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

Abstract

To provide a vehicle control device capable of suppressing discomfort given to a driver of a vehicle while controlling the vehicle so as not to cause danger even if a malfunction occurs in one of a plurality of sensors used for sensing objects present around the vehicle.SOLUTION: A vehicle control device comprises: a malfunction sensing unit 31 for sensing that a malfunction occurs in a first sensor 2 of a plurality of sensors (2, 3-1 to 3-3) which can sense objects around an own vehicle 10 and have sensing ranges at least partially overlapping each other; a detection unit 32 for detecting another vehicle traveling around the own vehicle 10, on the basis of a sensor signal from each of the plurality of sensors; and a vehicle control unit 33 for decelerating the own vehicle 10 at first deceleration in a case where the malfunction in the first sensor 2 is sensed, and where the other vehicle is sensed on the basis of a sensor signal from one of second sensors (3-1 to 3-3) having lower priority than the first sensor 2 in sensing the other vehicle cutting in front of the own vehicle 10.SELECTED DRAWING: Figure 4

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] In vehicles to which autonomous driving control can be applied, sensors detect objects around the vehicle, and the detection results are used for autonomous driving control. Therefore, if an abnormality occurs in such a sensor, it may become difficult to properly execute autonomous driving control. Therefore, a technology has been proposed that controls the vehicle to prevent accidents from occurring even if a sensor used to detect objects around the vehicle malfunctions (see Patent Document 1).

[0003] The periphery recognition device described in Patent Document 1 performs speed control to decelerate the vehicle when a specific detector among multiple detectors that detect objects present in different areas detects an abnormality.The periphery recognition device then uses information obtained from detectors other than the specific detector among the multiple detectors to infer whether an object exists in the detection area of ​​the specific detector that has been detected as abnormal. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Publication No. 2019-99051 Summary of the Invention [Problem to be solved by the invention]

[0005] If the vehicle is decelerated at a relatively strong deceleration rate every time one of the multiple sensors used to detect objects around the vehicle malfunctions, the frequency with which such deceleration control is performed increases, which may cause discomfort to the driver of the vehicle.

[0006] Therefore, the present invention aims to provide a vehicle control device that can control the vehicle so as to prevent danger even if one of multiple sensors used to detect objects around the vehicle malfunctions, while suppressing discomfort to the vehicle driver. [Means for solving the problem]

[0007] According to one embodiment, there is provided a vehicle control device including: a malfunction detection unit that detects a malfunction of a first sensor among a plurality of sensors that are capable of detecting objects around the host vehicle and have detection ranges that at least partially overlap each other; a detection unit that detects other vehicles traveling around the host vehicle based on sensor signals from each of the plurality of sensors; and a vehicle control unit that decelerates the host vehicle at a first deceleration when the malfunction of the first sensor is detected and another vehicle is detected based on a sensor signal from a second sensor among the plurality of sensors that has a lower priority than the first sensor in detecting the other vehicle cutting in front of the host vehicle.

[0008] Preferably, the vehicle control device further includes a storage unit that stores a hazard zone that includes a position within the detection range of the second sensor where there is a possibility of a collision between the host vehicle and another vehicle when the other vehicle cuts in. Preferably, when a malfunction of the first sensor is detected and the position of the detected other vehicle is within the hazard zone, the vehicle control unit decelerates the host vehicle at a second deceleration that is stronger than the first deceleration until the other vehicle and the host vehicle become equal in speed, and when a malfunction of the first sensor is detected and the position of the detected other vehicle is not within the hazard zone, the vehicle control unit decelerates the host vehicle at the first deceleration.

[0009] In this case, it is preferable that the vehicle control unit decelerates the host vehicle at a first deceleration when the speed of the host vehicle becomes equal to or lower than the speed of another vehicle located in the danger zone.

[0010] Furthermore, in this vehicle control device, it is preferable that the detection unit detects a predetermined object including another vehicle based on a sensor signal obtained from the first sensor, and the malfunction detection unit detects that the first sensor has malfunctioned when the frequency at which the predetermined object is detected by the detection unit during a predetermined period is lower than a certain level relative to an expected frequency at which the predetermined object will be detected from a series of time-series sensor signals obtained from the first sensor during the most recent predetermined period.

[0011] According to another embodiment, there is provided a vehicle control method including: detecting a malfunction of a first sensor among a plurality of sensors capable of detecting objects around the host vehicle and having at least partially overlapping detection ranges; detecting another vehicle traveling around the host vehicle based on a sensor signal from each of the plurality of sensors; and decelerating the host vehicle at a first deceleration when the malfunction of the first sensor is detected and the other vehicle is detected based on a sensor signal from a second sensor among the plurality of sensors that has a lower priority than the first sensor in detecting an intrusion of the other vehicle ahead of the host vehicle.

[0012] According to yet another embodiment, there is provided a computer program for controlling a vehicle, the computer program including instructions for causing a processor mounted on the host vehicle to execute the following: detect a malfunction of a first sensor among a plurality of sensors capable of detecting objects around the host vehicle and having detection ranges that at least partially overlap each other; detect other vehicles traveling around the host vehicle based on sensor signals from each of the plurality of sensors; and decelerate the host vehicle at a first deceleration when the malfunction of the first sensor is detected and the other vehicle is detected based on a sensor signal from a second sensor among the plurality of sensors that has a lower priority than the first sensor in detecting an intrusion of the other vehicle ahead of the host vehicle. [Effects of the Invention]

[0013] The vehicle control device according to the present disclosure has the advantage of being able to control the vehicle so as to prevent danger from occurring while suppressing discomfort to the driver of the vehicle even if any of the multiple sensors used to detect objects around the vehicle malfunctions. [Brief explanation of the drawings]

[0014] [Figure 1] 1 is a schematic configuration diagram of a vehicle control system in which a vehicle control device is implemented. [Figure 2] 3 is a schematic diagram showing an example of the relationship between the imaging range of a camera and the distance measurement ranges of each distance measurement sensor. FIG. [Figure 3] 1 is a hardware configuration diagram of an electronic control device that is one embodiment of a vehicle control device. [Figure 4] FIG. 2 is a functional block diagram of a processor of an electronic control unit related to vehicle control processing. [Figure 5] 10 is a diagram showing an example of the relationship between the position of another vehicle detected from a distance measurement signal obtained by a distance measurement sensor and the deceleration set for the vehicle when a malfunction of the camera is detected; FIG. [Figure 6] FIG. 10 is a diagram showing another example of the relationship between the position of another vehicle detected from the distance measurement signal obtained by the distance measurement sensor and the deceleration set for the vehicle when a malfunction of the camera is detected. [Figure 7] 4 is an operational flowchart of a vehicle control process. DETAILED DESCRIPTION OF THE INVENTION

[0015] A vehicle control device, a vehicle control method, and a vehicle control computer program executed by the vehicle control device will be described below with reference to the drawings. The vehicle control device detects other vehicles traveling around the host vehicle based on respective sensor signals from multiple sensors that can detect objects around the host vehicle and have at least partially overlapping detection ranges. The vehicle control device then decelerates the host vehicle when a malfunction is detected in a first sensor among the multiple sensors and another vehicle is detected based on a sensor signal from a second sensor. The second sensor has a lower priority than the first sensor in detecting an intrusion of another vehicle ahead of the host vehicle. In this way, the vehicle control device not only detects a malfunction of any of the sensors but also decelerates the host vehicle when another vehicle is detected based on a sensor signal from another sensor, thereby reducing the frequency of deceleration due to sensor malfunction. Therefore, even if one of the multiple sensors malfunctions, the vehicle control device can control the vehicle to prevent danger and reduce discomfort to the vehicle driver.

[0016] Note that the term "vehicle" is not limited to vehicles with four or more wheels, such as ordinary passenger cars and large vehicles, but also includes vehicles with fewer than four wheels, such as two-wheeled vehicles such as motorcycles and bicycles.

[0017] FIG. 1 is a schematic diagram of a vehicle control system in which a vehicle control device is implemented. The vehicle control system 1 is mounted on a vehicle 10 and controls the vehicle 10. To this end, the vehicle control system 1 includes a camera 2, three distance measurement sensors 3-1 to 3-3, a storage device 4, and an electronic control unit (ECU) 5, which is an example of a vehicle control device. The camera 2, the distance measurement sensors 3-1 to 3-3, the storage device 4, and the ECU 5 are communicatively connected via an in-vehicle network that conforms to a standard such as a controller area network. The vehicle 10 is an example of a host vehicle. The vehicle control system 1 may also include a navigation device (not shown) for searching for a planned driving route to a destination. The vehicle control system 1 may also include a GPS receiver (not shown) for determining the position of the vehicle 10. The vehicle control system 1 may also include a wireless communication terminal (not shown) for wireless communication with devices external to the vehicle 10.

[0018] Camera 2 is an example of a sensor capable of detecting objects around vehicle 10. Camera 2 has 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. Camera 2 is attached, for example, inside the passenger compartment of vehicle 10 so as to face forward of vehicle 10. Camera 2 photographs the area ahead of vehicle 10 at predetermined photographing intervals (e.g., 1 / 30 to 1 / 10 seconds) and generates an image of the area ahead. The image obtained by camera 2 is an example of a sensor signal and may be a color image or a gray image. The photographing range of camera 2 is an example of a detection range in which objects around vehicle 10 can be detected. Note that vehicle 10 may be equipped with two or more cameras with different photographing directions or focal lengths. For example, in addition to camera 2, vehicle 10 may be equipped with another camera attached facing rearward of vehicle 10. Furthermore, a camera having a focal length different from that of camera 2 may be provided to capture the area in front of vehicle 10.

[0019] Every time the camera 2 generates an image, it outputs the generated image to the ECU 5 via the in-vehicle network.

[0020] Each of the three distance measuring sensors 3-1 to 3-3 is another example of a sensor capable of detecting other objects around the vehicle 10. The distance measuring sensors 3-1 to 3-3 may be, for example, distance measuring sensors using LiDAR, radar, or sonar. The distance measuring sensors 3-1 to 3-3 generate a distance measurement signal representing the distance to an object present in each direction included in a predetermined distance measurement range around the vehicle 10 at a predetermined period. The distance measurement signal is another example of a sensor signal. The distance measurement range of each of the distance measuring sensors 3-1 to 3-3 is another example of a detection range capable of detecting objects around the vehicle 10. Each of the distance measuring sensors 3-1 to 3-3 is attached to the vehicle 10, for example, so that the distance measurement range of that sensor at least partially overlaps with the shooting area of ​​the camera 2 or the distance measurement range of another distance measuring sensor. The vehicle 10 may be provided with four or more distance measurement sensors with different distance measurement ranges, or the number of distance measurement sensors provided in the vehicle 10 may be one or two.

[0021] Each time the distance measurement sensors 3-1 to 3-3 generate a distance measurement signal, the distance measurement sensors 3-1 to 3-3 output the generated distance measurement signal to the ECU 5 via the in-vehicle network.

[0022] 2 is a schematic diagram showing an example of the relationship between the imaging range of camera 2 and the respective distance measurement ranges of distance measurement sensors 3-1 to 3-3. As shown in Fig. 2, camera 2 is attached to vehicle 10 so as to face forward of vehicle 10, and imaging range 201 of camera 2 covers the area ahead of vehicle 10. Similarly, distance measurement sensor 3-1 is attached to vehicle 10 so as to face forward of vehicle 10, and distance measurement range 202 of distance measurement sensor 3-1 covers the area ahead of vehicle 10. Therefore, imaging range 201 of camera 2 and distance measurement range 202 of distance measurement sensor 3-1 partially overlap each other.

[0023] Furthermore, the distance measurement sensor 3-2 is attached to the vehicle 10 so as to face diagonally forward to the right of the vehicle 10, and the distance measurement range 203 of the distance measurement sensor 3-2 covers a range extending from the right side of the vehicle 10 to the front of the vehicle 10. In contrast, the distance measurement sensor 3-3 is attached to the vehicle 10 so as to face diagonally forward to the left of the vehicle 10, and the distance measurement range 204 of the distance measurement sensor 3-3 covers a range extending from the left side of the vehicle 10 to the front of the vehicle 10. Therefore, the distance measurement range 203 of the distance measurement sensor 3-2 partially overlaps with the shooting range 201 of the camera 2, the distance measurement range 202 of the distance measurement sensor 3-1, and the distance measurement range 204 of the distance measurement sensor 3-3. Similarly, the distance measurement range 204 of the distance measurement sensor 3-3 partially overlaps with the shooting range 201 of the camera 2, the distance measurement range 202 of the distance measurement sensor 3-1, and the distance measurement range 203 of the distance measurement sensor 3-2.

[0024] When detecting the behavior of other vehicles traveling around the vehicle 10, using images obtained by the camera 2 provides higher accuracy than using the sensor signals of the distance measuring sensors 3-1 to 3-3. Therefore, when detecting another vehicle cutting in ahead of the vehicle 10, the priority of the camera 2 is set higher than the priority of the distance measuring sensors 3-1 to 3-3. In other words, the camera 2 is an example of a first sensor, and the distance measuring sensors 3-1 to 3-3 are examples of a second sensor.

[0025] The storage device 4 is an example of a storage unit, and includes, for example, a hard disk drive, a nonvolatile semiconductor memory, or an optical recording medium and an access device therefor. The storage device 4 stores a high-precision map, which is an example of map information. The high-precision map includes, for example, information representing road markings such as lane markings and stop lines for each road included in a predetermined area represented on the high-precision map, information representing road signs, and information representing features around the road (for example, soundproof walls, etc.).

[0026] Furthermore, the storage device 4 may have a processor for executing processes such as updating the high precision map and processing related to a request to read out a high precision map from the ECU 5. In this case, for example, the storage device 4 transmits a request to acquire a high precision map together with the current position of the vehicle 10 to a map server via a wireless communication terminal (not shown) every time the vehicle 10 moves a predetermined distance. The storage device 4 then receives a high precision map of a predetermined area around the current position of the vehicle 10 from the map server via the wireless communication terminal. Furthermore, when the storage device 4 receives a request to read out a high precision map from the ECU 5, the storage device 4 extracts an area that includes the current position of the vehicle 10 and is relatively smaller than the predetermined area from the high precision map stored therein, and outputs the extracted area to the ECU 5 via the in-vehicle network.

[0027] The ECU 5 is configured to automatically control at least the speed of the vehicle 10. Alternatively, the ECU 5 may be configured to automatically control the driving of the vehicle 10.

[0028] Fig. 3 is a hardware configuration diagram of an ECU 5, which is an example of a vehicle control device. As shown in Fig. 3, the ECU 5 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 separate circuits, or may be integrated into a single integrated circuit.

[0029] The communication interface 21 has an interface circuit for connecting the ECU 5 to the in-vehicle network. Every time the communication interface 21 receives an image from the camera 2, it passes the received image to the processor 23. Furthermore, every time the communication interface 21 receives a distance measurement signal from any of the distance measurement sensors 3-1 to 3-3, it passes the received distance measurement signal to the processor 23. Furthermore, the communication interface 21 passes the high-precision map read from the storage device 4 to the processor 23.

[0030] 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 of the ECU 5. For example, the memory 22 stores a high-precision map, parameters representing the focal length, angle of view, shooting direction, mounting position, and shooting range of the camera 2, and the ranging range and danger zone of the ranging sensors 3-1 to 3-3. The memory 22 also stores a parameter set for identifying an object detection classifier used to detect other vehicles traveling around the vehicle 10. The memory 22 also temporarily stores sensor signals such as images and ranging signals. The memory 22 also temporarily stores various data generated during the vehicle control process.

[0031] Furthermore, the memory 22 stores a danger zone for each of the distance measurement sensors 3-1 to 3-3. The danger zone is a zone within the distance measurement range of the distance measurement sensor that includes a position where there is a possibility of a collision between the vehicle 10 and another vehicle traveling around the vehicle 10 when the other vehicle cuts in front of the vehicle 10.

[0032] 2, within the measurement range 203 of the distance measuring sensor 3-2, a range 203a extending from the front to the side of the vehicle 10 is the danger range. Similarly, within the measurement range 204 of the distance measuring sensor 3-3, a range 204a extending from the front to the side of the vehicle 10 is the danger range. Furthermore, the entire measurement range 202 of the distance measuring sensor 3-1, which covers the area in front of the vehicle 10, may be set as the danger range.

[0033] The processor 23 includes one or more central processing units (CPUs) and their peripheral circuits. The processor 23 may further include other arithmetic circuits such as a logic unit, a numerical calculation unit, or a graphics processing unit. The processor 23 executes vehicle control processing for the vehicle 10.

[0034] 4 is a functional block diagram of the processor 23 related to vehicle control processing. The processor 23 has a malfunction detection unit 31, a detection unit 32, and a vehicle control unit 33. 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.

[0035] Malfunction detection unit 31 detects that camera 2 has malfunctioned. A malfunction of camera 2 refers to a state of camera 2 in which it is difficult to detect objects around vehicle 10 from images generated by camera 2. Therefore, a malfunction of camera 2 includes not only an inability of camera 2 to generate images due to a malfunction of camera 2, but also a temporary decrease in detection accuracy due to the environment around vehicle 10. Such environments include an environment in which camera 2 is backlit, an environment in which camera 2's view is obstructed by snow or rain, and the like.

[0036] The malfunction detection unit 31 determines that the camera 2 is malfunctioning when the ECU 5 cannot receive images from the camera 2 for a certain period longer than the camera 2's shooting cycle, or when the ECU 5 receives a signal from the camera 2 indicating a malfunction. Alternatively, the malfunction detection unit 31 may determine that the camera 2 is malfunctioning when an image feature that makes object detection difficult, such as blown-out highlights or crushed shadows, continues to appear in part or all of the image for a predetermined period. The predetermined period may be, for example, one second to several seconds. In this case, the malfunction detection unit 31 divides the received image into multiple blocks each time it receives an image from the camera 2 and calculates a statistical representative value, such as the average, median, or mode, of the brightness values ​​for each block. The malfunction detection unit 31 then determines that a malfunction feature has appeared when the statistical representative value of the brightness values ​​in any block is equal to or less than a crushed shadow reference value corresponding to crushed shadows, or equal to or more than a blown-out highlight reference value corresponding to blown-out highlights.

[0037] Alternatively, the malfunction detection unit 31 may determine that the camera 2 is malfunctioning if the frequency at which an object is actually detected by the detection unit 32 during a given period is lower than the expected frequency at which an object is detected in a time-series series of images acquired during that most recent period. In this case, the expected frequency at which an object is detected is pre-stored in the memory 22. Alternatively, the expected frequency may be calculated based on past detection history. For example, the malfunction detection unit 31 calculates the number of object detections per unit time over the past few hours based on the detection history as a reference detection number. Then, the malfunction detection unit 31 determines that the camera 2 is malfunctioning if the number of object detections per unit time calculated from the number of object detections during the most recent given period is less than a value obtained by multiplying the reference detection number by a predetermined coefficient less than 1 (e.g., 0.3 to 0.6). In this way, by examining the actual object detection frequency, the malfunction detection unit 31 can accurately detect malfunction of the camera 2 even if no features that would indicate a malfunction of the camera 2 appear in the images.

[0038] When the malfunction detection unit 31 determines that the camera 2 is malfunctioning, it notifies the vehicle control unit 33 that the malfunction of the camera 2 has been detected.

[0039] The detection unit 32 detects other vehicles traveling around the vehicle 10 based on the sensor signals obtained by each sensor. In this embodiment, the detection unit 32 detects other vehicles traveling around the vehicle 10 based on the images acquired from the camera 2 and the distance measurement signals acquired from each of the distance measurement sensors 3-1 to 3-3. Furthermore, the detection unit 32 may detect objects that may affect the traveling of the vehicle 10, as well as other vehicles, based on the images acquired from the camera 2 and the distance measurement signals acquired from each of the distance measurement sensors 3-1 to 3-3. Such objects include, for example, road markings such as lane markings or stop lines, various road signs, pedestrians, and structures present on or around the road, such as guardrails. Hereinafter, objects (including other vehicles) to be detected by the detection unit 32 may be referred to as target objects.

[0040] For example, the detection unit 32 detects a target object by inputting an image acquired from the camera 2 into a classifier for object detection. As such a classifier, the detection unit 32 may use a deep neural network (DNN) with a convolutional neural network (CNN) architecture, such as a Single Shot MultiBox Detector (SSD) or Faster R-CNN. Alternatively, the detection unit 32 may use a DNN with a self-attention network (SAN) architecture. Alternatively, the detection unit 32 may use a classifier based on another machine learning method, such as an AdaBoost classifier. Such a classifier is trained in advance according to a predetermined learning method, such as backpropagation, using a large number of training images depicting target objects, so as to detect target objects present around the vehicle 10 from images. The classifier outputs information identifying an object region containing the target object detected in the input image and information indicating the type of the detected object.

[0041] Furthermore, the detection unit 32 detects target objects present around the vehicle 10 based on the ranging signal. In this case, too, the detection unit 32 can detect target objects around the vehicle 10 by inputting the ranging signal to a classifier that has been trained in advance to detect target objects around the vehicle 10 from the ranging signal. The detection unit 32 can use a DNN with a CNN or SAN architecture as the classifier that detects target objects from the ranging signal. Alternatively, the detection unit 32 may detect target objects using another method for detecting objects from ranging signals.

[0042] When the detection unit 32 detects another vehicle traveling around the vehicle 10 as a target object from the distance measurement signal generated by any of the distance measurement sensors 3-1 to 3-3, it determines whether the position of the detected other vehicle is within the danger zone set for that distance measurement sensor. The detection unit 32 compares the direction toward the other vehicle detected in the distance measurement signal with the danger zone, and if that direction is within the danger zone, it determines that the position of the detected other vehicle is within the danger zone set for that distance measurement sensor. On the other hand, if that direction is not within the danger zone, the detection unit 32 determines that the position of the detected other vehicle is not within the danger zone set for that distance measurement sensor.

[0043] The detection unit 32 notifies the vehicle control unit 33 of the detection result of the target object from the image captured by the camera 2 and the detection result of the target object from the distance measurement signal from each of the distance measurement sensors 3-1 to 3-3. Furthermore, when another vehicle traveling around the vehicle 10 is detected based on the distance measurement signal obtained by any of the distance measurement sensors 3-1 to 3-3, the detection unit 32 notifies the vehicle control unit 33 of the determination result as to whether or not the position of the other vehicle is within the danger zone.

[0044] The vehicle control unit 33 controls the speed of the vehicle 10 so as to maintain the target speed set for the vehicle 10 as long as the distance between the vehicle 10 and other vehicles traveling around the vehicle 10 is equal to or greater than a predetermined distance. Furthermore, if a malfunction of the camera 2 is detected and another vehicle is detected based on the distance measurement signal generated by any of the distance measurement sensors 3-1 to 3-3, the vehicle control unit 33 controls each unit of the vehicle 10 to decelerate the vehicle 10. In particular, the vehicle control unit 33 sets a second deceleration when the position of the other vehicle detected from the distance measurement signal is within a hazard zone set for the distance measurement sensor that generated the signal to be stronger than a first deceleration when the other vehicle is not within the hazard zone. Note that the first deceleration may be, for example, 0.1 G to 0.2 G, and the second deceleration may be 0.35 G. If the position of the detected other vehicle is within the hazard zone, the vehicle control unit 33 continues decelerating the vehicle 10 at the set deceleration until the speed of the vehicle 10 becomes equal to the speed of the other vehicle. Then, when the speed of vehicle 10 decreases to the same speed as or slower than the speed of the other vehicle, vehicle control unit 33 decelerates vehicle 10 at the first deceleration. Note that if the speed of the other vehicle is equal to or faster than the speed of vehicle 10 at the time the other vehicle is detected, vehicle control unit 33 may decelerate vehicle 10 at the first deceleration regardless of whether the other vehicle is within the danger zone. In this way, by decelerating vehicle 10 at a relatively strong deceleration only when there is a risk of collision due to the cut-in of the detected other vehicle, vehicle control unit 33 can prevent a collision between vehicle 10 and the other vehicle while further reducing the frequency of strong deceleration control.

[0045] When the change over time in the direction and distance from vehicle 10 to another vehicle, which are indicated by multiple distance measurement signals obtained in a time series from one distance measurement sensor, becomes equal to or less than a predetermined amount, vehicle control unit 33 determines that vehicle 10 and another vehicle have become equal in speed. Furthermore, when the direction from vehicle 10 to another vehicle shifts forward of vehicle 10 over time, vehicle control unit 33 determines that another vehicle is faster than vehicle 10. Alternatively, when the other vehicle is located ahead of a direction perpendicular to the traveling direction of vehicle 10 and the distance from vehicle 10 to the other vehicle increases over time, vehicle control unit 33 may determine that the other vehicle is faster than vehicle 10. Alternatively, when the other vehicle is located behind a direction perpendicular to the traveling direction of vehicle 10 and the distance from vehicle 10 to the other vehicle decreases over time, vehicle control unit 33 may determine that the other vehicle is faster than vehicle 10.

[0046] The vehicle control unit 33 sets the accelerator opening or braking amount so as to achieve the set deceleration. The vehicle control unit 33 then 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 vehicle control unit 33 controls a power supply device to a motor for driving the vehicle 10 so as to supply power corresponding to the set accelerator opening to the motor. Alternatively, the vehicle control unit 33 outputs a control signal corresponding to the set braking amount to the brake of the vehicle 10.

[0047] FIG. 5 is a diagram showing an example of the relationship between the position of another vehicle detected from the distance measurement signal obtained by the distance measurement sensor and the deceleration set for the vehicle 10 when a malfunction of the camera 2 is detected.

[0048] 5, a malfunction of the camera 2 is detected. In addition, another vehicle 510 is detected at a position outside the danger zone 501a within the distance measurement range 501 of the distance measurement sensor 3-2 mounted on the vehicle 10. Therefore, a relatively weak first deceleration is set for the vehicle 10.

[0049] FIG. 6 is a diagram showing another example of the relationship between the position of another vehicle detected from the distance measurement signal obtained by the distance measurement sensor and the deceleration set for the vehicle 10 when a malfunction of the camera 2 is detected.

[0050] 6, a malfunction of the camera 2 is also detected. In this example, another vehicle 510 is detected within the danger zone 501a within the distance measurement range 501 of the distance measurement sensor 3-2 mounted on the vehicle 10. Therefore, a relatively strong second deceleration is set for the vehicle 10.

[0051] Furthermore, if a malfunction of the camera 2 is detected and another vehicle is detected based on the ranging signal generated by any of the ranging sensors 3-1 to 3-3, the vehicle control unit 33 may request the driver of the vehicle 10 to transfer control of the vehicle 10 to the driver. Hereinafter, a request to transfer control of the vehicle 10 to the driver may be referred to as a driving change request. In this case, the vehicle control unit 33 displays a message or icon representing the driving change request on a display device of a user interface (not shown) provided in the cabin of the vehicle 10, or turns on or blinks a light source corresponding to the notification of the driving change request. Alternatively, the vehicle control unit 33 outputs an audio signal representing the driving change request to a speaker of the user interface. Alternatively, the vehicle control unit 33 vibrates a vibration device of the user interface according to a vibration type (vibration period or vibration intensity) corresponding to the notification of the driving change request. In addition, if the user interface has two or more of the above devices, the vehicle control unit 33 may notify the driver of a request to take over driving via each or any of the two or more devices.

[0052] After notifying the driver of the driving change request, the vehicle control unit 33 continues to decelerate the vehicle 10 until the driver performs a driving operation or the vehicle 10 stops. Note that the vehicle control unit 33 determines that the driver has performed a driving operation when the accelerator or brake is depressed by a predetermined amount or more. Alternatively, the vehicle control unit 33 may determine that the driver has performed a driving operation when it detects via a touch sensor provided on the steering wheel that the driver has held the steering wheel or when the force applied to the steering wheel reaches a predetermined amount or more.

[0053] Furthermore, if no malfunction of the camera 2 is detected, the vehicle control unit 33 controls the speed of the vehicle 10 so as to maintain a target speed set for the vehicle 10 as long as the distance between the vehicle 10 and a moving object traveling around the vehicle 10 is equal to or greater than a predetermined distance. The target speed is set, for example, by operating a speed setting button provided in the vehicle cabin. Alternatively, the target speed may be set to the speed limit or legal speed of the road on which the vehicle 10 is traveling. In this case, the vehicle control unit 33 identifies the road on which the vehicle 10 is traveling by referring to the current position of the vehicle 10 measured by a GPS receiver (not shown) provided in the vehicle 10 and a high-precision map. The vehicle control unit 33 then sets the target speed to the speed limit or legal speed set for the road on which the vehicle 10 is traveling, as shown on the high-precision map.

[0054] Furthermore, when a moving object (including another vehicle) is detected from the image acquired by camera 2 or the distance measurement signals acquired by distance sensors 3-1 to 3-3, vehicle control unit 33 controls the speed of vehicle 10 so that the distance between the detected moving object and vehicle 10 is equal to or greater than a predetermined distance. In particular, when the detected moving object is located in the lane in which vehicle 10 is traveling and traveling ahead of vehicle 10, vehicle control unit 33 controls the speed of vehicle 10 so that the distance between the moving object and vehicle 10 is equal to or greater than a predetermined distance. To this end, vehicle control unit 33 determines whether a moving object detected from an image generated by camera 2 is traveling in the current lane based on the position of the moving object on the image. For example, vehicle control unit 33 identifies the lane markings closest to vehicle 10 on each of the left and right sides of vehicle 10 from among the multiple lane markings detected on the image by detection unit 32 as those that define the current lane. If the lower end of the object area in which the moving object is represented is included in the area between the two lane markings that define the own lane, the vehicle control unit 33 determines that the moving object is traveling in the own lane. On the other hand, if the lower end of the object area in which the moving object is represented is outside the area between the two lane markings that define the own lane, the vehicle control unit 33 determines that the moving object is traveling in a lane other than the own lane. Furthermore, if a moving object is detected by a ranging signal from any ranging sensor, the vehicle control unit 33 may determine that the moving object is traveling in the own lane if the difference between the direction toward the detected moving object and the traveling direction of the vehicle 10 is less than a predetermined angle difference.

[0055] Furthermore, the vehicle control unit 33 determines whether a detected moving object in front of the vehicle 10 will cut into the vehicle's own lane. If it determines that the moving object will cut into the vehicle's own lane, it controls the speed of the vehicle 10 so that the distance between the moving object and the vehicle 10 is equal to or greater than a predetermined distance. In this case, if the same moving object is detected in both the image captured by the camera 2 and the ranging signal from one of the ranging sensors, the vehicle control unit 33 prioritizes the image when determining whether to cut in. Note that the position of the moving object on the image corresponds one-to-one to the orientation of the moving object as seen from the camera 2. Furthermore, the position of the bottom edge of the object area in which the moving object is represented on the image is estimated to represent the position where the moving object is in contact with the road surface. Therefore, the vehicle control unit 33 can estimate the orientation of the vehicle 10 toward the moving object and the distance between the vehicle 10 and the moving object based on the position of the bottom edge of the object area in which the moving object is represented and parameters such as the shooting direction and mounting position of the camera 2. Therefore, the vehicle control unit 33 compares the estimated direction from the vehicle 10 to the moving object and the distance between the vehicle 10 and the moving object with the direction to the moving object and the distance to the moving object detected in the ranging signal. If the difference between the two is equal to or less than a predetermined amount, the vehicle control unit 33 determines that the moving object detected from the image by the camera 2 and the moving object detected from the ranging signal of one of the ranging sensors are the same.

[0056] The vehicle control unit 33 determines that a moving object will cut into the current lane when the bottom edge of the object area representing the moving object intersects with a lane marking that divides the current lane. Alternatively, the vehicle control unit 33 may input the object area representing a moving object determined to be traveling in a lane other than the current lane to an indicator classifier that identifies the lighting status of the turn signal. In this way, the vehicle control unit 33 may determine whether the turn signal provided on the moving object is flashing. Then, the vehicle control unit 33 determines that the moving object will cut into the current lane when the turn signal on the current lane side is flashing. Note that the vehicle control unit 33 may use a CNN-type DNN or a recurrent neural network (RNN) as the indicator classifier. When an RNN is used as the indicator classifier, the vehicle control unit 33 may input the object areas detected from each of the multiple images obtained in time series to the indicator classifier in chronological order. In this case, the vehicle control unit 33 may use a tracking method such as the KLT method to associate object regions that represent the same moving object detected across multiple images.

[0057] Furthermore, for a moving object that is not detected in an image captured by the camera 2 but is detected from a ranging signal from one of the ranging sensors, the vehicle control unit 33 determines whether the moving object will cut into the vehicle's own lane based on the direction of the moving object and the distance to the moving object. For example, the vehicle control unit 33 determines that the moving object will cut into the vehicle's own lane when the angular difference between the direction of the detected moving object and the traveling direction of the vehicle 10 is equal to or smaller than a predetermined angle and the distance to the moving object is equal to or smaller than a predetermined threshold distance.

[0058] If the distance to a moving object traveling in front of the vehicle 10 or a moving object cutting in front of the vehicle 10 is equal to or greater than a predetermined distance, the vehicle control unit 33 controls each unit of the vehicle 10 so that the speed of the vehicle 10 becomes a target speed. On the other hand, if the distance to the moving object is less than the predetermined distance, the vehicle control unit 33 controls each unit of the vehicle 10 so as to decelerate the vehicle 10. In this case, the vehicle control unit 33 may increase the deceleration as the distance to the moving object becomes shorter. However, the vehicle control unit 33 sets the deceleration so that it is equal to or less than a predetermined upper limit deceleration.

[0059] 7 is an operational flowchart of the vehicle control process executed by the processor 23. The processor 23 executes the vehicle control process at predetermined intervals in accordance with the following operational flowchart.

[0060] The detection unit 32 of the processor 23 detects target objects including other vehicles traveling around the vehicle 10 based on the image obtained by the camera 2 and the distance measurement signals obtained by the distance measurement sensors 3-1 to 3-3 (step S101). Furthermore, the malfunction detection unit 31 of the processor 23 determines whether or not a malfunction of the camera 2 has been detected (step S102).

[0061] If no malfunction of the camera 2 is detected (step S102-No), the vehicle control unit 33 of the processor 23 controls the vehicle 10 to maintain the target speed as long as a predetermined distance can be maintained between the detected target object, particularly a moving object, and the vehicle 10 (step S103).

[0062] On the other hand, if a malfunction of the camera 2 is detected (step S102-Yes), the vehicle control unit 33 determines whether or not another vehicle traveling around the vehicle 10 has been detected from the distance measurement signal of any of the distance measurement sensors 3-1 to 3-3 by the detection unit 32 (step S104). If another vehicle has not been detected from the distance measurement signal of any of the distance measurement sensors (step S104-No), the vehicle control unit 33 executes the process of step S103.

[0063] On the other hand, if another vehicle is detected from the distance measurement signal of any of the distance measurement sensors 3-1 to 3-3 (step S104-Yes), the vehicle control unit 33 determines whether the detected other vehicle is within the danger zone (step S105).If the detected other vehicle is not within the danger zone (step S105-No), the vehicle control unit 33 decelerates the vehicle 10 at a relatively weak first deceleration (step S106).

[0064] On the other hand, if the detected other vehicle is within the danger zone (step S105-Yes), the vehicle control unit 33 decelerates the vehicle 10 at a relatively strong second deceleration until the other vehicle and the vehicle 10 become equal in speed (step S107).

[0065] After step S106 or step S107, the vehicle control unit 33 notifies the driver of a driving change request via a user interface provided in the vehicle cabin (step S108). Note that the vehicle control unit 33 may execute the process of step S108 together with the process of step S106 or step S107.

[0066] After step S103 or step S108, processor 23 ends the vehicle control process.

[0067] As described above, this vehicle control device detects other vehicles traveling around the host vehicle using the first sensor, which has a relatively high priority in detecting other vehicles cutting in ahead of the host vehicle, and the second sensor, which has a relatively low priority. Furthermore, this vehicle control device decelerates the host vehicle when a malfunction of the first sensor is detected and another vehicle is detected based on the sensor signal of the second sensor.

[0068] According to a modified example, the malfunction detection unit 31 may detect malfunctions of the distance measurement sensors 3-1 to 3-3 in addition to malfunctions of the camera 2. For example, if the malfunction detection unit 31 cannot receive a distance measurement signal from any of the distance measurement sensors for a predetermined period of time or longer, or if it receives a signal indicating a malfunction, the malfunction detection unit 31 may determine that the distance measurement sensor has malfunctioned. If the vehicle control unit 33 detects a malfunction of any of the distance measurement sensors but does not detect a malfunction of the camera 2, the vehicle control unit 33 may notify a driver change request via the user interface without controlling the deceleration of the vehicle 10.

[0069] A computer program that realizes the functions of the processor 23 of the ECU 5 according to the above embodiment or variant 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.

[0070] 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]

[0071] 1. Vehicle control system 10 vehicles 2 Cameras 3-1~3-3 Distance measurement sensor 4. Storage devices 5 Electronic Control Unit (ECU) 21 Communication Interface 22 Memory 23 processors 31 Malfunction detection unit 32 Detection unit 33 Vehicle control unit

Claims

1. a malfunction detection unit that detects that a first sensor among a plurality of sensors capable of detecting objects around the host vehicle and having detection ranges that at least partially overlap each other has malfunctioned, and that a second sensor among the plurality of sensors that has a lower priority than the first sensor in detecting an intrusion of another vehicle traveling around the host vehicle ahead of the host vehicle has malfunctioned; a detection unit that detects the other vehicle based on sensor signals from each of the plurality of sensors; a storage unit that stores a danger zone that includes a position within the detection zone of the second sensor where there is a possibility of a collision between the other vehicle and the host vehicle when the other vehicle cuts in; a vehicle control unit that, when a malfunction of the first sensor is detected and the other vehicle is detected based on a sensor signal from the second sensor, decelerates the host vehicle at a first deceleration if the position of the detected other vehicle is not within the danger zone, and decelerates the host vehicle at a second deceleration that is stronger than the first deceleration if the position of the detected other vehicle is within the danger zone until the other vehicle and the host vehicle become equal in speed; and, when a malfunction of the first sensor is not detected and a malfunction of the second sensor is detected, notifies the driver of the host vehicle of a driving change request via a user interface provided in the host vehicle; A vehicle control device having the above.

2. 2. The vehicle control device according to claim 1, wherein the vehicle control unit decelerates the host vehicle at the first deceleration when the speed of the host vehicle becomes equal to or lower than the speed of the other vehicle located at a position included in the danger zone.

3. the detection unit detects a predetermined object including the other vehicle based on the sensor signal obtained from the first sensor; 3. The vehicle control device according to claim 1, wherein the malfunction detection unit detects that the first sensor has malfunctioned when the frequency at which the specified object is detected by the detection unit during a specified period is lower than a certain level compared to an expected value of the frequency at which the specified object is detected from a time-series series of sensor signals obtained from the first sensor during the most recent specified period.

4. Detecting that a first sensor among a plurality of sensors capable of detecting objects around the host vehicle and having detection ranges that at least partially overlap each other has malfunctioned, and that a second sensor among the plurality of sensors that has a lower priority than the first sensor in detecting an intrusion of another vehicle traveling around the host vehicle ahead of the host vehicle has malfunctioned, Detecting other vehicles traveling around the host vehicle based on the sensor signals from each of the plurality of sensors; When a malfunction of the first sensor is detected and the other vehicle is detected based on a sensor signal from the second sensor, if the position of the detected other vehicle is not within a danger zone within the detection range of the second sensor that includes a position where there is a possibility of a collision between the other vehicle and the host vehicle when the other vehicle cuts in, the host vehicle is decelerated at a first deceleration, and if the position of the detected other vehicle is within the danger zone, the host vehicle is decelerated at a second deceleration that is stronger than the first deceleration until the other vehicle and the host vehicle become equal in speed; If a malfunction of the first sensor is not detected and a malfunction of the second sensor is detected, notifying the driver of the host vehicle of a request to take over driving via a user interface provided in the host vehicle. A vehicle control method comprising:

5. Detecting that a first sensor among a plurality of sensors capable of detecting objects around the host vehicle and having detection ranges that at least partially overlap each other has malfunctioned, and that a second sensor among the plurality of sensors that has a lower priority than the first sensor in detecting an intrusion of another vehicle traveling around the host vehicle ahead of the host vehicle has malfunctioned, Detecting other vehicles traveling around the host vehicle based on the sensor signals from each of the plurality of sensors; When a malfunction of the first sensor is detected and the other vehicle is detected based on a sensor signal from the second sensor, if the position of the detected other vehicle is not within a danger zone within the detection range of the second sensor that includes a position where there is a possibility of a collision between the other vehicle and the host vehicle when the other vehicle cuts in, the host vehicle is decelerated at a first deceleration, and if the position of the detected other vehicle is within the danger zone, the host vehicle is decelerated at a second deceleration that is stronger than the first deceleration until the other vehicle and the host vehicle become equal in speed; If a malfunction of the first sensor is not detected and a malfunction of the second sensor is detected, notifying the driver of the host vehicle of a request to take over driving via a user interface provided in the host vehicle. A computer program for vehicle control that causes a processor mounted on the vehicle to execute the above.

Images