Lane recognition method and lane recognition device

Abstract

The present invention provides a lane recognition method and a lane recognition device, the method including: when recognizing a lane for a vehicle (V) by collating first boundary information about boundaries that divide traffic lanes acquired from map information (14) and second boundary information about boundaries that divide lanes acquired from a detection device of the vehicle (V), detecting a movable center line that is a center line (C) that can move in the width direction of the road on which the vehicle (V) is traveling from at least one of the first boundary information and the second boundary information; and when the movable center line is detected, not performing the collation between the first boundary information and the second boundary information on the side where the movable center line is detected among the left side and the right side of the vehicle (V).

Description

Technical Field

[0001] The present invention relates to a lane recognition method and a lane recognition device.

Background Art

[0002] When estimating the vehicle's own position on a map based on an image around the vehicle, vehicle state quantities such as vehicle speed, the latitude and longitude where the vehicle is located, and map data, an increase / decrease section of the number of road lanes is recognized from the image. When the increase / decrease section of the number of lanes is recognized, the weighting of the estimated position based on the map data is set smaller than when the increase / decrease section of the number of lanes is not recognized, and there is known a self-position estimation device that corrects the estimated position of the vehicle (Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in the above prior art, when the position of the center line changes in the width direction of the road, the lane information obtained from the image around the vehicle does not match the lane information obtained from the map information, and there is a problem that the running position of the vehicle may not be accurately estimated.

[0005] The problem to be solved by the present invention is to provide a lane recognition method and a lane recognition device that can suppress misrecognition of the running position of a vehicle.

Means for Solving the Problems

[0006] When recognizing the driving lane of a vehicle by collating first boundary information of a boundary that divides lanes, obtained from map information, and second boundary information of a boundary that divides lanes, obtained from a vehicle detection device, a movable center line, which is a center line movable in the width direction of the road on which the vehicle travels, is detected from at least one of the first boundary information and the second boundary information. When the movable center line is detected, the above problem is solved by not collating the first boundary information and the second boundary information on the side where the movable center line is detected, out of the right side and the left side of the vehicle.

Effects of the Invention

[0007] According to the present invention, it is possible to suppress misrecognition of the driving position of a vehicle.

Brief Description of the Drawings

[0008]

Figure 1

Figure 2A

Figure 2B

Figure 3A

Figure 3B

Modes for Carrying Out the Invention

[0009] Hereinafter, embodiments of the present invention will be described with reference to the drawings. Note that the following description is based on the premise that in a country having a traffic law of driving on the right side, a vehicle travels on the right side. In a country having a traffic law of driving on the left side, since a vehicle travels on the left side, the right and left in the following description should be read symmetrically.

[0010] [Configuration of Driving Support System] FIG. 1 is a block diagram showing a driving support system 10 according to the present invention. The driving support system 10 is an in-vehicle system that drives a vehicle to a set destination by autonomous driving control. The autonomous driving control refers to autonomously controlling the driving operation of the vehicle using a driving support device 19 described later, and the driving operation includes all driving operations such as acceleration, deceleration, starting, stopping, steering to the right or left, lane change, and centering. Further, autonomously controlling the driving operation means that the driving support device 19 controls the driving operation using the vehicle devices. That is, the driving support device 19 intervenes in and controls these driving operations within a predetermined range. For driving operations that are not intervened, manual operations by the driver are performed.

[0011] The driving support system 10 of the present embodiment can correctly recognize the lane (hereinafter also referred to as "travel lane") in which the vehicle is traveling when the center line of the road can move in the width direction of the road on which the vehicle is traveling (that is, when the road on which the vehicle is traveling has a reversible lane). Hereinafter, the center line that can move in the width direction of the road on which the vehicle is traveling is also referred to as a "movable center line". When moving the center line in the width direction of the road, the type of line marked on the road surface may be changed. For example, the solid white line that was the center line is switched to a broken line, and one of the broken white lines marked on the road surface is switched to a solid line to move the position of the center line of the road.

[0012] The center line is not limited to the line marked on the road surface as long as it can divide the traveling direction of the vehicle on the road, and may be an object that prevents the vehicle from changing lanes across the center line. Examples of such objects include structures such as a median strip, rectangular or circular objects that serve as vehicle barriers, etc. An example of a movable center line is the movable barrier of the Golden Gate Bridge in San Francisco, USA. The movable barrier is a block that can move in the width direction of the road with a barrier transfer machine.

[0013] As shown in FIG. 1, the driving support system 10 includes an imaging device 11, a distance measuring device 12, a state detection device 13, map information 14, a position detection device 15, a navigation device 16, a vehicle control device 17, a display device 18, and a driving support device 19. Further, as shown in FIG. 1, the driving support device 19 of the present embodiment includes, as a part thereof, a lane recognition device having a lane recognition function. The devices constituting the driving support system 10 are connected by a CAN (Controller Area Network) or other in-vehicle LAN and can exchange information with each other.

[0014] The imaging device 11 is a device that recognizes an object around the vehicle by an image, and is, for example, a camera including an image sensor such as a CCD, an ultrasonic camera, an infrared camera, or the like. A plurality of imaging devices 11 can be provided on one vehicle, and can be arranged, for example, in the front grille portion of the vehicle, the lower part of the left and right door mirrors, and the vicinity of the rear bumper. Thereby, the dead angle when recognizing an object around the vehicle can be reduced.

[0015] The distance measuring device 12 is a device for calculating the relative distance and relative speed between the vehicle and the object, and is, for example, a radar device such as a laser radar, a millimeter wave radar (such as an LRF), a LiDAR (light detection and ranging) unit, an ultrasonic radar, or a sonar. A plurality of distance measuring devices 12 can be provided on one vehicle, and can be arranged, for example, in the front, right side, left side, and rear of the vehicle. Thereby, the relative distance and relative speed to the object around the vehicle can be accurately calculated.

[0016] The objects detected by the imaging device 11 and the distance measuring device 12 are road lane boundary lines, center lines, road surface markings, median strips, guardrails, curbstones, side walls of highways, road signs, traffic signals, crosswalks, construction sites, accident sites, traffic restrictions, etc. Further, the objects include obstacles that may affect the running of the vehicle, such as automobiles (other vehicles) other than the host vehicle, motorcycles, bicycles, and pedestrians. The detection results of the imaging device 11 and the distance measuring device 12 are acquired by the driving support device 19 at predetermined time intervals as necessary.

[0017] In addition, the detection results of the imaging device 11 and the distance measuring device 12 can be integrated or synthesized by the driving support device 19, whereby the insufficient information of the detected object can be complemented. For example, the driving support device 19 can calculate the position information of the object based on the self-position information, which is the position where the vehicle travels, acquired by the position detection device 15, and the relative position (distance and direction) between the vehicle and the object. The calculated position information of the object is integrated by the driving support device 19 with the detection results of the imaging device 11 and the distance measuring device 12, as well as a plurality of information such as the map information 14, to become the environmental information around the vehicle. Further, using the detection results of the imaging device 11 and the distance measuring device 12 and the map information 14, it is also possible to recognize the objects around the vehicle and predict their movements.

[0018] The state detection device 13 is a device for detecting the driving state of the vehicle, and examples thereof include a vehicle speed sensor, an acceleration sensor, a yaw rate sensor (for example, a gyro sensor), a steering angle sensor, and an inertial measurement unit. There are no particular limitations on these devices, and known devices can be used. Also, the arrangement and number of these devices can be appropriately set within a range where the driving state of the vehicle can be appropriately detected. The detection results of each device are acquired by the driving support device 19 at a predetermined time interval as necessary.

[0019] The map information 14 is information used for generating a driving route, controlling a driving operation, etc., and includes road information, facility information, and their attribute information. The road information and the attribute information of the road include information such as the width of the road, the radius of curvature of the road, the structure of the road shoulder, road traffic regulations (speed limit, possibility of lane change), the merging points and branching points of the road, and the positions where the number of lanes increases or decreases. The map information 14 is high-precision map information capable of grasping the movement trajectory for each lane, and includes two-dimensional position information and / or three-dimensional position information at each map coordinate, the boundary information of the road and lane at each map coordinate, road attribute information, the up / down information of the lane, lane identification information, connection destination lane information, etc.

[0020] The road and lane boundary information of high-precision map information is information indicating the boundary between the road on which the vehicle travels and the rest. The road on which the vehicle travels is a road for the vehicle to travel, and the form of the road is not particularly limited. The boundaries exist on the left and right sides respectively with respect to the traveling direction of the vehicle, and the form is not particularly limited. The boundary is, for example, a road surface marking or a road structure. Examples of road surface markings include lane boundary lines and center lines, and examples of road structures include median strips, guardrails, curbstones, tunnels, and side walls of expressways. Note that at locations where the road boundary cannot be clearly identified, such as within an intersection, a boundary for the road is set in advance. This boundary is virtual and is not an actual road surface marking or road structure.

[0021] The map information 14 is stored in a record medium provided in the driving support device 19, an in-vehicle device, or a server on the network in a state readable therefrom. The driving support device 19 acquires the map information 14 as necessary.

[0022] The position detection device 15 is a positioning system for detecting the current position of the vehicle, is not particularly limited, and a known one can be used. The position detection device 15 calculates the current position of the vehicle, for example, from radio waves received from satellites for GPS (Global Positioning System). Further, the position detection device 15 may estimate the current position of the vehicle from the vehicle speed information and acceleration information acquired from the vehicle speed sensor, acceleration sensor, and gyro sensor, which are the state detection devices 13, and calculate the current position of the vehicle by collating the estimated current position with the map information 14.

[0023] The navigation device 16 is a device that calculates a driving route from the current position of the vehicle detected by the position detection device 15 to the destination set by the occupant (including the driver) with reference to the map information 14. The navigation device 16 searches for a driving route for the vehicle to reach the destination from the current position using the road information and facility information in the map information 14. The driving route includes at least information on the road on which the vehicle travels, the driving lane, and the driving direction of the vehicle, and is displayed linearly, for example. Depending on the search conditions, there may be multiple driving routes. The driving route calculated by the navigation device 16 is output to the driving support device 19.

[0024] The vehicle control device 17 is an in-vehicle computer such as an electronic control unit (ECU: Electronic Control Unit), and electronically controls in-vehicle devices that regulate the driving of the vehicle. The vehicle control device 17 includes a vehicle speed control device 171 that controls the driving speed of the vehicle and a steering control device 172 that controls the steering operation of the vehicle. The vehicle speed control device 171 and the steering control device 172 autonomously control the operations of these drive devices and steering devices according to the control signals input from the driving support device 19. As a result, the vehicle can autonomously drive according to the set driving route. Information necessary for the autonomous control by the vehicle speed control device 171 and the steering control device 172, such as the driving speed, acceleration, steering angle, and attitude of the vehicle, is acquired from the state detection device 13.

[0025] Examples of the drive device controlled by the vehicle speed control device 171 include an electric motor and / or an internal combustion engine that are driving power sources, a power transmission device including a drive shaft and an automatic transmission that transmit the output from these driving power sources to the drive wheels, and a drive device that controls the power transmission device. Further, the braking device controlled by the vehicle speed control device 171 is, for example, a braking device that brakes the wheels. A control signal corresponding to the set driving speed is input to the vehicle speed control device 171 from the driving support device 19. The vehicle speed control device 171 generates a signal for controlling these drive devices based on the control signal input from the driving support device 19, and transmits the signal to the drive devices, thereby autonomously controlling the driving speed of the vehicle.

[0026] On the one hand, the steering device controlled by the steering control device 172 is a steering device that controls the steering wheel according to the steering angle of the steering wheel. For example, a steering actuator such as a motor attached to the column shaft of the steering can be mentioned. The steering control device 172 autonomously controls the operation of the steering device so that the vehicle travels while maintaining a predetermined lateral position (position in the left - right direction of the vehicle) with respect to the set travel route based on the control signal input from the driving support device 19. At least one of the detection results of the imaging device 11 and the distance measuring device 12, the running state of the vehicle acquired by the state detection device 13, the map information 14, and the information on the current position of the vehicle acquired by the position detection device 15 is used for this control.

[0027] The display device 18 is a device for providing necessary information to the vehicle occupants. For example, it is a liquid crystal display provided on the instrument panel, a projector such as a head - up display (HUD). The display device 18 may be provided with an input device for the vehicle occupants to input instructions to the driving support device 19. Examples of the input device include a touch panel input by the user's finger touch or a stylus pen, a microphone that acquires instructions by the user's voice, and a switch attached to the steering wheel of the vehicle. Further, the display device 18 may be provided with a speaker as an output device.

[0028] The driving support device 19 is a device that controls and cooperates the devices constituting the driving support system 10 to control the running of the vehicle and make the vehicle travel to the set destination. The destination is set by the vehicle occupants, for example. The driving support device 19 is, for example, a computer and includes a CPU (Central Processing Unit) 191 as a processor, a ROM (Read Only Memory) 192 in which programs are stored, and a RAM (Random Access Memory) 193 that functions as an accessible storage device. The CPU 191 is an operation circuit that executes the programs stored in the ROM 192 to realize the functions of the driving support device 19.

[0029] The driving support device 19 has a driving support function that drives the vehicle to a set destination by autonomous driving control. Further, the driving support device 19 of the present embodiment has an information acquisition function for acquiring information from the devices constituting the driving support system 10, a detection function for detecting the movable center line of the road, a recognition function for recognizing the driving lane of the vehicle, and an estimation function for estimating the driving position of the vehicle. The program stored in the ROM 192 includes programs for realizing these functions, and these functions are realized when the CPU 191 executes the program stored in the ROM 192. In FIG. 1, each function is extracted and shown for convenience as a functional block.

[0030] [Functions of Functional Blocks] Hereinafter, the functions realized by the control unit 20, acquisition unit 21, detection unit 22, recognition unit 23, and estimation unit 24, which are functional blocks, will be described with reference to FIGS. 2A and 2B.

[0031] The control unit 20 has a function (that is, a driving support function) of driving the vehicle to a set destination by autonomous driving control. FIG. 2A is a plan view showing an example of a driving scene in which driving support by the function of the control unit 20 is being executed. In the driving scene shown in FIG. 2A, the vehicle V is traveling by autonomous driving control toward a destination (not shown) set on the upper side of FIG. 2A. Since the road shown in FIG. 2A is a right-hand traffic road, the vehicle V travels in the direction from the lower side to the upper side of FIG. 2A.

[0032] The road shown in FIG. 2A is a six-lane road. Each lane shall be referred to as lane L1, lane L2, lane L3, lane L4, lane L5, and lane L6 in order from the right side of the drawing. As shown in FIG. 2A, lane L1 is defined by boundary B1 and boundary B2, lane L2 is defined by boundary B2 and boundary B3, lane L3 is defined by boundary B3 and the center line C, lane L4 is defined by the center line C and boundary B4, lane L5 is defined by boundary B4 and boundary B5, and lane L6 is defined by boundary B5 and boundary B6. In the driving scene shown in FIG. 2A, the center line C is located between lane L3 and lane L4 and divides the driving direction of vehicles on the road. The driving directions of lanes L1 to L3 are from the lower side to the upper side of FIG. 2A, and the driving directions of lanes L4 to L6 are from the upper side to the lower side of FIG. 2A. Also, the center line C shown in FIG. 2A is a movable barrier (i.e., a movable center line) and is assumed to be movable in the width direction of the road by a barrier transfer machine.

[0033] The control unit 20 acquires necessary information from the imaging device 11, the distance measuring device 12, the state detection device 13, the position detection device 15, etc., and recognizes the environment around the vehicle V. Then, so that the vehicle V does not contact surrounding obstacles, the driving of the vehicle V is autonomously controlled by the vehicle control device 17 (specifically, the vehicle speed control device 171 and the steering control device 172). When recognizing the environment around the vehicle V, the control unit 20 of the present embodiment collates the boundary information of the boundary that divides the lane (hereinafter, also referred to as "first boundary information") acquired from the map information 14 with the boundary information of the boundary that divides the lane (hereinafter, also referred to as "second boundary information") acquired from the detection device of the vehicle V to recognize the driving lane of the vehicle V. The recognition of the driving lane is mainly realized by the functions of the acquisition unit 21, the detection unit 22, the recognition unit 23, and the estimation unit 24.

[0034] The acquisition unit 21 has a function of acquiring information (i.e., information acquisition function) from the devices constituting the driving support system 10. The driving support device 19 acquires the current position information of the vehicle V from the position detection device 15, for example, by the function of the acquisition unit 21. In calculating the current position, in addition to the radio waves received from the GPS satellites, the running state information of the vehicle V (for example, vehicle speed information and acceleration information) acquired from the state detection device 13 may be used. Then, the driving support device 19 acquires the first boundary information from the map information 14 based on the acquired current position information of the vehicle V.

[0035] The first boundary information includes information on the boundaries that divide the lanes and exist around the current position of the vehicle V. The first boundary information includes, for example, information on the type of the boundary and the position information of the boundary. The information on the type of the boundary is, for example, information indicating whether the boundary corresponds to a road marking or a road structure. Specifically, it is information indicating whether the boundary is a road marking such as a white line or an object such as a movable barrier. Also, when the boundary is a road marking, information on the form of the road marking is included. For example, when the boundary is a white line, it includes information indicating whether the white line is a solid line or a broken line.

[0036] On the other hand, the position information of the boundary is information indicating where the boundary is located on the road on which the vehicle V travels. The position information of the boundary is, for example, the positional relationship between the boundaries. Specifically, it is the arrangement order of the boundaries along the width direction of the road with respect to the boundary that exists on the rightmost or leftmost side in the traveling direction of the vehicle V as a reference. Instead of or in addition to this, the position information of the boundary includes the positional relationship between the current position of the vehicle V and the boundaries that exist around the current position of the vehicle V.

[0037] In addition, information indicating whether the center line of a road is a movable center line is pre-registered in the map information 14. Therefore, the driving support device 19 can acquire, as the first boundary information, information indicating whether the center line of the road on which the vehicle V is traveling is a movable center line by the function of the acquisition unit 21. Note that although the movable center line can move in the width direction of the road, the position of the movable center line registered in the map information 14 is a representative position (for example, the position where the movable center line exists for the longest time). In the driving scene shown in FIG. 2A, the position of the center line C registered in the map information 14 is between the boundaries B3 and B4.

[0038] An explanation will be given of the acquisition of the first boundary information in the driving scene shown in FIG. 2A. First, the driving support device 19 acquires, by the function of the acquisition unit 21, the position of the vehicle V shown in FIG. 2A from the position detection device 15 as current position information. Next, the driving support device 19 acquires, from the map information 14, information on the boundaries (first boundary information) existing around the current position of the vehicle V shown in FIG. 2A. In this case, the first boundary information includes, as boundaries existing around the vehicle V, the boundaries B1 to B6 which are white lines marked on the road surface, and information on the center line C which is a movable barrier. In addition to this, as the form of the white lines, it is included that the boundaries B1 and B6 are solid lines, and the boundaries B2 to B5 are broken lines. Further, in addition to this, as the arrangement order of the boundaries, based on the boundary B1 which exists on the rightmost side with respect to the traveling direction of the vehicle V, in order from the right side of FIG. 2A, the boundary B1 which is a solid white line, the boundary B2 which is a broken white line, the boundary B3 which is a broken white line, the center line C which is a movable barrier (movable center line), the boundary B4 which is a broken white line, the boundary B5 which is a broken white line, and the boundary B6 which is a solid white line are arranged in this order.

[0039] Next, the second boundary information will be described. The driving assistance device 19 acquires the second boundary information from the detection device of the vehicle V by the function of the acquisition unit 21. The detection device of the vehicle V is, for example, the imaging device 11 and the distance measuring device 12, and the driving assistance device 19 recognizes the boundary that divides the lane from the detection results of the imaging device 11 and the distance measuring device 12. Similar to the first boundary information, the second boundary information includes information on the boundaries existing around the vehicle V (particularly, information on the type of the boundary and the position information of the boundary).

[0040] The information on the type of the boundary can be acquired, for example, from the image acquired by the imaging device 11. As an example, the driving assistance device 19 acquires an image in front of the vehicle V from the imaging device 11, performs edge detection processing on the acquired image, performs pattern matching on the image after the edge detection processing, and recognizes the boundary. Thereby, as the second boundary information, information indicating whether the boundary corresponds to a road marking or a road structure can be acquired. Further, when the recognized boundary is a line marked on the road surface, it is identified whether the line is a solid line or a broken line. Thereby, the information on the form of the road marking can also be acquired.

[0041] As another example, the driving assistance device 19 acquires the information on the type of the boundary from the detection result of the distance measuring device 12. For example, from the detection results of the radar and / or LiDAR, the information on the shape of the obstacle existing around the vehicle V and the distance from the vehicle V to the obstacle is acquired. Then, based on the information on the shape of the obstacle and the information on the distance to the obstacle, it is determined whether the obstacle corresponds to a road structure (such as a median strip, a guardrail, a curb of the road shoulder, etc.).

[0042] On the one hand, the boundary position information is obtained, for example, by integrating the detection result of the imaging device 11 and the detection result of the distance measuring device 12. As an example, the driving assistance device 19 performs image processing such as pattern matching on the image obtained from the imaging device 11, and recognizes the type of boundary existing around the vehicle V from features such as the shape of the object. Next, from the detection result of the distance measuring device 12 (for example, radar), the distance to the boundary existing around the vehicle V and the position of the boundary based on the position of the vehicle V are detected. Thereby, the information on the type of boundary, the distance from the vehicle V to the boundary, and the boundary position information can be obtained as the second boundary information.

[0043] In addition, when the driving assistance device 19 recognizes the type of boundary from the detection results of the imaging device 11 and the distance measuring device 12, the driving assistance device 19 determines whether the boundary is the center line of the road on which the vehicle V travels. Then, when it is recognized that the boundary is the center line, it is determined whether the boundary is movable in the width direction of the road (that is, whether the boundary is a movable center line). Specifically, the shape of the object corresponding to the movable center line is registered in the program in advance, and when performing pattern matching on the image obtained from the imaging device 11, it is determined whether the object of the registered shape is included. Instead of or in addition to this, it is determined whether the shape of the obstacle obtained from the detection results of the radar and / or LiDAR (distance measuring device 12) matches the shape of the pre-registered movable center line. Thereby, the driving assistance device 19 can obtain, as the second boundary information, information indicating whether there is a movable center line around the vehicle V.

[0044] The acquisition of the second boundary information in the driving scene shown in FIG. 2A will be described. First, the driving assistance device 19 acquires the detection results of the imaging device 11 and the distance measuring device 12 by the function of the acquisition unit 21. Assuming that the range in which the imaging device 11 and the distance measuring device 12 can detect the object is the detection area X shown in FIG. 2A, the driving assistance device 19 performs image processing such as edge detection and pattern matching on the image acquired from the imaging device 11, and recognizes the boundaries B1 to B3 which are white lines marked on the road surface. Further, as the form of the white line, it is recognized that the boundary B1 is a solid line, and the boundaries B2 and B3 are broken lines. Furthermore, the driving assistance device 19 recognizes the center line C existing on the left side of the vehicle V from the above-described pattern matching.

[0045] Next, from the detection results of the radar and / or LiDAR (distance measuring device 12), the distance from the vehicle V to the center line C and the position of the center line C with respect to the vehicle V are detected. In this case, the position information of the center line C includes, for example, that the center line C exists on the left side of the vehicle V. In addition to this, the driving assistance device 19 determines whether the recognized center line C is a movable center line or not. In the driving scene shown in FIG. 2A, since the center line C is a movable barrier, it is determined that the center line C is a movable center line. The driving assistance device 19 acquires these pieces of information as the second boundary information.

[0046] Also, based on the distance from the vehicle V to the center line C and the direction in which the boundaries B1 to B3 and the center line C are located with respect to the vehicle V, the order of the boundaries is obtained in the same manner as in the case of the first boundary information. In the driving scene of FIG. 2A, on the right side of the vehicle, a solid white line boundary B1 and a dashed white line boundary B2 are arranged, and on the left side of the vehicle, a dashed white line boundary B3 and a movable barrier center line C are arranged. Therefore, on the right side in the traveling direction of the vehicle V, with the boundary B1 located at the position farthest from the vehicle V as a reference, in order from the right side of FIG. 2A, the solid white line boundary B1, the dashed white line boundary B2, the vehicle V, the dashed white line boundary B3, and the movable barrier center line C are recognized as being arranged in this order. The difference from the order of the boundaries of the first boundary information is that the position of the vehicle V is included in the order. The driving support device 19 acquires the said order as the second boundary information.

[0047] When the driving support device 19 acquires the second boundary information in the driving scene of FIG. 2A, by the function of the control unit 20, the drivable area Y1 is recognized as an area where the vehicle V can travel without contacting an obstacle. The drivable area Y1 is an area within the detection area X surrounded by the boundary B1 and the center line C. The driving support device 19 autonomously controls the travel of the vehicle V by the vehicle control device 17 so that the vehicle V travels within the drivable area Y1.

[0048] The detection unit 22 has a function of detecting the movable center line of the road (that is, the detection function). The driving support device 19 detects the movable center line from at least one of the first boundary information and the second boundary information by the function of the detection unit 22. As described above, the first boundary information and the second boundary information include information indicating whether the center line of the road on which the vehicle V travels is a movable center line. Therefore, the driving support device 19 can detect the movable center line based on the first boundary information and the second boundary information.

[0049] For example, in the driving scene shown in FIG. 2A, the driving assistance device 19 detects a movable barrier (center line C) on the road on which the vehicle V is traveling based on the first boundary information. Alternatively or in addition to this, the driving assistance device 19 detects a movable barrier (center line C) existing on the left side of the vehicle V based on the second boundary information.

[0050] Further, when the detection unit 22 detects a movable center line from the second boundary information, it has a function of determining whether the position of the movable center line is within an adjacent lane of the driving lane on which the vehicle V is traveling. Specifically, two boundaries defining the driving lane of the vehicle V are extracted from the second boundary information, and the distance between each of the two extracted boundaries and the movable center line is obtained. The distance shall be the distance along the width direction of the road on which the vehicle V is traveling. Then, when either one of the obtained distances is smaller than the width of one lane of the road on which the vehicle is traveling, it is determined that the position of the movable center line is within the adjacent lane of the driving lane on which the vehicle V is traveling. On the contrary, when both of the obtained two distances are equal to or greater than the width of one lane of the road on which the vehicle is traveling, it is determined that the position of the movable center line is not within the adjacent lane of the driving lane on which the vehicle V is traveling.

[0051] Using the driving scene shown in FIG. 2A, the above-described determination will be specifically described. First, the driving assistance device 19 extracts boundaries B2 and B3 that define the lane L2 on which the vehicle V is traveling from the second boundary information. Then, the distances between the boundaries B2 and B3 and the movable barrier (center line C) are obtained. Since the movable barrier is a block and has a wider width than the line marked on the road surface, the distance between the boundary B3 and the movable barrier (center line C) is smaller than the width of the lane L3. Therefore, in the driving scene shown in FIG. 2A, it is determined that the position of the movable barrier (movable center line) is within the lane L3, which is the adjacent lane of the lane L2 on which the vehicle V is traveling.

[0052] Furthermore, the detection unit 22 has a function of determining whether the boundary of the driving lane on which the vehicle V travels is a movable center line. Specifically, from the second boundary information, two boundaries that define the driving lane of the vehicle V are extracted, and it is determined whether either one of the two extracted boundaries is a movable center line. If either one of the two extracted boundaries is a movable center line, it is determined that the boundary of the driving lane on which the vehicle V travels is a movable center line. On the other hand, if neither of the two extracted boundaries is a movable center line, it is determined that the boundary of the driving lane on which the vehicle V travels is not a movable center line.

[0053] For example, in the driving scene shown in FIG. 2A, from the second boundary information, the boundaries that define the lane L2 on which the vehicle V travels are extracted as boundary B2 and boundary B3. Therefore, it is determined that the boundary of the lane L2 on which the vehicle V travels is not a movable center line.

[0054] The recognition unit 23 has a function (i.e., a recognition function) of recognizing the driving lane of the vehicle. The driving support device 19 collates the first boundary information and the second boundary information according to the function of the recognition unit 23 to recognize the driving lane of the vehicle V. Thereby, the driving lane of the vehicle V can be recognized more accurately.

[0055] When collating the first boundary information and the second boundary information, for example, the types of boundaries included in the first boundary information and the types of boundaries included in the second boundary information are compared in order from the right side or the left side with respect to the traveling direction of the vehicle V. Specifically, the comparison starts from the boundary existing on the rightmost or leftmost side with respect to the traveling direction of the vehicle V, and the comparison of the boundaries is performed until the position of the vehicle V included in the second boundary information is reached. The comparison of the boundaries is performed only on either the right side or the left side in the traveling direction of the vehicle V, but it may also be performed on both the right side and the left side.

[0056] Regarding the comparison of boundaries, the driving scene shown in FIG. 2A will be used for explanation. In the driving scene shown in FIG. 2A, for the order of the boundaries of the first boundary information, based on the boundary B1 that exists on the rightmost side with respect to the driving direction of the vehicle V, the boundaries are the solid white line boundary B1, the dashed white line boundary B2, the dashed white line boundary B3, the movable barrier center line C, the dashed white line boundary B4, the dashed white line boundary B5, and the solid white line boundary B6 in this order. On the other hand, for the order of the boundaries of the second boundary information, on the right side of the driving direction of the vehicle V, based on the boundary B1 that exists at the position farthest from the vehicle V, the boundaries are the solid white line boundary B1, the dashed white line boundary B2, the vehicle V, the dashed white line boundary B3, and the movable barrier center line C in this order.

[0057] In this case, when comparing the boundary type information of the first boundary information with the boundary type information of the second boundary information, on the right side of the vehicle V, the order of the solid white line boundary B1 and the dashed white line boundary B2 matches. Also, on the left side of the vehicle V, the order of the dashed white line boundary B3 and the movable barrier center line C matches. Based on this comparison result, lanes where the order of the boundaries matches on the right and left sides of the vehicle V are searched. In the driving scene shown in FIG. 2A, assuming that the vehicle V is driving in lane L2, the order of the boundaries matches on the right side of the vehicle V. Therefore, the driving support device 19 recognizes that the driving lane of the vehicle V is lane L2. The driving support device 19 outputs to the display device 18 that the recognized driving lane is lane L2.

[0058] Further, when the recognized lane initially estimated and the recognized lane recognized as a result of the collation are different, the recognition unit 23 has a function of correcting the initially estimated driving lane. The driving support device 19 calculates a correction amount for correcting the driving lane by the function of the recognition unit 23, and corrects the initially estimated driving lane using the calculated correction amount. The initially estimated driving lane is corrected so as to coincide with the recognized lane recognized as a result of the collation. The correction amount for correcting the driving lane is equal to the distance for moving from the initially estimated driving lane to the recognized lane recognized as a result of the collation along the width direction of the road on which the vehicle V travels. For example, in the driving scene shown in FIG. 2A, when the width of one lane is 3.5 m and the initially estimated lane is lane L4, the calculated correction amount is 3.5 × 2 = 7 (m). The corrected driving lane is output to the display device 18.

[0059] When the movable center line is detected by the detection unit 22, the recognition unit 23 of the present embodiment has a function of not collating the first boundary information and the second boundary information on the side where the movable center line is detected, either on the right side or the left side of the vehicle V. Thereby, the misrecognition of the driving lane of the vehicle V is suppressed. Hereinafter, this function will be described with reference to FIG. 2B.

[0060] The driving scene shown in FIG. 2B is a scene in which the center line C, which is a movable barrier, has been moved to the right with respect to the traveling direction of the vehicle V in the driving scene of FIG. 2A. In the driving scene shown in FIG. 2B, as in the driving scene shown in FIG. 2A, the vehicle V is traveling in lane L2. However, the center line C is not between lane L3 and lane L4, but is located between lane L2 and lane L3. Therefore, the traveling direction of lanes L1 to L2 is from the lower side to the upper side in FIG. 2A, and the traveling direction of lanes L3 to L6 is from the upper side to the lower side in FIG. 2A. The difference from the driving scene shown in FIG. 2A is that as the lane boundaries, lane L2 is defined by boundary B2 and the center line C, lane L3 is defined by the center line C and boundary B3a, and lane L4 is defined by boundary B3a and boundary B4.

[0061] In this case, the first boundary information acquired by the driving assistance device 19 is the same as that of the driving scene shown in FIG. 2A. This is because the position of the movable center line registered in the map information 14 is only a representative position, and the position of the movable barrier moved from the representative position cannot be acquired from the map information 14. On the other hand, the second boundary information acquired by the driving assistance device 19 is different from that of the driving scene shown in FIG. 2A. This is because the imaging device 11 and the distance measuring device 12 can detect the position of the movable barrier after movement.

[0062] The acquisition of the second boundary information in the driving scene shown in FIG. 2B will be described. First, the driving assistance device 19 acquires the detection results of the imaging device 11 and the distance measuring device 12 in the detection area X shown in FIG. 2B by the function of the acquisition unit 21. The driving assistance device 19 recognizes the boundaries B1, B2, and B3a, which are white lines marked on the road surface, from the image acquired from the imaging device 11. Further, as the form of the white line, it is recognized that the boundary B1 is a solid line, and the boundaries B2 and B3a are broken lines. Furthermore, the driving assistance device 19 recognizes the center line C existing on the left side of the vehicle V.

[0063] Next, from the detection results of the distance measuring device 12 (such as a radar), the distance from the vehicle V to the center line C and the position of the center line C with respect to the vehicle V are detected. In this case, the position information of the center line C includes that the center line C exists on the left side of the vehicle V. In addition to this, the driving assistance device 19 determines whether the recognized center line C is a movable center line. In the driving scene shown in FIG. 2B, since the center line C is a movable barrier, it is determined that the center line C is a movable center line. The driving assistance device 19 acquires these pieces of information as the second boundary information.

[0064] Also, based on the distance from the vehicle V to the center line C, the boundaries B1 to B3 a and the direction in which the center line C is located, the order of the boundaries is acquired. In the driving scene of FIG. 2B, since the center line C is located between the lane L2 and the lane L3, with the boundary B1 as a reference, in order from the right side of FIG. 2A, the boundary B1, which is a solid white line, the boundary B2, which is a broken white line, the vehicle V, the center line C, which is a movable barrier, and the boundary B3, which is a broken white linea It is recognized that the boundaries are arranged in the order of. The driving support device 19 acquires the order as the second boundary information.

[0065] When the driving support device 19 acquires the second boundary information in the driving scene of FIG. 2B, the control unit 20 functions to recognize the drivable area Y2 as an area where the vehicle V can travel without contacting an obstacle. The drivable area Y2 is an area within the detection area X that is surrounded by the boundary B1 and the center line C. Different from the driving scene shown in FIG. 2A, in the driving scene shown in FIG. 2B, since the vehicle V cannot travel in lane L3, the drivable area Y2 shown in FIG. 2B is narrower than the drivable area Y1 by the width of lane L3.

[0066] Next, a comparison of the boundaries in the driving scene shown in FIG. 2B will be described. In the driving scene shown in FIG. 2B, the order of the boundaries of the first boundary information is the same as that in the driving scene shown in FIG. 2A. Based on the boundary B1, the boundaries are, in order, the solid white line boundary B1, the dashed white line boundary B2, the dashed white line boundary B3, the movable barrier center line C, the dashed white line boundary B4, the dashed white line boundary B5, and the solid white line boundary B6. In contrast, the order of the boundaries of the second boundary information is, based on the boundary B1, the solid white line boundary B1, the dashed white line boundary B2, the vehicle V, the movable barrier center line C, and the dashed white line boundary B3a.

[0067] In this case, when comparing the information on the types of boundaries of the first boundary information and the information on the types of boundaries of the second boundary information, on the right side of the vehicle V, the order of the solid white line boundary B1 and the dashed white line boundary B2 matches. In contrast, on the left side of the vehicle V, the order of the boundaries does not match. That is, in the first boundary information, on the right side of the driving direction of the vehicle V, in order from the right, the dashed white line boundary B3 and the movable barrier center line C are arranged as boundaries, while in the second boundary information, the movable barrier center line C and the dashed white line boundary B3a are arranged as boundaries.

[0068] Based on the comparison results on the right side of the vehicle V, when searching for lanes with the same boundary order, similar to the driving scene shown in FIG. 2A, it is recognized that lane L2 is the driving lane of the vehicle V. In contrast, in the comparison results on the left side of the vehicle V, since the boundary order of the first boundary information does not match the boundary order of the second boundary information, it is impossible to search for lanes with the same boundary order, and the driving lane of the vehicle V cannot be accurately recognized. If the driving lane of the vehicle V cannot be accurately recognized, the driving lane displayed on the display device 18 will be different from the lane on which the vehicle V is actually driving, which will give the passengers a sense of discomfort. In addition, inaccurate recognition of the driving lane leads to the generation of an inaccurate driving route by the navigation device 16. Therefore, when the movable center line is detected by the detection unit 22, the driving support device 19 does not perform the collation between the first boundary information and the second boundary information on the side where the movable center line is detected (the left side in the driving scene shown in FIG. 2B) among the right side and the left side of the vehicle V, but performs the collation between the first boundary information and the second boundary information on the opposite side of the side where the movable center line is detected (the right side in the driving scene shown in FIG. 2B).

[0069] As shown in the driving scenes of FIGS. 2A and 2B, after the movable center line is detected, when the movable center line is no longer detected, the recognition unit 23 has a function of restarting the collation between the first boundary information and the second boundary information on the side where the movable center line is no longer detected. For example, in the driving scene shown in FIG. 2B, when the movable barrier located on the left side of the vehicle V is no longer detected, the driving support device 19 restarts the collation between the first boundary information and the second boundary information on the left side of the vehicle V.

[0070] In addition, when the detection unit 22 determines that the position of the movable center line is within the adjacent lane of the driving lane of the vehicle V, the recognition unit 23 has a function of not performing the collation between the first boundary information and the second boundary information on the side where the movable center line is detected. Also, when the detection unit 22 determines that the movable center line is the boundary of the driving lane of the vehicle V, the recognition unit 23 has a function of not performing the collation between the first boundary information and the second boundary information on the side where the movable center line is detected.

[0071] However, when it is determined that the position of the movable center line is not within the adjacent lane and the movable center line is not the boundary of the travel lane of the vehicle V, exceptionally, the collation between the first boundary information and the second boundary information may be performed on the side where the movable center line is detected. For example, in the driving scene shown in FIG. 2B, when the position of the movable barrier (center line C) is located between the lanes L5 and L6, the driving support device 19 can perform the collation between the first boundary information and the second boundary information on the left side of the vehicle V. This is because if the position of the vehicle V and the movable center line is far apart, the influence on the collation between the first boundary information and the second boundary information will not be so great.

[0072] The estimation unit 24 has a function of estimating the travel position of the vehicle (that is, the estimation function). After the driving support device 19 recognizes the travel lane of the vehicle V by the function of the recognition unit 23, the driving support device 19 acquires the travel state information of the vehicle V from the state detection device 13 by the function of the estimation unit 24. Examples of the travel state information include vehicle speed information, acceleration information, yaw rate information, and steering angle information. Next, the driving support device 19 calculates the movement amount of the vehicle V from the travel state information, and calculates the predicted position of the vehicle V from the calculated movement amount. Then, the predicted position of the vehicle V is collated with the map information 14 and the current position information, and the current position is updated using the collated predicted position. The updated current position information is output to the display device 18.

[0073] [Processing in the Driving Support System] With reference to FIGS. 3A and 3B, the procedure when the driving support device 19 processes information will be described. FIGS. 3A and 3B are examples of flowcharts showing the processing of information executed in the driving support system 10 of the present embodiment. The processing described below is executed at predetermined time intervals by the CPU 191 which is a processor of the driving support device 19.

[0074] First, in step S1, the acquisition unit 21 obtains the current position information of the vehicle V from the position detection device 15. In the subsequent step S2, the first boundary information is obtained from the map information 14, and in step S3, the second boundary information is obtained from the imaging device 11 and the distance measuring device 12. Next, in step S4, the recognition unit 23 estimates the driving lane of the vehicle V using the first boundary information and / or the second boundary information.

[0075] In step S5, the detection unit 22 detects the movable center line existing on the right side or the left side of the vehicle V from the first boundary information and / or the second boundary information. In the subsequent step S6, it is determined whether the movable center line is detected on the left side of the vehicle V. If it is determined that the movable center line is not detected on the left side of the vehicle V, the process proceeds to step S7, and the recognition unit 23 compares the order of the boundaries of the first boundary information and the second boundary information on the left side of the vehicle V. On the other hand, if it is determined that the movable center line is detected on the left side of the vehicle V, the process proceeds to step S8. In step S8, the detection unit 22 determines whether the position of the movable center line is not within the adjacent lane on the left side of the vehicle V and whether the movable center line is not the boundary on the left side of the driving lane of the vehicle V. If it is determined that the position of the movable center line is not within the adjacent lane on the left side of the vehicle V and the movable center line is not the boundary on the left side of the driving lane of the vehicle V, the process proceeds to step S7, and the order of the boundaries of the first boundary information and the second boundary information is compared on the left side of the vehicle V. On the other hand, if it is determined that the position of the movable center line is within the adjacent lane on the left side of the vehicle V or the movable center line is the boundary on the left side of the driving lane of the vehicle V, the process proceeds to step S9 without performing the collation between the first boundary information and the second boundary information on the left side of the vehicle V.

[0076] In step S9, it is determined whether a movable center line is detected on the right side of the vehicle V. If it is determined that the movable center line is not detected on the right side of the vehicle V, the process proceeds to step S10, and the function of the recognition unit 23 is used to compare the order of the boundaries between the first boundary information and the second boundary information on the right side of the vehicle V. On the other hand, if it is determined that the movable center line is detected on the right side of the vehicle V, the process proceeds to step S11. In step S11, the function of the detection unit 22 is used to determine whether the position of the movable center line is not within the adjacent lane on the right side of the vehicle V and whether the movable center line is not the boundary on the right side of the driving lane of the vehicle V. If it is determined that the position of the movable center line is not within the adjacent lane on the right side of the vehicle V and the movable center line is not the boundary on the right side of the driving lane of the vehicle V, the process proceeds to step S10, and the order of the boundaries between the first boundary information and the second boundary information is compared on the right side of the vehicle V. On the other hand, if it is determined that the position of the movable center line is within the adjacent lane on the right side of the vehicle V or the movable center line is the boundary on the right side of the driving lane of the vehicle V, the comparison between the first boundary information and the second boundary information is not performed on the right side of the vehicle V, and the process proceeds to step S12.

[0077] In step S12, the function of the recognition unit 23 is used to determine whether there is a lane in which the order of the boundaries matches when the driving lane of the vehicle V is assumed. In the determination in step S12, it is sufficient that the order of the boundaries matches on either the right side or the left side of the vehicle V, and it is not necessary for the order of the boundaries to match on both the right side and the left side of the vehicle V. If it is determined that there is no lane in which the order of the boundaries matches, since the driving lane of the vehicle V cannot be accurately recognized, the driving support by the driving support device 19 is terminated. At this time, the display device 18 is used to request the driver to perform an operation by manual driving. On the other hand, if it is determined that there is a lane in which the order of the boundaries matches, the process proceeds to step S13.

[0078] In step S13, the function of the recognition unit 23 calculates a correction amount for matching the driving lane estimated in step S4 with the driving lane recognized in step S12. In the subsequent step S14, the driving lane estimated in step S4 is corrected using the correction amount calculated in step S13. In the subsequent step S15, the corrected driving lane is output to the display device 18 as the driving lane of the vehicle V.

[0079] In step S16, the function of the estimation unit 24 acquires the driving state information of the vehicle V (for example, vehicle speed information, acceleration information, and yaw rate information). In the subsequent step S17, the movement amount of the vehicle V is calculated from the driving state information, and in step S18, the predicted position of the vehicle V is calculated from the calculated movement amount. In the subsequent step S19, the predicted position of the vehicle V is compared with the map information 14 and the current position information, and in step S20, the current position is updated using the compared predicted position. Then, in step S21, the updated current position information is output to the display device 18.

[0080] [Embodiments of the Present Invention] As described above, according to the present embodiment, in a lane recognition method in which a processor is used to compare the first boundary information of the boundary that divides the lane, acquired from the map information 14, with the second boundary information of the boundary that divides the lane, acquired from the detection device of the vehicle V, and recognize the driving lane of the vehicle V, the processor detects a movable center line C that is a center line movable in the width direction of the road on which the vehicle V travels, from at least one of the first boundary information and the second boundary information. When the movable center line is detected, a lane recognition method is provided in which the comparison between the first boundary information and the second boundary information is not performed on the side where the movable center line is detected, out of the right side and the left side of the vehicle V. Thereby, when the vehicle V is traveling on a road where the position of the center line moves, it is possible to suppress misrecognition of the traveling position of the vehicle V.

[0081] Also, according to the lane recognition method of the present embodiment, after the movable center line is detected, when the movable center line is no longer detected, the processor resumes the collation on the side where the movable center line is no longer detected. Thereby, the collation between the first boundary information and the second boundary information can be controlled according to the state of the road on which the vehicle V travels.

[0082] Also, according to the lane recognition method of the present embodiment, when the movable center line is detected from the second boundary information, the processor determines whether the position of the movable center line is within the adjacent lane of the driving lane and whether the movable center line is the boundary of the driving lane. When it is determined that the position of the movable center line is within the adjacent lane or when it is determined that the movable center line is the boundary of the driving lane, the collation is not performed on the side where the movable center line is detected. When it is determined that the position of the movable center line is not within the adjacent lane and that the movable center line is not the boundary of the driving lane, the collation is performed on the side where the movable center line is detected. Thereby, when the detected movable center line does not have a great influence on the collation between the first boundary information and the second boundary information, the collation between the first boundary information and the second boundary information can be performed on both the right side and the left side of the vehicle V. As a result, even when traveling on a road with a movable center line, misrecognition of the traveling position of the vehicle V can be suppressed.

[0083] Also, according to the lane recognition method of the present embodiment, when the movable center line is detected, the processor performs the collation on the side opposite to the side where the movable center line is detected. Thereby, when the vehicle V is traveling on a road where the movable center line is arranged, since the collation between the first boundary information and the second boundary information is performed on either the right side or the left side of the vehicle V, misrecognition of the traveling position of the vehicle V can be further suppressed.

[0084] Moreover, according to the lane recognition method of the present embodiment, the first boundary information includes the type of the boundary of the lane on the road on which the vehicle V travels, the second boundary information includes the type of the boundary of the lane detected by the detection device, and when performing the collation, the processor compares the type of the boundary included in the first boundary information and the type of the boundary included in the second boundary information in order from the right side or the left side with respect to the traveling direction of the vehicle V. Thereby, the collation between the first boundary information and the second boundary information can be performed more accurately.

[0085] Moreover, according to the present embodiment, there is provided a lane recognition device including: a recognition unit 23 that collates first boundary information of a boundary that divides a lane, acquired from map information 14, with second boundary information of the boundary that divides the lane, acquired from a detection device of the vehicle V, to recognize a traveling lane of the vehicle V; and a detection unit 22 that detects a movable center line C, which is a center line movable in the width direction of the road on which the vehicle V travels, from at least one of the first boundary information and the second boundary information. When the detection unit 22 detects the movable center line, the recognition unit 23 does not perform the collation between the first boundary information and the second boundary information on the side where the movable center line is detected, out of the right side and the left side of the vehicle V. Thereby, when the vehicle V is traveling on a road where the position of the center line moves, it is possible to suppress misrecognition of the traveling position of the vehicle V.

Explanation of Signs

[0086] 10... Driving support system 11... Imaging device 12... Distance measuring device 13... State detection device 14... Map information 15... Position detection device 16... Navigation device 17... Vehicle control device 171... Vehicle speed control device 172... Steering control device 18... Display device 19... Driving support device (lane recognition device) 191... CPU (Processor) 192…ROM 193…RAM 20…Control unit 21…Acquisition unit 22…Detection unit 23…Recognition unit 24…Estimation unit B1, B2, B3, B3a, B4, B5, B6…Boundary C…Center line L1, L2, L3, L4, L5, L6…Lane X…Detection area Y1, Y2…Drivable area V…Vehicle

Claims

1. In a lane recognition method for recognizing a travel lane of a vehicle by collating first boundary information of a boundary that divides a lane, obtained from map information, with second boundary information of the boundary that divides the lane, obtained from a vehicle detection device, using a processor, the processor: detects a movable center line, which is a center line movable in the width direction of the road on which the vehicle travels, from at least one of the first boundary information and the second boundary information; When the movable center line is detected, a lane recognition method in which the collation between the first boundary information and the second boundary information is not performed on the side where the movable center line is detected, out of the right side and the left side of the vehicle.

2. The lane recognition method according to claim 1, wherein after the movable center line is detected, when the movable center line is no longer detected, the processor resumes the collation on the side where the movable center line is no longer detected.

3. The processor: When the movable center line is detected from the second boundary information, determines whether the position of the movable center line is within an adjacent lane of the travel lane and whether the movable center line is a boundary of the travel lane; When it is determined that the position of the movable center line is within the adjacent lane or it is determined that the movable center line is a boundary of the travel lane, the collation is not performed on the side where the movable center line is detected; The lane recognition method according to claim 1 or 2, wherein when it is determined that the position of the movable center line is not within the adjacent lane and it is determined that the movable center line is not a boundary of the travel lane, the collation is performed on the side where the movable center line is detected.

4. The lane recognition method according to any one of claims 1 to 3, wherein when the movable center line is detected, the processor performs the collation on the side opposite to the side where the movable center line is detected.

5. The first boundary information includes the type of the boundary of the lane on the road on which the vehicle travels; The second boundary information includes the type of the boundary of the lane detected by the detection device; The lane recognition method according to any one of claims 1 to 4, wherein when performing the collation, the processor compares the type of the boundary included in the first boundary information and the type of the boundary included in the second boundary information in order from the right side or the left side with respect to the travel direction of the vehicle.

6. A recognition unit that recognizes the driving lane of the vehicle by collating first boundary information of a boundary that divides a lane, obtained from map information, and second boundary information of the boundary that divides the lane, obtained from a detection device of the vehicle; A detection unit that detects a movable center line, which is a center line movable in the width direction of the road on which the vehicle travels, from at least one of the first boundary information and the second boundary information; and The recognition unit is a lane recognition device that does not collate the first boundary information and the second boundary information on the side where the movable center line is detected, out of the right side and the left side of the vehicle, when the movable center line is detected by the detection unit.

Images