle 10 at a reflected wave information acquisition time set at a predetermined cycle, and receives a reflected wave reflected by a reflecting object. The time required for the reflected wave to return contains distance information between the vehicle 10 and another object located in the direction of the laser irradiation. The LiDAR sensor 3 outputs reflected wave information including the direction of laser irradiation and the time required for the reflected wave to return, together with the reflected wave information acquisition time when the laser was emitted, to the automatic control device 11 or the like via the in-vehicle network 13. The reflected wave information is used in the automatic control device 11 for processing to detect other objects around the vehicle 10. The reflected wave information is an example of environmental information representing the environment around the vehicle 10. Since the LiDAR sensor 3 is attached to the outer surface of the vehicle 10, raindrops may adhere to the portion of the LiDAR sensor 3 that emits and receives radar.

[0037] The sound sensor 4 inputs sounds around the vehicle 10 and generates a sound signal. The sound sensor 4 outputs the sound signal to the driving mode control device 12 and the like via the in-vehicle network 13. For example, a microphone can be used as the sound sensor 4. It is preferable that the sound sensor 4 is disposed inside the passenger compartment 30 from the viewpoint of protecting the sound sensor 4 from the external environment. In the example shown in FIG. 1, the sound sensor 4 is disposed on the ceiling of the passenger compartment 30. The sound sensor 4 can input sounds such as the sound of raindrops hitting the roof of the passenger compartment 30.

[0038] The UI5 ​​is an example of a notification unit. The UI5 ​​is controlled by the automatic control device 11 or the driving mode control device 12, etc., and notifies the driver 40 of operation information and the like related to the vehicle 10. The operation information related to the vehicle 10 includes driving information of the vehicle 10, a control transition request, etc. The UI5 ​​has a display device 5a such as a liquid crystal display or a touch panel to display the operation information and the like. The UI5 ​​may also have an audio output device (not shown) for notifying the driver 40 of the operation information and the like. The UI5 ​​generates an operation signal according to an operation from the driver 40 to the vehicle 10. Examples of the operation information include a destination position, a waypoint, a vehicle speed, and an approval operation for a control transition request. The UI5 ​​has, for example, a touch panel or an operation button as an input device for inputting operation information from the driver 40 to the vehicle 10. The UI5 ​​outputs the input operation information to the automatic control device 11, the driving mode control device 12, etc. via the in-vehicle network 13.

[0039] The automatic control device 11 controls the operation including the driving of the vehicle 10. The automatic control device 11 has a plurality of driving modes that differ in the degree of involvement of the driver 40 in the driving. The automatic control device 11 controls the operation of the vehicle 10 according to the driving mode.

[0040] The multiple driving modes are roughly divided into automatic driving modes (e.g., driving modes of levels 3 to 5) in which the automatic control device 11 mainly drives the vehicle 10, and manual driving modes (e.g., driving modes of levels 0 to 2) in which the driver 40 mainly drives the vehicle 10. The automatic control device 11 outputs information indicating the current driving mode of the vehicle 10 to the driving mode control device 12 and the like via the in-vehicle network 13. The automatic driving mode is an example of a first driving mode, and the manual driving mode is an example of a second driving mode.

[0041] The multiple driving modes may include a first mode in which some or all of the driving operations required for driving the vehicle 10 are automatically executed, and a second mode in which the types of driving operations executed automatically are fewer than those in the first mode, or none at all.

[0042] In the autonomous driving mode, the automatic control device 11 generates a driving plan for controlling operations such as steering, driving, and braking based on detection information from the forward camera 2 and the LiDAR sensor 3 mounted on the vehicle 10. The automatic control device 11 outputs an automatic control signal based on this driving plan via the in-vehicle network 13 to an actuator (not shown) that controls the steering wheels, a driving device (not shown), or a brake (not shown).

[0043] In addition, in the manual driving mode, the automatic control device 11 generates a manual control signal that controls the operation of the vehicle 10, such as steering, driving, braking, etc., based on the operation of the driver 40, and outputs this manual control signal to an actuator that drives the steering wheels, a drive device, or a brake via the in-vehicle network 13.

[0044] The automatic control device 11 can drive the vehicle 10 in the automatic driving mode in an area where the automatic driving mode is permitted (for example, an area where a high-precision map for controlling the vehicle 10 is prepared).

[0045] When the reliability of the front camera 2 or the LiDAR sensor 3 is degraded, the automatic control device 11 is unable to accurately detect the environment around the vehicle 10 (for example, the road surface, road features, moving objects, etc.). When the reliability of the front camera 2 or the LiDAR sensor 3 is degraded, the automatic control device 11 notifies the driver 40 via the UI 5 of a control transition request requesting that the driving of the vehicle 10 be transitioned from an automatic driving mode to a manual driving mode. The driver 40 starts driving the vehicle 10 after performing an approval action to approve the control transition request.

[0046] For example, raindrops adhering to the light receiving portion (e.g., lens, etc.) of the front camera 2 make the camera image unclear. Furthermore, the presence of raindrops between the front camera 2 and road features, etc. makes the road features, etc. shown in the camera image unclear. When the camera image becomes unclear, it becomes difficult to detect road features, such as lane markings, from the camera image. When road features cannot be detected from the camera image for a predetermined period of time, the automatic control device 11 determines that the reliability of the front camera 2 has decreased.

[0047] Furthermore, in the LiDAR sensor 3, if raindrops adhere to the radar emitting and receiving parts or if the emitted laser is scattered by raindrops, the radar is not received normally, and the distance between the vehicle 10 and other objects cannot be accurately measured. If the inability to accurately measure the distance between the vehicle 10 and other objects continues for a predetermined period of time, the automatic control device 11 determines that the reliability of the LiDAR sensor 3 has decreased.

[0048] When the reliability of the front camera 2 or the LiDAR sensor 3 is reduced, the automatic control device 11 determines that driving of the vehicle 10 in the automatic driving mode is not permitted. In this case, the automatic control device 11 transitions the driving mode of the vehicle 10 from the automatic driving mode to the manual driving mode. In addition, the automatic control device 11 transitions from the automatic driving mode to the manual driving mode or from the manual driving mode to the automatic driving mode in response to a request from the driver 40.

[0049] The driving mode control device 12 executes estimation processing, judgment processing, decision processing, and control processing. To this end, the driving mode control device 12 has a communication interface (IF) 21, a memory 22, and a processor 23. The communication interface 21, the memory 22, and the processor 23 are connected via a signal line 24. The communication interface 21 has an interface circuit for connecting the driving mode control device 12 to the in-vehicle network 13.

[0050] The memory 22 is an example of a storage unit and includes, for example, a volatile semiconductor memory and a non-volatile semiconductor memory. The memory 22 stores computer programs of applications used in the information processing executed by the processor 23 and various data.

[0051] All or part of the functions of the operation mode control device 12 are functional modules realized by, for example, a computer program running on the processor 23. The processor 23 has an estimation unit 231, a judgment unit 232, a decision unit 233, and a control unit 234. Alternatively, the functional modules of the processor 23 may be dedicated arithmetic circuits provided in the processor 23. The processor 23 has one or more central processing units (CPUs) and their peripheral circuits. The processor 23 may further have other arithmetic circuits such as a logic arithmetic unit, a numerical arithmetic unit, or a graphic processing unit. The operation of the operation mode control device 12 will be described later.

[0052] The automatic control device 11 and the driving mode control device 12 are, for example, electronic control units (ECUs). In Fig. 2, the automatic control device 11 and the driving mode control device 12 are described as separate devices, but all or part of these devices may be configured as a single device.

[0053] Fig. 3 is an example of an operation flowchart relating to the operation mode control process of the operation mode control device 12 of this embodiment. The operation mode control process of the operation mode control device 12 will be described below with reference to Fig. 3. The operation mode control device 12 executes the operation mode control process according to the operation flowchart shown in Fig. 3 at an operation mode control time having a predetermined cycle. The cycle for executing the operation mode control process can be, for example, 1 second to 10 seconds.

[0054] First, the estimation unit 231 estimates the amount of rainfall per unit time based on the sound signal acquired from the sound sensor 4 (step S101). The amount of rainfall is expressed, for example, as the depth of rainfall (for example, mm) per unit time (for example, 1 hour). The estimation unit 231 has a classifier that has been trained to output the amount of rainfall per unit time by inputting the sound sensor 4. As the classifier, for example, a deep neural network (DNN) that has been trained in advance to detect the amount of rainfall per unit time from the input sound signal can be used. As training data for this classifier, data in which the amount of rainfall is labeled for the sounds of thunder and raindrops may be used. This allows the amount of rainfall during a thunderstorm to be accurately estimated.

[0055] Next, the determination unit 232 determines whether the current driving mode of the vehicle 10 is an automatic driving mode in which the driver 40 is less involved in driving, or a manual driving mode in which the driver 40 is more involved in driving than the automatic driving mode, based on the information representing the driving mode of the vehicle 10 (step S102). When the information representing the driving mode of the vehicle 10 represents the automatic driving mode, the determination unit 232 determines that the current driving mode of the vehicle 10 is the automatic driving mode. When the information representing the driving mode of the vehicle 10 represents the manual driving mode, the determination unit 232 determines that the current driving mode of the vehicle 10 is the manual driving mode. When the current driving mode of the vehicle 10 is not the automatic driving mode (step S102-No), the series of processes ends.

[0056] If the current driving mode of the vehicle 10 is the autonomous driving mode (step S102-Yes), the decision unit 233 calculates a second time T2 until the reliability of the detection of the environment around the vehicle 10 by the other sensor that detects the environment around the vehicle 10 becomes equal to or lower than a predetermined reference reliability based on the amount of rainfall (step S103). The front camera 2 and the LiDAR sensor 3 are examples of the other sensor that detects the environment around the vehicle 10. The time calculation process in which the decision unit 233 calculates the second time T2 will be described in detail later.

[0057] Next, the decision unit 233 judges whether the second time T2 is equal to or shorter than the reference time (step S104). When the second time T2 is relatively long (for example, 60 minutes), there is a certain amount of time until the reliability of the detection of the environment around the vehicle 10 by other sensors becomes equal to or lower than a predetermined reference reliability, so there is little need to immediately notify the driver 40 of the control transition request. It is preferable to notify the driver 40 of the control transition request when the time from the current time to the reliability decline time becomes shorter to a certain extent. The reference time can be, for example, 5 to 10 minutes. When the second time T2 is not equal to or shorter than the reference time (step S104-No), the series of processes ends. It is preferable that the cycle in which the driving mode control process is executed is shorter than the reference time.

[0058] On the other hand, if the second time T2 is equal to or less than the reference time (step S104-Yes), the determination unit 233 determines the first time T1 based on the second time T2, and ends the series of processes (step S105).

[0059] The determination unit 233 may determine the first time T1 so that it is shorter than the second time T2 by at least the minimum transition time (for example, 4 to 10 seconds) required for the driver 40 to approve the transition of the driving mode of the vehicle 10 from the autonomous driving mode to the manual driving mode. This allows the driver 40 to operate the UI 5 to operate the control transition request and then transition the driving mode of the vehicle 10 from the autonomous driving mode to the manual driving mode before the reliability of the front camera 2 and the LiDAR sensor 3 becomes low.

[0060] Furthermore, the determination unit 233 may determine the first time T1 so that the first time T1 is shorter than the second time T2 by a time obtained by adding a predetermined added time to the minimum transition time. This added time may be a fixed time or may be a time according to the speed of the vehicle 10. For example, the added time may be longer as the speed of the vehicle 10 is faster.

[0061] The control unit 234 may notify the driver 40 via the UI 5 that the driving mode of the vehicle 10 is scheduled to be shifted from the first driving mode to the second driving mode after the first time T1 has elapsed. This allows the driver 40 to know in advance that a control shift request will be notified after the first time T1 has elapsed. The control unit 234 is an example of a notification control unit.

[0062] The decision unit 233 outputs information to the automatic control device 11 via the in-vehicle network 13 requesting that the driving mode of the vehicle 10 be transitioned from an automatic driving mode to a manual driving mode at a first time T1 and after the first time T1 has elapsed from the current time.

[0063] After a first time T1 has elapsed from the current time, the automatic control device 11 notifies the driver 40 of a control transition request to transition the driving mode of the vehicle 10 from the automatic driving mode to the manual driving mode via the UI 5. The driver 40 starts driving the vehicle 10 after performing an approval action to approve the control transition request.

[0064] Next, the time calculation process in which the second time T2 is calculated by the decision unit 233 will be described below with reference to Fig. 4. Fig. 4 is an example of an operational flowchart relating to the time calculation process of the operation mode control device 12 of this embodiment.

[0065] 4, between steps S201 and S204, the processes of steps S202 and S203 are performed for each sensor that detects the environment around the vehicle 10. In this embodiment, the sensors include the front camera 2 and the LiDAR sensor 3.

[0066] First, the decision unit 233 acquires a critical rainfall amount at which the reliability of detecting the environment around the vehicle 10 by the sensor is equal to or lower than a predetermined reference reliability (step S202).

[0067] FIG. 5 is a diagram illustrating an example of the relationship between sensor performance and total rainfall. The vertical axis of FIG. 5 represents the reliability of the sensor performance for detecting the environment around the vehicle 10. The horizontal axis of FIG. 5 represents the total rainfall, which represents the total amount of rain received by the sensor mounted on the vehicle 10. The total rainfall is the amount of rain that the sensor continues to receive during a predetermined time from the current time. It is calculated as follows. Specifically, it is calculated by multiplying the current rainfall amount by the time the sensor continues to receive rain. The sensor performance decreases as the total rainfall amount increases.

[0068] 5 shows a reference reliability of the sensor performance. When the reliability of the sensor performance is higher than the reference reliability, the automatic control device 11 can generate a safe driving plan for the vehicle 10 while detecting the environment around the vehicle 10 using the sensor. The relationship between the sensor performance and the total rainfall amount shown in FIG. 5 is stored in the memory 22 together with the reference reliability for each sensor, for example. The determination unit 233 refers to the relationship shown in FIG. 5 and obtains a limit rainfall amount corresponding to the reference reliability determined for each sensor.

[0069] If the sensor is a forward camera 2, the reliability of the sensor performance may be the reliability indicating that the road feature is output from a classifier when the camera image is input to a classifier trained to detect road features.

[0070] The relationship between the sensor performance and the total rainfall amount shown in Fig. 5 can be obtained by inputting the camera image of the road feature captured by the front camera 2 in the rain to the classifier and examining the relationship between the reliability indicating that the road feature is a road feature and the total rainfall amount. For example, the total rainfall amount at which the reliability indicating that the road feature is a road feature is equal to or less than the reference reliability amount is obtained as the critical rainfall amount.

[0071] Furthermore, when the sensor is the LiDAR sensor 3, the reliability of the sensor performance includes the accuracy of the distance between the vehicle 10 and other objects obtained from the reflected wave information.

[0072] The relationship between the sensor performance and the total amount of rainfall shown in Fig. 5 can be obtained by investigating the relationship between the accuracy of the distance between the vehicle 10 and other objects and the total amount of rainfall based on the reflected wave information reflected from other objects while exposing the LiDAR sensor 3 to rain. For example, the total amount of rainfall at which the accuracy of this distance is equal to or lower than the standard accuracy is obtained as the limit amount of rainfall.

[0073] Next, the determination unit 233 calculates the second time T2 based on the critical rainfall and the rainfall (step S203). The determination unit 233 calculates the second time T2 using the following formula (1).

[0074] T2 = Y / (S × X) (1)

[0075] Here, Y is the limit rainfall amount, S is the area of ​​the detection part exposed to the outside of the sensor, and X is the rainfall amount (estimated in step S101). If the sensor is the front camera 2, S represents the area of ​​the light receiving part (e.g., lens) of the front camera 2. If the sensor is the LiDAR sensor 3, S is the area of ​​the part that emits and receives the radar. The area S is stored in the memory 22.

[0076] After the second time T2 is calculated for each of the sensors, the determination unit 233 selects the smallest second time (step S205) and ends the series of processes. The determination unit 233 selects the smallest time from the second time for the front camera 2 and the second time for the LiDAR sensor 3 as the second time T2.

[0077] In the above-described process, the determination unit 233 may determine the second time T2 based on the amount of rainfall and the speed of the vehicle 10. When the speed of the vehicle 10 is high, the area where the raindrops contact the detection unit of the sensor increases, and therefore, the faster the speed of the vehicle 10, the shorter the second time T2 becomes.

[0078] If the speed of the vehicle 10 is Vv and the falling speed of the raindrops is Vr, the degree A1 of the raindrops adhering to the surface of the sensor is expressed by the following formula (2).

[0079] A1 = Vv / Vr (2)

[0080] Here, the falling speed Vr of the raindrops may be a representative falling speed of the raindrops. The falling speed Vr is stored in the memory 22. The speed Vv of the vehicle 10 is detected by a vehicle speed sensor (not shown). A1 increases as the speed Vv of the vehicle 10 increases.

[0081] In this case, the second time T2 is expressed by the following formula (3).

[0082] T2 = B1 × F1 (A1) × Y / (S × X) (3)

[0083] Here, B1 is a predetermined coefficient. F1(A1) is a function of the correction value A1 and decreases as the correction value A1 increases. For example, F1(A1) may be a function that obtains the inverse of A1.

[0084] Furthermore, when calculating the second time, the determination unit 233 may determine the second time T2 based on the amount of rainfall and the orientation of the detection unit of the sensor. When the sensor is the front camera 2, the orientation of the detection unit of the sensor represents a direction perpendicular to the surface of the light receiving unit of the front camera 2. When the sensor is the LiDAR sensor 3, the orientation of the detection unit of the sensor represents a direction perpendicular to the part that emits and receives the radar.

[0085] The amount of raindrops that adhere to the surface of the sensor varies depending on the orientation of the sensor's detection section. When the sensor's detection section is oriented vertically upward, a large amount of raindrops adhere to the sensor's detection section. On the other hand, when the sensor's detection section is oriented perpendicular to the vertical, a small amount of raindrops adhere to the sensor's detection section.

[0086] Here, if the orientation of the detection portion of the sensor with respect to the upward vertical direction is expressed as θ (0 to 90 degrees), the degree A2 at which raindrops adhere to the surface of the sensor is expressed by the following formula (4).

[0087] A2 = F2(θ) (4)

[0088] Here, F2(θ) is a function of θ and decreases as θ increases. For example, a cosine function may be used as F2(θ).

[0089] In this case, the second time T2 is expressed by the following formula (5): Here, B2 is a predetermined coefficient.

[0090] T2 = B2 × F2 (θ) × Y / (S × X) (5)

[0091] Furthermore, the second time T2 may be determined based on the amount of rainfall, the orientation of the detection portion of the sensor, and the speed of the vehicle 10.

[0092] As described above, the driving mode detection device can shift the driving of the vehicle to a driving mode in which the driver is more involved in driving before the reliability of the sensor for generating a driving plan of the vehicle is reduced due to rain. This allows the driver to start driving the vehicle in a driving mode in which the driver is more involved in driving while the automatic control device is safely driving the vehicle before the reliability of the sensor is reduced.

[0093] In the present disclosure, the vehicle control device, the computer program for controlling a vehicle, and the vehicle control method of the above-mentioned embodiments can be appropriately modified without departing from the spirit of the present disclosure. Furthermore, the technical scope of the present disclosure is not limited to those embodiments, but extends to the inventions described in the claims and their equivalents.

[0094] For example, in the present disclosure, the first time may be determined based on the amount of rainfall without calculating the second time. Fig. 6 is an example of an operational flowchart relating to another operation mode control process of the operation mode control device of the present embodiment.

[0095] In the operational flowchart shown in FIG. 6, the processes in steps S301 and S302 are similar to the processes in steps S101 and S102 described above.

[0096] If the current driving mode of the vehicle 10 is the autonomous driving mode (step S302-Yes), the decision unit calculates the first time T1 based on the transition rainfall amount and the rainfall amount, and ends the series of processes (step S303).

[0097] The determination unit calculates the first time T1 by using the following formula (6).

[0098] T1 = Z / (S × X) (6)

[0099] Here, Z is the transition rainfall amount, S is the area of ​​the detection part exposed to the outside of the sensor, and X is the rainfall amount (estimated in step S301).

[0100] The transitional rainfall amount can be determined using the relationship between the sensor performance and the total rainfall amount shown in Fig. 5. First, the determination unit obtains the critical rainfall amount based on the relationship between the sensor performance and the total rainfall amount shown in Fig. 5. Then, the determination unit determines the transitional rainfall amount that is smaller than the critical rainfall amount based on the critical rainfall amount. For example, the determination unit determines the transitional rainfall amount by multiplying the critical rainfall amount by a predetermined coefficient (a positive real number smaller than 1, for example, 0.8).

[0101] Furthermore, if the amount of rainfall is greater than zero, the decision unit may set the first time to zero and immediately transition the vehicle's driving mode from the first driving mode to the second driving mode. [Explanation of symbols]

[0102] 1 Vehicle Control System 2. Front camera 3 LiDAR Sensor 4 Sound Sensor 5 User Interface 5a Display device 10 Vehicles 11 Automatic control device 12 Operation mode control device 21 Communication Interface 22 Memory 23 Processors 231 Estimation Department 232 Judgment section 233 Decision Section 234 Control Unit 13 In-vehicle network 30 Cabin 40 Drivers

Claims

1. An estimation unit that estimates a rainfall amount per unit time based on a sound signal acquired from a sound sensor mounted on the vehicle; A determination unit that determines whether a current driving mode of the vehicle is a first driving mode in which the driver is less involved in driving, or a second driving mode in which the driver is more involved in driving than the first driving mode; a determination unit that, when the vehicle operation mode is the first operation mode, determines a first time period until the vehicle operation mode is shifted from the first operation mode to the second operation mode based on the amount of rainfall; having The vehicle control device is characterized in that the determination unit calculates a second time until the reliability of detecting the environment around the vehicle by another sensor that detects the environment around the vehicle becomes equal to or lower than a predetermined standard reliability based on the amount of rainfall, and determines the first time so that it is shorter than the second time.

2. The vehicle control device according to claim 1 , wherein the determination unit determines the second time period based on an amount of rainfall and a speed of the vehicle.

3. The vehicle control device according to claim 1 , wherein the determination unit determines the second time period based on the amount of rainfall and an orientation of the other sensor.

4. 2. The vehicle control device according to claim 1, wherein the determination unit determines the first time so that the first time is shorter than the second time by at least a time required for a driver to approve a transition of the vehicle's driving mode from the first driving mode to the second driving mode.

5. The vehicle control device according to any one of claims 1 to 4, further comprising a notification control unit that notifies a driver via a notification unit that the driving mode of the vehicle is scheduled to be transitioned from the first driving mode to the second driving mode after the first time has elapsed.

6. A rainfall amount per unit time is estimated based on a sound signal acquired from a sound sensor mounted on the vehicle; Determine whether the driving mode is a first driving mode in which the driver is less involved in driving, or a second driving mode in which the driver is more involved in driving than the first driving mode; when the driving mode of the vehicle is the first driving mode, determining a first time period until the driving mode of the vehicle is shifted from the first driving mode to the second driving mode based on the amount of rainfall; causing a processor to execute a process including: A computer program for vehicle control, characterized in that a second time until a reliability of detecting the environment around the vehicle by another sensor that detects the environment around the vehicle falls below a predetermined standard reliability based on the amount of rainfall is calculated, and the first time is determined so as to be shorter than the second time.

7. A rainfall amount per unit time is estimated based on a sound signal acquired from a sound sensor mounted on the vehicle; Determine whether the driving mode is a first driving mode in which the driver is less involved in driving, or a second driving mode in which the driver is more involved in driving than the first driving mode; when the driving mode of the vehicle is the first driving mode, determining a first time period until the driving mode of the vehicle is shifted from the first driving mode to the second driving mode based on the amount of rainfall; The vehicle control device executes the above. A vehicle control method comprising: calculating a second time until a reliability of detecting the environment surrounding the vehicle by another sensor that detects the environment surrounding the vehicle falls below a predetermined standard reliability based on the amount of rainfall; and determining the first time so that it is shorter than the second time.

Images