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

Abstract

To provide a vehicle control device capable of planning stable space creation processing when another vehicle is detected in a merging terrain.SOLUTION: A vehicle control device detects another vehicle in a detection mode 1 in a boundary region including a boundary within a predetermined visual field, and detects another vehicle in a detection mode 2 with higher precision than the detection mode 1 in a region other than the boundary region in the visual field. When it is determined that there is a merging terrain, and another vehicle traveling in an adjacent lane is detected in the boundary region in the visual field, the vehicle control device plans to control a speed of an own vehicle in a deceleration mode 1 until another vehicle traveling in the adjacent lane is detected in the region other than the boundary region in the visual field. When it is determined that there is the merging terrain, and another vehicle traveling in the adjacent lane is detected in the region other than the boundary region in the visual field, the vehicle control device plans space creation processing for controlling the speed of the own vehicle in a deceleration mode 2 allowing the own vehicle to decelerate at a greater speed change than the deceleration mode 1, thereby creating, on a travel lane ahead of the own vehicle, a space allowing another vehicle to move from the adjacent lane.SELECTED DRAWING: Figure 2

Description

Technical Field

[0001] The present disclosure relates to a vehicle control device, a vehicle control computer program, and a vehicle control method.

Background Art

[0002] An automatic control system mounted on a vehicle generates a navigation route of the vehicle based on the current position of the vehicle, the destination position of the vehicle, and a navigation map. The automatic control system estimates the current position of the vehicle using map information and controls the vehicle to travel along the navigation route.

[0003] In a merging terrain where an adjacent lane adjacent to the driving lane on which the host vehicle is traveling merges into the driving lane and disappears, other vehicles traveling in the adjacent lane move into the driving lane. When other vehicles traveling in the adjacent lane are detected in front of the host vehicle, the automatic control system of the host vehicle generates a space (yield control) in which other vehicles can move in front of the host vehicle within the range where a driving plan can be generated, and controls the host vehicle so that other vehicles can move into the driving lane (see, for example, Patent Document 1).

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] In a merging terrain, when other vehicles are present near the boundary of the field of view of sensors such as a camera or LiDAR mounted on the host vehicle, the automatic control system may not be able to accurately detect the other vehicles.

[0006] If other vehicles cannot be accurately detected, the automatic control system cannot grasp the positional relationship between the other vehicles and the host vehicle. Therefore, even if the space generation process is started when an other vehicle is detected at the visual field boundary, there has been a problem that the space generation process becomes an unstable control state.

[0007] Therefore, an object of the present disclosure is to provide a vehicle control device capable of planning a stable space generation process even when an other vehicle is detected in a boundary region including a boundary of a predetermined visual field in a merging terrain.

Means for Solving the Problem

[0008] (1) According to one embodiment, a vehicle control device is provided. This vehicle control device is a detection unit that detects other vehicles based on surrounding environment information representing the surrounding environment of the host vehicle within a predetermined visual field, and detects other vehicles in a first detection mode in a boundary region including the boundary of the visual field, and in a region other than the boundary region of the visual field, a detection unit that detects other vehicles in a second detection mode with higher accuracy of detecting other vehicles than the first detection mode, a determination unit that determines whether there is a merging terrain in which an adjacent lane adjacent to the driving lane on which the host vehicle travels disappears due to merging with the driving lane within a predetermined range from the current position of the host vehicle toward the front of the vehicle's travel route, and a planning unit that plans to execute a space generation process of controlling the speed of the host vehicle to generate a space on the driving lane in front of the host vehicle where other vehicles can move from the adjacent lane, wherein the planning unit plans to control the speed of the host vehicle in a first deceleration mode until an other vehicle traveling in the adjacent lane is detected in a region other than the boundary region of the visual field when the determination unit determines that there is the merging terrain and the detection unit detects an other vehicle traveling in the adjacent lane in the boundary region of the visual field, and when the determination unit determines that there is the merging terrain and the detection unit detects an other vehicle traveling in the adjacent lane in a region other than the boundary region of the visual field, plans to control the speed of the host vehicle in a second deceleration mode capable of decelerating with a greater speed change than the first deceleration mode and execute the space generation process.

[0009] (2) In the vehicle control device of (1), when the planning unit controls the speed of the host vehicle in the first deceleration mode and then another vehicle is detected by the detection unit in an area outside the boundary area of the visual field, it is preferable that the planning unit plans to control the speed of the host vehicle in the second deceleration mode and execute the space generation process.

[0010] (3) In the vehicle control device of (1) or (2), it is preferable that the planning unit plans to decelerate the host vehicle without using braking in the first deceleration mode and decelerate the host vehicle using braking in the second deceleration mode.

[0011] (4) According to another embodiment, a vehicle control computer program is provided. This vehicle control computer program is a detection unit that detects other vehicles based on peripheral environment information representing the peripheral environment of the host vehicle within a predetermined visual field. In a boundary area including the boundary of the visual field, other vehicles are detected in a first detection mode, and in an area outside the boundary area of the visual field, other vehicles are detected in a second detection mode with higher accuracy of detecting other vehicles than the first detection mode. It is determined whether there is a merging terrain where an adjacent lane adjacent to the driving lane on which the host vehicle is traveling disappears due to merging with the driving lane within a predetermined range ahead of the vehicle's path from the current position of the host vehicle. The processor is caused to execute a process including planning to control the speed of the host vehicle to execute a space generation process for generating a space on the driving lane in front of the host vehicle where other vehicles can move from the adjacent lane. When it is determined that there is the merging terrain and another vehicle traveling in the adjacent lane is detected in the boundary area of the visual field, it is planned to control the speed of the host vehicle in a first deceleration mode until another vehicle traveling in the adjacent lane is detected in an area outside the boundary area of the visual field. When it is determined that there is the merging terrain and another vehicle traveling in the adjacent lane is detected in an area outside the boundary area of the visual field, it is planned to control the speed of the host vehicle in a second deceleration mode capable of decelerating the host vehicle with a speed change greater than that in the first deceleration mode and execute the space generation process.

[0012] (5) According to another embodiment, a vehicle control method is provided. This vehicle control method is a vehicle control method executed by a vehicle control device, and is a detection unit that detects other vehicles based on peripheral environment information representing the peripheral environment of the host vehicle within a predetermined field of view. In a boundary region including the boundary of the field of view, other vehicles are detected in a first detection mode, and in a region outside the boundary region of the field of view, other vehicles are detected in a second detection mode with higher accuracy of detecting other vehicles than the first detection mode. It is determined whether there is a merging terrain where an adjacent lane adjacent to the driving lane on which the host vehicle travels disappears by merging with the driving lane within a predetermined range in front of the driving route of the vehicle from the current position of the host vehicle, and the speed of the host vehicle is controlled to generate a space on the driving lane in front of the host vehicle where other vehicles can move from the adjacent lane. It includes planning to execute a space generation process, and when it is determined that there is the merging terrain and another vehicle traveling in the adjacent lane is detected in the boundary region of the field of view, the speed of the host vehicle is controlled in a first deceleration mode until another vehicle traveling in the adjacent lane is detected in a region outside the boundary region of the field of view. When it is determined that there is the merging terrain and another vehicle traveling in the adjacent lane is detected in a region outside the boundary region of the field of view, the speed of the host vehicle is controlled in a second deceleration mode that can decelerate the host vehicle with a greater speed change than the first deceleration mode, and it is planned to execute the space generation process. This is a feature.

Advantages of the Invention

[0013] The vehicle control device according to the present disclosure can accurately detect other vehicles and plan a stable space generation process for each case where other vehicles are detected in a boundary region including the boundary of a predetermined field of view and where other vehicles are detected in a region outside the boundary region of the field of view.

Brief Description of the Drawings

[0014]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Mode for Carrying Out the Invention

[0015] FIG. 1 is a diagram for explaining the outline of the operation of the operation planning device 14 according to this embodiment. Hereinafter, with reference to FIG. 1, the outline of the operation regarding the vehicle control process of the operation planning device 14 disclosed in this specification will be explained. The operation planning device 14 is an example of a vehicle control device.

[0016] As shown in FIG. 1, the vehicle 10 is traveling on the lane 51 of the road 50 having lanes 51 and 52. The vehicle 10 is an example of the host vehicle. The lane 51 and the lane 52 are demarcated by a lane dividing line (lane boundary line) 53. The vehicle 10 is traveling straight on the lane 51 of the road 50.

[0017] Ahead of the current position of the vehicle 10, there is a merging terrain J where the road 60 merges with the road 50. In the merging terrain J, between the merging start position 62 and the merging end position 63, the lane 61 of the road 60 and the lane 51 of the road 50 are connected. The lane 61 and the lane 51 are demarcated by a lane dividing line (lane boundary line) 54. The lane 61 of the road 60 is adjacent to the lane 51 of the road 50 on which the vehicle 10 is traveling.

[0018] In the merging terrain J, the lane 61 of the road 60 disappears by merging with the lane 51. In the merging terrain J, another vehicle 70 traveling on the lane 61 of the road 60 moves from the lane 61 to the lane 51. The other vehicle 70 is an example of another vehicle.

[0019] Vehicle 10 has a driving plan device 14. Based on the information acquired by sensors such as camera 2, the driving plan device 14 detects vehicle 70 in front of the periphery of vehicle 10. Further, the driving plan device 14 generates a driving plan representing the planned driving trajectory of vehicle 10 up to a predetermined time in the future with reference to the position of vehicle 70.

[0020] In the example shown in FIG. 1, the driving plan device 14 determines that there is a merging terrain J within the immediate driving section based on the current position of vehicle 10 and the map information.

[0021] When the driving plan device 14 detects vehicle 70 traveling in lane 61 of road 60 in the merging terrain J, it plans to execute a space generation process to control the speed of vehicle 10 to create a movable space 55 for vehicle 70 to move from lane 61 onto lane 51 in front of vehicle 10.

[0022] In the merging terrain J, when vehicle 70 exists near the boundary of the visual field F1 of sensors such as camera 2 mounted on vehicle 10, the driving plan device 14 may not be able to accurately detect vehicle 70. In particular, when vehicle 70 overlaps with a rubber pole 64 or the like, it may be difficult to accurately detect vehicle 70.

[0023] In the example shown in FIG. 1, camera 2 has a visual field F1 facing the front of vehicle 10. A predetermined area from the left boundary of visual field F1 towards the inside of visual field F1 is boundary area R11, and a predetermined area from the right boundary of visual field F1 towards the inside of visual field F1 is boundary area R12. Area R13 outside the boundary areas is an area including the center of visual field F1.

[0024] If vehicle 70 cannot be accurately detected, the driving plan device 14 cannot grasp the positional relationship between vehicle 70 and vehicle 10. Therefore, when vehicle 70 moves from lane 61 to lane 51, there is a possibility of an unstable control state when creating a movable space 55 for vehicle 70 in front of vehicle 10.

[0025] The driving plan device 14 detects the vehicle 70 in the boundary regions R11 and R12 including the boundary of the field of view F1 of sensors such as the camera 2, and in the region R13 outside the boundary region of the field of view F1, the vehicle 70 is detected in a second detection mode with higher accuracy of detecting the vehicle 70 than the first detection mode.

[0026] At time T1, when the driving plan device 14 determines that there is a merging terrain J and a vehicle 70 traveling in the lane 61 is detected in the boundary region R11 of the field of view F1, until a vehicle 70 traveling in the lane 61 is detected in the region R13 outside the boundary region of the field of view F1, it plans to control the speed of the vehicle 10 in the first deceleration mode. This process is a pre-process of the space generation process.

[0027] And when the vehicle 10 decelerates in the first deceleration mode, the vehicle 70 moves relatively forward of the vehicle 10, so the vehicle 70 is detected in the region R13 outside the boundary region of the field of view F1.

[0028] At time T2, since the driving plan device 14 detects a vehicle 70 traveling in the lane 61 in the region R13 outside the boundary region of the field of view F1, it plans to control the speed of the vehicle 10 in a second deceleration mode capable of decelerating the vehicle 10 with a speed change greater than that in the first deceleration mode and execute the space generation process.

[0029] Also, at time T1, when the driving plan device 14 determines that there is a merging terrain J and a vehicle 70 traveling in the lane 61 is detected in the region R13 outside the boundary region of the field of view F1, it plans to control the speed of the vehicle 10 in the second deceleration mode from the beginning and execute the space generation process.

[0030] As described above, when the driving plan device 14 detects a vehicle 70 traveling in the lane 61 in the boundary region R11 of the field of view F1 and when it detects a vehicle 70 traveling in the lane 61 in the region R13 outside the boundary region of the field of view F1, for each case, it can plan a stable space generation process after accurately detecting the vehicle 70.

[0031] Figure 2 is a schematic configuration diagram of a vehicle 10 in which the vehicle control system 1 of the present embodiment is implemented. The vehicle 10 includes a camera 2, a LiDAR sensor 3, a positioning information receiver 4, a navigation device 5, a user interface (UI) 6, a map information storage device 11, a position estimation device 12, a travel lane planning device 13, a driving plan device 14, a vehicle control device 15, and the like. Further, the vehicle 10 may include a distance measuring sensor (not shown), such as a millimeter wave radar, for measuring the distance to an object around the vehicle 10. The vehicle control system 1 includes the camera 2, the LiDAR sensor 3, and the driving plan device 14.

[0032] The camera 2, the LiDAR sensor 3, the positioning information receiver 4, the navigation device 5, the UI 6, the map information storage device 11, the position estimation device 12, the travel lane planning device 13, the driving plan device 14, and the vehicle control device 15 are communicably connected via an in-vehicle network 16 compliant with a standard such as a controller area network.

[0033] The camera 2 is an example of an imaging unit provided in the vehicle 10. The camera 2 is attached to the vehicle 10 so as to face the front of the vehicle 10. The camera 2 captures a camera image representing the environment of an area within a predetermined field of view in front of the vehicle 10, for example, at a camera image capture time set at a predetermined cycle. The camera image may represent a road included in a predetermined area in front of the vehicle 10 and road features such as lane dividing lines on the road surface. The camera 2 includes a two-dimensional detector composed of an array of photoelectric conversion elements sensitive to visible light, such as a CCD or a C-MOS, and an imaging optical system that forms an image of an area to be photographed on the two-dimensional detector. The camera image is an example of peripheral environment information.

[0034] Each time the camera 2 captures a camera image, the camera image and the camera image capture time are output via the in-vehicle network 16 to the position estimation device 12, the driving plan device 14, and the like. The camera image is used in the position estimation device 12 for processing to estimate the position of the vehicle 10. Further, the camera image is used in the driving plan device 14 for processing to detect other objects around the vehicle 10.

[0035] The LiDAR sensor 3 is attached to, for example, the outer surface of the vehicle 10 so as to face the front of the vehicle 10. At the reflection wave information acquisition time set at a predetermined cycle, the LiDAR sensor 3 emits a laser beam so as to scan a predetermined visual field in front of the vehicle 10, and receives the reflected wave reflected by the reflecting object. The time required for the reflected wave to return has distance information between the vehicle 10 and other objects located in the direction irradiated by the radar. The LiDAR sensor 3 outputs the reflected wave information including the irradiation direction of the radar and the time required for the reflected wave to return, together with the reflection wave information acquisition time when the radar was emitted, to the driving plan device 14 and the like via the in-vehicle network 16. The reflected wave information is used in the driving plan device 14 for processing to detect other objects around the vehicle 10. The reflected wave information is an example of the surrounding environment information.

[0036] The positioning information receiver 4 outputs positioning information representing the current position of the vehicle 10. For example, the positioning information receiver 4 can be a GNSS receiver. Each time the positioning information receiver 4 acquires the positioning information at a predetermined reception cycle, it outputs the positioning information and the positioning information acquisition time when the positioning information was acquired to the navigation device 5, the map information storage device 11, and the like.

[0037] Based on the navigation map information, the target position of the vehicle 10 input from the UI6, and the positioning information representing the current position of the vehicle 10 input from the positioning information receiver 4, the navigation device 5 generates a navigation route from the current position of the vehicle 10 to the target position. The navigation route includes information regarding positions such as right turns, left turns, merges, and bifurcations. When the target position is newly set, or when the current position of the vehicle 10 deviates from the navigation route, etc., the navigation device 5 newly generates the navigation route of the vehicle 10. Each time the navigation device 5 generates a navigation route, it outputs the navigation route to the position estimation device 12, the driving lane planning device 13, the driving plan device 14, and the like via the in-vehicle network 16. Note that when the target position is not set, the navigation device 5 does not generate a navigation route.

[0038] UI6 is an example of a notification unit. UI6 is controlled by the navigation device 5, the driving plan device 14, the vehicle control device 15, etc., and notifies the driver of the driving information of the vehicle 10 and the like. The driving information of the vehicle 10 includes information such as the current position of the vehicle and information regarding the current and future routes of the vehicle such as the navigation route. UI6 has a display device 6a such as a liquid crystal display or a touch panel in order to display the driving information and the like. Further, UI6 may have an acoustic output device (not shown) for notifying the driver of the driving information and the like. Further, UI6 generates an operation signal corresponding to an operation on the vehicle 10 by the driver. Examples of the operation information include a destination position, a waypoint, the speed of the vehicle, and other control information. UI6 has, as an input device for inputting operation information from the driver to the vehicle 10, for example, a touch panel or an operation button. UI6 outputs the input operation information to the navigation device 5, the driving plan device 14, etc. via the in-vehicle network 16.

[0039] The map information storage device 11 stores wide-area map information of a relatively wide range (for example, a range of 10 to 30 km square) including the current position of the vehicle 10. This map information has high-precision map information including three-dimensional information of the road surface, information such as the speed limit of the road, the curvature of the road, road features such as lane demarcation lines on the road, and information representing the type and position of structures.

[0040] The map information storage device 11 receives wide-area map information from an external server via a base station by wireless communication via a wireless communication device (not shown) mounted on the vehicle 10 according to the current position of the vehicle 10, and stores it in the storage device. Each time the map information storage device 11 inputs positioning information from the positioning information receiver 4, it refers to the stored wide-area map information and outputs map information of a relatively narrow area (for example, a range of 100 m square to 10 km square) including the current position represented by the positioning information to the position estimation device 12, the driving lane planning device 13, the driving plan device 14, the vehicle control device 15, etc. via the in-vehicle network 16.

[0041] The position estimation device 12 estimates the position of the vehicle 10 at the time of camera image capture based on the road features around the vehicle 10 represented in the camera image captured by the camera 2. For example, the position estimation device 12 compares the lane dividing lines identified in the camera image with the lane dividing lines represented in the map information input from the map information storage device 11, and obtains the estimated position and estimated azimuth angle of the vehicle 10 at the time of camera image capture. Further, the position estimation device 12 estimates the driving lane on the road where the vehicle 10 is located based on the lane dividing lines represented in the map information, the estimated position and estimated azimuth angle of the vehicle 10. Each time the position estimation device 12 obtains the estimated position, estimated azimuth angle, and driving lane of the vehicle 10 at the time of camera image capture, it outputs this information to the detection unit 232, the driving lane planning device 13, the driving plan device 14, the vehicle control device 15, etc.

[0042] The driving lane planning device 13 selects the lanes within the road on which the vehicle 10 travels based on the map information, the navigation route and the surrounding environment information, and the current position of the vehicle 10 in the nearest driving section (for example, 10 km) selected from the navigation route at the driving lane planning generation time set at a predetermined cycle, and generates a driving lane plan representing the planned driving lane on which the vehicle 10 travels. The driving lane planning device 13 generates, for example, a driving lane plan such that the vehicle 10 travels in a lane other than the overtaking lane. Each time the driving lane planning device 13 generates a driving lane plan, it outputs this driving lane plan to the driving plan device 14, etc.

[0043] The driving plan device 14 executes planning processing, detection processing, and determination processing. For this purpose, the driving plan device 14 includes a communication interface (IF) 21, a memory 22, and a processor 23. The communication interface 21, the memory 22, and the processor 23 are connected via a signal line 24. The communication interface 21 has an interface circuit for connecting the driving plan device 14 to the in-vehicle network 16.

[0044] The memory 22 is an example of a storage unit and has, for example, a volatile semiconductor memory and a non-volatile semiconductor memory. The memory 22 stores a computer program of an application and various data used in information processing executed by the processor 23.

[0045] All or part of the functions of the driving plan device 14 are, for example, functional modules realized by a computer program operating on the processor 23. The processor 23 includes a planning unit 231, a detection unit 232, and a determination unit 233. Alternatively, the functional module of the processor 23 may be a dedicated arithmetic circuit provided in the processor 23. The processor 23 includes one or more CPUs (Central Processing Units) and their peripheral circuits. The processor 23 may further include other arithmetic circuits such as a logical arithmetic unit, a numerical arithmetic unit, or a graphic processing unit.

[0046] At the driving plan generation time set at a predetermined cycle, the planning unit 231 executes a driving plan process for generating a driving plan representing the planned driving trajectory of the vehicle 10 up to a predetermined time (for example, 5 seconds) ahead based on the driving lane plan, the map information, the current position of the vehicle 10, the surrounding environment information, and the vehicle state information. The driving plan is preferably generated so as to satisfy a predetermined limit. Examples of the predetermined limit include acceleration, deceleration, yaw rate, etc. The surrounding environment information includes the positions and speeds of other vehicles traveling around the vehicle 10. The vehicle state information includes the current position of the vehicle 10, the vehicle speed, the acceleration, and the traveling direction, etc. The driving plan is represented as a set of the target positions of the vehicle 10 and the target vehicle speeds at these target positions at each time from the current time to a predetermined time ahead. The cycle at which the driving plan is generated is preferably shorter than the cycle at which the driving lane plan is generated. The driving plan device 14 generates a driving plan so as to maintain an interval of a predetermined distance or more between the vehicle 10 and other objects (such as vehicles). Each time the driving plan device 14 generates a driving plan, it outputs the driving plan to the vehicle control device 15.

[0047] In addition, the planning unit 231 plans space generation processing. For example, when the distance between the confluence end position in the confluence terrain and the current position of the vehicle 10 is equal to or greater than a predetermined reference distance, and the relative speed between the vehicle 10 and other vehicles is within a predetermined reference speed, and the relative distance between the vehicle 10 and other vehicles is within a predetermined reference distance, the planning unit 231 determines to start the space generation processing. Here, the other vehicle is a vehicle traveling in an adjacent lane that merges into the lane in which the vehicle 10 is traveling and disappears. Even if it is determined to start the space generation processing, if it is necessary to generate a driving plan that does not satisfy a predetermined limit such as decelerating at a deceleration equal to or greater than a predetermined reference deceleration, the space generation processing is not planned. When the space generation processing is planned, the planning unit 231 generates a driving plan including the space generation processing.

[0048] The detection unit 232 detects other objects around the vehicle 10 and their types based on the camera image. The other objects include other vehicles traveling around the vehicle 10. The detection unit 232 detects the objects represented in the image, for example, by inputting the camera image into an identifier. The detection unit 232 compares the reliability of the detected object output from the identifier with a predetermined reference reliability, and determines that the object is detected when the reliability of the object is equal to or greater than the reference reliability.

[0049] As the identifier, for example, a deep neural network (DNN) pre-trained to detect the objects represented in the input image can be used. The detection unit 232 may use an identifier other than the DNN. For example, as the identifier, the detection unit 232 may use a support vector machine (SVM) pre-trained to output the confidence that the object to be detected is represented in the window by using the feature amount (for example, Histograms of Oriented Gradients, HOG) calculated from the window set on the camera image as an input. Alternatively, the detection unit 232 may detect the object area by performing template matching between the template representing the object to be detected and the image.

[0050] Further, the detection unit 232 may detect other objects around the vehicle 10 based on the reflected wave information output by the LiDAR sensor 3. Further, the detection unit 232 may determine the orientation of other objects with respect to the vehicle 10 based on the positions of other objects in the camera image, and determine the distance between this other object and the vehicle 10 based on this orientation and the reflected wave information output by the LiDAR sensor 3. The detection unit 232 estimates the position of other objects, for example, represented in the world coordinate system, based on the current position of the vehicle 10, the distance and orientation to other objects with respect to the vehicle 10. Further, the detection unit 232 may track other objects detected from the latest camera image by associating the other objects detected from the latest camera image with the objects detected from past images according to the tracking process based on the optical flow. Then, the detection unit 232 may obtain the trajectory of other objects being tracked based on the positions of the objects in the world coordinate system from past images to the latest image. The detection unit 232 can estimate the speed of the object with respect to the vehicle 10 based on the change in the position of the other object over time. Further, the detection unit 232 can estimate the acceleration of the other object based on the change in the speed of the other object over time. Furthermore, the detection unit 232 specifies the driving lane in which the other object is traveling based on the lane division lines represented in the map information and the position of the other object. For example, the detection unit 232 determines that the other object is traveling in the lane specified by two adjacent lane division lines positioned so as to sandwich the horizontal center position of the other object.

[0051] Further, the detection unit 232 may detect an object represented in the reflected wave information (distance image) by inputting the reflected wave information (distance image) output by the LiDAR sensor 3 to the discriminator. As the discriminator, for example, a deep neural network (DNN) pre-trained to detect an object represented in the input reflected wave information (distance image) can be used. The detection unit 232 compares the reliability of the detected object output from the discriminator with a predetermined reference reliability, and determines that the object is detected when the reliability of the object is equal to or higher than the reference reliability. The detection unit 232 may detect other objects around the vehicle 10 and their types based on the camera image and the reflected wave information. Further, the detection unit 232 may detect other objects around the vehicle 10 and their types based on the camera image. Furthermore, the detection unit 232 may detect other objects around the vehicle 10 and their types based on the reflected wave information.

[0052] The detection unit 232 notifies the planning unit 231, the determination unit 233, etc. of object detection information including information indicating the type of the detected other object, information indicating its position, speed, acceleration, and the driving lane. Other operations of the driving plan device 14 will be described later.

[0053] The vehicle control device 15 controls each part of the vehicle 10 based on the current position of the vehicle 10, the vehicle speed and yaw rate, and the driving plan generated by the driving plan device 14. For example, the vehicle control device 15 obtains the steering angle, acceleration, and angular acceleration of the vehicle 10 according to the driving plan, the vehicle speed, and the yaw rate of the vehicle 10, and sets the steering amount, accelerator opening, or brake amount so as to be the steering angle, acceleration, and angular acceleration. Then, the vehicle control device 15 outputs a control signal corresponding to the set steering amount to an actuator (not shown) that controls the steering wheel of the vehicle 10 via the in-vehicle network 16. Further, the vehicle control device 15 outputs a control signal corresponding to the set accelerator opening to the drive device (engine or motor) of the vehicle 10 via the in-vehicle network 16. Alternatively, the vehicle control device 15 outputs a control signal corresponding to the set brake amount to the brake (not shown) of the vehicle 10 via the in-vehicle network 16.

[0054] The map information storage device 11, the position estimation device 12, the driving lane planning device 13, the driving plan device 14, and the vehicle control device 15 are, for example, electronic control units (ECUs). In FIG. 2, the map information storage device 11, the position estimation device 12, the driving lane planning device 13, the driving plan device 14, and the vehicle control device 15 are described as separate devices, but all or part of these devices may be configured as one device.

[0055] Also, in FIG. 2, the detection unit 232 is described as part of the driving plan device 14, but the detection unit 232 may be configured separately from the driving plan device 14. In this case, the detection unit 232 and the driving plan device 14 constitute the vehicle control device.

[0056] FIG. 3 is an example of an operation flowchart regarding the space determination process of the driving plan device 14 of the present embodiment. With reference to FIG. 3, the space determination process of the driving plan device 14 will be described below. The driving plan device 14 executes a space determination process according to the operation flowchart shown in FIG. 3 at a space determination time having a predetermined period.

[0057] First, the determination unit 233 determines whether there is a merging terrain where an adjacent lane adjacent to the driving lane on which the vehicle 10 travels disappears due to the merging of the adjacent lane with the driving lane within a predetermined range from the current position of the vehicle 10 toward the front of the route of the vehicle 10 (step S101). Specifically, the determination unit 233 determines whether there is a merging terrain within the latest driving section of the navigation route based on the current position of the vehicle 10, the navigation route, and the map information. The merging terrain includes a case where another road merges into the road on which the vehicle 10 travels and the adjacent lane adjacent to the driving lane merges with the driving lane and disappears (see FIG. 1), and a case where within the road on which the vehicle 10 travels, the adjacent lane adjacent to the driving lane merges with the driving lane and disappears (for example, a boarding lane). It is determined that there is a merging terrain until the vehicle 10 passes the merging end position where the connection between the driving lane and the adjacent lane ends.

[0058] When there is a merging terrain (step S101 - Yes), the determination unit 233 determines whether the vehicle 10 has reached the determination start position at which the space determination process is to be started (step S102). The determination unit 233 sets, as the determination start position, a position a predetermined distance ahead of the merging start position at which the running lane and the adjacent lane start to connect. The determination start position is preferably set at a position where the driver can visually recognize the merging terrain.

[0059] The predetermined distance can be determined, for example, based on the speed of the vehicle 10. The speed of the vehicle 10 may be the legal speed of the road, the speed limit, or the most recent average speed of the vehicle 10. As the predetermined distance determined based on the speed of the vehicle 10, for example, the sight distance can be used. The sight distance is determined for each legal speed, and is the distance that the driver can visually recognize so that road structures are installed when constructing the road so as not to obstruct the driver's field of vision. If the vehicle 10 has not reached the determination start position (step S102 - No), the series of processes is terminated. Note that the determination start position may be, for example, the position of the soft nose. The position of the soft nose can be obtained based on the map information. Also, when there is no merging terrain (step S101 - No), the series of processes is terminated.

[0060] When the vehicle 10 has reached the determination start position (step S102 - Yes), the determination unit 233 determines whether another vehicle traveling in the adjacent lane is detected in the boundary region of the fields of view of the sensors 2 and 3 by the detection unit 232 (step S103). Here, the adjacent lane is a lane that disappears by merging with the running lane in the merging terrain. This also applies to the following description. Detection of another vehicle traveling in the adjacent lane by the detection unit 232 in the boundary region of the fields of view of the sensors 2 and 3 will be described later.

[0061] When another vehicle is detected in the boundary region of the field of view by the detection unit 232 (step S103 - Yes), the planning unit 231 plans to control the speed of the vehicle 10 in the first deceleration mode until another vehicle traveling in the adjacent lane is detected in a region other than the boundary region of the fields of view of the sensors 2 and 3 by the detection unit 233 (step S104), and ends a series of processes. This process is a pre - process for the space generation process.

[0062] In the first deceleration mode, the vehicle 10 is decelerated so that another vehicle traveling in the adjacent lane is relatively moved forward of the vehicle 10 and another vehicle is detected in a region other than the boundary region of the fields of view of the sensors 2 and 3. The deceleration in the first deceleration mode is preferably such that the driver hardly recognizes that the vehicle 10 is decelerating without looking at the speedometer. In the first deceleration mode, the acceleration by the drive device (engine or motor) may be stopped and the vehicle 10 may be decelerated by engine braking or frictional force without performing braking by the brake. Thereby, it is possible to prevent the driver from feeling that the vehicle 10 is decelerating.

[0063] On the other hand, when another vehicle traveling in the adjacent lane is not detected in the boundary region of the fields of view of the sensors 2 and 3 by the detection unit 232 (step S103 - No), the determination unit 233 determines whether or not another vehicle traveling in the adjacent lane is detected in a region other than the boundary region of the fields of view of the sensors 2 and 3 by the detection unit 232 (step S105). Detection of another vehicle traveling in the adjacent lane in a region other than the boundary region of the fields of view of the sensors 2 and 3 by the detection unit 232 will be described later.

[0064] When another vehicle traveling in the adjacent lane is detected in a region other than the boundary region of the fields of view of the sensors 2 and 3 by the detection unit 232 (step S105 - Yes), the planning unit 231 plans to control the speed of the vehicle 10 in the second deceleration mode capable of decelerating the vehicle 10 with a greater speed change than the first deceleration mode, execute the space generation process (step S106), and end a series of processes.

[0065] In the second deceleration mode, the vehicle 10 is decelerated as necessary to generate a space on the driving lane in front of the vehicle 10 where other vehicles can move from the adjacent lane. In the second deceleration mode, braking may be performed using the brake. By performing braking using the brake, a space can be surely generated and the driver can be made to recognize that the vehicle 10 is executing the space generation process.

[0066] Also, when no other vehicle traveling in the adjacent lane is detected in the regions other than the boundary regions of the fields of view of the sensors 2 and 3 by the detection unit 232 (step S105 - No), the series of processes is terminated. In this case, in the merging terrain, since there is no other vehicle traveling in the adjacent lane, the space generation process is not executed.

[0067] Next, the detection by the detection unit 232 of vehicles traveling in the adjacent lane in the boundary regions and the regions other than the boundary regions of the fields of view of the sensors 2 and 3 will be described below.

[0068] First, the boundary region of the field of view of the camera 2 will be described below with reference to FIG. 4. FIG. 4 illustrates the boundary region of the field of view of the camera image, FIG. 4(A) is a plan view showing the boundary of the field of view, and FIG. 4(B) is a diagram for explaining the boundary region of the camera image.

[0069] The camera 2 has a field of view F1 facing the front of the vehicle 10. The field of view F1 includes a predetermined range on the left and right from the front of the vehicle 10. A predetermined region from the left boundary of the field of view F1 toward the inside of the field of view F1 is the boundary region R11, and a predetermined region from the right boundary of the field of view F1 toward the inside of the field of view F1 is the boundary region R12. The region R13 other than the boundary regions is a region including the center of the field of view F1. The boundary region R11 and the boundary region R12 can be defined by the azimuth angle with the direction toward the front of the vehicle 10 as the origin.

[0070] In the camera image 100, the left region 101 represents the environment included in the boundary region R11, and the right region 102 represents the environment included in the boundary region R12. The central region 103 of the camera image 100 represents the environment included in the region R13 other than the boundary region. In the camera image 100, the regions 101, 102, and 103 can be determined based on the installation position of the camera 2 with respect to the vehicle 10, the installation direction, the internal parameters of the camera, and the like.

[0071] The detection unit 232 compares the reliability indicating that the detected object output from the identifier is a vehicle with a predetermined reference reliability. When the reliability of the object is equal to or higher than the reference reliability, the detection unit 232 determines that a vehicle has been detected. This reference reliability is changed according to the position of the detected object within the camera image. When at least a part of the detected object is included in the boundary region R11 or the boundary region R12, the detection unit 232 uses a first reference reliability (for example, 0.5 to 0.7). When the detected object is included in a region other than the boundary region R11 and the boundary region R12, the detection unit 232 uses a second reference reliability higher than the first reference reliability. When a vehicle is detected using the second reference reliability (for example, 0.7 to 0.9), the detection accuracy of the vehicle is higher than when a vehicle is detected using the first reference reliability.

[0072] In addition, as described above, the detection unit 232 determines that another vehicle is traveling in a lane specified by two lane division lines adjacent to each other and positioned so as to sandwich the horizontal center position of the other vehicle. The detection unit 232 determines that it is an adjacent lane when the lane in which the other vehicle is traveling is adjacent to the travel lane in which the vehicle 10 is traveling and disappears by merging with the travel lane.

[0073] In the example shown in FIG. 4(B), the vehicle 70 detected in the left region 101 is included in the boundary region R11. Also, the vehicle 70 is traveling in an adjacent lane. That is, a vehicle 70 traveling in an adjacent lane is detected in the boundary region R11. Since the detection unit 232 shows a value of the reliability of the object equal to or higher than the first reference reliability based on the camera image 100, it is determined that a vehicle 70 traveling in the adjacent lane is detected in the boundary region R11.

[0074] Next, the boundary region of the field of view of the LiDAR sensor 3 will be described below with reference to FIG. 5. FIG. 5 is a diagram for explaining the boundary region of the field of view of the distance image.

[0075] The LiDAR sensor 3 has a field of view F2 facing forward of the vehicle 10. Based on the reflected wave information, a distance image within the field of view F2 is generated in the detection unit 232. The distance image is generated for a region within a predetermined range from the vehicle 10 in the left-right direction.

[0076] FIG. 5 is an example of a distance image generated when the vehicle 10 is located in front of the merging terrain J. A predetermined region from the left boundary of the distance image toward the inside of the field of view F2 is the boundary region R21, and a predetermined region from the right boundary of the field of view F2 toward the inside of the field of view F2 is the boundary region R22. The region R23 other than the boundary region is a region including the center of the field of view F2.

[0077] The boundary region R21 is a quadrangular region surrounded by four points B1, B2, B3, and B4 when the field of view F2 is viewed in plan. Also, the boundary region R22 is a quadrangular region surrounded by four points B5, B6, B7, and B8 when the field of view F2 is viewed in plan.

[0078] The detection unit 232 compares the reliability indicating that the detected object output from the discriminator is a vehicle with a predetermined reference reliability. When the reliability of the object is equal to or higher than the reference reliability, it determines that a vehicle has been detected. This reference reliability is changed according to the position of the detected object in the distance image. When at least a part of the detected object is included in the boundary region R21 or the boundary region R22, the detection unit 232 uses a first reference reliability (for example, 0.5 to 0.7). Also, when the detected object is included in a region other than the boundary region R21 and the boundary region R22, the detection unit 232 uses a second reference reliability higher than the first reference reliability. When a vehicle is detected using the second reference reliability (for example, 0.7 to 0.9), the detection accuracy is higher than when a vehicle is detected using the first reference reliability.

[0079] For example, when the rear end portion of another vehicle is included in the boundary region of the visual field, the detection unit 232 based on the reflected wave information may misidentify it as a moving object with a low relative speed to the vehicle 10. Therefore, when at least a part of the detected object is included in the boundary region R21 or the boundary region R22, by using the first reference reliability, the detected object is more likely to be detected as a vehicle. Note that instead of the LiDAR sensor 3, other objects may be similarly detected based on the reflected wave information measured by a millimeter-wave radar.

[0080] In the example shown in FIG. 5, the vehicle 70 is included in the boundary region R21. Also, the vehicle 70 is traveling in an adjacent lane. That is, a vehicle 70 traveling in the adjacent lane is detected in the boundary region R21. Since the reliability of the object shown a value equal to or higher than the first reference reliability based on the distance image, the detection unit 232 determines that a vehicle 70 traveling in the adjacent lane in the boundary region R21 has been detected.

[0081] Next, with reference to FIG. 1, the space generation process of the driving plan device 14 will be described below.

[0082] As described above, after the determination unit 233 determines that there is a confluence terrain J and the vehicle 10 reaches the determination start position, at time T1, it detects the vehicle 70 traveling in the lane 61 in the boundary regions R11 and R21 of the visual fields F1 and F2 of the sensors 2 and 3.

[0083] The determination unit 233 may determine whether the vehicle 70 is traveling in the adjacent lane 61 in the boundary regions R11 and R21 of the visual fields F1 and F2 of the sensors 2 and 3 based on the camera image and the distance image. In this case, when it is determined that the vehicle 70 is in the boundary regions R11 and R21 of the visual fields F1 and F2 in both the camera image and the distance image, it is determined that the vehicle 70 traveling in the adjacent lane 61 in the boundary regions R11 and R21 is detected (step S103 - Yes). Also, the determination unit 233 may determine whether the vehicle 70 is traveling in the adjacent lane 61 in the boundary regions R11 and R21 of the visual fields F1 and F2 of the sensors 2 and 3 based on only one of the camera image or the distance image.

[0084] The planning unit 231 plans to control the speed of the vehicle 10 in the first deceleration mode until a vehicle 70 traveling in the lane 61 is detected in the region R13 other than the boundary region of the visual field F1. This process is a pre - process of the space generation process.

[0085] By detecting the vehicle 70 with low accuracy in the boundary region R11 of the visual field F1, the vehicle 70 can be detected early.

[0086] Then, as the vehicle 10 decelerates in the first deceleration mode, the vehicle 70 moves relatively forward of the vehicle 10, so the vehicle 70 is detected in the region R13 other than the boundary region of the visual field F1. The driving plan device 14 can accurately acquire the position etc. of the vehicle 70 by detecting the vehicle 70 with high accuracy in the region R13 other than the boundary region of the visual field F1.

[0087] When the planning unit 231 detects a vehicle 70 traveling in the lane 61 in the region R13 outside the boundary region of the visual field F1, it plans to control the speed of the vehicle 10 in a second deceleration mode that can decelerate the vehicle 10 with a greater speed change than the first deceleration mode and execute the space generation process. Thereby, the driving plan device 14 can grasp the positional relationship between the vehicle 70 and the vehicle 10 and plan a stable space generation process.

[0088] The vehicle control device 15 executes the space generation process based on the driving plan including the space generation process. By executing the space generation process, it is possible to prevent the vehicle 70 traveling in the adjacent lane 61 from forcibly moving into the traveling lane 51, thereby avoiding the occurrence of a dangerous situation.

[0089] Also, when the driving plan device 14 determines at time T1 that there is a merging terrain J and detects a vehicle 70 traveling in the lane 61 in the region R13 outside the boundary region of the visual field F1, it plans to control the speed of the vehicle 10 in the second deceleration mode and execute the space generation process.

[0090] As described above, when the driving plan device detects another vehicle traveling in the adjacent lane in the boundary region including the boundary of the predetermined visual field and when it detects another vehicle traveling in the adjacent lane in the region outside the boundary region of the visual field, it can accurately detect the other vehicle and then plan a stable space generation process.

[0091] Specifically, when detecting another vehicle traveling in the adjacent lane in the boundary region including the boundary of the predetermined visual field, the driving plan device generates a plan that is a pre-process of the space generation process so that the other vehicle is detected in the region outside the boundary region of the visual field. Then, after detecting another vehicle traveling in the adjacent lane in the region outside the boundary region of the visual field, the driving plan device plans the space generation process.

[0092] In the present disclosure, the vehicle control device, the vehicle control computer program, and the vehicle control method of the above-described embodiments can be appropriately modified as long as they do not depart from the gist of the present disclosure. Further, the technical scope of the present disclosure is not limited to those embodiments, but extends to the invention described in the claims and its equivalents.

Explanation of Signs

[0093] 1 Vehicle control system 2 Camera 3 LiDAR sensor 4 Positioning information receiver 5 Navigation device 6 User interface 6a Display device 10 Vehicle 11 Map information storage device 12 Position estimation device 13 Driving lane planning device 14 Driving plan device 21 Communication interface 22 Memory 23 Processor 231 Planning section 232 Detection section 233 Judgment section 15 Vehicle control device 16 In-vehicle network

Claims

1. A detection unit that detects other vehicles based on surrounding environment information representing the surrounding environment of the host vehicle within a predetermined field of view. In a boundary region including the boundary of the field of view, other vehicles are detected in a first detection mode, and in a region outside the boundary region of the field of view, other vehicles are detected in a second detection mode with higher accuracy of detecting other vehicles than the first detection mode. A determination unit that determines whether there is a merging terrain where an adjacent lane adjacent to the driving lane on which the host vehicle is traveling disappears due to merging into the driving lane within a predetermined range in front of the driving route of the host vehicle from the current position of the host vehicle. A planning unit that plans to execute a space generation process of controlling the speed of the host vehicle to generate a space on the driving lane in front of the host vehicle where other vehicles can move from the adjacent lane. The planning unit When the determination unit determines that there is the merging terrain and the detection unit detects an other vehicle traveling in the adjacent lane in the boundary region of the field of view, plans to control the speed of the host vehicle in a first deceleration mode until an other vehicle traveling in the adjacent lane is detected in a region outside the boundary region of the field of view by the detection unit. When the determination unit determines that there is the merging terrain and the detection unit detects an other vehicle traveling in the adjacent lane in a region outside the boundary region of the field of view, plans to control the speed of the host vehicle in a second deceleration mode with a larger speed change than the first deceleration mode and execute the space generation process. A vehicle control device characterized by the above.

2. The planning unit plans to control the speed of the host vehicle in the second deceleration mode and execute the space generation process when an other vehicle is detected in a region outside the boundary region of the field of view by the detection unit after controlling the speed of the host vehicle in the first deceleration mode. The vehicle control device according to Claim 1.

3. The planning unit plans to decelerate the host vehicle without using braking in the first deceleration mode and decelerate the host vehicle using braking in the second deceleration mode. The vehicle control device according to Claim 1 or 2.

4. A detection unit that detects other vehicles based on surrounding environment information representing the surrounding environment of the host vehicle within a predetermined field of view, wherein in a boundary region including the boundary of the field of view, other vehicles are detected in a first detection mode, and in a region outside the boundary region of the field of view, other vehicles are detected in a second detection mode with higher accuracy of detecting other vehicles than the first detection mode. Determine whether there is a merging terrain within a predetermined range from the current position of the host vehicle toward the front of the travel route of the host vehicle, where an adjacent lane adjacent to the travel lane on which the host vehicle is traveling disappears due to merging with the travel lane. Plan to execute a space generation process of controlling the speed of the host vehicle to generate a space on the travel lane in front of the host vehicle where other vehicles can move from the adjacent lane. Cause a processor to execute a process including this. When it is determined that there is the merging terrain and an other vehicle traveling in the adjacent lane is detected in the boundary region of the field of view, it is planned to control the speed of the host vehicle in a first deceleration mode until an other vehicle traveling in the adjacent lane is detected in a region outside the boundary region of the field of view. When it is determined that there is the merging terrain and an other vehicle traveling in the adjacent lane is detected in a region outside the boundary region of the field of view, it is planned to control the speed of the host vehicle in a second deceleration mode that can decelerate the host vehicle with a greater speed change than the first deceleration mode and execute the space generation process. A vehicle control computer program characterized by this.

5. A vehicle control method executed by a vehicle control device, A detection unit that detects other vehicles based on surrounding environment information representing the surrounding environment of the host vehicle within a predetermined field of view, wherein in a boundary region including the boundary of the field of view, other vehicles are detected in a first detection mode, and in a region outside the boundary region of the field of view, other vehicles are detected in a second detection mode with higher accuracy of detecting other vehicles than the first detection mode. Determine whether there is a merging terrain within a predetermined range from the current position of the host vehicle toward the front of the travel route of the host vehicle, where an adjacent lane adjacent to the travel lane on which the host vehicle is traveling disappears due to merging with the travel lane. Plan to execute a space generation process of controlling the speed of the host vehicle to generate a space on the travel lane in front of the host vehicle where other vehicles can move from the adjacent lane. Including this. When it is determined that there is the merging terrain and another vehicle traveling in the adjacent lane is detected in the boundary region of the field of view, it is planned to control the speed of the host vehicle in a first deceleration mode until another vehicle traveling in the adjacent lane is detected in a region other than the boundary region of the field of view. When it is determined that there is the merging terrain and another vehicle traveling in the adjacent lane is detected in a region other than the boundary region of the field of view, it is planned to control the speed of the host vehicle in a second deceleration mode capable of decelerating the host vehicle with a greater speed change than the first deceleration mode and execute the space generation process. A vehicle control method characterized by this.

Images