Determination device, determination method, and program

Abstract

To perform determination of deviation of compartment lines more properly, in accordance with a situation of a movement road.SOLUTION: A determination device according to an embodiment is provided with: a first recognition part that recognizes a peripheral situation including a first compartment line comparting a movement road on which a moving body moves, on the basis of output of a sensing device having sensed the peripheral situation of the moving body; a second recognition part that recognizes a second partition line partitioning a movement road around the moving body from map information, on the basis of position information on the moving body; and a determination part that determines whether the first compartment line has deviated from the second compartment line or not. The map information includes height information and bend-degree information on the movement road. When the height information and the bend-degree information satisfy a predetermined condition, the determination part is suppressed from determining that the first compartment line deviates from the second compartment line.SELECTED DRAWING: Figure 2

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 traffic participants have been gaining momentum. To achieve this, efforts are being focused on research and development into autonomous driving technology to further improve traffic safety and convenience. In this regard, conventionally, technologies have been known that select one of multiple special measurement methods for measuring the curvature of the road ahead based on the accuracy of gradient information, or control vehicle steering based on the curvature of the driving lane at the vehicle's position identified by a road curvature identification unit and the vehicle's lateral position determined by a lateral position determination unit (see, for example, Patent Documents 1 and 2). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2017-116450 A [Patent Document 2] Patent No. 6415629 Summary of the Invention [Problem to be solved by the invention]

[0004] However, conventional autonomous driving technology does not take into account the fact that the appearance of lane markings changes depending on the slope of the road, and there is a problem in that, depending on the road conditions, the deviation between lane markings recognized by a camera or the like and lane markings obtained from map information may not be properly determined.

[0005] In order to solve the above-mentioned problems, one of the objects of the present application is to provide a determination device, a determination method, and a program that can more appropriately determine deviations from lane markings depending on the conditions of the travel route, thereby contributing to the development of sustainable transportation systems. [Means for solving the problem]

[0006] The determination device, the determination method, and the program according to the present invention employ the following configuration. (1): A determination device according to one embodiment of the present invention includes a first recognition unit that recognizes the surrounding conditions, including a first dividing line that divides a path along which a moving body moves, based on the output of a detection device that detects the surrounding conditions of the moving body; a second recognition unit that recognizes a second dividing line that divides the path along which the moving body moves from map information based on position information of the moving body; and a determination unit that determines whether the first dividing line and the second dividing line are separated, wherein the map information includes height information and curvature information of the path, and the determination unit suppresses a determination that the first dividing line and the second dividing line are separated when the height information and the curvature information satisfy predetermined conditions.

[0007] (2): In the above aspect (1), when the judgment unit determines that the specified condition is met, it predicts that the first dividing line recognized by the first recognition unit will deviate to one side or the other in the width direction of the travel path compared to when the specified condition is not met, and when the predicted direction of deviation matches the direction of the first dividing line, it suppresses the judgment that the first dividing line and the second dividing line are deviating.

[0008] (3) In the above aspect (2), the height information is height information of the center of the movement path.

[0009] (4) In the above aspect (2), the determination unit performs a determination using the predetermined conditions for each of the outer and inner lane lines of the travel path.

[0010] (5): In the above aspect (2), the judgment unit suppresses the judgment that the first marking line and the second marking line are diverging when the vertical gradient influence in the pitch direction of the moving body based on the height information and the lateral gradient influence in the roll direction of the moving body based on the curvature degree information satisfy the specified conditions.

[0011] (6): In the above aspect (5), the predetermined condition includes a case where the lateral gradient influence degree is greater than a first threshold value that is greater than zero.

[0012] (7): In the above aspect (5), the predetermined condition includes a case where the lateral gradient influence degree is less than a second threshold value that is smaller than zero.

[0013] (8) In the above aspect (5), the predetermined condition includes a case where a value obtained by adding the longitudinal gradient influence degree and the lateral gradient influence degree is greater than a third threshold value.

[0014] (9) In the above aspect (5), the predetermined condition includes a case where the combined value of the longitudinal gradient influence degree and the lateral gradient influence degree is less than a fourth threshold value.

[0015] (10): In the above aspect (5), the predetermined condition includes a case where the longitudinal gradient influence degree is greater than a fifth threshold value that is greater than zero.

[0016] (11): In the above aspect (5), the predetermined condition includes a case where the longitudinal gradient influence degree is less than a sixth threshold value that is smaller than zero.

[0017] (12): In the above aspect (5), the predetermined condition includes a case where the lateral gradient influence is equal to or less than a first threshold value, the longitudinal gradient influence is equal to or less than a fifth threshold value, and the combined value of the longitudinal gradient influence and the lateral gradient influence is greater than a third threshold value.

[0018] (13): In the above aspect (5), the predetermined condition includes a case where the lateral gradient influence is equal to or greater than the second threshold value and the longitudinal gradient influence is equal to or greater than the sixth threshold value, and the combined value of the longitudinal gradient influence and the lateral gradient influence is less than the fourth threshold value.

[0019] (14): In the above aspect (5), the specified condition is when the height information and the curvature degree information are greater than a specified value, and when the specified condition is met, the judgment unit predicts that there is a possibility that the first dividing line will deviate in both one and the other directions of the width of the travel path.

[0020] (15): In the above aspect (5), the specified condition is when the lateral gradient influence is greater than a first threshold value greater than 0 and the longitudinal gradient influence is less than a sixth threshold value less than 0, and when the specified condition is met, the judgment unit predicts that there is a possibility that the first dividing line will deviate in both one and the other directions of the travel path width direction.

[0021] (16): In the above aspect (5), the specified condition is when the lateral gradient influence is less than a second threshold value less than 0 and the longitudinal gradient influence is greater than a fifth threshold value greater than 0, and when the specified condition is met, the judgment unit predicts that there is a possibility that the first dividing line will deviate in both one and the other directions of the travel path width direction.

[0022] (17): Another aspect of the present invention is a determination method in which a computer recognizes the surrounding conditions, including a first dividing line that divides the path along which a moving body moves, based on the output of a detection device that detects the surrounding conditions of the moving body, recognizes a second dividing line that divides the path along which the moving body moves from map information based on the position information of the moving body, and determines whether the first dividing line and the second dividing line are separated, the map information including height information and curvature information of the path, and suppresses a determination that the first dividing line and the second dividing line are separated when the height information and the curvature information satisfy predetermined conditions.

[0023] (18): Another aspect of the present invention is a program that causes a computer to recognize the surrounding conditions, including a first dividing line that divides a path along which a moving body moves, based on the output of a detection device that detects the surrounding conditions of the moving body; recognize a second dividing line that divides the path along which the moving body moves from map information based on the position information of the moving body; and determine whether the first dividing line and the second dividing line are separated; the map information includes height information and curvature information of the path; and suppresses the determination that the first dividing line and the second dividing line are separated when the height information and the curvature information satisfy predetermined conditions. [Effects of the Invention]

[0024] According to the above aspects (1) to (18), it is possible to more appropriately determine the deviation of the lane markings in accordance with the conditions of the travel route. [Brief explanation of the drawings]

[0025] [Figure 1] 1 is a configuration diagram of a vehicle system 1 including a determination device according to an embodiment. [Figure 2] 2 is a functional configuration diagram of a first control unit 120 and a second control unit 160. FIG. [Figure 3] 1 is a diagram for explaining driving control of a vehicle M in a first scene. FIG. [Figure 4] FIG. 10 is a diagram for explaining traveling on a road with a slope in a second scene. [Figure 5] 10 is a diagram for explaining the influence of a lateral gradient near the host vehicle M on the appearance of the lane markings on the camera. FIG. [Figure 6] 10 is a diagram for explaining the influence of a lateral gradient at a position away from the vehicle M on the appearance of the camera lane marking CL. FIG. [Figure 7] 10 is a diagram for explaining the influence of the longitudinal gradient of the host vehicle M on the appearance of the lane markings on the camera. FIG. [Figure 8]10A and 10B are diagrams for explaining predetermined conditions for a longitudinal gradient influence degree and a lateral gradient influence degree in the embodiment. [Figure 9] 10A and 10B are diagrams for explaining a process of determining whether or not a camera lane marking CL is affected by a gradient. [Figure 10] 10 is a diagram for explaining the shapes of the camera division lines CL and the map division lines ML as seen from the host vehicle M traveling on a curved road. FIG. [Figure 11] 10 is a diagram showing an example of lane marking selection by a selection unit 144. FIG. [Figure 12] 4 is a flowchart illustrating an example of a flow of an operation control process in the embodiment. [Figure 13] 10 is a flowchart illustrating an example of a deviation determination process. [Figure 14] 10 is a flowchart illustrating an example of a selection process. DETAILED DESCRIPTION OF THE INVENTION

[0026] Hereinafter, with reference to the drawings, embodiments of a determination device, a determination method, and a program according to the present invention will be described. Hereinafter, a vehicle will be used as an example of a moving body, and an embodiment in which a determination device is applied to an autonomous vehicle will be described. Autonomous driving refers to automatically controlling one or both of the steering and speed of a vehicle to perform driving control. Driving control may include various driving controls, such as Automated Lane Change (ALC), Lane Keeping Assistance System (LKAS), Adaptive Cruise Control System (ACC), Traffic Jam Pilot (TJP), and Collision Mitigation Brake System (CMBS). Furthermore, an autonomous vehicle may be manually controlled by a vehicle user (e.g., a passenger) (so-called manual driving). In addition to vehicles, the moving body may include, for example, a ship capable of moving on land such as a hovercraft, an aircraft capable of traveling on roads, a stand-up vehicle with a power unit, and the like.

[0027] [Overall configuration] 1 is a configuration diagram of a vehicle system 1 including a determination device according to an embodiment. The vehicle (hereinafter referred to as host vehicle M) on which the vehicle system 1 is mounted is, for example, a two-wheeled, three-wheeled, or four-wheeled vehicle or micromobility, and its drive source is 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 battery (storage battery) such as a secondary battery or a fuel cell.

[0028] The vehicle system 1 includes, for example, a camera 10, a radar device 12, a light detection and ranging (LIDAR) device 14, an object recognition device 16, a communication device 20, a human machine interface (HMI) device 30, vehicle sensors 40, a navigation device 50, a map positioning unit (MPU) device 60, a driving operation control device 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 controller area network (CAN) 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. The combination of the camera 10, the radar device 12, the LIDAR device 14, and the object recognition device 16 is an example of a "detection device DD." The HMI device 30 is an example of an "output device." The automatic driving control device 100 is an example of a "mobile object control device."

[0029] The camera 10 is a digital camera that uses 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 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, the front of the vehicle body, etc. When capturing an image of the rear, the camera 10 is attached to the top of the rear windshield, the back door, etc. When capturing an image of the side, the camera 10 is attached to a door mirror, etc. The camera 10 periodically and repeatedly captures images of the surroundings of the host vehicle M, for example. The camera 10 may be a stereo camera.

[0030] The radar device 12 emits radio waves such as millimeter waves around the vehicle M and detects radio waves reflected by surrounding objects (reflected waves) to detect at least the position (distance and direction) of the objects. The radar device 12 is attached to any location on the vehicle M. The radar device 12 may detect the position and speed of the objects using an FM-CW (Frequency Modulated Continuous Wave) method.

[0031] The LIDAR 14 irradiates light around the vehicle M and measures the scattered light. The LIDAR 14 detects the distance to the target based on the time between emitting and receiving the light. The irradiated light is, for example, a pulsed laser beam. The LIDAR 14 is attached to any location on the vehicle M.

[0032] The object recognition device 16 performs sensor fusion processing on the detection results from some or all of the camera 10, radar device 12, and 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. Alternatively, the object recognition device 16 may output the detection results from the camera 10, radar device 12, and LIDAR 14 directly to the automatic driving control device 100. In that case, the object recognition device 16 may be omitted from the configuration of the vehicle system 1 (detection device DD).

[0033] The communication device 20 communicates with, for example, other vehicles in the vicinity of the vehicle M, terminal devices of users using the vehicle M, or various server devices, using networks such as a cellular network, a Wi-Fi network, Bluetooth (registered trademark), DSRC (Dedicated Short Range Communication), LAN (Local Area Network), WAN (Wide Area Network), or the Internet.

[0034] The HMI 30 outputs various information to the occupants of the vehicle M and accepts input operations by the occupants. The HMI 30 includes, for example, various display devices, speakers, buzzers, touch panels, switches, keys, microphones, and the like.

[0035] 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 the yaw rate (for example, the rotational angular velocity around a vertical axis passing through the center of gravity of the host vehicle M), and a direction sensor that detects the orientation of the host vehicle M. The vehicle sensor 40 may also be provided with a position sensor that detects the position of the host vehicle M. The position sensor is an example of a "position measurement unit." The position sensor is, for example, a sensor that acquires position information (longitude and latitude information) from a GPS (Global Positioning System) device. The position sensor may also be a sensor that acquires position information using a GNSS (Global Navigation Satellite System) receiver 51 of the navigation device 50. The vehicle sensor 40 may derive the speed of the host vehicle M from the difference (i.e., distance) of the position information at a predetermined time in the position sensor. The results detected by the vehicle sensor 40 are output to the automatic driving control device 100.

[0036] The navigation device 50 includes, for example, a GNSS 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 a 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 sensor 40. The navigation HMI 52 includes a display device, a speaker, a touch panel, keys, etc. The GNSS receiver 51 may be provided in the vehicle sensor 40. 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 route on a map) from the position of the vehicle M identified by the GNSS receiver 51 (or an arbitrary 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 that indicate roads (an example of a travel route) and nodes connected by the links. The first map information 54 may also include POI (Point Of Interest) information and the like. 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 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. The navigation device 50 outputs the determined route on the map to the MPU 60.

[0037] The MPU 60 includes, for example, a recommended lane determination unit 61, and stores second map information 62 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 it into 100 m intervals 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.

[0038] 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, the number of lanes (number of travel routes), the type and shape of road dividing lines (hereinafter referred to as dividing lines), information on the center of lanes, and road boundary information. The second map information 62 may also include information on whether the road boundary is a boundary (physical boundary) that includes a structure that prevents a vehicle from passing (including crossing or coming into contact with). Examples of physical boundaries include guardrails, curbs, medians, fences, etc. The term "impassable" may also include the presence of a low level step that allows passage if unusual vehicle vibrations are tolerated. The second map information 62 may also include road shape information, traffic regulation information, address information (address and postal code), facility information, parking information, telephone number information, etc. Road shape information includes, for example, road width, height information, degree of curvature, etc. Here, the height information may be, for example, height information from a reference position (e.g., horizontal position) at the center of the road (travel path), road elevation, or height difference information for each predetermined distance. The curvature degree is, for example, an index value indicating the magnitude of the road curvature (which may also be expressed as the radius of curvature; the same applies below), and the greater the curvature, the greater the curvature. The curvature degree may also be a curvature value or a curvature change amount. In the following description, it is assumed that the second map information 62 does not store the longitudinal gradient (longitudinal gradient) or the lateral gradient (lateral gradient) of the road (travel path). The second map information 62 may be updated as needed by the communication device 20 communicating with an external device. The first map information 54 and the second map information 62 may be provided as an integrated piece of map information. The map information may also be stored in the storage unit 190.

[0039] The driving operators 80 include, for example, a steering wheel, an accelerator pedal, and a brake pedal. The driving operators 80 may also include a shift lever, a variable steering wheel, a joystick, or other operators. Each operator of the driving operators 80 is equipped with an operation detection unit that detects, for example, the amount of operation of the operator by the occupant or whether or not the operator is operated. The operation detection unit detects, for example, the steering angle and steering torque of the steering wheel, the amount of depression of the accelerator pedal and the brake pedal, etc. The operation detection unit then outputs the detection results to the automatic driving control device 100 or one or both of the driving force output device 200, the brake device 210, and the steering device 220.

[0040] The automatic driving control device 100 executes various types of driving control associated with automatic driving for the host vehicle M. The automatic driving control device 100 includes, for example, a first control unit 120, a second control unit 160, an HMI control unit 180, and a storage unit 190. The first control unit 120, the second control unit 160, and the HMI control unit 180 are each realized by a hardware processor such as a CPU (Central Processing Unit) executing a program (software). Furthermore, 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 above-mentioned program may be stored in advance in a storage device (a storage device with a non-transitory storage medium) such as an HDD or flash memory of the automatic driving control device 100, or may be stored in a removable storage medium such as a DVD, CD-ROM, or memory card, and installed in the storage device of the automatic driving control device 100 by inserting the storage medium (non-transitory storage medium) into a drive device, card slot, etc.

[0041] The storage unit 190 may be realized by the various storage devices described above, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a ROM (Read Only Memory), or a RAM (Random Access Memory). The storage unit 190 stores, for example, various types of information, programs, and the like in the embodiments. The storage unit 190 may also store map information (for example, the first map information 54 and the second map information 62).

[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 and an action plan generation unit 140. 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 concurrently executing intersection recognition using deep learning or the like and recognition based on predefined conditions (such as the presence of traffic lights and road markings that can be pattern matched), and then scoring and comprehensively evaluating both. This ensures the reliability of autonomous driving. The first control unit 120 also executes control related to autonomous driving of the host vehicle M based on instructions from, for example, the MPU 60, the HMI control unit 180, or the like.

[0043] The recognition unit 130 recognizes the surrounding situation of the host vehicle M based on the recognition results of the detection device DD (information input from at least the camera 10 out of the camera 10, the radar device 12, and the LIDAR 14 via the object recognition device 16). For example, the recognition unit 130 recognizes the status of objects present around the host vehicle M (within a predetermined distance), such as their position, speed, and acceleration. Objects include traffic participants such as other vehicles, pedestrians, and bicycles, as well as physical boundaries that define roads (travel paths). The position of an object is recognized as a position on an absolute coordinate system with a representative point of the host 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 by a represented area. For example, if the object is a moving object such as another vehicle, the "state" of the object may include the acceleration or jerk of the moving object, or the "behavioral state" (for example, whether the other vehicle is changing lanes or about to change lanes).

[0044] The recognition unit 130 also recognizes, for example, stop lines, obstacles, red lights, toll booths, other road phenomena, markings (speed limits) posted on the road, and road signs indicating speed limits. The recognition unit 130 also includes, for example, a first recognition unit 132 and a second recognition unit 134. Details of these functions will be described later.

[0045] The behavior plan generation unit 140 generates a behavior plan for driving the host vehicle M by autonomous driving based on the recognition results of the recognition unit 130, etc. For example, the behavior plan generation unit 140 generates a target trajectory for the host vehicle M to travel automatically (without driver operation) in the future, so that the host vehicle M can respond to the surrounding conditions of the host vehicle M, while essentially traveling in the recommended lane determined by the recommended lane determination unit 61, based on the recognition results by the recognition unit 130 and the surrounding road shapes based on the current position of the host vehicle M acquired from map information, etc. The target trajectory includes, for example, a speed element. For example, the target trajectory is expressed as a sequential arrangement of points (trajectory points) to be reached by the host vehicle M. The trajectory points are points to be reached by the host vehicle M at predetermined travel distances (e.g., on the order of several meters) along the road, and separately, target speeds and target accelerations for predetermined sampling times (e.g., on the order of a few tenths of a second) are generated as part of the target trajectory. Alternatively, the trajectory points may be positions to be reached by the host vehicle M at the sampling times for each predetermined sampling time. In this case, the target speed and target acceleration information are expressed as the interval between trajectory points.

[0046] The action plan generation unit 140 may set an autonomous driving event when generating the target trajectory. Examples of the event include a constant speed driving event in which the host vehicle M drives in the same lane at a constant speed, a following driving event in which the host vehicle M follows another vehicle that is within a predetermined distance (for example, within 100 m) ahead of the host vehicle M and is closest to the host vehicle M, a lane change event in which the host vehicle M changes lanes from the host vehicle's own lane to an adjacent lane, a branching event in which the host vehicle M branches off into a lane on the destination side at a road branching point, a merging event in which the host vehicle M merges into a main lane at a merging point, a takeover event in which the autonomous driving is terminated and the host vehicle M switches to manual driving, and so on. Examples of the event may also include an overtaking event in which the host vehicle M temporarily changes lanes to an adjacent lane, overtakes a leading vehicle in the adjacent lane, and then changes lanes back to the original lane, and an avoidance event in which the host vehicle M performs at least one of braking and steering to avoid an obstacle ahead of the host vehicle M.

[0047] Furthermore, the behavior plan generation unit 140 may change an event already determined for the current section to another event or set a new event for the current section, depending on the surrounding conditions of the host vehicle M recognized while the host vehicle M is traveling. Furthermore, the behavior plan generation unit 140 may change an event already set for the current section to another event or set a new event for the current section, depending on the operation of the occupant on the HMI 30. The behavior plan generation unit 140 generates a target trajectory according to the set event.

[0048] The behavior plan generation unit 140 also includes, for example, a determination unit 142, a selection unit 144, and a travel control unit 146. The first recognition unit 132, the second recognition unit 134, and the determination unit 142 are an example of a "determination device." The travel control unit 146 and the second control unit 160 are an example of a "mobility control unit." Details of these functions will be described later.

[0049] 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.

[0050] The second control unit 160 includes, for example, a target trajectory acquisition unit 162, a speed control unit 164, and a steering control unit 166. The target trajectory 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.

[0051] Returning to FIG. 1 , the HMI control unit 180 notifies the occupant of predetermined information via the HMI 30. The predetermined information includes, for example, information related to the traveling of the vehicle M, such as information related to the state of the vehicle M and information related to driving control. The information related to the state of the vehicle M includes, for example, the speed of the vehicle M, engine speed, and shift position. The information related to driving control includes, for example, information inquiring whether or not driving control is being performed by autonomous driving, information regarding the driving control status by autonomous driving, information regarding the automation level, and information prompting the occupant to drive when switching from autonomous driving to manual driving. The predetermined information may also include information related to the surrounding conditions recognized by the detection device DD. The predetermined information may also include information unrelated to the traveling of the vehicle M, such as television programs, content (e.g., movies) stored on a storage medium such as a DVD, and the like. The predetermined information may also include, for example, information regarding the current location and destination during autonomous driving, and the remaining fuel level of the vehicle M. The HMI control unit 180 may output the information received by the HMI 30 to the communication device 20, the navigation device 50, the first control unit 120, and the like.

[0052] The HMI control unit 180 may also cause the HMI 30 to output inquiry information for the occupant, processing results by the first control unit 120 and the second control unit 160, etc. The HMI control unit 180 may also transmit various pieces of information to be output by the HMI 30 to a terminal device used by the occupant of the vehicle M via the communication device 20.

[0053] Traveling drive force output device 200 outputs a traveling drive force (torque) to the drive wheels for the vehicle to travel. Traveling drive 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 second control unit 160 or information input from the accelerator pedal of driving operator 80.

[0054] The braking 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 according to information input from the second control unit 160 or information input from the brake pedal of the driving operation device 80, so that a braking torque corresponding to the braking operation is output to each wheel. The braking device 210 may include a backup mechanism that transmits hydraulic pressure generated by operation of the brake pedal to the cylinder via a master cylinder. Note that the braking device 210 is not limited to the configuration described above, and may also be an electronically controlled hydraulic braking device that controls an actuator according to information input from the second control unit 160 to transmit hydraulic pressure from the master cylinder to the cylinder.

[0055] The steering device 220 includes, for example, a steering ECU and an electric motor. The electric motor changes the direction of the steered wheels by, for example, applying a force to a rack and pinion mechanism. The steering ECU drives the electric motor to change the direction of the steered wheels in accordance with information input from the second control unit 160 or information input from the steering wheel of the driving operator 80.

[0056] [Recognition and Action Plan Generation] Next, the details of the functions of the recognition unit 130 (mainly the first recognition unit 132 and the second recognition unit 134) and the behavior plan generation unit 140 (mainly the determination unit 142, the selection unit 144, and the driving control unit 146) will be described. Note that, below, the contents of the driving control of the host vehicle M (movement control of a moving body) using the functions of the recognition unit 130 and the behavior plan generation unit 140 will be described in several scenes.

[0057] [Scene 1] FIG. 3 is a diagram for explaining driving control of the host vehicle M in a first scenario. The first scenario illustrates driving control of the host vehicle M in a road condition in which there is neither a longitudinal gradient (a gradient in the longitudinal direction of the road (travel path) (the traveling direction of the host vehicle M)) nor a lateral gradient (a gradient in the lateral direction of the road). The example of FIG. 3 shows lane markings CL1 to CL3 recognized by the detection device DD and lane markings ML1 to ML3 obtained from map information (e.g., second map information 62) based on the position information of the host vehicle M. In the map information, lane L1 is defined by lane markings ML1 and ML2, and lane L2 is defined by lane markings ML2 and ML3. Lanes L1 and L2 are lanes on which a vehicle can travel in the same direction (the X-axis direction in the figure). In the example of FIG. 3, lane markings CL1 to CL3 are an example of a "first lane marking," and lane markings ML1 to ML3 are an example of a "second lane marking." In the following, the lane markings CL1 to CL3 may be referred to as "camera lane markings CL1 to CL3," and the lane markings ML1 to ML3 may be referred to as "map lane markings ML1 to ML3." When the camera lane markings CL1 to CL3 are not distinguished from one another, they may simply be referred to as "camera lane markings CL," and when the map lane markings ML1 to ML3 are not distinguished from one another, they may simply be referred to as "map lane markings ML." In the first scene shown in FIG. 3, the host vehicle M is assumed to be traveling (moving) on ​​the lane L1 at a speed VM along the extension direction of the lane L1 (longitudinal direction, on the X-axis in the drawing).

[0058] In a first scene, the first recognition unit 132 recognizes the surrounding conditions of the host vehicle M based on the output of the detection device DD that detects the surrounding conditions (external world) of the host vehicle M. For example, the first recognition unit 132 recognizes left and right camera marking lines CL1 and CL2 that demarcate the driving lane (lane L1) of the host vehicle M based on an image captured by the camera 10 (hereinafter referred to as a camera image). The first recognition unit 132 may also recognize a camera marking line CL3 that demarcates an adjacent lane (lane L2) adjacent to the driving lane.

[0059] For example, the first recognition unit 132 analyzes the camera image, extracts edge points in the image that have a large difference in brightness from adjacent pixels, and recognizes the camera lane marking lines CL1 to CL3 on the image plane by connecting the edge points. Furthermore, the first recognition unit 132 converts the positions of the camera lane marking lines CL1 to CL3 into a vehicle coordinate system (for example, the XY plane coordinates in FIG. 3) based on the position of the representative point of the host vehicle M.

[0060] The first recognition unit 132 may also recognize the curvature (an example of the degree of curvature) of the camera lane markings CL1 to CL3, for example. The camera lane markings CL1 to CL3 may be recognized or corrected based on the output of a detection device other than the camera 10 (for example, the radar device 12 or the LIDAR 14). The first recognition unit 132 may also recognize the curvature change (an example of the degree of curvature) of the camera lane markings CL1 to CL3. The curvature change is, for example, the time rate of change in the curvature of the camera lane markings CL1 to CL3 recognized by the camera 10 at a distance x [m] forward as viewed from the host vehicle M. The first recognition unit 132 may also recognize the curvature or the curvature change of the lane markings CL1 to CL3 by averaging the curvatures or the curvature change of each of the camera lane markings CL1 to CL3. The camera lane markings CL1 to CL3 may be recognized or corrected based on the output of a detection device other than the camera 10 (for example, the radar device 12 or the LIDAR 14).

[0061] The first recognition unit 132 may also recognize the degree of parallelism of the camera lane markings CL1 to CL3. The degree of parallelism is an index value where a larger value indicates a closer degree of parallelism. For example, the first recognition unit 132 acquires the distance between the camera lane markings CL1 and CL2 as seen from the host vehicle M at predetermined intervals and recognizes the degree of parallelism according to the amount of change in the distance. In this case, the smaller the amount of change in the distance (the closer to 0, the less change there is), the larger the value of the degree of parallelism. The first recognition unit 132 may recognize the degree of parallelism between the camera lane markings CL1 and CL3, or the degree of parallelism between the camera lane markings CL2 and CL3. In the first scene, the first recognition unit 132 may also recognize, for example, objects (physical boundaries, other vehicles, etc.) present around the host vehicle M.

[0062] The second recognition unit 134 recognizes lane markings around the host vehicle M from map information based on the position of the host vehicle M detected by, for example, the vehicle sensor 40 or the GNSS receiver 51. For example, the second recognition unit 134 refers to map information based on the position information of the host vehicle M, and recognizes map marking lines ML1 to ML3 that exist in the traveling direction of the host vehicle M or in directions in which the host vehicle M can travel.

[0063] Furthermore, of the recognized map division lines ML1 to ML3, the second recognition unit 134 may recognize map division lines ML1 and ML2 as division lines that divide lane L1, which is the lane in which the host vehicle M is traveling, and may recognize map division lines ML2 and ML3 as division lines that divide lane L2, which is the lane adjacent to lane L1. Furthermore, the second recognition unit 134 recognizes the curvature or curvature change amount (an example of the degree of curvature) of each of the map division lines ML1 to ML3 from the second map information 62. Furthermore, the second recognition unit 134 may average the curvature or curvature change amount of each of the map division lines ML1 to ML3 to recognize the curvature or curvature change amount of the lanes divided by the map division lines.

[0064] The determination unit 142 determines whether the camera lane lines CL1-CL3 recognized by the first recognition unit 132 deviate from the map lane lines ML1-ML3 recognized by the second recognition unit 134. For example, the determination unit 142 derives the degree of deviation between the lane lines CL1 and ML1 located closest to the left of the host vehicle M, the degree of deviation between the lane lines CL2 and ML2 located closest to the right of the host vehicle M, and the degree of deviation between the lane lines CL3 and ML3 on the adjacent lane side. If the derived degree of deviation is equal to or greater than a threshold, the determination unit 142 determines that the camera lane lines CL and the map lane lines ML deviate, and if the degree of deviation is less than the threshold, the determination unit 142 determines that there is no deviation. The determination of whether there is a deviation may be performed repeatedly at a predetermined timing or periodically.

[0065] For example, the determination unit 142 superimposes the camera lane lines CL1, CL2, and CL3 and the map lane lines ML1, ML2, and ML3 on the plane of the vehicle coordinate system (XY plane) based on the position of the representative point of the host vehicle M. When determining the lane lines to be compared (lane lines CL1 and ML1, lane lines CL2 and ML2, and lane lines CL3 and ML3), the determination unit 142 determines that the lane lines are deviating if the deviation degree of at least one lane line is equal to or greater than a threshold, and determines that the lane lines are not deviating if all lane lines are less than the threshold. The deviation degree is, for example, the degree of deviation (deviation distance, travel lane width direction deviation) in the road width direction (travel lane width direction, lateral direction, Y-axis direction in the figure). In the example of Figure 3, the deviation determination may be performed using the average value of the lateral position deviation D1 between the marking lines CL1 and ML1, the lateral position deviation D2 between the marking lines CL2 and ML2, and the lateral position deviation D3 between the marking lines CL3 and ML3, or the deviation determination may be performed using the maximum or minimum value of the deviations D1, D2, and D3.

[0066] Furthermore, the degree of deviation may be, for example, the degree of the angle (deviation angle) formed by the two compared marking lines instead of (or in addition to) the above-mentioned lateral position deviation amount. In the example of Fig. 3, the average value of the angle θ1 formed by marking lines CL1 and ML1, the angle θ2 formed by marking lines CL2 and ML2, and the angle θ3 formed by marking lines CL3 and ML3 may be used, or the maximum or minimum value of the angles θ1, θ2, and θ3 may be used.

[0067] Furthermore, the degree of deviation may be the degree (magnitude) of difference in curvature change of the lane markings, instead of (or in addition to) the lateral position deviation or the angle formed by the lane markings. The curvature change is mainly used when the lane is a curved road. For example, the determination unit 142 may use the average value of the difference in curvature change between lane markings CL1 and ML1, the difference in curvature change between lane markings CL2 and ML2, and the difference in curvature change between lane markings CL3 and ML3, or may use the maximum or minimum of these differences. The determination unit 142 may also use the difference between the average value of the curvature change of lane markings CL1 to CL3 and the average value of the curvature change of lane markings ML1 to ML3. The determination unit 142 may also use the difference between the curvature change of the lane markings (lanes L1 and L2) recognized from the camera image and the curvature change of the lane markings recognized from map information.

[0068] The determination unit 142 may also adjust the threshold value to suppress determination that the camera lane markings CL and the map lane markings ML are separated. For example, if it is determined that the lane markings are separated when the degree of separation is equal to or greater than a threshold value, the threshold value can be increased to make it less likely that the lane markings are separated. The threshold value may be adjusted within a preset range, or an adjustment value may be set depending on the surrounding conditions, the driving control being performed, the automation level, etc.

[0069] Based on the determination result by the determination unit 142, the selection unit 144 selects a lane marking that serves as a reference when generating a target trajectory, etc., of the host vehicle M. For example, if the determination unit 142 determines that the camera lane marking CL and the map lane marking ML do not deviate from each other, the selection unit 144 selects at least one of the camera lane marking CL and the map lane marking ML. In this case, the selection unit 144 may select a predetermined lane marking (e.g., the camera lane marking CL), or may select the map lane marking ML when the recognition accuracy of the camera 10 is below a threshold, or may select the camera lane marking CL when the map information is old (e.g., the map update date is earlier than a predetermined date and time). The selection unit 144 may also interpolate or adjust the position of one of the camera lane marking CL and the map lane marking ML with the position of the other. The selection unit 144 may also preferentially select one of the camera lane marking CL and the map lane marking ML depending on the surrounding circumstances and the recognition situation. For example, when there is heavy rain or at night around the vehicle M, the camera lane lines CL are difficult to recognize, so the selection unit 144 selects the map lane lines ML. Furthermore, when it is determined that the camera lane lines CL and the map lane lines ML are separated, the selection unit 144 selects either the camera lane lines CL or the map lane lines ML. In this case, the selection unit 144 may select one of the predetermined lines (for example, the camera lane lines CL), or may select one of the lines depending on the surrounding conditions (including road conditions).

[0070] The driving control unit 146 determines driving control (driving control, movement control) for the vehicle M based on the recognition results of the first recognition unit 132 and the second recognition unit 134, the determination result of the determination unit 142, the lane markings selected by the selection unit 144, and the like, and generates a target trajectory based on the determined driving control. "Determining driving control" may include, for example, determining the content (type) of driving control, or determining whether to execute (suppress) driving control. Furthermore, "executing driving control" may include, for example, continuing driving control that is already being executed, in addition to switching and executing the content of driving control. "Suppressing driving control" may include not only not executing driving control, but also lowering the automation level of driving control.

[0071] Here, the driving control executed by the driving control unit 146 includes at least a first driving control and a second driving control. The first driving control is, for example, driving control that executes one or both of steering control and speed control of the host vehicle M based on at least one of the camera lane markings CL and the map lane markings ML. For example, in the case of LKAS control, the first driving control causes the host vehicle M to travel so that a representative point of the host vehicle M passes through the center of a lane marked by lane markings. In addition, in the case of ALC control, the first driving control generates a driving trajectory for the host vehicle M to change lanes from the driving lane (e.g., lane L1) to a lane (e.g., lane L2) of a destination lane change (course change destination), and causes the host vehicle M to travel on a trajectory that follows the generated driving trajectory. In the first driving control, for example, if the camera recognition accuracy is below a threshold, driving control may be performed with priority given to the map lane lines ML, and if the map information is old (for example, the map update date is earlier than a predetermined date and time), driving control may be performed with priority given to the camera lane lines CL. Also, based on the determination result by the determination unit 142, driving control may be performed based on the camera lane lines CL or the map lane lines ML.

[0072] The second driving control is, for example, driving control that executes one or both of steering control and speed control of the host vehicle M based on an object (for example, a physical boundary, another vehicle) recognized by the first recognition unit 132. The second driving control, for example, identifies the position of a lane based on the physical boundary or the position of another vehicle, and drives the host vehicle M so that a representative point of the host vehicle M runs in the center of the identified lane. In addition, the second driving control drives the host vehicle M so that a representative point of the host vehicle M runs on a trajectory that follows the driving trajectory of the other vehicle.

[0073] Furthermore, the driving control may include a plurality of driving control functions with different automation levels (an example of the degree of automation). The automation levels may include, for example, a first level, a second level with a lower degree of automation of driving control than the first level, and a third level with a lower degree of automation of driving control than the second level. The automation levels may also include a fourth level with a lower degree of automation of driving control than the third level. Here, the automation level may be a level determined by standardized information, laws and regulations, or an index value set independently. Therefore, the types, contents, and number of automation levels are not limited to the following examples. A low degree of automation of driving control means, for example, a low automation rate in driving control and a large (heavy) task assigned to the driver. A low degree of automation of driving control means a low degree of control of the steering or acceleration / deceleration of the host vehicle M by the automatic driving control device 100 (a high degree of need for the driver to intervene in steering or acceleration / deceleration operations). Tasks assigned to the driver include, for example, monitoring the surroundings of the host vehicle M and operating driving controls. The operation of the driving controls includes, for example, the driver gripping the steering wheel (hereinafter referred to as a hands-on state). The tasks assigned to the driver are, for example, tasks for the occupant (driver tasks) necessary to maintain the autonomous driving of the host vehicle M. Therefore, if the occupant is unable to perform the assigned tasks, the automation level will be reduced. For example, the first level of driving control may include driving controls such as ALC, LKAS, ACC, TJP, and CMBS. Furthermore, the second or third level of driving control may include driving controls such as ALC, LKAS, ACC, and CMBS. The fourth level of driving control may include manual driving. Furthermore, the fourth level of driving control may include driving controls such as ACC and CMBS. Of the first to fourth levels, the first level has the highest degree of automation of driving control, and the fourth level has the lowest degree of automation of driving control.

[0074] Furthermore, at the first level, no tasks are assigned to the occupant (the tasks assigned to the driver are the lightest), and therefore, for example, driving control is permitted when the driver of the host vehicle M is not gripping the steering wheel (hereinafter referred to as a hands-off state). At the second level, a task assigned to the driver is, for example, monitoring the surroundings (particularly the front) of the host vehicle M. At the third level, a task assigned to the driver is, for example, monitoring the surroundings of the host vehicle M and being in a hands-on state. At the fourth level, a task assigned to the driver is, for example, monitoring the surroundings of the host vehicle M and being in a hands-on state, as well as operating the driving operator 80 to control the steering and speed of the host vehicle M. In other words, at the fourth level, the occupant can immediately take over driving, and the tasks assigned to the driver are the most severe. The content of driving control and the tasks assigned to the occupant at each automation level are not limited to the examples described above. The automatic driving control device 100 executes driving control at one of first to fourth levels based on the surrounding conditions of the vehicle M and the task being performed by the occupant.

[0075] For example, the driving control unit 146 executes the first driving control when the recognition unit 130 (first recognition unit 132, second recognition unit 134) recognizes the camera lane lines CL and the map lane lines ML, and executes the second driving control when at least one of the camera lane lines CL and the map lane lines ML is not recognized or when a physical boundary or another vehicle is present around the vehicle M. Furthermore, the driving control unit 146 may, for example, execute control to switch from the first driving control to the second driving control when a predetermined condition is satisfied, or may execute control to terminate the driving control of the vehicle M and switch to manual driving by the occupant. Furthermore, the driving control unit 146 may switch the automation level depending on the surrounding conditions and the type of driving control.

[0076] [Second Scene] Next, a diagram for explaining driving control of the host vehicle M in a second scene is shown. The second scene shows a scene in which the host vehicle M is traveling on a road with a longitudinal gradient and a lateral gradient. Here, the influence of the longitudinal gradient and the lateral gradient on the height of the lane markings will be explained. FIG. 4 is a diagram for explaining traveling on a road with a gradient in the second scene. The road shown in FIG. 4 is a left-hand curve road with lanes L1 and L2 having a lateral gradient of an angle θ [rad]. When the host vehicle M is traveling on the road shown in FIG. 4, the appearance of the camera lane markings CL (the position of the camera lane markings CL recognized from the camera image) may change due to the influence of the gradient.

[0077] FIG. 5 is a diagram illustrating the influence of a lateral gradient near the host vehicle M on the appearance of camera lane markings. The example in FIG. 5 illustrates the scene shown in FIG. 4 as viewed from the YZ plane. The example in FIG. 5 also illustrates the appearance (positions recognized by the first recognition unit 132) of camera lane markings CL1 to CL3 near the host vehicle M (within a first predetermined distance from the host vehicle M). In FIG. 5, the inclination of the road surface when the host vehicle M is on the lane L1 is corrected (rotated right) so that it becomes horizontal. Because the area near the host vehicle is hardly affected by the gradient, the camera lane markings CL appear in approximately the same position as the lane markings (or map lane markings ML) actually drawn on the road. Hereinafter, road surface height information (amount of deviation from a reference position) caused by the influence of a lateral gradient near the host vehicle M will be referred to as dlat0. The road surface height dlat0 may be calculated for the camera lane markings CL3 on the outside of the turn and the camera lane markings CL1 on the inside of the turn, or it may be the average of the heights of the camera lane markings CL1 and CL3.

[0078] FIG. 6 is a diagram illustrating the effect of a lateral gradient on the appearance of a camera lane marking CL at a position farther from the host vehicle M (a position farther than a first predetermined distance from the host vehicle M). As shown in the example of FIG. 6, at a position farther from the host vehicle M (a position farther than a first predetermined distance from the host vehicle M), the camera lane marking CL1 on the left side as viewed from the host vehicle M (a lane marking located lower than the host vehicle M) is predicted to appear to tilt toward the inside of a turning (left curve) road due to shape recognition errors and the like, depending on the lateral gradient of the road (lanes L1 and L2). Conversely, the camera lane marking CL3 on the right side as viewed from the host vehicle M (a lane marking located higher than the host vehicle M) is predicted to appear to tilt toward the outside of a turning road as the distance from the host vehicle M increases. Furthermore, the amount of tilt is predicted to increase as the lateral gradient increases, and also increases as the distance from the host vehicle M increases. Hereinafter, the height (deviation) of the road surface caused by the effect of the lateral gradient at a second predetermined distance far from the host vehicle M is referred to as dlat. The value obtained by adding the height dlat0 and the height dlat is an example of the "lateral gradient influence degree." The road surface height dlat may be calculated for the camera lane marking line CL3 on the outside of the turn and the camera lane marking line CL1 on the inside of the turn, or may be calculated as the average of the heights of the camera lane marking lines CL1 and CL3.

[0079] FIG. 7 is a diagram illustrating the effect of the longitudinal gradient of the host vehicle M on the appearance of lane markings from the camera. The example in FIG. 7 illustrates a case where the height of the road center increases in the direction of travel of the host vehicle M (the longitudinal direction of the road) (i.e., in the case of an uphill slope; hereinafter, this may be referred to as "height +"). When the height in the direction of travel increases, as shown in FIG. 7, it is predicted that all of the lane markings CL1 to CL3 will appear to be tilted toward the outside of the turn (to the right of the dotted line in the figure) due to shape recognition errors or the like at a position that is a third predetermined distance or more away from the host vehicle M. Conversely, when the height of the road center decreases in the direction of travel of the host vehicle M (i.e., in the case of a downhill slope; hereinafter, this may be referred to as "height -"), it is predicted that all of the lane markings CL1 to CL3 will appear to be tilted toward the inside of the turn (to the left of the dotted line in the figure) due to shape recognition errors or the like. Furthermore, it is predicted that the amount of tilt increases as the longitudinal gradient increases and as the distance from the host vehicle M increases. Hereinafter, the road surface height (deviation amount) caused by the influence of the longitudinal gradient at the third predetermined distance will be referred to as dlon. The height dlon is an example of the “longitudinal gradient influence degree.” The road surface height dlon may be calculated for the camera lane marking CL3 on the outside of the turn and the camera lane marking CL1 on the inside of the turn, or may be calculated as the average height of the camera lane markings CL1 to CL3.

[0080] Therefore, in the second scenario, if the road on which the vehicle is traveling has a vertical gradient or a horizontal gradient, the judgment unit 142 predicts the direction (deviation direction) in which the camera lane marking CL deviates from the actual lane marking (or map lane marking ML) due to shape recognition errors, etc., based on the vertical gradient influence (dlon) and the horizontal gradient influence (dlat0+dlat), and judges the deviation between the camera lane marking CL and the map lane marking ML, including information (results) on the predicted deviation direction.

[0081] In the embodiment, if the map information includes elevation information for the center of the road but does not include longitudinal gradient information, the elevation information for the center of the road is used instead of the longitudinal gradient. In this case, since the elevation information is set for each predetermined distance, the determining unit 142 calculates the longitudinal gradient by dividing the difference in elevation at the predetermined distance by the predetermined distance, and derives the longitudinal gradient influence degree (dlon) from the calculated longitudinal gradient.

[0082] Furthermore, if the map information does not include lateral gradient information, the lateral gradient is predicted from the curvature based on the fact that there is a predetermined correlation between the curvature degree information (e.g., curvature) and the road surface gradient. In this case, the determination unit 142 predicts the lateral gradient based on the curvature value using the correlation, because the lateral gradient increases proportionally as the curvature increases within a predetermined range, and derives the lateral gradient influence degree (dlat0+dlat) from the predicted lateral gradient. Note that if the curvature is equal to or greater than a predetermined value, the lateral gradient is kept constant at an upper limit value.

[0083] [Deviation determination based on prediction of deviation direction of lane marking CL by camera] Next, the deviation determination process of the determination unit 142 based on the prediction of the deviation direction of the camera lane marking CL in the second scene will be specifically described. In the second scene, when the map information includes road height information and curvature degree information, the determination unit 142 performs control to suppress a determination that the camera lane marking CL and the map lane marking ML are deviating if the height information and the curvature degree information satisfy a predetermined condition. "Suppressing the determination" includes, for example, adjusting a threshold value used in the deviation determination or adjusting the determination target area to make it less likely that the lane markings are deviating. Specifically, the determination unit 142 performs control to suppress a determination that the camera lane marking CL and the map lane marking ML are deviating if it determines that the longitudinal gradient influence (dlon) in the pitch direction of the host vehicle M calculated from the height information and the lateral gradient influence (dlat0+dlat) in the roll direction calculated from the curvature degree information satisfy a predetermined condition. This makes it possible to suppress the influence of the gradient when determining the deviation, and to prevent excessive deviation determinations. A specific example of the predetermined condition will now be described with reference to FIG.

[0084] Fig. 8 is a diagram for explaining predetermined conditions for the longitudinal gradient influence degree and the lateral gradient influence degree in an embodiment. In the example of Fig. 8, the horizontal axis represents the longitudinal gradient influence degree (dlon), and the vertical axis represents the lateral gradient influence degree (dlat0 + dlat). Below, each of the predetermined conditions will be explained with reference to Fig. 8.

[0085] <Condition (1): Height increases due to lateral slope> Condition (1) is the case where the lateral gradient influence degree (dlat0 + dlon) is greater than a first threshold value. The first threshold value is, for example, a fixed value greater than 0 (zero). When condition (1) is met, the lateral gradient influence degree indicates that the lateral gradient of the road is large, and the height of one of the left and right camera lane lines is estimated to be high due to the lateral gradient ("height +" in FIG. 8). This corresponds to the situation of camera lane line CL3 shown in FIG. 6. Therefore, the camera lane line CL is predicted to deviate outward (toward the outside of the turn) from the actual lane line (or map lane line). Therefore, when condition (1) is met, the determination unit 142 determines that the road is affected by the gradient and suppresses the determination that the camera lane line CL and the map lane line ML are deviating.

[0086] <Condition (2): Height decreases due to lateral slope> Condition (2) is the case where the lateral gradient influence (dlat0 + dlon) is less than a second threshold. The second threshold is, for example, a fixed value smaller than 0. When condition (2) is met, it is estimated that the lateral gradient of the road is large due to the lateral gradient influence, and that the height of one of the left and right camera lane lines is small due to the lateral gradient ("Height -" in Figure 8). This corresponds to the situation of the camera lane line CL1 shown in Figure 6. The camera lane line CL is predicted to deviate inward (toward the inside of the turn) from the actual lane line (or map lane line). Therefore, when condition (2) is met, the determination unit 142 determines that the road is affected by the gradient and suppresses the determination that the camera lane line CL and the map lane line ML are deviating.

[0087] <Condition (3): The combined height of the vertical and horizontal gradients increases> Condition (3) is satisfied when the combined value of the longitudinal gradient influence and the lateral gradient influence (dlat0 + dlat + dlon) is greater than the third threshold. As shown in FIG. 8, the third threshold is a value represented by a straight line in a two-dimensional coordinate system consisting of the longitudinal gradient influence (dlon) and the lateral gradient influence (dlat0 + dlat). In other words, the threshold differs depending on the longitudinal gradient influence and the lateral gradient influence. When condition (3) is satisfied, the position at which the camera lane marking CL is recognized by the first recognition unit 132 is expected to change due to both gradient influences. Furthermore, when condition (3) is satisfied, the camera lane marking CL is predicted to deviate outward (toward the outside of the turn) from the actual lane marking (or map lane marking). Therefore, when condition (3) is satisfied, the determination unit 142 determines that the camera lane marking CL is affected by the gradient and suppresses the determination that the camera lane marking CL and the map lane marking ML are deviating from each other.

[0088] <Condition (4): The combined height of the vertical and horizontal gradients decreases> Condition (4) is satisfied when the combined value of the longitudinal gradient influence and the lateral gradient influence (dlat0 + dlat + dlon) is less than the fourth threshold. As shown in FIG. 8, the fourth threshold is a value represented by a straight line in a two-dimensional coordinate system consisting of the longitudinal gradient influence (dlon) and the lateral gradient influence (dlat0 + dlat), and is smaller than the third threshold. In this case, as with condition (3), the appearance of the camera lane markings by the first recognition unit 132 is expected to change depending on the influence of both gradients. Furthermore, when condition (3) is satisfied, the camera lane markings CL are predicted to deviate inward (toward the inside of the turn) from the actual lane markings (or map lane markings). Therefore, when condition (4) is satisfied, the determination unit 142 determines that the camera lane markings CL are affected by the gradient and suppresses the determination that the camera lane markings CL and the map lane markings ML are deviating from each other.

[0089] <Condition (5): Road surface height increases due to the influence of the vertical gradient> Condition (5) is the case where the longitudinal gradient influence degree (dlon) is greater than a fifth threshold value. The fifth threshold value is, for example, a fixed value greater than 0. In the case of condition (5), if the longitudinal gradient of the road is large due to the longitudinal gradient influence degree and the value based on the height is large, it is estimated that the uphill gradient is large. Therefore, when condition (5) is satisfied, the determination unit 142 suppresses the determination that the camera lane marking CL and the map lane marking ML are separated.

[0090] <Condition (6): Road surface height decreases due to the vertical gradient> Condition (6) is the case where the longitudinal gradient influence degree (dlon) is less than a sixth threshold value. The sixth threshold value is, for example, a fixed value less than 0. If the height-based value is smaller, it is estimated that the downward gradient is steep. Therefore, when condition (6) is satisfied, the determination unit 142 suppresses the determination that the camera lane marking CL and the map lane marking ML are separated.

[0091] Each of the above conditions (1) to (6) may be combined with other conditions, either directly or with modifications. For example, when the lateral gradient influence is equal to or less than the first threshold and the longitudinal gradient influence is equal to or less than the fifth threshold, the above condition (3) may be applied when the combined value of the longitudinal gradient influence and the lateral gradient influence is greater than the third threshold. This allows the combined value to reflect the gradient influence of the entire road, even if the gradient influence is small in either the longitudinal or lateral direction.

[0092] Furthermore, when the lateral gradient influence is equal to or greater than the second threshold and the longitudinal gradient influence is equal to or greater than the sixth threshold, the combined value of the longitudinal gradient influence and the lateral gradient influence may be less than the fourth threshold as the above-mentioned condition (4). This allows the combined value to reflect the gradient influence of the entire road, even if the gradient influence is large in either the longitudinal or lateral direction.

[0093] If any one of the above conditions (1) to (6) is satisfied, the determination unit 142 may predict that the camera lane line CL recognized by the first recognition unit 132 will deviate to one side or the other of the road width direction (travel path width direction) compared to when all of the conditions (1) to (6) are not satisfied. Furthermore, the determination unit 142 may perform control to suppress a determination that the camera lane line CL and the map lane line ML deviate from each other when the predicted deviation direction (prediction direction) and the deviation direction of the camera lane line CL actually recognized by the first recognition unit 132 from the map lane line ML match (within a predetermined error tolerance range). This allows the camera lane line CL recognized by the first recognition unit 132 to be determined to be due to the influence of a gradient when the predicted direction and the deviation direction match. Therefore, by suppressing a determination that the camera lane line CL and the map lane line ML deviate from each other, excessive deviation determinations can be suppressed.

[0094] <Other conditions> Other conditions may include, for example, the predetermined condition being that the height information and the curvature information are greater than a predetermined value. More specifically, in the example of FIG. 8, the case may be one in which the lateral gradient influence is greater than the first threshold and the longitudinal gradient influence is less than the sixth threshold (the shaded area in the upper left of the figure), or one in which the lateral gradient influence is less than the second threshold and the longitudinal gradient influence is greater than the fifth threshold (the shaded area in the lower right of the figure). Under these conditions, the signs of the longitudinal gradient influence and the lateral gradient influence may be reversed, and a combination of positive and negative values ​​may make it impossible to determine whether the result is "height +" or "height -." Therefore, when the above conditions are met, the determination unit 142 predicts that the camera lane marking CL recognized by the first recognition unit 132 may deviate in both the road width direction (travel path width direction) and the other direction. The phrase "there is a possibility of deviation in both one and the other direction" means that the camera lane line CL may deviate in one direction in the road width direction (e.g., toward the inside of the road) or in the other direction (e.g., toward the outside of the road). In other words, when the above conditions are met, it is easier to determine that the camera lane line CL and the map lane line ML are deviating than when the above conditions are not met. Furthermore, when the deviation direction predicted as described above matches the direction of the camera lane line CL actually recognized by the first recognition unit 132 (the deviation direction of the camera lane line CL from the map lane line ML), the determination unit 142 suppresses determining that the camera lane line CL and the map lane line ML are deviating. This makes it possible to suppress excessive deviation determinations even under the above conditions.

[0095] [Modification of the determination unit] For example, on a curved road where the degree of curvature is equal to or greater than a threshold, the heights of the lane markings on the inside and outside of the turning lane are different (the lane markings on the outside of the turning lane are higher), so the determination unit 142 may perform the above-described determination process separately for each lane. This can improve the accuracy of the determination.

[0096] The determination unit 142 may also determine whether the camera lane marking CL is affected by a gradient based on the predicted direction and the deviation direction of the camera lane marking CL, taking into account the above-mentioned conditions and other conditions. FIG. 9 is a diagram for explaining the determination of whether the camera lane marking CL is affected by a gradient. In the example of FIG. 9, the determination unit 142 acquires the shape of the road in the longitudinal direction (longitudinal direction, extension direction) from height information (map height information) obtained from map information, and acquires an estimated lateral gradient from curvature degree information (map curvature degree information) obtained from the map information. Next, the determination unit 142 predicts the deviation direction based on the road longitudinal shape and the estimated lateral gradient information under the above-mentioned conditions, and determines whether the predicted direction matches the deviation direction of the camera lane marking CL from the map lane marking ML recognized by the first recognition unit 132.

[0097] Furthermore, if there is a match, the road shape is a shape that is affected by a predetermined gradient, and the curvature (degree of curvature) ahead of the vehicle M is large (above a threshold), the determination unit 142 determines that the camera lane marking CL is affected by the road gradient. This makes it possible to perform more appropriate deviation determination and driving control depending on whether or not there is a gradient effect.

[0098] As another variation, in addition to (or instead of) the above-described conditions, the determination unit 142 may directly use the height information and curvature information, compare them with corresponding thresholds, and predict whether the camera lane marking CL deviates to one side or the other in the road width direction based on the comparison result. Note that since determining the gradient influence degree using the height information and curvature information directly is expected to be less accurate than when the gradient influence degree is used, it is preferable to impose a restriction on the determination unit 142 so that it is used only in situations where both values ​​are greater than or equal to the threshold. For example, when the height information and curvature information are greater than a predetermined value and the corresponding predetermined condition is satisfied, the determination unit 142 predicts that the camera lane marking CL recognized by the first recognition unit 132 deviates to both sides in the road width direction more than when the predetermined condition is not satisfied. Then, the determination unit 142 suppresses the determination that the camera lane line CL and the map lane line ML are deviating when the predicted deviation direction matches the direction of the camera lane line CL recognized by the first recognition unit 132 (the deviation direction of the camera lane line CL from the map lane line ML). This allows for more appropriate deviation determination using the height information and curvature degree information.

[0099] [Selection] Next, the details of the processing of the selection unit 144 will be described. For example, as described above, the camera lane markings CL recognized based on the camera image of the camera 10 or the like are affected by the road gradient, which can cause recognition errors in the camera lane markings CL and lead to deviations from the actual lane markings (or map lane markings ML). Conventionally, when traveling on a curved road, the camera lane markings were selected as the correct lane markings if the parallelism between the left and right camera lane markings as viewed from the vehicle M was equal to or greater than a threshold, and map lane markings were selected if the parallelism was less than the threshold. However, if the shape of the road on which the vehicle M is traveling has a gradient, errors in the shape recognition of the lane markings could result in the wrong lane markings being selected.

[0100] 10 is a diagram illustrating the shapes of the camera lane markings CL and map lane markings ML as seen from the host vehicle M traveling on a curved road. As shown in FIG. 10, the camera lane markings CL1 and ML1, and the camera lane markings CL2 and ML2, which are compared, are separated from each other, so one of the lane markings is selected. However, because a shape recognition error occurs in the camera lane markings CL due to the influence of the gradient, the map lane markings ML1 and ML2 should have been selected. However, because the parallelism between the left and right camera lane markings CL1 and CL2 is equal to or greater than a threshold, the camera lane markings were erroneously selected. Therefore, in the embodiment, the selection unit 144 selects the map lane markings ML when it determines that the camera lane markings CL are affected by the gradient.

[0101] For example, when the determination unit 142 determines that the camera division line CL and the map division line ML are deviating, the selection unit 144 predicts the deviation direction of the camera division line CL based on the gradient influence (vertical gradient influence, horizontal gradient influence) from the map information, and selects the map division line ML when the predicted direction matches the deviation direction of the camera division line CL from the map division line ML recognized by the first recognition unit 132.

[0102] More specifically, the selection unit 144 selects the map lane lines ML1 and ML2 when, for example, the determination unit 142 determines that the camera lane lines CL and the map lane lines ML are separated, the parallelism of multiple camera lane lines CL1 and CL2 present in the traveling direction of the host vehicle M recognized by the first recognition unit 132 is equal to or greater than a threshold, and the height of the road (travel surface) on which the host vehicle M is traveling (the height of the road in the traveling direction of the host vehicle M) is decreasing (downhill). Whether the height of the road is decreasing may be determined based on height information of the center of the road included in the map information, or longitudinal gradient information may be acquired from the height information and used to determine the decrease. Furthermore, if the map information includes longitudinal gradient information, whether the height of the road is decreasing may be determined based on the longitudinal gradient information.

[0103] This allows the map lane markings ML to be selected even in a situation where the camera lane markings CL recognized by the first recognition unit 132 are recognized as having a different shape from their actual shape due to the influence of road gradient, and the camera lane markings are determined to be parallel due to their changed appearance. Therefore, driving control can be performed using information on the lane markings that is more accurate.

[0104] Note that the selection unit 144 selects the camera lane marking CL when it is determined that the camera lane marking CL and the map lane marking ML are separated and the parallelism is equal to or greater than a threshold, but the height of the road on which the host vehicle M is traveling is not decreasing (when the road is not downhill). When the road is not downhill, the parallelism is unlikely to be equal to or greater than the threshold due to the influence of the gradient, so conversely, by selecting the parallel camera lane marking CL as the correct lane marking, it is possible to select the lane marking with higher accuracy.

[0105] For example, based on the curvature degree information included in the map information, the selection unit 144 may select the map lane marking ML when the road on which the vehicle M is traveling is a curved road (for example, the curvature is equal to or greater than a predetermined value) and the camera lane marking CL recognized by the first recognition unit 132 deviates from the map lane marking ML on the inside of the turn, even if the parallelism of the multiple camera lane markings CL1, CL2 is equal to or greater than a threshold value, and the height of the road is decreasing. Note that the determination of whether or not the road is a curved road may be made by acquiring lateral gradient information based on the curvature degree and using the acquired lateral gradient information, or, if the map information includes lateral gradient information, whether or not the road is a curved road may be determined based on the lateral gradient information.

[0106] As a result, when the road height decreases, the camera division line CL recognized by the first recognition unit 132 is likely to be recognized as deviating more to the inside of the turn than the map division line ML, so by adding the deviation of the camera division line CL from the map division line ML to the conditions for selecting the map division line ML, it is possible to select the map division line ML under more appropriate road conditions.

[0107] Here, an example will be described in which the selection unit 144 selects map lane lines instead of camera lane lines. FIG. 11 is a diagram showing an example of lane line selection by the selection unit 144. The example of FIG. 11 also shows an example of processing by the determination unit 142. In the example of FIG. 11, the determination unit 142 acquires the road longitudinal shape from height information (map height information) obtained from map information, and acquires an estimated lateral gradient from curvature degree information (map curvature degree information) obtained from the map information. Next, the determination unit 142 calculates a height change due to the influence of the longitudinal gradient (e.g., the aforementioned longitudinal gradient influence degree) from the road longitudinal shape, and calculates a height change due to the influence of the lateral gradient (e.g., the aforementioned lateral gradient influence degree) based on the estimated lateral gradient. Furthermore, the determination unit 142 determines whether the height of the road on which the host vehicle M is traveling is decreasing based on the respective calculation results of the height change due to the influence of the longitudinal gradient and the height change due to the influence of the lateral gradient.

[0108] The selection unit 144 then selects the map lane markings ML instead of the camera lane markings CL when it is determined that the road height is decreasing, the roadway on which the vehicle M is traveling has a shape that is affected by a predetermined gradient, the camera lane markings CL deviate inward from the map lane markings ML, and the curvature (degree of curvature) ahead of the vehicle M is large (above a threshold). This makes it possible to more appropriately select the lane markings that define the lane on which the vehicle M is traveling depending on whether or not there is a gradient effect. This makes it possible to perform more appropriate driving control depending on the surrounding road conditions.

[0109] [Processing flow] The following describes the processing executed by the automatic driving control device 100 of the embodiment. Of the processing executed by the automatic driving control device 100, the following mainly describes the driving control processing based on the recognition status of lane markings, etc. It should be noted that when the flow starts, the host vehicle M is assumed to be executing a predetermined driving control (for example, LKAS control in a first driving state (for example, the driver's hands are off)). The processing described below may be executed repeatedly at a predetermined timing or at a predetermined cycle (for example, while driving control by the automatic driving control device 100 is being executed).

[0110] 12 is a flowchart showing an example of the flow of a driving control process in an embodiment. In the example of FIG. 12, the first recognition unit 132 recognizes the surrounding situation including lane lines (camera lane lines) present around the host vehicle M based on the output of the detection device DD that detects the surrounding situation of the host vehicle M (step S100). In the processing of step S100, for example, objects present around the host vehicle M (e.g., physical boundaries, other vehicles, etc.) may be recognized. Next, the second recognition unit 134 refers to map information based on the position information of the host vehicle M and recognizes lane lines (map lane lines) present around the host vehicle M from the map information (step S110).

[0111] Next, the determination unit 142 performs a deviation determination to determine whether or not the camera lane markings CL and the map lane markings ML deviate from each other (step S120). The processing of step S120 will be described later. Next, the selection unit 144 executes a selection process to select a lane marking based on the determination result by the determination unit 142 (step S130). The processing of step S130 will be described later. Next, the driving control unit 146 generates a target trajectory so that the vehicle M travels along the selected lane marking (step S140), and causes the second control unit 160 to drive the vehicle M along the generated target trajectory (step S150). This ends the processing of this flowchart.

[0112] [Deviation Determination Process (Step S120)] FIG. 13 is a flowchart showing an example of deviation determination processing. In the example of FIG. 13, the determination unit 142 acquires elevation information of the road on which the vehicle M is traveling from map information based on the position information of the vehicle M (step S121). Next, the determination unit 142 acquires curvature information of the road on which the vehicle M is traveling from the map information (step S122). Next, the determination unit 142 acquires (calculates) the longitudinal gradient from the elevation information, and acquires (predicts) the lateral gradient from the curvature degree (step S123). Next, the determination unit 142 determines whether the longitudinal gradient and the lateral gradient satisfy predetermined conditions (step S124). If it is determined that the predetermined conditions are satisfied, the determination unit 142 adjusts a threshold value or the like in the deviation determination to suppress determination that the camera lane marking CL and the map lane marking ML are deviating more than usual (step S125). If it is determined that the predetermined condition is not satisfied, the determining unit 142 performs a deviation determination according to the normal determination criteria (threshold value) etc. (step S126), and the processing of this flowchart ends.

[0113] [Selection process (step S130)] FIG. 14 is a flowchart showing an example of the selection process. In the example of FIG. 14, the selection unit 144 determines whether the camera lane lines CL and the map lane lines ML are separated from each other based on the determination result of the determination unit 142 (step S131). If it is determined that there is a separation, the selection unit 144 determines whether the parallelism of the multiple camera lane lines CL is equal to or greater than a threshold based on the recognition result by the first recognition unit 132 (step S132). If it is determined that the parallelism is equal to or greater than the threshold, the selection unit 144 determines whether the height of the road (road surface in the traveling direction) on which the host vehicle M is traveling is decreasing (whether the road is downhill) (step S133). If it is determined that the height of the road is decreasing, the selection unit 144 selects the map lane lines ML as the lane lines that serve as the basis for driving control of the host vehicle M (step S134). Furthermore, if it is determined in the processing of step S132 that the parallelism of the multiple camera lane lines is not equal to or greater than the threshold, the selection unit 144 also selects the map lane lines ML (step S134).

[0114] Furthermore, if it is determined in the processing of step S133 that the road surface height has not decreased, the selection unit 144 selects the camera lane marking as the lane marking that serves as the reference for the vehicle M to travel on (step S135). Furthermore, if it is determined in the processing of step S131 that the camera lane marking CL and the map lane marking ML do not diverge, the selection unit 144 selects at least one of the camera lane marking CL and the map lane marking ML (step S136). In the processing of step S136, a preset one may be selected, or both may be selected and driving control may be performed based on information about both lane marks (or the position of one lane marking may be interpolated with the position of the other lane marking, for example). Alternatively, the more accurate one of the lane marks may be selected depending on the recognition accuracy, the update history of the map information, and the like. This ends the processing of this flowchart.

[0115] [Variations] In the above-described embodiment, the deviation direction due to a shape recognition error is predicted or the determination of deviation is suppressed depending on which of a plurality of preset conditions the longitudinal gradient influence degree and the lateral gradient influence degree satisfy. However, the deviation direction may be obtained by inputting the longitudinal gradient influence degree and the lateral gradient influence degree, or road height information and curvature degree information, using a function. Alternatively, a trained model may be generated in advance by machine learning or the like, which inputs the longitudinal gradient influence degree and the lateral gradient influence degree, or road height information and curvature degree information, and outputs the deviation direction, and the generated trained model may be used to obtain the deviation direction.

[0116] According to the above-described embodiment, the determination device includes a first recognition unit 132 that recognizes the surrounding conditions, including camera marking lines (an example of first marking lines) that define the path along which the vehicle M (an example of a moving body) travels, based on the output of a detection device DD that detects the surrounding conditions of the vehicle M; a second recognition unit 134 that recognizes map marking lines (an example of second marking lines) that define the path along which the vehicle M travels from map information based on the position information of the vehicle M; and a determination unit 142 that determines whether the camera marking lines and the map marking lines are separated. The map information includes height information and curvature information of the path along which the vehicle M travels. If the height information and curvature information satisfy predetermined conditions, the determination unit 142 suppresses a determination that the camera marking lines and the map second marking lines are separated. This allows the determination unit 142 to more appropriately determine the separation of the marking lines according to the conditions of the path along which the vehicle M travels. This ultimately contributes to the development of a sustainable transportation system.

[0117] Specifically, according to the embodiment, even if gradient information is not available as map information, the road gradient can be estimated to a certain extent based on the road height and the magnitude of the curvature. Therefore, by using the height information and curvature information, it is possible to suppress the determination that the lane markings deviate when traveling on a road with a steep gradient. Even if gradient information is not available, it is possible to suppress the impact of the appearance of the lane markings on a gradient road deviating from the actual shape of the lane markings. This allows the vehicle M to select a more appropriate lane marking based on the deviation determination result and travel along the selected lane marking.

[0118] The above-described embodiment can be expressed as follows. a storage medium for storing computer-readable instructions; a processor connected to the storage medium; The processor executes the computer-readable instructions to: Based on an output from a detection device that detects the surrounding situation of the moving object, the surrounding situation including a first dividing line that divides a path along which the moving object moves is recognized; Recognizing a second dividing line that divides a travel path around the moving object from map information based on the position information of the moving object; determining whether the first demarcation line and the second demarcation line are separated from each other; the map information includes altitude information and curvature information of the travel path; suppressing a determination that the first marking line and the second marking line are separated when the height information and the curvature degree information satisfy a predetermined condition; Judgment device.

[0119] 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]

[0120] 1...vehicle system, 10...camera, 12...radar device, 14...LIDAR, 16...object recognition device, 20...communication device, 30...HMI, 40...vehicle sensor, 50...navigation device, 60...MPU, 80...driving operator, 100...automatic driving control device, 120...first control unit, 130...recognition unit, 132...first recognition unit, 134...second recognition unit, 140...action plan generation unit, 142...determination unit, 144...selection unit, 146...travel control unit, 160...second control unit, 162...target trajectory acquisition unit, 164...speed control unit, 166...steering control unit, 180...HMI control unit, 190...memory unit, 200...traveling drive force output device, 210...brake device, 220...steering device, M...host vehicle

Claims

1. a first recognition unit that recognizes a surrounding situation including a first division line that divides a path along which the moving object moves, based on an output of a detection device that detects a surrounding situation of the moving object; a second recognition unit that recognizes a second division line that divides a travel path around the moving object from map information based on position information of the moving object; a determination unit that determines whether the first demarcation line and the second demarcation line are separated from each other, the map information includes altitude information and curvature information of the travel path; The determination unit suppresses a determination that the first demarcation line and the second demarcation line are separated when the height information and the curvature degree information satisfy a predetermined condition, The determination unit When it is determined that the predetermined condition is satisfied, it is predicted that the first demarcation line recognized by the first recognition unit will deviate to one side or the other side in the width direction of the travel path compared to when the predetermined condition is not satisfied, When the predicted deviation direction and the direction of the first demarcation line match, the determination that the first demarcation line and the second demarcation line are deviating is suppressed. Judgment device.

2. The height information is height information of the center of the movement path. The determination device according to claim 1 .

3. the determination unit performs a determination using the predetermined condition for each of a lane marking on an outer side of a turning of the travel path and a lane marking on an inner side of the turning of the travel path. The determination device according to claim 1 .

4. the determination unit suppresses a determination that the first marking line and the second marking line are separated when a longitudinal gradient influence degree in a pitch direction of the moving body based on the height information and a lateral gradient influence degree in a roll direction of the moving body based on the turning degree information satisfy the predetermined condition. The determination device according to claim 1 .

5. The predetermined condition includes a case where the lateral gradient influence degree is greater than a first threshold value greater than 0. The determination device according to claim 4 .

6. The predetermined condition includes a case where the lateral gradient influence degree is less than a second threshold value that is less than 0. The determination device according to claim 4 .

7. the predetermined condition includes a case where a sum of the longitudinal gradient influence degree and the lateral gradient influence degree is greater than a third threshold value. The determination device according to claim 4 .

8. the predetermined condition includes a case where a sum of the longitudinal gradient influence degree and the lateral gradient influence degree is less than a fourth threshold value. The determination device according to claim 4 .

9. The predetermined condition includes a case where the longitudinal gradient influence degree is greater than a fifth threshold value greater than 0. The determination device according to claim 4 .

10. The predetermined condition includes a case where the longitudinal gradient influence degree is less than a sixth threshold value that is less than 0. The determination device according to claim 4 .

11. The predetermined condition includes a case where, when the lateral gradient influence degree is equal to or less than a first threshold value and the longitudinal gradient influence degree is equal to or less than a fifth threshold value, a sum of the longitudinal gradient influence degree and the lateral gradient influence degree is greater than a third threshold value. The determination device according to claim 4 .

12. The predetermined condition includes a case where, when the lateral gradient influence degree is equal to or greater than a second threshold value and the longitudinal gradient influence degree is equal to or greater than a sixth threshold value, a sum of the longitudinal gradient influence degree and the lateral gradient influence degree is less than a fourth threshold value. The determination device according to claim 4 .

13. the predetermined condition is that the height information and the bending degree information are greater than predetermined values; the determination unit predicts that there is a possibility that the first demarcation line will deviate from the first demarcation line in both one and the other directions of the travel path width when the predetermined condition is satisfied; The determination device according to claim 4 .

14. the predetermined condition is a case where the lateral gradient influence degree is greater than a first threshold value that is greater than 0 and the longitudinal gradient influence degree is less than a sixth threshold value that is less than 0, the determination unit predicts that there is a possibility that the first demarcation line will deviate from the first demarcation line in both one and the other directions of the travel path width when the predetermined condition is satisfied; The determination device according to claim 4 .

15. the predetermined condition is that the lateral gradient influence degree is less than a second threshold value that is less than 0, and the longitudinal gradient influence degree is greater than a fifth threshold value that is greater than 0, the determination unit predicts that there is a possibility that the first demarcation line will deviate from the first demarcation line in both one and the other directions of the travel path width when the predetermined condition is satisfied; The determination device according to claim 4 .

16. The computer Recognizing a surrounding situation including a first dividing line dividing a path along which the moving object moves, based on an output from a detection device that detects a surrounding situation of the moving object; Recognizing a second dividing line that divides a travel path around the moving object from map information based on the position information of the moving object; determining whether the first demarcation line and the second demarcation line are separated from each other; the map information includes altitude information and curvature information of the travel path; When the height information and the curvature degree information satisfy a predetermined condition, a determination that the first marking line and the second marking line are separated is suppressed, When it is determined that the predetermined condition is satisfied, it is predicted that the recognized first demarcation line will deviate to one side or the other in the width direction of the travel path compared to when the predetermined condition is not satisfied, When the predicted deviation direction and the direction of the first demarcation line match, the determination that the first demarcation line and the second demarcation line are deviating is suppressed. Judgment method.

17. On the computer, recognizes a surrounding situation including a first dividing line dividing a path along which the moving object moves, based on an output of a detection device that detects a surrounding situation of the moving object; a second division line that divides a travel path around the moving object from map information based on the position information of the moving object; determining whether or not the first demarcation line and the second demarcation line are separated from each other; the map information includes altitude information and curvature information of the travel path; When the height information and the curvature degree information satisfy a predetermined condition, a determination that the first demarcation line and the second demarcation line are separated is suppressed, When it is determined that the predetermined condition is satisfied, it is predicted that the recognized first demarcation line will deviate to one side or the other in the width direction of the travel path, compared to when the predetermined condition is not satisfied; When the predicted deviation direction and the direction of the first demarcation line match, a determination that the first demarcation line and the second demarcation line are deviating is suppressed. program.

Images