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

Abstract

To provide a vehicle control device capable of appropriately ensuring a distance allowing sensing behind a vehicle.SOLUTION: A vehicle control device comprises: a detection unit 31 for detecting another vehicle traveling behind an own vehicle 10, on the basis of a sensor signal obtained by each of sensors (3-1, 3-2) for sensing a situation around the own vehicle 10; and a vehicle control unit 34 for determining whether the other vehicle detected satisfies an obstructing condition under which view behind the own vehicle 10 is obstructed, and controlling the own vehicle 10 so as to ensure the view behind the own vehicle 10 when the obstructing condition is satisfied.SELECTED DRAWING: Figure 3

Description

Technical Field

[0001] The present invention relates to a vehicle control device, a vehicle control method, and a vehicle control computer program for automatically controlling the driving of a vehicle.

Background Art

[0002] Technologies for automatically controlling the driving of a vehicle based on the behavior of other vehicles traveling around the host vehicle have been researched (see, for example, Patent Document 1).

[0003] The vehicle control device described in Patent Document 1 detects another vehicle approaching from behind or the side of the host vehicle based on surrounding information of the host vehicle, and controls the avoidance operation of the host vehicle based on the detected other vehicle. When the same other vehicle is detected a predetermined number of times or more within a predetermined time, or when the same other vehicle is detected for a predetermined time or more, the vehicle control device suppresses a new avoidance operation.

Prior Art Literature

Patent Literature

[0004]

Patent Document 1

Summary of the Invention

Problem to be Solved by the Invention

[0005] Even when a vehicle is under automatic driving control, the vehicle is required to comply with laws and regulations defined for vehicle travel. In particular, when an emergency vehicle travels around a vehicle under automatic driving control, it is required to control the vehicle so as not to interfere with the travel of the emergency vehicle. However, large vehicles may travel around the vehicle under automatic driving control. Additionally, there may be other vehicles traveling with a reduced inter-vehicle distance from the vehicle under automatic driving control. In such cases, the visibility around the vehicle under automatic driving control, particularly behind the vehicle, may be blocked, making it impossible to sufficiently monitor the surroundings of the vehicle.

[0006] Therefore, the present invention aims to provide a vehicle control device that can appropriately secure a detectable distance behind the vehicle. [Means for solving the problem]

[0007] According to one embodiment, a vehicle control device is provided. This vehicle control device includes a detection unit that detects a large vehicle traveling behind the vehicle and the lane in which the detected large vehicle is traveling, based on sensor signals obtained from a sensor that detects the conditions around the vehicle, and a unit that determines whether or not the area around the vehicle will be congested within a predetermined period from the present time to a predetermined time in the future. In addition, if it determines that congestion is occurring around the vehicle, it predicts when that congestion will occur. It has a traffic congestion prediction unit and a vehicle control unit.

[0008] If the vehicle control unit determines that congestion will occur around the vehicle within a predetermined period, and that the lane the vehicle is currently traveling in is the same lane in which the detected large vehicle is traveling, then the vehicle Check The large vehicle that pulled out moved into a lane that was not currently occupied. The lane change to be made is completed before traffic congestion occurs around the vehicle where it is anticipated. It is preferable to control the vehicle in such a manner.

[0009] In this case, the vehicle control unit is If it is determined that congestion will occur around your vehicle within a specified period, and the lane in which your vehicle is traveling is the same lane in which a large vehicle is traveling, Based on the map information stored in the memory unit, the planned route to the vehicle's destination, and the vehicle's current location, the system identifies the lane on the road the vehicle is currently traveling in that can reach the destination. , special fixed Reaching the destination If your lane is different from the lane the large vehicle is traveling in, move your vehicle into the designated lane. Before the predicted time when traffic congestion will occur around your vehicle Move it, one side , special fixed The lane that allows you to reach your destination is the same lane that a large vehicle is traveling in. In that case, In a different lane from the one the large vehicle is traveling in, Change lanes to the lane that requires a lane change to reach your destination. Before the predicted time when traffic congestion will occur around your vehicle It is preferable to control your vehicle to move it.

[0010] Furthermore, in this vehicle control device, The detection unit further detects other vehicles, other than large vehicles, traveling behind its own vehicle based on the sensor signal. The vehicle control unit, in each of the multiple lanes included in the road on which the vehicle is traveling, Large vehicles and Multiple other vehicles were detected. beIn this case, when your vehicle changes lanes among multiple lanes... In the lane your vehicle is traveling in after changing lanes It is preferable to control your vehicle to move it to the lane where the largest number of other vehicles are expected to be positioned between you and the large vehicle.

[0011] Alternatively, it is preferable that the vehicle control device further includes a distance estimation unit that estimates the distance between the vehicle and a vehicle traveling behind it in the same lane, among other detected vehicles. In this vehicle control device, it is preferable that the detection unit further detects lane markings that demarcate the vehicle's lane, and the vehicle control unit controls the position of the vehicle such that, when the estimated distance is less than or equal to a predetermined distance threshold, the lateral distance from the vehicle's position in the transverse direction of the lane to the lane markings is smaller than the lateral distance when the estimated distance is greater than the predetermined distance threshold.

[0012] In this case, the vehicle control unit refers to the map information and the current position of the vehicle to determine whether there is a shoulder on the road the vehicle is traveling on and whether there are two lanes in the direction the vehicle is traveling on that road. If there is no shoulder on that road and there are two lanes in the direction the vehicle is traveling on that road, it is preferable to control the position of the vehicle so that the lateral distance to the lane marking on the center side is shorter than the lateral distance to the lane marking on the edge side of the road.

[0013] Alternatively, if the vehicle control unit is traveling in a lane adjacent to a merging lane, it is preferable to control the vehicle's position such that the lateral distance to the lane marking on the merging lane side is smaller than the lateral distance to the lane marking on the opposite side of the merging lane.

[0014] Another embodiment provides a vehicle control method. This vehicle control method detects a large vehicle traveling behind the vehicle based on sensor signals obtained from sensors mounted on the vehicle that detect the conditions around the vehicle, detects the lane in which the detected large vehicle is traveling, and determines whether or not the area around the vehicle will be congested within a predetermined period from the present time to a predetermined time in the future. In addition, if it determines that congestion is occurring around the vehicle, it predicts the timing of that congestion.and, when it is determined that congestion will occur around the host vehicle within a predetermined period, and the own lane on which the host vehicle is traveling is the same as the lane on which the detected large vehicle is traveling, the host vehicle Check to a lane in which the detected large vehicle is not traveling The lane change to be made is completed before traffic congestion occurs around the vehicle where it is anticipated. controlling the host vehicle in this manner.

[0015] According to still another embodiment, a computer program for vehicle control is provided. This vehicle control computer program detects a large vehicle traveling behind the host vehicle based on sensor signals obtained by a sensor mounted on the host vehicle that detects surrounding conditions of the host vehicle, detects the lane on which the detected large vehicle is traveling, and determines whether congestion will occur around the host vehicle within a predetermined period from the current time to a time point a predetermined time ahead In addition, if it determines that congestion is occurring around the vehicle, it predicts the timing of that congestion. and, when it is determined that congestion will occur around the host vehicle within a predetermined period, and the own lane on which the host vehicle is traveling is the same as the lane on which the detected large vehicle is traveling, the host vehicle Check to a lane in which the detected large vehicle is not traveling The lane change to be made is completed before traffic congestion occurs around the vehicle where it is anticipated. comprises instructions for causing a processor mounted on the host vehicle to execute controlling the host vehicle in this manner.

Effects of the Invention

[0016] The vehicle control device according to the present invention produces the effect that an appropriately detectable distance can be secured behind the vehicle.

Brief Description of Drawings

[0017] [Figure 1] FIG. 1 is a schematic configuration diagram of a vehicle control system in which a vehicle control device is implemented. [Figure 2] FIG. 2 is a hardware configuration diagram of an electronic control device which is one embodiment of the vehicle control device. [Figure 3] FIG. 3 is a functional block diagram of a processor of the electronic control device related to vehicle control processing. [Figure 4] FIG. 4 is a diagram showing an example of control of the host vehicle when a large vehicle traveling behind the host vehicle is detected. [Figure 5]This diagram shows an example of vehicle control when the distance between your vehicle and another vehicle traveling behind it is short. [Figure 6] This is an operation flowchart of the vehicle control process. [Modes for carrying out the invention]

[0018] The following describes the vehicle control device, the vehicle control method implemented by the vehicle control device, and the vehicle control computer program, with reference to the diagrams. This vehicle control device detects other vehicles traveling behind its own vehicle based on sensor signals obtained from sensors mounted on the vehicle that detect the surrounding conditions. The vehicle control device then determines whether the detected other vehicle meets the occlusion conditions that obstruct the view behind the vehicle, and if the occlusion conditions are met, it controls the vehicle to ensure the view behind the vehicle.

[0019] In this embodiment, the vehicle control device is capable of applying Level 2 automated driving control, as defined by the Society of Automotive Engineers (SAE), to its own vehicle. That is, the vehicle control device is capable of automated driving control of its own vehicle, provided that the driver monitors the area around the vehicle. Furthermore, the vehicle control device may be capable of applying Level 3 automated driving control to its own vehicle under certain conditions, such as when the area around the vehicle is congested. That is, the vehicle control device may be capable of automated driving control of its own vehicle even when the driver is not monitoring the area around the vehicle when the area is congested.

[0020] 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 device, which is one embodiment of the vehicle control device. In this embodiment, the vehicle control system 1, which is mounted on and controls the vehicle 10, includes a GPS receiver 2, two cameras 3-1 and 3-2, a wireless communication terminal 4, a storage device 5, and an electronic control unit (ECU) 6, which is an example of a vehicle control device. The GPS receiver 2, cameras 3-1 and 3-2, wireless communication terminal 4, storage device 5, and ECU 6 are connected to each other via an in-vehicle network compliant with standards such as a controller area network. Vehicle 10 is an example of the vehicle itself. The vehicle control system 1 may also have a distance sensor (not shown) such as LiDAR or radar that measures the distance from the vehicle 10 to objects in the vicinity of the vehicle 10. Such a distance sensor is an example of a sensor capable of detecting other objects in the vicinity of the vehicle 10. Furthermore, the vehicle control system 1 may have a navigation device (not shown) for searching for a planned route to a destination.

[0021] The GPS receiver 2 receives GPS signals from GPS satellites at predetermined intervals and determines the vehicle's position based on the received GPS signals. At predetermined intervals, the GPS receiver 2 outputs positioning information representing the vehicle's position based on the GPS signals to the ECU 6 via the in-vehicle network. The vehicle 10 may also have a receiver compliant with a satellite positioning system other than the GPS receiver 2. In this case, that receiver is responsible for determining the vehicle's position.

[0022] Cameras 3-1 and 3-2 are examples of sensors capable of detecting other objects around the vehicle 10. Each camera 3-1 and 3-2 has a two-dimensional detector composed of an array of photoelectric conversion elements sensitive to visible light, such as a CCD or C-MOS, and an imaging optical system that forms an image of the area to be photographed on the two-dimensional detector. Camera 3-1 is mounted, for example, inside the vehicle 10 so as to face forward of the vehicle 10. Camera 3-2, on the other hand, is mounted, for example, inside the vehicle 10 so as to face rearward of the vehicle 10. Cameras 3-1 and 3-2 each photograph the front or rear area of ​​the vehicle 10 at predetermined shooting cycles (e.g., 1 / 30 second to 1 / 10 second) and generate an image of that front or rear area. The images obtained by cameras 3-1 and 3-2 are examples of sensor signals and may be color images or grayscale images. Vehicle 10 may be equipped with three or more cameras with different shooting directions or focal lengths.

[0023] Cameras 3-1 and 3-2 each output the generated image to ECU6 via the in-vehicle network each time they generate an image.

[0024] The wireless communication terminal 4 communicates wirelessly with the wireless base station in accordance with a predetermined mobile communication standard. The wireless communication terminal 4 then receives traffic information (for example, information from the Vehicle Information and Communication System, VICS®) from other devices via the wireless base station, representing the traffic conditions on or around the road on which the vehicle 10 is traveling. The wireless communication terminal 4 outputs the received traffic information to the ECU 6 via the in-vehicle network. The traffic information includes, for example, information on sections where congestion occurs, road construction, accidents, or traffic restrictions, and information on the location and time when road construction, accidents, or traffic restrictions are in place. The wireless communication terminal 4 may also receive a high-precision map used for automatic driving control of a predetermined area around the current location of the vehicle 10 from a map server via the wireless base station, and output the received high-precision map to the storage device 5.

[0025] The storage device 5 is an example of a storage unit and includes, for example, a hard disk drive, a non-volatile semiconductor memory, or an optical recording medium and its access device. The storage device 5 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 or 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 roads (for example, sound barriers).

[0026] Furthermore, the storage device 5 may have a processor for performing processes such as updating high-precision maps and processing requests for reading high-precision maps from the ECU 6. In this case, for example, each time the vehicle 10 moves a predetermined distance, the storage device 5 sends a request to acquire a high-precision map to the map server via the wireless communication terminal 4, along with the current location of the vehicle 10. The storage device 5 then receives a high-precision map from the map server via the wireless communication terminal 4 for a predetermined area around the current location of the vehicle 10. Also, when the storage device 5 receives a request to read a high-precision map from the ECU 6, it extracts a range from the stored high-precision map that includes the current location of the vehicle 10 and is relatively smaller than the predetermined area, and outputs it to the ECU 6 via the in-vehicle network.

[0027] The ECU 6 detects other vehicles traveling around vehicle 10 and controls the movement of vehicle 10 based on the other vehicles it detects.

[0028] As shown in Figure 2, the ECU 6 includes 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 they may be integrated as a single integrated circuit.

[0029] The communication interface 21 has an interface circuit for connecting the ECU 6 to the in-vehicle network. Whenever the communication interface 21 receives positioning information from the GPS receiver 2, it passes that positioning information to the processor 23. Also, whenever the communication interface 21 receives images from cameras 3-1 and 3-2, it passes the received images to the processor 23. Furthermore, the communication interface 21 passes the high-precision map read from the storage device 5 to the processor 23.

[0030] Memory 22 is another example of a storage unit and includes, for example, volatile semiconductor memory and non-volatile semiconductor memory. Memory 22 stores various data used in vehicle control processing executed by the processor 23 of the ECU 6. For example, memory 22 stores parameters representing high-precision maps, focal length, field of view, shooting direction, and mounting position of cameras 3-1 and 3-2, and a parameter set for identifying an object detection classifier used to detect other vehicles traveling around vehicle 10. Furthermore, memory 22 temporarily stores sensor signals such as images of the vehicle 10's surroundings generated by camera 3-1 or camera 3-2, and the positioning results of the GPS receiver 2. In addition, memory 22 temporarily stores various data generated during vehicle control processing.

[0031] The processor 23 has one or more CPUs (Central Processing Units) and their peripheral circuits. The processor 23 may further have other arithmetic circuits such as a logic unit, a numerical unit, or a graphics processing unit. The processor 23 then performs vehicle control processing for the vehicle 10.

[0032] Figure 3 is a functional block diagram of the processor 23 related to vehicle control processing. The processor 23 includes a detection unit 31, a traffic congestion prediction unit 32, a distance estimation unit 33, and a vehicle control unit 34. Each of these parts of the processor 23 is, for example, a functional module realized by a computer program running on the processor 23. Alternatively, each of these parts of the processor 23 may be a dedicated arithmetic circuit provided on the processor 23.

[0033] The detection unit 31 detects other vehicles around the vehicle 10 based on the image acquired by the ECU 6 each time the ECU 6 acquires an image from camera 3-1 or camera 3-2.

[0034] For example, the detection unit 31 detects other vehicles traveling around vehicle 10 by inputting the image to a classifier whenever the ECU 6 acquires an image from camera 3-1 or camera 3-2. As such a classifier, the detection unit 31 can 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. Such a classifier is pre-trained to detect other objects to be detected present around vehicle 10 from the image (e.g., passenger cars, heavy vehicles, motorcycles, pedestrians, road markings such as lane markings, road signs, etc.). The classifier outputs information that identifies the object region containing the detected object on the input image and information that represents the type of detected object (passenger car, heavy vehicle, motorcycle, pedestrian, road markings, road signs, etc.). In this embodiment, since camera 3-2 is positioned to photograph the area behind vehicle 10, other vehicles shown in the image acquired from camera 3-2 (hereinafter referred to as the rear image) are rear vehicles traveling behind vehicle 10. Therefore, the detection unit 31 identifies other vehicles detected by inputting the rear image into the classifier as rear vehicles. In particular, by inputting the rear image into the classifier, the detection unit 31 detects vehicles classified as large vehicles by the classifier as large vehicles traveling behind vehicle 10.

[0035] Furthermore, the detection unit 31 detects lane markings and the lane in which the vehicle 10 is traveling (hereinafter referred to as the vehicle's own lane). In this embodiment, by inputting images acquired from camera 3-1 or camera 3-2 into the classifier, not only other vehicles but also lane markings are detected. Since camera 3-2 is mounted facing the rear of the vehicle 10, the detection unit 31 can identify the lane corresponding to the area between the two lane markings that are located on both sides of the horizontal center of the rear image and are closest to that center as the vehicle's own lane. Furthermore, the detection unit 31 can identify these two lane markings as the lane markings that define the vehicle's own lane.

[0036] Furthermore, the detection unit 31 identifies the lane in which each detected rear vehicle is traveling. For example, the detection unit 31 identifies the lane in which the rear vehicle is traveling by comparing the position of each detected rear vehicle on the rear image with the position of the individual lane markings detected from the rear image. Specifically, the detection unit 31 defines the lane in which the rear vehicle is traveling as the lane corresponding to the area between the two lane markings located on both sides of the lower end of the object area representing the rear vehicle in the rear image. As described above, the detection unit 31 can define the lane corresponding to the area between the two lane markings located on both sides of the horizontal center of the rear image and the area closest to that center as the vehicle's own lane. Therefore, the detection unit 31 can identify the position of the lane in which the rear vehicle is traveling, relative to the vehicle's own lane, by counting the number of lane markings located between the area corresponding to the lane in which the rear vehicle is traveling and the area corresponding to the vehicle's own lane in the rear image.

[0037] Furthermore, if the vehicle 10 is equipped with a distance measuring sensor, the detection unit 31 can estimate the direction from the vehicle 10 to the vehicle behind it, which corresponds to the center of gravity of the object region representing the rear vehicle in the rear image. The detection unit 31 can also estimate the distance measured by the distance measuring sensor at that direction as the distance from the vehicle 10 to the vehicle behind it. From the estimated distance and direction to the vehicle behind it, the detection unit 31 determines the distance from the vehicle 10 to the vehicle behind it in a direction perpendicular to the direction of travel of the vehicle 10 (hereinafter, the distance in a direction perpendicular to the direction of travel of the vehicle 10 is called the lateral distance). The detection unit 31 then divides this lateral distance by the width of each lane to determine the position of the lane in which the vehicle behind is traveling, relative to the vehicle's own lane. The detection unit 31 only needs to determine the width of each lane at the vehicle's position determined by the GPS receiver 2 by referring to map information.

[0038] The detection unit 31 notifies the traffic congestion prediction unit 32, the distance estimation unit 33, and the vehicle control unit 34 of information representing the position of each detected rear vehicle, and the lane in which each detected rear vehicle (especially large vehicles) is traveling.

[0039] The traffic congestion prediction unit 32 determines whether or not traffic congestion will occur around the vehicle 10 within a predetermined period from the current time to a predetermined time in the future. Hereinafter, the prediction that traffic congestion will occur around the vehicle 10 in the future will be referred to as the presence of a traffic congestion prediction.

[0040] For example, the congestion prediction unit 32 determines whether or not there are signs of congestion based on the behavior of other vehicles traveling around the vehicle 10, which is detected by the detection unit 31.

[0041] To this end, the traffic congestion prediction unit 32 tracks other vehicles by performing predetermined tracking processes, such as optical flow tracking, on each of the time-series images acquired from camera 3-1 or camera 3-2. The traffic congestion prediction unit 32 then performs viewpoint transformation processing on each image using parameters of camera 3-1 or camera 3-2, such as focal length, shooting direction, and installation height, to convert each image into a bird's-eye view image. This allows the traffic congestion prediction unit 32 to calculate the relative position of the other vehicle being tracked with respect to vehicle 10 at the time each image is acquired. In this case, as explained in the detection unit 31, the traffic congestion prediction unit 32 may also use the distance measurement to the other vehicle by the distance measuring sensor to calculate the relative position of the other vehicle. Furthermore, the lower end of the object region representing the other vehicle is presumed to represent the position where the road surface and the other vehicle are in contact. Therefore, the traffic congestion prediction unit 32 may estimate the distance from vehicle 10 to other vehicles at the time each image is acquired, based on the orientation and installation height from camera 3-1 or camera 3-2 corresponding to the lower edge of the object region in which the other vehicles are represented in each image. The traffic congestion prediction unit 32 may then use the estimated distance to calculate the relative position of the other vehicles being tracked with respect to vehicle 10.

[0042] The congestion prediction unit 32 selects a preceding vehicle from among the other vehicles being tracked that is traveling ahead of vehicle 10. If there are multiple preceding vehicles, the congestion prediction unit 32 may select the preceding vehicle that is closest to vehicle 10. The congestion prediction unit 32 then applies a prediction filter, such as a Kalman filter, to the time change in the relative position from vehicle 10 to the selected preceding vehicle during the period in which the selected preceding vehicle is being tracked. Furthermore, the congestion prediction unit 32 predicts the change in vehicle 10's speed over a predetermined period in the future by applying the prediction filter to the time change in the measured speed of vehicle 10 over a recent period. The congestion prediction unit 32 can, for example, obtain the measured speed of vehicle 10 from a vehicle speed sensor (not shown) mounted on vehicle 10 via the communication interface 21 to determine the time change in vehicle speed over a recent period to which the prediction filter is applied. As a result, the traffic congestion prediction unit 32 predicts changes in the relative speed between vehicle 10 and the vehicle ahead, and changes in the distance between vehicles, over a predetermined period in the future from the current time to a predetermined time ahead.

[0043] The traffic congestion prediction unit 32 determines whether there exists a first period within a predetermined timeframe from the current time to a predetermined time in the future in which the absolute value of the relative speed between vehicle 10 and the preceding vehicle is less than or equal to a predetermined relative speed threshold, and the distance between vehicle 10 and the preceding vehicle is predicted to be within a predetermined distance range. If such a first period exists, the traffic congestion prediction unit 32 determines that there is a sign of traffic congestion and predicts the start time of that first period as the timing when vehicle 10 will be caught in traffic. The relative speed threshold is set to, for example, 1 m / s. The predetermined distance range is set to, for example, 3 m or more and 25 m or less. The first period is set to, for example, 3 to 5 seconds.

[0044] Alternatively, the congestion prediction unit 32 may predict the changes in relative speed and distance between vehicle 10 and other vehicles for all other vehicles being tracked over a predetermined period from the current time to a predetermined time in the future. The congestion prediction unit 32 may then determine that there is a sign of congestion if, for all other vehicles being tracked, there is a first period within that predetermined period during which the relative speed to vehicle 10 is predicted to be below a predetermined relative speed threshold (for example, 3 m / s). In this case as well, the congestion prediction unit 32 predicts that the start of the first period is the timing when vehicle 10 will be caught in congestion.

[0045] Alternatively, the congestion prediction unit 32 may determine whether or not there are signs of congestion based on a prediction of the time change of the vehicle 10's speed over a predetermined period in the future. For example, the congestion prediction unit 32 determines that there are signs of congestion if it is predicted that the vehicle 10's speed will remain below a first speed threshold (e.g., 20 km / h) for a second period (e.g., 5 seconds) or longer within a predetermined period in the future. Alternatively, the congestion prediction unit 32 may determine that there are signs of congestion if it is predicted that the change in the vehicle 10's speed over a second period will be within a predetermined speed change range (e.g., 1 m / s). In this case as well, the congestion prediction unit 32 predicts that the start of the second period will be the timing when the vehicle 10 gets caught in congestion.

[0046] Alternatively, the congestion prediction unit 32 may determine that there is a sign of congestion if the traffic information received via the wireless communication terminal 4 indicates that congestion is occurring within a predetermined distance in the direction of travel of the vehicle 10 and on the road the vehicle 10 is traveling on. In this case, the congestion prediction unit 32 only needs to identify the road the vehicle 10 is traveling on by referring to the vehicle 10's current location and a high-precision map. Furthermore, the congestion prediction unit 32 predicts the timing at which the vehicle 10 will be caught in congestion, based on the predicted time at which the vehicle 10 will reach the congested section indicated in the traffic information, assuming the vehicle 10 continues to travel at its average speed over a certain period of time.

[0047] Alternatively, the congestion prediction unit 32 may determine that there is a congestion warning only if it determines that there is a congestion warning with respect to two or more of the above congestion determination methods. In this case, the congestion prediction unit 32 may determine that the vehicle 10 is caught in the congestion at the earliest timing among the timings at which the vehicle 10 is predicted to be caught in the congestion for each of the two or more congestion warnings.

[0048] The traffic congestion prediction unit 32 notifies the vehicle control unit 34 of the result of its determination of whether or not there are signs of traffic congestion.

[0049] The distance estimation unit 33 estimates the distance between vehicle 10 and each of the following vehicles traveling behind vehicle 10, as detected by the detection unit 31. The distance estimation unit 33 can estimate the distance between each following vehicle and vehicle 10 using the same method as described in the detection unit 31 or the traffic congestion prediction unit 32. That is, the distance estimation unit 33 can estimate the distance between vehicle 10 and the following vehicles based on the orientation from camera 3-1 or camera 3-2 corresponding to the position of the lower end of the object region including the following vehicles in the image, and the installation height of those cameras. Alternatively, the distance estimation unit 33 can estimate the distance between vehicle 10 and the following vehicles based on the distance measurement from vehicle 10 to the following vehicles measured by the distance measuring sensor.

[0050] The distance estimation unit 33 notifies the vehicle control unit 34 of the estimated distance for each rear vehicle.

[0051] The vehicle control unit 34 determines, based on the estimated distance to each following vehicle or the presence or absence of signs of congestion, whether the detected following vehicles meet the occlusion conditions that obstruct the rear view of vehicle 10. If the occlusion conditions are met, the vehicle control unit 34 controls vehicle 10 to ensure the rear view of vehicle 10.

[0052] For example, the vehicle control unit 34 determines that the shielding condition is met if the congestion prediction unit 32 determines that there is a sign of congestion within a predetermined period from the current time to a predetermined time in the future, and at least one of the vehicles behind is a large vehicle. In this case, the vehicle control unit 34 controls vehicle 10 to move it to a lane different from the lane in which the large vehicle behind is traveling. In particular, it is preferable for the vehicle control unit 34 to control vehicle 10 so that the lane change is completed before the timing at which congestion is predicted to occur around vehicle 10. If the lane in which the large vehicle traveling behind vehicle 10 is located is different from the vehicle's own lane, the vehicle control unit 34 should control vehicle 10 so that it continues to travel in its own lane. By moving vehicle 10 to a lane in which the large vehicle is not traveling before vehicle 10 gets caught in congestion, the vehicle control unit 34 can prevent the detectable distance behind vehicle 10 from becoming shorter, thereby facilitating the detection of approaching emergency vehicles or motorcycles. As a result, opportunities to apply autonomous driving control during traffic congestion can be increased.

[0053] The vehicle control unit 34 refers to the high-precision map, the planned route to the destination of the vehicle 10 received from the navigation system, and the current position of the vehicle determined by the GPS receiver 2 in order to identify the lane to which the vehicle 10 should change. The vehicle control unit 34 then identifies the lane on the road that the vehicle 10 is currently traveling in that will allow it to reach the destination. For example, if the vehicle 10 needs to turn right at the next intersection to reach its destination, the lane that allows a right turn at the next intersection will be the lane that will allow it to reach its destination. Alternatively, if there is a branch road branching off from the left lane at a predetermined distance from the vehicle 10's current position, and the vehicle 10 needs to enter that branch road to reach its destination, the left lane will be the lane that will allow it to reach its destination. If there are no large vehicles traveling behind the vehicle 10 in the identified lane, the vehicle control unit 34 moves the vehicle 10 into the identified lane. On the other hand, only if a large vehicle is traveling behind vehicle 10 in the specified lane, the vehicle control unit 34 moves vehicle 10 to a lane in which a lane change is necessary to reach the destination, and in which no large vehicle is traveling behind vehicle 10.

[0054] Furthermore, if the road on which vehicle 10 is traveling includes three or more lanes, and no large vehicles are detected behind vehicle 10 in two or more of those lanes, the vehicle control unit 34 prefers to change vehicle 10 to an overtaking lane among the lanes where no large vehicles are detected. In particular, if the road on which vehicle 10 is traveling has a climbing lane, there is a high possibility that a large vehicle will enter the climbing lane. Therefore, even if no large vehicles are detected behind vehicle 10 in the climbing lane, the vehicle control unit 34 prefers to change vehicle 10 to a lane other than the climbing lane. By selecting the destination lane in this way, the vehicle control unit 34 can reduce the possibility of a large vehicle getting behind vehicle 10 when the area around vehicle 10 is congested, thereby improving the possibility of securing a clear view behind vehicle 10.

[0055] Furthermore, if multiple vehicles are detected behind vehicle 10 in each of the multiple lanes of the road it is traveling on, and any of them are large vehicles, the vehicle control unit 34 may predict the trajectories of vehicle 10 and each of the rear vehicles in the event of a lane change. The vehicle control unit 34 may then predict the number of vehicles that will be between vehicle 10 and the large vehicle based on the prediction results. The more vehicles that will be between vehicle 10 and the large vehicle in a lane, the longer the distance at which rear vehicles can be detected. Therefore, it is preferable for the vehicle control unit 34 to select the lane with the largest number of vehicles between vehicle 10 and the large vehicle as the lane to change to.

[0056] In this case, the vehicle control unit 34 applies a predictive filter such as a Kalman filter to the tracking results of each other vehicle traveling around vehicle 10, obtained by the congestion prediction unit 32, to predict the trajectory of each other vehicle for a predetermined period from the present time to a predetermined time in the future. The vehicle control unit 34 then sets a provisional planned route for each of the candidate lanes to which vehicle 10 will move from its own lane to that candidate lane, and to stay at a predetermined distance or more from the predicted trajectory of the other vehicles. The vehicle control unit 34 then predicts the number of vehicles that would be between vehicle 10 and the large vehicle, assuming that vehicle 10 moves along the provisional planned route based on the predicted trajectories of the other vehicles.

[0057] Furthermore, the vehicle control unit 34 determines that the shielding condition is met if the distance from vehicle 10 to a vehicle traveling in the same lane is less than or equal to a predetermined distance threshold. In this case, the vehicle control unit 34 controls vehicle 10 to move it closer to either the left or right lane marking line that defines the same lane. Specifically, it is preferable for the vehicle control unit 34 to control vehicle 10 so that the lateral distance between the position of vehicle 10 in the transverse direction of the same lane and the lane marking line that defines the same lane is smaller than the lateral distance when the estimated distance to the vehicle behind is longer than the predetermined distance threshold. In this way, by driving vehicle 10 closer to the lane marking line when a vehicle behind is present, the vehicle control unit 34 can prevent the detectable distance behind vehicle 10 from becoming shorter, thereby facilitating the detection of approaching emergency vehicles or motorcycles.

[0058] In this case, the vehicle control unit 34 may refer to high-precision map information and the current position of the vehicle 10 determined by the GPS receiver 2 to determine whether there is a shoulder on the road the vehicle 10 is traveling on, and whether there are two lanes in the direction of travel of the vehicle 10 on that road. If there is no shoulder on the road the vehicle 10 is traveling on, and there are two lanes in the direction of travel of the vehicle 10 on that road, the vehicle control unit 34 controls the position of the vehicle 10 so that the lateral distance to the lane marking on the center side is shorter than the lateral distance to the lane marking on the side of the road. This makes it easier for the vehicle control unit 34 to detect other vehicles approaching the vehicle 10 from behind.

[0059] When vehicle 10 is traveling on a curved road, it is possible to maintain a clear view of the rear without having to move the vehicle 10 too close to the lane markings. Therefore, the vehicle control unit 34 may set the lateral distance from the lane markings to vehicle 10 when vehicle 10 is traveling on a curved road to be greater than the lateral distance when vehicle 10 is traveling on a straight road. This allows the vehicle control unit 34 to maintain a clear view of the rear of vehicle 10 while also ensuring a certain distance between vehicle 10 and other vehicles traveling in adjacent lanes when vehicle 10 is traveling on a curved road.

[0060] Furthermore, the vehicle control unit 34 may reduce the lateral distance to the lane markings as the distance between vehicle 10 and other vehicles traveling behind it in its own lane decreases. Alternatively, if another vehicle traveling behind it in its own lane is traveling closer to either the left or right lane marking than the center of the lane, the vehicle control unit 34 may control vehicle 10 to move closer to the lane marking on the opposite side of the lane marking that the other vehicle is closer to. This makes it easier for the vehicle control unit 34 to ensure a clear view of the area behind vehicle 10.

[0061] Furthermore, if it is predicted that the speed of other vehicles will decrease between the current time and a predetermined time in the future compared to the current speed of other vehicles, it is assumed that the distance between vehicle 10 and the vehicle behind will decrease. In such a case, the vehicle control unit 34 may control the position of vehicle 10 so as to reduce the lateral distance from vehicle 10 to the lane markings in advance, before the distance between vehicles decreases. The vehicle control unit 34 can determine whether or not the speed of other vehicles will decrease based on the predicted trajectories of other vehicles as described above. Alternatively, the vehicle control unit 34 may refer to the current position of vehicle 10 and a high-precision map to search for a point in the direction of travel of vehicle 10 up to a predetermined distance ahead of the current position of vehicle 10 where the legal speed will decrease. If such a point exists, the vehicle control unit 34 may determine that the speed of other vehicles will decrease.

[0062] Furthermore, if vehicle 10 is traveling in a lane adjacent to the merging lane, other undetected vehicles may approach from the merging lane. Therefore, the vehicle control unit 34 may control the position of vehicle 10 so that the lateral distance to the lane marking on the merging lane side is smaller than the lateral distance to the lane marking on the opposite side of the merging lane, in order to make it easier to detect the approach of such other vehicles. The vehicle control unit 34 can determine whether or not its own lane is adjacent to the merging lane by referring to its own position and a high-precision map.

[0063] As described above, when the vehicle control unit 34 decides to perform a lane change or a change in lateral position within its own lane, it generates a planned route for the vehicle 10 according to the result of that decision. For example, if the vehicle control unit 34 detects a large vehicle traveling behind the vehicle 10 and there are signs of congestion, it sets the planned route so that the vehicle 10 changes lanes to a different lane from the one the large vehicle is traveling in, before the predicted timing when the vehicle 10 will be caught in congestion. Alternatively, if the distance from the vehicle 10 to the vehicle traveling behind in its own lane is less than or equal to a predetermined distance threshold, the vehicle control unit 34 sets the planned route so that the vehicle 10 approaches either the left or right lane marking that defines its own lane. In this case, it is preferable for the vehicle control unit 34 to refer to the predicted trajectories of other vehicles traveling around the vehicle 10 and set the planned route so that the distance between the vehicle and other vehicles is greater than or equal to a predetermined distance. The planned route is represented, for example, as a set of target positions for the vehicle 10 at each time point when the vehicle 10 travels a predetermined section.

[0064] Once a planned route is set, the vehicle control unit 34 controls various parts of the vehicle 10 so that the vehicle 10 travels along that planned route. For example, the vehicle control unit 34 determines the target acceleration of the vehicle 10 according to the planned route and the current vehicle speed of the vehicle 10 measured by a vehicle speed sensor (not shown), and sets the accelerator opening or brake amount to achieve that target acceleration. The vehicle control unit 34 then determines the fuel injection amount according to the set accelerator opening and outputs a control signal corresponding to that fuel injection amount to the fuel injection device of the vehicle 10's engine. Alternatively, the vehicle control unit 34 controls the power supply device to the motor that drives the vehicle 10 so that power corresponding to the set accelerator opening is supplied to the motor. Or, the vehicle control unit 34 outputs a control signal corresponding to the set brake amount to the brakes of the vehicle 10. Furthermore, the vehicle control unit 34 determines the steering angle of the vehicle 10 necessary for the vehicle 10 to travel along the planned route based on the planned route and the current position of the vehicle 10, and outputs a control signal corresponding to that steering angle to the actuator (not shown) that controls the steering wheels of the vehicle 10. The vehicle control unit 34 can estimate the position and direction of the vehicle 10 at the time of image generation by determining the position and direction of the vehicle 10 when the detected features projected from the latest image onto a high-precision map best match with the corresponding features on the high-precision map. The vehicle control unit 34 can then estimate the current position of the vehicle 10 by correcting the position and direction of the vehicle 10 at the time of image generation using the acceleration and yaw rate of the vehicle 10 from the time of image generation to the present time.

[0065] Figure 4 shows an example of how vehicle 10 is controlled when a large vehicle is detected traveling behind it. In this example, as shown in the upper part of Figure 4, a large vehicle 410 is traveling behind vehicle 10 in lane 401. As a result, the rear view 420 of vehicle 10 is obstructed by the large vehicle 410, making it impossible for vehicle 10 to see other vehicles 411 traveling further behind the large vehicle 410. Therefore, as shown in the lower part of Figure 4, by changing lanes to lane 402 adjacent to lane 401 before vehicle 10 gets caught in traffic, it becomes possible to secure the rear view 420 of vehicle 10. As a result, it becomes possible for vehicle 10 to see other vehicles 411 traveling further behind the large vehicle 410.

[0066] Figure 5 shows an example of vehicle 10 control when the distance between vehicle 10 and another vehicle traveling behind it is short. In this example, as shown in the upper part of Figure 5, another vehicle 510 is traveling behind vehicle 10 in lane 501. The distance d between vehicle 10 and the other vehicle 510 is shorter than the distance threshold Th. As a result, the rear view 520 of vehicle 10 is obstructed by the other vehicle 510, and vehicle 10 cannot see another vehicle 511 traveling further behind the other vehicle 510. Therefore, as shown in the lower part of Figure 5, by moving vehicle 10 closer to the lane marking 502, it is possible to secure the rear view 520 of vehicle 10. As a result, vehicle 10 can see the other vehicle 511 traveling further behind the other vehicle 510.

[0067] Figure 6 is an operation flowchart of the vehicle control process executed by the processor 23. The processor 23 should execute the vehicle control process according to the following operation flowchart at predetermined intervals.

[0068] The detection unit 31 of the processor 23 detects a vehicle traveling behind the vehicle 10 (step S101). Furthermore, the detection unit 31 detects lane markings (step S102).

[0069] The congestion prediction unit 32 of the processor 23 determines whether or not there are signs of congestion around vehicle 10 within a predetermined period from the current time to a predetermined time in the future (step S103). The distance estimation unit 33 of the processor 23 also estimates the distance between vehicle 10 and each of the vehicles behind it (step S104).

[0070] The vehicle control unit 34 of the processor 23 determines whether there are signs of congestion and whether at least one of the vehicles behind is a large vehicle (step S105). If there are signs of congestion and at least one of the vehicles behind is a large vehicle (step S105-Yes), the vehicle control unit 34 determines that the shielding condition is met. The vehicle control unit 34 then controls vehicle 10 to move vehicle 10 to a different lane from the lane in which the large vehicle behind is traveling (step S106).

[0071] On the other hand, if none of the vehicles behind are large vehicles, or if there are no signs of congestion (step S105-No), the vehicle control unit 34 determines whether the distance from vehicle 10 to the vehicles behind traveling in its own lane is below a predetermined distance threshold (step S107). If the distance from vehicle 10 to the vehicles behind traveling in its own lane is below a predetermined distance threshold (step S107-Yes), the vehicle control unit 34 determines that the shielding condition is met. The vehicle control unit 34 then controls vehicle 10 to move it closer to either the left or right lane marking line that defines its own lane (step S108).

[0072] If, in step S107, the distance from vehicle 10 to a following vehicle traveling in the same lane is greater than a predetermined distance threshold (step S107-No), the vehicle control unit 34 determines that the shielding condition is not met. The vehicle control unit 34 then controls vehicle 10 to maintain its lateral position within the same lane (step S109).

[0073] After steps S106, S108, or S109, the processor 23 terminates the vehicle control process. If both the shielding conditions shown in step S105 and step S107 are met, the vehicle control unit 34 only needs to execute the process in step S106. That is, the vehicle control unit 34 only needs to control vehicle 10 to move it to a different lane from the one in which the large vehicle behind it is traveling. If the shielding conditions in step S107 are met after vehicle 10 has changed lanes, the vehicle control unit 34 only needs to execute the process in step S108.

[0074] As explained above, this vehicle control system detects other vehicles traveling behind it based on sensor signals obtained from sensors mounted on the vehicle that detect the surrounding environment. The vehicle control system then determines whether the detected other vehicle meets the occlusion conditions that obstruct the rearward view of the vehicle, and if the occlusion conditions are met, it controls the vehicle to ensure a clear rearward view. Therefore, this vehicle control system can appropriately maintain a detectable distance behind the vehicle.

[0075] In a modified version, the detection unit 31 may detect a vehicle behind based on sensor signals acquired by sensors for detecting objects present around the vehicle 10 other than cameras 3-1 and 3-2, for example, distance measurement signals from a distance measurement sensor. In this case, the classifier used by the detection unit 31 should be pre-trained to detect other vehicles in each of a plurality of regions set within the detection range of the sensor, based on the sensor signals acquired by that sensor. In this case as well, the classifier can be configured using a DNN, similar to the above embodiment or modified version. Alternatively, the classifier may be a classifier using a machine learning method different from a DNN, such as a support vector machine.

[0076] The computer program that realizes the functions of the processor 23 of the ECU 6 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.

[0077] 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]

[0078] 1. Vehicle control system 10 vehicles 2 GPS receivers 3-1, 3-2 Camera 4 Wireless communication terminals 5. Storage devices 6. Electronic Control Unit (ECU) 21 Communication Interface 22 memory 23 processors 31 Detection unit 32 Traffic congestion prediction unit 33 Distance Estimation Unit 34 Vehicle Control Unit

Claims

1. A detection unit detects a large vehicle traveling behind the vehicle and the lane in which the large vehicle is traveling, based on sensor signals obtained from sensors that detect the surrounding conditions of the vehicle. A congestion prediction unit determines whether or not the area around the vehicle will be congested within a predetermined period from the current time to a predetermined time in the future, and predicts the timing at which the area around the vehicle will become congested if it is determined that congestion will occur. A vehicle control unit controls the vehicle so that, if it is determined that congestion will occur around the vehicle within the predetermined period, and the vehicle is traveling in the same lane as the large vehicle, the lane change to move the vehicle to a lane not occupied by the large vehicle is completed before the predicted timing. A vehicle control device having

2. The vehicle control unit determines that congestion will occur around the vehicle within the predetermined period, and that the lane the vehicle is traveling in and the lane the large vehicle is traveling in are the same, and based on the map information stored in the memory unit, the planned route the vehicle is traveling on to its destination, and the vehicle's current position, it identifies a lane on the road the vehicle is traveling on that can reach the destination. If the lane that can reach the identified destination is different from the lane in which the large vehicle is traveling, the vehicle is controlled so that the lane change to move the vehicle to the identified lane is completed before the predicted timing. On the other hand, if the lane that can reach the identified destination is the same lane in which the large vehicle is traveling, the vehicle control device according to claim 1 controls the vehicle to move to a different lane from the one in which the large vehicle is traveling, and to a lane in which a lane change is necessary to reach the destination, so that the lane change is completed before the predicted timing.

3. Based on sensor signals obtained from sensors that detect the surrounding conditions of the vehicle, the system detects a large vehicle traveling behind the vehicle and also detects the lane in which the large vehicle is traveling. The system determines whether or not the area around the vehicle will be congested within a predetermined period from the current time to a predetermined time in the future, and if it determines that the area around the vehicle will be congested, it predicts the timing at which the area around the vehicle will become congested. If it is determined that congestion will occur around the vehicle within the predetermined period, and the vehicle is traveling in the same lane as the large vehicle, the vehicle is controlled to complete a lane change to move the vehicle to a lane not occupied by the large vehicle before the predicted timing. A vehicle control method that includes the following.

4. Based on sensor signals obtained from sensors that detect the surrounding conditions of the vehicle, the system detects a large vehicle traveling behind the vehicle and also detects the lane in which the large vehicle is traveling. The system determines whether or not the area around the vehicle will be congested within a predetermined period from the current time to a predetermined time in the future, and if it determines that the area around the vehicle will be congested, it predicts the timing at which the area around the vehicle will become congested. If it is determined that congestion will occur around the vehicle within the predetermined period, and the vehicle is traveling in the same lane as the large vehicle, the vehicle is controlled to complete a lane change to move the vehicle to a lane not occupied by the large vehicle before the predicted timing. A vehicle control computer program that causes the processor installed in the vehicle to perform the following action.

Images