JP2017084137A - Road section line recognition device, vehicle control apparatus, road section line recognition method, and road section line recognition program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a road section line recognition device, a vehicle control apparatus, a road section line recognition method, and a road section line recognition program, which enable the determination of a level of certainty of a road section line more accurately.SOLUTION: A road section line recognition device includes: a first road section line recognition part for recognizing a first road section line pattern from an image picked up by an imaging part that images a road surrounding a vehicle itself; a second road section line recognition part for recognizing a second road section line pattern on the basis of a position of the vehicle itself on the basis of a radio wave from a satellite and map information; and a determination part for comparing between the first road section line pattern recognized by the first road section line recognition part and the second road section line pattern recognized by the second road section line recognition part, and determining a level of certainty of the position of the road section line recognized at least by the first road section line recognition part.SELECTED DRAWING: Figure 3

Description

  The present invention relates to a road lane marking recognition device, a vehicle control device, a road lane marking recognition method, and a road lane marking recognition program.

  In recent years, research has been conducted on technologies for automatically driving vehicles such as four-wheel vehicles. In this connection, when the driver operates the instruction means for instructing the start of the automatic driving of the host vehicle, the setting means for setting the destination of automatic driving, and the instruction means by the driver, Determining means for determining an automatic driving mode based on whether or not the destination is set, and a control means for controlling vehicle travel based on the automatic driving mode determined by the determining means, When the destination is not set, the determination means determines whether the automatic driving mode is automatic driving or automatic stopping that travels along the current traveling path of the host vehicle. (For example, refer to Patent Document 1).

International Publication No. 2011/158347

  However, in the conventional technique, there is a case where the certainty of the road lane marking cannot be accurately determined.

  The present invention has been made in view of such circumstances, and is capable of determining the accuracy of a road lane marking more accurately, a road lane marking recognition device, a vehicle control device, a road lane marking recognition method, and One of the purposes is to provide a road lane marking recognition program.

  The invention according to claim 1 recognizes the position and type of the road marking line included in the image captured by the imaging unit that images the road around the host vehicle, and determines the position and type of the recognized road marking line. A position of the host vehicle acquired by a first road lane marking recognition unit that recognizes a first road lane marking pattern including the host vehicle position acquisition unit that acquires a position of the host vehicle based on radio waves from a satellite; And a second road lane line pattern including the position and type of the road lane line is recognized by searching map information in which the position and type of the road lane line is described in association with the position of the road. 2 road lane line recognition units, a first road lane line pattern recognized by the first road lane line recognition unit, and a second road lane line recognized by the second road lane line recognition unit Compare with pattern A road division line recognition apparatus and a determination unit for determining at least certainty of position of the first recognized road segment line by the road lane line recognition unit.

  The invention according to claim 2 is the invention according to claim 1, wherein the first road lane marking recognition unit recognizes the color of the road lane marking included in the image captured by the imaging unit, Recognizing the first road lane marking pattern including the recognized road lane marking color, the map information describes the color of the road lane marking in association with the position of the road, and the second road lane marking; The line recognition unit recognizes the second road lane marking pattern including the color of the road lane marking.

  According to a third aspect of the present invention, in the invention according to the first or second aspect, in addition to the comparison between the first road lane line pattern and the second road lane line pattern, the determination unit The position of the road lane line recognized by at least the first road lane line recognition unit based on the recognition result of the first road lane line recognition unit or the individual factor of the recognition result of the second road lane line recognition unit This is to determine the certainty.

  According to a fourth aspect of the present invention, in the third aspect of the invention, the determination unit determines that the position of the road lane line that is repeatedly recognized by the first road lane line recognition unit is vibrating. When the vibration condition is satisfied, at least the probability of the position of the road lane marking recognized by the first road lane marking recognition unit is reduced.

  According to a fifth aspect of the present invention, in the invention according to the third or fourth aspect, the determination unit is a road segment that is repeatedly recognized by the first road segment line recognition unit or the second road segment line recognition unit. The probability of the position of the road marking line recognized by at least the first road marking line recognition unit is reduced based on the number of times or the frequency at which the line position can be identified.

  The invention according to claim 6 is the invention according to any one of claims 3 to 5, wherein the determination unit is based on the position of the host vehicle acquired by the host vehicle position acquisition unit and the map information. When it is determined that the host vehicle is traveling near a point where the type of the road lane marking changes, at least the position of the road lane marking recognized by the first road lane marking recognition unit It reduces the certainty.

  The invention according to claim 7 is the invention according to any one of claims 3 to 6, wherein the determination unit is based on the position of the host vehicle and the map information acquired by the host vehicle position acquisition unit. Reducing the likelihood of the position of the road marking line recognized by at least the first road marking line recognition unit when it is determined that the host vehicle is traveling at a point where the road branches or merges It is.

  The invention according to claim 8 is the invention according to any one of claims 3 to 7, wherein the determination unit is based on the position of the own vehicle and the map information acquired by the own vehicle position acquisition unit. , When it is determined that the vehicle is traveling at a point where the road is marked differently from the road marking line, at least of the road marking line recognized by the first road marking line recognition unit This reduces the accuracy of the position.

  The invention according to claim 9 is determined by the road lane marking recognition device according to any one of claims 1 to 8 and the road lane marking recognition device to have a certainty or more certainty. A track generation unit that generates a track on which the host vehicle should travel based on the position of the road marking line, and a travel control unit that drives the host vehicle along the track generated by the track generation unit; It is a vehicle control apparatus provided with.

  The invention according to a tenth aspect is the invention according to the ninth aspect, wherein the trajectory generating unit has not been determined to have a certain degree of certainty by the road lane marking recognition device. Complementation is performed based on the position of the road lane marking that has been determined to be more than a certain degree of accuracy by the road lane marking recognition device in the past, and a track on which the host vehicle should travel is generated.

  In the invention according to claim 11, the in-vehicle computer recognizes the position and type of the road marking line included in the image captured by the imaging unit that images the road around the host vehicle, and the recognized road marking line. Recognizing the first road marking line pattern including position and type, and using the position of the host vehicle acquired by the host vehicle position acquisition unit that acquires the position of the host vehicle based on radio waves from satellites, By searching for map information in which the position and type of the road lane line are described in association with the position, a second road lane line pattern including the position and type of the road lane line is recognized, and the first road A road lane line recognition that compares a lane line pattern with the second road lane line pattern and determines the likelihood of the position of the road lane line recognized by at least the first road lane line recognition unit. It is a method.

  According to the twelfth aspect of the present invention, the in-vehicle computer recognizes the position and type of the road marking line included in the image captured by the imaging unit that images the road around the host vehicle, and the recognized road marking line. Using the position of the host vehicle acquired by the host vehicle position acquisition unit that recognizes the first road lane marking pattern including the position and type and acquires the position of the host vehicle based on radio waves from a satellite, By searching for map information in which the position and type of the road lane line are described in association with the position, a second road lane line pattern including the position and type of the road lane line is recognized, and the first road A road block that compares a lane line pattern with the second road lane line pattern and determines the likelihood of the position of the road lane line recognized by at least the first road lane line recognition unit. Is a line recognition program.

  According to the first to eighth, eleventh, or twelfth aspects of the present invention, it is possible to more accurately determine the probability of the road marking line.

  According to the invention described in claim 9 or 10, more accurate vehicle control can be performed based on the probability of the road lane marking determined by the road lane marking recognition device.

It is a figure which shows the component which the vehicle by which the vehicle control apparatus 100 which concerns on embodiment is mounted in has. It is a functional lineblock diagram of self-vehicles M centering on vehicle control device 100 concerning an embodiment. It is a block diagram centering on the own vehicle position recognition part. It is a figure which shows an example of the captured image IM by the camera. It is the figure which imaged the 1st road lane marking pattern recognized by the 1st road lane marking recognition part 102A. It is a figure which shows a mode that the relative position of the own vehicle M with respect to the driving lane L1 is recognized by 102 A of 1st road marking lines recognition parts. It is a figure which shows some information contained in the map information 152. FIG. It is a flowchart which shows an example of the flow of the process performed by 102 C of determination parts. It is a figure which shows an example of the action plan produced | generated about a certain area. It is a figure which shows an example of the track | orbit produced | generated by the 1st track | orbit production | generation part 112. FIG. It is a figure which shows a mode that the target position setting part 122 in embodiment sets the target area | region TA. It is a figure which shows a mode that the 2nd track generation part 126 in an embodiment generates a track.

Hereinafter, embodiments of a road lane marking recognition device, a vehicle control device, a road lane marking recognition method, and a road lane marking recognition program according to the present invention will be described with reference to the drawings.
[Vehicle configuration]
FIG. 1 is a diagram illustrating components included in a vehicle (hereinafter referred to as a host vehicle M) on which a vehicle control device 100 according to the embodiment is mounted. The vehicle on which the vehicle control device 100 is mounted is, for example, a motor vehicle such as a two-wheel, three-wheel, or four-wheel vehicle, and a vehicle using an internal combustion engine such as a diesel engine or a gasoline engine as a power source, or an electric vehicle using a motor as a power source. And a hybrid vehicle having an internal combustion engine and an electric motor. Moreover, the electric vehicle mentioned above drives using the electric power discharged by batteries, such as a secondary battery, a hydrogen fuel cell, a metal fuel cell, and an alcohol fuel cell, for example.

  As shown in FIG. 1, the vehicle M includes a finder 20-1 to 20-7, a radar 30-1 to 30-6, a sensor such as a camera 40, a navigation device 50, and the vehicle control device 100 described above. And will be installed. The finders 20-1 to 20-7 are, for example, LIDAR (Light Detection and Ranging) that measures scattered light with respect to irradiation light and measures the distance to the target. For example, the finder 20-1 is attached to a front grill or the like, and the finders 20-2 and 20-3 are attached to a side surface of a vehicle body, a door mirror, the inside of a headlamp, a side lamp, and the like. The finder 20-4 is attached to a trunk lid or the like, and the finders 20-5 and 20-6 are attached to the side surface of the vehicle body, the interior of the taillight, or the like. The above-described finders 20-1 to 20-6 have a detection area of about 150 degrees in the horizontal direction, for example. The finder 20-7 is attached to a roof or the like. The finder 20-7 has a detection area of 360 degrees in the horizontal direction, for example.

  The above-described radars 30-1 and 30-4 are, for example, long-range millimeter wave radars having a detection area in the depth direction wider than other radars. Radars 30-2, 30-3, 30-5, and 30-6 are medium-range millimeter-wave radars that have a narrower detection area in the depth direction than radars 30-1 and 30-4. Hereinafter, when the finders 20-1 to 20-7 are not particularly distinguished, they are simply referred to as “finder 20”, and when the radars 30-1 to 30-6 are not particularly distinguished, they are simply referred to as “radar 30”. The radar 30 detects an object by, for example, an FM-CW (Frequency Modulated Continuous Wave) method.

  The camera 40 is a digital camera using an individual image sensor such as a CCD (Charge Coupled Device) or a CMOS (Complementary Metal Oxide Semiconductor). The camera 40 is attached to the upper part of the front windshield, the rear surface of the rearview mirror or the like. For example, the camera 40 periodically images the front of the host vehicle M repeatedly.

  The configuration illustrated in FIG. 1 is merely an example, and a part of the configuration may be omitted, or another configuration may be added.

  FIG. 2 is a functional configuration diagram of the host vehicle M centering on the vehicle control device 100 according to the embodiment. In addition to the finder 20, the radar 30, and the camera 40, the host vehicle M includes a navigation device 50, a vehicle sensor 60, an operation device 70, an operation detection sensor 72, a changeover switch 80, and a travel driving force output device 90. The steering device 92, the brake device 94, and the vehicle control device 100 are mounted. These devices and devices are connected to each other by a multiple communication line such as a CAN (Controller Area Network) communication line, a serial communication line, a wireless communication network, or the like.

  The navigation device 50 includes a GNSS (Global Navigation Satellite System) receiver and map information (navigation map) that identifies the position of the host vehicle M based on radio waves from a satellite, a touch panel display device that functions as a user interface, a speaker, a microphone Etc. The navigation device 50 identifies the position of the host vehicle M using the GNSS receiver, and derives a route from the position to the destination specified by the user. The route derived by the navigation device 50 is stored in the storage unit 150 as route information 154. The position of the host vehicle M may be specified or supplemented by an INS (Inertial Navigation System) using the output of the vehicle sensor 60. In addition, the navigation device 50 guides the route to the destination by voice or navigation display when the vehicle control device 100 is executing the manual operation mode. The configuration for specifying the position of the host vehicle M may be provided independently of the navigation device 50. Moreover, the navigation apparatus 50 may be implement | achieved by one function of terminal devices, such as a smart phone and a tablet terminal which a user holds, for example. In this case, information is transmitted and received between the terminal device and the vehicle control device 100 by radio or communication. The configuration for specifying the position of the host vehicle M may be provided independently of the navigation device 50.

  The vehicle sensor 60 includes a vehicle speed sensor that detects a vehicle speed, an acceleration sensor that detects acceleration, a yaw rate sensor that detects an angular velocity around a vertical axis, a direction sensor that detects the direction of the host vehicle M, and the like.

  For example, when the host vehicle M is an automobile using an internal combustion engine as a power source, the traveling driving force output device 90 includes an engine and an engine ECU (Electronic Control Unit) that controls the engine, and the host vehicle M uses a motor as a power source. When the vehicle M is a hybrid vehicle, an engine and an engine ECU, a traveling motor, and a motor ECU are provided. When the travel driving force output device 90 includes only the engine, the engine ECU adjusts the throttle opening, shift stage, etc. of the engine in accordance with information input from the travel control unit 130, which will be described later, and travel for the vehicle to travel. Outputs driving force (torque). Further, when the travel driving force output device 90 includes only the travel motor, the motor ECU adjusts the duty ratio of the PWM signal given to the travel motor according to the information input from the travel control unit 130, and the travel drive described above. Output force. Further, when the traveling driving force output device 90 includes an engine and a traveling motor, both the engine ECU and the motor ECU control the traveling driving force in cooperation with each other according to information input from the traveling control unit 130.

  The steering device 92 includes, for example, an electric motor, a steering torque sensor, a steering angle sensor, and the like. The electric motor changes the direction of the steering wheel by applying a force to a rack and pinion function or the like, for example. The steering torque sensor detects, for example, twisting of the torsion bar when the steering wheel is operated as steering torque (steering force). For example, the steering angle sensor detects a steering angle (or an actual steering angle). The steering device 92 drives the electric motor according to the information input from the travel control unit 130 and changes the direction of the steering wheel.

  The brake device 94 includes a master cylinder to which a brake operation performed on the brake pedal is transmitted as hydraulic pressure, a reservoir tank that stores brake fluid, a brake actuator that adjusts a braking force output to each wheel, and the like. The brake control unit 44 controls the brake actuator and the like so that the brake torque according to the pressure of the master cylinder is output to each wheel according to the information input from the travel control unit 130. The brake device 94 is not limited to the electronically controlled brake device that operates by the hydraulic pressure described above, but may be an electronically controlled brake device that operates by an electric actuator.

  The operation device 70 includes, for example, an accelerator pedal, a steering wheel, a brake pedal, a shift lever, and the like. The operation device 70 is provided with an operation detection sensor 72 that detects the presence / absence and amount of operation by the driver. The operation detection sensor 72 includes, for example, an accelerator opening sensor, a steering torque sensor, a brake sensor, a shift position sensor, and the like. The operation detection sensor 72 outputs the accelerator opening, steering torque, brake pedal stroke, shift position, and the like as detection results to the travel control unit 130. Instead of this, the detection result of the operation detection sensor 72 may be directly output to the travel driving force output device 90, the steering device 92, or the brake device 94.

  The changeover switch 80 is a switch operated by a driver or the like. The changeover switch 80 may be, for example, a mechanical switch installed on a steering wheel, a garnish (dashboard), or a GUI (Graphical User Interface) switch provided on the touch panel of the navigation device 50. Good. The changeover switch 80 receives an operation of a driver or the like, generates a control mode designation signal that designates the control mode by the traveling control unit 130 as either the automatic driving mode or the manual driving mode, and outputs the control mode designation signal to the control switching unit 140. . As described above, the automatic operation mode is an operation mode that travels in a state where the driver does not perform an operation (or the operation amount is small or the operation frequency is low compared to the manual operation mode), and more specifically. Is an operation mode in which a part or all of the driving force output device 90, the steering device 92, and the brake device 94 are controlled based on the action plan.

[Vehicle control device]
Hereinafter, the vehicle control apparatus 100 will be described. The vehicle control device 100 includes, for example, a host vehicle position recognition unit 102, an external environment recognition unit 104, an action plan generation unit 106, a travel mode determination unit 110, a first track generation unit 112, and a lane change control unit 120. The travel control unit 130, the storage control unit 132, the control switching unit 140, and the storage unit 150 are provided. Self-vehicle position recognition unit 102 (including each unit described later), external environment recognition unit 104, action plan generation unit 106, travel mode determination unit 110, first track generation unit 112, lane change control unit 120, travel control unit 130, storage Part or all of the control unit 132 and the control switching unit 140 is a software function unit that functions when a processor such as a CPU (Central Processing Unit) executes a program. Some or all of these may be hardware function units such as LSI (Large Scale Integration) and ASIC (Application Specific Integrated Circuit). The storage unit 150 is realized by a ROM (Read Only Memory), a RAM (Random Access Memory), an HDD (Hard Disk Drive), a flash memory, or the like. The program executed by the processor may be stored in the storage unit 150 in advance, or may be downloaded from an external device via an in-vehicle internet facility or the like. Further, the portable storage medium storing the program may be installed in the storage unit 150 by being mounted on a drive device (not shown).

  The own vehicle position recognition unit 102 is based on the map information 152 stored in the storage unit 150 and information input from the finder 20, the radar 30, the camera 40, the navigation device 50, or the vehicle sensor 60. Recognizes the lane in which the vehicle is traveling (the traveling lane) and the relative position of the host vehicle M with respect to the traveling lane. The map information 152 is, for example, map information with higher accuracy than the navigation map included in the navigation device 50, and includes information on the center of the lane or information on the boundary of the lane. More specifically, the map information 152 includes road information, traffic regulation information, address information (address / postal code), facility information, telephone number information, and the like. The road information includes information indicating types of roads such as expressways, toll roads, national roads, and prefectural roads, the number of road lanes, the width of each lane, and the type of road lane marking that divides the lane (solid line, broken line, thick line). It includes a solid line, a thick broken line, a dot sequence (bottom dot or cat's eye)) and a color (white line or yellow line). In addition, road information includes road gradient, road position (three-dimensional coordinates including longitude, latitude, and height), lane curve curvature, lane junction and branch point positions, road signs, etc. Information is included. The traffic regulation information includes information that the lane is blocked due to construction, traffic accidents, traffic jams, or the like.

  FIG. 3 is a configuration diagram centering on the vehicle position recognition unit 102. The own vehicle position recognition unit 102 includes a first road lane marking recognition unit 102A, a second road lane marking recognition unit 102B, and a determination unit 102C. These components constitute a “road marking line recognition device”.

  The first road lane marking recognition unit 102A recognizes the position and type of the road lane marking included in the image captured by the camera 40 and includes the position and type of the recognized road lane marking. Recognize patterns. FIG. 4 is a diagram illustrating an example of a captured image IM by the camera 40. The first road lane marking recognition unit 102A extracts road lane line contour candidates by, for example, edge extraction processing or straight line extraction processing, and determines an area formed by two contour candidates having a predetermined width as road lane markings. Recognize as In the example of FIG. 4, a solid road partition line PL1 drawn at the left end of the road, broken road partition lines PL2 to PL4, and a solid road partition line PL5 drawn at the right end of the road are recognized. The first road marking line recognition unit 102A detects the color of the road marking line by detecting the color or luminance in the captured image IM.

FIG. 5 is an image of the first road lane marking pattern recognized by the first road lane marking recognition unit 102A. As shown in the figure, the first road lane marking pattern is, for example, a road with four lanes on one side, solid road lane markings at both ends, and a broken road lane marking separating the lanes between them. There are three, and the width of each lane (indicated by D ₁₂ , D ₂₃ , D ₃₄ , and D ₄₅ in the figure) is recognized in terms of how many meters it is.

  Furthermore, the first road lane marking recognition unit 102A recognizes the relative position of the host vehicle M with respect to the lane (traveling lane) in which the host vehicle M is traveling. FIG. 6 is a diagram illustrating a state in which the relative position of the host vehicle M with respect to the traveling lane L1 is recognized by the first road lane marking recognition unit 102A. The own vehicle position recognizing unit 102 is, for example, a line connecting the deviation OS of the reference point (for example, the center of gravity or the center of the rear wheel axle) of the own vehicle M from the travel lane center CL and the travel lane center CL in the traveling direction of the own vehicle M Is recognized as the relative position of the host vehicle M with respect to the traveling lane L1. Instead, the first road lane marking recognition unit 102A uses the position of the reference point of the host vehicle M with respect to any side edge of the host lane L1 as the relative position of the host vehicle M with respect to the traveling lane. You may recognize it.

  The second road lane marking recognition unit 102B searches the map information 152 using the position of the host vehicle M acquired by the navigation device 50, so that the second road lane marking including the position and type of the road lane marking is obtained. Recognize patterns. FIG. 7 is a diagram illustrating a part of information included in the map information 152. As shown in the figure, the map information 152 describes information such as the number of lanes, the color of road lane markings, and the road width (or width for each lane) for each road section (including the direction). The second road lane marking recognition unit 102B derives the position and traveling direction of the host vehicle M from the history of the position of the host vehicle M acquired by the navigation device 50, and extracts items of the map information 152 corresponding thereto. . And, based on information such as the number of lanes extracted, the color of the road lane marking, the road width, etc., there is a broken road lane marking between the solid road lane markings at both ends, or the number if there is, Information such as the width of each lane is derived and recognized as the second road lane marking pattern.

  The determination unit 102C compares the first road lane line pattern recognized by the first road lane line recognition unit 102A and the second road lane line pattern recognized by the second road lane line recognition unit 102B. Then, the likelihood of the position of the road lane marking recognized by at least the first road lane marking recognition unit 102A is determined. For example, the determination unit 102C calculates a score indicating the likelihood of the position for each road lane marking.

  In addition to the comparison between the first road lane line pattern and the second road lane line pattern, the determination unit 102C recognizes the recognition result by the first road lane line recognition unit 102A or the second road lane line recognition unit 102B. Based on the individual factors of the recognition result, at least the likelihood of the position of the road lane marking recognized by the first road lane marking recognition unit 102A is determined. Hereinafter, these processes will be described.

  FIG. 8 is a flowchart illustrating an example of a flow of processing executed by the determination unit 102C. The processing of this flowchart is executed for each road lane marking included in the first road lane marking pattern and the second road lane marking pattern.

First, the determination unit 102C determines whether or not the type and color of the road lane marking line match in the comparison between the first road lane marking pattern and the second road lane marking pattern (step S200). If the type and color of the road lane lines do not match between patterns, the determination unit 102C is, [alpha] 1 decreases the scores from the base score alpha _b (step S202). Here, the score is an index value indicating the probability of the position (or presence) of the road marking line. Also, [alpha] 1 may be the same value as the base score alpha _b. That is, if the type and color of the road lane marking do not match between the patterns, the determination unit 102C may reject the position of the road lane marking.

  Moreover, the determination process of step S200 may determine whether a 1st road lane marking pattern and a 2nd road lane marking pattern correspond as a whole. Here, “matching as a whole” may mean that it is not determined whether or not the road marking lines that exist outside the angle of view of the camera 40 match. In this case, the determination unit 102 </ b> C may vary α <b> 1 to be subtracted between a case where the target road lane line does not match and a case where road lane lines other than the target road lane line do not match.

Next, the determination unit 102C determines whether or not the position of the road lane marking is vibrating in the detection result by the first road lane marking recognition unit 102A (step S204). For example, the determination unit 102 </ b> C determines that the road lane marking of the road lane line is satisfied when a vibration condition such that the displacement of the road lane marking in the width direction of the host vehicle M fluctuates by a predetermined distance or more within a predetermined period satisfies a reference value or more. It is determined that the position is vibrating. Such a phenomenon indicates that the position of the road lane marking is difficult to detect by redrawing or the like such as blurring of the road lane marking. When the position of the road marking line is vibrating, the determination unit 102C reduces the score by α2 (step S206). Here, the score for which decreasing α2, the base score alpha _b or a score process is performed to α1 decreases from the base score alpha _b in S202. Hereinafter, it is assumed that the score is sequentially lowered in the same manner.

  Next, the determination unit 102C determines whether or not the number of times (or frequency) that can be identified in the road lane line identification process repeatedly performed by the first road lane line recognition unit 102A is equal to or greater than a threshold value. (Step S208). When the number (or frequency) at which identification was possible is less than the threshold, the determination unit 102C decreases the score by α3 (step S210).

  Next, the determination unit 102C determines whether or not the host vehicle M is traveling at a point where the type (and / or color) of the road lane marking changes (step S212). Information about the point where the host vehicle M is traveling is acquired based on the result of the second road lane marking recognition unit 102B searching the map information 152. When the host vehicle M is traveling at a point where the type (and / or color) of the road marking line changes, the determination unit 102C decreases the score by α4 (step S214). This is because misrecognition is likely to occur at such points in recognition processing of road lane markings by image analysis.

  Next, the determination unit 102C determines whether or not the host vehicle M is traveling at a point where the road branches or merges (step S216). When the host vehicle M is traveling at a point where the road branches or merges, the determination unit 102C decreases the score by α5 (step S218). This is because misrecognition is likely to occur at such points in recognition processing of road lane markings by image analysis.

  Next, the determination unit 102C determines whether or not a sign (speed sign, temporary stop sign, or other sign) different from the road lane marking is placed on the road (step S220). When a sign different from the road lane marking is provided on the road, the determination unit 102C decreases the score by α6 (step S222). This is because misrecognition is likely to occur at such points in recognition processing of road lane markings by image analysis.

  Then, the determination unit 102C determines whether or not the final score sequentially subtracted by the processes in steps S200 to S222 is equal to or greater than a threshold value (step S224). When the final score is greater than or equal to the threshold, the determination unit 102 employs the road lane line as a control reference (step S226). When the final score is less than the threshold, the determination unit 102 does not employ the road lane line as a control reference ( (Reject) (step S228).

  By such processing, the vehicle position recognition unit (road lane line recognition device) 102 can more accurately determine the likelihood of the road lane line.

  The external environment recognition unit 104 recognizes the position of the surrounding vehicle and the state such as speed and acceleration based on information input from the finder 20, the radar 30, the camera 40, and the like. The peripheral vehicle in the present embodiment is a vehicle that travels around the host vehicle M and travels in the same direction as the host vehicle M. The position of the surrounding vehicle may be represented by a representative point such as the center of gravity or corner of the other vehicle, or may be represented by a region expressed by the contour of the other vehicle. The “state” of the surrounding vehicle may include the acceleration of the surrounding vehicle and whether or not the lane is changed (or whether or not the lane is changed) based on the information of the various devices. In addition to the surrounding vehicles, the external environment recognition unit 104 may recognize the positions of guardrails, utility poles, parked vehicles, pedestrians, and other objects.

  The action plan generation unit 106 generates an action plan in a predetermined section. The predetermined section is, for example, a section that passes through a toll road such as an expressway among the routes derived by the navigation device 50. Not only this but the action plan production | generation part 106 may produce | generate an action plan about arbitrary sections.

  The action plan is composed of, for example, a plurality of events that are sequentially executed. Examples of the event include a deceleration event for decelerating the host vehicle M, an acceleration event for accelerating the host vehicle M, a lane keeping event for driving the host vehicle M so as not to deviate from the traveling lane, and a lane change event for changing the traveling lane. In the overtaking event in which the own vehicle M overtakes the preceding vehicle, in the branch event in which the own vehicle M is changed so as not to deviate from the current driving lane, or in the lane junction point A merging event for accelerating / decelerating the vehicle M and changing the traveling lane is included. For example, when a junction (branch point) exists on a toll road (for example, an expressway), the vehicle control device 100 changes the lane so that the host vehicle M travels in the direction of the destination in the automatic driving mode. Need to maintain lanes. Therefore, when it is determined that the junction exists on the route with reference to the map information 152, the action plan generation unit 106 from the current position (coordinates) of the host vehicle M to the position (coordinates) of the junction. In the meantime, a lane change event is set for changing the lane to a desired lane that can proceed in the direction of the destination. Information indicating the action plan generated by the action plan generation unit 106 is stored in the storage unit 150 as action plan information 156.

  FIG. 9 is a diagram illustrating an example of an action plan generated for a certain section. As shown in the figure, the action plan generation unit 106 classifies scenes that occur when traveling according to a route to a destination, and generates an action plan so that an event corresponding to each scene is executed. In addition, the action plan production | generation part 106 may change an action plan dynamically according to the condition change of the own vehicle M. FIG.

  For example, the action plan generation unit 106 may change (update) the generated action plan based on the state of the outside world recognized by the outside world recognition unit 104. In general, while the vehicle is traveling, the state of the outside world constantly changes. In particular, when the host vehicle M travels on a road including a plurality of lanes, the distance between the other vehicles changes relatively. For example, when the vehicle ahead is decelerated by applying a sudden brake, or when a vehicle traveling in an adjacent lane enters the front of the host vehicle M, the host vehicle M determines the behavior of the preceding vehicle or the adjacent lane. It is necessary to travel while appropriately changing the speed and lane according to the behavior of the vehicle. Therefore, the action plan generation unit 106 may change the event set for each control section in accordance with the external state change as described above.

  Specifically, the action plan generation unit 106 determines that the speed of the other vehicle recognized by the external recognition unit 104 during traveling of the vehicle exceeds a threshold value or the direction of movement of the other vehicle traveling in the lane adjacent to the own lane is autonomous. When the vehicle heads in the lane direction, the event set in the driving section where the host vehicle M is scheduled to travel is changed. For example, when the event is set so that the lane change vent is executed after the lane keep event, the vehicle is more than the threshold from the rear of the lane to which the lane is changed during the lane keep event according to the recognition result of the external recognition unit 104. When it is determined that the vehicle has traveled at the speed of, the action plan generation unit 106 changes the event next to the lane keep event from a lane change to a deceleration event, a lane keep event, or the like. As a result, the vehicle control device 100 can avoid the host vehicle M from colliding with the lane change destination vehicle. As a result, the vehicle control device 100 can safely drive the host vehicle M safely even when a change occurs in the external environment.

[Lane Keep Event]
When the lane keeping event included in the action plan is executed by the travel control unit 130, the travel mode determination unit 110 is one of constant speed travel, follow-up travel, deceleration travel, curve travel, obstacle avoidance travel, etc. The travel mode is determined. For example, the traveling mode determination unit 110 determines the traveling mode to be constant speed traveling when there is no other vehicle ahead of the host vehicle. In addition, the travel mode determination unit 110 determines the travel mode to follow running when traveling following the preceding vehicle. In addition, the travel mode determination unit 110 determines the travel mode to be decelerated when the external environment recognition unit 104 recognizes deceleration of the preceding vehicle or when an event such as stopping or parking is performed. In addition, the travel mode determination unit 110 determines the travel mode to be a curve travel when the outside recognition unit 104 recognizes that the host vehicle M has reached a curved road. In addition, when the outside recognition unit 104 recognizes an obstacle in front of the host vehicle M, the driving mode determination unit 110 determines the driving mode as obstacle avoidance driving.

  The first trajectory generation unit 112 generates a trajectory based on the travel mode determined by the travel mode determination unit 110. A track is a set of points obtained by sampling a future target position expected to reach when the host vehicle M travels based on the travel mode determined by the travel mode determination unit 110 (every predetermined time). Locus).

  FIG. 10 is a diagram illustrating an example of a trajectory generated by the first trajectory generation unit 112. As shown to (A) in the figure, for example, the first trajectory generation unit 112 uses the current position of the host vehicle M as a reference every time a predetermined time Δt has elapsed from the current time, K (1), K (2) , K (3),... Are set as the track of the host vehicle M. Hereinafter, when these target positions are not distinguished, they are simply referred to as “target positions K”. For example, the number of target positions K is determined according to the target time T. For example, when the target time T is set to 5 seconds, the first trajectory generation unit 112 sets the target position K on the center line of the traveling lane in a predetermined time Δt (for example, 0.1 second) in this 5 seconds, The arrangement intervals of the plurality of target positions K are determined based on the running mode. For example, the first track generation unit 112 may derive the center line of the traveling lane from information such as the width of the lane included in the map information 152. You may acquire from the map information 152.

  For example, when the travel mode is determined to be constant speed travel by the travel mode determination unit 110 described above, the first trajectory generation unit 112 sets a plurality of target positions K at equal intervals, as shown in FIG. To generate a trajectory. When the travel mode is determined by the travel mode determination unit 110 to be decelerated travel (including the case where the preceding vehicle is decelerated during the follow-up travel), the first trajectory generation unit 112 is as shown in FIG. The trajectory is generated by increasing the interval for the target position K that arrives earlier and narrowing the interval for the target position K that arrives later. As a result, the target position K that arrives later from the host vehicle M approaches the current position of the host vehicle M, so that the travel control unit 130 described later decelerates the host vehicle M.

  Further, as shown in (C) in the figure, when the road is a curved road, the traveling mode determining unit 110 determines the traveling mode to be curved traveling. In this case, for example, the first trajectory generation unit 112 arranges a plurality of target positions K while changing the lateral position (position in the lane width direction) with respect to the traveling direction of the host vehicle M according to the curvature of the road. Is generated. Further, as shown in (D) in the figure, when an obstacle OB such as a human or a stopped vehicle exists on the road ahead of the host vehicle M, the traveling mode determination unit 110 sets the traveling mode to the obstacle avoidance traveling. decide. In this case, the first trajectory generation unit 112 generates a trajectory by arranging a plurality of target positions K so as to travel while avoiding the obstacle OB.

  Note that the first track generation unit 112 is based on the position of the road lane marking determined by the determination unit 102C of the own vehicle position recognition unit 102 to have a certain degree of certainty (adopted as a control reference). Generate a trajectory for The first trajectory generation unit 112 has previously determined that the road marking line that has not been determined to have a certain degree of certainty or more (rejected) by the determination unit 102C of the vehicle position recognition unit 102 is the vehicle position recognition unit. Completion is performed based on the position of the road lane marking determined to have a certain degree of certainty or not by 102, and a track on which the host vehicle M should travel is generated. The same applies to the second trajectory generation unit 126 described below.

[Lane change event]
The lane change control unit 120 performs control when a lane change event included in the action plan is executed by the travel control unit 130. The lane change control unit 120 includes, for example, a target position setting unit 122, a lane change availability determination unit 124, and a second track generation unit 126. The lane change control unit 120 may perform processing to be described later when a branching event or a merging event is performed by the traveling control unit 130.

  The target position setting unit 122 travels in an adjacent lane adjacent to a lane (own lane) in which the host vehicle M travels, travels in front of the host vehicle M, travels in an adjacent lane, and A vehicle traveling behind the vehicle M is specified, and a target area TA is set between these vehicles. Hereinafter, a vehicle traveling in the adjacent lane and traveling ahead of the host vehicle M is referred to as a front reference vehicle, and a vehicle traveling in the adjacent lane and traveling rearward of the host vehicle M is referred to as a rear reference vehicle. Will be described.

  The lane change possibility determination unit 124 does not have a surrounding vehicle on the target area TA set by the target position setting unit 122, and the virtual collision allowance time TTC (Time-To) between the host vehicle M and the front reference vehicle. Collision) and the virtual collision allowance time TTC between the host vehicle M and the rear reference vehicle both satisfy a predetermined setting condition such as being equal to or greater than a threshold value. It is determined that the vehicle M can change lanes. The collision allowance time TTC is, for example, assumed that the host vehicle M has changed lanes on the target area TA, and the inter-vehicle distance between the virtual host vehicle M on the target area TA and the front reference vehicle (or the rear reference vehicle). It is derived by dividing the distance by the speed of the host vehicle M and the relative speed of the front reference vehicle (or the rear reference vehicle).

  FIG. 11 is a diagram illustrating how the target position setting unit 122 according to the embodiment sets the target area TA. In the figure, mA represents a preceding vehicle, mB represents a front reference vehicle, and mC represents a rear reference vehicle. An arrow d represents the traveling (traveling) direction of the host vehicle M, L1 represents the host lane, and L2 represents an adjacent lane.

  In the example of FIG. 11, the target position setting unit 122 sets a target area TA between the front reference vehicle mB and the rear reference vehicle mC on the adjacent lane L2. In such a case, the lane change possibility determination unit 124 virtually arranges the host vehicle M on the target area TA set by the target position setting unit 122, and the front reference vehicle is based on the virtual host vehicle M. A collision margin time TTC (B) for mB and a collision margin time TTC (C) for the rear reference vehicle mC are derived. The lane change possibility determination unit 124 determines whether or not both of these derived collision margin times TTC satisfy a predetermined setting condition, and when both the collision margin times TTC both satisfy a predetermined setting condition (for example, forward If it is equal to or more than the threshold value set for each of the rear), it is determined that the host vehicle M can change the lane on the target area TA set on the adjacent lane L2. Note that the target position setting unit 122 may set the target area TA behind the rear reference vehicle mC (between the rear reference vehicle mC and the vehicle existing behind it) on the adjacent lane L2.

  Further, the lane change possibility determination unit 124 considers the own vehicle M on the target area TA in consideration of the speed, acceleration, jerk, etc. of the preceding vehicle mA, the forward reference vehicle mB, and the backward reference vehicle mC. It may be determined whether or not the lane can be changed. For example, the speed of the front reference vehicle mB and the rear reference vehicle mC is higher than the speed of the front running vehicle mA, and the front reference vehicle mB and the rear reference vehicle mC run forward within the time range required for the lane change of the host vehicle M When it is predicted that the vehicle mA will be overtaken, the lane change possibility determination unit 124 determines that the host vehicle M cannot change the lane on the target area TA set between the front reference vehicle mB and the rear reference vehicle mC. judge.

  When it is determined by the above-described lane change possibility determination unit 124 that the host vehicle M can change lanes on the target area TA, the second trajectory generation part 126 determines a track for changing lanes on the target area TA. Generate.

  FIG. 12 is a diagram illustrating a state in which the second trajectory generation unit 126 according to the embodiment generates a trajectory. For example, the second track generation unit 126 assumes that the front reference vehicle mB and the rear reference vehicle mC travel with a predetermined speed model, and based on the speed model of these three vehicles and the speed of the host vehicle M. The track is generated so that the host vehicle M exists between the front reference vehicle mB and the rear reference vehicle mC or behind the rear reference vehicle mC at a certain time in the future. For example, the second track generation unit 126 smoothly connects the current position of the host vehicle M to the position of the forward reference vehicle mB or the backward reference vehicle mC at a certain future time using a polynomial curve such as a spline curve. A predetermined number of target positions K are arranged on this curve at regular intervals or at irregular intervals. At this time, the second trajectory generation unit 126 generates a trajectory so that at least one of the target positions K is arranged on the target area TA.

[Running control]
The travel control unit 130 sets the control mode to the automatic operation mode or the manual operation mode under the control of the control switching unit 140, and the travel driving force output device 90, the steering device 92, and the brake device 94 are set according to the set control mode. Control a controlled object including part or all of it. The traveling control unit 130 reads the behavior plan information 156 generated by the behavior plan generation unit 106 in the automatic driving mode, and controls the control target based on the event included in the read behavior plan information 156.

  For example, the traveling control unit 130 follows the trajectory generated by the first trajectory generating unit 112 or the second trajectory generating unit 126, and the control amount (for example, the rotational speed) of the electric motor in the steering device 92 and the travel driving force output device 90. ECU control amount (for example, engine throttle opening, shift stage, etc.) is determined. Specifically, the traveling control unit 130 determines the control amount of the ECU in the traveling driving force output device 90 according to the target speed ν (or acceleration or jerk) every predetermined time Δt calculated from the target position K of the track. To do. Further, the traveling control unit 130 controls the electric motor in the steering device 92 according to the angle formed by the traveling direction of the host vehicle M for each target position K and the direction of the next target position with reference to the target position. Determine the amount.

  The traveling control unit 130 outputs information indicating the control amount to the corresponding control target. Accordingly, each device (90, 92, 94) to be controlled can control its own device according to the information indicating the control amount input from the travel control unit 130. In addition, the traveling control unit 130 appropriately adjusts the determined control amount based on the detection result of the vehicle sensor 60.

  The traveling control unit 130 controls the control target based on the operation detection signal output from the operation detection sensor 72 in the manual operation mode. For example, the traveling control unit 130 outputs the operation detection signal output by the operation detection sensor 72 to each device to be controlled as it is.

  Based on the action plan information 156 generated by the action plan generation unit 106 and stored in the storage unit 150, the control switching unit 140 changes the control mode of the host vehicle M by the travel control unit 130 from the automatic driving mode to the manual driving mode. Or, switch from manual operation mode to automatic operation mode. Further, the control switching unit 140 automatically changes the control mode of the host vehicle M by the travel control unit 130 from the automatic operation mode to the manual operation mode or automatically from the manual operation mode based on the control mode designation signal input from the changeover switch 80. Switch to operation mode. That is, the control mode of the traveling control unit 130 can be arbitrarily changed during traveling or stopping by an operation of a driver or the like.

  The control switching unit 140 switches the control mode of the host vehicle M by the travel control unit 130 from the automatic driving mode to the manual driving mode based on the operation detection signal input from the operation detection sensor 72. For example, when the operation amount included in the operation detection signal exceeds a threshold value, that is, when the operation device 70 receives an operation with an operation amount exceeding the threshold value, the control switching unit 140 automatically sets the control mode of the travel control unit 130. Switch from operation mode to manual operation mode. For example, when the host vehicle M is automatically traveling by the traveling control unit 130 set to the automatic driving mode, when the driver operates the steering wheel, the accelerator pedal, or the brake pedal with an operation amount exceeding a threshold value, The control switching unit 140 switches the control mode of the travel control unit 130 from the automatic operation mode to the manual operation mode. As a result, the vehicle control device 100 does not go through the operation of the changeover switch 80 by the operation performed by the driver when an object such as a person jumps out on the roadway or the preceding vehicle suddenly stops. You can immediately switch to manual operation mode. As a result, the vehicle control device 100 can cope with an emergency operation by the driver, and can improve safety during traveling.

  According to the vehicle position recognition unit (road lane line recognition device) 102 of the embodiment described above, the position and type of the road lane line included in the image captured by the camera 40 are recognized, and the recognized road lane line is recognized. By searching the map information 152 using the first road marking line recognition unit 102A that recognizes the first road marking line pattern including the position and type of the vehicle and the position of the host vehicle M acquired by the navigation device 50 The second road lane line recognition unit 102B for recognizing the second road lane line pattern including the position and type of the road lane line, and the first road lane line recognized by the first road lane line recognition unit 102A The pattern is compared with the second road lane line pattern recognized by the second road lane line recognition unit 102B, and is recognized by at least the first road lane line recognition unit 102A. By providing a determination unit 102C the likelihood of the position of the road lane lines were, it is possible to determine more accurately the likelihood of the road lane lines.

  Further, according to the vehicle control device 100 using the own vehicle position recognition unit (road lane line recognition device) 102 of the embodiment, the road lane marking determined by the own vehicle position recognition unit (road lane line recognition device) 102 is displayed. More accurate vehicle control can be performed based on the certainty.

  As mentioned above, although the form for implementing this invention was demonstrated using embodiment, this invention is not limited to such embodiment at all, In the range which does not deviate from the summary of this invention, various deformation | transformation and substitution Can be added.

DESCRIPTION OF SYMBOLS 20 ... Finder, 30 ... Radar, 40 ... Camera, 50 ... Navigation apparatus, 60 ... Vehicle sensor, 70 ... Operation device, 72 ... Operation detection sensor, 80 ... Changeover switch, 90 ... Driving force output device, 92 ... Steering device 94 ... Brake device, 100 ... Vehicle control device, 102 ... Vehicle position recognition unit (road lane line recognition device), 102A ... first road lane line recognition unit, 102B ... second road lane line recognition unit, 102C DESCRIPTION OF SYMBOLS ... Determination part 104 ... External field recognition part 106 ... Action plan generation part 110 ... Traveling mode determination part 112 ... First track generation part 120 ... Lane change control part 122 ... Target position determination part 124 ... Lane change Applicability determination unit, 126 ... second track generation unit, 130 ... travel control unit, 140 ... control switching unit, 150 ... storage unit, M ... own vehicle

Claims (12)

Recognizing the position and type of the road marking line included in the image captured by the imaging unit that images the road around the host vehicle, and the first road marking line pattern including the position and type of the recognized road marking line A first road lane marking recognition unit that recognizes;
The position and type of the road lane marking are described in association with the position of the road using the position of the own vehicle acquired by the own vehicle position acquisition unit that acquires the position of the own vehicle based on radio waves from a satellite. A second road lane marking recognition unit that recognizes a second road lane marking pattern including the position and type of the road lane marking by searching the map information
Comparing the first road lane line pattern recognized by the first road lane line recognition unit with the second road lane line pattern recognized by the second road lane line recognition unit; A determination unit that determines the probability of the position of the road lane line recognized by the road lane line recognition unit of 1;
A road lane marking recognition device. The first road lane line recognition unit recognizes the color of the road lane line included in the image captured by the imaging unit and includes the color of the recognized road lane line. Recognize
The map information describes the color of the road marking line in association with the position of the road,
The second road lane marking recognition unit recognizes a second road lane marking pattern including a color of the road lane marking;
The road marking line recognition apparatus according to claim 1. In addition to the comparison between the first road lane marking pattern and the second road lane marking pattern, the determination unit recognizes the recognition result by the first road lane marking recognition unit or the second road lane marking recognition. Determining the likelihood of the position of the road lane line recognized by at least the first road lane line recognition unit based on individual factors of the recognition result by the unit;
The road marking line recognition device according to claim 1 or 2. The determination unit has at least the first road lane marking when satisfying a vibration condition for determining that the position of the road lane marking recognized repeatedly by the first road lane marking recognition unit is vibrating. Reduce the probability of the position of the road lane marking recognized by the recognition unit,
The road marking line recognition device according to claim 3. The determination unit is based on the number of times or the frequency at which the position of the road lane marking recognized repeatedly by the first road lane marking recognition unit or the second road lane marking recognition unit is identifiable. Reducing the probability of the position of the road marking line recognized by the first road marking line recognition unit;
The road marking line recognition device according to claim 3 or 4. The determination unit determines that the host vehicle is traveling in the vicinity of a point where the type of the road lane marking changes based on the position of the host vehicle acquired by the host vehicle position acquisition unit and the map information. When it is done, at least the probability of the position of the road lane marking recognized by the first road lane marking recognition unit is reduced,
The road marking line recognition device according to any one of claims 3 to 5. The determination unit is at least when it is determined that the host vehicle is traveling on a point where a road branches or merges based on the position of the host vehicle and map information acquired by the host vehicle position acquisition unit. Reducing the probability of the position of the road lane line recognized by the first road lane line recognition unit;
The road marking line recognition device according to any one of claims 3 to 6. The determination unit is configured such that the host vehicle travels at a point on the road where an indication different from the road lane marking is made based on the position of the host vehicle and map information acquired by the host vehicle position acquisition unit. Reducing the probability of the position of the road lane line recognized by at least the first road lane line recognition unit,
The road marking line recognition device according to any one of claims 3 to 7. The road marking line recognition device according to any one of claims 1 to 8,
A track generation unit that generates a track on which the host vehicle should travel based on the position of the road lane marking determined to have a certain degree of certainty or more by the road lane marking recognition device;
A vehicle control device comprising: a travel control unit that causes the host vehicle to travel along the track generated by the track generation unit. When the road lane marking that has not been determined to have a certain degree of certainty by the road lane marking recognition device has a certain degree of certainty in the past by the road lane marking recognition device, Complementing based on the determined position of the road marking line, generating a track on which the host vehicle should travel,
The vehicle control device according to claim 9. In-vehicle computer
Recognizing the position and type of the road marking line included in the image captured by the imaging unit that images the road around the host vehicle, and the first road marking line pattern including the position and type of the recognized road marking line Recognized,
The position and type of the road lane marking are described in association with the position of the road using the position of the own vehicle acquired by the own vehicle position acquisition unit that acquires the position of the own vehicle based on radio waves from a satellite. The second road lane marking pattern, including the location and type of the road lane marking,
Comparing the first road lane marking pattern with the second road lane marking pattern and determining the likelihood of the position of the road lane marking recognized at least by the first road lane marking recognition unit;
Road lane marking recognition method. On-board computer
Recognizing the position and type of the road marking line included in the image captured by the imaging unit that images the road around the host vehicle, and the first road marking line pattern including the position and type of the recognized road marking line Let them recognize
The position and type of the road lane marking are described in association with the position of the road using the position of the own vehicle acquired by the own vehicle position acquisition unit that acquires the position of the own vehicle based on radio waves from a satellite. By searching the map information, the second road lane marking pattern including the position and type of the road lane marking is recognized,
Comparing the first road lane line pattern with the second road lane line pattern, and determining the likelihood of the position of the road lane line recognized by at least the first road lane line recognition unit;
Road lane marking recognition program.

Images