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

Abstract

To provide a vehicle control device capable of preventing a driver from feeling uneasiness even when any of a plurality of maps is used for travel control of a vehicle.SOLUTION: A vehicle control device includes: storage units (8, 22) configured to store a first map representing information on a road and a second map representing information on the road and having lower accuracy of information on the road than the first map; a determination unit 33 for determining whether or not involvement request conditions for requesting a driver of a vehicle 10 to involve in driving of the vehicle 10 are satisfied; and a notification processing unit 34 for notifying the driver of a request to involve in driving via a notification device 7 provided in the vehicle when it is determined that the involvement request conditions are satisfied. The determination unit 33 relaxes the involvement request conditions in a case where the vehicle 10 is subjected to automatic driving control based on the second map more than the involvement request conditions in a case where the vehicle 10 is subjected to the automatic driving control based on the first map.SELECTED DRAWING: Figure 3

Description

[Technical field]

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

[0002] A technology has been proposed for implementing automatic driving control of a vehicle by referring to map information (see Patent Document 1).

[0003] The driving control method disclosed in Patent Document 1 sets a first driving control when traveling along a first route belonging to a first map including driving lane identification information among routes to a destination, and sets a second driving control having a lower level of autonomous driving than the first driving control when traveling along a second route belonging to a second map not including driving lane identification information. This driving control method then creates a driving plan for causing a vehicle to travel along the first or second route with the set driving control content. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] International Publication No. 2018 / 189843 Summary of the Invention [Problem to be solved by the invention]

[0005] If the road information displayed on the map used for automatic driving control of the vehicle is not accurate enough, the vehicle's behavior may become unstable, such as going out of the lane it is traveling in. As a result, the driver may feel uneasy.

[0006] Therefore, an object of the present invention is to provide a vehicle control device that can suppress the driver's anxiety regardless of the map used for vehicle driving control. [Means for solving the problem]

[0007] According to one embodiment, a vehicle control device is provided. The vehicle control device includes a storage unit that stores a first map that represents information about roads and a second map that represents information about roads and has lower accuracy of information about roads than the first map, a determination unit that determines whether or not an involvement request condition that requests the driver of the vehicle to participate in driving the vehicle is satisfied based on an outside sensor signal generated by an outside sensor that detects the situation around the vehicle, an inside sensor signal generated by an inside sensor that detects the situation inside the vehicle, a vehicle behavior signal generated by a behavior sensor that detects the behavior of the vehicle, or the position of the vehicle when the vehicle is under automatic driving control, and a notification processing unit that notifies the driver of the request for participation in driving via a notification device provided in the vehicle when it is determined that the involvement request condition is satisfied. The determination unit relaxes the involvement request condition when the vehicle is under automatic driving control based on the second map compared to the involvement request condition when the vehicle is under automatic driving control based on the first map.

[0008] In this vehicle control device, the judgment unit measures the lateral distance between the vehicle and a lane marking that defines the lane in which the vehicle is traveling based on an external sensor signal, and judges that the involvement request condition is satisfied when the lateral distance becomes less than a predetermined distance threshold, and preferably sets the distance threshold when the vehicle is under autonomous driving control based on the second map to be larger than the distance threshold when the vehicle is under autonomous driving control based on the first map.

[0009] In this case, it is preferable that the determination unit increases the distance threshold the greater the degree of discrepancy between information regarding roads represented on the first map and information regarding roads represented on the second map in the section where the vehicle is under automatic driving control based on the second map.

[0010] In addition, it is preferable that the determination unit determines that the engagement request condition is satisfied when the vehicle speed represented by the vehicle behavior signal is faster than the speed limit of the road on which the vehicle is traveling by a predetermined speed threshold or more, and sets the speed threshold when the vehicle is under autonomous driving control based on the second map to a lower value than the speed threshold when the vehicle is under autonomous driving control based on the first map.

[0011] Furthermore, it is preferable that the judgment unit determines that the engagement request condition is satisfied when the speed limit of the road on which the vehicle is traveling is less than a predetermined speed, and sets the predetermined speed when the vehicle is under automatic driving control based on the second map to a higher value than the predetermined speed when the vehicle is under automatic driving control based on the first map.

[0012] Furthermore, it is preferable that the judgment unit judges that the involvement request condition is satisfied when the radius of curvature of a curve located while the vehicle is traveling or within a section up to a predetermined distance away is less than a predetermined curvature radius threshold, and sets the curvature radius threshold when the vehicle is under autonomous driving control based on the second map to a value greater than the curvature radius threshold when the vehicle is under autonomous driving control based on the first map.

[0013] Furthermore, it is preferable that the determination unit determines that the involvement request condition is satisfied when the gradient of the road while the vehicle is traveling or within a section up to a predetermined distance away is equal to or greater than a predetermined gradient threshold, and sets the gradient threshold when the vehicle is under automatic driving control based on the second map to a smaller value than the gradient threshold when the vehicle is under automatic driving control based on the first map.

[0014] According to another embodiment, a vehicle control method is provided. The vehicle control method includes, when the vehicle is under automatic driving control, judging whether or not an involvement request condition that requests the driver of the vehicle to participate in driving of the vehicle is satisfied based on an external sensor signal generated by an external sensor that detects the situation around the vehicle, an internal sensor signal generated by an internal sensor that detects the situation inside the vehicle, a vehicle behavior signal generated by a vehicle behavior sensor that detects the behavior of the vehicle, or a position of the vehicle, and notifying the driver of the request for participation in driving via a notification device provided in the vehicle when it is determined that the involvement request condition is satisfied. The determination of whether or not the involvement request condition is satisfied includes relaxing the involvement request condition when the vehicle is under automatic driving control based on a second map that represents information about roads and has lower accuracy of information about roads than the involvement request condition when the vehicle is under automatic driving control based on a first map that represents information about roads.

[0015] According to yet another embodiment, a computer program for controlling a vehicle is provided. The computer program for controlling a vehicle includes instructions for causing a processor mounted on the vehicle to execute the following when the vehicle is under automatic driving control: determining whether or not an involvement request condition for requesting the driver of the vehicle to participate in driving the vehicle is satisfied based on an external sensor signal generated by an external sensor that detects the situation around the vehicle, an internal sensor signal generated by an internal sensor that detects the situation inside the vehicle, a vehicle behavior signal generated by a vehicle behavior sensor that detects the behavior of the vehicle, or the position of the vehicle; and notifying the driver of the request for participation in driving via a notification device provided in the vehicle when it is determined that the involvement request condition is satisfied. The determination of whether or not the involvement request condition is satisfied includes relaxing the involvement request condition when the vehicle is under automatic driving control based on a second map that represents information about roads and has lower accuracy of information about roads than the involvement request condition when the vehicle is under automatic driving control based on a first map that represents information about roads. Effect of the Invention

[0016] The vehicle control device according to the present invention has an effect of suppressing the driver's anxiety, regardless of the map used for vehicle driving control. [Brief description of the drawings]

[0017] [Figure 1] 1 is a schematic configuration diagram of a vehicle control system in which a vehicle control device is implemented. [Diagram 2] 1 is a hardware configuration diagram of an electronic control device that is an embodiment of a vehicle control device. [Diagram 3] FIG. 2 is a functional block diagram of a processor of an electronic control unit related to vehicle control processing. [Figure 4] A figure showing an example of a hands-on request threshold when a first map is used for driving control and a hands-on request threshold when a second map is used for driving control. [Diagram 5] FIG. 11 is a diagram showing an example of a driving change request threshold when a first map is used for driving control and a driving change request threshold when a second map is used for driving control. [Figure 6] 4 is an operation flowchart of a vehicle control process. [Figure 7] 13A and 13B are diagrams showing examples of adjustment of the hands-on request threshold according to a modified example. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0018] Hereinafter, a vehicle control device, a vehicle control method executed on the vehicle control device, and a computer program for vehicle control will be described with reference to the drawings. The vehicle control device performs automatic driving control of the vehicle's travel using either a first map showing information about roads or a second map showing information about roads and having lower accuracy of information about roads than the first map. More specifically, the vehicle control device determines whether or not an involvement request condition that requests the driver of the vehicle to participate in the driving of the vehicle is satisfied, and when it is determined that the involvement request condition is satisfied, notifies the driver of the request for participation in the driving via a notification device provided in the vehicle cabin. The vehicle control device relaxes the involvement request condition when the vehicle is automatically driven based on the second map compared to the involvement request condition when the vehicle is automatically driven based on the first map.

[0019] In this embodiment, each of the two maps includes information about roads that is used for vehicle driving control, such as road markings such as lane markings, information representing the types of features such as curbs, road signs, and signs along the road, and information representing the positions of these features.

[0020] In addition, it is preferable that the first map, which has higher accuracy of information on roads shown on the two maps, is set as the map to be used as the standard map. This makes it possible to more appropriately control the running of the vehicle. Note that the smaller the error in the position of the road or the features around the road shown on the map, or the more certain the type and presence of the feature, the higher the accuracy of the information on the road shown on the map. Therefore, for a road section that has not changed since the first map and the second map were last updated, the accuracy of the position of the feature in the road section and the certainty of the type and presence of the feature are higher in the first map than in the second map. Furthermore, in this embodiment, the timing of the map update refers to the timing when the information on the roads shown on the map is updated. For example, when a map server that manages the map or distributes the map to the vehicle updates the information on a specific road section of the first map to a first date and time, the first date and time becomes the timing of the update.

[0021] On the other hand, it is preferable that the second map is updated more frequently than the first map. As a result, even if the first map does not show accurate information about a specific road section because some construction work was carried out on the specific road section after the first map was last updated, the second map may have been last updated after the construction work was carried out on the specific road section. Therefore, the second map may show accurate information about the specific road section. Therefore, the vehicle control device can appropriately control the traveling of the vehicle by selectively using the first and second maps depending on the situation.

[0022] However, when the second map is used for driving control, the vehicle's driving behavior is more likely to become unstable than when the first map is used for driving control. For example, when the second map is used for driving control, the vehicle is more likely to deviate from the lane in which it is traveling or to get too close to the lane markings that divide the lane. Therefore, the vehicle control device relaxes the involvement request condition when the vehicle is under automatic driving control based on the second map, so that the driver can be requested to participate in driving before the vehicle's driving behavior becomes unstable.

[0023] FIG. 1 is a schematic diagram of a vehicle control system in which a vehicle control device is implemented. FIG. 2 is a hardware configuration diagram of an electronic control device, which is an embodiment of a vehicle control device. In this embodiment, a vehicle control system 1 that is mounted on a vehicle 10 and controls the vehicle 10 includes a camera 2, a driver monitor camera 3, a GPS receiver 4, a behavior sensor 5, a wireless communication terminal 6, a notification device 7, a storage device 8, and an electronic control unit (ECU) 9, which is an example of a vehicle control device. The camera 2, the driver monitor camera 3, the GPS receiver 4, the wireless communication terminal 6, the notification device 7, the storage device 8, and the ECU 9 are communicatively connected via an in-vehicle network that complies with a standard such as a controller area network. Furthermore, the behavior sensor 5 is also communicatively connected to the ECU 9. The vehicle control system 1 may further include a distance measurement sensor (not shown) such as a LiDAR or a radar that measures the distance from the vehicle 10 to an object present around the vehicle 10. The vehicle control system 1 may further include a navigation device (not shown) for searching a route to a destination.

[0024] The camera 2 is an example of an outside-vehicle sensor, and includes a two-dimensional detector configured with an array of photoelectric conversion elements, such as a CCD or C-MOS, that are sensitive to visible light, and an imaging optical system that forms an image of the area to be photographed on the two-dimensional detector. The camera 2 is attached, for example, inside the cabin of the vehicle 10 so as to face the front of the vehicle 10. The camera 2 photographs the area in front of the vehicle 10 at a predetermined photographing period (for example, 1 / 30 to 1 / 10 seconds) and generates an image showing the area in front of the vehicle 10. The image obtained by the camera 2 is an example of an outside-vehicle sensor signal that indicates the situation around the vehicle 10. Note that the vehicle 10 may be provided with a plurality of cameras with different photographing directions or focal lengths.

[0025] Every time the camera 2 generates an image, the camera 2 outputs the generated image to the ECU 9 via the in-vehicle network.

[0026] The driver monitor camera 3 is an example of an in-vehicle sensor, and like the camera 2, has a two-dimensional detector composed of an array of photoelectric conversion elements, such as CCD or C-MOS, sensitive to visible light or infrared light, and an imaging optical system that forms an image of the area to be photographed on the two-dimensional detector. The driver monitor camera 3 may further have a light source, such as an infrared LED, for illuminating the driver. The driver monitor camera 3 is attached, for example, on the instrument panel or in its vicinity, facing the driver so that the head of the driver seated on the driver's seat of the vehicle 10 is included in the area to be photographed, that is, so that the driver's head can be photographed. The driver monitor camera 3 photographs the driver at a predetermined photographing period (for example, 1 / 30 to 1 / 10 seconds) and generates an image in which the driver is photographed (hereinafter referred to as a driver image). The driver image obtained by the driver monitor camera 3 is an example of an in-vehicle sensor signal that represents the situation inside the cabin of the vehicle 10, and may be a color image or a gray image. Every time the driver monitor camera 3 generates a driver image, it outputs the generated driver image to the ECU 9 via the in-vehicle network.

[0027] The GPS receiver 4 receives GPS signals from GPS satellites at predetermined intervals and determines the own position of the vehicle 10 based on the received GPS signals. Then, the GPS receiver 4 outputs positioning information representing the positioning result of the own position of the vehicle 10 based on the GPS signals to the ECU 9 via the in-vehicle network at predetermined intervals. Note that the vehicle 10 may have a receiver that receives positioning signals from satellites of other satellite positioning systems and determines the own position of the vehicle 10, instead of the GPS receiver.

[0028] The behavior sensor 5 is a sensor for detecting the behavior of the vehicle 10, and may be, for example, an acceleration sensor, a speed sensor, or a gyro sensor. The vehicle control system 1 may have a plurality of different types of behavior sensors 5. The behavior sensor 5 outputs the generated sensor signal to the ECU 9 every time it generates a sensor signal representing the behavior of the vehicle 10. The sensor signal generated by the behavior sensor 5 (for example, a signal representing acceleration / deceleration generated by an acceleration sensor, or a signal representing speed generated by a speed sensor) is an example of a vehicle behavior signal representing the behavior of the vehicle 10.

[0029] The wireless communication terminal 6 wirelessly communicates with a wireless base station in accordance with a predetermined mobile communication standard. The wireless communication terminal 6 receives map information representing the first map or the second map, or update information of the first map or the second map, from the map server via the wireless base station. The wireless communication terminal 6 then outputs the received map information or update information to the storage device 8 via the in-vehicle network.

[0030] The notification device 7 is provided in the vehicle cabin of the vehicle 10, and is a device that provides a predetermined notification to the driver by light, sound, vibration, character display, or image display. For this purpose, the notification device 7 has at least one of a speaker, a light source, a vibrator, or a display device. When the notification device 7 receives a notification signal indicating a predetermined notification to the driver (for example, a hands-on request or a driving change request) from the ECU 9, the notification device 7 executes the notification to the driver by sound from the speaker, light emission or blinking of the light source, vibration of the vibrator, or display of a message on the display device. When the notification device 7 has two or more types of devices, the notification may be given to the driver via each of the two or more types of devices.

[0031] The storage device 8 is an example of a storage unit, and includes, for example, a hard disk device, a non-volatile semiconductor memory, or an optical recording medium and an access device therefor. The storage device 8 stores the first map and the second map, and update information indicating the date and time when information on each road section shown on the first map and the second map was last updated. Furthermore, the first map and the second map may each include information indicating the accuracy of information on roads (for example, the average error of the positions of features shown on the maps).

[0032] Furthermore, the storage device 8 has a processor for executing an update process of the first map or the second map, and a process related to a map read request from the ECU 9. For example, the storage device 8 transmits a request to acquire the first map and the second map together with the current position of the vehicle 10 to the map server via the wireless communication terminal 6 every time the vehicle 10 moves a predetermined distance. The storage device 8 receives map information including the first map and the second map for a predetermined area around the current position of the vehicle 10 from the map server via the wireless communication terminal 6, and stores the first map and the second map included in the received map information. When the storage device 8 receives update information of the first map or the second map via the wireless communication terminal 6, the storage device 8 stores the update information. When the storage device 8 receives a map read request from the ECU 9, the storage device 8 extracts an area that includes the current position of the vehicle 10 and is relatively narrower than the above-mentioned predetermined area from the stored first map and second map, and outputs the area to the ECU 9 via the in-vehicle network.

[0033] The ECU 9 controls the automatic driving of the vehicle 10 based on the first map or the second map. Furthermore, while executing the automatic driving control of the vehicle 10, the ECU 9 determines whether or not an involvement request condition that requests the driver to be involved in the driving of the vehicle is satisfied, and requests the driver to be involved in the driving via the notification device 7 when the involvement request condition is satisfied.

[0034] The request to be involved in driving includes a request to hold the steering wheel (hands-on request) and a request to transfer control to the driver (driving handover request).

[0035] 2, the ECU 9 has a communication interface 21, a memory 22, and a processor 23. The communication interface 21, the memory 22, and the processor 23 may each be configured as a separate circuit, or may be configured integrally as a single integrated circuit.

[0036] The communication interface 21 has an interface circuit for connecting the ECU 9 to other devices. The communication interface 21 passes the received image to the processor 23 every time it receives an image from the camera 2. The communication interface 21 passes the received driver image to the processor 23 every time it receives a driver image from the driver monitor camera 3. The communication interface 21 passes the positioning information to the processor 23 every time it receives positioning information from the GPS receiver 4. The communication interface 21 passes the sensor signal to the processor 23 every time it receives a sensor signal from the behavior sensor 5. The communication interface 21 passes the first and second maps and update information read from the storage device 8 to the processor 23. The communication interface 21 outputs a notification signal received from the processor 23 to the notification device 7.

[0037] The memory 22 is another example of a storage unit, and includes, for example, a volatile semiconductor memory and a non-volatile semiconductor memory. The memory 22 stores various data used in the vehicle control process executed by the processor 23. For example, the memory 22 stores an image of the surroundings of the vehicle 10 received from the camera 2, a driver image received from the driver monitor camera 3, positioning information of the vehicle 10 received from the GPS receiver 4, measured values ​​representing the behavior of the vehicle 10 represented by a sensor signal received from the behavior sensor 5, and the first and second maps and update information read from the storage device 8. Furthermore, the memory 22 stores parameters such as the focal length, shooting direction, and mounting position of the camera 2, and various parameters for identifying a classifier for object detection used to detect features and the like. Furthermore, the memory 22 temporarily stores various data generated during the vehicle control process.

[0038] 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 processor 23 executes vehicle control processing for the vehicle 10 at predetermined intervals.

[0039] 3 is a functional block diagram of the processor 23 related to vehicle control processing. The processor 23 has a switching point detection unit 31, a control unit 32, a determination unit 33, and a notification processing unit 34. Each of these units in the processor 23 is, for example, a functional module realized by a computer program running on the processor 23. Alternatively, each of these units in the processor 23 may be a dedicated arithmetic circuit provided in the processor 23.

[0040] The switching point detection unit 31 detects a switching point where the map used for driving control of the vehicle 10 is switched from one of the first and second maps to the other in a section from the current position of the vehicle 10 to a predetermined distance away in the traveling direction of the vehicle 10.

[0041] For this purpose, the switching point detection unit 31 sets the position of the vehicle 10 indicated by the latest positioning information as the current position of the vehicle 10. The switching point detection unit 31 also specifies the traveling direction of the vehicle 10 based on a change in the position of the vehicle 10 indicated by the most recent multiple pieces of positioning information, or based on a sensor signal indicating the orientation of the vehicle 10 received by the ECU 9 from an orientation sensor (not shown) mounted on the vehicle 10. Furthermore, the switching point detection unit 31 refers to the map currently being used to control the traveling of the vehicle 10 out of the first map and the second map, and specifies a road including the current position of the vehicle 10 as the road on which the vehicle 10 is traveling.

[0042] The switching point detection unit 31 compares the timings of the last updates of the first map and the second map for a section of the road on which the vehicle 10 is traveling, which is a predetermined distance from the current position of the vehicle 10, by referring to the update information. Then, it determines whether or not there is a section of the first map and the second map in which the update timing of the map used for the travel control of the vehicle 10 at the current position of the vehicle 10 is later than the update timing of the other map. If there is such a section, the switching point detection unit 31 detects the start point, which is the end point of the section closer to the vehicle 10, as the switching point.

[0043] Alternatively, the switching point detection unit 31 determines whether or not there is an unsupported section on the road on which the vehicle 10 is traveling, within a section from the current position of the vehicle 10 to a predetermined distance ahead, that is not shown on one of the first and second maps, which is used for driving control of the vehicle 10 at the current position of the vehicle 10. Furthermore, if the unsupported section is shown on the other map, the switching point detection unit 31 detects the start point, which is the end point of the unsupported section closer to the vehicle 10, as the switching point.

[0044] Alternatively, the switching point detection unit 31 determines whether or not there is a deviation section in which the information shown on the first map and the information shown on the second map diverge within a section from the current position of the vehicle 10 to a predetermined distance ahead. If there is a deviation section, the switching point detection unit 31 may detect, as a switching point, each of a start point, which is an end point of the deviation section closer to the vehicle 10, and an end point, which is an end point farther from the vehicle 10. However, if the map having a shorter elapsed time from the timing when the information on the deviation section was updated and the map having a shorter elapsed time from the timing when the information on the sections before and after the deviation section was updated are the same among the first map and the second map, the switching point detection unit 31 may not set the end point of the deviation section as the switching point. This is because, in both the deviation section and the sections before and after the deviation section, the map having a shorter elapsed time from the timing when the information was updated is more likely to represent more accurate information than the other map.

[0045] In order to detect the deviation section, the switching point detection unit 31 sets sampling points at first intervals (e.g., several hundreds of meters to 1 km) in a section from the current position of the vehicle 10 to a predetermined distance ahead along the traveling direction of the vehicle 10. Then, for each sampling point, the switching point detection unit 31 calculates the distance between the position of the road on which the vehicle 10 is traveling or the surrounding features (e.g., lane markings, curbs, guard rails, or road signs) shown on the first map at that sampling point, and the position of the corresponding feature shown on the second map as the deviation. Note that, when features that are continuous along the road, such as the lane markings in the above example, are used to calculate the deviation, the switching point detection unit 31 may calculate the distance from the position of the feature shown on the first map at the sampling point of interest to the closest position of the corresponding feature shown on the second map as the deviation. In addition, the switching point detection unit 31 may calculate the deviation as the average value of the distance between each position of a plurality of features shown on the first map at the sampling point of interest and the position of the corresponding feature shown on the second map.

[0046] The switching point detection unit 31 compares the deviation calculated for each sampling point with a predetermined threshold. Then, the switching point detection unit 31 identifies a sampling point where the deviation is equal to or greater than the predetermined threshold. The switching point detection unit 31 resets sampling points at second intervals (for example, several tens of meters to 100 meters) narrower than the first intervals before and after the sampling point where the deviation is equal to or greater than the predetermined threshold. Then, the switching point detection unit 31 calculates the deviation between the first map and the second map for each reset sampling point in the same manner as described above. The switching point detection unit 31 identifies a sampling point where the deviation is equal to or greater than the predetermined threshold among the reset sampling points. The switching point detection unit 31 detects, as a deviation section, a section from a sampling point one before the sampling point closest to the vehicle 10 among the sampling points where the deviation degree is equal to or greater than the predetermined threshold to a sampling point one after the sampling point farthest from the vehicle 10 among the sampling points where the deviation degree is equal to or greater than the predetermined threshold.

[0047] The switching point detection unit 31 may set a deviation degree equal to or greater than a predetermined threshold value for sampling points where the number of lanes or the number of lane markings differ between the first map and the second map. The switching point detection unit 31 may also set a deviation degree equal to or greater than a predetermined threshold value for sampling points where the type of lane markings differ between the first map and the second map. Furthermore, the switching point detection unit 31 may set a point where the presence or absence of a predetermined feature, such as a road sign or a guardrail, differs between the first map and the second map as a sampling point having a deviation degree equal to or greater than a predetermined threshold value.

[0048] The switching point detection unit 31 notifies the control unit 32 of the detected switching point.

[0049] The control unit 32 controls the traveling of the vehicle 10 by referring to the map used for controlling the traveling of the vehicle 10, out of the first and second maps. In this embodiment, until the vehicle 10 reaches the switching point, the map used up to that point, out of the first and second maps, is used for the traveling control. On the other hand, when the vehicle passes the switching point, the control unit 32 uses the map different from the map used up to that point, out of the first and second maps, for the traveling control. More specifically, when the switching point is set due to the difference between the last update timing of the first map and the last update timing of the second map, the control unit 32 uses the map with the later update timing, out of the first and second maps, for the section before the switching point and the section after the switching point, respectively. In addition, when the switching point is set due to the presence or absence of an unsupported section, the control unit 32 uses the map, out of the first and second maps, in which information of the section is displayed, for the traveling control, out of the first and second maps, for the section before the switching point and the section after the switching point, respectively. Furthermore, when a switching point is set depending on the presence or absence of a deviation section, the control unit 32 uses, for driving control, the first map, which has more accurate road-related information, out of the first map and the second map, for sections other than the deviation section, and for driving control, for the deviation section, the control unit 32 uses, for driving control, the second map or the map which has been updated less time ago.

[0050] For example, the control unit 32 controls each part of the vehicle 10 so that the vehicle 10 continues traveling in the own lane. In this case, the control unit 32 creates a planned traveling route that passes through the own lane by referring to a map used for the traveling control. For example, the control unit 32 creates a planned traveling route that passes through the center between two lane markings that divide the own lane, which are shown on the map. Then, the control unit 32 controls each part of the vehicle 10 so that the vehicle 10 travels along the planned traveling route.

[0051] For this purpose, the control unit 32 detects the position of the vehicle 10 at every predetermined period, and compares the detected position of the vehicle 10 with the planned travel route. In order to detect the exact position of the vehicle 10, the control unit 32 compares the image generated by the camera 2 with a map used for travel control. For example, the control unit 32 assumes the position and attitude of the vehicle 10 and projects the features on or around the road detected from the image onto the map, or projects the features on or around the road around the vehicle 10 shown on the map onto the image. The features on or around the road can be, for example, road markings such as lane markings or stop lines, or curbs. The control unit 32 then detects the position and attitude of the vehicle 10 when the features detected from the image and the features shown on the map most closely match as the exact position of the vehicle 10. Furthermore, the control unit 32 detects the lane including the vehicle's own position on the map as the vehicle's own lane. Furthermore, the control unit 32 determines that the lane markings detected in the areas on the image corresponding to the left and right sides of the vehicle 10 and closest to the vehicle 10 are the lane markings that divide the vehicle's own lane.

[0052] The control unit 32 may determine the position where the feature is projected on the map or image using the assumed initial values ​​of the position and attitude of the vehicle 10 and the parameters of the camera 2, such as the focal length, the installation height, and the shooting direction. As the initial values ​​of the position and attitude of the vehicle 10, the latest position of the vehicle 10 measured by the GPS receiver 4, or the position and attitude of the vehicle 10 estimated at the time of the previous self-position detection, corrected using the odometry information, is used. Then, the control unit 32 calculates the degree of match between the feature on or around the road detected from the image and the corresponding feature shown on the map (for example, the inverse of the square sum of the distance between the corresponding features).

[0053] The control unit 32 repeats the above process while changing the assumed position and attitude of the vehicle 10. Then, the control unit 32 detects the assumed position and attitude when the degree of match is maximized as the accurate position of the vehicle 10.

[0054] The control unit 32 may detect the feature by inputting the image to a classifier that has been trained in advance to detect the feature to be detected from the image. The control unit 32 may use a deep neural network (DNN) having a convolutional neural network (CNN) type architecture, such as Single Shot MultiBox Detector or Faster R-CNN, as such a classifier. Alternatively, the control unit 32 may use a DNN having a self attention network (SAN) type architecture, such as Vision Transformer, as such a classifier. Alternatively, the control unit 32 may use a classifier based on another machine learning method, such as an AdaBoost classifier, as such a classifier. Such a classifier is trained in advance according to a predetermined learning method, such as backpropagation, using a large number of teacher images in which the feature is depicted, so as to detect the feature to be detected from the image.

[0055] The control unit 32 may measure the position of the vehicle 10 without using a map. In particular, when the second map, which has lower accuracy of information about roads, is used for driving control, the control unit 32 estimates the position of the vehicle 10 without using a map, thereby suppressing a decrease in the estimation accuracy of the position of the vehicle 10. In this case, the control unit 32 detects the left and right lane markings that divide the vehicle's own lane shown in the image by inputting the image obtained by the camera 2 to a classifier. Then, the control unit 32 estimates the positions of the lane markings corresponding to the reference positions on the image, based on the camera 2, for each of the left and right lane markings, based on the reference positions in the horizontal direction of the pixels showing the left and right lane markings at the position closest to the bottom of the image, and parameters such as the focal length, shooting direction, and installation height of the camera 2. Furthermore, the control unit 32 measures the lateral position of the vehicle 10 within the own lane by determining the distance from the camera 2 to each of the left and right lane markings based on the estimation result, the extension direction of the lane markings, and the shooting direction of the camera 2.

[0056] If the measured position of vehicle 10 is on the planned travel route, control unit 32 determines the steering angle of vehicle 10 so that vehicle 10 moves along the planned travel route, and controls the steering of vehicle 10 to achieve the determined steering angle. Also, if the measured position of vehicle 10 is away from the planned travel route, control unit 32 determines the steering angle of vehicle 10 so that vehicle 10 approaches the planned travel route, and controls the steering of vehicle 10 to achieve the determined steering angle.

[0057] Furthermore, the control unit 32 refers to the current position of the vehicle 10 and a map used for driving control, sets the speed limit of the road on which the vehicle 10 is traveling as the target vehicle speed, and controls each part of the vehicle 10 so that the speed of the vehicle 10 approaches the set target vehicle speed. The control unit 32 also controls the acceleration / deceleration of the vehicle 10 so that the inter-vehicle distance between the vehicle 10 and a preceding vehicle traveling in front of the vehicle 10 in the own lane is maintained at a certain distance or more. To this end, the control unit 32 detects other vehicles traveling around the vehicle 10 by inputting an image obtained by the camera 2 to a classifier that has been trained in advance to detect other vehicles. As such a classifier, the control unit 32 can use a classifier similar to the classifier used to detect features. Alternatively, the classifier used to detect features may be trained in advance to detect other vehicles as well. In this case, the control unit 32 can detect not only features but also other vehicles by inputting an image to the classifier used to detect features. The control unit 32 may determine, among the other detected vehicles, a vehicle whose bottom end is located within an area between two lane markings that divide the vehicle's own lane on the image as a preceding vehicle. Furthermore, the control unit 32 may estimate the distance between the vehicle 10 and the preceding vehicle based on the position of the bottom end of the object area in which the preceding vehicle is represented on the image and parameters such as the shooting direction, focal length, and installation height of the camera 2. If the estimated distance to the preceding vehicle is less than a certain distance, the control unit 32 sets the acceleration / deceleration of the vehicle 10 so as to decelerate the vehicle 10. On the other hand, if the estimated distance to the preceding vehicle is equal to or greater than the certain distance, the control unit 32 sets the acceleration / deceleration of the vehicle 10 so that the speed of the vehicle 10 approaches the target speed.

[0058] When the acceleration / deceleration is set as described above, the control unit 32 sets the accelerator opening or the braking amount according to the set acceleration / deceleration. The control unit 32 calculates the fuel injection amount according to the set accelerator opening, and outputs a control signal corresponding to the fuel injection amount to a fuel injection device of the engine of the vehicle 10. Alternatively, the control unit 32 calculates the amount of power supplied to the motor according to the set accelerator opening, and controls a drive circuit of the motor so that the amount of power is supplied to the motor. Alternatively, the control unit 32 outputs a control signal corresponding to the set braking amount to the brake of the vehicle 10.

[0059] In addition, the control unit 32 may stop the automatic driving control or stop the vehicle 10 if the driver does not participate as requested even after a predetermined period has elapsed since the driver was notified of a request to participate in driving. For example, if the ECU 9 does not receive a signal indicating that the steering wheel has been held from a touch sensor (not shown) provided on the steering wheel even after a predetermined period has elapsed since the hands-on request was notified, the control unit 32 may stop the automatic driving control and transfer driving control to the driver. In addition, if the ECU 9 does not receive a signal indicating that the steering wheel has been held from a touch sensor provided on the steering wheel or a signal indicating that the steering wheel, accelerator, or brake has been operated even after a predetermined period has elapsed since the driver change request was notified, the control unit 32 may stop the vehicle 10.

[0060] The determination unit 33 determines whether or not the involvement request condition is satisfied. In this embodiment, the determination unit 33 compares the distance from the vehicle 10 to each of the left and right lane markings that divide the vehicle's lane (hereinafter referred to as the lateral distance) with the hands-on request threshold. If either of the left and right lateral distances is less than the hands-on request threshold, the determination unit 33 determines that the involvement request condition is satisfied. If the determination unit 33 determines that the involvement request condition is satisfied, it notifies the notification processing unit 34 of the determination result. The hands-on request threshold is an example of a distance threshold.

[0061] Here, the determination unit 33 sets the hands-on request threshold when the second map is used for driving control to a value larger than the hands-on request threshold when the first map is used for driving control. That is, the involvement request condition when the second map is used for driving control is relaxed compared to the involvement request condition when the first map is used for driving control. For example, the determination unit 33 sets the hands-on request threshold when the first map is used for driving control to 0.2m to 0.3m, and sets the hands-on request threshold when the second map is used for driving control to 0.4m to 0.5m. By setting the hands-on request threshold in this manner, even when the second map, which has relatively low accuracy of information about roads, is used for driving control, it is possible to request the driver to hold the steering wheel before the vehicle 10 gets too close to the lane markings.

[0062] As described in the control unit 32, the determination unit 33 may estimate the position of the lane markings relative to the camera 2 based on the positions of the lane markings on the image detected from the image and the parameters of the camera 2. Furthermore, the determination unit 33 may obtain the lateral distance for each of the left and right sides of the vehicle 10 by subtracting the distance from the mounting position of the camera 2 to the side of the vehicle 10 from the distance from the camera 2 to the lane marking.

[0063] 4 is a diagram showing an example of a hands-on request threshold when a first map is used for driving control and a hands-on request threshold when a second map is used for driving control. In this example, the first map is used for driving control while the vehicle 10 is traveling in section S1. In contrast, the second map is used for driving control while the vehicle 10 is traveling in section S2.

[0064] While the vehicle 10 is traveling in the section S1, the first value HOnTh1 is used as the hands-on request threshold. Therefore, when the vehicle 10 is traveling in the section S1, if the lateral distance L between the vehicle 10 and either the left or right lane marking 401 becomes less than the hands-on request threshold HOnTh1, it is determined that the involvement request condition is satisfied, and a hands-on request is notified.

[0065] In contrast, while the vehicle 10 is traveling in the section S2, the second value HOnTh2 is used as the hands-on request threshold. Therefore, when the vehicle 10 is traveling in the section S2, if the lateral distance L between the vehicle 10 and either the left or right lane marking 401 becomes less than the hands-on request threshold HOnTh2, it is determined that the involvement request condition is satisfied, and a hands-on request is notified. In addition, the second value HOnTh2 is set to a value larger than the first value HOnTh1. Therefore, the involvement request condition is more likely to be satisfied when the second map is used for driving control than when the first map is used for driving control. Therefore, even if the second map, which has relatively low accuracy of information about the road, is used for driving control, a hands-on request is notified before the vehicle 10 gets too close to the lane marking 401.

[0066] The determination unit 33 also compares the lateral distance to each of the left and right lane markings with the driving change request threshold. If either of the left and right lateral distances is less than the driving change request threshold, the determination unit 33 determines that the involvement request condition is satisfied. The driving change request threshold is another example of a distance threshold.

[0067] The determination unit 33 sets the driving change request threshold when the second map is used for driving control to a value greater than the driving change request threshold when the first map is used for driving control. For example, the determination unit 33 sets the driving change request threshold when the first map is used for driving control to 0.1 m to 0.2 m, and sets the driving change request threshold when the second map is used for driving control to 0.2 m to 0.3 m. By setting the driving change request threshold in this manner, the determination unit 33 can transfer driving control to the driver before the vehicle 10 gets too close to the lane markings, even when the second map, which has relatively low accuracy of information about roads, is used for driving control.

[0068] 5 is a diagram showing an example of a driving change request threshold when a first map is used for driving control and a driving change request threshold when a second map is used for driving control. In this example, the first map is used for driving control while the vehicle 10 is traveling in section S1. In contrast, the second map is used for driving control while the vehicle 10 is traveling in section S2.

[0069] While the vehicle 10 is traveling in the section S1, the first value TDTh1 is used as the driving change request threshold. Therefore, when the vehicle 10 is traveling in the section S1, if the lateral distance L between the vehicle 10 and either the left or right lane marking 501 becomes less than the driving change request threshold TDTh1, it is determined that the involvement request condition is satisfied, and a driving change request is notified.

[0070] In contrast, while the vehicle 10 is traveling in the section S2, the second value TDTh2 is used as the driving change request threshold. Therefore, when the vehicle 10 is traveling in the section S2, if the lateral distance L between the vehicle 10 and either the left or right lane marking 501 becomes less than the driving change request threshold TDTh2, it is determined that the involvement request condition is satisfied, and a driving change request is notified. In addition, the second value TDTh2 is set to a value larger than the first value TDTh1. Therefore, the involvement request condition is more likely to be satisfied when the second map is used for driving control than when the first map is used for driving control. Therefore, even if the second map, which has relatively low accuracy of information regarding the road, is used for driving control, a driving change request is notified before the vehicle 10 gets too close to the lane marking 501.

[0071] When the notification processing unit 34 receives a determination result from the determination unit 33 that the participation request condition has been satisfied, the notification processing unit 34 notifies the driver via the notification device 7 of a request corresponding to the satisfied participation request condition.

[0072] As described above, when it is determined that the lateral distance is less than the hands-on request threshold, the notification processing unit 34 notifies the driver of a hands-on request via the notification device 7. When it is determined that the lateral distance is less than the driving change request threshold, the notification processing unit 34 notifies the driver of a driving change request via the notification device 7.

[0073] 6 is an operational flowchart of a vehicle control process related to a change in the degree of driver involvement in driving. The processor 23 may execute the vehicle control process in accordance with the following operational flowchart at predetermined intervals.

[0074] The determination unit 33 of the processor 23 determines whether or not the map used for driving control is the first map (step S101).

[0075] If the map used for driving control is the first map (step S101-Yes), the determination unit 33 sets the engagement requirement condition relatively strict (step S102). On the other hand, if the map used for driving control is the second map (step S101-No), the determination unit 33 sets the engagement requirement condition relatively loose (step S103).

[0076] The determination unit 33 determines whether the set participation request condition is satisfied (step S104). If the participation request condition is satisfied (step S104-Yes), the notification processing unit 34 of the processor 23 notifies the driver of a request for participation in driving, which corresponds to the satisfied participation request condition, via the notification device 7 (step S105).

[0077] If the involvement request condition is not satisfied in step S104 (step S104-No), or after step S105, the processor 23 ends the vehicle control process.

[0078] As described above, the vehicle control device determines whether or not the involvement request condition that requests the driver of the vehicle to participate in the driving of the vehicle is satisfied, and when it is determined that the involvement request condition is satisfied, notifies the driver of the request for participation in the driving via a notification device provided in the vehicle cabin. The vehicle control device relaxes the involvement request condition when the vehicle is controlled for automatic driving based on the second map, which has information about roads with lower accuracy than the first map, compared to the involvement request condition when the vehicle is controlled for automatic driving based on the first map. Therefore, when the second map is used for driving control, the involvement request condition is more likely to be satisfied. Therefore, even when the second map, which has information about roads with relatively lower accuracy, is used for driving control, the vehicle control device can request the driver to participate in driving before the vehicle falls into an unstable situation. As a result, the vehicle control device can suppress the driver from feeling uneasy about the behavior of the vehicle during automatic driving control.

[0079] According to a modified example, the hands-on request threshold when the second map is used for driving control may be set to a value greater than half the width of the vehicle's lane. In this case, when the second map is used for driving control, the involvement request condition is always satisfied, so that the notification processor 34 always requests the driver to hold the steering wheel.

[0080] According to another modification, the determination unit 33 may adjust the hands-on request threshold or the driving change request threshold according to the degree of deviation between the first map and the second map in the section where the second map is used for the driving control. For example, the determination unit 33 may increase the hands-on request threshold or the driving change request threshold as the degree of deviation increases. In this case, the determination unit 33 refers to the average value of the deviation of each sampling point in the deviation section calculated by the switching point detection unit 31, and increases the hands-on request threshold or the driving change request threshold as the average value increases. At that time, the hands-on request threshold or the driving change request threshold may also increase continuously as the average value of the deviation increases. Alternatively, the hands-on request threshold or the driving change request threshold may be set in a stepwise manner. In this case, the determination unit 33 increases the hands-on request threshold or the driving change request threshold by a predetermined step amount each time the average value of the deviation increases by a predetermined value. Furthermore, the determination unit 33 may divide the deviation section into a plurality of subsections and adjust the hands-on request threshold or the driving change request threshold for each subsection. In this case, the determination unit 33 calculates the average value of the deviation degree at each sampling point included in each subsection. Then, similar to the above process, the determination unit 33 may increase the hands-on request threshold or the driving change request threshold as the average value of the deviation degree in the subsection increases. Furthermore, even if the switching point is set based on a section other than the deviation section, the determination unit 33 may adjust the hands-on request threshold or the driving change request threshold based on the deviation degree by performing the same process as described above for the section in which the second map is used for driving control.

[0081] 7(a) and 7(b) are diagrams showing an example of the adjustment of the hands-on request threshold according to this modified example. In FIG. 7(a) and FIG. 7(b), the lane markings 701 that divide the lane in which the vehicle 10 is traveling are shown by solid lines. In the first map, the lane markings are shown by dashed lines 702, and in the second map, the lane markings are shown by dashed lines 703. In the example shown in FIG. 7(a), the deviation between the lane markings 702 shown in the first map and the lane markings 703 shown in the second map is relatively small. Therefore, the hands-on request threshold HOnTh2 when the second map is used for driving control is set to a relatively small value. However, even in this case, the hands-on request threshold HOnTh2 is set to a value larger than the hands-on request threshold when the first map is used for driving control.

[0082] In contrast, in the example shown in Fig. 7(b), the deviation between the lane marking 702 shown on the first map and the lane marking 703 shown on the second map is relatively large. Therefore, the hands-on request threshold value HOnTh2 when the second map is used for driving control is set to a relatively large value compared to the example shown in Fig. 7(a).

[0083] In this way, by adjusting the hands-on request threshold or the driving change request threshold depending on the degree of deviation between the first map and the second map, the judgment unit 33 can more appropriately prevent the vehicle 10 from getting too close to the lane markings.

[0084] Furthermore, when the second map is used for driving control, the lower the certainty of the detected lane markings that demarcate the own lane, the larger the hands-on request threshold or the driving change request threshold may be. In this case, the determination unit 33 may use the reliability of the lane markings output by the classifier used to detect the lane markings as the certainty.

[0085] According to another modification, the determination unit 33 may determine whether or not the involvement request condition is satisfied based on the behavior of the vehicle 10, the state of the driver, or the situation around the vehicle 10, instead of the lateral distance. In this case, it is preferable that the determination unit 33 relaxes the involvement request condition when the second map is used for driving control, compared to the involvement request condition when the first map is used for driving control. By relaxing the involvement request condition when the second map is used for driving control in this way, the determination unit 33 can request the driver to participate in driving before the vehicle 10 falls into an unstable situation due to the behavior of the vehicle 10, the state of the driver, or the situation around the vehicle 10, even when the second map is used for driving control.

[0086] For example, the determination unit 33 determines that the involvement request condition is satisfied when the speed of the vehicle 10 measured by a speed sensor, which is an example of the behavior sensor 5, is faster than the speed limit of the road on which the vehicle 10 is currently traveling by a predetermined speed threshold or more. Then, the notification processing unit 34 notifies the driver of a hands-on request via the notification device 7. In this case, the determination unit 33 sets the speed threshold when the second map is used for the traveling control to a value lower than the speed threshold when the first map is used for the traveling control. This allows the determination unit 33 to appropriately request the driver to participate in driving when the speed of the vehicle 10 exceeds the speed limit. Note that the determination unit 33 refers to the map being used for the traveling control and identifies the road including the position of the vehicle 10 represented in the latest positioning information by the GPS receiver 4 as the road on which the vehicle 10 is traveling. Then, the determination unit 33 may refer to the map being used for the traveling control and identify the speed limit of the road on which the vehicle 10 is traveling. Alternatively, the determination unit 33 may input the image generated by the camera 2 to a classifier that has been trained in advance to detect the speed limit indicated on a speed sign, thereby identifying the speed limit of the road on which the vehicle 10 is traveling. As such a classifier, the determination unit 33 may use a classifier similar to the classifier used for detecting features, as described in the control unit 32.

[0087] Furthermore, when the vehicle 10 is traveling in a section where the vehicle speed limit is less than a predetermined speed, the determination unit 33 determines that the involvement request condition is satisfied. Then, the notification processing unit 34 notifies the driver of a hands-on request via the notification device 7. In this case, the determination unit 33 sets the predetermined speed when the second map is used for driving control to be higher than the predetermined speed when the first map is used for driving control. This allows the determination unit 33 to appropriately request the driver to participate in driving when the vehicle speed limit of the road on which the vehicle 10 is traveling is low and more careful control of the vehicle 10 is required.

[0088] Alternatively, the determination unit 33 determines that the involvement request condition is satisfied when the curvature radius of a curve where the vehicle 10 is traveling or located within a section up to a predetermined distance (for example, several hundred meters to 1 km) ahead is less than a predetermined curvature radius threshold. Then, when the curvature radius of the curve is less than the predetermined curvature radius threshold, the notification processing unit 34 notifies the driver of a hands-on request via the notification device 7. Alternatively, the notification processing unit 34 may notify the driver of a driving change request via the notification device 7. In this case, the determination unit 33 sets the curvature radius threshold when the second map is used for driving control to a value larger than the curvature radius threshold when the first map is used for driving control. Thereby, the determination unit 33 can appropriately request the driver to participate in driving according to the curvature radius of the curve where the vehicle 10 is traveling or is scheduled to travel. Similarly to the above, the determination unit 33 may refer to the map being used for driving control and identify the road including the position of the vehicle 10 indicated in the latest positioning information by the GPS receiver 4 as the road on which the vehicle 10 is traveling. Furthermore, the determination unit 33 may refer to the traveling direction of the vehicle 10 indicated by a direction sensor (not shown) mounted on the vehicle 10 and the map being used for driving control and identify the radius of curvature of a curve included in a section from the current position of the vehicle 10 to a predetermined distance ahead on the road on which the vehicle 10 is traveling.

[0089] Alternatively, the determination unit 33 determines that the involvement request condition is satisfied when the gradient of the road on which the vehicle is traveling or in a section up to a predetermined distance away is equal to or greater than a predetermined gradient threshold. Then, the notification processing unit 34 notifies the driver of a hands-on request via the notification device 7. Alternatively, the notification processing unit 34 may notify the driver of a driving change request via the notification device 7. In this case, the determination unit 33 sets the gradient threshold in the case where the second map is used for driving control to a value smaller than the gradient threshold in the case where the first map is used for driving control. This allows the determination unit 33 to appropriately request the driver to participate in driving in accordance with the gradient of the road section on which the vehicle 10 is traveling or is scheduled to travel. Note that, similarly to the above, the determination unit 33 may refer to the map being used for driving control and identify the road including the position of the vehicle 10 represented in the latest positioning information by the GPS receiver 4 as the road on which the vehicle 10 is traveling. Furthermore, the determination unit 33 may refer to the direction of travel of the vehicle 10 indicated by a direction sensor (not shown) mounted on the vehicle 10 and the map being used for driving control, and identify the gradient of the section of the road on which the vehicle 10 is traveling, from the current position of the vehicle 10 to a predetermined distance ahead.

[0090] Alternatively, the determination unit 33 determines that the involvement request condition is satisfied when the unheld period during which the steering wheel is not held by the driver continues for a predetermined unheld period threshold or more. Then, the notification processing unit 34 notifies the driver of a hands-on request via the notification device 7. In this case, the unheld period threshold when the second map is used for driving control is set to a value smaller than the unheld period threshold when the first map is used for driving control. Note that the determination unit 33 may determine the unheld period as the elapsed time since the ECU 9 last received a signal indicating that the steering wheel is being held from a touch sensor provided on the steering wheel.

[0091] Alternatively, the determination unit 33 determines that the involvement request condition is satisfied when the driver ignores any of the face lost warning, inattentive warning, closed eyes warning, or hands off warning given via the notification device 7 for a period of time equal to or longer than a predetermined time threshold. Then, the notification processing unit 34 notifies the driver of a hands-on request via the notification device 7. In this case, the time threshold when the second map is used for driving control is set to a value smaller than the time threshold when the first map is used for driving control.

[0092] The determination unit 33 determines whether or not a face area showing the driver's face can be detected on the driver image by inputting the driver image generated by the driver monitor camera 3 to a classifier that has been trained in advance to detect the driver's face. The determination unit 33 can use a classifier similar to the classifier that the control unit 32 uses to detect features as such a classifier. If the face area is not detected, the determination unit 33 determines that the driver is in a face-lost state in which the driver's face cannot be detected. If the face-lost state continues for a predetermined period of time, the determination unit 33 notifies the driver of a face-lost warning via the notification device 7. If the driver's face is detected from the generated driver image after the face-lost warning is notified, or if the driver performs a response operation corresponding to the face-lost warning provided in the vehicle cabin, the determination unit 33 determines that the driver has responded to the face-lost warning. On the other hand, if the driver's face is not detected from the driver image even after the face-lost warning is notified, and no response operation is performed to the face-lost warning, the determination unit 33 may determine that the driver has ignored the face-lost warning. The response operation may be performed, for example, by operating a predetermined switch provided in the vehicle cabin, or by the driver making a predetermined utterance. The voice uttered by the driver is collected by a speaker provided in the vehicle cabin and output as a voice signal to the ECU 9. The processor 23 may determine whether the driver has made the predetermined utterance by performing a predetermined voice recognition process such as GMM-HMM or DNN-HMM on the voice signal.

[0093] The determination unit 33 also determines the direction of the driver's face by matching the face region with a three-dimensional face model. If the direction of the driver's face is outside a predetermined angle range centered on the traveling direction of the vehicle 10, the determination unit 33 determines that the driver is in an inattentive state. Alternatively, the determination unit 33 may detect the driver's line of sight, and if the detected line of sight is outside the above-mentioned angle range, determine that the driver is in an inattentive state. In this case, the determination unit 33 detects the upper eyelid and the lower eyelid of either the left or right eye of the driver by applying an edge detection filter to the face region to detect edges that are continuous in the horizontal direction, or by inputting the face region to a classifier. Furthermore, the determination unit 33 detects the pupil center and the corneal reflection of the light source by performing template matching on the region surrounded by the upper eyelid and the lower eyelid. The determination unit 33 may then detect the line of sight based on the positional relationship between the pupil center and the corneal reflection of the light source. When the inattentive state continues for a predetermined period of time, the determination unit 33 notifies the driver of an inattentive warning via the notification device 7. When the detected face direction or line of sight direction of the driver after the inattentive warning notification falls within the above-mentioned angle range, that is, when the inattentive state is resolved, the determination unit 33 determines that the driver has responded to the inattentive warning. On the other hand, when the inattentive state is not resolved even after the inattentive warning notification, the determination unit 33 may determine that the driver has ignored the inattentive warning.

[0094] Furthermore, the determination unit 33 calculates the ratio of the detected distance between the upper eyelid and the lower eyelid to a reference distance between the upper eyelid and the lower eyelid when the driver has his / her eyes completely open as the degree of eye closure. The reference distance is stored in advance in the memory 22. Then, when the degree of eye closure is equal to or less than a predetermined eye closure threshold, the determination unit 33 determines that the driver is in an eye closure state with his / her eyes closed. When the eye closure state continues for a predetermined period, the determination unit 33 notifies the driver of an eye closure warning via the notification device 7. When the degree of eye closure of the driver detected after the notification of the eye closure warning becomes greater than the eye closure threshold, that is, when the eye closure state is resolved, the determination unit 33 determines that the driver has responded to the eye closure warning. On the other hand, when the eye closure state is not resolved even after the notification of the eye closure warning, the determination unit 33 may determine that the driver has ignored the eye closure warning.

[0095] Furthermore, when the ECU 9 receives a signal indicating that the steering wheel is not being held from the touch sensor provided on the steering wheel, the determination unit 33 determines that the driver is in a hands-off state where the driver is not holding the steering wheel. When the ECU 9 is controlling the vehicle 10 in an automatic driving state at a level where the driver is required to hold the steering wheel, and the hands-off state continues for a predetermined time or more, the determination unit 33 notifies the driver of a hands-off warning via the notification device 7. After the hands-off warning is notified, when the ECU 9 receives a signal indicating that the steering wheel is being held from the touch sensor, the determination unit 33 determines that the hands-off state has been resolved. On the other hand, when the ECU 9 does not receive a signal indicating that the steering wheel is being held from the touch sensor even after the hands-off warning is notified, the determination unit 33 may determine that the driver has ignored the hands-off warning.

[0096] The judgment unit 33 may judge whether or not all of the relaxed requirement conditions in the above-mentioned embodiment or variant examples are satisfied, or may judge whether or not any one or more of the relaxed requirement conditions are satisfied.

[0097] A computer program for realizing the functions of the processor 23 of the ECU 9 according to the above embodiment or variant example may be provided in a form recorded on a computer-readable portable recording medium, such as a semiconductor memory, a magnetic recording medium or an optical recording medium.

[0098] As described above, those skilled in the art can make various modifications to the embodiments within the scope of the present invention. [Explanation of symbols]

[0099] 1 Vehicle Control System 10 Vehicles 2 Camera 3 Driver monitor camera 4 GPS receiver 5. Behavior Sensor 6. Wireless communication terminals 7 Notification device 8. Storage Devices 9 Electronic Control Unit (ECU) 21 Communication Interface 22 Memory 23 Processors 31 Switching point detector 32 Control section 33 Judgment section 34 Notification processing section

Claims

1. a storage unit that stores a first map that represents information about roads and a second map that represents the information about the roads and has lower accuracy of the information about the roads than the first map; a determination unit that, when the vehicle is under autonomous driving control, determines whether or not an involvement request condition that requests the driver of the vehicle to participate in driving the vehicle is satisfied based on an outside sensor signal generated by an outside sensor that detects the situation around the vehicle, an inside sensor signal generated by an inside sensor that detects the situation inside the cabin of the vehicle, a vehicle behavior signal generated by a behavior sensor that detects the behavior of the vehicle, or the position of the vehicle; a notification processing unit that notifies a request for involvement in driving via a notification device provided in the vehicle cabin when it is determined that the involvement request condition is satisfied; having the determination unit relaxes the engagement requirement condition when the vehicle is being controlled under autonomous driving control based on the second map compared to the engagement requirement condition when the vehicle is being controlled under autonomous driving control based on the first map. Vehicle control device.

2. The determination unit is measuring a lateral distance between the vehicle and a lane marking that marks the lane in which the vehicle is traveling, based on the external sensor signal; and determining that the engagement requirement condition is satisfied when the lateral distance becomes less than a predetermined distance threshold value; 2. The vehicle control device according to claim 1, wherein the distance threshold is set to be larger when the vehicle is being controlled to drive autonomously based on the second map than when the vehicle is being controlled to drive autonomously based on the first map.

3. 3. The vehicle control device according to claim 2, wherein the determination unit increases the distance threshold value the greater the degree of discrepancy between information about the road represented on the first map and information about the road represented on the second map in a section in which the vehicle is being controlled to drive automatically based on the second map.

4. The determination unit is determining that the engagement requirement condition is satisfied when the speed of the vehicle represented by the vehicle behavior signal is faster than a speed limit of a road on which the vehicle is traveling by a predetermined speed threshold or more; 2. The vehicle control device according to claim 1, wherein the speed threshold when the vehicle is being controlled to drive autonomously based on the second map is set to a lower value than the speed threshold when the vehicle is being controlled to drive autonomously based on the first map.

5. The determination unit is determining that the engagement requirement condition is satisfied when a speed limit of a road on which the vehicle is traveling is less than a predetermined speed; 2. The vehicle control device according to claim 1, wherein the predetermined speed when the vehicle is being controlled to drive autonomously based on the second map is set to a higher value than the predetermined speed when the vehicle is being controlled to drive autonomously based on the first map.

6. The determination unit is determining that the involvement requirement condition is satisfied when the radius of curvature of a curve located during the vehicle's travel or within a section up to a predetermined distance away is less than a predetermined curvature radius threshold; 2. The vehicle control device according to claim 1, wherein the curvature radius threshold is set to a value greater when the vehicle is under automatic driving control based on the second map than when the vehicle is under automatic driving control based on the first map.

7. The determination unit is determining that the involvement requirement condition is satisfied when the gradient of a road within a section during which the vehicle is traveling or within a predetermined distance ahead is equal to or greater than a predetermined gradient threshold; 2. The vehicle control device according to claim 1, wherein the gradient threshold is set to a value smaller when the vehicle is being controlled to drive autonomously based on the second map than when the vehicle is being controlled to drive autonomously based on the first map.

8. When a vehicle is under autonomous driving control, a determination is made as to whether or not an involvement request condition that requests the driver of the vehicle to participate in driving the vehicle is satisfied based on an outside sensor signal generated by an outside sensor that detects the situation around the vehicle, an inside sensor signal generated by an inside sensor that detects the situation inside the cabin of the vehicle, a vehicle behavior signal generated by a behavior sensor that detects the behavior of the vehicle, or the position of the vehicle; When it is determined that the involvement request condition is satisfied, a notification of a request for involvement in driving is issued via a notification device provided in the vehicle cabin. Including, The determination of whether or not the involvement requirement condition is satisfied is made by relaxing the involvement requirement condition when the vehicle is autonomously controlled based on a second map that represents information about the road and has less accurate information about the road than the involvement requirement condition when the vehicle is autonomously controlled based on a first map that represents information about the road. A vehicle control method comprising:

9. When a vehicle is under autonomous driving control, a determination is made as to whether or not an involvement request condition that requests the driver of the vehicle to participate in driving the vehicle is satisfied based on an outside sensor signal generated by an outside sensor that detects the situation around the vehicle, an inside sensor signal generated by an inside sensor that detects the situation inside the cabin of the vehicle, a vehicle behavior signal generated by a behavior sensor that detects the behavior of the vehicle, or the position of the vehicle; When it is determined that the involvement request condition is satisfied, a notification of a request for involvement in driving is issued via a notification device provided in the vehicle cabin. A vehicle control computer program for causing a processor mounted on the vehicle to execute the above-mentioned The determination of whether or not the involvement requirement condition is satisfied is made by relaxing the involvement requirement condition when the vehicle is autonomously controlled based on a second map that represents information about the road and has less accurate information about the road than the involvement requirement condition when the vehicle is autonomously controlled based on a first map that represents information about the road. A computer program for controlling a vehicle, comprising:

Images