JP2019056953A - Vehicle controller, method for controlling vehicle, and program - Google Patents

Abstract

To provide a vehicle controller, a method for controlling vehicle, and a program that can correctly estimate a road which you can enter.SOLUTION: The vehicle controller according to an embodiment includes: a road recognition unit for recognizing a compartment line and a stop line of a road around a vehicle; a one-way traffic determination unit for determining whether the road around the vehicle is a one-way road according to the stop line recognized by the road recognition unit; and an entrance acceptance estimation unit for estimating that the vehicle can enter a road that the one-way determination unit has not determined to be a one-way road when the vehicle is entering an intersection.SELECTED DRAWING: Figure 2

Description

  The present invention relates to a vehicle control device, a vehicle control method, and a program.

  Conventionally, in a guidance device using a building shape map that displays a building shape map depicting buildings and roads, the road is a one-way road by calculating the route width from the number of lanes of the route road. There is known a technique for determining whether or not a display range is determined in accordance with a traveling road based on a determination result (for example, see Patent Document 1).

JP-A-10-333558

  However, in the prior art, since the determination is based on the number of lanes, there is a case where it is not possible to accurately estimate a road that can be traveled, which can be accurately recognized as a one-way road.

  The present invention has been made in view of such circumstances, and an object of the present invention is to provide a vehicle control device, a vehicle control method, and a program capable of correctly estimating a road that can travel.

  (1): A road recognition unit (132) that recognizes road marking lines and stop lines of roads around the vehicle, and a road around the vehicle is one-way based on the stop lines recognized by the road recognition unit. A one-way determination unit (134) that determines whether or not the road is a road, and when the vehicle enters an intersection, the one-way determination unit does not determine that the road is a one-way road It is a vehicle control apparatus provided with the progress possibility estimation part (136) which presumes that progress to is possible.

  (2): In (1), the advanceability estimation unit determines that the vehicle enters an intersection when the vehicle enters a road in which the road lane marking is not continuous in a straight line direction. .

  (3): In (1) or (2), the road recognizing unit further recognizes a preceding vehicle of the vehicle, and the progress propriety estimating unit is configured to detect the preceding vehicle recognized by the road recognizing unit. Based on the behavior, the degree of certainty that the road is a one-way road is increased.

  (4): In any one of (1) to (3), the travel propriety estimation unit is a stop line recognized by the road recognition unit in the width direction of the road among the roads around the vehicle. It is determined that a road in which the width of the region where there is no road is one lane or one vehicle width or more is a road on which the vehicle can travel.

  (5): The road recognizing unit recognizes road marking lines and stop lines of roads around the vehicle, and the one-way determining unit is configured based on the stop lines recognized by the road recognizing unit. It is determined whether or not the road is a one-way road. When the vehicle enters an intersection, the one-way determination unit determines that the road is a one-way road. This is a vehicle control method that estimates that it is possible to proceed to a non-road.

  (6): Based on the recognized stop line, a road around the vehicle is loaded on a computer installed in the vehicle including a road recognition unit that recognizes road marking lines and stop lines of roads around the vehicle. A program for determining whether or not the road is a one-way road, and for estimating that the road is not determined to be a one-way road when the vehicle enters an intersection. It is.

  According to (1) to (6), a one-way road can be recognized more accurately.

It is a lineblock diagram of vehicle system 1 using a vehicle control device concerning an embodiment. 3 is a functional configuration diagram of a first control unit 120 and a second control unit 160. FIG. It is a figure for demonstrating the recognition method of the width of the road by the road recognition part 132 in a 1st method. It is a figure for demonstrating the other recognition method of the width of the road by the road recognition part 132 in a 1st method. It is a figure for demonstrating whether it is a one-way road based on the stop line LS in a 2nd method. It is a figure for demonstrating the mode of recognition of the stop line LS when a part of stop line LS is shielded. It is a figure for demonstrating whether the line drawn on the road is a stop line based on the position and extension direction of the line drawn on the road in the 3rd method. It is a figure for demonstrating in the 4th method determining whether it is a one-way road by the drawing position of a road sign. It is a figure for demonstrating in the 5th method determining whether it is a one-way road by the mark which shows the advancing direction drawn on the road. It is a figure for demonstrating the road which can advance from the stop line of the lane connected with intersection CR in the 6th method. It is a figure for demonstrating raising the certainty of estimation of the propriety of progress based on the behavior of the preceding vehicle m1. It is a flowchart which shows an example of the process performed by the automatic driving | operation control apparatus 100 of embodiment. It is a figure showing an example of hardware constitutions of automatic operation control device 100 of an embodiment.

  Hereinafter, embodiments of a vehicle control device, a vehicle control method, and a program according to the present invention will be described with reference to the drawings.

[overall structure]
FIG. 1 is a configuration diagram of a vehicle system 1 using a vehicle control device according to an embodiment. The vehicle on which the vehicle system 1 is mounted is, for example, a vehicle such as a two-wheel, three-wheel, or four-wheel vehicle, and a drive source thereof is an internal combustion engine such as a diesel engine or a gasoline engine, an electric motor, or a combination thereof. When the electric motor is provided, the electric motor operates using electric power generated by the electric generator connected to the internal combustion engine or electric discharge power of the secondary battery or the fuel cell.

  The vehicle system 1 includes, for example, a camera 10, a radar device 12, a finder 14, an object recognition device 16, a communication device 20, an HMI (Human Machine Interface) 30, a vehicle sensor 40, a navigation device 50, An MPU (Map Positioning Unit) 60, a driving operator 80, an automatic driving control device (vehicle control device) 100, a driving force output device 200, a brake device 210, and a steering device 220 are provided. 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 configuration illustrated in FIG. 1 is merely an example, and a part of the configuration may be omitted, or another configuration may be added.

  The camera 10 is a digital camera using a solid-state image sensor such as a CCD (Charge Coupled Device) or a CMOS (Complementary Metal Oxide Semiconductor). One or a plurality of cameras 10 are attached to any part of a vehicle (hereinafter referred to as the host vehicle M) on which the vehicle system 1 is mounted. When imaging the front, the camera 10 is attached to the upper part of the front windshield, the rear surface of the rearview mirror, or the like. For example, the camera 10 periodically and repeatedly images the periphery of the host vehicle M. The camera 10 may be a stereo camera.

  The radar device 12 radiates radio waves such as millimeter waves around the host vehicle M, and detects radio waves (reflected waves) reflected by the object to detect at least the position (distance and direction) of the object. One or a plurality of radar devices 12 are attached to arbitrary locations of the host vehicle M. The radar apparatus 12 may detect the position and speed of an object by FM-CW (Frequency Modulated Continuous Wave) method.

  The finder 14 is LIDAR (Light Detection and Ranging). The finder 14 irradiates light around the host vehicle M and measures scattered light. The finder 14 detects the distance to the object based on the time from light emission to light reception. The irradiated light is, for example, pulsed laser light. One or a plurality of the finders 14 are attached to arbitrary locations of the host vehicle M.

  The object recognition device 16 performs sensor fusion processing on detection results of some or all of the camera 10, the radar device 12, and the finder 14 to recognize the position, type, speed, and the like of the object. The object recognition device 16 outputs the recognition result to the automatic driving control device 100. Further, the object recognition device 16 may output the detection results of the camera 10, the radar device 12, and the finder 14 as they are to the automatic driving control device 100 as necessary.

  The communication device 20 communicates with other vehicles around the host vehicle M using, for example, a cellular network, a Wi-Fi network, Bluetooth (registered trademark), DSRC (Dedicated Short Range Communication), or wirelessly. It communicates with various server apparatuses via a base station.

  The HMI 30 presents various information to the occupant of the host vehicle M and accepts an input operation by the occupant. The HMI 30 includes various display devices, speakers, buzzers, touch panels, switches, keys, and the like.

  The vehicle sensor 40 includes a vehicle speed sensor that detects the speed of the host vehicle M, an acceleration sensor that detects acceleration, a yaw rate sensor that detects an angular velocity around the vertical axis, a direction sensor that detects the direction of the host vehicle M, and the like.

  The navigation device 50 includes, for example, a GNSS (Global Navigation Satellite System) receiver 51, a navigation HMI 52, and a route determination unit 53. The first map information 54 is stored in a storage device such as an HDD (Hard Disk Drive) or a flash memory. Holding. The GNSS receiver 51 specifies the position of the host vehicle M based on the signal received from the GNSS satellite. 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 40. The navigation HMI 52 includes a display device, a speaker, a touch panel, keys, and the like. The navigation HMI 52 may be partly or wholly shared with the HMI 30 described above. The route determination unit 53 is, for example, a route from the position of the host vehicle M specified by the GNSS receiver 51 (or any input position) to the destination input by the occupant using the navigation HMI 52 (hereinafter, referred to as “route”). The route on the map is determined with reference to the first map information 54. The first map information 54 is information in which a road shape is expressed by, for example, a link indicating a road and nodes connected by the link. The first map information 54 may include road curvature and POI (Point Of Interest) information. The on-map route determined by the route determination unit 53 is output to the MPU 60. Further, the navigation device 50 may perform route guidance using the navigation HMI 52 based on the on-map route determined by the route determination unit 53. In addition, the navigation apparatus 50 may be implement | achieved by the function of terminal devices, such as a smart phone and a tablet terminal which a passenger | crew holds, for example. Further, the navigation device 50 may transmit the current position and the destination to the navigation server via the communication device 20 and acquire the on-map route returned from the navigation server.

  For example, the MPU 60 functions as the recommended lane determining unit 61 and holds the second map information 62 in a storage device such as an HDD or a flash memory. The recommended lane determining unit 61 divides the route provided from the navigation device 50 into a plurality of blocks (for example, every 100 [m] with respect to the vehicle traveling direction), and refers to the second map information 62 for each block. Determine the recommended lane. The recommended lane determining unit 61 performs determination such as what number of lanes from the left to travel. The recommended lane determining unit 61 determines a recommended lane so that the host vehicle M can travel on a reasonable route for proceeding to the branch destination when there is a branch point, a junction point, or the like on the route.

  The second map information 62 is map information with higher accuracy than the first map information 54. The second map information 62 includes, for example, information on the center of the lane or information on the boundary of the lane. The second map information 62 may include road information, traffic regulation information, address information (address / postal code), facility information, telephone number information, and the like. The second map information 62 may be updated at any time by accessing another device using the communication device 20.

  The driving operation element 80 includes, for example, an accelerator pedal, a brake pedal, a shift lever, a steering wheel, a deformed steer, a joystick, and other operation elements. A sensor for detecting the amount of operation or the presence or absence of an operation is attached to the driving operator 80, and the detection result is the automatic driving control device 100, or the traveling driving force output device 200, the brake device 210, and the steering device. 220 is output to one or both of 220.

  The automatic operation control device 100 includes, for example, a first control unit 120 and a second control unit 160. Each of the first control unit 120 and the second control unit 160 is realized by a hardware processor such as a CPU (Central Processing Unit) executing a program (software), for example. Some or all of these components are hardware (circuits) such as LSI (Large Scale Integration), ASIC (Application Specific Integrated Circuit), FPGA (Field-Programmable Gate Array), and GPU (Graphics Processing Unit). Part (including circuit)), or may be realized by cooperation of software and hardware.

  FIG. 2 is a functional configuration diagram of the first control unit 120 and the second control unit 160. The first control unit 120 includes, for example, a recognition unit 130 and an action plan generation unit 140.

  The first control unit 120 implements, for example, a function based on AI (Artificial Intelligence) and a function based on a predetermined model in parallel. For example, the “recognize intersections” function is a parallel recognition of intersections based on image recognition methods using deep learning, etc., and recognition based on pre-given conditions (pattern matching signals, road markings, etc.) It is realized by scoring and comprehensively evaluating both sides. This ensures the reliability of automatic driving.

  Based on information input from the camera 10, the radar device 12, and the finder 14 via the object recognition device 16, the recognition unit 130 determines the positions of objects around the host vehicle M and the state such as speed and acceleration. recognize. The position of the object is recognized, for example, as a position on absolute coordinates with the representative point (the center of gravity, the center of the drive shaft, etc.) of the host vehicle M as the origin, and is used for control. The position of the object may be represented by a representative point such as the center of gravity or corner of the object, or may be represented by a represented area. The “state” of the object may include acceleration or jerk of the object, or “behavioral state” (for example, whether or not the lane is changed or is about to be changed). Further, the recognition unit 130 recognizes the shape of the curve through which the host vehicle M will pass based on the captured image of the camera 10. The recognizing unit 130 converts the shape of the curve from the captured image of the camera 10 to a real plane, and, for example, information representing the shape of the curve by using two-dimensional point sequence information or information equivalent to this model To the action plan generation unit 140.

  The recognizing unit 130 recognizes the lane (traveling lane) in which the host vehicle M is traveling. For example, the recognizing unit 130 has a road lane marking line around the host vehicle M recognized from the road lane marking pattern (for example, an array of solid lines and broken lines) obtained from the second map information 62 and an image captured by the camera 10. The driving lane is recognized by comparing with the pattern. Note that the recognition unit 130 may recognize a travel lane by recognizing not only a road lane line but also a road lane line (road boundary) including a road lane line, a road shoulder, a curb, a median strip, a guardrail, and the like. . In this recognition, the position of the host vehicle M acquired from the navigation device 50 and the processing result by INS may be taken into account. In addition, the recognition unit 130 recognizes a stop line, an obstacle, a red light, a toll gate, and other road events.

  When recognizing the traveling lane, the recognizing unit 130 recognizes the position and posture of the host vehicle M with respect to the traveling lane. For example, the recognizing unit 130 determines the relative position of the host vehicle M with respect to the travel lane by making an angle between the deviation of the reference point of the host vehicle M from the center of the lane and the line connecting the center of the lane in the traveling direction of the host vehicle M And may be recognized as a posture. Instead of this, the recognition unit 130 determines the position of the reference point of the host vehicle M with respect to any side edge (road lane line or road boundary) of the traveling lane, and the relative position of the host vehicle M with respect to the traveling lane. You may recognize as.

  Moreover, the recognition part 130 may derive | lead-out recognition accuracy in said recognition process, and may output it to the action plan production | generation part 140 as recognition accuracy information. For example, the recognition unit 130 generates recognition accuracy information based on the frequency with which road lane markings can be recognized in a certain period. The details of the function of the recognition unit 130 in this embodiment will be described later.

  In principle, the action plan generation unit 140 travels in the recommended lane determined by the recommended lane determination unit 61, and further, the host vehicle M is configured so that automatic driving corresponding to the surrounding situation of the host vehicle M is executed. Generate a target trajectory to travel in the future. The target trajectory includes, for example, a velocity element. For example, the target track is expressed as a sequence of points (track points) that the host vehicle M should reach.

  The second control unit 160 includes, for example, an acquisition unit 162, a speed control unit 164, and a steering control unit 166. The acquisition unit 162 acquires information on the target trajectory (orbit point) generated by the action plan generation unit 140 and stores it in a memory (not shown). The speed control unit 164 controls the travel driving force output device 200 or the brake device 210 based on a speed element associated with the target track stored in the memory. The steering control unit 166 controls the steering device 220 according to the degree of bending of the target trajectory stored in the memory. The processing of the speed control unit 164 and the steering control unit 166 is realized by, for example, a combination of feedforward control and feedback control. As an example, the steering control unit 166 executes a combination of feed-forward control corresponding to the curvature of the road ahead of the host vehicle M and feedback control based on deviation from the target track.

  The traveling driving force output device 200 outputs a traveling driving force (torque) for traveling of the vehicle to driving wheels. The traveling driving force output device 200 includes, for example, a combination of an internal combustion engine, an electric motor, a transmission, and the like, and an ECU that controls these. The ECU controls the above-described configuration according to information input from the second control unit 160 or information input from the driving operator 80.

  The brake device 210 includes, for example, a brake caliper, a cylinder that transmits hydraulic pressure to the brake caliper, an electric motor that generates hydraulic pressure in the cylinder, and a brake ECU. The brake ECU controls the electric motor in accordance with the information input from the second control unit 160 or the information input from the driving operation element 80 so that the brake torque corresponding to the braking operation is output to each wheel. The brake device 210 may include, as a backup, a mechanism that transmits the hydraulic pressure generated by operating the brake pedal included in the driving operation element 80 to the cylinder via the master cylinder. The brake device 210 is not limited to the configuration described above, and is an electronically controlled hydraulic brake device that controls the actuator according to information input from the second control unit 160 and transmits the hydraulic pressure of the master cylinder to the cylinder. Also good.

  The steering device 220 includes, for example, a steering ECU and an electric motor. For example, the electric motor changes the direction of the steered wheels by applying a force to a rack and pinion mechanism. The steering ECU drives the electric motor according to the information input from the second control unit 160 or the information input from the driving operator 80, and changes the direction of the steered wheels.

[Details of functions of recognition unit 130]
Next, details of the function of the recognition unit 130 will be described. The recognition unit 130 includes a road recognition unit 132, a one-way determination unit 134, and a travel possibility estimation unit 136.

  The road recognition unit 132 recognizes the width of the road around the host vehicle M. The roads around the host vehicle M are, for example, roads on which the host vehicle M travels, roads connected to intersections to which the roads are connected, and the like.

  The one-way determination unit 134 determines whether or not the road around the host vehicle M is a one-way road based on the road width recognized by the road recognition unit 132.

  The progress possibility estimation unit 136 is based on at least one or both of the recognition result by the road recognition unit 132 or the determination result by the one-way determination unit 134 whether or not the road is a one-way road. Is estimated whether or not the host vehicle M can proceed.

  The road recognition unit 132, the one-way determination unit 134, and the travel propriety estimation unit 136 perform at least one of recognition, determination, and estimation by any method or combination described below.

(First method)
FIG. 3 is a diagram for explaining a road width recognition method by the road recognition unit 132 in the first method. For example, the road recognition unit 132 recognizes the left and right road lane markings LL and LR that divide the traveling lane based on the captured image of the camera 10, and determines the distance between the recognized road lane markings LL and LR as the road. Is recognized as the width W1. Further, when the road marking line LL or LR cannot be recognized, the recognizing unit 130 estimates both ends of the road based on a luminance difference or the like in the image, and uses the estimated distance between the both ends as the road width W1. You may recognize it.

  FIG. 4 is a diagram for describing another recognition method of the road width by the road recognition unit 132 in the first method. In the example of FIG. 4, the object OB is installed on the side of the road lane marking LL that divides the lane L1. The object OB is a roadside structure such as a utility pole, for example. The object OB may be a guardrail, a vending machine, or other objects. These objects OB are recognized by the recognition unit 130. In the example of FIG. 4, the road recognizing unit 132 recognizes the distance from the end closer to the road lane marking LR of the object OB installed on the road to the road lane marking LR as the road width W1.

  Hereinafter, what is recognized by the recognition method illustrated in FIG. 3 or FIG. 4 is treated as the width W1 of the road.

  In the first method, the one-way determination unit 134 determines that the road on which the host vehicle M is traveling is a one-way road when the width W1 of the road recognized by the road recognition unit 132 is equal to or less than the first predetermined value. It is determined that On the other hand, the one-way determination unit 134 determines that the road on which the host vehicle M is traveling is not a one-way road when the width W1 of the road recognized by the road recognition unit 132 exceeds the first predetermined value. . Further, the first predetermined value may be appropriately set to a value obtained by further reducing the above-described value.

  The first predetermined value is, for example, a fixed value set to about twice the vehicle width of a large ordinary vehicle (for example, the vehicle width WM of the host vehicle M). As a result, the first predetermined value is a value corresponding to the width of the road in which the assumed ordinary vehicles cannot pass each other.

(Second method)
In the second method, the road recognition unit 132 recognizes a stop line drawn on a road around the host vehicle M, and the one-way determination unit 134 uses the stop line for the road width recognized by the road recognition unit 132. Based on the length ratio, it is determined whether or not the road around the host vehicle M is a one-way road.

  FIG. 5 is a diagram for explaining whether the road is a one-way road based on the stop line LS in the second method. The road recognition unit 132 recognizes the road width W1 of the lane L1 based on the captured image of the camera 10, and recognizes the stop line LS drawn on the road. For example, the road recognizing unit 132 may recognize the stop line LS by an image recognition method using deep learning or the like, and stops based on a predetermined condition (there is a signal that can be matched with a pattern, a road marking, and the like). The line LS may be recognized. In addition, the road recognition unit 132 recognizes the stop line LS by performing recognition by deep learning or the like and recognition based on a predetermined condition in parallel, scoring both, and comprehensively evaluating them. May be.

  The one-way determination unit 134 determines that the road in the lane L1 is a one-way road when the width W2 of the stop line LS recognized by the road recognition unit 132 is equal to or greater than a second predetermined value determined based on the road width W1. It is determined that The second predetermined value is determined based on, for example, the road width W1. Specifically, the second predetermined value is a length of about 50% of the road width W1.

  In addition, the one-way determination unit 134 determines that the width W3 of the area without the stop line, which is obtained as a difference between the road width W1 of the lane L1 recognized by the road recognition unit 132 and the stop line LS, is equal to or greater than the third predetermined value. In this case, it may be determined that the road is not a one-way road. The third predetermined value is, for example, a fixed value that is set to a value about the vehicle width of a large ordinary vehicle (for example, the vehicle width WM of the host vehicle M). Further, the third predetermined value may be a fixed value that is set to a value that is about a predetermined width of one lane. The third predetermined value may be appropriately set to a value obtained by further reducing the above-described value.

  In the second method, the road recognition unit 132 recognizes the length of the stop line LS from the recognized area when a part of the stop line LS is blocked by the preceding vehicle of the host vehicle M and cannot be recognized. May be.

  FIG. 6 is a diagram for explaining how the stop line LS is recognized when a part of the stop line LS is shielded. For example, when a part of the stop line LS is shielded by the vehicle body of the preceding vehicle m1 of the host vehicle M, the left and right unshielded stop lines LSL and stop LSR of the vehicle body are recognized. In addition, the road recognition unit 132 estimates that the stop line LSL and the stop LSR are communicated with each other in a region shielded by the vehicle body of the preceding vehicle, and recognizes the width W2 of the stop line LS. Alternatively, the road recognition unit 132 may recognize the stop line LSR, and may set the length from the right end of the recognized stop line LSR to the road segment line LR as the width W3 of the area without the stop line.

(Third method)
In the third method, the road recognition unit 132 recognizes the position and extension direction of the line drawn on the road, and the one-way determination unit 134 recognizes the position and extension direction of the line recognized by the road recognition unit 132. Based on the above, it is determined that the line drawn on the road is not a stop line.

  FIG. 7 is a diagram for explaining whether or not the line drawn on the road is a stop line based on the position and the extension direction of the line drawn on the road in the third technique. It is. The road recognition unit 132 uses the second lines LV1 to LV1 along the road longitudinal direction with respect to the first lines LH1 and LH2 in the road width direction and the first lines LH1 and LH2 based on the captured image of the camera 10. Recognizes LV4.

  The one-way determination unit 134 includes the first line LH recognized by the road recognition unit 132 and the first line LH1 when the plurality of second lines LV1 to LV4 are connected to the first line. The lines LH1 and LH2 are determined not to be stop lines. In addition, the one-way determination unit 134 is configured such that even if there is one first line LH recognized by the road recognition unit 132, the plurality of second lines LV1 to LV4 are connected to the first line LH. If there is, it may be determined that the first line LH is not a stop line. Thereby, the stop line LS and a line other than the stop line (for example, a line forming a pedestrian crossing) can be more accurately distinguished. Therefore, it can be determined more accurately whether or not the road on which the vehicle M is traveling is a one-way road.

(Fourth method)
In the fourth method, the road recognition unit 132 recognizes the road sign drawn on the road, and the one-way determination unit 134 has the recognized road sign drawing position at the center in the width direction of the road. In addition, it is determined that the road is a one-way road. The road sign drawn on the road is a road sign that displays road traffic regulations or instructions, and is a line, a symbol, a character, or the like made from a road fence, paint, stone, or the like. The road sign is, for example, a “stop” character drawn on the road or a rhombus figure indicating a pedestrian crossing notice display.

  FIG. 8 is a diagram for explaining whether the road is a one-way road according to the road sign drawing position in the fourth method. In the example of FIG. 8, the road recognition unit 132 recognizes the road sign RS based on the captured image of the camera 10. For example, the road recognition unit 132 may recognize the road marking RS by an image recognition method using deep learning or the like, or may recognize the road sign RS based on a predetermined condition. Further, the road recognition unit 132 recognizes a road sign by performing recognition by deep learning or the like and recognition based on a predetermined condition in parallel, scoring both, and comprehensively evaluating them. May be.

  Further, the road recognition unit 132 recognizes the drawing position on the road of the road sign RS. For example, the road recognition unit 132 recognizes a distance W4L from the road marking line LL to the left end portion of the road sign RS and a distance W4R from the road marking line LR to the right end portion of the road sign RS. The one-way determination unit 134 calculates the difference between the distance W4L and the distance W4R recognized by the road recognition unit 132. If the absolute value of the calculated difference is within the fourth predetermined value, the road sign RS is It is determined that the image is drawn at the center in the width direction of the road. The fourth predetermined value is a fixed value such as 1 [m] or less. In addition, when the one-way determination unit 134 determines that the road sign RS drawn on the road is drawn at the center portion in the width direction of the road, the one-way determination unit 134 determines that the road is a one-way road.

(Fifth technique)
In the fifth method, the road recognizing unit 132 recognizes a mark such as an arrow indicating the traveling direction drawn on the road, and the one-way determining unit 134 is based on the mark MK recognized by the road recognizing unit 132. It is determined whether the road is a one-way street.

  FIG. 9 is a diagram for explaining whether or not the road is a one-way road based on a mark indicating the traveling direction drawn on the road in the fifth technique. In the example of FIG. 9, a mark MK indicating the traveling direction is drawn on the road in the lane L1. A mark MK shown in FIG. 9 is a mark representing a one-way road. The road recognition unit 132 recognizes the mark MK based on the captured image of the camera 10. For example, the road recognizing unit 132 may recognize the mark MK by an image recognition method using deep learning or the like, or may recognize the mark MK based on a predetermined condition. Further, the road recognition unit 132 recognizes the mark MK by executing recognition based on deep learning or the like and recognition based on a predetermined condition in parallel, scoring both, and comprehensively evaluating them. May be.

  The one-way determination unit 134 recognizes that the road on which the host vehicle M is traveling is a one-way road based on the mark MK recognized by the road recognition unit 132. Further, the one-way determination unit 134 may determine that the road existing in the traveling direction indicated by the recognized mark MK is a road on which the host vehicle M can travel.

(Sixth method)
In the sixth method, the road recognition unit 132 recognizes the stop line LS of the lane around the own vehicle M when the own vehicle M arrives on a road where the lane is not continuous in the straight line direction, and whether or not the vehicle can proceed. The estimation unit 136 estimates a road that can travel based on the recognition result by the road recognition unit 132. A road whose lane is not continuous in a straight line direction is a road such as an intersection (including a T-shaped road).

  FIG. 10 is a diagram for explaining estimation of a road that can travel from a lane stop line connected to the intersection CR in the sixth method. In the example of FIG. 10, lanes L1 to L4 are connected to the intersection CR. The lane L2 is a road in a direction that goes straight through the intersection CR as viewed from the lane L1. The lane L3 is a road in the direction of turning right at the intersection CR as viewed from the lane L1. The lane L4 is a road in the direction of turning left at the intersection CR as viewed from the lane L1.

  In the sixth method, the road recognition unit 132 and the one-way determination unit 134 use at least one of the first to fifth methods described above before the host vehicle M reaches the vicinity of the intersection CR. Thus, it is determined whether the traveling lane L1 is a one-way road. The vicinity of the intersection CR is determined based on, for example, the center position of the intersection CR or the position of the stop line. Specifically, the vicinity of the intersection CR is within a range of about 30 [m] before the stop line. The position of the intersection CR can be acquired from the first map information 54 or the second map information 62, for example.

  Further, when the host vehicle M reaches the vicinity of the intersection CR, the road recognition unit 132 recognizes the lanes L2 to L4 other than the lane L1 connected to the intersection CR based on the captured image of the camera 10, and each road width. Recognize W1a to w1c. Further, the road recognition unit 132 recognizes the presence or absence of a stop line on the traveling lanes L2 to L4 of the host vehicle M. In the example of FIG. 10, the road recognition unit 132 recognizes the stop line LS2 of the lane L2 and the stop line LS3 of the lane L3. Further, the road recognition unit 132 recognizes the width W2a of the stop line LS2 and the width W3a of the area where the stop line LS2 is not drawn in the width direction of the lane L2 based on the captured image of the camera 10. Further, the road recognition unit 132 recognizes the width W2b of the stop line LS3 and the width W3b of the area where the stop line LS3 is not drawn in the width direction of the lane L3 based on the captured image of the camera 10.

  For example, when the width W2a of the stop line LS2 is equal to or greater than a fifth predetermined value, the travel possibility estimation unit 136 estimates that the lane L2 is a one-way road that cannot travel from the position of the host vehicle M. The fifth predetermined value is, for example, a length of about 50% of the width W1a of the lane L2.

  Further, for example, when the width W2b of the stop line LS3 is equal to or larger than a sixth predetermined value, the travel possibility estimation unit 136 estimates that the lane L3 is a one-way road that cannot travel from the position of the host vehicle M. To do. The sixth predetermined value is, for example, a length of about 50% of the width W1 of the lane L3.

  Further, the travel possibility estimation unit 136 estimates the lane L4 in which the stop line is not recognized by the road recognition unit 132 as a road that can travel from the position of the host vehicle M.

  Further, when it is estimated that the lanes L1 to L3 are one-way roads that cannot enter from the position of the lane L4, the travel possibility estimation unit 136 may estimate the lane L4 as a one-way road.

  In addition, in the lane L2, if the width W3a of the area where the stop line LS2 is not drawn is equal to or larger than the above-described third predetermined value, the travelability estimation unit 136 determines that the lane L2 is not a one-way road. Alternatively, it may be estimated that the road can travel from the position of the host vehicle M. In addition, in the lane L3, the travel possibility estimation unit 136 determines that the lane L3 is not a one-way road when the width W3b of the area where the stop line LS3 is not drawn is equal to or greater than the third predetermined value described above. Alternatively, it may be estimated that the road can travel from the position of the host vehicle M.

  Furthermore, when the preceding vehicle m1 of the host vehicle M is recognized by the recognizing unit 130, the progress possibility estimating unit 136 determines whether or not the road to the surrounding road of the host vehicle M is based on the recognized behavior of the preceding vehicle m1. You may raise the certainty of estimation of the propriety of progress.

  FIG. 11 is a diagram for explaining increasing the certainty of estimation of the propriety of progress based on the behavior of the preceding vehicle m1. The recognizing unit 130 recognizes that the preceding vehicle m1 turns left at the intersection CR and proceeds to the lane L4. After that, the travel possibility estimation unit 136 estimates the lane that can travel based on the presence or absence of the stop line for each lane obtained from the captured image of the camera 10 and the width of the stop line with respect to the lane as described above. In this case, the certainty factor when the lane L4 ahead of the preceding vehicle m1 makes a left turn is estimated to be a lane that can travel is made higher than when the behavior of the preceding vehicle m1 is not recognized. Thereby, the information of the lane which can advance can be output to the action plan production | generation part 140 more correctly.

  The action plan generation unit 140 generates a target trajectory corresponding to a one-way road when the recognition road 130 recognizes that the road being traveled or the road that will be traveled in the future is a one-way road. The target track corresponding to the one-way road is, for example, a target track that travels in the center of the lane. By traveling in the center of the lane, it is possible to easily avoid contact with other vehicles entering from other roads (sideways, alleys, etc.) connected to the road.

  On the other hand, when the action plan generation unit 140 recognizes that the road being traveled or the road to be traveled in the future is a road that does not have a road lane marking with the opposite lane and is not a one-way road by the recognition unit 130. Considering the possibility of passing the oncoming vehicle, a target track that travels at a position offset to the left of the center of the lane is generated. Thereby, passing with an oncoming vehicle can be performed smoothly.

  In addition, when the action plan generation unit 140 acquires information on a road that can be traveled by the travel progress estimation unit 136, the action plan generation unit 136 gives priority to a road with a high degree of certainty that can be traveled. A trajectory may be generated.

[Processing flow]
FIG. 12 is a flowchart illustrating an example of processing executed by the automatic operation control device 100 according to the embodiment. The process of this flowchart may be repeatedly executed at a predetermined cycle or a predetermined timing, for example. The road recognition unit 132 recognizes the width of the road around the host vehicle M (step S100). Next, the one-way determination unit 134 determines, for example, whether or not the recognized road width is equal to or smaller than a first predetermined value (step S102). If the recognized road width is equal to or smaller than the first predetermined value, the one-way determination unit 134 determines that the recognized road is a one-way road (step S104). If the recognized road width is not equal to or less than the first predetermined value, the one-way determination unit 134 determines that the recognized road is not a one-way road (step S106).

  Next, the progress possibility estimation unit 136 determines whether or not the position of the host vehicle M recognized by the recognition unit 130 reaches the vicinity of the intersection (step S108). When the position of the host vehicle M reaches the vicinity of the intersection, the travel possibility estimation unit 136 can proceed based on the result of determining whether the lane connected to the intersection is one-way by the above-described method. A correct lane is estimated (step S110). Next, the action plan generation unit 140 generates a target track that travels in a travelable lane estimated by the travel possibility estimation unit 136 (step S112). If the position of the host vehicle M has not reached the vicinity of the intersection, the travel possibility estimation unit 136 generates a target track based on the result of determining whether the vehicle is one-way (step S114). Next, the second control unit 160 automatically controls one or both of the speed and steering of the host vehicle M based on the generated target track, and causes the host vehicle M to travel (step S116). Thereby, the process of this flowchart is complete | finished. Note that, in the above-described processing of S102, the determination may be performed in combination with or in combination with other determination methods described above.

  According to the above-described embodiment, the road marking line and the stop line of the road around the host vehicle M are recognized, and whether the road around the host vehicle M is a one-way road based on the recognized stop line. If the vehicle M enters a road where the road lane marking is not continuous in a straight line direction, it is possible to proceed to a road that is not determined to be a one-way road. By estimating, a road that can be traveled can be correctly estimated. Moreover, according to this embodiment, automatic driving | operation can be performed based on the target track | orbit produced | generated based on the estimation result.

  In addition, this embodiment is not limited to the automatic driving vehicle mentioned above, It can apply also to the vehicle by which a driving assistance device is mounted. In this case, the function of the recognition unit 130 is provided in the driving support device. For example, if the one-way determination unit 134 determines that the host vehicle M is about to enter a one-way direction in the reverse direction, the recognition unit 130 causes the HMI 30 to output an alarm. The recognition unit 130 may display the position of the one-way road determined by the one-way determination unit 134 on the display device of the HMI 30.

  The recognizing unit 130 also determines the position of the one-way road determined by the one-way determining unit 134, the traveling direction to the road determined to be advancing by the progress possibility estimating unit 136, and the like (Augmented Reality). ) Technology may be used for display. Specific examples of display using the AR technology include, for example, a mark or symbol indicating a one-way or approach direction on a HUD (Head-Up Display) or a transmissive liquid crystal display pasted on a front windshield. By displaying characters or the like, it is possible to easily notify the occupant that the surrounding road is a one-way road or an accessible road.

[Hardware configuration]
The automatic operation control device 100 of the above-described embodiment is realized by a hardware configuration as shown in FIG. 13, for example. FIG. 13 is a diagram illustrating an example of a hardware configuration of the automatic driving control apparatus 100 according to the embodiment.

  The automatic operation control device 100 includes a communication controller 100-1, a CPU 100-2, a RAM 100-3, a ROM 100-4, a secondary storage device 100-5 such as a flash memory and an HDD, and a drive device 100-6. They are configured to be connected to each other by a dedicated communication line. The drive device 100-6 is loaded with a portable storage medium such as an optical disk. The program 100-5a stored in the secondary storage device 100-5 is expanded in the RAM 100-3 by a DMA controller (not shown) or the like and executed by the CPU 100-2, whereby the first control unit 120 and the second The control unit 160 is realized. The program referred to by the CPU 100-2 may be stored in a portable storage medium attached to the drive device 100-6, or may be downloaded from another device via the network NW.

The above embodiment can be expressed as follows.
A storage device for storing information;
A hardware processor for executing the program,
The storage device includes the hardware processor,
Road recognition processing for recognizing road lane markings and stop lines on roads around the vehicle;
A one-way determination process for determining whether or not a road around the vehicle is a one-way road based on the stop line recognized by the road recognition process;
When the vehicle enters an intersection, a progress propriety estimation process that estimates that the road is not determined to be a one-way road by the one-way determination process;
Storing the program for executing
Vehicle control device.

  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 1 ... Vehicle system, 10 ... Camera, 12 ... Radar device, 14 ... Finder, 16 ... Object recognition device, 20 ... Communication device, 30 ... HMI, 40 ... Vehicle sensor, 50 ... Navigation device, 60 ... MPU, 80 ... Driving Operation unit 100 ... Automatic driving control device 120 ... first control unit 130 ... recognition unit 132 ... road recognition unit 134 ... one-way determination unit 136 ... progress propriety estimation unit 140 ... action plan generation unit 160 ... 2nd control part, 200 ... Driving force output device, 210 ... Brake device, 220 ... Steering device, M ... Own vehicle

Claims (6)

A road recognition unit for recognizing road marking lines and stop lines of roads around the vehicle;
A one-way determination unit that determines whether or not a road around the vehicle is a one-way road based on the stop line recognized by the road recognition unit;
When the vehicle enters an intersection, a progress propriety estimation unit that estimates that the road is not determined to be a one-way road by the one-way determination unit;
A vehicle control device comprising: The advanceability estimation unit determines that the vehicle enters an intersection when the vehicle enters a road where the road lane marking is not continuous in a straight line direction,
The vehicle control device according to claim 1. The road recognition unit further recognizes a preceding vehicle of the vehicle,
The advanceability estimation unit increases the certainty that the road is a one-way road based on the behavior of the preceding vehicle recognized by the road recognition unit.
The vehicle control device according to claim 1 or 2. The travel propriety estimation unit is a road in which the width of an area without a stop line recognized by the road recognition unit in the road width direction is equal to or more than one lane or one vehicle width among roads around the vehicle Is determined to be a road on which the vehicle can travel,
The vehicle control device according to any one of claims 1 to 3. The road recognition unit recognizes road lane markings and stop lines around the vehicle,
The one-way determination unit determines whether or not the road around the vehicle is a one-way road based on the stop line recognized by the road recognition unit;
When the vehicle enters the intersection, the progress propriety estimation unit estimates that the one-way determination unit can proceed to a road that is not determined to be a one-way road.
Vehicle control method. A computer mounted on the vehicle including a road recognition unit that recognizes road marking lines and stop lines of roads around the vehicle,
Based on the recognized stop line, it is determined whether the road around the vehicle is a one-way road,
When the vehicle enters an intersection, it is estimated that the road can proceed to a road that is not determined to be a one-way road.
program.

Images