Vehicle control device, vehicle control method, and computer program

Abstract

The present invention provides a vehicle control device, a vehicle control method, and a computer program capable of suppressing misrecognition of objects in a predetermined road environment where misrecognition of objects is possible. [Solution] The present invention provides a vehicle control device 10 comprising a control unit 11 that performs driving assistance for a vehicle, the control unit associates a first recognition result obtained by image recognition of a detection area in front of the vehicle with a second recognition result obtained by object recognition of the detection area, detects a moving object V present in the detection area, performs driving assistance according to the recognition result of the moving object, adjusts the detection range of the detection area according to the detection result of the road environment on which the vehicle is traveling, and if it is determined that the road environment is a predetermined road environment in which there is a possibility of misrecognizing a moving object, it detects the moving object in a narrowed detection area which is a narrowed detection range.

Description

Technical Field

[0001] The present invention relates to a vehicle control device, a vehicle control method, and a computer program for executing driving assistance.

Background Art

[0002] In recent years, a vehicle control device is known that scans a region in front of a vehicle with radar waves and executes driving assistance for an object based on a detection result of another vehicle or the like that is an object of the scan. When such a vehicle control device travels in a place surrounded by walls such as a tunnel, a road with a soundproof wall, or a place surrounded by steel materials such as around a bridge, it receives radar waves reflected by hitting a structure existing on the side such as a wall as noise, and thus there is a possibility of misrecognizing another vehicle existing around the host vehicle.

[0003] Patent Document 1 describes a vehicle control device that reduces the detection sensitivity of a radar device when it is determined that the vehicle is traveling in a predetermined road environment such as a tunnel, and returns the detection sensitivity of the radar device to the original state when the predetermined road environment ends.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] According to the technique described in Patent Document 1, although the sensitivity of the radar device is reduced in a predetermined road environment, it does not prevent the detection of a structure existing on the side of the road, and there is still a possibility of misrecognizing an object.

[0006] The present invention aims to provide a vehicle control device, a vehicle control method, and a computer program capable of suppressing misrecognition of objects in a predetermined road environment where misrecognition of objects is possible. [Means for solving the problem]

[0007] One aspect of the present invention is a vehicle control device comprising a control unit that performs driving assistance for a vehicle, wherein the control unit associates a first recognition result obtained by image recognition of a detection area in front of the vehicle with a second recognition result obtained by object recognition of the detection area to detect a moving object present in the detection area, performs the driving assistance according to the recognition result of the moving object, adjusts the detection range of the detection area according to the detection result of the road environment on which the vehicle is traveling, and, if it is determined that the road environment is a predetermined road environment in which there is a possibility of misrecognizing the moving object, detects the moving object in a narrow detection area which is a narrower detection range than the current detection range. [Effects of the Invention]

[0008] According to the present invention, it is possible to suppress misrecognition of objects in a predetermined road environment where there is a possibility of misrecognition of objects. [Brief explanation of the drawing]

[0009] [Figure 1] This is a block diagram showing the configuration of the vehicle control system. [Figure 2] This is a diagram showing the detection area of ​​the detection unit. [Figure 3] This figure shows the results of recognizing a moving object. [Figure 4] This figure shows an example of a designated road environment. [Figure 5] This figure shows an example of a situation in which a moving object may be misrecognized in a given road environment. [Figure 6] This figure shows an example of the state in which a predetermined road environment is detected. [Figure 7] This figure shows an example of a narrow detection area in a given road environment. [Figure 8]This flowchart shows the processing flow of the vehicle control method executed in the vehicle control device. [Modes for carrying out the invention]

[0010] As shown in Figure 1, Vehicle 1 is configured to perform driver assistance. Vehicle 1 is configured with a detection unit 2 and a vehicle control device 10 to perform driver assistance such as ADAS (Advanced Driver-Assistance Systems). The detection unit 2 detects the environment around Vehicle 1. The detection unit 2 is composed of multiple devices depending on the application. The detected values ​​detected by the detection unit 2 are used for driver assistance and navigation devices, etc.

[0011] The detection unit 2 is equipped with a camera 2A that captures images of the environment around the vehicle 1. The camera 2A captures images of the area around the vehicle 1 and outputs the captured data. In this embodiment, the camera 2A captures a predetermined range in front of the vehicle 1. The captured data from the camera 2A is used, for example, for driver assistance or as a drive recorder for the vehicle 1. The imaging range and imaging direction of the camera 2A may differ depending on the vehicle 1.

[0012] The detection unit 2 includes a lidar device 2B that detects three-dimensional data around the vehicle 1. The lidar device 2B periodically irradiates laser light in front of or around the vehicle 1 within the detection area and measures the reflected light from the target object. The lidar device 2B is configured to allow adjustment of the detection area. The lidar device 2B scans the laser light within the detection area and acquires measurement data. The lidar device 2B is configured to generate three-dimensional point cloud data around the vehicle 1 based on the measurement data.

[0013] The measurements from the LiDAR device 2B are used to detect other vehicles, pedestrians, bicycles, motorcycles, and other traffic participants around vehicle 1, as well as objects around vehicle 1. The LiDAR device 2B also detects road structures present in the road environment.

[0014] The detection unit 2 includes, for example, a radar device 2C that scans radar waves to detect objects existing around the vehicle 1. The radar device 2C is configured to complement the detection of objects with the lidar device 2B. The radar device 2C irradiates millimeter-wave radar waves in the detection area and receives the reflected waves reflected by an object to detect the relative distance to the object. The radar device 2C is configured to be able to adjust the detection area.

[0015] The measured values of the radar device 2C are used to detect other vehicles, traffic participants such as pedestrians, bicycles, and motorcycles existing around the vehicle 1, and objects existing around the vehicle 1. The radar device 2C detects road structures existing in the road environment. The object recognition unit is constituted by the lidar device 2B and / or the radar device 2C.

[0016] The detection unit 2 includes a position sensor 2D that detects the current position of the vehicle 1. The position sensor 2D is, for example, a GPS (Global Positioning System) sensor or a GNSS (Global Navigation Satellite System) sensor. The position sensor 2D may mutually complement the position of the vehicle 1 by an autonomous sensor (not shown) used for autonomous navigation such as a gyro sensor or an acceleration sensor.

[0017] The vehicle 1 includes an input / output unit 3 that receives a user's operation and can display information. The input / output unit 3 is constituted by, for example, a touch panel that receives a touch operation and can display a display image. The input / output unit 3 may be individually constituted by an input unit that receives an input operation such as a physical switch and a display unit that can display information such as an LCD (Liquid Crystal Display) or an organic EL (Electro Luminescence) display. The input / output unit 3 receives a user's operation to adjust the detection areas of the lidar device 2B and the radar device 2C as described later.

[0018] Vehicle 1 includes a communication unit 4 that can be communicatively connected to the network W. The communication unit 4 is a communication interface configured for wireless communication. The communication unit 4 communicatively connects, for example, to a wireless base station existing around the vehicle 1 and communicates with various communication targets via the network W. Vehicle 1 communicates, for example, with a server device 20 communicatively connected to the network W and acquires map data including the current position of vehicle 1.

[0019] Vehicle 1 includes a drive unit 5 that generates power for traveling. The drive unit 5 is configured, for example, by an internal combustion engine using fuel. The drive unit 5 is configured by an electric motor when vehicle 1 is an electric vehicle. The drive unit 5 may be configured by combining an internal combustion engine and an electric motor when vehicle 1 is a hybrid vehicle. The drive unit 5 is controlled by the vehicle control device 10 during the execution of driving assistance, and the speed is adjusted.

[0020] Vehicle 1 includes a braking unit 6 for decelerating the vehicle speed and controlling it to a stop state. The braking unit 6 is configured, for example, by a brake device that generates braking force. The braking unit 6 may be integrated with the drive unit 5 when vehicle 1 is an electric vehicle. The braking unit 6 is controlled by the vehicle control device 10 during the execution of driving assistance.

[0021] Vehicle 1 includes a steering unit 7 for operating the traveling direction. The steering unit 7 is configured by a power steering device or the like that gives a steering angle to the steering wheel according to the steering operation. The steering unit 7 may be integrated with the drive unit 5 that variably controls the left and right driving forces of the drive wheels when vehicle 1 is an electric vehicle. The steering unit 7 is controlled by the vehicle control device 10 during the execution of driving assistance, and the steering angle is adjusted.

[0022] The vehicle control device 10 includes a control unit 11 that performs control related to the driving of the vehicle 1. Based on the detection values ​​detected by the detection unit 2, the control unit 11 integrates and executes control of the vehicle 1, such as driving, driving assistance, navigation, and communication via the network W. The control unit 11 is composed of at least one hardware processor such as a CPU (Central Processing Unit). The control unit 11 may be implemented by hardware (including circuitry) such as an LSI (Large Scale Integration), ASIC (Application Specific Integrated Circuit), FPGA (Field-Programmable Gate Array), or GPU (Graphics Processing Unit), or it may be implemented by the cooperation of software and hardware.

[0023] The vehicle control device 10 includes a storage unit 12 for storing data and programs. The storage unit 12 is composed of a non-temporary storage medium such as a hard disk drive (HDD) or a solid-state disk (SSD). The storage unit 12 stores computer programs and data necessary for controlling the vehicle 1. The programs may be stored in the storage unit 12 in advance, or they may be stored on an externally connectable storage medium such as a DVD or CD-ROM and installed in the storage unit 12 when the storage medium is mounted on the drive device. The control unit 11 controls the drive unit 5, braking unit 6, and steering unit 7 based on the detection values ​​detected by the detection unit 2, and performs driving assistance control such as Obstacle Anticipation Assist (OAA).

[0024] As shown in Figure 2, vehicle 1 detects moving objects V, such as traffic participants, in the lane R of the road it is traveling on, and the vehicle control device 10 performs driving assistance. In the vehicle control device 10, the control unit 11 performs image recognition of the detection area T1 in front of vehicle 1 based on the image data captured by camera 2A. The detection range of the detection area T1 is set according to the image capture range of camera 2A. Based on the first recognition result obtained by image recognition of the detection area T1 in front of vehicle 1, the control unit 11 recognizes other moving objects V, such as preceding vehicles, as objects to be supported by driving assistance.

[0025] As shown in Figure 3, the control unit 11 recognizes an object moving within the captured image M1 based on the first recognition result. The control unit 11 compares multiple captured images frame by frame and recognizes a group of pixels that move overall within the image as the background. For example, the control unit 11 compares multiple captured images frame by frame and extracts a group of pixels that move in the same direction relative to the background within the image as the object. The control unit 11 calculates estimated values ​​such as the assumed position, relative direction of movement, and relative velocity of the object moving within the image.

[0026] The control unit 11 recognizes an object in the detection area T2 based on the detection values ​​detected by the lidar device 2B and / or radar device 2C. Under normal conditions, the detection area T2 is set to a range that substantially coincides with the detection area T1. Based on the second recognition result, the control unit 11 calculates estimated values ​​related to the object, such as the relative position, relative speed of movement, and relative direction of movement of the object moving within the detection area T2.

[0027] The control unit 11 performs a process to associate the first recognition result obtained by image recognition of the detection area T1 in front of the vehicle 1 with the second recognition result obtained by object recognition of the detection area T2. The control unit 11 associates the object present in the detection area T1 with the object present in the detection area T2 and detects the moving object V present in the detection areas T1 and T2. For example, the control unit 11 determines whether the error between the estimated value based on the first recognition result and the estimated value based on the second recognition result is below a preset standard.

[0028] The control unit 11 determines that the object in detection area T1 and the object in detection area T2 are the same moving object V if the error between the estimated value based on the first recognition result and the estimated value based on the second recognition result is less than or equal to a preset standard. Based on the determination result H, the control unit 11 detects the moving object V in detection areas T1 and T2. The control unit 11 performs driving assistance according to the recognition result of the moving object V. The control unit 11 recognizes the moving object V extracted by the second recognition result, which recognizes an object in the detection area T2 in front of the vehicle 1, as the object to be driven for assistance. The control unit 11 tracks the detected moving object V as the object to be driven for assistance.

[0029] The control unit 11 calculates the relative distance and relative speed between the detected moving object V and the vehicle 1. The control unit 11 calculates the TTC (Time to Collision), which indicates the time until the vehicle 1 collides with the moving object V, by dividing the relative distance by the relative speed. The control unit 11 monitors the TTC relative to the moving object V and, when the TTC is within a predetermined range indicating the approach of the moving object V, executes driving support control by outputting predetermined notifications such as voice or images from the input / output unit 3. Based on the recognition result of the moving object V, the control unit 11 monitors the TTC relative to the moving object V and, when the TTC falls below a predetermined threshold for contact with the moving object V, controls the braking unit 6, drive unit 5, and steering unit 7 to execute driving support control to prevent contact between the moving object V and the vehicle 1.

[0030] As shown in Figures 4 and 5, a road structure C1 may exist to the side of the lane R on which vehicle 1 is traveling. The road structure C1 is a structure that is adjacent to and continuously provided on the outside of lane R in a road environment, classified as, for example, a tunnel side wall, a bridge structural member, a retaining wall, a sound barrier, a guardrail, a steep cliff slope, a tree, or an underpass side wall. In a predetermined road environment where such a road structure C1 exists, the detection areas T1 and T2 may include the road structure C1.

[0031] In a predetermined road environment where road structures C1 are included in detection regions T1 and T2, the first recognition result of road structures C1 located near the moving object V and the second recognition result of road structures C1 located near the moving object V may be associated and calculated as the determination result H of the moving object V. As a result, if road structures C1 located near the moving object V are recognized as the moving object V, driving assistance may be performed, potentially causing inconvenience to the user. The vehicle control device 10 is configured to adjust the detection range in detection regions T1 and T2 based on user operation, for example. In addition to user operation, the control unit 11 is configured to automatically adjust the detection range of detection regions T1 and T2 according to the detection results of the road environment on which the vehicle 1 is traveling.

[0032] As shown in Figure 6, the control unit 11 determines whether or not to travel in a predetermined road environment where there is a possibility of misidentifying the moving object V, based on the detected value of the vehicle 1's current position. The control unit 11 obtains the detected value of the vehicle 1's current position data from the position sensor 2D and the autonomous sensor. The control unit 11 obtains map data including the current position stored in the storage unit 12. The control unit 11 may also obtain map data from the server device 20.

[0033] The control unit 11 performs a route search based on map data and determines the attributes of the lane R on which vehicle 1 is traveling. Based on the determination result of the attributes of lane R, the control unit 11 determines whether or not a predetermined road environment is included in lane R. If the control unit 11 determines that there is a possibility of misrecognizing a moving object V in the road environment regardless of the map data, it may determine that lane R is a predetermined road environment. Based on the recognition result using the captured image, the control unit 11 may determine that road construction sections, congested vehicles in adjacent lanes, road structures, etc., which are not present in the map data, are a predetermined road environment.

[0034] If the control unit 11 determines that a predetermined road environment is included in lane R, it calculates a first point X1 where the predetermined road environment begins and a second point X2 where the predetermined road environment ends in lane R. Based on the detected value of the vehicle's current position, if the control unit 11 determines that vehicle 1 has reached the first point X1, it determines that vehicle 1 is traveling through the predetermined road environment. For example, if the control unit 11 recognizes the road environment on which vehicle 1 is traveling as a tunnel or bridge based on the detected value of the vehicle's current position, it determines that the road environment is a predetermined road environment where there is a possibility of misidentifying a moving object. The control unit 11 is configured to adjust the detection range of the current detection areas T1 and T2 according to the detection result of the road environment on which vehicle 1 is traveling.

[0035] As shown in Figure 7, when the control unit 11 determines that a predetermined road environment exists, it adjusts to narrow detection areas T1A and T2A, which have a narrower detection range compared to the current detection areas T1 and T2. The narrow detection areas T1A and T2A are set to have a narrower scanning range for the lidar device 2B and the radar device 2C compared to the detection areas T1 and T2, so as not to include road structures C1 located outside the lane R.

[0036] The control unit 11 is configured to adjust the detection range to at least two stages: detection areas T1, T2 and narrow detection areas T1A, T2A. The control unit 11 may be configured to adjust the detection range not only in two stages, but freely according to the road environment. For example, if the control unit 11 determines that the road environment on which vehicle 1 is traveling is a tunnel or a bridge, it adjusts the current detection areas T1, T2 to narrow detection areas T1A, T2A so as not to include road structures C1 located to the side of the tunnel or bridge. The detection ranges of detection areas T1, T2 may be set in two or more stages in order of detection sensitivity. The control unit 11 may adjust to the narrow detection areas T1A, T2A in which the scanning range of the lidar device 2B and the detection sensitivity of the radar device 2C are set to the smallest among the multiple ranges set in stages, and / or the scanning range of the lidar device 2B and the scanning range of the radar device 2C are set to the smallest. In this case, for example, outside the narrow detection areas T1A and T2A, the detection sensitivity for the moving object V is high, and driving assistance is performed.

[0037] The control unit 11 detects a moving object V present in the detection area by relating a first recognition result obtained by image recognition of the detection area in front of the vehicle in the narrow detection area T1A with a second recognition result obtained by object recognition in the narrow detection area T2A. The control unit 11 calculates the TTC for the moving object V and performs driving assistance according to the calculated TTC value.

[0038] Based on the detected current position of the vehicle 1, the control unit 11 determines that the predetermined road environment has ended when it determines that the vehicle 1 has reached the second point X2. When the control unit 11 determines that the predetermined road environment has ended, it executes a process to return the narrow detection areas T1A and T2A to their original detection areas T1 and T2. The control unit 11 continues to perform driving assistance based on the detection areas T1 and T2 (see Figure 2). The detection areas T1 and T2 may be areas that have been adjusted based on user operations. When the control unit 11 determines that the predetermined road environment has ended, it may execute a process to return the narrow detection areas T1A and T2A to the detection areas T1 and T2 that have been adjusted based on user operations prior to the first point X1.

[0039] Figure 8 shows the processing flow of the vehicle control method executed in the vehicle control device 10. The vehicle control method is executed by a processor installed in the vehicle control device 10, which provides driving assistance for vehicle 1. The computer program installed in the vehicle control device 10 causes the processor to perform the following processes.

[0040] The control unit 11 detects the current position of the vehicle 1 using the detection unit 2 (S100). Based on the detected value of the vehicle 1's current position, the control unit 11 searches map data including the current position and determines whether the road environment of the lane R in which the vehicle 1 is traveling is a predetermined road environment (S102). If the control unit 11 determines that the road environment is not a predetermined road environment (S102: No), it adjusts the detection range of the lidar device 2B and / or radar device 2C to the detection areas T1 and T2 set by the user (S104).

[0041] When the control unit 11 recognizes a moving object V in the detection areas T1 and T2, it performs driving assistance for the moving object V (S106). Processing based on the detection areas T1 and T2 is performed within a predetermined time range of one cycle. The control unit 11 returns the process to S100 and continues processing. If the control unit 11 determines in S102 that the road environment is a predetermined road environment (S102: Yes), it adjusts the detection range of the lidar device 2B and / or radar device 2C to narrower detection areas T1A and T2A compared to the detection range of the detection areas T1 and T2 (S108).

[0042] When the control unit 11 recognizes a moving object V in the narrow detection areas T1A and T2A, it performs driving assistance for the moving object V (S110). Processing based on the narrow detection areas T1A and T2A is performed within a predetermined time range of one cycle. The control unit 11 returns the process to S100 and continues processing. If the control unit 11 determines in S102 that the predetermined road environment has ended (S102: No), it adjusts the detection range of the lidar device 2B and / or radar device 2C to the detection areas T1 and T2 (S104) and performs driving assistance (S106).

[0043] As described above, the vehicle control device 10 can reduce misrecognition of a moving object V by adjusting the detection range of the LiDAR device 2B and / or the radar device 2C when the road environment on which the vehicle 1 is traveling is a predetermined road environment where there is a possibility of misrecognizing a moving object V. The vehicle control device 10 can reduce misrecognition of a road structure C1 located near the lane R as a moving object V by adjusting the detection range of the LiDAR device 2B and / or the radar device 2C to narrow detection areas T1A and T2A that are narrower than the detection range of detection areas T1 and T2 in the predetermined road environment. The vehicle control device 10 can reduce the likelihood of users feeling annoyed by excessive driving assistance in the predetermined road environment.

[0044] In the embodiments described above, the computer programs executed in each configuration of the vehicle control device 10 may be provided in the form of being recorded on a computer-readable portable recording medium such as a semiconductor memory, a magnetic recording medium, or an optical recording medium. The computer programs may also be provided as a computer product for realizing the vehicle control device 10 and the vehicle control method. [Explanation of Symbols]

[0045] 1 Vehicle, 2 Detection unit, 2A Camera, 2B LiDAR device, 2C Radar device, 2D Position sensor, 3 Input / Output unit, 4 Communication unit, 5 Drive unit, 6 Braking unit, 7 Steering unit, 10 Vehicle control device, 11 Control unit, 12 Memory unit, 20 Server device, C1 Road structure, EL Organic, H Judgment result, M1 Acquired image, R Lane, T1, T2 Detection area, T1A, T2A Narrow detection area, V Moving object, W Network, X1 First point, X2 Second point

Claims

1. It is equipped with a control unit that performs driving assistance for the vehicle, The control unit, The first recognition result obtained by image recognition of the detection area in front of the vehicle and the second recognition result obtained by object recognition of the detection area are associated to detect a moving object present in the detection area. The driving assistance is performed according to the recognition result of the moving object. The detection range of the detection area is adjusted according to the detection results of the road environment on which the vehicle is traveling. If it is determined that the road environment is a predetermined road environment in which there is a possibility of misidentifying the moving object, the moving object is detected in a narrow detection area which is a reduced detection range. Vehicle control system.

2. The control unit, If it is determined that the predetermined road conditions have ended, the narrow detection area is returned to the detection area, and the driving assistance is continued. The vehicle control device according to claim 1.

3. The control unit, If the aforementioned road environment is recognized as a tunnel or bridge, it is determined to be the aforementioned specified road environment. The current detection range is adjusted to the narrow detection area so as not to include road structures located to the side of the tunnel or bridge. The vehicle control device according to claim 1.

4. The control unit, If the aforementioned road environment is recognized as a tunnel or bridge, it is determined to be the aforementioned specified road environment. The detection range is adjusted to the narrow detection region with the lowest detection sensitivity among a plurality of ranges set in steps according to the detection sensitivity. The vehicle control device according to claim 1.

5. A vehicle control method for performing driving assistance for a vehicle, The computer that constitutes the vehicle control system mounted on the aforementioned vehicle, The first recognition result obtained by image recognition of the detection area in front of the vehicle and the second recognition result obtained by object recognition of the detection area are associated to detect a moving object present in the detection area. The driving assistance is performed according to the recognition result of the moving object. The detection range of the detection area is adjusted according to the detection results of the road environment on which the vehicle is traveling. If it is determined that the road environment is a predetermined road environment in which there is a possibility of misidentifying the moving object, the moving object is detected in a narrow detection area which is a reduced detection range. Vehicle control method.

6. A computer program executed by a processor mounted on a vehicle control system that provides driving assistance for a vehicle, The first recognition result obtained by image recognition of the detection area in front of the vehicle and the second recognition result obtained by object recognition of the detection area are associated to detect a moving object present in the detection area. The driving assistance is performed according to the recognition result of the moving object. The detection range of the detection area is adjusted according to the detection results of the road environment on which the vehicle is traveling. If it is determined that the road environment is a predetermined road environment in which there is a possibility of misidentifying the moving object, the processor is instructed to perform a process to detect the moving object in a narrow detection area which is a reduced detection range. Computer program.

Images