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

Abstract

The present invention provides a vehicle control system that can reduce anxiety among the occupants of a vehicle regarding its behavior when there is another vehicle that may cut in front of it. [Solution] The vehicle control device includes: an other vehicle detection unit 21 that detects other vehicles traveling in adjacent lanes adjacent to the lane in which the vehicle 10 is traveling based on external sensor signals and detects the relative behavior of the other vehicles with respect to the vehicle 10; a determination unit 22 that determines whether the relative behavior of the other vehicles satisfies predetermined interruption determination conditions; a control unit 23 that decelerates the vehicle 10 if the behavior satisfies the interruption determination conditions; a gaze status detection unit 24 that detects the gaze status of the occupants of the vehicle 10 toward the other vehicle based on the detection result of the gaze direction of the occupants of the vehicle 10 based on in-vehicle images; and an adjustment unit 25 that adjusts the interruption determination conditions according to the gaze status.

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 Art

[0002] When there is another vehicle that is expected to cut in front of the host vehicle, a technique has been proposed to control the host vehicle so that the other vehicle and the host vehicle do not get too close (see Patent Document 1).

[0003] The above document describes that when a target vehicle traveling in a lane adjacent to the lane in which the host vehicle is traveling attempts to cut into the host lane, the host vehicle changes its speed, acceleration, and / or changes to another lane to avoid being cut in by the target vehicle. Further, the above document describes avoiding frequently performing unnecessary braking and / or acceleration when the target vehicle appears to be attempting to cut in but actually does not cut in. And for that avoidance, the sensitivity to attempts to cut in is changed based on static road features such as lane endings and road dividers, dynamic road features such as the presence of other vehicles in front of the vehicle that may attempt to cut in, and / or traffic rules and driving habits within the geographical area.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] If the behavior of the host vehicle with respect to the behavior of another vehicle that may cut in front of the host vehicle is different from what the passengers of the host vehicle expect, the passengers may feel不安.

[0006] Therefore, the present invention aims to provide a vehicle control device that can reduce anxiety among the occupants of a vehicle regarding the behavior of the vehicle when there is another vehicle that may cut in front of the vehicle. [Means for solving the problem]

[0007] According to one embodiment, a vehicle control device is provided. This vehicle control device includes: an other vehicle detection unit that detects other vehicles traveling in adjacent lanes adjacent to the lane in which the vehicle is traveling based on external sensor signals representing a predetermined area around the vehicle, and detects the relative behavior of the other vehicles with respect to the vehicle; a determination unit that determines whether the relative behavior of the other vehicles satisfies predetermined interruption determination conditions; a control unit that decelerates the vehicle if the behavior satisfies the interruption determination conditions; a gaze status detection unit that detects the gaze direction of the vehicle's occupants based on an interior image representing the interior of the vehicle, and detects the gaze status of the vehicle's occupants toward the other vehicle based on the gaze direction detection result; and an adjustment unit that adjusts the interruption determination conditions according to the gaze status.

[0008] In one embodiment, the adjustment unit relaxes the interruption detection conditions as the duration for which the driver of the vehicle's occupants is intently watching another vehicle increases.

[0009] In one embodiment, the adjustment unit relaxes the interruption detection conditions as the number of occupants of its own vehicle who are watching other vehicles increases.

[0010] Another embodiment provides a vehicle control method. This vehicle control method includes detecting other vehicles traveling in adjacent lanes adjacent to the lane in which the vehicle is traveling based on external sensor signals representing a predetermined area around the vehicle, detecting the relative behavior of the other vehicles with respect to the vehicle, determining whether the relative behavior of the other vehicles satisfies predetermined interruption judgment conditions, decelerating the vehicle if the behavior satisfies the interruption judgment conditions, detecting the gaze direction of the vehicle's occupants based on an interior image representing the inside of the vehicle, detecting the gaze status of the vehicle's occupants toward the other vehicle based on the gaze direction detection result, and adjusting the interruption judgment conditions according to the gaze status.

[0011] In yet another embodiment, a computer program for vehicle control is provided. This computer program for vehicle control includes instructions to cause a processor installed in the vehicle to perform the following actions: detect other vehicles traveling in adjacent lanes adjacent to the vehicle's lane based on external sensor signals representing a predetermined area around the vehicle; detect the relative behavior of the other vehicles with respect to the vehicle; determine whether the relative behavior of the other vehicles satisfies predetermined interruption criteria; decelerate the vehicle if the behavior satisfies the interruption criteria; detect the gaze direction of the vehicle's occupants based on an interior image representing the vehicle's interior; detect the gaze status of the vehicle's occupants toward the other vehicle based on the gaze direction detection result; and adjust the interruption criteria according to the gaze status. [Effects of the Invention]

[0012] The vehicle control device disclosed herein has the effect of making it less likely for the occupants of the vehicle to feel anxious about the behavior of the vehicle when there is another vehicle that may cut in front of the vehicle. [Brief explanation of the drawing]

[0013] [Figure 1] This is a schematic diagram of the vehicle control system in which the vehicle control device is implemented. [Figure 2] This is a hardware configuration diagram of an electronic control unit, which is one embodiment of a vehicle control system. [Figure 3] This is a functional block diagram of the processor in an electronic control unit related to vehicle control processing. [Figure 4] This diagram illustrates the overview of the vehicle control process according to this embodiment. [Figure 5] This is an operation flowchart of the vehicle control process. [Modes for carrying out the invention]

[0014] The following describes the vehicle control device, the vehicle control method executed on the vehicle control device, and the vehicle control computer program, with reference to the diagram. This vehicle control device detects the relative behavior of other vehicles traveling in adjacent lanes adjacent to the lane in which the vehicle is traveling. When the relative behavior of the other vehicle satisfies predetermined interruption detection conditions, this vehicle control device controls the vehicle so that even if the other vehicle moves into the vehicle's lane in front of the vehicle, the distance between the vehicle and the other vehicle is maintained at or above a predetermined distance. At that time, this vehicle control device adjusts the interruption detection conditions according to the degree to which the vehicle's occupants are paying attention to the other vehicle.

[0015] Figure 1 is a schematic diagram of a vehicle control system on which a vehicle control device is implemented. Figure 2 is a hardware diagram of an electronic control unit, which is one embodiment of the vehicle control device. In this embodiment, the vehicle control system 1, which is mounted on and controls a vehicle 10, which is an example of the vehicle itself, includes at least one external sensor 2, an in-vehicle monitor camera 3, and an electronic control unit (ECU) 4, which is an example of a vehicle control device. The external sensor 2, the in-vehicle monitor camera 3, and the ECU 4 are connected to each other so as to be able to communicate with each other via an in-vehicle network. The vehicle control system 1 may further include a wireless communication terminal (not shown) for communicating with other devices. Furthermore, the vehicle control system 1 may also include a positioning device (not shown) that measures the position of the vehicle 10 in accordance with a satellite positioning system, such as a GPS receiver.

[0016] Each external vehicle sensor 2 is a sensor for detecting the situation around the vehicle 10, and is, for example, a camera or a ranging sensor such as radar or LiDAR. Note that the vehicle 10 may be provided with a plurality of external vehicle sensors having different detection ranges or types. In FIG. 1, two external vehicle sensors 2 (an external vehicle sensor having the front of the vehicle 10 as a detection range and an external vehicle sensor having the rear of the vehicle 10 as a detection range) are illustrated. In the present embodiment, it is preferable that the vehicle 10 is provided with a plurality of external vehicle sensors 2 having different detection ranges so as to be able to detect the entire periphery of the vehicle 10. Each external vehicle sensor 2 generates an external vehicle sensor signal representing the situation of a predetermined detection range around the vehicle 10 at every predetermined cycle, and outputs the generated external vehicle sensor signal to the ECU 4.

[0017] The in-vehicle monitor camera 3 is an example of an in-vehicle sensor, and is attached to the front of the vehicle interior so as to face the vehicle interior such that each occupant of the vehicle 10 including the driver is included in its imaging target area. The in-vehicle monitor camera 3 may have a light source such as an infrared LED. Then, the in-vehicle monitor camera 3 generates an image (hereinafter referred to as an in-vehicle image) in which the occupants of the vehicle 10 are captured by imaging the imaging target area inside the vehicle at every predetermined imaging cycle, and outputs the generated in-vehicle image to the ECU 4. Note that the vehicle 10 may be provided with a plurality of in-vehicle monitor cameras 3 having different seats as imaging target areas.

[0018] The ECU 4 automatically controls the vehicle 10 or executes driving support for the driver of the vehicle 10. In particular, when it is predicted that another vehicle traveling in an adjacent lane will move into the own lane in front of the vehicle 10, the ECU 4 decelerates the vehicle 10 to keep the distance between the other vehicle and the vehicle 10 at a certain level or more, and performs deceleration control on the vehicle 10.

[0019] As shown in FIG. 2, the ECU 4 includes a communication interface 11, a memory 12, and a processor 13. The communication interface 11, the memory 12, and the processor 13 may each be configured as a separate circuit, or may be integrally configured as one integrated circuit.

[0020] The communication interface 11 has an interface circuit for connecting the ECU 4 to the in-vehicle network. Whenever the communication interface 11 receives an out-vehicle sensor signal from the out-vehicle sensor 2, it transmits the received out-vehicle sensor signal to the processor 13. Also, whenever the communication interface 11 receives an in-vehicle image from the in-vehicle monitor camera 3, it transmits the received in-vehicle image to the processor 13.

[0021] The memory 12 is an example of a storage unit and has, for example, a volatile semiconductor memory and a non-volatile semiconductor memory. The memory 12 stores various data used in vehicle control processing executed by the processor 13. For example, the memory 12 stores various parameters of the out-vehicle sensor 2 (such as focal length, shooting direction, and mounting position, etc.) and various parameters for specifying an identifier for detecting an object around the vehicle 10. Further, the memory 12 stores various information used for detecting the line-of-sight direction of an occupant and determining fixation on another vehicle. Further, the memory 12 temporarily stores out-vehicle sensor signals and in-vehicle images. Further, the memory 12 temporarily stores various data generated during vehicle control processing.

[0022] The processor 13 has one or more CPUs (Central Processing Unit) and its peripheral circuits. The processor 13 may further have other arithmetic circuits such as a logical arithmetic unit, a numerical arithmetic unit, or a graphic processing unit. And the processor 13 executes vehicle control processing for the vehicle 10.

[0023] FIG. 3 is a functional block diagram of the processor 13 regarding vehicle control processing. The processor 13 has an other-vehicle detection unit 21, a determination unit 22, a control unit 23, a fixation situation detection unit 24, and an adjustment unit 25. Each of these units of the processor 13 is a functional module realized by a computer program operating on the processor 13. Alternatively, each of these units may be a dedicated arithmetic circuit provided in the processor 13.

[0024] The other vehicle detection unit 21 detects one or more other vehicles traveling in an adjacent lane to the vehicle's own lane. When the other vehicle detection unit 21 detects other vehicles traveling in an adjacent lane, it detects the relative behavior of those other vehicles with respect to vehicle 10. Hereafter, for the sake of explanation, other vehicles traveling in adjacent lanes may be referred to as "vehicles of interest."

[0025] The other vehicle detection unit 21 detects other vehicles by, for example, inputting external sensor signals generated by individual external sensors 2 into a classifier that has been pre-trained to detect other vehicles. The classifier is configured as a convolutional neural network (CNN) type architecture or a deep neural network (DNN) with an attention mechanism. Alternatively, the classifier may be configured as a classifier based on a machine learning algorithm other than a DNN, such as a support vector machine. The classifier for other vehicle detection may be further configured to identify the type of other vehicle. The types of other vehicles to be identified include passenger cars, large vehicles such as buses or trucks, and emergency vehicles such as ambulances, fire trucks or police vehicles. The classifier for other vehicle detection may also be configured to further identify the illumination status of warning lights on the detected emergency vehicle.

[0026] Furthermore, if the external sensor 2 is a camera, the other vehicle detection unit 21 may detect lane markings by inputting an external image, which is an example of an external sensor signal generated by the camera, into a classifier that has been pre-trained to detect lane markings. The classifier for lane marking detection is also configured as a CNN-type architecture or a DNN with an attention mechanism. Note that a single classifier may be pre-trained to detect both other vehicles and lane markings.

[0027] The other vehicle detection unit 21 identifies the other vehicle traveling in the adjacent lane as the vehicle of interest among the detected other vehicles. If the external sensor signal is an external image, the other vehicle detection unit 21 identifies the lane marking closest to vehicle 10 as the lane marking that demarcates the vehicle's own lane. The other vehicle detection unit 21 then compares the position of the lower edge of the object region representing the detected other vehicle on the external image with the position of the lane marking. If the lower edge of the object region is located further from vehicle 10 than the lane marking, and closer to vehicle 10 than other lane markings adjacent to the lane marking, the other vehicle detection unit 21 identifies the other vehicle represented in that object region as the vehicle of interest. Furthermore, if the external sensor signal is a distance measurement signal generated by a distance measuring sensor, which is an example of an external sensor 2, the other vehicle detection unit 21 determines the distance between vehicle 10 and the other vehicle in a direction perpendicular to the direction of travel of vehicle 10 (hereinafter referred to as the lateral direction) (hereinafter referred to as the lateral distance) based on the distance and direction to the other vehicle detected on the distance measurement signal. If the other vehicle detection unit 21 determines that the lateral distance to the other vehicle is within a range of values ​​corresponding to the distance between two vehicles traveling in adjacent lanes (for example, 1m to 3m), it identifies the other vehicle as a vehicle of interest.

[0028] The other vehicle detection unit 21 determines the relative behavior of the vehicle of interest with respect to vehicle 10. In this embodiment, the other vehicle detection unit 21 determines the relative speed of the vehicle of interest with respect to vehicle 10, the distance between vehicle 10 and the vehicle of interest along the direction of travel of vehicle 10 (hereinafter referred to as the vertical distance), and the relative positional relationship between vehicle 10 and the vehicle of interest as index values ​​representing the relative behavior.

[0029] To this end, the other vehicle detection unit 21 tracks the vehicle of interest by applying a predetermined tracking method, such as ByteTrack, to each of the multiple external sensor signals obtained in time series. The other vehicle detection unit 21 then determines the vertical distance and relative position between the vehicle of interest being tracked and vehicle 10 at the time each external sensor signal is acquired. Furthermore, the other vehicle detection unit 21 determines the relative speed of the vehicle of interest to vehicle 10 based on the time change of the vertical distance and the acquisition interval of the external sensor signals. Here, if the external sensor signal is an external image, the lower end of the object region representing the vehicle of interest corresponds to the position where the vehicle of interest is placed on the road surface. Furthermore, the position of each pixel in the external image corresponds one-to-one with the orientation as seen from the camera. Therefore, the other vehicle detection unit 21 can determine the orientation and distance from vehicle 10 to the vehicle of interest based on the parameters of the camera, which is the external sensor 2 (installation height, shooting direction, and field of view, etc.), and the position of the lower end of the object region representing the vehicle of interest in the external image. Furthermore, if the external sensor is a distance measurement signal, the other vehicle detection unit 21 can use the direction in which the vehicle of interest is represented on the distance measurement signal as the direction from vehicle 10 to the vehicle of interest, and the measured distance for that direction as the distance from vehicle 10 to the vehicle of interest. The other vehicle detection unit 21 then uses the direction and distance from vehicle 10 to the vehicle of interest as an index value representing the relative position of the vehicle of interest with respect to vehicle 10. In addition, the other vehicle detection unit 21 can determine the vertical distance between vehicle 10 and the vehicle of interest based on the direction and distance from vehicle 10 to the vehicle of interest.

[0030] The other vehicle detection unit 21 calculates the relative speed of the vehicle of interest with respect to vehicle 10 by dividing the change in the vertical distance between the vehicle of interest and vehicle 10, determined for each of the two most recently obtained external sensor signals, by the acquisition interval of those two external sensor signals.

[0031] Furthermore, if multiple vehicles of interest are detected, the other vehicle detection unit 21 can perform a tracking process to track each vehicle of interest and obtain an index value representing the relative behavior of each vehicle being tracked.

[0032] The other vehicle detection unit 21 determines index values ​​(relative speed, longitudinal distance, and relative position) that represent the relative behavior of the vehicle of interest with respect to vehicle 10, and each time it does so, it notifies the determination unit 22, the control unit 23, and the gaze status detection unit 24 of these index values. Furthermore, if the type of the vehicle of interest and the illumination status of its warning lights are identified, the other vehicle detection unit 21 notifies the adjustment unit 25 of the identification result.

[0033] The determination unit 22 determines whether an index value representing the relative behavior of the vehicle of interest with respect to vehicle 10 satisfies a predetermined interruption determination condition. If the predetermined interruption determination condition is met, the determination unit 22 determines that the vehicle of interest may move from an adjacent lane into its own lane in front of vehicle 10, that is, there is a possibility that it may cut in front of vehicle 10.

[0034] In this embodiment, the interruption detection conditions are that the relative speed of the vehicle of interest to vehicle 10 is faster than or equal to a predetermined speed threshold, the vehicle of interest is approaching vehicle 10 from behind, and the longitudinal distance is less than a predetermined distance threshold. The interruption detection conditions are adjusted according to the attention status of the vehicle of interest by the occupants of vehicle 10. Details of the adjustment of the interruption detection conditions will be described later with respect to the adjustment unit 25.

[0035] When the determination unit 22 determines that the interrupt determination condition has been met, it notifies the control unit 23 of the determination result.

[0036] When the control unit 23 receives notification from the determination unit 22 that the interrupt determination condition has been met, it controls the powertrain or brakes of vehicle 10 to decelerate vehicle 10. This ensures that even if the vehicle of interest cuts in front of vehicle 10, the control unit 23 maintains a distance greater than or equal to the target inter-vehicle distance. At this time, the control unit 23 sets the brake operation amount or the target torque for the powertrain so that vehicle 10 decelerates at a preset deceleration rate. A map representing the relationship between the deceleration rate, the behavior of vehicle 10 (accelerator opening, shift position, speed, etc.), the target torque, and the brake operation amount is stored in the memory 12 in advance. The control unit 23 can then refer to this map to set the target torque and brake operation amount. The control unit 23 decelerates vehicle 10 by controlling the powertrain to achieve the set target torque or by operating the brakes to achieve the set brake operation amount. The control unit 23 then continues to decelerate vehicle 10 for a preset period of time (for example, several seconds), and after that period has elapsed, it stops decelerating vehicle 10. Furthermore, if the vehicle of interest has not moved into the vehicle's lane after a certain period of time has elapsed, the control unit 23 may control the powertrain so that the speed of vehicle 10 approaches the speed before deceleration. Similarly, if the distance between vehicle 10 and vehicle 10 after vehicle 10 has moved into the vehicle's lane in front of vehicle 10 is greater than the target inter-vehicle distance, the control unit 23 may control the powertrain so that the speed of vehicle 10 approaches the speed before deceleration. In addition, if there is space for vehicle 10 to enter the adjacent lane on the opposite side of the vehicle's lane from the adjacent lane in which vehicle 10 is traveling, the control unit 23 may control various parts of vehicle 10 to move vehicle 10 to the adjacent lane on the opposite side instead of decelerating vehicle 10.

[0037] The gaze detection unit 24 detects the driver's gaze direction in the vehicle 10 based on the in-vehicle image, and detects the driver's gaze towards the vehicle of interest based on the detected gaze direction. The driver is an example of an occupant of the vehicle 10. To this end, the gaze detection unit 24 detects the driver's gaze direction from the latest in-vehicle image at predetermined intervals (for example, each time an in-vehicle image is generated).

[0038] The gaze detection unit 24 detects the area in the in-car image where the driver's eyes are visible (hereinafter referred to as the eye region) by inputting the in-car image into a classifier that has been pre-trained to detect the driver's eyes from the in-car image. Such a classifier is configured as a DNN with a CNN-type architecture, a support vector machine, or an AdaBoost classifier. The gaze detection unit 24 may also detect the eye region from the in-car image according to other methods for detecting the eye region, such as template matching.

[0039] The gaze detection unit 24 detects the corneal reflection image of the light source (hereinafter referred to as the Purkinje image) and the centroid of the pupil (hereinafter simply referred to as the pupil centroid) from the eye region for at least one of the driver's left and right eyes as shown on the in-car image. In this case, the gaze detection unit 24 detects the Purkinje image by template matching between the Purkinje image template and the eye region. Similarly, the gaze detection unit 24 detects the pupil by template matching between the pupil template and the eye region, and the centroid of the region where the detected pupil is shown is taken as the pupil centroid. The gaze detection unit 24 then determines the positional relationship between the Purkinje image and the pupil centroid and detects the driver's gaze direction by referring to a table that shows the relationship between this positional relationship and the driver's gaze direction. Such a table may be stored in memory 12 beforehand.

[0040] Each time the gaze detection unit 24 detects the driver's gaze direction, it compares that gaze direction with the latest value of the direction from vehicle 10 to the vehicle of interest to determine whether the driver is facing the vehicle of interest. In this case, the gaze detection unit 24 determines that the driver is facing the vehicle of interest if the direction to the vehicle of interest is within a predetermined angular range centered on the gaze direction. The predetermined angular range can be, for example, the range corresponding to the effective field of view (±30 to 35° in the left and right directions). If the vehicle of interest is behind vehicle 10, the gaze detection unit 24 may determine that the driver is looking towards the vehicle of interest if the driver's gaze direction is within the angular range from the driver to the rearview mirror or to the side mirror. In this case, the gaze detection unit 24 determines the angular range from the driver to the rearview mirror by referring to a table that shows the relationship between the seat position of the driver's seat and its angular range. The gaze detection unit 24 can also identify the seat position by receiving a signal representing the seat position from the driver's seat. Furthermore, if the vehicle of interest is located to the left of vehicle 10, the gaze detection unit 24 can determine the angle range to the door mirror by referring to a table that shows the relationship between the driver's seat position and the angle range to the left door mirror. Similarly, if the vehicle of interest is located to the right of vehicle 10, the gaze detection unit 24 can determine the angle range to the door mirror by referring to a table that shows the relationship between the driver's seat position and the angle range to the right door mirror. These tables can be pre-stored in memory 12.

[0041] The gaze detection unit 24 calculates, at predetermined gaze determination periods (e.g., 1 to several seconds), the ratio of the number of times the driver was determined to be looking towards the vehicle of interest to the total number of in-vehicle images obtained during that gaze determination period. If this ratio is equal to or greater than a gaze detection threshold (e.g., 0.4 to 0.6), the gaze detection unit 24 determines that the driver was looking at the vehicle of interest during that gaze determination period.

[0042] The gaze detection unit 24 may also perform the same processing on the in-vehicle image for occupants other than the driver to determine whether or not an occupant is gazing at the vehicle of interest during each gaze determination period. If an individual in-vehicle monitor camera 3 is provided for each occupant's seating position, the gaze detection unit 24 can determine whether or not an occupant at a seating position is gazing at the vehicle of interest based on the in-vehicle image from the in-vehicle monitor camera 3 corresponding to that seating position. In this case, for in-vehicle images where no eye region is detected, the gaze detection unit 24 may determine that there is no occupant at the seating position corresponding to the in-vehicle image and may not perform gaze direction detection or gaze status determination for that seating position. Furthermore, if multiple occupants are shown in a single in-vehicle image obtained from a single in-vehicle monitor camera 3, the gaze detection unit 24 can detect the gaze direction of each occupant by detecting the eye region of each occupant for each region on the in-vehicle image corresponding to each seating position. The gaze detection unit 24 then determines whether each occupant is gazing at the vehicle of interest based on the detection results of each occupant's gaze direction.

[0043] The gaze status detection unit 24 notifies the adjustment unit 25 of the determination result (hereinafter sometimes referred to as the gaze determination result) of whether the driver and other occupants are looking at the vehicle of interest, at each gaze determination cycle. Furthermore, the gaze status detection unit 24 may also notify the adjustment unit 25 of the average value of the longitudinal distance to the vehicle of interest and the average value of the relative speed at that gaze determination cycle.

[0044] The adjustment unit 25 adjusts the interruption judgment conditions according to the gaze status of the vehicle of interest by the occupants of the vehicle 10. To this end, the adjustment unit 25 refers to the gaze judgment results of the driver for the vehicle of interest for each gaze judgment cycle. Furthermore, if gaze judgment results for the vehicle of interest have also been obtained from occupants other than the driver, the adjustment unit 25 refers to the gaze judgment results of the occupants other than the driver for the vehicle of interest for each gaze judgment cycle.

[0045] For example, if the attention determination result indicates that the driver has been continuously looking at the vehicle of interest over multiple attention determination cycles, the adjustment unit 25 will relax the interruption determination condition as the continuous attention period during which the driver has been determined to be looking at the vehicle of interest increases. In the above example, the longer the attention period, the smaller the distance threshold will be set by the adjustment unit 25. In this case, the adjustment unit 25 should add a predetermined count value each time it is notified that the driver has been determined to be looking at the vehicle of interest, and the larger the sum of these count values, the more the interruption determination condition will be relaxed. Alternatively, the adjustment unit 25 may subtract a predetermined count value from the sum of the above count values ​​each time it is notified that the driver has been determined not to be looking at the vehicle of interest. Or, the adjustment unit 25 may reset the sum of the count values ​​to 0 if it is notified a predetermined number of times that the driver has been determined not to be looking at the vehicle of interest. Therefore, even if the driver is temporarily looking at the vehicle of interest, the interruption determination condition will not be relaxed if the driver is not currently looking at the vehicle of interest. Furthermore, if the driver is not paying close attention to the vehicle in question, relatively stricter conditions will be set for determining whether an vehicle is cutting in.

[0046] Furthermore, the adjustment unit 25 may relax the interruption detection conditions as the number of occupants determined to be intently watching the vehicle of interest increases. In this case, the adjustment unit 25 calculates the sum of the above count values ​​for each occupant, and the number of occupants whose sum is equal to or greater than a predetermined gaze detection threshold is considered to be the number of occupants determined to be intently watching the vehicle of interest. This is because the longer the driver continues to gaze, and the more occupants who are intently watching the vehicle of interest, the more likely it is that the driver or other occupants will anticipate the vehicle of interest cutting in front of vehicle 10. Therefore, even if vehicle 10 actually slows down due to the relaxation of the interruption detection conditions, it will not feel unnatural to the driver or other occupants.

[0047] The adjustment unit 25 may also adjust the count value according to the distance to the vehicle of interest. For example, the adjustment unit 25 may reduce the count value in a gaze judgment period for longer gaze judgment periods with longer average distances to the vehicle of interest. This reduces the impact on the interruption judgment condition when the vehicle of interest is far from vehicle 10. Therefore, the closer the vehicle of interest is when the occupant of vehicle 10 is looking at it, the more relaxed the interruption judgment condition becomes.

[0048] Furthermore, the adjustment unit 25 may set the count value for occupants other than the driver to be lower than the count value for the driver. This is because occupants other than the driver are not necessarily paying attention to the behavior of the vehicle of interest and are intently watching it. Also, if the sum of the count values ​​for the driver is less than the attention determination threshold, that is, if the driver is not intently watching the vehicle of interest, the adjustment unit 25 may set the number of occupants determined to be intently watching the vehicle of interest for determining the interruption determination condition to 0.

[0049] Furthermore, the adjustment unit 25 may set the count value when the vehicle of interest is a special vehicle to be smaller than the count value when the vehicle of interest is a vehicle of a type other than a special vehicle. In this case, the adjustment unit 25 may set the count value when the warning light of the vehicle of interest is illuminated to be even smaller than the count value when the warning light is not illuminated. This is because, when the vehicle of interest is a special vehicle, the occupants may keep their eyes on the vehicle of interest even if they are not concerned about the vehicle cutting them off.

[0050] The adjustment unit 25 notifies the determination unit 22 of the set interrupt determination conditions.

[0051] Figure 4 is a diagram illustrating the overview of the vehicle control process according to this embodiment. In this example, it is assumed that vehicle 400, traveling in the adjacent lane from the left rear of vehicle 10, is attempting to overtake vehicle 10. The three charts shown on the right side of Figure 4, from top to bottom, represent the time changes of the speed v1 of vehicle 10 and the speed v2 of vehicle 400, the time changes of the vertical distance ld between vehicle 10 and vehicle 400, and the time changes of the acceleration of vehicle 10. In each chart, the horizontal axis represents time. The vertical axis represents speed in the top chart, vertical distance ld in the second chart from the top, and acceleration in the bottom chart. Note that a negative acceleration value indicates that vehicle 10 is decelerating. Furthermore, in the top chart, graph 401 represents the time change of the speed v1 of vehicle 10 when relatively strict interruption judgment conditions are set, and graph 402 represents the time change of the speed v1 of vehicle 10 when relatively lenient interruption judgment conditions are set. Furthermore, Graph 403 shows the time change of the speed v2 of the vehicle of interest 400. In addition, in the second chart from the top, Graph 411 shows the time change of the vertical distance ld. The distance threshold Th1 corresponds to a relatively strict interruption judgment condition, and the distance threshold Th2 corresponds to a relatively lenient interruption judgment condition. Furthermore, in the bottom chart, Graph 421 shows the time change of the acceleration of vehicle 10 when a relatively strict interruption judgment condition is set, and Graph 422 shows the time change of the acceleration of vehicle 10 when a relatively lenient interruption judgment condition is set.

[0052] In this example, since the speed v2 of vehicle 400 is faster than the speed v1 of vehicle 10, vehicle 400 approaches vehicle 10 over time, and the vertical distance ld decreases. As shown in each chart, if a relatively lenient interruption detection condition is set, for example, if the driver continues to keep an eye on vehicle 400, at time t1 the vertical distance ld becomes less than or equal to the distance threshold Th1, and vehicle 10 begins to decelerate, resulting in a decrease in the speed v1 of vehicle 10. As a result of this deceleration, the vertical distance ld decreases more rapidly after time t1 than in graph 411, and vehicle 400 overtakes vehicle 10 earlier. On the other hand, if a relatively strict interruption detection condition is set, for example, if the driver does not keep an eye on vehicle 400 at all, the vertical distance ld will not fall below the distance threshold Th2 until time t2. Therefore, vehicle 10 does not begin to decelerate until time t2, and the speed v1 of vehicle 10 remains constant. As a result, when a vehicle that the driver is not paying attention to approaches from behind, the automatic deceleration of vehicle 10 at a time unintended by the driver is suppressed.

[0053] Figure 5 is an operation flowchart of the vehicle control process executed by the processor 13. The processor 13 should execute the vehicle control process according to the following operation flowchart.

[0054] The other vehicle detection unit 21 detects the vehicle of interest traveling in an adjacent lane adjacent to the lane in which the vehicle 10 is traveling, and detects the relative behavior of the vehicle of interest with respect to the vehicle 10 (step S101). The gaze status detection unit 24 detects the gaze status of the occupants of the vehicle of interest (step S102). Then the adjustment unit 25 adjusts the interruption judgment conditions according to the gaze status of the vehicle of interest (step S103).

[0055] The determination unit 22 determines whether the relative behavior of the vehicle of interest with respect to vehicle 10 satisfies the interruption determination condition (step S104). If the interruption determination condition is met (step S104-Yes), the control unit 23 controls vehicle 10 to decelerate so that even if the vehicle of interest enters its own lane in front of vehicle 10, the distance between the vehicle of interest and vehicle 10 is maintained at or above a predetermined distance (step S105). On the other hand, if the interruption determination condition is not met (step S104-No), the control unit 23 continues the control of vehicle 10 as it was up to that point (step S106). After step S105 or S106, the processor 13 terminates the vehicle control process.

[0056] As explained above, this vehicle control device adjusts the interruption detection conditions for initiating deceleration control of the vehicle in preparation for an interruption by a vehicle in the adjacent lane, depending on the level of attention the vehicle's occupants are paying to the vehicle in question. Therefore, this vehicle control device can make it less likely for the occupants of the vehicle to feel uneasy about the vehicle's behavior when there is another vehicle that may interrupt them.

[0057] The computer program that realizes the functions of the processor 13 of the ECU4 according to the above embodiment or modification may be provided in the form of being recorded on a computer-readable portable recording medium such as semiconductor memory, magnetic recording medium, or optical recording medium.

[0058] As described above, those skilled in the art can make various modifications within the scope of the present invention to suit the implemented form. [Explanation of symbols]

[0059] 1 Vehicle control system, 10 Vehicle, 2 External sensors, 3 In-vehicle monitor camera, 4 Electronic control unit (ECU), 11 Communication interface, 12 Memory, 13 Processor, 21 Other vehicle detection unit, 22 Judgment unit, 23 Control unit, 24 Gaze status detection unit, 25 Adjustment unit

Claims

1. A vehicle detection unit detects other vehicles traveling in adjacent lanes adjacent to the lane in which the vehicle is traveling, based on external sensor signals representing a predetermined area around the vehicle, and detects the relative behavior of the other vehicles with respect to the vehicle. A determination unit that determines whether the relative behavior of the other vehicle satisfies predetermined interruption determination conditions, A control unit that decelerates the vehicle when the aforementioned behavior satisfies the interrupt determination condition, A gaze detection unit detects the gaze direction of the occupants of the vehicle based on an interior image representing the interior of the vehicle, and detects the occupants' gaze towards other vehicles based on the gaze direction detection result. An adjustment unit that adjusts the interrupt determination conditions according to the aforementioned viewing conditions, A vehicle control device having

2. The vehicle control device according to claim 1, wherein the adjustment unit relaxes the interruption determination condition as the duration of time during which the driver among the occupants is intently watching the other vehicle increases.

3. The vehicle control device according to claim 1, wherein the adjustment unit relaxes the interruption determination condition as the number of occupants of the vehicle that are watching the other vehicle increases.

4. Based on external sensor signals representing a predetermined area around the vehicle, the system detects other vehicles traveling in adjacent lanes adjacent to the lane in which the vehicle is traveling. The relative behavior of the other vehicle with respect to the vehicle itself is detected, Determine whether the relative behavior of the other vehicle satisfies the predetermined interruption determination conditions. If the aforementioned behavior satisfies the interruption determination condition, the vehicle itself will decelerate. Based on the interior image representing the interior of the vehicle, the direction of the gaze of the occupants of the vehicle is detected, and based on the detection result of the gaze direction, the state of the occupants' gaze toward the other vehicle is detected. The interrupt determination conditions are adjusted according to the aforementioned viewing status. A vehicle control method that includes the following.

5. Based on external sensor signals representing a predetermined area around the vehicle, the system detects other vehicles traveling in adjacent lanes adjacent to the lane in which the vehicle is traveling. The relative behavior of the other vehicle with respect to the vehicle itself is detected, Determine whether the relative behavior of the other vehicle satisfies the predetermined interruption determination conditions. If the aforementioned behavior satisfies the interruption determination condition, the vehicle itself will decelerate. Based on the interior image representing the interior of the vehicle, the direction of the gaze of the occupants of the vehicle is detected, and based on the detection result of the gaze direction, the state of the occupants' gaze toward the other vehicle is detected. The interrupt determination conditions are adjusted according to the aforementioned viewing status. A vehicle control computer program that causes the processor installed in the vehicle to perform the following action.

Images