Determination device, determination method, and program

Abstract

To properly cope with misrecognition occurring for a camera lane marking or a map lane marking at the timing before a host vehicle enters a curved road.SOLUTION: A determination device comprises: a recognition unit to recognize a lane marking present in a moving direction of a vehicle; and a determination unit to determine whether the recognized lane marking matches a map lane marking based on map information stored in a storage unit. When the vehicle approaches a curved road, the determination unit determines whether the lane marking recognized by the recognition unit matches the map lane marking, with a restriction on a range of the recognized lane marking to a range before a reference point taking into consideration a switching point to the curved road.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a determination device, a determination method, and a program. [Background technology]

[0002] In recent years, efforts to provide access to sustainable transportation systems that take into consideration vulnerable transport participants have been gaining momentum. To achieve this, we are focusing on research and development into autonomous driving technology to further improve traffic safety and convenience.

[0003] In autonomous driving technology, road dividing lines recognized from camera images are confirmed to coincide with road dividing lines recognized from map information, and the coincidence is used to generate a target trajectory for the vehicle. However, when the vehicle travels on a curved road or a branching road, for example, there is a problem in that the road dividing lines recognized from camera images are likely to be misrecognized. To address this problem, for example, Patent Document 1 discloses a technique for restricting image recognition on the branching side when the vehicle is located in a branching road section. Furthermore, Patent Document 2 discloses a technique for integrating information on the actual boundary and the map boundary obtained from the recognition ranges in front and behind the vehicle when the continuity evaluation of the actual boundary and the map boundary is high, while using the map boundary when the evaluation is low. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Publication No. 2017-068617 [Patent Document 2] Japanese Patent Application Publication No. 2018-200501 Summary of the Invention [Problem to be solved by the invention]

[0005] However, these conventional techniques set all road shapes that are difficult to recognize as detection suppression ranges, and as a result of excessive suppression, the recognition accuracy of road dividing lines may decrease.

[0006] The present invention has been made in consideration of the above circumstances, and one of its objects is to provide a determination device, a determination method, and a program that can appropriately set the recognition range of a road-dividing line camera while the vehicle is traveling on a curved road, thereby contributing to the development of a sustainable transportation system. [Means for solving the problem]

[0007] The determination device according to the present invention employs the following configuration. (1): A determination device according to one embodiment of the present invention includes a recognition unit that recognizes road dividing lines present in the direction of travel of a vehicle, and a determination unit that determines whether the recognized road dividing lines match map road dividing lines based on map information stored in a memory unit. When the vehicle is traveling on a curved road, the determination unit sets the distance from the vehicle to the far end of the determination range in the direction of travel of the vehicle to be shorter than when the vehicle is not traveling on a curved road.

[0008] (2) In the above aspect (1), the determination unit sets the distance to the far end of the determination range in accordance with the gradient of the curved road.

[0009] (3): In the above aspect (2), the determination unit sets the distance to the position where the difference in the vehicle width direction between the map road dividing line and a gradient map road dividing line obtained by correcting the map road dividing line according to the gradient is equal to or greater than a specified value as the distance to the far end.

[0010] (4): In the above aspect (2), the determination unit sets the distance to the far end as the distance to a position a predetermined distance before the position where the difference in the vehicle width direction between the map road dividing line and the gradient map road dividing line obtained by correcting the map road dividing line according to the gradient is equal to or greater than a specified value.

[0011] (5): In the above aspect (1), the recognition unit identifies a junction where a line extending from a predetermined position of the vehicle meets one of the recognized road dividing lines on the inside of the curved road, and the determination unit sets the distance to the far end of the determination range according to the position of the junction.

[0012] (6): In the above aspect (5), the determination unit sets the distance from the position of the contact point to a position a predetermined distance further back within the determination range as the distance to the far end.

[0013] (7) In the above aspect (1), the determination unit sets the distance to the far end of the determination range in accordance with the degree of curvature of the curved road.

[0014] (8) In the above aspect (7), the determining unit shortens the distance to the far end as the degree of curvature of the curved road increases.

[0015] (9): In the above aspect (1), the recognition unit identifies a junction where a line extending from a predetermined position of the vehicle meets one of the recognized road dividing lines on the inside of the curved road, and the determination unit sets a first candidate for the far end according to the gradient of the curved road, sets a second candidate for the far end according to the position of the junction, and sets a third candidate for the far end according to the degree of curvature of the curved road, and the determination unit sets the candidate that is located in front of the vehicle out of at least two of the first candidate, the second candidate, and the third candidate as the far end.

[0016] (10): In the above aspect (9), the determination unit sets the position where the difference in the vehicle width direction between the map road dividing line and a gradient map road dividing line obtained by correcting the map road dividing line according to the gradient is equal to or greater than a specified value as the first candidate, and the determination unit sets a position a predetermined distance behind the position of the tangent point as the second candidate.

[0017] (11): In the above aspect (9) or (10), the determination unit sets the position where the difference in the vehicle width direction between the map road dividing line and a gradient map road dividing line obtained by correcting the map road dividing line according to the gradient is equal to or greater than a specified value as the first candidate, and the determination unit sets a position a predetermined distance behind the position of the tangent point as the second candidate.

[0018] (12): In another aspect of the present invention, a determination method is provided in which a computer mounted on a vehicle recognizes road dividing lines present in the direction of travel of the vehicle, determines whether the recognized road dividing lines match map road dividing lines based on map information stored in a memory unit, and, when the vehicle is traveling on a curved road, sets the distance from the vehicle to the far end of the determination range in the direction of travel of the vehicle to be shorter than when the vehicle is not traveling on a curved road.

[0019] (13): Another aspect of the present invention is a program that causes a computer mounted on a vehicle to recognize road dividing lines that exist in the direction of travel of the vehicle, determine whether the recognized road dividing lines match map road dividing lines based on map information stored in a memory unit, and, when the vehicle is traveling on a curved road, set the distance from the vehicle to the far end of the judgment range in the direction of travel of the vehicle to be shorter than when the vehicle is not traveling on a curved road. [Effects of the Invention]

[0020] According to the above aspects (1) to (13), the recognition range of the road dividing line by the camera can be appropriately set while the vehicle is traveling on a curved road.

[0021] According to the above aspects (2) to (4), the recognition range of the road dividing line with the camera can be appropriately set according to the gradient of the curved road.

[0022] According to the above aspects (5) to (8), the recognition range of the road dividing line with the camera can be appropriately set according to the degree of curvature of the curved road.

[0023] According to the above aspects (9) to (11), the recognition range of the road dividing line with the camera can be appropriately set according to the gradient and degree of curvature of the curved road. [Brief explanation of the drawings]

[0024] [Figure 1] 1 is a configuration diagram of a vehicle system using a determination device according to an embodiment; [Figure 2] FIG. 2 is a functional configuration diagram of a first control unit and a second control unit. [Figure 3] FIG. 2 is a diagram illustrating an example of a correspondence relationship between a driving mode, a control state of a host vehicle, and a task. [Figure 4] 10 is a diagram showing an example of a scene of a determination process executed by a determination unit 132. FIG. [Figure 5] 10 is a diagram showing another example of a scene of the determination process executed by the determination unit 132. FIG. [Figure 6] 10 is a diagram for explaining a method for selecting a far end portion by a determining unit 132. FIG. [Figure 7] 10 is a flowchart showing an example of the flow of processing executed by a determination unit 132. [Figure 8] 10 is a diagram for explaining a method for selecting a far end portion by a determining unit 132 according to a modified example. FIG. DETAILED DESCRIPTION OF THE INVENTION

[0025] Hereinafter, embodiments of a determination device, a determination method, and a program according to the present invention will be described with reference to the drawings.

[0026] [Overall configuration] 1 is a configuration diagram of a vehicle system 1 that uses a determination device according to an embodiment. The vehicle on which the vehicle system 1 is mounted may be, for example, a two-wheeled, three-wheeled, or four-wheeled vehicle, and its drive source may be an internal combustion engine such as a diesel engine or a gasoline engine, an electric motor, or a combination of these. The electric motor operates using power generated by a generator connected to the internal combustion engine, or discharged power from a secondary battery or a fuel cell.

[0027] The vehicle system 1 includes, for example, a camera 10, a radar device 12, a LIDAR (Light Detection and Ranging) 14, an object recognition device 16, a communication device 20, an HMI (Human Machine Interface) 30, vehicle sensors 40, a navigation device 50, an MPU (Map Positioning Unit) 60, a driver monitor camera 70, a driving operator 80, an automatic driving control device 100, a driving force output device 200, a braking device 210, and a steering device 220. These devices and equipment are connected to each other via multiplexed communication lines such as a CAN (Controller Area Network) communication line, serial communication lines, a wireless communication network, etc. Note that the configuration shown in FIG. 1 is merely an example, and some of the configuration may be omitted, or other configurations may be added.

[0028] The camera 10 is, for example, a digital camera using a solid-state imaging element such as a CCD (Charge Coupled Device) or a CMOS (Complementary Metal Oxide Semiconductor). The camera 10 is attached to any location of a vehicle (hereinafter referred to as the host vehicle M) in which the vehicle system 1 is installed. When capturing an image of the front, the camera 10 is attached to the top of the front windshield, the back of the rearview mirror, or the like. The camera 10, for example, periodically and repeatedly captures images of the surroundings of the host vehicle M. The camera 10 may be a stereo camera.

[0029] The radar device 12 emits radio waves such as millimeter waves around the vehicle M and detects radio waves reflected by an object (reflected waves) to detect at least the position (distance and direction) of the object. The radar device 12 is attached to any location on the vehicle M. The radar device 12 may detect the position and speed of an object using an FM-CW (Frequency Modulated Continuous Wave) method.

[0030] The LIDAR 14 irradiates the surroundings of the vehicle M with light (or electromagnetic waves with wavelengths similar to light) and measures the scattered light. The LIDAR 14 detects the distance to the target based on the time between light emission and light reception. The irradiated light is, for example, pulsed laser light. The LIDAR 14 is attached to any location on the vehicle M.

[0031] The object recognition device 16 performs sensor fusion processing on the detection results from some or all of the camera 10, the radar device 12, and the LIDAR 14 to recognize the position, type, speed, etc. of the object. The object recognition device 16 outputs the recognition results to the automatic driving control device 100. The object recognition device 16 may output the detection results from the camera 10, the radar device 12, and the LIDAR 14 directly to the automatic driving control device 100. The object recognition device 16 may be omitted from the vehicle system 1.

[0032] The communication device 20 communicates with other vehicles in the vicinity of the vehicle M, for example, using a cellular network, a Wi-Fi network, Bluetooth (registered trademark), DSRC (Dedicated Short Range Communication), etc., or communicates with various server devices via a wireless base station.

[0033] The HMI 30 presents various information to the occupants of the vehicle M and accepts input operations by the occupants. The HMI 30 includes various display devices, a speaker, a buzzer, a touch panel, switches, keys, and the like.

[0034] 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 angular velocity around a vertical axis, a direction sensor that detects the direction of the host vehicle M, and the like.

[0035] 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 navigation device 50 stores first map information 54 in a storage device such as a hard disk drive (HDD) or flash memory. The GNSS receiver 51 identifies the position of the vehicle M based on signals received from GNSS satellites. The position of the vehicle M may be identified or supplemented by an inertial navigation system (INS) that uses the output of the vehicle sensors 40. The navigation HMI 52 includes a display device, a speaker, a touch panel, keys, etc. The navigation HMI 52 may share some or all of the components with the HMI 30 described above. The route determination unit 53 determines, for example, a route (hereinafter, a map route) from the position of the vehicle M identified by the GNSS receiver 51 (or any input position) to a destination input by the occupant using the navigation HMI 52, with reference to the first map information 54. The first map information 54 is information that represents road shapes using, for example, links indicating roads and nodes connected by the links. The first map information 54 may also include information such as road curvature and POI (Point of Interest) information. The route on the map is output to the MPU 60. The navigation device 50 may provide route guidance using the navigation HMI 52 based on the route on the map. The navigation device 50 may be realized, for example, by the functions of a terminal device such as a smartphone or tablet device owned by the occupant. The navigation device 50 may transmit the current position and destination to a navigation server via the communication device 20 and obtain a route equivalent to the route on the map from the navigation server.

[0036] The MPU 60 includes, for example, a recommended lane determination unit 61, and stores second map information 62 and distance measurement map information 64 in a storage device such as an HDD or flash memory. The recommended lane determination unit 61 divides the route on the map provided by the navigation device 50 into a plurality of blocks (for example, by dividing each block into 100 m in the vehicle travel direction), and determines a recommended lane for each block by referring to the second map information 62. The recommended lane determination unit 61 determines, for example, which lane from the left the vehicle should travel in. When there is a branch point on the route on the map, the recommended lane determination unit 61 determines a recommended lane so that the vehicle M can travel on a reasonable route to the branch point.

[0037] 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 centers of lanes or information on lane boundaries. The second map information 62 may also include road information, traffic regulation information, address information (address and postal code), facility information, telephone number information, information on prohibited sections where mode A or mode B, described below, is prohibited, and the like. The second map information 62 may be updated as needed by the communication device 20 communicating with another device.

[0038] Like the second map information 62, the measured map information 64 includes information on the center of a lane or information on lane boundaries, and is map information in which gradient information (e.g., values ​​such as elevation) associated with each position of the lane is pre-recorded. When the host vehicle M travels on a curved road, the determination unit 132, which will be described later, corrects the boundary of the lane where the host vehicle M is located based on the gradient information and converts it into a lane boundary from the host vehicle M's viewpoint that takes into account the gradient of the lane. Hereinafter, the lane boundary information obtained from the second map information 62 will be referred to as a "map road dividing line," and the lane boundary information obtained by correcting the lane boundaries stored in the measured map information 64 based on the gradient information will be referred to as a "gradient map road dividing line." The gradient map road dividing line can be expressed as a prediction of the lane boundary from the host vehicle M's viewpoint recognized by the camera 10 using the gradient information recorded in the measured map information 64. In another embodiment, the gradient map road dividing lines can be expressed as map road dividing lines corrected using gradient information recorded in the distance measurement map information 64.

[0039] The driver monitor camera 70 is, for example, a digital camera that uses a solid-state imaging element such as a CCD or CMOS. The driver monitor camera 70 is attached to any location on the vehicle M in a position and orientation that allows it to capture an image of the head of an occupant (hereinafter, driver) seated in the driver's seat of the vehicle M from the front (in an orientation that captures an image of the face). For example, the driver monitor camera 70 is attached to the top of a display device provided in the center of the instrument panel of the vehicle M.

[0040] The driving operators 80 include, for example, a steering wheel 82, an accelerator pedal, a brake pedal, a shift lever, and other operators. The driving operators 80 are equipped with sensors that detect the amount of operation or the presence or absence of operation, and the detection results are output to the automatic driving control device 100 or some or all of the driving force output device 200, the brake device 210, and the steering device 220. The steering wheel 82 is an example of an "operator that accepts steering operation by the driver." The operator does not necessarily have to be annular and may be in the form of an irregular steering wheel, a joystick, a button, or the like. A steering grip sensor 84 is attached to the steering wheel 82. The steering grip sensor 84 is realized by a capacitance sensor or the like, and outputs a signal to the automatic driving control device 100 that can detect whether the driver is gripping the steering wheel 82 (meaning that the driver is in contact with the steering wheel in a state where force can be applied).

[0041] The automatic driving control device 100 includes, for example, a first control unit 120 and a second control unit 160. The first control unit 120 and the second control unit 160 are each realized by, for example, a hardware processor such as a CPU (Central Processing Unit) executing a program (software). Some or all of these components may be realized by hardware (including circuitry) such as an LSI (Large Scale Integration), an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array), a GPU (Graphics Processing Unit), or an SOC (System On Chip), or may be realized by a combination of software and hardware. The program may be stored in advance in a storage device (a storage device having a non-transitory storage medium) such as a HDD or flash memory of the automatic driving control device 100, or may be stored in a removable storage medium such as a DVD or CD-ROM, and installed in the HDD or flash memory of the automatic driving control device 100 by inserting the storage medium (non-transitory storage medium) into a drive device. The automatic driving control device 100 including the determination unit 132 described later is an example of a "determination device."

[0042] 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, a determination unit 132, an action plan generation unit 140, and a mode determination unit 150. The first control unit 120, for example, implements functions based on AI (Artificial Intelligence) and functions based on a predefined model in parallel. For example, the function of "recognizing intersections" may be implemented by executing intersection recognition using deep learning or the like and recognition based on predefined conditions (such as traffic lights and road markings that can be pattern-matched) in parallel, and then scoring and comprehensively evaluating both. This ensures the reliability of autonomous driving.

[0043] The recognition unit 130 recognizes the position, speed, acceleration, and other states of objects around the vehicle M based on information input from the camera 10, the radar device 12, and the LIDAR 14 via the object recognition device 16. The position of an object is recognized as a position on an absolute coordinate system with a representative point of the vehicle M (such as the center of gravity or the center of the drive shaft) as the origin, and is used for control. The position of an object may be represented by a representative point such as the center of gravity or a corner of the object, or may be represented by an area. The "state" of an object may include the acceleration or jerk of the object, or the "behavioral state" (for example, whether the object is changing lanes or is about to change lanes).

[0044] The recognition unit 130 also recognizes, for example, the lane in which the host vehicle M is traveling (driving lane). For example, the recognition unit 130 recognizes the driving lane by comparing the pattern of road dividing lines obtained from the second map information 62 (hereinafter, sometimes referred to as "map road dividing lines") with the pattern of road dividing lines around the host vehicle M recognized from an image captured by the camera 10 (hereinafter, sometimes referred to as "camera road dividing lines"). More specifically, the determination unit 132 of the recognition unit 130 calculates, for example, the deviation between the map road dividing lines and the camera road dividing lines, and if it determines that the calculated deviation is equal to or less than a threshold (i.e., if it determines that they match), it recognizes either the map road dividing lines or the camera road dividing lines (or their midline, etc.) as the driving lane. Details of the comparison process between the camera road dividing lines and the camera road dividing lines by the determination unit 132 will be described later. The recognition unit 130 may recognize the driving lane by recognizing road boundaries (road boundaries) including not only road dividing lines but also road shoulders, curbs, medians, guardrails, etc. In this recognition, the position of the vehicle M obtained from the navigation device 50 and the processing results by the INS may be taken into consideration. The recognition unit 130 also recognizes stop lines, obstacles, red lights, toll booths, and other road phenomena.

[0045] When recognizing the driving lane, the recognition unit 130 recognizes the position and attitude of the host vehicle M with respect to the driving lane. For example, the recognition unit 130 may recognize the deviation of the reference point of the host vehicle M from the center of the lane and the angle it forms with a line connecting the centers of the lanes in the traveling direction of the host vehicle M as the relative position and attitude of the host vehicle M with respect to the driving lane. Alternatively, the recognition unit 130 may recognize the position of the reference point of the host vehicle M with respect to either side edge of the driving lane (a road dividing line or a road boundary) as the relative position of the host vehicle M with respect to the driving lane.

[0046] The behavior plan generation unit 140 automatically (without driver input) generates a target trajectory for the host vehicle M to travel in the recommended lane determined by the recommended lane determination unit 61, and to avoid approaching any objects recognized by the recognition unit 130 (excluding objects that can be overcome, such as road dividing lines, road markings, and manholes). For example, the recognition unit 130 sets a risk area centered on the object whose status has been output, and within the risk area, the recognition unit 130 sets a risk as an index value indicating the degree to which the host vehicle M should not approach. The behavior plan generation unit 140 generates a target trajectory for the host vehicle M to avoid passing through points where the risk is equal to or greater than a predetermined value and to travel within the recognized travel lane. Because some objects are moving, the risk distribution is not one per control cycle, but is set for multiple future time points, taking into account the future position of the object predicted based on the object's speed. For example, the target trajectory is expressed as a sequential list of points (trajectory points) to be reached by the host vehicle M. The trajectory points are points that the host vehicle M should reach at every predetermined travel distance (for example, about several meters) along the road, and separately, the target speed and target acceleration are generated as part of the target trajectory at every predetermined sampling time (for example, about a few tenths of a second). The trajectory points may also be positions that the host vehicle M should reach at every predetermined sampling time. In this case, the information on the target speed and target acceleration is expressed as the interval between the trajectory points.

[0047] The behavior plan generation unit 140 may set an autonomous driving event when generating the target trajectory. The autonomous driving events include a constant speed driving event, a low-speed following driving event, a lane change event, a branching event, a merging event, a takeover event, etc. The behavior plan generation unit 140 generates a target trajectory according to the activated event.

[0048] The mode determination unit 150 determines the driving mode of the host vehicle M to be one of a plurality of driving modes that assign different tasks to the driver. FIG. 3 is a diagram showing an example of the correspondence between the driving modes, the control state of the host vehicle M, and the tasks. The driving modes of the host vehicle M include, for example, five modes, Mode A to Mode E. The control state, i.e., the degree of automation of the driving control of the host vehicle M, is Mode A, which is the highest, followed by Mode B, Mode C, and Mode D, with Mode E being the lowest. Conversely, the tasks assigned to the driver are Mode A, which is the lightest, followed by Mode B, Mode C, and Mode D, with Mode E being the most severe. Note that Modes D and E are non-autonomous driving control states, and therefore the autonomous driving control device 100 is responsible for terminating control related to autonomous driving and transitioning to driving assistance or manual driving. The contents of each driving mode are exemplified below.

[0049] In Mode A, the vehicle is in an autonomous driving state, and the driver is not required to monitor the road ahead or grip the steering wheel 82 (in the figure, gripping the steering wheel). However, even in Mode A, the driver is required to be in a position where he or she can quickly switch to manual driving in response to a request from a system centered on the automatic driving control device 100. Note that, as used herein, "automatic driving" refers to control of both steering and acceleration / deceleration without driver input. "Ahead" refers to the space in the direction of travel of the host vehicle M, as viewed through the front windshield. Mode A is a driving mode that can be implemented, for example, on a motorway such as an expressway, when certain conditions are met, such as the host vehicle M traveling at a predetermined speed (e.g., approximately 50 km / h) or less and there is a vehicle ahead to be followed, and is sometimes referred to as TJP (Traffic Jam Pilot). If these conditions are no longer met, the mode determination unit 150 changes the driving mode of the host vehicle M to Mode B.

[0050] In mode B, the vehicle is in a driving assistance state, and the driver is tasked with monitoring the area ahead of the vehicle M (hereinafter referred to as forward monitoring), but is not tasked with holding the steering wheel 82. In mode C, the vehicle is in a driving assistance state, and the driver is tasked with monitoring the area ahead and holding the steering wheel 82. Mode D is a driving mode that requires some degree of driver operation for at least one of steering and acceleration / deceleration of the vehicle M. For example, in mode D, driving assistance such as ACC (Adaptive Cruise Control) and LKAS (Lane Keeping Assist System) is provided. Mode E is a manual driving state in which the driver must perform both steering and acceleration / deceleration operations. In both mode D and mode E, the driver is naturally tasked with monitoring the area ahead of the vehicle M.

[0051] The driving modes are not limited to those illustrated in FIG. 3 and may be defined by other definitions. For example, among driving modes that require both forward monitoring and gripping the steering wheel, there may be driving modes with lenient thresholds for determining that the steering wheel is being gripped and driving modes with stricter thresholds. More specifically, driving modes may be defined such that in one driving mode, it is sufficient for the driver to have either the left or right hand touching the steering wheel 82, while in another driving mode that imposes a heavier task on the driver, the driver must grip the steering wheel 82 with both hands with a strength equal to or greater than a threshold. Driving modes that differ in the severity of the tasks imposed on the driver may be defined in any other way.

[0052] The automatic driving control device 100 (and the driving assistance device (not shown)) executes an automated lane change according to the driving mode. There are two types of automated lane changes: a system-requested automated lane change (1) and a driver-requested automated lane change (2). The automated lane change (1) is an automated lane change for overtaking, which is performed when the speed of the vehicle ahead is slower than the speed of the vehicle itself by a standard or more, and an automated lane change for proceeding toward the destination (an automated lane change due to a change in the recommended lane). The automated lane change (2) is a lane change in which, when conditions related to the speed and the positional relationship with surrounding vehicles are met and the driver operates the turn signal, the vehicle M changes lanes in the direction of the operation.

[0053] In mode A, the automatic driving control device 100 does not perform either automated lane change (1) or (2). In modes B and C, the automatic driving control device 100 performs either automated lane change (1) or (2). In mode D, the driving assistance device (not shown) does not perform automated lane change (1), but performs automated lane change (2). In mode E, neither automated lane change (1) nor (2) is performed.

[0054] When the driver does not perform a task related to the determined driving mode (hereinafter, the current driving mode), the mode determination unit 150 changes the driving mode of the vehicle M to a driving mode with a more difficult task.

[0055] For example, in mode A, if the driver is in a position where he or she cannot switch to manual driving in response to a request from the system (for example, if the driver continues to look away from the road outside the allowable area or if a sign of driving difficulty is detected), the mode determination unit 150 uses the HMI 30 to prompt the driver to switch to manual driving, and if the driver does not comply, the mode determination unit 150 performs control such as pulling the host vehicle M to the shoulder of the road and gradually stopping it, and stopping the automatic driving. After the automatic driving is stopped, the host vehicle enters a state of mode D or E, and the host vehicle M can be started by manual operation by the driver. The same applies below to "stopping automatic driving." In mode B, if the driver is not monitoring the road ahead, the mode determination unit 150 performs control such as prompting the driver to monitor the road ahead using the HMI 30, and if the driver does not comply, pulling the host vehicle M to the shoulder of the road and gradually stopping it, and stopping the automatic driving. In mode C, if the driver is not monitoring the road ahead or is not gripping the steering wheel 82, the mode determination unit 150 uses the HMI 30 to prompt the driver to monitor the road ahead and / or grip the steering wheel 82, and if the driver does not comply, the mode determination unit 150 controls the vehicle M to move to the shoulder of the road and gradually stop, thereby terminating automatic driving.

[0056] The mode determination unit 150 further monitors the driver's state for the above-mentioned mode change and determines whether the driver's state is appropriate for the task. For example, the mode determination unit 150 analyzes the image captured by the driver monitor camera 70 and performs posture estimation processing to determine whether the driver is in a position that prevents them from switching to manual driving in response to a request from the system. In addition, the driver state determination unit 152 analyzes the image captured by the driver monitor camera 70 and performs line-of-sight estimation processing to determine whether the driver is monitoring the road ahead.

[0057] Furthermore, in this embodiment, if the determination unit 132 determines that the map road dividing lines and the camera road dividing lines do not match, the mode determination unit 150 changes the driving mode of the host vehicle M to a driving mode with a more difficult task. For example, if the mode determination unit 150 determines that the map road dividing lines and the camera road dividing lines do not match while the host vehicle M is traveling in a driving mode (mode A or mode B) that does not require gripping the steering wheel, the mode determination unit 150 changes the driving mode to mode D or mode E.

[0058] The mode determination unit 150 further performs various processes for changing the mode. For example, the mode determination unit 150 instructs the action plan generation unit 140 to generate a target trajectory for stopping on the shoulder of the road, instructs a driving assistance device (not shown) to operate, and controls the HMI 30 to prompt the driver to take action.

[0059] The second control unit 160 controls the traveling driving force output device 200, the braking device 210, and the steering device 220 so that the host vehicle M passes through the target trajectory generated by the action plan generation unit 140 at the scheduled time.

[0060] Returning to FIG. 2, 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 (trajectory points) generated by the action plan generation unit 140 and stores it in a memory (not shown). The speed control unit 164 controls the driving force output device 200 or the brake device 210 based on a speed element associated with the target trajectory stored in the memory. The steering control unit 166 controls the steering device 220 according to the curvature 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 feedforward control according to the curvature of the road ahead of the host vehicle M and feedback control based on the deviation from the target trajectory.

[0061] The driving force output device 200 outputs a driving force (torque) for the vehicle to travel to the drive wheels. The driving force output device 200 includes, for example, a combination of an internal combustion engine, an electric motor, a transmission, etc., and an ECU (Electronic Control Unit) that controls these. The ECU controls the above components according to information input from the second control unit 160 or information input from the driving operator 80.

[0062] Braking device 210 may include, 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 according to information input from second control unit 160 or information input from driving operation device 80, so that a brake torque corresponding to the braking operation is output to each wheel. Braking device 210 may include a backup mechanism that transmits hydraulic pressure generated by operation of a brake pedal included in driving operation device 80 to the cylinder via a master cylinder. Note that braking device 210 is not limited to the configuration described above, and may also be an electronically controlled hydraulic brake device that controls an actuator according to information input from second control unit 160 to transmit hydraulic pressure from a master cylinder to the cylinder.

[0063] The steering device 220 includes, for example, a steering ECU and an electric motor. The electric motor applies a force to a rack and pinion mechanism to change the direction of the steered wheels. The steering ECU drives the electric motor in accordance with information input from the second control unit 160 or information input from the driving operator 80 to change the direction of the steered wheels.

[0064] [Processing when driving on a curved road] As described above, the determination unit 132 compares the map road dividing lines obtained from the second map information 62 with the camera road dividing lines recognized from the camera image to determine whether they match. If it is determined that the map road dividing lines and the camera road dividing lines match, the behavior plan generation unit 140 generates a target trajectory for the host vehicle M so that the host vehicle M travels in a driving lane that aligns with the map road dividing lines or the camera road dividing lines. However, for example, when the host vehicle M travels on a curved road (more generally, a road where the curvature change of the dividing lines is equal to or greater than a threshold), erroneous recognition of camera road dividing lines that are located farther in the traveling direction of the host vehicle M is likely to occur, resulting in a determination that the map road dividing lines and the camera road dividing lines do not match. As a result, even if the erroneous recognition is corrected over time and a change in the driving mode is not necessary, the mode determination unit 150 may change the driving mode of the host vehicle M to a driving mode with a more complex task, which may impair convenience for the driver.

[0065] In light of this, when the determination unit 132 determines, based on the second map information 62, that the host vehicle M is traveling on a curved road, the determination unit 132 sets the distance from the host vehicle M to the far end of the range of the camera road dividing lines recognized by the recognition unit 130 (hereinafter, sometimes referred to as the "determination range") in the host vehicle M's traveling direction to be shorter than when the vehicle is not traveling on a curved road. In this case, the near end of the determination range may be a predetermined location on the host vehicle M or may be a predetermined distance ahead of that. Furthermore, the determination unit 132 may determine that the host vehicle M is traveling on a curved road based on registration information indicating the curved road stored in the second map information 62, or may calculate the curvature of the road on which the host vehicle M is traveling from the road information stored in the second map information 62, and determine that the host vehicle M is traveling on a curved road when the calculated curvature is equal to or greater than a threshold value. Hereinafter, the determination process by the determination unit 132 will be described in detail with reference to FIGS. 4 to 6.

[0066] FIG. 4 is a diagram illustrating an example of a scene of the determination process executed by the determination unit 132. In FIG. 4, the symbol CL represents the camera road dividing line recognized by the recognition unit 130, the symbol ML represents the map road dividing line, and the symbol ML' represents the gradient map road dividing line. As an example, FIG. 4 illustrates a situation in which the map road dividing line, the camera road dividing line, and the gradient map road dividing line deviate from each other due to a downward gradient of the curved road on which the host vehicle M is traveling, and ΔY represents the deviation in the vehicle width direction Y between the map road dividing line ML and the gradient map road dividing line ML'. The greater the gradient value of the curved road, the greater the deviation ΔY, which in turn tends to increase the deviation between the map road dividing line ML and the camera road dividing line CL (in other words, the greater the misrecognition of the camera road dividing line CL). Generally, if the curved road has a downward gradient, the gradient map road division line ML' tends to deviate to the inside of the curve, and if the curved road has an upward gradient, it tends to deviate to the outside of the curve.

[0067] Therefore, while the host vehicle M is traveling on a curved road, the determination unit 132 identifies a point EP1 on the map road-dividing line ML where the deviation ΔY is equal to or greater than a specified value. Here, the specified value indicates the limit of the allowable range of erroneous recognition of the camera road-dividing line CL used for matching with the map road-dividing line ML. Upon identifying point EP1 where the deviation ΔY is equal to or greater than the specified value, the determination unit 132 sets the point EP1 as the far end of the range within the recognition range RA where the camera road-dividing line CL and the map road-dividing line ML are matched.

[0068] Next, the determination unit 132 determines whether the camera road dividing line CL and the map road dividing line ML match in the range of the recognition range RA that is closer to the far end EP1 in the traveling direction X of the vehicle M. As a result, in the case of FIG. 4, the distance d' between the camera road dividing line CL and the map road dividing line ML in the range of the recognition range RA that is further back than the far end EP1 is not used for the comparison process, and instead, for example, the distance d in the range closer to the far end EP1 is used for the comparison process. This prevents a downgrade in the driving mode caused by a mismatch between the camera road dividing line CL and the map road dividing line ML due to erroneous recognition of the camera road dividing line CL caused by the gradient of a curved road.

[0069] In FIG. 4, as an example, the point EP1 where the deviation ΔY is a specified value is set as the far end EP1 as it is, but the present invention is not limited to such a configuration, and the far end EP1 may be set as a point offset a predetermined distance toward the front or the back in the traveling direction X of the host vehicle M from the point EP1 where the deviation ΔY is a specified value.

[0070] FIG. 5 is a diagram illustrating another example of a determination process executed by the determination unit 132. While FIG. 4 illustrates a method for dealing with errors in the camera-captured road lane markings CL due to the gradient of a curved road, FIG. 5 illustrates a method for dealing with errors in the camera-captured road lane markings CL due to a large degree of curvature of the curved road (i.e., a small radius of curvature). More specifically, the camera-captured road lane markings CL generally have low recognition accuracy in the traveling direction X, and the greater the curvature of the curved road, the greater the impact of errors in recognition accuracy in the traveling direction X on distance measurement errors in the vehicle width direction Y. In other words, even if the error in recognition accuracy in the traveling direction X is small, the greater the degree of curvature of the curved road will result in larger distance measurement errors in the vehicle width direction Y. As a result, it is more likely that the camera-captured road lane markings CL and the map road lane markings ML will be determined to be inconsistent (misrecognition of the camera-captured road lane markings CL). The method shown in FIG. 5 takes into consideration the relationship between the error in recognition accuracy in the traveling direction X and the distance measurement error in the vehicle width direction Y, and by limiting the recognition range RA, it becomes easier to avoid determining that the camera road-dividing lines CL and the map road-dividing lines ML do not match.

[0071] More specifically, while the host vehicle M is traveling on a curved road, the determination unit 132 first identifies a point of contact CP between a reference line originating from a reference point RP of the host vehicle M and a camera road-dividing line CL on the inside of the curved road (the side that is more tolerant to the degree of curvature of the curved road). Here, the reference point RP may be, for example, a predetermined position at the front end of the host vehicle M (for example, the installation position of the camera 10), or the center of gravity. Next, the determination unit 132 sets a point EP2 a predetermined distance Ex_x behind the identified position of the point of contact CP in the traveling direction X of the host vehicle M as the far end of a range in which the camera road-dividing line CL and the map road-dividing line ML are matched.

[0072] Next, the determination unit 132 determines whether the camera road dividing line CL and the map road dividing line ML match in a range of the recognition range RA that is closer to the far end EP2 in the traveling direction X of the host vehicle M. In the above algorithm, the far end EP2 is set closer to the host vehicle M in the traveling direction X, the greater the curvature of the curved road (the smaller the radius of curvature). As a result, in the case of FIG. 5 , the distance d' between the camera road dividing line CL and the map road dividing line ML in the range of the recognition range RA that is further back than the far end EP2 is not used for the comparison process. For example, the distance d in the range closer to the far end EP2 is used for the comparison process. This prevents a misrecognition of the camera road dividing line CL due to the curvature of the curved road from determining that the camera road dividing line CL and the map road dividing line ML do not match, and prevents the driving mode from being downgraded.

[0073] 4 and 5 each limit the recognition range RA for matching the camera road-dividing lines CL with the map road-dividing lines ML in order to address erroneous recognition of the camera road-dividing lines CL due to the gradient and curvature of a curved road. In this embodiment, the determination unit 132 selects, from the calculated far end EP1 and far end EP2, the far end that is closer in the traveling direction X of the host vehicle M in order to simultaneously address erroneous recognition of the camera road-dividing lines CL due to these two factors. In this case, the far end EP1 is an example of a "first candidate" in the claims, and the far end EP2 is an example of a "second candidate" in the claims.

[0074] FIG. 6 is a diagram illustrating a method for selecting a far end by the determination unit 132. FIG. 6 illustrates, as an example, a situation in which the map road dividing line, the camera road dividing line, and the gradient map road dividing line are separated due to an uphill gradient of a curved road on which the host vehicle M is traveling. As shown in FIG. 6, while the host vehicle M is traveling on a curved road, the determination unit 132 calculates a far end EP1 at which the deviation ΔY in the vehicle width direction Y between the map road dividing line ML and the gradient map road dividing line ML′ is equal to or greater than a predetermined value. At the same time, the determination unit 132 calculates a far end EP2 that is a predetermined distance Ex_x further back in the traveling direction X of the host vehicle M from the position of a junction CP between a reference line starting from the reference point RP of the host vehicle M and the camera road dividing line CL on the inside of the curved road. Next, the determination unit 132 sets the far end EP that is closer to the host vehicle M in the traveling direction X of the host vehicle M out of the calculated far end EP1 and far end EP2 as the far end EP to be finally used. For example, in the case of FIG. 6, the determination unit 132 determines that the far end portion EP1 is located closer to the front in the traveling direction X of the host vehicle M, and sets it as the far end portion EP to be finally used.

[0075] Next, the determination unit 132 determines whether the camera road dividing lines CL and the map road dividing lines ML match within the recognition range RA, in a range before the far end EP in the traveling direction X of the vehicle M. As a result, according to this embodiment, it is possible to prevent a mismatch between the camera road dividing lines CL and the map road dividing lines ML, which would be determined due to erroneous recognition of the camera road dividing lines CL caused by the gradient and curvature of the curved road, and to prevent the driving mode from being downgraded.

[0076] 4, the gradient map road dividing line ML', the camera road dividing line CL, and the map road dividing line ML are arranged in this order from the inside of the turn, whereas in FIG. 6, the map road dividing line ML, the gradient map road dividing line ML', and the camera road dividing line CL are arranged in this order from the inside of the turn. When the map road dividing line ML is arranged on the outermost side of the turn, this means that the curved road has a downward slope, whereas when the map road dividing line ML is arranged on the innermost side of the turn, this means that the curved road has an upward slope. The order of the gradient map road dividing line ML' and the camera road dividing line CL can vary depending on the actual recognition results by the camera 10.

[0077] Next, the flow of processing executed by the determination unit 132 will be described with reference to Fig. 7. Fig. 7 is a flowchart showing an example of the flow of processing executed by the determination unit 132. The processing shown in the flowchart in Fig. 7 is repeatedly executed by the determination unit 132 while the host vehicle M is traveling in a driving mode in which autonomous driving or driving assistance is executed.

[0078] First, the determination unit 132 determines whether or not the presence of a curved road has been detected in the traveling direction of the host vehicle M, based on the second map information 62 (step S100). If it is determined that the presence of a curved road has not been detected in the traveling direction of the host vehicle M, the determination unit 132 executes the process of step S100 again after a certain time has elapsed. On the other hand, if it is determined that the presence of a curved road has been detected in the traveling direction of the host vehicle M, the determination unit 132 next determines whether or not the host vehicle M has entered a curved road (step S102). If it is determined that the host vehicle M has not entered a curved road, the determination unit 132 executes the process of step S102 again after a certain time has elapsed.

[0079] Next, the determination unit 132 sets a first candidate for the far end of the determination range in accordance with the gradient of the curved road (step S104). Next, the determination unit 132 sets a second candidate for the far end of the determination range in accordance with the point of intersection between the reference line from the host vehicle M and the curved road (step S106). Next, the determination unit 132 sets the candidate that is closer to the far end in the traveling direction X of the host vehicle M, of the first and second candidates for the far end, as the far end (step S108). Next, the determination unit 132 compares the camera road dividing lines with the map road dividing lines within the recognition range of the camera 10, in the range from the far end to the front side of the host vehicle M (step S110). This ends the processing of this flowchart.

[0080] In the above flowchart, for convenience of explanation, the first candidate for the far end is set first, followed by the second candidate for the far end. However, the present invention is not limited to such a configuration. The determination unit 132 may set the first and second candidates for the far end in the reverse order, or may set them simultaneously in parallel. If the determination unit 132 determines that the camera road-dividing line and the map road-dividing line match through the processing of the above flowchart, the mode determination unit 150 continues the automated driving or driving assistance in the current driving mode. On the other hand, if the determination unit 132 determines that the camera road-dividing line and the map road-dividing line do not match, the mode determination unit 150 downgrades the driving mode or prioritizes the map road-dividing line and continues the current driving mode.

[0081] According to the present embodiment described above, when the vehicle is traveling on a curved road, the determination unit sets the distance from the vehicle to the far end in the vehicle's direction of travel within the determination range for making a determination so that it is shorter than when the vehicle is not traveling on a curved road. This makes it possible to appropriately set the camera's road marking recognition range while the vehicle is traveling on a curved road.

[0082] [Variations] In the above embodiment, the determination unit 132 sets the first candidate EP1 and the second candidate EP2 for the far end using the deviation ΔY in the vehicle width direction Y between the map road dividing line ML and the gradient map road dividing line ML′, and the point of contact CP between the reference line starting from the reference point RP of the host vehicle M and the camera road dividing line CL on the inside of the curved road. As a modified example, the determination unit 132 may set the third candidate EP3 for the far end more simply depending on the degree of curvature of the curved road, without performing the calculation process as described above, and may set the candidate that is located in front of the host vehicle M out of at least two of the first candidate EP1, the second candidate EP2, and the third candidate EP3 for the far end as the far end EP.

[0083] FIG. 8 is a diagram illustrating a method for selecting a far end by the determination unit 132 according to a modified example. Similar to FIG. 6, FIG. 8 illustrates a situation in which the map road dividing line, the camera road dividing line, and the gradient map road dividing line are separated due to an uphill gradient of a curved road on which the host vehicle M is traveling. As shown in FIG. 8, while the host vehicle M is traveling on a curved road, the determination unit 132 calculates, for example, the curvature or radius of curvature as the degree of curvature of the recognized camera road dividing line CL or map road dividing line ML. The larger the calculated curvature or the smaller the calculated radius of curvature, the smaller the distance from the host vehicle M is set to the third candidate EP3 on the camera road dividing line CL or map road dividing line ML. Next, the determination unit 132 sets the far end that is closer to the host vehicle M in the traveling direction X of the host vehicle M among the first candidate EP1, the second candidate EP2, and the third candidate EP3 as the far end to be finally used. For example, in the case of FIG. 8, the determination unit 132 determines that the far end portion EP3 is located closer to the front in the traveling direction X of the host vehicle M, and sets it as the far end portion EP to be finally used.

[0084] Next, the determination unit 132 determines whether the camera road-dividing lines CL and the map road-dividing lines ML match within the recognition range RA, in a range before the far end EP in the traveling direction X of the vehicle M. As a result, according to this modification, it is possible to more reliably prevent a mismatch between the camera road-dividing lines CL and the map road-dividing lines ML from being determined and the driving mode from being downgraded.

[0085] The above-described embodiment can be expressed as follows. a storage device storing a program; a hardware processor; The hardware processor executes the program, Recognizes road markings in the direction of travel of the vehicle, determining whether the recognized road dividing line matches a map road dividing line based on map information stored in a storage unit; When the vehicle is traveling on a curved road, the distance from the vehicle to the far end of the determination range in the traveling direction of the vehicle is set to be shorter than when the vehicle is not traveling on a curved road. The determination device is configured as follows.

[0086] The above describes the form for carrying out the present invention using an embodiment, but the present invention is not limited to such an embodiment, and various modifications and substitutions can be made within the scope that does not deviate from the gist of the present invention. [Explanation of symbols]

[0087] 10 Camera 12 Radar equipment 14 LIDAR 16 Object recognition device 100 Automatic driving control device 120 First Control Section 130 Recognition part 132 Judgment section 140 Action Plan Generation Unit 150 Mode determination unit 160 Second Control Section

Claims

1. a recognition unit that recognizes road dividing lines present in the traveling direction of the vehicle; a determination unit that determines whether the recognized road dividing line matches a map road dividing line based on map information stored in a storage unit, the determination unit sets, when the vehicle is traveling on a curved road, a distance from the vehicle to a far end in the traveling direction of the vehicle within a determination range for making the determination so as to be shorter than a distance when the vehicle is not traveling on a curved road. Judgment device.

2. The determination unit sets the distance to the far end of the determination range in accordance with the gradient of the curved road. The determination device according to claim 1 .

3. the determination unit sets, as the distance to the far end, a distance to a position where a difference in a vehicle width direction of the vehicle between the map road division line and a gradient map road division line obtained by correcting the map road division line in accordance with the gradient is equal to or greater than a predetermined value. The determination device according to claim 2 .

4. the determination unit sets, as the distance to the far end, a distance to a position a predetermined distance before a position where a difference in a vehicle width direction of the vehicle between the map road division line and a gradient map road division line obtained by correcting the map road division line in accordance with the gradient becomes equal to or greater than a predetermined value. The determination device according to claim 2 .

5. the recognition unit identifies a point of contact where a line extending from a predetermined position of the vehicle contacts one of the recognized road dividing lines on an inner side of the curved road; The determination unit sets a distance to the far end of the determination range in accordance with the position of the contact point. The determination device according to claim 1 .

6. the determination unit sets a distance from the position of the contact point to a position a predetermined distance further back within the determination range as the distance to the far end. The determination device according to claim 5 .

7. The determination unit sets a distance to the far end of the determination range in accordance with a degree of curvature of the curved road. The determination device according to claim 1 .

8. The determination unit shortens the distance to the far end as the degree of curvature of the curved road increases. The determination device according to claim 7 .

9. the recognition unit identifies a point of contact where a line extending from a predetermined position of the vehicle contacts one of the recognized road dividing lines on an inner side of the curved road; the determination unit sets a first candidate for the far end portion according to a gradient of the curved road, sets a second candidate for the far end portion according to a position of the tangent point, and sets a third candidate for the far end portion according to a degree of curvature of the curved road; the determination unit sets, as the far end portion, one of at least two of the first candidate, the second candidate, and the third candidate that is located on a nearer side of the vehicle; The determination device according to claim 1 .

10. the determination unit sets, as the first candidate, a position where a difference in a vehicle width direction of the vehicle between the map road dividing line and a gradient map road dividing line obtained by correcting the map road dividing line in accordance with the gradient is equal to or greater than a predetermined value, and the determination unit sets, as the second candidate, a position that is a predetermined distance behind the position of the tangent point. The determination device according to claim 9 .

11. The determination unit sets a position set according to a degree of curvature of the curved road as the third candidate. The determination device according to claim 9 or 10.

12. The vehicle's on-board computer Recognizes road markings in the direction of travel of the vehicle, determining whether the recognized road dividing line matches a map road dividing line based on map information stored in a storage unit; When the vehicle is traveling on a curved road, the distance from the vehicle to the far end of the determination range in the traveling direction of the vehicle is set to be shorter than when the vehicle is not traveling on a curved road. Judgment method.

13. The vehicle's on-board computer Recognizes road dividing lines in the direction of travel of the vehicle, determining whether or not the recognized road dividing line coincides with a map road dividing line based on map information stored in a storage unit; When the vehicle is traveling on a curved road, the distance from the vehicle to the far end of the determination range in the traveling direction of the vehicle is set to be shorter than when the vehicle is not traveling on a curved road. program.

Images