Vehicle control device, vehicle control method, and storage medium

Abstract

A vehicle control device, a vehicle control method, and a storage medium capable of suppressing erroneous determination of a dividing line on the basis of the surrounding situation of the vehicle. A vehicle control device is provided with: a first recognition unit that recognizes, on the basis of an output from a detection device that detects a surrounding situation of a host vehicle, a surrounding situation including a first division line that divides a travel lane of the host vehicle and another vehicle present in the periphery of the host vehicle; a second recognition unit that recognizes, from the map information, a second division line that divides lanes around the vehicle on the basis of the position information of the vehicle; and a determination unit that determines whether or not the first and second division lines match, and when the first recognition unit recognizes a plurality of one-sided first division lines among the left and right first division lines of the host vehicle, the first one-sided first division line included in the recognized plurality of one-sided first division lines matches the second division line, and a predetermined condition is satisfied, the determination unit determines whether or not the first and second division lines match the first one-sided first division line and the second one-sided first division line. The reliability of matching information of a first division line and a second division line of a first single side is reduced.

Description

Technical Field

[0001] The present invention relates to a vehicle control device, a vehicle control method and a storage medium. Background Art

[0002] In recent years, efforts to provide sustainable transportation systems that take into account vulnerable individuals, particularly those in traffic, have intensified. To achieve this, research and development efforts are underway in autonomous driving technologies to further improve traffic safety and convenience. Relatedly, a technique is known that determines whether road signs identified by image recognition processing match those in map information and adjusts the reliability of the map information based on the determination result (e.g., Japanese Patent Application Laid-Open No. 2019-212188). Summary of the Invention

[0003] However, even when the camera demarcation lines derived from captured camera images match the map demarcation lines derived from map information, conventional autonomous driving technology is not always reliable. For example, during road construction, temporary demarcation lines are drawn on the road to help vehicles avoid the construction site. However, these temporary demarcation lines may remain during or after the construction. In such cases, even if the camera demarcation lines match the map demarcation lines, they may still be incorrect. This presents the problem of misjudging demarcation lines depending on surrounding conditions.

[0004] One of the objectives of the present application is to provide a vehicle control device, a vehicle control method, and a storage medium that can suppress erroneous determination of dividing lines based on the surrounding conditions of the vehicle in order to solve the above-mentioned problems, thereby contributing to the development of a sustainable transportation system.

[0005] The vehicle control device, vehicle control method, and storage medium according to the present invention employ the following structures.

[0006] (1): One embodiment of the present invention relates to a vehicle control device, wherein the vehicle control device comprises: a first recognition unit that recognizes the surrounding conditions including a first dividing line that divides the driving lane of the vehicle and other vehicles existing around the vehicle based on the output of a detection device that detects the surrounding conditions of the vehicle; a second recognition unit that recognizes the second dividing line that divides the lanes around the vehicle based on map information based on the position information of the vehicle; and a determination unit that determines whether the first dividing line and the second dividing line match, the determination unit reducing the reliability of the matching information of the matching first unilateral first dividing line and the second dividing line when the first recognition unit recognizes multiple unilateral first dividing lines existing on the left and right first dividing lines of the vehicle, and the first unilateral first dividing line included in the multiple recognized unilateral first dividing lines matches the second dividing line, and satisfies a specified condition.

[0007] (2): In the above-mentioned solution (1), the prescribed condition includes a situation where the other vehicle passes on the first one-side first dividing line determined to coincide with the second dividing line.

[0008] (3): In the scheme of (1) above, the vehicle control device further includes a driving control unit, which controls one or both of the steering and speed of the vehicle based on the determination result determined by the determination unit to perform driving control. When there is a second unilateral first dividing line among the multiple unilateral first dividing lines identified by the first identification unit, which is determined by the determination unit to be inconsistent with the second dividing line, the driving control unit controls the driving of the vehicle based on the second unilateral first dividing line.

[0009] (4): In the above-mentioned aspect (1), the predetermined condition includes the fact that the host vehicle is traveling within a predetermined distance from a location where construction is being carried out or a location where construction was carried out in the past.

[0010] (5): In the above-mentioned aspect (1), the predetermined condition includes the existence of a physical road boundary in the direction of travel of the host vehicle.

[0011] (6): In the scheme of (1) above, the vehicle control device further includes a driving control unit that controls one or both of the steering and speed of the vehicle based on the determination result determined by the determination unit to perform driving control, and the driving control unit causes the vehicle to travel along the physical boundary of the road when there is a physical boundary of the road extending in a direction different from the first unilateral first dividing line and the second dividing line that match.

[0012] (7): In the above-mentioned scheme (3), the determination unit determines that the second single-side first dividing line is a correct dividing line when the second single-side first dividing line extends along the physical boundary of the road, and the driving control unit causes the vehicle to travel along the second single-side first dividing line.

[0013] (8): In the solution of (7) above, the driving control unit adjusts the position of the second unilateral first dividing line along the direction in which the physical boundary of the road extends, and causes the host vehicle to travel along the adjusted position of the second unilateral first dividing line.

[0014] (9): In the above-mentioned solution (8), the driving control unit adjusts the position of the second unilateral first dividing line when the distance between the road physical boundary and the second unilateral first dividing line is less than a predetermined distance.

[0015] (10): In the above aspect (6), the driving control unit does not perform driving control based on the physical boundary of the road when the host vehicle is traveling in a lane having a slope greater than a predetermined value.

[0016] (11): In the above-mentioned aspect (6), when there is sign information indicating a construction site in the direction of travel of the host vehicle, the driving control unit causes the host vehicle to travel along the physical boundary of the road.

[0017] (12): One embodiment of the present invention relates to a vehicle control method, wherein the vehicle control method causes a computer to perform the following processing: based on the output of a detection device that detects the surrounding conditions of the vehicle, identify the surrounding conditions including a first dividing line that divides the driving lane of the vehicle and other vehicles existing around the vehicle; based on the position information of the vehicle, identify the second dividing line that divides the lane around the vehicle according to map information; determine whether the first dividing line and the second dividing line are consistent; and when multiple single-sided first dividing lines are identified among the first dividing lines on the left and right sides of the vehicle, and the first single-sided first dividing line included in the multiple identified single-sided first dividing lines is consistent with the second dividing line, and a specified condition is satisfied, reduce the reliability of the consistent information of the first single-sided first dividing line and the second dividing line.

[0018] (13): One embodiment of the present invention relates to a storage medium storing a program, wherein the program causes a computer to perform the following processing: based on the output of a detection device that detects the surrounding conditions of the vehicle, identify the surrounding conditions including a first dividing line that divides the driving lane of the vehicle and other vehicles existing around the vehicle; based on the position information of the vehicle, identify the second dividing line that divides the lane around the vehicle according to map information; determine whether the first dividing line and the second dividing line are consistent; and when multiple unilateral first dividing lines are identified among the left and right first dividing lines of the vehicle, and the first unilateral first dividing line included in the multiple identified unilateral first dividing lines is consistent with the second dividing line, and a specified condition is satisfied, reduce the reliability of the consistency information of the first unilateral first dividing line and the second dividing line that are consistent.

[0019] According to the above-mentioned aspects (1) to (13), it is possible to suppress erroneous determination of the dividing line based on the surrounding conditions of the host vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 It is a configuration diagram of a vehicle system including a vehicle control device according to an embodiment.

[0021] Figure 2 This is a functional structure diagram of the first control unit and the second control unit.

[0022] Figure 3 It is a diagram for explaining the determination process and driving control in the first scenario.

[0023] Figure 4 It is a diagram for explaining the determination process and driving control in the second scenario.

[0024] Figure 5 It is a diagram for explaining the determination process and driving control in the third scenario.

[0025] Figure 6 This is a flowchart showing an example of processing performed by the automatic driving control device of the embodiment. DETAILED DESCRIPTION

[0026] The following describes embodiments of the vehicle control device, vehicle control method, and storage medium of the present invention with reference to the accompanying drawings. As an example, the following describes an embodiment in which the present vehicle is applied to an autonomous vehicle including the vehicle control device. Autonomous driving refers to driving control, for example, by automatically controlling one or both of the vehicle's steering and speed. Examples of such driving control include ACC (Adaptive Cruise Control System), TJP (Traffic Jam Pilot), LKAS (Lane Keeping Assistance System), ALC (Automated Lane Change), and CMBS (Collision Mitigation Brake System). Autonomous vehicles can also perform driving control manually by the vehicle user (e.g., passenger) (so-called manual driving). The following describes a case where left-hand traffic regulations apply. However, if right-hand traffic regulations apply, the left and right sections can be reversed.

[0027] [Overall structure]

[0028] Figure 1 This is a structural diagram of a vehicle system 1 including a vehicle control device according to an embodiment. The vehicle equipped with the vehicle system 1 (hereinafter referred to as the host vehicle M) is, for example, a two-wheeled, three-wheeled, or four-wheeled vehicle. Its driving source is an internal combustion engine such as a diesel engine or a gasoline engine, an electric motor, or a combination thereof. The electric motor operates using power generated by a generator connected to the internal combustion engine or power discharged from a battery (storage battery) such as a secondary battery or a fuel cell.

[0029] Vehicle system 1 includes, for example, a camera 10, a radar device 12, a LIDAR (Light Detection and Ranging) device 14, an object recognition device 16, a communication device 20, an HMI (Human Machine Interface) 30, vehicle sensors 40, a navigation device 50, an MPU (Map Positioning Unit) 60, a driving control element 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 interconnected via multiplexed communication lines such as CAN (Controller Area Network) communication lines, serial communication lines, and wireless communication networks. Figure 1The illustrated configuration is merely an example; portions of the configuration may be omitted, or additional configurations may be added. The combination of camera 10, radar device 12, LIDAR 14, and object recognition device 16 is an example of a "detection device DD." HMI 30 is an example of an "output device." Autonomous driving control device 100 is an example of a "vehicle control device."

[0030] The camera 10 is, for example, a digital camera that utilizes a solid-state imaging element such as a CCD (Charge Coupled Device) or a CMOS (Complementary Metal Oxide Semiconductor). The camera 10 is installed at any location of the vehicle M equipped with the vehicle system 1. When photographing the front, the camera 10 is installed at the top of the front windshield, the back of the rearview mirror inside the vehicle, the front head of the vehicle body, etc. When photographing the rear, the camera 10 is installed at the top of the rear windshield, the tailgate, etc. When photographing the side, the camera 10 is installed at the rearview mirror on the door, etc. The camera 10, for example, periodically and repeatedly photographs the surroundings of the vehicle M. The camera 10 may also be a stereo camera.

[0031] The radar device 12 radiates radio waves, such as millimeter waves, around the vehicle M and detects the radio waves (reflected waves) reflected by surrounding objects to detect at least the object's position (range and direction). The radar device 12 can be mounted anywhere on the vehicle M. The radar device 12 can also detect the position and velocity of objects using the FM-CW (Frequency Modulated Continuous Wave) method.

[0032] The LIDAR 14 irradiates light around the vehicle M and measures the scattered light. The LIDAR 14 detects the distance to an object based on the time between light emission and light reception. The irradiated light is, for example, pulsed laser light. The LIDAR 14 is mounted at any location on the vehicle M.

[0033] 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 identify the position, type, speed, and other aspects of the object. The object recognition device 16 outputs the recognition results to the automatic driving control device 100. The object recognition device 16 can directly output the detection results from the camera 10, radar device 12, and LIDAR 14 to the automatic driving control device 100. In this case, the object recognition device 16 can be omitted from the configuration of the vehicle system 1 (detection device DD).

[0034] The communication device 20 utilizes a network such as a cellular network, a Wi-Fi network, Bluetooth (registered trademark), DSRC (Dedicated Short Range Communication), a LAN (Local Area Network), a WAN (Wide Area Network), or the Internet to communicate with, for example, other vehicles located around the vehicle M, terminal devices of users of the vehicle M, or various server devices.

[0035] The HMI 30 outputs various information to the occupants of the vehicle M and receives input operations from the occupants. The HMI 30 includes, for example, various display devices, speakers, buzzers, touch panels, switches, buttons, microphones, and the like.

[0036] The vehicle sensors 40 include a speed sensor for detecting the speed of the host vehicle M, an acceleration sensor for detecting acceleration, a yaw rate sensor for detecting yaw rate (for example, the angular velocity of rotation about a vertical axis passing through the center of gravity of the host vehicle M), and an azimuth sensor for detecting the orientation of the host vehicle M. The vehicle sensors 40 may also include, for example, a tilt angle sensor for detecting the inclination (tilt angle) of the host vehicle M based on gravity or the like. The vehicle sensors 40 may also include a position sensor for detecting the vehicle's position. A position sensor is an example of a "position measurement unit." For example, a position sensor acquires position information (longitude and latitude) from a GPS (Global Positioning System) device. Alternatively, the position sensor may acquire position information using a GNSS (Global Navigation Satellite System) receiver 51 of the navigation device 50. The vehicle sensors 40 may also derive the speed of the host vehicle M based on the difference (i.e., distance) in position information collected by the position sensor over a predetermined period of time. The detection results of the vehicle sensors 40 are output to the automatic driving control device 100.

[0037] 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 flash memory. The GNSS receiver 51 determines the position of the vehicle M based on signals received from GNSS satellites. The position of the vehicle M can also be determined or supplemented by an INS (Inertial Navigation System) utilizing the output of the vehicle sensors 40. The navigation HMI 52 includes a display, speakers, a touch panel, keys, etc. The GNSS receiver 51 can also be provided with the vehicle sensors 40. The navigation HMI 52 can also partially or entirely be shared with the HMI 30 described above. The route determination unit 53, for example, refers to the first map information 54 to determine a route (hereinafter referred to as a "mapped route") from the position of the vehicle M determined by the GNSS receiver 51 (or an input arbitrary position) to a destination input by the occupant using the navigation HMI 52. The first map information 54 is information representing the road shape, for example, by representing road links 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 also provide route guidance using the navigation HMI 52 based on the route on the map. The navigation device 50 may also transmit the current location 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.

[0038] The MPU 60 includes, for example, a recommended lane determination unit 61, which stores second map information 62 in a storage device such as a HDD or flash memory. The recommended lane determination unit 61 divides the route on the map provided by the navigation device 50 into multiple blocks (for example, every 100 meters in the vehicle's 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 the lane to travel on from the left. If the route on the map branches, the recommended lane determination unit 61 determines a recommended lane so that the vehicle M can travel on a reasonable route to the branch destination.

[0039] 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, the type and shape of road dividing lines (hereinafter referred to as dividing lines), information on lane centers, and road boundary information. The second map information 62 may also include information on whether a road boundary includes a structure that a vehicle cannot pass through (including crossing over or contacting). Structures include, for example, guardrails, curbs, medians, and fences. Impassable structures may also include low steps that are passable if the vehicle is allowed to vibrate in a way that would normally be impossible. The second map information 62 may include road shape information, traffic restriction information, address information (address, postal code), facility information, parking information, and telephone number information. Road shape information includes, for example, the curvature (also referred to as curvature radius, hereinafter the same), width, and slope of the road. The second map information 62 can be updated at any time by communicating with an external device via the communication device 20. The first map information 54 and the second map information 62 may also be provided as a single piece of map information. The map information may also be stored in the storage unit 190 .

[0040] The driving operating parts 80 include, for example, a steering wheel, an accelerator pedal, and a brake pedal. The driving operating parts 80 may also include a shift lever, a special-shaped steering gear, a joystick, and other operating parts. Each operating part of the driving operating parts 80 is equipped with, for example, an operation detection unit that detects the amount of operation of the operating part by the occupant or the presence or absence of operation. The operation detection unit detects, for example, the steering angle of the steering wheel, the steering torque, the amount of depression of the accelerator pedal and the brake pedal. In addition, the operation detection unit outputs the detection results to the automatic driving control device 100, and one or both of the driving force output device 200, the braking device 210, and the steering device 220.

[0041] The automatic driving control device 100 performs various driving controls related to automatic driving on 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 implemented by a hardware processor, such as a CPU (Central Processing Unit), executing a program (software). Some or all of these components may be implemented using 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 a System on Chip (SOC), or through a combination of software and hardware. The above-mentioned program can be pre-stored in a storage device such as an HDD, a flash memory, or the like of the automatic driving control device 100 (a storage device having a non-temporary storage medium), or can be stored in a removable storage medium such as a DVD, a CD-ROM, or a memory card, and installed in the storage device of the automatic driving control device 100 by assembling the storage medium (non-temporary storage medium) in a drive device, a card slot, or the like.

[0042] The storage unit 190 may be implemented by any of the aforementioned storage devices, or by an EEPROM (Electrically Erasable Programmable Read Only Memory), a ROM (Read Only Memory), or a RAM (Random Access Memory). For example, the storage unit 190 stores various information and programs according to the embodiments. The storage unit 190 may also store map information (e.g., the first map information 54 and the second map information 62).

[0043] Figure 2This is a functional structure diagram of the first control unit 120 and the second control unit 160. The first control unit 120 includes, for example, an identification unit 130 and an action plan generation unit 140. The first control unit 120 implements, for example, functions based on AI (Artificial Intelligence) and functions based on a pre-given model in parallel. For example, the function of "identifying intersections" can be achieved by performing, in parallel, identification of intersections based on deep learning, etc., and identification based on pre-given conditions (the presence of signals, road signs, etc. that can be pattern-matched), and comprehensively evaluating both by scoring them. In this way, the reliability of autonomous driving is ensured. The first control unit 120 performs control related to autonomous driving of the vehicle M, for example, based on instructions from the MPU 60, the HMI control unit 180, etc.

[0044] The recognition unit 130 identifies the surrounding conditions of the host vehicle M based on the recognition results of the detection device DD (information input from the camera 10, radar device 12, and LIDAR 14 via the object recognition device 16). For example, the recognition unit 130 identifies the position, velocity, acceleration, and other conditions of objects surrounding the host vehicle M (within a predetermined distance). Examples of such objects include other vehicles (surrounding vehicles), road users (pedestrians, bicycles, etc.), road structures, and other surrounding obstacles. Examples of such road structures include road signs, traffic signals, railway crossings, curbs, medians, guardrails, and fences. The position of an object is identified, for example, as an absolute coordinate system with a representative point (such as the center of gravity or the center of the drive shaft) of the host vehicle M as the origin, and used for control purposes. The position of an object can also be represented by a representative point such as the center of gravity or a corner, or by a displayed area. The so-called "state" of an object, for example, when the object is a moving object such as another vehicle, may also include the acceleration, jerk, or "action state" of the moving object (for example, whether the other vehicle is or is about to change lanes).

[0045] The recognition unit 130 includes, for example, a first recognition unit 132 and a second recognition unit 134. Details of their functions will be described later.

[0046] The action plan generation unit 140 generates an action plan for autonomous driving of the host vehicle M based on, for example, the recognition results from the recognition unit 130. For example, the action plan generation unit 140 generates a target trajectory for the host vehicle M to automatically (independent of driver control) travel in the future, in a manner that allows the host vehicle M to travel in the recommended lane determined by the recommended lane determination unit 61 and, based on the recognition results from the recognition unit 130 and the surrounding road shape derived from the current position of the host vehicle M obtained from map information, adapts to the surrounding conditions of the host vehicle M. The target trajectory includes, for example, a speed element. For example, the target trajectory is represented by a sequence of locations (track points) that the host vehicle M should reach. Track points are locations that the host vehicle M should reach at predetermined distances (e.g., several meters) along the route. Separately, target speeds and target accelerations are generated as part of the target trajectory at predetermined sampling times (e.g., a few tenths of a second). Alternatively, track points may be locations that the host vehicle M should reach at the specified sampling times. In this case, information on the target speed and target acceleration is expressed by the intervals between track points.

[0047] When generating the target trajectory, the action plan generation unit 140 may set events for autonomous driving. Examples of these events include a constant speed driving event that causes the host vehicle M to travel in the same lane at a constant speed; a following driving event that causes the host vehicle M to follow another vehicle that is within a predetermined distance (e.g., within 100 meters) ahead of the host vehicle M and is closest to the host vehicle M; a lane change event that causes the host vehicle M to change lanes from its own lane to an adjacent lane; a diverging event that causes the host vehicle M to diverge into the lane closer to the destination at a road divergence point; a merging event that causes the host vehicle M to merge onto the main road at a merging point; and a takeover event that terminates autonomous driving and switches to manual driving. Examples of these events include an overtaking event that causes the host vehicle M to temporarily change lanes to an adjacent lane, overtake a preceding vehicle in the adjacent lane, and then change lanes back to its original lane; and an avoidance event that causes the host vehicle M to at least brake or steer to avoid an obstacle ahead of the host vehicle M.

[0048] For example, the action plan generation unit 140 can change an event already determined for the current section to another event, or set a new event for the current section, based on the surrounding conditions of the vehicle M detected during travel. The action plan generation unit 140 can also change an event already determined for the current section to another event, or set a new event for the current section, based on an occupant's operation of the HMI 30. The action plan generation unit 140 generates a target trajectory corresponding to the set event.

[0049] The action plan generation unit 140 includes, for example, a determination unit 142 and an execution control unit 144. Details of their functions will be described later. For example, the recognition unit 130 and the determination unit 142 are examples of "determination means." The execution control unit 144 and the second control unit 160 are examples of "driving control units."

[0050] The second control unit 160 controls the travel 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 generating unit 140 at a predetermined timing.

[0051] 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 point) 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 braking device 210 based on the speed element associated with the target trajectory stored in the memory. The steering control unit 166 controls the steering device 220 based on the degree of curvature of the target trajectory stored in the memory. The processing of the speed control unit 164 and the steering control unit 166 is implemented, for example, by a combination of feedforward control and feedback control. As an example, the steering control unit 166 performs a combination of feedforward control corresponding to the curvature of the road ahead of the vehicle M and feedback control based on the deviation from the target trajectory.

[0052] return Figure 1 The HMI control unit 180 notifies the occupants of specified information via the HMI 30. Examples of the specified information include information related to the status of the vehicle M, information related to driving control, and other information related to the driving of the vehicle M. Examples of information related to the status of the vehicle M include the speed, engine speed, and gear position of the vehicle M. Examples of information related to driving control include information regarding the execution of driving control based on autonomous driving, information inquiring whether to start autonomous driving, information regarding the status of driving control based on autonomous driving, information regarding the automation level, and information prompting the occupants to drive when switching from autonomous driving to manual driving. The specified information may also include information unrelated to the driving of the vehicle M, such as television programs and items stored on storage media such as DVDs (e.g., movies). Examples of the specified information include information related to the current location, destination, and fuel level of the vehicle M during autonomous driving. The HMI control unit 180 may also output information received by the HMI 30 to the communication device 20, the navigation device 50, the first control unit 120, and other devices.

[0053] The HMI control unit 180 may also cause the HMI 30 to output information to be inquired of the occupant, processing results processed by the first control unit 120 and the second control unit 160, etc. The HMI control unit 180 may also transmit various information output to the HMI 30 to a terminal device used by a user of the vehicle M via the communication device 20.

[0054] The driving force output device 200 outputs the driving force (torque) used to propel the vehicle to the drive wheels. The driving force output device 200 includes, for example, a combination of an internal combustion engine, an electric motor, and a transmission, as well as an ECU (Electronic Control Unit) that controls them. The ECU controls the aforementioned components based on information input from the second control unit 160 or from the accelerator pedal of the driving control element 80.

[0055] Braking device 210 includes, for example, a brake caliper, a hydraulic cylinder that transmits hydraulic pressure to the caliper, an electric motor that generates hydraulic pressure in the hydraulic cylinder, and a brake ECU. The brake ECU controls the electric motor based on information input from the second control unit 160 or information input from the brake pedal of the driver's operating element 80, thereby outputting a braking torque corresponding to the braking operation to each wheel. Braking device 210 may include a backup mechanism for transmitting the hydraulic pressure generated by operating the brake pedal to the hydraulic cylinder via a master hydraulic cylinder. Braking device 210 is not limited to the structure described above and may also be an electronically controlled hydraulic braking device that controls an actuator based on information input from the second control unit 160 to transmit the hydraulic pressure from the master hydraulic cylinder to the hydraulic cylinder.

[0056] The steering system 220 includes, for example, a steering ECU and an electric motor. The electric motor applies force to, for example, a rack-and-pinion mechanism to change the direction of the steering wheel. The steering ECU drives the electric motor based on information input from the second control unit 160 or information input from the steering wheel of the driving control unit 80 to change the direction of the steering wheel.

[0057] [Identification Department and Action Plan Generation Department]

[0058] Next, the functions of recognition unit 130 (first recognition unit 132 and second recognition unit 134) and action plan generation unit 140 (determination unit 142 and execution control unit 144) will be described in detail. The following description focuses on the determination process in this embodiment and the driving control (travel control) based on the determination results, divided into several scenarios.

[0059] [Scene 1]

[0060] Figure 3 : is a diagram for explaining the determination process and driving control in the first scenario. Figure 3In the example shown, the dividing lines CL1 and CL2 recognized by the detection device DD, the dividing lines ML1 to ML3 obtained from the map information (for example, the second map information 62) based on the position information of the vehicle M, and the dividing lines RL1 to RL5 actually drawn on the road are shown. In the map information, lane L1 is divided by the dividing lines ML1 and ML2, and lane L2 is divided by the dividing lines ML2 and ML3. Lanes L1 and L2 are lanes that can travel in the same direction (the X-axis direction in the figure). Figure 3 In the example of , the dividing lines CL1 to CL2 are examples of “first dividing lines”, and the dividing lines ML1 to ML3 are examples of “second dividing lines”. Figure 3 In the example of FIG, the host vehicle M is traveling in the lane L1 at a speed VM.

[0061] In the first scenario, there are other vehicles m1 and m2 around the vehicle M. Figure 3 In the example, another vehicle m1 is traveling at a speed Vm1 in front of the vehicle M, and another vehicle m2 is traveling at a speed Vm2 in front of the vehicle M (other vehicle m1). Figure 3 In the figure, a road construction site is located in lane L1, and temporary dividing lines RL4 and RL5 are drawn to allow vehicles to avoid entering the restricted area AR1 containing the construction site. During the construction, a vehicle traveling in lane L1 can avoid entering the restricted area AR1 by traveling in the area defined by dividing lines RL4 and RL5 and moving toward lane L2.

[0062] 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 of the host vehicle M. For example, the first recognition unit 132 recognizes the left and right dividing lines CL1 and CL2 that divide the lane (lane L1) in which the host vehicle M is traveling based on an image captured by the camera 10 (hereinafter referred to as a camera image). The first recognition unit 132 may also recognize the dividing line that divides an adjacent lane (lane L2) adjacent to the driving lane. Hereinafter, the dividing lines CL1 and CL2 may be referred to as "camera dividing lines CL1 and CL2."

[0063] For example, the first recognition unit 132 analyzes the camera image and extracts edge points with large brightness differences between adjacent pixels in the image. The edge points are connected to identify the camera dividing lines CL1 and CL2 in the image plane. The first recognition unit 132 transforms the positions of the camera dividing lines CL1 and CL2 based on the position of the representative point of the host vehicle M into the vehicle coordinate system (for example, Figure 3The first recognition unit 132 may also recognize the curvature or curvature change of each camera dividing line CL1 or CL2. The curvature change refers to, for example, the time rate of change of the curvature of the camera dividing lines CL1 or CL2 at a distance X [m] ahead, as viewed from the vehicle M, as recognized by the camera 10. The first recognition unit 132 may also recognize the curvature or curvature change of the lane divided by the camera dividing lines CL1 or CL2 by averaging the curvature or curvature change of each camera dividing line CL1 or CL2. The camera dividing lines CL1 and CL2 may be recognized or corrected based on the output of a detection device other than the camera 10.

[0064] The first recognition unit 132 recognizes each of the left and right camera dividing lines of the vehicle M, when at least one of the single-side camera dividing lines exists in plurality due to branching (forking) or the like. Figure 3 In the example, multiple camera dividing lines CL2a and CL2b are identified along the way for camera dividing line CL2 on the right side of the vehicle M. Camera dividing line CL2a is an example of a "first single-side first dividing line" or a "first single-side camera dividing line," and dividing line CL2b is an example of a "second single-side first dividing line" or a "second single-side camera dividing line." The first recognition unit 132 recognizes construction sites, prohibited driving areas AR1, obstacles, and the like in the direction of travel.

[0065] The first recognition unit 132 identifies other vehicles that are around the vehicle M (within a specified distance). For example, the first recognition unit 132 identifies other vehicles m1 and m2 that are in front of the vehicle M based on the output of the detection device DD that detects the surrounding conditions of the vehicle M. The first recognition unit 132 recognizes the position (relative position with respect to the vehicle M) and speed (relative speed with respect to the vehicle M) of each of the other vehicles m1 and m2. The first recognition unit 132 can also recognize the driving position information of the other vehicles m1 and m2. Driving position information refers to, for example, driving trajectories K1 and K2 based on the positions of representative points of each of the other vehicles m1 and m2 at a specified time. The driving position information may include, for example, information related to the predicted future driving trajectory of the other vehicles m1 and m2 based on the driving trajectories K1 and K2 and the directions of the other vehicles m1 and m2.

[0066] The second recognition unit 134 identifies lane dividing lines around the vehicle M (within a predetermined distance) from map information, based on the position of the vehicle M detected by the vehicle sensor 40 and the GNSS receiver 51. For example, the second recognition unit 134 references the map information based on the position information of the vehicle M and identifies lane dividing lines ML1-ML3 that are located in the direction in which the vehicle M is traveling or in which the vehicle M can travel. Hereinafter, the lane dividing lines ML1-ML3 may be referred to as "map lane dividing lines ML1-ML3."

[0067] The second recognition unit 134 may also recognize the map dividing lines ML1 and ML2 as the lines that divide the lane L1 in which the host vehicle M is traveling, among the recognized map dividing lines ML1 to ML3. The second recognition unit 134 may recognize the curvature or curvature change of each of the map dividing lines ML1 to ML3 based on the map information. The second recognition unit 134 may also average the curvature or curvature change of each of the map dividing lines ML1 to ML3 to recognize the curvature or curvature change of each lane L1 or L2 divided by the map dividing lines.

[0068] The determination unit 142 determines whether at least one of the camera dividing lines CL (CL1, CL2) and the map dividing lines ML (ML1-ML3) is correct, based on, for example, at least one of the camera dividing lines CL and the map dividing lines ML, as well as the travel trajectories K1 and K2 of other vehicles m1 and m2. Based on the determination result determined by the determination unit 142, the execution control unit 144 generates a target trajectory for driving control by controlling one or both of the steering and speed of the host vehicle M so that the host vehicle M travels along the dividing line determined to be correct, generates a target trajectory for driving control to avoid contact with an obstacle, or terminates driving control (or does not initiate driving control) if both dividing lines are determined to be incorrect.

[0069] exist Figure 3 In the example, the determination unit 142 first determines whether the camera dividing lines CL (CL1, CL2) recognized by the first recognition unit 132 and the map dividing lines ML (ML1, ML2) recognized by the second recognition unit 134 match each other. For example, the determination unit 142 derives the degree of match between the dividing lines CL1, which are located closest to the left side when viewed from the vehicle M, and ML1, and the degree of match between the dividing lines CL2, which are located closest to the right side when viewed from the vehicle M, and ML2. The determination unit 142 then determines that the camera dividing line CL and the map dividing line ML match each other if the derived degree of match is greater than a threshold value, and determines that they do not match each other if the degree of match is less than the threshold value. This match determination is repeated at a predetermined timing or periodically.

[0070] For example, the determination unit 142 overlaps the camera dividing lines CL1 and CL2 and overlaps the map dividing lines ML1 and ML2 on the plane of the vehicle coordinate system (XY plane) with the position of the representative point of the vehicle M as a reference. Furthermore, the determination unit 142 determines the degree of fit of the dividing lines of the comparison object (dividing lines CL1 and ML1, dividing lines CL2 and ML2). The degree of fit refers to, for example, an index value related to the offset of the lateral position (for example, the Y-axis direction in the figure), and the smaller the offset, the greater the degree of fit. The degree of fit corresponding to the offset can also be derived, for example, by a prescribed function with the offset as input and the degree of fit as output, or can be derived using a table that establishes a correspondence between the offset and the degree of fit. Figure 3 In the example, the degree of coincidence corresponding to the offset D1 of the lateral position between the dividing line CL1 and ML1 and the offset D2 of the lateral position between the dividing line CL2 and ML2 can also be derived, or the degree of coincidence can be derived based on the average, maximum or minimum value of the offsets D1 and D2. Figure 3 As shown, regarding the portion where a plurality of camera dividing lines CL2 exist on one side, the degree of agreement between each of the camera dividing lines CL2a and CL2b and the map dividing line ML2 is derived.

[0071] The degree of fit may be, for example, an index value related to the angle (deviation angle) formed by the two dividing lines of the comparison object instead of (or in addition to) the above-mentioned lateral position offset. In this case, the smaller the deviation angle, the greater the degree of fit. Figure 3 In the example, the degree of fit can be derived based on the deviation angle between the dividing line CL1 and ML1, and the deviation angle between the dividing line CL2 (CL2a, CL2b) and ML2, or based on the average, maximum or minimum value of each angle.

[0072] The degree of fit may also be determined by (or in addition to) the difference in curvature variation between the dividing lines, instead of (or in addition to) the aforementioned lateral position offset or dividing line deviation angle. In this case, the smaller the difference in curvature variation, the greater the degree of fit. The curvature variation is primarily used when the lane is curved. The determination unit 142 may derive the degree of fit based on the average of the difference in curvature variation between the dividing lines CL1 and ML1 and the difference in curvature variation between the dividing lines CL2 (CL2a, CL2b) and ML2, or based on the maximum or minimum value of these differences. The determination unit 142 may also derive the degree of fit based on the difference between the average of the curvature variation between the dividing lines CL1 and CL2 and the average of the curvature variation between the dividing lines ML1 and ML2, or based on the difference between the curvature variation of the lane (lane L1) identified from the camera image and the curvature variation of lane L1 identified from map information. The degree of matching corresponding to the difference in the deviation angle or curvature change amount can be derived using a predetermined function, a correspondence table, or the like, similarly to the offset amount.

[0073] For example, if the recognition accuracy of camera dividing lines CL1, CL2 (CL2a, CL2b) identified by the first recognition unit 132 is lower than a threshold, or if the camera dividing line CL cannot be recognized, the determination unit 142 may derive the degree of agreement using the angles formed between the driving trajectories K1, K2 of other vehicles m1, m2 traveling nearby and the map dividing line ML. The determination unit 142 may also set an imaginary dividing line parallel to the driving trajectories K1, K2 and derive the degree of agreement between the set imaginary dividing line and the map dividing line ML. The determination unit 142 may also perform an agreement determination with the dividing line obtained using the driving trajectories K1, K2, regardless of the recognition result of the camera dividing line CL. Similarly, if the camera dividing line CL is recognized but the surrounding map dividing lines ML cannot be recognized based on the map information, the determination unit 142 may perform an agreement determination between the camera dividing line CL and the driving trajectories K1, K2, and use the agreement result to determine whether the camera dividing line CL is correct. The determination unit 142 may determine whether the camera dividing line CL and the driving trajectories K1 and K2 match, regardless of the recognition result of the map dividing line ML.

[0074] If the camera dividing line CL and the map dividing line ML are determined to be consistent through the above-described consistency determination using the degree of consistency, the determination unit 142 determines that the camera dividing line CL and the map dividing line ML are correct dividing lines in the correct / incorrect determination. Alternatively, if the camera dividing line CL and the map dividing line ML are determined to be inconsistent, the determination unit 142 may determine that at least one of the camera dividing line CL and the map dividing line ML is incorrect. For example, if the camera dividing line CL and the map dividing line ML are inconsistent and the vehicle M is performing driving control to avoid a forward obstacle, the determination unit 142 may determine that the camera dividing line CL is incorrect (or that the map dividing line ML is correct).

[0075] The determination unit 142 may determine that the camera dividing line CL is incorrect (or that the map dividing line ML is correct) if the camera dividing line CL does not coincide with the map dividing line ML, and a predetermined number or more of the recognized driving trajectories of multiple other vehicles are driving trajectories along the map dividing line ML (including a predetermined allowable range). The determination unit 142 may determine that the map dividing line ML is incorrect (or that the camera dividing line CL is correct) if the camera dividing line CL does not coincide with the map dividing line ML, and a predetermined number or more of the recognized driving trajectories of multiple other vehicles are driving trajectories along the camera dividing line CL (including a predetermined allowable range). For example, the determination unit 142 may determine that the camera dividing line and the map dividing line are incorrect if the degree of coincidence is smaller than a lower limit value that is smaller than a threshold value.

[0076] Here, for example, if the first recognition unit 132 recognizes multiple unilateral camera dividing lines among the left and right camera dividing lines CL1 and CL2 of the vehicle M's driving lane L1, and a first unilateral camera dividing line included in the recognized unilateral camera dividing lines matches the map dividing line ML and satisfies predetermined conditions, the determination unit 142 reduces the reliability of the matching information between the matching first unilateral camera dividing line and the second unilateral camera dividing line. Matching information refers to, for example, the degree of matching, and reducing the reliability means, for example, reducing the degree of matching. Matching information may also refer to the result of a determination of whether a dividing line is correct.

[0077] exist Figure 3In the example, one of the camera dividing lines CL1 and CL2 is identified as a single-sided camera dividing line CL2 that branches into two. Furthermore, among the multiple identified camera dividing lines CL2a and CL2b, camera dividing line CL2a, which is the first single-sided camera dividing line, coincides with map dividing line ML2 (the degree of coincidence is greater than a threshold value). In this case, if the predetermined conditions are further satisfied, the determination unit 142 reduces the degree of coincidence between camera dividing line CL2a and map dividing line ML2, making it less likely that map dividing line ML2 is the correct dividing line. The determination unit 142 may also reduce the reliability of the correct / false determination result. If the reliability of the determination result is reduced, the determination unit 142 will not determine that map dividing line ML2 is the correct dividing line.

[0078] The specified condition is, for example, that other vehicles m1 and m2 traveling ahead of the host vehicle M pass over the map dividing line ML2 (or camera dividing line CL2a) that has been determined to match. "Passing" means that a specified position (e.g., center, center of gravity, front end) or the entire body of the other vehicles m1 and m2 passes over (or straddles) the map dividing line ML2 and moves to another lane (an adjacent lane). Whether or not the vehicles have passed over the map dividing line ML2 can be determined based on the behavior of the other vehicles m1 and m2, or based on their driving trajectories K1 and K2. In this way, if the other vehicles m1 and m2 pass over the dividing line that has been determined to match, there is a high probability that the path along the dividing line is not the correct path, thus reducing the reliability of the matching information and preventing misjudgments of the dividing line or road shape.

[0079] The aforementioned prescribed conditions may also include the requirement that a specified number or more other vehicles traveling ahead of the host vehicle M pass along the map dividing line ML2 (or along the camera dividing line CL2a). For example, if only one other vehicle passes along the map dividing line ML2, that other vehicle may have changed lanes from lane L1 to lane L2. Therefore, including the requirement that two or more other vehicles pass along the map dividing line or road shape allows for more accurate determination of the dividing line or road shape. The aforementioned prescribed conditions may also include the requirement that all other vehicles traveling ahead of the host vehicle M in the lane (lane L1) that the host vehicle M is traveling in pass along the map dividing line ML2 (or along the camera dividing line CL2a).

[0080] The prescribed conditions may include, for example, the vehicle M traveling within a prescribed distance from a construction site (or a prohibited driving area AR1 including the construction site). The so-called construction site may be a construction site during construction or a construction site after construction (where construction was carried out in the past (before a prescribed time). Whether construction is in progress is determined, for example, based on road signs, signboards, construction vehicles, construction workers, and physical boundaries of the road described later that are identified by the first recognition unit 132. Whether construction was carried out in the past is determined, for example, by obtaining surrounding construction history based on the position information of the vehicle M from a server that manages construction history via the communication device 20. During the prescribed period during or after construction, there is a high possibility that a temporarily drawn dividing line remains in the road environment. Therefore, by reducing the reliability of the matching information in this case, it is possible to suppress erroneous determination of the dividing line (the road shape obtained based on the dividing line).

[0081] For example, the execution control unit 144 may also execute driving control to make the vehicle M travel along the single-side camera dividing line when the above-mentioned conditions are met and the reliability of the matching information is reduced, and when there is a single-side camera dividing line among the multiple identified single-side camera dividing lines that does not match the map dividing line. Figure 3 In the example shown in FIG. 2 , camera dividing line CL2b, the second of the multiple recognized single-side camera dividing lines CL2a and CL2b, does not coincide with any of the map dividing lines ML1 to ML3. Therefore, the execution control unit 144 generates a target trajectory for the host vehicle M along camera dividing line CL2b in the section where camera dividing line CL2 branches, and then drives the host vehicle M along the generated target trajectory. Since camera dividing line CL2b is likely a new dividing line drawn due to construction, driving control of the host vehicle M using autonomous driving can be continued by driving the host vehicle M along it.

[0082] Thus, according to the first scenario, even when construction-related information (road information during or after construction) is not reflected in the map information, for example, it is possible to prevent misjudgments regarding dividing lines (road shape based on dividing lines). This prevents driving along incorrect routes, thereby suppressing automatic braking and the switching control from automatic to manual driving, allowing driving control to continue.

[0083] [Scene 2]

[0084] Figure 4 : is a diagram for explaining the determination process and driving control in the second scenario. Figure 4 In the example, with Figure 3The difference from the first scene shown is that there are no other vehicles around the vehicle M, and there is a physical road boundary RPB. The physical road boundary RPB refers to a boundary for demarcating the driving path that is different from the dividing line drawn in advance on the road, for example, by an object OB (e.g., a fence, a safety fence, a roadblock, a road cone (pylon, a registered trademark)) set on the road. The physical road boundary RPB is set, for example, to prevent vehicles from entering a driving-restricted area. There may be multiple objects OB, or multiple objects OB may be arranged or connected. Figure 4 In the example, as viewed from the host vehicle M, a physical road boundary RPB1 exists along dividing line RL1 up to point P1, a physical road boundary RPB2 exists along dividing line RL4 from point P1 to point P2, and a physical road boundary RPB3 exists along dividing line RL2 after point P2. Physical road boundaries RPB1 to RPB3 may be connected or integrated physical boundaries.

[0085] In the second scenario as well, when the first recognition unit 132 recognizes multiple single-sided camera dividing lines among the camera dividing lines CL1 and CL2 on the left and right sides of the driving lane L1 of the host vehicle M, and the first single-sided camera dividing line included in the recognized multiple single-sided camera dividing lines matches the map dividing line ML and satisfies the prescribed conditions, the determination unit 142 reduces the reliability of the matching information of the matching first single-sided camera dividing line and the second dividing line. Here, the prescribed conditions in the second scenario are, for example, the existence of a road physical boundary RPB (RPB1 to RPB3) in the traveling direction of the host vehicle M. For example, Figure 4 As shown by the physical road boundary RPB2, there is a high probability that at least a portion of the physical road boundary RPB does not lie along the map dividing lines ML1 to ML3 registered in the map information. Therefore, the physical road boundary RPB does not coincide with the map dividing lines (or the degree of coincidence with the map dividing lines is low). Therefore, the determination unit 142 includes the presence of the physical road boundary RPB in the direction of travel of the host vehicle M as a predetermined condition, thereby preventing erroneous determinations regarding the dividing lines (based on the road shape at the dividing lines).

[0086] In the second scenario, the execution control unit 144 may also execute driving control to cause the host vehicle M to travel along the physical road boundary RPB when there is a physical road boundary RPB extending in a direction different from the extending direction of the aligned camera dividing line CL2a and the map dividing line ML2 by a predetermined angle or more. Figure 4In the example, the physical road boundary RPB2 extends in a direction that differs by a predetermined angle or more relative to the extending directions of the aligned camera dividing line CL2a and map dividing line ML2. In this case, the execution control unit 144 generates a target trajectory K11 in the section between points P1 and P2 where the physical road boundary RPB2 exists, such that the host vehicle M travels along the physical road boundary RPB2, and then causes the host vehicle M to travel along the generated target trajectory K11.

[0087] In this way, according to the second scenario, it is judged that the configuration direction of the road physical boundary RPB is a direction that can avoid entering a driving prohibited area including a construction site, and the vehicle travels along the road physical boundary RPB, thereby suppressing the misjudgment of the dividing line (based on the road shape of the dividing line) and enabling driving control to continue.

[0088] The determination unit 142 may also determine the correctness of the camera dividing line CL based on the road physical boundary RPB. In this case, for example, if the determination unit 142 recognizes multiple single-sided camera dividing lines and one of them (for example, a camera dividing line that does not coincide with the map dividing line) extends along the extension direction of the road physical boundary RPB (or parallel to the extension direction of the road physical boundary RPB), the determination unit 142 determines that the camera dividing line is the correct dividing line. Figure 4 In the example, the camera dividing line CL2b, which is the second unilateral camera dividing line and does not coincide with the map dividing line, extends along the extension direction of the road physical boundary RPB2, so the determination unit 142 determines that the camera dividing line CL2b is the correct dividing line.

[0089] If the camera dividing line CL2b is determined to be the correct dividing line, the execution control unit 144 generates a target trajectory for the host vehicle M to travel along the camera dividing line CL2b, and then causes the host vehicle M to travel along the generated target trajectory. As described above, when traveling along the physical road boundary RPB, the host vehicle M must travel at a predetermined distance from the physical road boundary RPB to avoid contact with the physical road boundary RPB. However, even if the camera dividing line CL2b contacts the host vehicle M (for example, even if the host vehicle M travels on the camera dividing line CL2b), there is no significant impact. Therefore, by generating the target trajectory K12 for causing the host vehicle M to travel along the camera dividing line CL2b, the execution control unit 144 can generate the target trajectory K12 at a position farther from the physical road boundary RPB2 than the target trajectory K11, thereby enabling safer travel of the host vehicle M.

[0090] If the distance between camera dividing line CL2b and the physical road boundary RPB2 is close (less than a predetermined distance), the execution control unit 144 may adjust the position of camera dividing line CL2b and then perform driving control to cause the host vehicle M to travel along camera dividing line CL2b. In this case, the execution control unit 144 adjusts the position of camera dividing line CL2b so that the distance between camera dividing line CL2b and the physical road boundary RPB2 is greater than a predetermined distance. The predetermined distance is, for example, the distance at which the physical road boundary RPB2 and the host vehicle M will not come into contact even if a predetermined position of the host vehicle M (e.g., the right side of the face, the center, or the center of gravity) is on camera dividing line CL2b (this distance may also include a predetermined safety factor). The predetermined distance may be a fixed distance or may be set to be variable based on the width of the host vehicle M or the width of the lane L1.

[0091] In this manner, even when the camera dividing line CL2b is close to the physical road boundary RPB2, by adjusting the position of the camera dividing line CL2b, a target trajectory K12 can be generated that avoids contact with the physical road boundary RPB2, thereby allowing the host vehicle M to travel. Furthermore, since travel can be performed at a distance from the physical road boundary RPB2, the anxiety of the occupants of the host vehicle M about the possibility of contact with the physical road boundary RPB2 can be suppressed.

[0092] Instead of generating a target trajectory based on camera dividing line CL2b as described above, the execution control unit 144 may generate a target trajectory based on camera dividing line CL1 and cause the host vehicle M to travel along the generated target trajectory. In this case, the execution control unit 144 generates the target trajectory using, for example, a portion of camera dividing line CL1 that deviates from and does not align with map dividing line ML1 but that lies along the physical road boundary RPB2. This allows the host vehicle M to be adjusted so that it travels reliably away from the physical road boundary RPB2. Thus, in this embodiment, the target trajectory can be generated at a more appropriate location (e.g., away from the physical road boundary) and caused to travel by using camera dividing line CL2b located on the same side as the one determined to be aligned, or a portion of camera dividing line CL1 located on a side not determined to be aligned (except once).

[0093] In the second scenario, when the host vehicle M is traveling on a road (lane L1) with a slope greater than a specified value, the execution control unit 144 may not execute driving control based on the physical road boundary RPB. The road slope can be obtained, for example, from the second map information 62 based on the position information of the host vehicle M, or based on the inclination (tilt angle) of the host vehicle M detected by the vehicle sensor 40. When the host vehicle M is traveling on a sloping road, the accuracy of recognizing the position, shape, size, etc. of the physical road boundary RPB (object OB) decreases compared to when traveling on a level road. Therefore, when the host vehicle M is traveling on a road with a slope greater than a specified value, the execution control unit 144 does not generate a target trajectory for causing the host vehicle M to travel along the physical road boundary RPB. This prevents the host vehicle M from executing driving control based on an incorrect target trajectory while traveling on a slope.

[0094] When the vehicle M is traveling on a road (lane L1) having a slope greater than a predetermined value, instead of not executing driving control based on the physical road boundary RPB, the correctness determination of the dividing line based on the physical road boundary RPB may be omitted.

[0095] According to the second scenario described above, even in a situation where there are no other vehicles nearby, for example, the physical road boundary RPB can be used to suppress erroneous determination of the dividing line (based on the road shape of the dividing line). A target trajectory can be generated at an appropriate position based on the physical road boundary RPB, and the host vehicle M can be caused to travel along the generated target trajectory, thereby continuing driving control.

[0096] [Scene 3]

[0097] Figure 5 : is a diagram for explaining the determination process and driving control in the third scenario. Figure 5 In the example, Figure 4 The second scenario shown is different in that there is sign information indicating the presence of a construction site in the direction of travel of the vehicle M. The sign information is, for example, a road sign RS, a notice board SB, etc. Therefore, the following description will focus on this difference.

[0098] For example, at road construction sites, etc. Figure 5As shown, before a vehicle arrives at the construction site, road signs RS1, RS2, and a signboard SB1 for notifying surrounding vehicles of information related to road construction are installed at a position closer to or near the construction site than the construction site. In the third scenario, the first recognition unit 132 recognizes the road signs RS1, RS2, and the signboard SB1 in addition to the camera dividing line CL and the road physical boundary RPB. In this case, the first recognition unit 132 can also recognize the specific content of the road signs RS1, RS2, and the signboard SB1 based on feature information such as the shape, appearance, text information, and color information of the road signs RS1, RS2, and the signboard SB1 contained in the camera image. The first recognition unit 132 can also recognize the distance to the construction site based on the type and installation location of the road signs RS1, RS2, and the signboard SB1.

[0099] In the third scenario, similar to the second scenario, if the first recognition unit 132 recognizes multiple single-side camera dividing lines among the left and right camera dividing lines CL1 and CL2 of the host vehicle M's driving lane L1, and if a first single-side camera dividing line included in the recognized multiple single-side camera dividing lines matches the map dividing line ML and satisfies a predetermined condition (a physical road boundary RPB exists in the traveling direction of the host vehicle M), the determination unit 142 reduces the reliability of the matching information between the matching first single-side camera dividing line and the second single-side camera dividing line. In this case, if the execution control unit 144 predicts the presence of a construction site within a predetermined distance in the traveling direction of the host vehicle M based on the recognition results of the road signs RS1 and RS2 and the sign SB1 recognized by the first recognition unit 132, the execution control unit 144 executes driving control to cause the host vehicle M to travel along the physical road boundary RPB.

[0100] Thus, according to the third scenario, the presence of a construction site can be more accurately determined based on surrounding sign information. Therefore, when a physical road boundary RPB exists in the direction of travel of the host vehicle M and sign information indicating a construction site is present, driving control is performed based on the physical road boundary RPB, not the camera dividing line CL or the map dividing line ML. This prioritizes the physical road boundary RPB and enables efficient driving control.

[0101] [About driving control]

[0102] Here, the driving control performed by the driving control unit will be described. The execution control unit 144 determines driving control for the host vehicle M based on the determination result of the determination unit 142 and executes the determined driving control. "Determining driving control" may include, for example, determining the content (type) of driving control and whether to execute (or suppress) the driving control. "Executing driving control" may include, for example, not only switching the content of driving control but also continuing an already executed driving control. Suppressing driving control not only includes not executing (terminating) driving control but also reducing the automation level of the driving control. The driving control executed by the execution control unit 144 may include ACC, TJP, LKAS, ALC, CMBS, and other driving controls, as well as various other driving controls for avoiding contact with surrounding vehicles. The execution control unit 144 generates a target trajectory for executing the driving control and outputs the generated target trajectory to the second control unit 160.

[0103] Here, the driving control executed by the execution control unit 144 includes at least a first driving control and a second driving control. The first driving control, for example, controls one or both of the steering and speed of the host vehicle M based on a dividing line recognized by the first recognition unit 132 or the second recognition unit 134 (e.g., a dividing line where the camera dividing line coincides with a map dividing line). For example, the first driving control controls the host vehicle M so that its representative point passes through the center of a lane defined by the dividing line. The second driving control controls one or both of the steering and speed of the host vehicle M based on a map dividing line or driving position information of other vehicles. For example, the second driving control controls the host vehicle M so that its representative point travels along a trajectory that follows the driving trajectory of the other vehicle m1.

[0104] Furthermore, the driving control may include a third driving control for prioritizing camera dividing lines over map dividing lines to execute at least steering control of the steering and speed of the host vehicle M, and a fourth driving control for prioritizing map dividing lines over camera dividing lines to execute at least steering control of the steering and speed of the host vehicle M. Prioritizing camera dividing lines over map dividing lines means, for example, that processing based on the camera dividing lines is generally performed, but processing based on the map dividing lines is temporarily switched to processing based on the map dividing lines when, for example, the recognition accuracy of the camera dividing lines falls below a threshold or the camera dividing lines cannot be recognized. Prioritizing map dividing lines over camera dividing lines means that processing based on the map dividing lines is generally performed, but processing based on the camera dividing lines is temporarily switched to processing based on the camera dividing lines when, for example, the map dividing lines cannot be identified. The third and fourth driving controls are, for example, driving controls for situations where the camera dividing lines do not match the map dividing lines (when the degree of match is less than a threshold).

[0105] Driving control may include multiple driving control levels based on automation levels (an example of the degree of automation). Automation levels include, for example, a first level, a second level with a lower degree of automation than the first level, and a third level with a lower degree of automation than the second level. Automation levels may also include a fourth level with a lower degree of automation than the third level. The automation level may be defined by standardized information, regulations, or other standards, or may be an indicator value independently set. Therefore, the types, content, and number of automation levels are not limited to the following examples. A low degree of automation in driving control means, for example, a low degree of automation in driving control and a high level of driver workload (heavy workload). A low level of automation in driving control means a low degree of control over steering or acceleration / deceleration by the automatic driving control device 100 (a high degree of driver intervention in steering or acceleration / deceleration operations). Driver workloads include, for example, monitoring the surroundings of the vehicle M and operating driving controls. Operating driving controls includes, for example, the driver's grip on the steering wheel (hereinafter referred to as "hands-on"). The tasks assigned to the driver are, for example, tasks assigned to the occupants (driver tasks) required to maintain the autonomous driving of the vehicle M. Therefore, if the occupants are unable to perform the assigned tasks, the automation level is lowered. For example, the first level of driving control may include driving controls such as ACC, ALC, LKAS, and TJP. The second or third levels of driving control may include driving controls such as ACC, ALC, and LKAS. The fourth level of driving control may include manual driving. In the fourth level of driving control, for example, driving controls such as ACC may be performed. Of the first to fourth levels, the first level of driving control has the highest degree of automation, and the fourth level of driving control has the lowest degree of automation.

[0106] In the first level, there are no tasks assigned to the occupants (the tasks assigned to the driver are the lightest). In the second level, the tasks assigned to the occupants include, for example, monitoring the surroundings of the host vehicle M (particularly the front). In the third level, the tasks assigned to the occupants include, for example, hands-on control in addition to monitoring the surroundings of the host vehicle M. In the fourth level, the tasks assigned to the occupants (e.g., the driver) include, for example, steering and speed control of the host vehicle M using the driving control elements 80 in addition to monitoring the surroundings of the host vehicle M and hands-on control. In other words, in the fourth level, the driving can be immediately handed over to the occupants, and the tasks assigned to the driver are the heaviest. The content of the driving control and the tasks assigned to the occupants in each automation level are not limited to the examples described above. The automatic driving control device 100 executes driving control at any of the first to fourth levels based on the surrounding conditions of the host vehicle M and the tasks currently being performed by the occupants. At least a portion of the first to fourth levels may be associated with, for example, the first to fourth driving control levels described above.

[0107] For example, if the determination unit 142 determines that both the camera dividing line CL and the map dividing line ML are correct (e.g., the camera dividing line CL and the map dividing line ML coincide), the execution control unit 144 generates a target trajectory for executing the first driving control. If one of the camera dividing line CL and the map dividing line ML is determined to be correct, the execution control unit 144 generates a target trajectory for executing any of the second to fourth driving controls based on the correct dividing line. Furthermore, the execution control unit 144 may also, based on the determination result, perform control such as terminating driving control of the host vehicle M and switching to manual driving by the occupant. Furthermore, the execution control unit 144 may also switch the automation level corresponding to the driving control based on the determination result. In this case, for example, if the camera dividing line CL and the map dividing line ML are determined to be correct, the first level of driving control is executed. If they are determined to be incorrect, the second to fourth levels of driving control are executed depending on the situation. In the first to third scenarios described above, the execution control unit 144 generates target trajectories corresponding to the respective determination results and executes driving control of the host vehicle M.

[0108] [Processing Flow]

[0109] The following describes the processing performed by the automatic driving control device 100 according to the embodiment. Figure 6This is a flowchart illustrating an example of processing executed by the automatic driving control device 100 according to an embodiment. The following description focuses on the driving control processing executed by the automatic driving control device 100, including the processing for suppressing erroneous determination of dividing lines. The processing described below can be repeatedly executed at predetermined timings or intervals, and can be repeatedly executed while the automatic driving control device 100 is executing automatic driving.

[0110] exist Figure 6 In the example shown in FIG. 1 , the first recognition unit 132 identifies the demarcation lines (camera demarcation lines) surrounding the vehicle M (within a predetermined distance) based on the output of the detection device DD that detects the surrounding conditions of the vehicle M (step S100). During step S100, the first recognition unit 132 may also identify other vehicles, physical road boundaries, signage, obstacles, and the like surrounding the vehicle. Next, the second recognition unit 134 references map information based on the location information of the vehicle M and identifies the demarcation lines (map demarcation lines) surrounding the vehicle M based on the map information (step S110).

[0111] Next, the determination unit 142 determines whether multiple single-side dividing lines, among the left and right camera dividing lines that divide the lane of the host vehicle M, have been recognized (step S120). If it is determined that multiple single-side dividing lines have been recognized, the determination unit 142 determines whether any one of the multiple recognized dividing lines (the first single-side camera dividing line) coincides with a map dividing line (step S130). If it is determined that they coincide (for example, the degree of coincidence is greater than a threshold), the determination unit 142 determines whether a predetermined condition is satisfied (step S140). If it is determined that the predetermined condition is satisfied, the determination unit 142 reduces the reliability of the coincidence between the first single-side camera dividing line and the map dividing line (step S150).

[0112] Next, the determination unit 142 determines whether any of the identified multiple single-side camera dividing lines (a second single-side camera dividing line) does not coincide with a map dividing line (the degree of coincidence is less than a threshold) (step S160). If the second single-side camera dividing line exists, the execution control unit 144 executes driving control to cause the host vehicle M to travel along the second single-side camera dividing line (step S170). If it is determined in step S120 that multiple single-side camera dividing lines are not identified, if it is determined in step S130 that multiple single-side camera dividing lines do not coincide with a map dividing line, if it is determined in step S140 that a predetermined condition is not met, or if it is determined in step S160 that the second single-side camera dividing line does not exist, the execution control unit 144 suppresses driving control for the host vehicle M (step S180). Suppressing driving control includes, for example, switching from the first driving control to any of the second to fourth driving controls, terminating the first driving control, not executing driving control if it is not already executed, or lowering the automation level. This ends the flowchart.

[0113] In an embodiment, it is also possible to replace Figure 6 The process of step S160 shown in the figure determines whether there is a physical road boundary in the traveling direction of the host vehicle M, and if it is determined that there is a physical road boundary, driving control is performed instead of the process of step S170 to make the host vehicle M travel along the physical road boundary.

[0114] [Variation]

[0115] For example, in the above-described embodiment, the determination unit 142 may determine the degree of deviation instead of determining the degree of alignment between the camera dividing lines (or driving trajectory) and the map dividing lines. The degree of deviation refers to an indicator value, such as the offset, deviation angle, or curvature change between the camera dividing lines and the map dividing lines, which increases with the difference. Furthermore, in the embodiment, even when there are other vehicles around (in front of) the vehicle M, the correctness of the dividing lines may be determined based on the physical road boundary and sign information, or a target trajectory for the vehicle M may be generated. In the embodiment, the determination unit 142 may determine the alignment of each camera dividing line with the map dividing line only if at least three single-sided camera dividing lines are recognized. The determination unit 142 may also determine that recognition accuracy has deteriorated and not perform the alignment determination if more than a predetermined number of single-sided camera dividing lines are recognized.

[0116] According to the above-described embodiment, the automatic driving control device 100 (an example of a vehicle control device) includes: a first recognition unit 132 for recognizing the surrounding conditions of the host vehicle M, including a camera dividing line (an example of a first dividing line) dividing the lane of the host vehicle M and other vehicles present around the host vehicle, based on the output of a detection device DD that detects the surrounding conditions of the host vehicle M; a second recognition unit 134 for recognizing a map dividing line (an example of a second dividing line) dividing the lanes around the host vehicle M based on map information based on position information of the host vehicle M; and a determination unit 142 for determining whether the first dividing line and the second dividing line coincide with each other. If the first recognition unit 132 recognizes a plurality of unilateral camera dividing lines among the left and right camera dividing lines of the host vehicle M, and a first unilateral camera dividing line included in the plurality of recognized unilateral camera dividing lines coincides with a map dividing line, and a predetermined condition is satisfied, the determination unit 142 reduces the reliability of the coincidence information between the coincident first unilateral camera dividing line and the map dividing line, thereby suppressing erroneous determination of the dividing lines based on the surrounding conditions of the host vehicle. Therefore, more appropriate driving control can be performed based on the recognition results of the vehicle's surroundings. According to the embodiment, the continuity of driving control can be further improved. This can further contribute to the development of a sustainable transportation system.

[0117] According to the embodiments, even when a single camera dividing line coincides with a map dividing line, the correctness of the dividing line is determined based on the driving trajectories of other vehicles, the physical boundaries of the road, and other factors, thereby more accurately preventing misjudgments. According to the embodiments, by performing the above-mentioned control in situations such as a construction site in the direction of travel, even in road conditions prone to misjudgment of dividing lines and road shape, such as where a dividing line is temporarily drawn to avoid the construction site, where a previous dividing line remains from a change due to construction, or where a newly drawn dividing line is drawn, misjudgments can be prevented, allowing driving control to be executed (continued) using more appropriate information.

[0118] The above-described embodiment can be expressed as follows.

[0119] A driving control device, wherein:

[0120] The driving control device comprises:

[0121] a storage medium storing computer-readable instructions; and

[0122] a processor connected to the storage medium,

[0123] The processor executes the computer-readable instructions to:

[0124] identifying the surrounding conditions including a first dividing line dividing the lane of the host vehicle and other vehicles existing around the host vehicle based on an output of a detection device that detects the surrounding conditions of the host vehicle;

[0125] identifying, based on the position information of the host vehicle and according to map information, a second dividing line that divides lanes around the host vehicle;

[0126] determining whether the first dividing line coincides with the second dividing line; and

[0127] When multiple single-sided first dividing lines are identified among the left and right first dividing lines of the vehicle, and the first single-sided first dividing line included in the identified multiple single-sided first dividing lines matches the second dividing line and satisfies the specified conditions, the reliability of the matching information of the matching first single-sided first dividing line and the second dividing line is reduced.

[0128] While specific embodiments of the present invention have been described above, the present invention is not limited to these embodiments at all, and various modifications and substitutions can be made without departing from the spirit of the present invention.

Claims

1. A vehicle control device, wherein: The vehicle control device comprises: a first recognition unit for recognizing a surrounding condition including a first dividing line dividing a lane in which the vehicle is traveling and other vehicles existing around the vehicle based on an output of a detection device that detects a surrounding condition of the vehicle; a second recognition unit that recognizes a second dividing line that divides lanes around the host vehicle according to map information based on the position information of the host vehicle; as well as a determination unit configured to determine whether the first dividing line and the second dividing line coincide with each other, The determination unit reduces the reliability of the matching information of the matching first unilateral first dividing line and the second dividing line when the first identification unit identifies multiple unilateral first dividing lines among the left and right first dividing lines of the vehicle, and the first unilateral first dividing line included in the identified multiple unilateral first dividing lines matches the second dividing line and satisfies the specified conditions.

2. The vehicle control device according to claim 1, wherein: The predetermined condition includes a situation where the other vehicle passes on the first one-side first dividing line determined to coincide with the second dividing line.

3. The vehicle control device according to claim 1, wherein: The vehicle control device further includes a driving control unit that controls one or both of the steering and the speed of the host vehicle to perform driving control based on the determination result determined by the determination unit. The driving control unit controls the travel of the host vehicle based on a second one-sided first dividing line determined by the determination unit not to coincide with the second dividing line when the plurality of one-sided first dividing lines identified by the first identification unit include a second one-sided first dividing line.

4. The vehicle control device according to claim 1, wherein: The predetermined condition includes that the host vehicle is traveling within a predetermined distance from a location where construction is being carried out or a location where construction was carried out in the past.

5. The vehicle control device according to claim 1, wherein: The predetermined condition includes the presence of a physical road boundary in the traveling direction of the host vehicle.

6. The vehicle control device according to claim 1, wherein: The vehicle control device further includes a driving control unit that controls one or both of the steering and the speed of the host vehicle to perform driving control based on the determination result determined by the determination unit. The driving control unit causes the host vehicle to travel along a physical road boundary when there is a physical road boundary extending in a direction different from the aligned first one-side first dividing line and the second dividing line.

7. The vehicle control device according to claim 3, wherein: The determination unit determines that the second one-side first dividing line is a correct dividing line when the second one-side first dividing line extends along a physical boundary of the road. The driving control unit causes the host vehicle to travel along the second one-side first dividing line.

8. The vehicle control device according to claim 7, wherein: The driving control unit adjusts the position of the second one-side first dividing line along the direction in which the physical boundary of the road extends, and causes the host vehicle to travel along the adjusted position of the second one-side first dividing line.

9. The vehicle control device according to claim 8, wherein: The driving control unit adjusts a position of the second one-side first dividing line when a distance between the physical boundary of the road and the second one-side first dividing line is less than a predetermined distance.

10. The vehicle control device according to claim 6, wherein: The driving control unit does not execute driving control based on the physical boundary of the road when the host vehicle is traveling in a lane having a slope greater than or equal to a predetermined value.

11. The vehicle control device according to claim 6, wherein: The driving control unit causes the host vehicle to travel along the physical boundary of the road when sign information indicating a construction site exists in the traveling direction of the host vehicle.

12. A vehicle control method, wherein: The vehicle control method causes the computer to perform the following processing: identifying, based on an output of a detection device that detects a surrounding condition of the host vehicle, a surrounding condition including a first dividing line that divides a lane in which the host vehicle is traveling and other vehicles that are present around the host vehicle; identifying, based on the position information of the host vehicle and according to map information, a second dividing line that divides lanes around the host vehicle; determining whether the first dividing line coincides with the second dividing line; as well as When multiple single-sided first dividing lines are identified among the left and right first dividing lines of the vehicle, and the first single-sided first dividing line included in the identified multiple single-sided first dividing lines matches the second dividing line and meets the specified conditions, the reliability of the matching information of the matching first single-sided first dividing line and the second dividing line is reduced.

13. A storage medium storing a program, wherein: The program causes the computer to perform the following processing: identifying, based on an output of a detection device that detects a surrounding condition of the host vehicle, a surrounding condition including a first dividing line that divides a lane in which the host vehicle is traveling and other vehicles that are present around the host vehicle; identifying, based on the position information of the host vehicle and according to map information, a second dividing line that divides lanes around the host vehicle; determining whether the first dividing line coincides with the second dividing line; as well as When multiple single-sided first dividing lines are identified among the left and right first dividing lines of the vehicle, and the first single-sided first dividing line included in the identified multiple single-sided first dividing lines matches the second dividing line and meets the specified conditions, the reliability of the matching information of the matching first single-sided first dividing line and the second dividing line is reduced.

Images