Mobile body control device, mobile body control method, and storage medium

Abstract

The present application provides a mobile body control device, a mobile body control method, and a storage medium that can more accurately identify a division line that divides a travel lane in which a vehicle travels. The mobile body control device of an embodiment includes a division line candidate identification unit that identifies a candidate of a division line that divides a travel lane in which a mobile body travels from an image that includes a periphery of the mobile body, the image being captured by an imaging unit; a virtual line setting unit that sets at least one or more virtual lines at positions that are outside a division line that is identified as a division line that has divided the travel lane in the past, when viewed from the mobile body; and a division line search unit that searches for a division line that divides a current travel lane of the mobile body, based on the candidate of the division line identified by the division line candidate identification unit and the one or more virtual lines.

Description

Technical Field

[0001] This invention relates to a mobile body control device, a mobile body control method, and a storage medium. Background Technology

[0002] In recent years, research related to autonomous driving, which automatically controls the driving of vehicles, has made increasing progress. In this regard, there are known technologies that adjust the configuration of driving lanes based on the driving lanes around the vehicle identified by sensors that detect the conditions around the vehicle, and the driving lanes around the vehicle obtained from map data according to the vehicle's position and posture (e.g., Japanese Patent Application Publication No. 2018-55414). Summary of the Invention

[0003] However, if the recognition by the sensors that detect the conditions around the vehicle is unstable and a line with a similar shape to the dividing line is identified near the dividing line being identified, it is possible to misidentify that line as the dividing line for the vehicle's driving lane.

[0004] The present invention was made in consideration of such circumstances, and one of its objectives is to provide a moving body control device, a moving body control method, and a storage medium that can more accurately identify the dividing lines that divide the driving lane of the vehicle.

[0005] The mobile body control device, mobile body control method, and storage medium of the present invention adopt the following structure.

[0006] (1): A mobile vehicle control device according to one aspect of the present invention includes: a dividing line candidate identification unit that identifies candidates for dividing lines that divide the driving lane of the mobile vehicle from an image captured by a camera unit, including the periphery of the mobile vehicle; an imaginary line setting unit that sets at least one imaginary line at a position further outward than the dividing line identified as a dividing line that previously divided the driving lane when viewed from the mobile vehicle; and a dividing line search unit that searches for the dividing line that divides the current driving lane of the mobile vehicle based on the dividing line candidates identified by the dividing line candidate identification unit and the one or more imaginary lines.

[0007] (2): In the above (1) scheme, the imaginary line setting unit sets the imaginary line at the location where the boundary of the road, which is predicted to include the current driving lane of the moving body, exists.

[0008] (3): In the above (1) scheme, the imaginary line setting unit sets an imaginary line at a position away from the dividing line identified as the dividing line that previously divided the driving lanes by a predetermined distance.

[0009] (4) In the aspect of (1) above, the division line search section decides the division line candidate that is closest to the division line that has divided the travel lane in the past, among the division line candidates, as the division line that divides the current travel lane of the moving body.

[0010] (5) In the aspect of (1) above, the division line search section does not decide the division line candidate that is within a prescribed distance from the imaginary line, among the division line candidates, as the division line that divides the current travel lane of the moving body.

[0011] (6) In the aspect of (1) above, the division line search section recognizes the division line candidate that is within a prescribed distance from the imaginary line, among the division line candidates, as a boundary line other than the division line that divides the current travel lane of the moving body.

[0012] (7) In the aspect of (1) above, there is further provided a driving control section that controls one or both of the speed and the steering of the moving body so that the moving body travels along the division line that divides the travel lane of the moving body, decided by the division line search section.

[0013] (8) A moving body control method according to an aspect of the present application causes a computer of a moving body control device to perform the following processes: recognizing a candidate of a division line that divides a travel lane in which a moving body travels, from an image that includes the surroundings of the moving body, taken by an imaging section; setting at least one or more imaginary lines at positions that are outside, when viewed from the moving body, of division lines recognized as division lines that have divided the travel lane in the past; and searching for a division line that divides a current travel lane of the moving body, based on the recognized candidate of the division line and the set one or more imaginary lines.

[0014] (9) A storage medium according to an aspect of the present application stores a program that causes a computer of a moving body control device to perform the following processes: recognizing a candidate of a division line that divides a travel lane in which a moving body travels, from an image that includes the surroundings of the moving body, taken by an imaging section; setting at least one or more imaginary lines at positions that are outside, when viewed from the moving body, of division lines recognized as division lines that have divided the travel lane in the past; and searching for a division line that divides a current travel lane of the moving body, based on the recognized candidate of the division line and the set one or more imaginary lines.

[0015] According to the aspects of (1) to (9) above, the division line that divides the travel lane in which the host vehicle travels can be recognized more accurately. BRIEF DESCRIPTION OF DRAWINGS

[0016] Figure 1Fig. 1 is a configuration diagram of a vehicle system using a mobile body control device according to an embodiment.

[0017] Figure 2 Fig. 2 is a functional configuration diagram of a first control section and a second control section.

[0018] Figure 3 Fig. 3 is a diagram for explaining the function of a virtual line setting section.

[0019] Figure 4 Fig. 4 is a diagram for explaining an example of the function of a division line search section.

[0020] Figure 5 Fig. 5 is a diagram for explaining the derivation of the distance between a division line candidate and a virtual line.

[0021] Figure 6 Fig. 6 is a flowchart showing an example of the flow of processing performed by the automatic driving control device according to the embodiment. DETAILED DESCRIPTION

[0022] Embodiments of a mobile body control device, a mobile body control method, and a storage medium of the present application will be described below with reference to the accompanying drawings. The mobile body control device is a device that performs movement control of a mobile body. The mobile body includes a vehicle of three or four wheels or the like, a two-wheeled vehicle, a micro mobile body, and the like, and can include all mobile bodies that are mounted on a road surface or the like on which a travel lane or the like exists and are capable of moving on the road surface or the like, for example. In the following description, the mobile body is assumed to be a four-wheeled vehicle, and is referred to as "host vehicle M". In the following description, a case in which the host vehicle M is mainly an automatic driving vehicle will be described. The automatic driving refers to driving control in which one or both of the steering and the speed of the host vehicle M are automatically controlled, for example. The driving control of the host vehicle M includes LKAS (Lane Keeping Assistance System) in which the host vehicle M is prevented from deviating from the lane on which the host vehicle M travels, for example. In addition, the driving control can include various driving assistance controls such as ALC (Auto Lane Changing) and ACC (Adaptive Cruise Control). The automatic driving vehicle can also be controlled by manual driving by an occupant (driver). Alternatively, the drive source of the host vehicle M is an internal combustion engine such as a diesel engine or a gasoline engine, an electric motor, or a combination thereof, for example. The electric motor operates using electric power generated by a generator coupled to the internal combustion engine, or discharge electric power of a secondary battery or a fuel cell.

[0023] [Overall Configuration]

[0024] Figure 1A structure diagram of a vehicle system 1 that is a mobile body control device using an embodiment will be described. The vehicle system 1 has, for example, a camera 10, a radar device 12, an object recognition device 16, a communication device 20, an HMI (Human Machine Interface) 30, a vehicle sensor 40, a navigation device 50, an MPU (Map Positioning Unit) 60, a driving operation member 80, an autonomous driving control device 100, a travel drive power output device 200, a brake device 210, and a steering device 220. These devices and apparatuses are connected to each other through a multiplex communication line such as a CAN (Controller Area Network) communication line, a serial communication line, a wireless communication network, or the like. Figure 1 The illustrated structure is only an example, and a part of the structure can be omitted, or another structure can be further added. The camera 10 is an example of an "imaging section". The autonomous driving control device 100 is an example of a "mobile body control device".

[0025] The camera 10 is, for example, a digital camera using a solid-state imaging element such as a CCD (Charge Coupled Device) or a CMOS (Complementary Metal Oxide Semiconductor). The camera 10 is attached to an arbitrary portion of a host vehicle M on which the vehicle system 1 is mounted. In a case where the front is imaged, the camera 10 is attached to an upper portion of a front windshield glass, a back surface of a door mirror, or the like. The camera 10 repeatedly images the surroundings of the host vehicle M periodically, for example. The camera 10 can also be a stereo camera.

[0026] The radar device 12 radiates an electric wave such as a millimeter wave to the surroundings of the host vehicle M, and detects a position (distance and direction) of an object by detecting an electric wave (reflected wave) reflected by the object. The radar device 12 is attached to an arbitrary portion of the host vehicle M. The radar device 12 can also detect the position and speed of the object by an FM-CW (Frequency Modulated Continuous Wave) method.

[0027] The object recognition device 16 analyzes the image taken by the camera 10, which represents the situation in front of the host vehicle M, and extracts the required information. Also, the object recognition device 16 performs sensor fusion processing on the detection results of the camera 10 and the radar device 12 to recognize the position, type, speed, and the like of an object, and outputs the recognition result to the automatic driving control device 100. The radar device 12 can be omitted in the present application, in which case the object recognition device 16 can also have only the function of analyzing the image. The detection result of the radar device 12 can also be output directly to the automatic driving control device 100 without performing sensor fusion processing. The function of the object recognition device 16 can also be included in the automatic driving control device 100 (more specifically, the recognition section 130 described later). In this case, the object recognition device 16 can also be omitted from the vehicle system 1.

[0028] The communication device 20 communicates with other vehicles existing in the periphery of the host vehicle M, or with various server devices via a wireless base station, using, for example, a cellular network, a Wi-Fi network, Bluetooth (registered trademark), DSRC (Dedicated Short Range Communication), and the like.

[0029] The HMI 30 outputs various information to the occupant of the host vehicle M by the control of the HMI control section 170. The HMI 30 can also function as a reception section that receives an input operation by the occupant. The HMI 30 includes, for example, a display device, a speaker, a microphone, a buzzer, a key, an indicator, and the like. The display device is, for example, an LCD (Liquid Crystal Display), an organic EL (Electro Luminescence) display device, or the like.

[0030] The vehicle sensor 40 includes a vehicle speed sensor that detects the speed of the host vehicle M, an acceleration sensor that detects acceleration, a yaw rate sensor that detects the angular velocity about the vertical axis, a direction sensor that detects the orientation of the host vehicle M, and the like. The vehicle sensor 40 can also include a position sensor that acquires the position of the host vehicle M. The position sensor is, for example, a sensor that acquires position information (longitude, latitude information) from a GPS (Global Positioning System) device. The position sensor can also be a sensor that acquires position information using the GNSS (Global Navigation Satellite System) receiver 51 of the navigation device 50.

[0031] The navigation device 50 includes, for example, a GNSS receiver 51, a navigation HMI 52, and a route decision section 53. The navigation device 50 holds first map information 54 in a storage device such as a hard disk drive (HDD), a flash memory, or the like. The GNSS receiver 51 determines the position of the host vehicle M based on signals received from GNSS satellites. The position of the host vehicle M can also be determined or supplemented by an inertial navigation system (INS) that utilizes the output of the vehicle sensor 40. The navigation HMI 52 includes a display device, a speaker, a touch panel, a button, or the like. The navigation HMI 52 can also be partially or wholly shared with the aforementioned HMI 30. The route decision section 53 determines, for example, a route (hereinafter referred to as an on-map route) from the position of the host vehicle M determined by the GNSS receiver 51 (or an arbitrary position input) to a destination input by a passenger using the navigation HMI 52, with reference to the first map information 54. The first map information 54 is, for example, information that represents the shape of a road by road segments and nodes connected by the road segments. The first map information 54 can also include the curvature of a road, point of interest (POI) information, or the like. The on-map route is output to the MPU 60. The navigation device 50 can also perform route guidance using the navigation HMI 52 based on the on-map route. The navigation device 50 can also be implemented by the functions of a terminal device such as a smartphone, a tablet terminal, or the like held by a passenger. The navigation device 50 can also transmit the current position and the destination to a navigation server via the communication device 20 and acquire a route equivalent to the on-map route from the navigation server.

[0032] The MPU 60 includes, for example, a recommended lane decision section 61 and holds second map information 62 in a storage device such as an HDD, a flash memory, or the like. The recommended lane decision section 61 divides the on-map route provided from the navigation device 50 into a plurality of blocks (for example, every 100 [m] in the direction of travel of the vehicle) and determines a recommended lane for each block with reference to the second map information 62. For example, the recommended lane decision section 61 makes a determination to travel on the nth lane from the left in a case where the lane currently being traveled on or the road to be traveled on in the near future is a plurality of lanes. The recommended lane decision section 61 determines a recommended lane so that the host vehicle M can travel on a reasonable route for traveling to a branched destination in a case where there is a branch point in the on-map route.

[0033] The second map information 62 is map information having higher precision than the first map information 54. The second map information 62 includes, for example, information of the center of a lane or information of the boundary of a lane (for example, a road division line, a shoulder, a curb, a median, a guardrail), and the like. The second map information 62 can include road information (a road category), the number of lanes of a road, the presence or absence of a branch or a junction, a legal speed (a limit speed, a maximum speed, a minimum speed), traffic restriction information, dwelling information (a dwelling, a postal code), facility information, telephone number information, and the like. The second map information 62 can be updated at any time by the communication device 20 communicating with another device.

[0034] The driving operation member 80 includes, for example, a steering wheel, an accelerator pedal, a brake pedal, a shift lever, and other operation members. A sensor that detects an operation amount or the presence or absence of an operation is installed in the driving operation member 80, and the detection result is output to some or all of the automatic driving control device 100 or the travel driving force output device 200, the brake device 210, and the steering device 220.

[0035] Next, the travel driving force output device 200, the brake device 210, and the steering device 220 will be described before the automatic driving control device 100 is described. The travel driving force output device 200 outputs a travel driving force (torque) for causing the host vehicle M to travel to a drive wheel. The travel driving force output device 200 includes, for example, a combination of an internal combustion engine, an electric motor, a transmission, and the like, and an ECU (Electronic Control Unit) that controls them. The ECU controls the above-described structure in accordance with information input from the automatic driving control device 100 (specifically, the second control section 160 described later) or information input from the driving operation member 80.

[0036] The brake device 210 includes, for example, a brake caliper, a hydraulic cylinder that transmits hydraulic pressure to the brake caliper, an electric motor that causes the hydraulic cylinder to generate hydraulic pressure, and a brake ECU. The brake ECU controls the electric motor in accordance with information input from the second control section 160 or information input from the driving operation member 80 to output a brake torque corresponding to a brake operation to each wheel. The brake device 210 can include a mechanism that transmits hydraulic pressure generated by an operation of a brake pedal included in the driving operation member 80 to the hydraulic cylinder via a master hydraulic cylinder as a backup. The brake device 210 is not limited to the structure described above, and can be an electronically controlled hydraulic brake device that transmits hydraulic pressure of the master hydraulic cylinder to the hydraulic cylinder by controlling an actuator in accordance with information input from the second control section 160.

[0037] The steering device 220, for example, is provided with a steering ECU and an electric motor. The electric motor, for example, causes a force to act on a rack-and-pinion mechanism to change the orientation of the steered wheels. The steering ECU drives the electric motor in accordance with information input from the second control section 160 or information input from the steering wheel 82 of the driving operation member 80, causing the orientation of the steered wheels to change.

[0038] Next, the automatic driving control device 100 will be described. The automatic driving control device 100, for example, is provided with the first control section 120, the second control section 160, the HMI control section 170, and the storage section 180. The first control section 120, the second control section 160, and the HMI control section 170 are each realized by, for example, a hardware processor such as a CPU executing a program (software). Some or all of these components can be realized by hardware (including circuitry) such as an LSI (Large Scale Integration), an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array), a GPU (Graphics Processing Unit), or the like, and can also be realized by a combination of software and hardware. The program can be stored in advance in a storage device (a storage device provided with a non-transitory storage medium) such as an HDD, a flash memory, or the like of the automatic driving control device 100, or can be stored in a removable storage medium such as a DVD, a CD-ROM, or the like, and installed in the HDD, the flash memory, or the like of the automatic driving control device 100 by mounting the storage medium (a non-transitory storage medium) in a drive device. The action plan generation section 140 and the second control section 160 together are an example of a "driving control section".

[0039] The storage section 180 can also be implemented by various storage devices described above, or an SSD (Solid State Drive), an EEPROM (Electrically Erasable Programmable Read Only Memory), a ROM (Read Only Memory), or a RAM (Random Access Memory), and the like. The storage section 180 stores, for example, image information 182, division line information 184, information necessary for executing various processes in the present embodiment, programs, and other various information, and the like. The image information 182 is information of a surrounding image of the host vehicle M (at least an image of a traveling direction of the host vehicle M) captured by the camera 10. Hereinafter, an image captured by the camera 10 will be referred to as a "camera image". It can also be that, in the image information 182, a correspondence relationship is established between a camera image and a capturing time and a position and a direction of the host vehicle M at the time of capturing by the camera 10. The image information 182 stores a camera image before a predetermined time (before a predetermined image frame). The predetermined time in this case can be a fixed time, or a variable time corresponding to a speed of the host vehicle M and a shape of a road. Hereinafter, a camera image before the predetermined time will be referred to as a "past camera image". The past camera image is an example of a "second image". The division line information 184 is information of a road division line (hereinafter, simply referred to as a "division line") that divides a traffic lane on a road, which is recognized by the recognition section 130 before the predetermined time. The division line information 184 can also include, for example, position information of a traffic lane (hereinafter, referred to as a "host traffic lane") in which the host vehicle M travels, which is obtained from an analysis result of the past camera image. In this case, the storage section 180 retains a division line that divides the host traffic lane in the past camera image. The storage section 180 can also store map information (the first map information 54, the second map information 62).

[0040] Figure 2 is a functional configuration diagram of the first control section 120 and the second control section 160. The first control section 120 is provided with, for example, the recognition section 130 and the action plan generation section 140. The first control section 120, for example, implements functions based on AI (Artificial Intelligence) and functions based on a model given in advance in parallel. For example, a function of "recognizing an intersection" can be implemented by "performing recognition of an intersection based on deep learning or the like and recognition based on a condition given in advance (presence of a signal capable of pattern matching, a road sign, or the like) in parallel, and comprehensively evaluating both by scoring". Thereby, reliability of automated driving is ensured.

[0041] The recognition unit 130 recognizes the position (relative position), speed (relative speed), acceleration, and the like of an object (for example, another vehicle, another obstacle) in the periphery of the host vehicle M, based on information input from the camera 10 and the radar device 12 via the object recognition device 16. The position of the object is recognized as a position in an absolute coordinate system (host vehicle center coordinate system) having a representative point (center of gravity, center of a drive shaft, or the like) of the host vehicle M as an origin, for example, and is used for control. The position of the object can also be represented by a representative point such as a center of gravity or a corner of the object, or can be represented by a region. The "state" of the object can also include the acceleration, jerk, or "behavioral state" (for example, whether or not a lane change is being made or is about to be made) of another vehicle in the case where the object is another vehicle or the like.

[0042] The recognition unit 130 recognizes the host vehicle lane, for example, based on at least information input from the camera 10. Specifically, the recognition unit 130 includes a virtual line setting unit 132, a point group acquisition unit 134, a division line candidate recognition unit 136, and a division line search unit 138, for example. The division line that divides the host vehicle lane, the host vehicle lane itself, or a boundary line other than the division line (for example, a road boundary line) is recognized by each function. Details of each function will be described later.

[0043] The recognition unit 130 recognizes the host vehicle lane using the functions of the virtual line setting unit 132, the point group acquisition unit 134, the division line candidate recognition unit 136, and the division line search unit 138, and in addition to or instead of this, recognizes the division line that divides the host vehicle lane, the host vehicle lane itself, by comparing the pattern (for example, arrangement of solid lines and dashed lines) of the division line obtained from the second map information 62 with the pattern of the division line in the periphery of the host vehicle M recognized from the image captured by the camera 10. The recognition unit 130 is not limited to recognizing the division line, and can recognize a travel road boundary (road boundary) including a shoulder, a curb, a median, a guardrail, and the like. In this recognition, the position of the host vehicle M acquired from the navigation device 50 and the processing result of the INS processing can also be taken into consideration. In addition, the recognition unit 130 recognizes a stop line, an obstacle, a red light, a toll gate, a road sign, and other road phenomena. The recognition unit 130 can also recognize an adjacent lane adjacent to the host vehicle lane, and an opposite lane facing the host vehicle lane. The adjacent lane is a lane that can travel in the same direction as the host vehicle lane, for example.

[0044] The recognition unit 130 can also recognize the position and posture of the host vehicle M with respect to the host vehicle lane in the case where the host vehicle lane is recognized. The recognition unit 130 can, for example, recognize the deviation of the reference point of the host vehicle M from the center of the lane and the angle of the traveling direction of the host vehicle M with respect to the line connecting the center of the lane as the relative position and posture of the host vehicle M with respect to the host vehicle lane. Instead, the recognition unit 130 can recognize the position of the reference point of the host vehicle M with respect to the arbitrary side end portion (e.g., a division line or a road boundary) of the host vehicle lane as the relative position of the host vehicle M with respect to the host vehicle lane. Here, the reference point of the host vehicle M can be the center or the center of gravity of the host vehicle M. The reference point can be the end portion (front end portion or rear end portion) of the host vehicle M or the position where one of the plurality of wheels provided in the host vehicle M is present.

[0045] The action plan generation unit 140 generates a target track along which the host vehicle M is to travel automatically (independently of the operation of the driver) in the future on the basis of the recognition result and the like recognized by the recognition unit 130 in such a manner that the host vehicle M travels on the recommended lane decided by the recommended lane decision unit 61 in principle and is able to cope with the surrounding situation of the host vehicle M. The target track includes, for example, a speed element. The target track is expressed, for example, as a track obtained by arranging the points (track points) at which the host vehicle M should arrive in order. The track points are the points at which the host vehicle M should arrive at every prescribed traveling distance (e.g., several [m]) along the route, and, instead of this, the target speed and the target acceleration at every prescribed sampling time (e.g., several [sec]) are generated as a part of the target track. The track points can also be the positions at which the host vehicle M should arrive at every prescribed sampling time. In this case, the information of the target speed and the target acceleration is expressed by the interval of the track points. The action plan generation unit 140 can also generate a target track in which the speed of the host vehicle M becomes a set speed within the range in which the host vehicle M can travel in the case where the set speed of the host vehicle M is decided.

[0046] The action plan generation unit 140 can set an event (function) of automatic driving when generating the target track. The event of automatic driving includes a constant speed traveling event, a low speed following traveling event, a lane changing event, a branching event, a merging event, a takeover event, and the like. The action plan generation unit 140 generates a target track corresponding to the event that is started. The action plan generation unit 140 can also propose (suggest) the execution of the driving control, the event, and the like of the host vehicle M to the occupant in accordance with the driving mode of the host vehicle M described later in the case where the driving control, the prescribed event, and the like of the host vehicle M are executed, and generate a corresponding target track in the case where the proposal is accepted.

[0047] The second control section 160 controls the travel driving force output device 200, the brake device 210, and the steering device 220 so that the vehicle M passes through the target track generated by the behavior plan generation section 140 at a predetermined time.

[0048] The second control section 160 includes, for example, an acquisition section 162, a speed control section 164, and a steering control section 166. The acquisition section 162 acquires information of the target track (track point) generated by the behavior plan generation section 140 and stores the information in a memory (not shown). The speed control section 164 controls the travel driving force output device 200 or the brake device 210 on the basis of a speed element attached to the target track stored in the memory. The steering control section 166 controls the steering device 220 in accordance with a bending situation of the target track stored in the memory. The processing of the speed control section 164 and the steering control section 166 is realized, for example, by a combination of feedforward control and feedback control. As an example, the steering control section 166 performs feedforward control corresponding to a curvature of a road ahead of the vehicle M in combination with feedback control based on a deviation from the target track.

[0049] The HMI control section 170 notifies a passenger (driver) of the host vehicle M of prescribed information by means of the HMI 30. The prescribed information includes, for example, driving support information. For example, the HMI control section 170 can generate an image including the prescribed information described above and cause the generated image to be displayed on a display device of the HMI 30, or can generate a sound indicating the prescribed information and cause the generated sound to be output from a speaker of the HMI 30. The HMI control section 170 can also output information accepted by the HMI 30 to the communication device 20, the navigation device 50, the first control section 120, and the like, for example.

[0050] [Assumed Line Setting Section, Point Group Acquisition Section, Division Line Candidate Recognition Section, and Division Line Search Section]

[0051] Hereinafter, details of functions of the assumed line setting section 132, the point group acquisition section 134, the division line candidate recognition section 136, and the division line search section 138 will be described. The assumed line setting section 132 sets an assumed line on the basis of a position of a division line included in the division line information 184 stored in the storage section 180, which is identified as a division line that divides the travel lane of the host vehicle M in the past. Figure 3 is a view for explaining a function of the assumed line setting section 132. In Figure 3 In the example of Fig. 17, it is assumed that the host vehicle M is traveling in the X-axis direction at a speed VM. The division lines LL and LR are division lines that are determined by the division line search section 138 on the basis of a past camera image (second image) to be division lines that divide the travel lane LI of the host vehicle M.

[0052] For example, in a road containing the lane in which vehicle M travels (hereinafter referred to as the vehicle's lane), in addition to the dividing line that separates the vehicle's lane, there are other lanes that can travel in the same direction as the vehicle's lane, dividing lines that separate opposing lanes for oncoming vehicles, shoulders, curbs, sidewalks, etc. Most of these extend along the vehicle's lane, so line segments extracted by image analysis are sometimes identified as dividing lines of the vehicle's lane. Therefore, the imaginary line setting unit 132 sets imaginary lines based on the positions of past dividing lines, at the positions of dividing lines that separate lanes other than the vehicle's lane, and at the positions of linear or non-linear line segments extracted from the camera image based on the edge portions of road boundaries such as shoulders, curbs, and sidewalks. For example, the imaginary line setting unit 132 sets one or more imaginary lines based on the dividing lines of the vehicle's lane identified from past camera images, at a position that is separated from the dividing lines by a predetermined distance when viewed from vehicle M. When setting multiple imaginary lines, they can also be set at specified intervals.

[0053] The aforementioned specified distance can be, for example, a fixed distance, or a distance based on the location information of the vehicle M obtained from the vehicle sensor 40, referring to map information (first map information 54, second map information 62), to obtain road information surrounding the vehicle M, and establishing a correspondence between this distance and the locations of road boundary lines such as dividing lines and shoulders outside the vehicle's driving lane. The specified distance can also be the same length as the width of the vehicle's driving lane L1. Therefore, imaginary lines can be set at locations where dividing lines separating oncoming or adjacent lanes are highly likely to exist. The number of imaginary lines can be fixed or variable depending on the road shape (e.g., the number of lanes on the road for the vehicle M to travel on, the presence or absence of sidewalks, etc., obtained from map information). Different numbers of imaginary lines can also be set for the left and right dividing lines LL and LR of the vehicle's driving lane L1.

[0054] exist Figure 3 In the example, using the dividing line LL on the left side of the lane L1 as a reference, an imaginary line VL1 is set at a distance D1 away from the dividing line LL when viewed from vehicle M, and an imaginary line VL2 is set at a distance D2 away from the dividing line LL, which is longer than the distance D1. Figure 3 In the example, taking the dividing line LR on the right side of the lane L1 of this vehicle as a reference, an imaginary line VL3 is set at a distance D3 away from the dividing line LR when viewed from this vehicle M.

[0055] The point group acquisition unit 134 acquires a current camera image (an image indicating the situation in front of the host vehicle M) from the camera 10, and acquires a point group of an object included in the acquired camera image. The current camera image is an example of the "first image". For example, the point group acquisition unit 134 extracts edge points from the camera image (the first image) by an existing image analysis process, and acquires a point group by aggregating points within a prescribed interval among the extracted edge points as a point group of an object. The point group acquired at this time is, for example, a point group defined in an image obtained by performing image conversion on the camera image to a two-dimensional coordinate system (a bird's-eye coordinate system) obtained by viewing the host vehicle M from above. The reference position (origin) of the two-dimensional coordinates in this case is, for example, a representative point of the host vehicle M. The point group acquisition unit 134 can also save the camera image acquired from the camera 10 as the image information 182 of the storage unit 180.

[0056] The division line candidate recognition unit 136 forms a point line from a point group arranged at an interval within a prescribed distance in the same direction (including a permissible angle range) among the point groups acquired by the point group acquisition unit 134, and recognizes a candidate of a division line by comparing the formed point line with a point line pattern decided in advance. For example, the division line candidate recognition unit 136 recognizes a point line as a candidate of a division line in a case where the point line extends in a linear shape over a prescribed distance or in a case where the point line extends over a prescribed distance although not in a linear shape but in a prescribed curvature.

[0057] The division line candidate recognition unit 136 acquires a candidate of a division line at the current time point by inputting point group data acquired by the point group acquisition unit 134 to a learned model such as a DNN (deep neural network) obtained by learning in a manner that the point group data is input and a candidate of a division line corresponding to the point group data is output. The division line candidate recognition unit 136 can also acquire a candidate of a division line at the current time point by inputting a camera image to a learned model such as a DNN obtained by learning in a manner that the camera image is input and a candidate of a division line corresponding to the image is output. In this case, the point group acquisition unit 134 can be omitted from the recognition unit 130. The learned model described above can be stored in the storage unit 180, or can be acquired from an external device through communication via the communication device 20.

[0058] The division line search unit 138 decides a division line that divides the host vehicle lane among the candidates of a division line recognized by the division line candidate recognition unit 136. Figure 4 is a diagram for explaining an example of the function of the division line search unit 138. In Figure 4In the example of FIG. 10, the dividing lines LL, LR of the left and right of the subject vehicle's lane LI recognized from a past (before a predetermined time) camera image (second image), the imaginary lines VL1 to VL3 set by the imaginary line setting section 132, and the dividing line candidates LC1 to LC3 recognized by the dividing line candidate recognizing section 136 based on a current camera image (first image) are shown. The second image in which the dividing lines LL, LR and the imaginary lines VL1 to VL3 are acquired is a past camera image, and the photographing time is different from the first image in which the dividing line candidates LC1 to LC3 are recognized by the dividing line candidate recognizing section 136. Therefore, the dividing line searching section 138 transforms the first image and the second image into a two-dimensional image obtained by viewing the subject vehicle M from above, and makes each of the images coincide with a two-dimensional coordinate system (subject vehicle center coordinate system) with the position of the subject vehicle M as a reference, to acquire the positional relationship between the dividing lines LL, LR and the imaginary lines VL1 to VL3 and the dividing line candidates LC1 to LC3 as shown in FIG. 10. The dividing line searching section 138 can also correct the position, shape of the dividing lines LL, LR and the imaginary lines VL1 to VL3, or the position, shape of the dividing line candidates LC1 to LC3 acquired from the second image, based on one or both of the amount of movement, the direction of movement of the subject vehicle M from when the first image is photographed to when the second image is photographed, or the shape of the road by the camera 10. Figure 4 The dividing line searching section 138 can also correct the position, shape of the dividing lines LL, LR and the imaginary lines VL1 to VL3, or the position, shape of the dividing line candidates LC1 to LC3 acquired from the second image, based on one or both of the amount of movement, the direction of movement of the subject vehicle M from when the first image is photographed to when the second image is photographed, or the shape of the road by the camera 10.

[0059] For example, in a case where the subject vehicle M has performed a turning travel after the photographing time of the past camera image, the dividing line searching section 138 positions the current camera image (first image) and the past camera image (second image) in such a manner that the orientations (directions of movement) of the subject vehicle are the same, and corrects the positions of the dividing lines LL, LR and the imaginary lines VL1 to VL3 from the second image in correspondence with the orientations. In a case where the inclination angle, the curvature of the road has changed after the photographing time of the past camera image of the subject vehicle M, the positions of the dividing lines LL, LR and the imaginary lines VL1 to VL3 are corrected in accordance with the inclination angle, the curvature. Thereby, the positional relationship between the dividing lines LL, LR and the imaginary lines VL1 to VL3 and the dividing line candidates LC1 to LC3 can be more accurately acquired.

[0060] The dividing line searching section 138 can also correct the position, shape of the dividing lines LL, LR and the imaginary lines VL1 to VL3, or the position, shape of the dividing line candidates LC1 to LC3 acquired from the second image, based on one or both of the amount of movement, the direction of movement of the subject vehicle M from when the first image is photographed to when the second image is photographed, or the shape of the road by the camera 10. Figure 4The position relationship between the division lines LL, LR and the imaginary lines VL1 to VL3 and the division line candidates LC1 to LC3 is searched for a line closest to each of the division line candidates LC1 to LC3 (for example, the closest division line or imaginary line). The "closest" means, for example, the closest distance. At least one of the closest, in addition to the distance, or instead of the distance, can include the inclination of the line, the shape of the line in a prescribed interval, the thickness of the line, the color of the line, the line type, and the like, when the traveling direction of the host vehicle is the reference. Hereinafter, as an example, an example of searching for a line closest to the division line candidate LC1 among the lines of the division lines LL, LR and the imaginary lines VL1 to VL3 will be described.

[0061] For example, the division line search section 138 cuts the interval between a reference point PLC1 on the division line candidate LC1 existing at a first prescribed distance from the position (for example, the representative point) of the host vehicle M and each of the reference points PV1 to PV3 on the imaginary lines VL1 to VL3 existing at a prescribed position with the position of the host vehicle M as the reference, and the reference points PLL, PLR on the division lines LL, LR, and derives the distance in the cut interval. The first prescribed distance is, for example, a value decided on the basis of the camera information (parameter information of the camera 10). The parameter information includes, for example, the angle of view, the photographable distance (limit distance), and the like. For example, the reference point PLC1 is set in a range not exceeding the photographable distance on the basis of the camera information, whereby more accurate comparison of the lines can be performed while suppressing the recognition error. The first prescribed distance can be, for example, the longest distance (the position farthest from the host vehicle M) at which the prescribed positions PLL, PLR, and the imaginary lines VL1 to VL3 exist in the road width direction, or can be a fixed distance (first fixed distance). The reference points PLL, PLR, and PV1 to PV3 are, for example, points corresponding to the lateral position direction of the representative point (for example, the front end portion of the host vehicle) of the host vehicle M, but can be based on other points. Hereinafter, the derivation of the distance in the cut interval of the division line candidate LC1 and the imaginary line VL1 will be described, but the same processing is performed for the derivation of the distance between the division line candidate LC1 and each of the division lines LL, LR and the imaginary lines VL2, VL3.

[0062] Figure 5 is a view for explaining the derivation of the distance between the division line candidate LC1 and the imaginary line VL1. In the view, the division line candidate LC1 and the imaginary line VL1 are shown as a line extending in the road width direction. The reference point PLC1 on the division line candidate LC1 and the reference point PV1 on the imaginary line VL1 are shown as points on the line. Figure 5In the example of FIG. 12, the division line search section 138 sets a predetermined number of points on the division line candidate LC1 that are present at regular intervals ΔI from the reference point PLC1 to the reference point PV1 of the virtual line VL1, with the reference point PLC1 of the division line candidate LC1 as the starting point of the search, and derives the distance from each of the set points to the point at which the line extending in the lateral direction (Y-axis direction) of the image (or the line extending in the vertical direction with respect to the extending direction of the division line candidate LC1) intersects the virtual line VL1. The regular intervals ΔI can be a fixed interval decided in advance, or a variable interval based on the speed of the host vehicle M, the shape of the road, and the like detected by the vehicle sensor 40. The predetermined number can be a fixed number decided in advance, or a variable number based on the speed of the host vehicle M, the shape of the road, and the like. In the example of FIG. 12, four search points PO1 to PO4 are set. The division line search section 138 derives the distance at each of the points based on the difference from the reference point PLC1 and the points of the search points PO1 to PO4 to the virtual line VL1 in the lateral position direction of the image. Figure 5 In the example of FIG. 12, the division line search section 138 sets a predetermined number of points on the division line candidate LC1 that are present at regular intervals ΔI from the reference point PLC1 to the reference point PV1 of the virtual line VL1, with the reference point PLC1 of the division line candidate LC1 as the starting point of the search, and derives the distance from each of the set points to the point at which the line extending in the lateral direction (Y-axis direction) of the image (or the line extending in the vertical direction with respect to the extending direction of the division line candidate LC1) intersects the virtual line VL1. The regular intervals ΔI can be a fixed interval decided in advance, or a variable interval based on the speed of the host vehicle M, the shape of the road, and the like detected by the vehicle sensor 40. The predetermined number can be a fixed number decided in advance, or a variable number based on the speed of the host vehicle M, the shape of the road, and the like. In the example of FIG. 12, four search points PO1 to PO4 are set. The division line search section 138 derives the distance at each of the points based on the difference from the reference point PLC1 and the points of the search points PO1 to PO4 to the virtual line VL1 in the lateral position direction of the image. Figure 5 In the example of FIG. 12, the division line search section 138 sets a predetermined number of points on the division line candidate LC1 that are present at regular intervals ΔI from the reference point PLC1 to the reference point PV1 of the virtual line VL1, with the reference point PLC1 of the division line candidate LC1 as the starting point of the search, and derives the distance from each of the set points to the point at which the line extending in the lateral direction (Y-axis direction) of the image (or the line extending in the vertical direction with respect to the extending direction of the division line candidate LC1) intersects the virtual line VL1. The regular intervals ΔI can be a fixed interval decided in advance, or a variable interval based on the speed of the host vehicle M, the shape of the road, and the like detected by the vehicle sensor 40. The predetermined number can be a fixed number decided in advance, or a variable number based on the speed of the host vehicle M, the shape of the road, and the like. In the example of FIG. 12, four search points PO1 to PO4 are set. The division line search section 138 derives the distance at each of the points based on the difference from the reference point PLC1 and the points of the search points PO1 to PO4 to the virtual line VL1 in the lateral position direction of the image.

[0063] The division line search section 138 derives the distance with respect to the other virtual lines VL2, VL3 and the division lines LL, LR as well as the division line candidate LC1. Furthermore, the division line search section 138 derives the closest division line. For example, the division line search section 138 decides that the division line candidate LC1 is the division line of the host vehicle lane L1 in the case where the line present closest to the division line candidate LC1 is the past division line LL or LR. The division line search section 138 can also decide that the division line candidate LC1 is not a division line that divides the host vehicle lane L1 in the case where the line present closest to the division line candidate LC1 is the virtual line VL1 to VL3 (or the division line candidate LC1 is a boundary line other than a division line that divides the travel lane). By deciding the division line candidate that is not a division line of the travel lane L1, the division line of the current host vehicle lane can be extracted more accurately.

[0064] If the lane divider search unit 138 determines that the lane divider candidate LC1 is a boundary line other than the lane divider that separates the driving lanes, it can exclude the lane divider candidate LC1 from the process of searching for the lane divider of the vehicle's driving lane L1 while the lane divider candidate identification unit 136 is identifying the lane divider candidate LC1. As a result, the processing load for determining the lane divider of the vehicle's driving lane L1 can be reduced.

[0065] The lane divider search unit 138 may also refuse to identify a lane divider as a lane divider if the distance between the lane divider LL, LR, and the imaginary lines VL1 to VL3 closest to the candidate lane divider LC1 is greater than or equal to a threshold. In this case, the lane divider search unit 138 continues to use the lane divider of the vehicle's previous driving lane as the lane divider for the current driving lane. Thus, even if a candidate lane divider cannot be identified from the camera image temporarily due to the surrounding environment of the vehicle M or the state of the lane dividers depicted on the road surface, driving support such as LKAS can continue based on the position of the lane divider obtained from past (e.g., just now) search results. If either of the past lane dividers LL or LR cannot be found based on the lane dividers LL, LR, and imaginary lines VL1 to VL3, the lane divider search unit 138 can output only the position information of the other lane divider that was found. Thus, the vehicle M can be driven based on the information of the lane divider obtained as a search result.

[0066] exist Figure 4 In the example, the line closest to candidate lane divider LC1 is the imaginary line VL1, the line closest to candidate lane divider LC2 is the lane divider LR, and the line closest to candidate lane divider LC3 is the imaginary line VL3. Therefore, the lane divider search unit 138 determines candidate lane divider LC2 as the lane divider LR on the right relative to the direction of travel of lane L1, and determines that candidates lane divider LC1 and LC3 are not lane dividers of lane L1.

[0067] In the example above, the dividing line search unit 138 sets points at predetermined intervals to derive distances from the reference point PLC1 of the dividing line candidate LC1 toward the reference point PV1 (in other words, the front side of the vehicle M). However, it is also possible to set a predetermined number of points at predetermined intervals △I on the imaginary line VL1, starting from the reference point PV1 and moving toward the reference point PLC1. The dividing line search unit 138 can also set the predetermined interval △I in a way that allows it to extract a predetermined number of points from the reference point PLC1.

[0068] The division line search section 138 can also extend the division line candidates LC1 to LC3, or the division lines LL, LR, and the imaginary lines VL1 to VL3 in the extending direction so that the distance based on the prescribed number of search points can be derived, in the case where the division lines LL, LR, and the imaginary lines VL1 to VL3 do not exist in the lateral direction of the division line candidates, or in the case where the lengths of the division lines LL, LR, and the imaginary lines VL1 to VL3 are short. By setting the prescribed number of search points, the closeness of the lines to each other, including the shape in the prescribed range, can be more accurately derived, rather than the distance of only one point.

[0069] The division line search section 138 saves the information related to the division line of the own-vehicle lane obtained by this search (for example, the position information of the division line with the position of the host vehicle M as the reference, and the like), and the information of the own-vehicle lane itself divided by the division line, to the division line information 184 of the storage section 180, and utilizes it at the time of dividing the division line of the own-vehicle lane at the next search.

[0070] The recognition section 130 outputs the recognition result including the division line information of the travel lane decided by the division line search section 138 to the action plan generation section 140. The action plan generation section 140 generates the target track of the host vehicle M in such a manner that the host vehicle M travels toward the destination set by the navigation device 50, based on the recognition result, and performs the driving control so that the host vehicle M travels along the generated target track.

[0071] [PROCESS FLOW]

[0072] Figure 6 is a flowchart showing an example of the flow of the process performed by the automatic driving control device 100 of the embodiment. Hereinafter, the process will be mainly explained focusing on the process in which the division line dividing the travel lane of the host vehicle M is searched for and the driving control of the host vehicle M is performed based on the information of the division line obtained as the search result, in the process performed by the automatic driving control device 100. Figure 6 The process of

[0073] In Figure 6 In the example of

[0074] Next, the point group acquisition unit 134 acquires a camera image including the front of the host vehicle M captured by the camera 10 (step S104), and transforms the acquired camera image into an image obtained by viewing the host vehicle M from above (step S106). Next, the point group acquisition unit 134 analyzes the image subjected to the coordinate transformation, and acquires point group data (step S108). Next, the division line candidate recognition unit 136 recognizes a candidate of a division line that divides the host vehicle lane based on the point group data acquired by the point group acquisition unit 134 (step S110).

[0075] Next, the division line search unit 138 derives distances between the past division line and the imaginary line and the division line candidate (step S112). Next, the division line search unit 138 determines whether there is a division line candidate whose distance from the past division line is less than a threshold value (step S114). In a case where it is determined that there is a division line candidate whose distance from the past division line is less than the threshold value, the division line search unit 138 decides the division line candidate as a division line that divides the current host vehicle lane (step S116).

[0076] In a case where it is determined in the process of step S114 that there is no division line candidate whose distance from the past division line is less than the threshold value, the division line search unit 138 determines whether there is an imaginary line whose distance from the past division line is less than the threshold value (step S118). In a case where it is determined that there is an imaginary line whose distance from the past division line is less than the threshold value, the division line search unit 138 recognizes the division line candidate as not being a division line that divides the current host vehicle lane (step S120).

[0077] After the process of step S120 or in a case where it is determined in the process of step S118 that there is no imaginary line whose distance from the past division line is less than the threshold value, the division line search unit 138 continues to use information of the division line recognized in the past, and decides the past division line as a division line that divides the current host vehicle lane (step S122).

[0078] After the process of step S116 or step S122, the division line search unit 138 stores information related to the decided division line in the storage unit 180 (step S124). In the process of step 124, information related to the division line candidate recognized as not being a division line that divides the host vehicle lane can also be stored.

[0079] Next, the action plan generation section 140 generates a target track for causing the host vehicle M to travel along the host lane divided by the decided dividing line and to travel in the center of the host lane (step S126). Next, the second control section 160 executes driving control of one or both of the speed and the steering to cause the host vehicle M to travel along the target track (step S128). Thereby, the processing of the present flowchart ends.

[0080] <Modification example>

[0081] In the above-described vehicle system 1, a LIDAR (Light Detection and Ranging) can also be provided. The LIDAR irradiates light (or an electromagnetic wave close to light in wavelength) to the periphery of the host vehicle M and measures scattered light. The LIDAR detects a distance to an object based on a time from light emission to light reception. The irradiated light is, for example, pulsed laser light. The LIDAR is installed at an arbitrary position of the host vehicle M. For example, the object recognition device 16 can also accept input from the LIDAR in addition to the camera 10 and the radar device 12, and recognize an object (including a dividing line) in the periphery based on a result of sensor fusion processing based on information from each of them.

[0082] In the above-described embodiment, in a case where the host vehicle M is traveling by the operation of the driver without being set a destination based on the navigation device 50, driving control of one part of driving of the steering and the speed of the host vehicle M to support the host vehicle M can also be performed using information of the dividing line of the host lane searched by the above-described dividing line search section 138.

[0083] The dividing line search section 138 can also derive the closest (for example, the highest degree of agreement) line using, for example, an existing matching algorithm in a case where a line closest to the dividing line candidate is searched from the past dividing line and the virtual line. Information of the virtual line set by the virtual line setting section 132 and information of the past dividing line can also be saved in the dividing line information 184 in a corresponding relationship. Information related to the past dividing line (the last searched dividing line) used at the time of search in the dividing line search section 138 can also be acquired from the image saved in the image information 182 instead of being acquired from the dividing line information 184.

[0084] According to the above-described embodiment, in the automatic driving control device (an example of a mobile body control device), there are provided: a division line candidate recognition unit 136 that recognizes a candidate of a division line that divides a travel lane in which a host vehicle (an example of a mobile body) M travels, from an image that includes a periphery of the host vehicle M and that is captured by a camera (an example of an imaging unit); a virtual line setting unit 132 that sets at least one or more virtual lines at positions that are outside, when viewed from the host vehicle M, of division lines that are recognized as division lines that have divided the travel lane in the past; and a division line search unit 138 that searches for a division line that divides a current travel lane of the host vehicle M, based on the candidate of the division line recognized by the division line candidate recognition unit 136 and the one or more virtual lines, whereby it is possible to more accurately recognize a division line that divides a travel lane in which the host vehicle travels.

[0085] Specifically, according to the above-described embodiment, by searching for a division line assuming that a line segment other than the host vehicle travel lane exists outside the division line of the host vehicle travel lane, it is possible to suppress a situation in which a division line other than the division line of the host vehicle travel lane is erroneously recognized as the division line of the host vehicle travel lane. According to the above-described embodiment, it is also possible to grasp a road boundary other than the division line that divides the host vehicle travel lane. The host vehicle M is caused to travel or driving support is performed based on the division lines to the left and right of the host vehicle M that are obtained by the search processing of the present embodiment, whereby it is possible to perform driving control that is more robust. According to the above-described embodiment, by increasing the number of virtual lines, it is possible to search for a boundary line in a wide search range, and thus it is also possible to apply to determination of the number of lanes of a road on which the host vehicle M travels and the like.

[0086] The above-described embodiment can be expressed as follows.

[0087] A mobile body control device is configured to include:

[0088] a storage device that stores a program; and

[0089] a hardware processor,

[0090] the program stored in the storage device is executed by the hardware processor to perform the following processing:

[0091] recognize a candidate of a division line that divides a travel lane in which a mobile body travels, from an image that includes a periphery of the mobile body and that is captured by an imaging unit;

[0092] set at least one or more virtual lines at positions that are outside, when viewed from the mobile body, of division lines that are recognized as division lines that have divided the travel lane in the past;

[0093] search for a division line that divides a current travel lane of the mobile body, based on the recognized candidate of the division line and the set one or more virtual lines.

[0094] The above describes the specific embodiments of the present application using the embodiments, but the present application is not limited at all by such embodiments, and various modifications and substitutions can be applied within the scope of the gist of the present application.

Claims

1. A mobile body control device, wherein the mobile body control device comprises: a division line candidate recognition unit that recognizes candidates of division lines that divide a travel lane in which a mobile body travels, from an image that includes a periphery of the mobile body, the image being captured by an imaging unit; a virtual line setting unit that sets at least one or more virtual lines in a region other than the travel lane, based on division lines that are recognized as division lines that have divided the travel lane in the past, in order to predict a position of a line segment that is linear or non-linear; and a division line search unit that searches for a division line that divides a current travel lane of the mobile body, based on the candidates of division lines recognized by the division line candidate recognition unit and the one or more virtual lines set by the virtual line setting unit.

2. The mobile body control device according to claim 1, wherein the virtual line setting unit sets the virtual line at a position where a boundary of a road that includes the current travel lane of the mobile body is predicted to exist.

3. The mobile body control device according to claim 1, wherein the virtual line setting unit sets a virtual line at a position that is a prescribed distance away from a division line that is recognized as a division line that has divided the travel lane in the past.

4. The mobile body control device according to claim 1, wherein the division line search unit determines a division line candidate that is closest to the division line that has divided the travel lane in the past, among the candidates of division lines, as the division line that divides the current travel lane of the mobile body.

5. The mobile body control device according to claim 1, wherein the division line search unit does not determine a division line candidate that is within a prescribed distance from the virtual line, among the candidates of division lines, as the division line that divides the current travel lane of the mobile body.

6. The mobile body control device according to claim 1, wherein the division line search unit recognizes a division line candidate that is within a prescribed distance from the virtual line, among the candidates of division lines, as a boundary line other than the division line that divides the current travel lane of the mobile body.

7. The mobile body control device according to claim 1, wherein the mobile body control device further comprises a driving control unit that controls one or both of a speed and a steering of the mobile body, in order to cause the mobile body to travel along the division line that divides the travel lane of the mobile body, which is determined by the division line search unit.

8. A mobile body control method, wherein the mobile body control method causes a computer of a mobile body control device to perform the following processes: recognize candidates of division lines that divide a travel lane in which a mobile body travels, from an image that includes a periphery of the mobile body, the image being captured by an imaging unit; set at least one or more virtual lines in a region other than the travel lane, based on division lines that are recognized as division lines that have divided the travel lane in the past, in order to predict a position of a line segment that is linear or non-linear; and search for a division line that divides a current travel lane of the mobile body, based on the recognized candidates of division lines and the set one or more virtual lines.

9. A storage medium that stores a program, wherein ​ The program causes a computer of a mobile body control device to perform the following processing: identifying a candidate of a division line that divides a travel lane in which a mobile body travels from an image including a periphery of the mobile body taken by an imaging section; setting at least one or more virtual lines that project a position of a linear or non-linear line segment in a region outside the travel lane with reference to a division line identified as a division line that divides the travel lane in the past; and searching for a division line that divides a current travel lane of the mobile body based on the candidate of the division line identified and the one or more virtual lines set.

Images