JP2023151306A - Runway estimation method and runway estimation device - Google Patents

Abstract

To suppress a decrease in the accuracy of estimating a runway due to that the runway of the host vehicle is estimated using road shapes of map data, when the road shapes of map data differ from the actual lane shapes.SOLUTION: The present invention includes: detecting a vehicle position that is the current position of the host vehicle; extracting a first road shape that represents the road shape of a first road along which the host vehicle travels, from map data in which road shapes are expressed in road units by arrangement of a plurality of nodes; detecting a road boundary shape that represents the shape of edges of the first road in the road width direction, along the extension direction of the first road; determining whether or not the first road shape and the road boundary shape agree; estimating a runway that represents a travel track along the first road on the basis of the first road shape or the road boundary shape, when the first road shape and the road boundary shape agree; and estimating a runway without using the first road shape, when the first road shape and the road boundary shape do not agree.SELECTED DRAWING: Figure 8

Description

The present invention relates to a route estimation method and a route estimation device.

Patent Document 1 discloses a method that reads position data of nodes that are road marking points located before and after the current position of the vehicle from a road map database, estimates the shape of the vehicle's road from a plurality of nodes, and controls the illumination of headlights. The techniques used are described.

Patent No. 4363640 specification

In the case of map data in which the shape of a road is expressed on a road-by-road basis by an array of multiple nodes, each node often indicates a position near the center of the road. Therefore, in places where the number of lanes increases, such as near the entrance of an intersection, the position of the node in the lane width direction moves in the direction where the number of lanes increases, so the shape represented by the arrangement of nodes differs from the actual lane shape. In such a case, if the route on which the host vehicle travels is estimated based on the road shape of the map data in autonomous driving control or driving support control, there is a risk that the estimation accuracy will be lowered.
An object of the present invention is to suppress a decrease in the accuracy of estimating the driving route by estimating the driving route of a vehicle using the road shape of the map data when the road shape of the map data differs from the actual lane shape. shall be.

In the driving route estimation method of the present invention, the vehicle position, which is the current position of the vehicle, is detected, and the road shape is expressed for each road by an array of nodes. A first road shape that is the road shape of one road is extracted, a road boundary shape that is a shape along the extending direction of the first road at the end of the first road in the road width direction is detected, and the first road shape is extracted. and the road boundary shape, and if the first road shape and the road boundary shape match, the travel trajectory along the first road is determined based on the first road shape or the road boundary shape. If the first road shape and the road boundary shape do not match, the travel route is estimated without using the first road shape.

According to the present invention, when the road shape of the map data differs from the actual lane shape, by estimating the route of the own vehicle using the road shape of the map data, it is possible to suppress a decrease in the accuracy of route estimation.

1 is a diagram illustrating an example of a schematic configuration of a vehicle equipped with a travel control device according to an embodiment. It is a schematic diagram of map data stored in a map database. FIG. 2 is a block diagram of an example of the functional configuration of the controller in FIG. 1. FIG. (a) is a schematic diagram of a method of calculating parallelism between a road shape and a road boundary shape, and (b) is a schematic diagram of a method of calculating a matching score between a road shape and a road boundary shape. FIG. 3 is a schematic diagram of the road shape of a second road, which is a road on which an oncoming vehicle travels. FIG. 3 is a schematic diagram of an example of a method for estimating a driving route in and near an intersection. FIG. 3 is a schematic diagram of an example of a road marking that foretells a branch between a straight lane and a right turn lane. It is a flowchart of an example of the route estimation method of an embodiment.

Embodiments of the present invention will be described below with reference to the drawings. Note that each drawing is schematic and may differ from the actual drawing. In addition, the embodiments of the present invention shown below illustrate devices and methods for embodying the technical idea of the present invention. is not limited to the following: The technical idea of the present invention can be modified in various ways within the technical scope defined by the claims.

(composition)
The host vehicle 1 includes a travel control device 10 that supports travel of the host vehicle 1. The driving control device 10 supports the driving of the own vehicle 1 by detecting the driving environment around the own vehicle 1 and automatically controlling the driving of the own vehicle 1 based on the detected driving environment. The travel control device 10 is an example of a "travel estimating device" described in the claims.
For example, the driving support for the own vehicle 1 by the driving control device 10 may include autonomous driving control in which the own vehicle 1 is automatically driven without involvement of a passenger (for example, a driver). Further, for example, the travel support of the host vehicle 1 by the travel control device 10 may include automatically controlling at least the steering angle of the host vehicle 1. Further, for example, the travel support of the host vehicle 1 by the travel control device 10 may include automatically controlling the driving force or braking force in addition to automatically controlling the steering angle of the host vehicle 1.

The travel control device 10 includes a positioning device 11 , a map database 12 , an external sensor 14 , a vehicle sensor 15 , a controller 16 , and an actuator 17 . Note that in the drawings, the map database is referred to as "map DB."
The positioning device 11 measures the current position of the own vehicle 1. In the following description, the current position of the own vehicle 1 will be referred to as "the own vehicle position." The positioning device 11 may include, for example, a Global Positioning System (GNSS) receiver. The GNSS receiver is, for example, a global positioning system (GPS) receiver or the like, and measures the position of the vehicle by receiving radio waves from a plurality of navigation satellites.

The map database 12 stores map data. The map data stored in the map database 12 may be, for example, navigation map data that includes information for each road. The map data for navigation may be data in which the shape of a road is expressed on a road-by-road basis by a string of nodes.
See FIG. 2. Each circle plot N drawn in the figure represents a node of map data. The same applies to FIGS. 4 to 6. In the example of FIG. 2, the road shape RS1 of the road R1 (hereinafter referred to as "first road R1") on which the host vehicle 1 travels is expressed in units of roads by a node string of a plurality of nodes N.

In this specification, a node string may be, for example, an arrangement of a plurality of nodes N, or an arrangement of a plurality of nodes N and a line segment (link L) connecting these nodes N with a curve or a straight line. It may also be data that includes. In other words, a node string represents an arrangement of a plurality of nodes N, that is, the shape of a road on a map, and only needs to include an arrangement of a plurality of nodes N, and is limited to an arrangement of a plurality of nodes N. Not done.

Please refer to FIG. The external sensor 14 detects various information about the environment around the own vehicle 1 (surrounding environment information). For example, the external sensor 14 detects objects around the host vehicle 1 . The external sensor 14 detects the surrounding environment of the own vehicle 1, such as objects existing around the own vehicle 1, the relative position between the own vehicle 1 and the object, the distance between the own vehicle 1 and the object, and the direction in which the object exists. . The external sensor 14 outputs detected information about the surrounding environment to the controller 16 as surrounding environment information.
For example, the external sensor 14 detects the relative positions of other vehicles and targets around the host vehicle 1 with respect to the host vehicle 1. Targets here include, for example, traffic lights installed on the road on which the host vehicle 1 is traveling, lines on the road surface (white lines, stop lines, lane boundaries, lane markings, etc.), curbs on the road shoulder, guardrails, poles, etc. A fence, a cat's eye, a block, etc.

The external sensor 14 may include a monocular camera, such as a full HD resolution color camera. The camera captures an image that includes a recognition target of the surrounding environment of the host vehicle 1, and outputs the captured image to the controller 16 as surrounding environment information.
Further, the external sensor 14 may include a distance measuring device such as a laser range finder (LRF), a radar, or a LiDAR (Light Detection and Ranging) laser radar. The distance measuring device detects, for example, a relative position determined by a relative distance and direction to objects existing around the host vehicle. The distance measuring device outputs the detected distance data to the controller 16 as surrounding environment information.

Vehicle sensor 15 detects various information (vehicle information) obtained from own vehicle 1 . The vehicle sensor 15 includes, for example, a vehicle speed sensor that detects the running speed (vehicle speed) of the own vehicle 1, a wheel speed sensor that detects the rotational speed of each tire included in the own vehicle 1, and an acceleration ( a 3-axis acceleration sensor (G sensor) that detects the steering angle (including deceleration), a steering angle sensor that detects the steering angle of the steering wheel, a turning angle sensor that detects the turning angle of the steered wheels, and the steering angle sensor that detects the turning angle of the steering wheel. It includes a gyro sensor that detects angular velocity, a yaw rate sensor that detects yaw rate, an accelerator sensor that detects the amount of operation of the accelerator pedal of the host vehicle 1, and a brake sensor that detects the amount of brake operation by the driver.

The controller 16 is an electronic control unit (ECU) that controls the running of the host vehicle 1 . When controlling the running of the own vehicle 1, the controller 16 automatically controls the running of the own vehicle 1 based on the surrounding environment. Note that the controller 16 may be configured as a single electronic control unit, or may be configured as a set of multiple electronic control units.
The controller 16 includes a processor 20 and peripheral components such as a storage device 21. The processor 20 may be, for example, a CPU (Central Processing Unit) or an MPU (Micro-Processing Unit).
The storage device 21 may include a semiconductor storage device, a magnetic storage device, an optical storage device, or the like. The storage device 21 may include memories such as a register, a cache memory, a ROM (Read Only Memory) used as a main storage device, and a RAM (Random Access Memory).
The functions of the controller 16 described below are realized, for example, by the processor 20 executing a computer program stored in the storage device 21.

Note that the controller 16 may be formed from dedicated hardware for executing each information process described below. For example, the controller 16 may include a functional logic circuit set in a general-purpose semiconductor integrated circuit. For example, the controller 16 may include a programmable logic device (PLD) such as a field-programmable gate array (FPGA).

The actuator 17 operates the accelerator opening and the brake device of the own vehicle 1 in response to a control signal from the controller 16 to generate a driving force for driving the own vehicle 1 or a braking force for braking the own vehicle 1 . The actuator 17 includes an accelerator opening actuator and a brake control actuator. The accelerator opening actuator controls the accelerator opening of the host vehicle 1 . The brake control actuator controls the braking operation of the brake device of the own vehicle 1.
Furthermore, the actuator 17 may include a steering actuator that controls the steering direction and amount of steering of the steering mechanism of the own vehicle 1. The actuator 17 may operate the steering mechanism of the host vehicle 1 in response to a control signal from the controller 16.

Next, driving control of the host vehicle 1 by the controller 16 will be explained. The driving control by the controller 16 includes estimating a running route, which is a traveling trajectory of the own vehicle 1, along the first road R1 on which the own vehicle 1 runs, and controlling at least the steering angle of the own vehicle 1 based on the estimated running route. may include automatic controls to For example, the travel control by the controller 16 may include lane departure prevention control (lane keep control) that controls the steering angle so that the host vehicle 1 travels along the estimated travel route.

Note that in this specification, the "travel road" may be, for example, an area on which the host vehicle 1 travels. That is, the running road may be a region having a width in the road width direction. In this case, for example, the controller 16 may estimate the left and right boundaries of the area forming the travel route. For example, the controller 16 may estimate the lane in which the host vehicle 1 travels (own lane) as the travel route.
Further, for example, the controller 16 may estimate a line or a series of dots representing the trajectory on which the own vehicle 1 travels as a "travel route." For example, the controller 16 may estimate a line or a series of dots representing a trajectory along which a reference point (eg, center of gravity, etc.) of the own vehicle 1 moves as a "trajectory."

In an area where there are no lanes, such as an intersection, the controller 16 may estimate a line or a series of dots representing the area where the vehicle 1 is traveling or the trajectory the vehicle 1 is traveling on as the "travel route."
The controller 16 acquires the road shape RS1 (hereinafter sometimes referred to as "first road shape RS1") of the first road R1 on which the host vehicle 1 travels from the map data stored in the map database 12, and determines the driving route. Estimate.

As described above, the map data stored in the map database 12 expresses road shapes on a road-by-road basis using node strings.
In the case of such map data, each node N often indicates a position near the center of the road, as shown in FIG. Therefore, when the number of lanes on a road increases, the position of the node N in the lane width direction moves in the direction in which the number of lanes increases.

In the example of FIG. 2, the number of lanes is increased because the lane of the first road R1 branches into a straight lane LN1 and a right turn lane LN2 in front of the course of the host vehicle 1. Therefore, the position of the node N in the lane width direction has moved toward the right turn lane LN2.
Therefore, the first road shape RS1 represented by the node string is different from the actual lane shape of the first road R1. In the example of FIG. 2, as the number of lanes increases by one, the position of node N moves toward the right turn lane LN2 by 1/2 lane. As a result, the first road shape RS1 is different from the actual shapes of the straight lane LN1 and the right turn lane LN2.
As a result, if the driving route Ld on which the vehicle 1 should travel is estimated based on the road shape of the map data, the estimation accuracy may become low.

Therefore, in the present invention, depending on whether or not the shapes of the left and right road boundaries EL and ER of the first road R1 match the first road shape RS1, the first road shape RS1 is used to guide the own vehicle 1. It is determined whether the travel route Ld can be estimated. In the following description, the shapes of the road boundaries EL and ER may be referred to as "road boundary shapes."
Specifically, the controller 16 detects the current position of the own vehicle 1 based on the measurement result of the positioning device 11, and detects the first position of the first road from the map data stored in the map database 12. Extract the road shape RS1.

Further, the controller 16 detects road boundaries EL and ER extending along the extending direction of the first road R1 at both ends of the first road R1 in the road width direction, based on the output signal of the external sensor 14. Then, it is determined whether the first road shape RS1 and the road boundary shape match.
When the first road shape RS1 and the road boundary shape match, the controller 16 estimates the driving route Ld, which is a travel trajectory along the first road, based on the first road shape RS1 or the road boundary shape. If the first road shape RS1 and the road boundary shape do not match, the controller 16 does not estimate the driving route Ld based on the first road shape RS1. In this case, the driving route Ld is estimated without using the first road shape RS1 as described later.
Note that "the first road shape RS1 and the road boundary shape match" does not only mean that the first road shape RS1 and the road boundary shape completely match, but also when the first road shape RS1 and the road boundary shape match. may include that the shape of the error is within a predetermined tolerance.

According to this embodiment, it is possible to determine whether the first road shape RS1 acquired from the map data is different from the actual lane shape of the first road R1. If the first road shape RS1 is different from the actual lane shape, it is possible to choose to estimate the driving route Ld without using the first road shape RS1.
Thereby, by estimating the driving path of the own vehicle using the first road shape RS1, it is possible to suppress a decrease in the accuracy of estimating the driving path.

Next, the travel control device 10 in the embodiment will be described in more detail. FIG. 3 is a block diagram of an example of the functional configuration of the controller 16 in FIG. 1. As shown in FIG. The controller 16 includes a vehicle position estimation section 40 , a road shape acquisition section 41 , a road boundary detection section 42 , a shape matching determination section 43 , a driving route estimation section 44 , and a vehicle control section 45 .
The own vehicle position estimating unit 40 calculates the own vehicle position in a fixed coordinate system (hereinafter sometimes referred to as "map coordinate system") of map data stored in the map database 12 based on the measurement result by the positioning device 11. presume. Methods for estimating the vehicle position include a Kalman filter using GNSS, but any method for estimating the vehicle position that can obtain the approximate shape of the road on which the vehicle is traveling may be used.

Based on the estimated vehicle position, the road shape acquisition unit 41 identifies a first road R1 on which the vehicle 1 is currently traveling among the roads described in the map data stored in the map database 12. Note that the road shape acquisition unit 41 may specify the first road R1 based on the planned travel route information of the own vehicle 1 set by a navigation system (not shown). The road shape acquisition unit 41 extracts the first road shape RS1 of the first road R1 from the map database 12.

The road boundary detection unit 42 detects the curb of the road shoulder, median strip, white line (solid line), road boundary line, guardrail, pole, fence, cat's eye, block, etc. indicating the road boundary, thereby detecting the first road R1. Road boundaries EL and ER extending along the extending direction of the first road R1 at both left and right ends in the road width direction are detected. Note that, although a detection method using a recognition camera or LiDAR is common, the detection method is not limited to this method as long as it can achieve the above purpose.

The shape matching determination unit 43 compares the first road shape RS1 acquired by the road shape acquisition unit 41 with the road boundary shapes of the road boundaries EL and ER detected by the road boundary detection unit 42, and determines whether the first road shape RS1 and It is determined whether the shape matches the road boundary shape.
Hereinafter, a method for determining whether the first road shape RS and the road boundary shape of the right road boundary ER match will be explained. However, the first road shape RS1 and the road boundary shape of the left road boundary EL match. Whether or not to do so can be similarly determined.
As a criterion for determining whether or not the first road shape RS1 and the road boundary shape match, for example, the degree of parallelism between the first road shape RS1 and the road boundary shape may be determined. When the first road shape RS1 and the road boundary shape are parallel (or when the degree of parallelism is high), the shape matching determination unit 43 determines that the first road shape RS1 and the road boundary shape match, and the first road shape RS1 and the road boundary shape match. When RS1 and the road boundary shape are not parallel (or when the degree of parallelism is low), it may be determined that the first road shape RS1 and the road boundary shape do not match.

FIG. 4A is a schematic diagram of a method for calculating the degree of parallelism between the first road shape RS and the road boundary shape of the right road boundary ER.
The shape matching determination unit 43 extends a perpendicular line in each of the nodes N1 to N6 of the first road shape RS1 in a direction perpendicular to the connection direction (link direction) with the adjacent nodes before and after, and determines the connection between the road boundary ER and the perpendicular line. Find the intersections P1 to P6... That is, the shape matching determination unit 43 extends the perpendicular line in a direction perpendicular to the arrangement direction of the nodes N1 to N6, and finds the intersections P1 to P6 between the road boundary ER and the perpendicular line. In FIG. 4(a), rectangular plots represent intersections P1 to P6, . . . . The same applies to FIG. 4(b).

The shape matching determination unit 43 calculates the distances d1 to d6 from each node N1 to N6 to the intersections P1 to P6 for each node N1 to N6, and if these distances d1 to d6 are substantially constant, then (That is, if the dispersion dv of the distances d1 to d6 is small), it may be determined that they are parallel. For example, it may be determined that they are parallel when the dispersion dv is less than or equal to a predetermined value. On the other hand, if the dispersion is large (if the dispersion dv is large), it may be determined that they are not parallel.
For example, the shape matching determination unit 43 may define the degree of parallelism as e ^(-dv) , and may express it as an exponential function having a value range of 0 to 1. The shape matching determination unit 43 may determine that the shapes match if the parallelism is high, and that the shapes do not match if the parallelism is low.

For example, the shape matching determination unit 43 determines whether the first road shape RS1 and the road boundary shape match based on the difference in curvature between the curvature k1 of the first road shape RS1 and the curvature k2 of the road boundary shape. You may. In this case, the shape matching determination unit 43 performs circular fitting for each of the road shape and road boundary shape, and sets the radii r1 and r2 of the respective estimated circles as radii of curvature. Then, calculate the respective curvatures k1=1/r1 and k2=1/r2, and if the difference between the curvatures k1 and k2 is small (for example, if the difference is less than a threshold value), the first road shape RS1 and the road boundary shape are the same. If the difference is large (for example, if the difference is greater than or equal to a threshold value), it may be determined that the first road shape RS1 and the road boundary shape do not match. As the difference between the curvatures k1 and k2, for example, the absolute value of the difference |k1-k2| may be used, or the square value of the difference (k1-k2) ² may be used.

For example, the shape matching determination unit 43 calculates a matching score representing the degree of similarity or dissimilarity between the first road shape RS1 and the road boundary shape, and determines whether the first road shape RS1 and the road boundary shape are different based on the matching score. It may be determined whether or not they match.
When calculating the matching score, the shape matching determination unit 43 calculates the error d1 between the nodes N1 to N6 of the first road shape RS1 and the intersections P1 to P6 on the road boundary shape (see FIG. 4(a)). The first road shape RS1 and the road boundary shape are aligned so that ~d6... is minimized, and based on the mean square error D=(d1 ² + d2 ² +...dm ² )/m after alignment, A matching score may be calculated.

For example, the matching score e ^(-D/σ) may be defined by appropriately setting the normalization term σ, and expressed by an exponential function having a range of 0 to 1. When the matching score is based on the error between the positions of the nodes N1 to N6... and the positions of the points P1 to P6..., the nodes N1 to N6... of the first road shape RS1 or the points P1 to P6 forming the road boundary... The error may be the distance in the direction perpendicular to .
Refer to FIG. 4(b). The shape matching determination unit 43 obtains normal vectors nr1 to nr6 at nodes N1 to N6 of the first road shape RS1 and normal vectors ne1 to ne6 at each point P1 to P6 of the road boundary ER, respectively. Angular similarity between normal vectors nr1 and ne1, between nr2 and ne2, between nr3 and ne3, between nr4 and ne4, between nr5 and ne5, between nr6 and ne6... The average value of may be calculated as the matching score.

When the shape matching determination unit 43 determines that the first road shape RS1 and the road boundary shape match, the running route estimating unit 44 estimates the running route Ld of the host vehicle 1 based on the first road shape RS1 or the road boundary shape. do.
For example, the driving route estimating unit 44 may estimate the driving path Ld based on the first road shape RS1 when the first road shape RS1 and at least one of the road boundary shapes of the road boundaries EL and ER match. For example, the driving route estimating unit 44 may estimate the driving path Ld based on a road boundary shape that matches the first road shape RS1.

When estimating the running route Ld based on the first road shape RS1, the running route estimation unit 44 may estimate the running route Ld by, for example, aligning the position of the first road shape RS1 with the current position of the own vehicle 1. For example, among the nodes of the first road shape RS1, the first road shape RS1 is translated in parallel so that the position of the node near the own vehicle position (for example, the nearest node) moves to the own vehicle position, and after the movement A line expressed by the first road shape RS1 or a region of a predetermined width including the first road shape RS1 may be estimated as the driving route Ld.

Similarly, when estimating the running route Ld based on the road boundary shape, for example, the running route estimation unit 44 estimates the running route Ld by aligning the position of any point on the road boundary shape with the current position of the host vehicle 1. You can estimate it. For example, the road boundary shape is translated in parallel so that the position of a nearby point (for example, the nearest point) on the road boundary shape close to the own vehicle position moves to the own vehicle position, and the line or road expressed by the moved road boundary shape is An area of a predetermined width including the boundary shape may be estimated as the running route Ld.

On the other hand, when the shape matching determination unit 43 determines that the first road shape RS1 and the road boundary shape do not match, the driving route estimating unit 44 estimates the driving route Ld without using the first road shape RS1. For example, the running route estimating unit 44 may estimate the running route Ld based on the surrounding environment of the vehicle 1 detected by the external sensor 14. As the route estimation based on the surrounding environment, for example, the route estimation unit 44 may estimate the route Ld based on the detection results of white lines (road boundary lines, lane markings, lane boundary lines) around the own vehicle 1. Alternatively, for example, the running route estimating unit 44 may estimate the running route Ld based on the traveling trajectory of other vehicles around the own vehicle 1 (for example, a preceding vehicle traveling in front of the own vehicle 1), as the running route estimation based on the surrounding environment. good.

See FIG. 5. When the shape matching determination unit 43 determines that the first road shape RS1 and the road boundary shape do not match, the traveling route estimation unit 44 determines that the first road shape RS1 and the road boundary shape do not match. The running route Ld of the host vehicle 1 may be estimated based on the second road shape RS2, which is the road shape of the second road R2. This is because the road width W changes in places where the number of lanes increases, such as before an intersection.If the first road shape RS1 differs from the actual lane shape, the second road shape of the oncoming road (second road R2) This is because RS2 may be able to be used for estimating the driving route without being affected by the increase in the number of lanes.
In this case, the road shape acquisition unit 41 may extract the second road shape RS2 of the second road R2 from the map database 12.

Similarly to the case of the first road shape RS1, the driving route estimation unit 44 may determine whether the second road shape RS2 matches the road boundary shapes of the road boundaries EL and ER of the first road R1.
When determining whether or not the second road shape RS2 matches the road boundary shape of the first road R1, for example, the driving route estimating unit 44 determines whether the node of the second road shape RS2 matches the node of the first road shape RS1. Move in the road width direction to the arranged position. For example, the route estimating unit 44 determines that the position of the node Nc2 near the midpoint of the second road R2 in the section between the intersection C1 behind the own vehicle 1 and the intersection C2 in front of the vehicle 1 is between the intersection C1 and the intersection C2. The position of the node of the second road shape RS2 may be moved in the road width direction so as to move to the position of the node Nc1 near the midpoint of the first road R1 in the section.

Further, for example, the position of the node of the second road shape RS2 is set so that the node Nn2 of the second road shape RS2 closest to the host vehicle 1 moves to the position of the node Nn1 of the first road shape RS1 closest to the host vehicle 1. may be moved in the width direction of the road.
Similarly to the case of the first road shape RS1, the driving route estimation unit 44 determines whether or not the second road shape RS2 after movement matches the road boundary shapes of the road boundaries EL and ER of the first road R1. . If the second road shape RS2 after movement matches the road boundary shape, the driving route estimating unit 44 may estimate the driving path Ld based on the second road shape RS2 after movement. If the second road shape RS2 after movement and the road boundary shape do not match, the driving route Ld may be estimated without using either the first road shape RS1 or the second road shape RS2 after movement.

Further, for example, when the driving route estimation unit 44 determines that the number of lanes of the first road R1 increases in front of the course of the host vehicle 1, the travel route estimating unit 44 determines that the host vehicle 1 The travel route Ld may be estimated based on the shape of the road boundary along the planned travel route along which the vehicle travels. For example, the driving route estimating unit 44 may determine that the number of lanes of the first road R1 increases in the forward direction of the course of the own vehicle 1 based on the recognition results of road signs and road surface markings around the own vehicle 1.
See FIG. 6. For example, the traveling route estimation unit 44 detects a road marking Ts that foretells a divergence between a straight lane and a right-turn lane by analyzing an image of the road surface of the own lane in front of the own vehicle 1 taken by the camera of the external sensor 14. You may do so.

FIG. 7 is a schematic diagram of an example of a road surface marking Ts that foretells a branch between a straight lane and a right turn lane. The road marking Ts is a road marking in which an arrow indicating going straight and an arrow indicating a right turn are arranged within a predetermined distance from each other in the road width direction, and the lane on which the road marking Ts is installed is divided into a going straight lane and a right turning lane in front. It shows that it is branching.
For example, if the planned travel route of the host vehicle 1 is a route that goes straight through an intersection, the travel route Ld may be estimated using the road boundary shape of the left road boundary EL. When the planned travel route of the own vehicle 1 is a route that turns right at an intersection, the travel route Ld may be estimated using the road boundary shape of the right road boundary ER.

See FIG. 6. Now, there is an intersection section Sc ahead of the course of the own vehicle 1, and in the section Su before the intersection section Sc (that is, the section closer to the own vehicle 1 than the intersection section Sc), the first road shape RS1 and the second road Assume a case where the shape RS2 does not match the road boundary shape and the travel path Ld1 of the host vehicle 1 is estimated without using the first road shape RS1 or the second road shape RS2 (that is, using the surrounding environment).
In this way, when estimating the running route Ld1 without using the road shape in the section Su before the intersection, the running route estimation unit 44 estimates the running route Ld1 without using the first road shape RS1 even in the intersection section Sc. Ld2 may be estimated.

This is because there is a high possibility that there are no road boundaries EL and ER to indicate the direction of travel of the own vehicle 1 within an intersection such as a cross intersection, and whether it is okay to estimate the driving route Ld using the first road shape RS1. This is because it cannot be determined based on the road boundaries EL and ER.
Note that whether or not the section Su for which the route Ld1 is estimated without using the first road shape RS1 is before an intersection is determined by the intersection node Nc where the road shape of the intersecting road and the first road shape RS1 intersect in the map database 12. The determination may be made based on whether or not the distance is within a predetermined distance.

Note that when estimating the running route Ld2 within the intersection section Sc without using the first road shape RS1, for example, the running route estimating unit 44 estimates the running route Ld2 based on the traveling trajectory of other vehicles around the host vehicle 1 as the surrounding environment. may be estimated. This is because there is a high possibility that the driving route cannot be estimated based on the white line in the intersection section Sc.
In addition, a temporary running route Ld3 is estimated using the first road shape RS1 in a far section Sf ahead of the course of the host vehicle 1 (hereinafter sometimes referred to as "distant section Sf"), and a temporary running route Ld3 is estimated using the first road shape RS1, and in a section Su before the intersection A trajectory that smoothly connects the running route Ld1 and the temporary running route Ld3 estimated based on the surrounding environment may be estimated as the running route Ld2 within the intersection section Sc.

As a result, it is possible to suppress an error in the driving route Ld due to estimation based on an incorrect road shape in a section where there is no recognition result of the surrounding environment.
For example, the far section Sf may be a section that is a predetermined distance d or more away from the own vehicle 1. For example, the far section Sf is a section in which it has not yet been determined whether or not the driving route Ld can be estimated using the first road shape RS1 based on the road boundaries EL and ER and the road width W of the first road R1. It may be.
For example, as in the example of FIG. 4, if the section Su in which the driving route Ld1 is estimated without using the first road shape RS1 is a section before an intersection, the far section Sf is closer to the intersection than the intersection when viewed from the host vehicle 1. It may be a far area.
Further, the running route estimating unit 44 may calculate, for example, a clothoid curve or a polynomial curve of degree 3 or higher as the running route that smoothly connects the running route Ld1 and the temporary running route Ld3.

Furthermore, even if the shape matching determination unit 43 determines that the first road shape RS1 or the second road shape RS2 match the road boundary shape, the driving route estimation unit 44 may detect the white line shape or other information detected as the surrounding environment. Based on the traveling trajectory of the vehicle, a traveling route that is smoothly connected throughout may be estimated as the traveling route Ld of the own vehicle 1.
The vehicle control unit 45 drives the actuator 17 to control the accelerator and brake, and the steering direction and amount of steering of the steering mechanism so that the vehicle 1 travels along the route Ld estimated by the route estimating unit 44. .

(motion)
FIG. 8 is a flowchart of an example of the route estimation method according to the embodiment.
In step S1, the own vehicle position estimating unit 40 acquires map data from the map database 12.
In step S2, the vehicle position estimation unit 40 estimates the vehicle position in the map coordinate system based on the measurement result by the positioning device 11.
In step S3, the road shape acquisition unit 41 extracts the first road shape RS1 of the first road R1 on which the own vehicle 1 is currently traveling.
In step S4, the road boundary detection unit 42 detects road boundaries EL and ER extending along the extending direction of the first road R1 at both left and right ends of the first road R1 in the road width direction.

In step S5, the shape matching determination unit 43 compares the first road shape RS1 with the road boundary shapes of the road boundaries EL and ER.
In step S6, the shape matching determination unit 43 determines whether the road boundary shapes of the left and right road boundaries EL and ER match the first road shape RS1. If they match (step S6: Y), the process advances to step S7. If they do not match (step S6: N), the process proceeds to step S8.

In step S7, the running route estimating unit 44 estimates the running route Ld of the host vehicle 1 based on the first road shape RS1 or the road boundary shape. Thereafter, the process proceeds to step S9.
In step S8, the running route estimation unit 44 estimates the running route Ld without using the first road shape RS1. Thereafter, the process proceeds to step S9.
In step S9, the vehicle control unit 45 controls the accelerator, the brake, and the steering direction and amount of the steering mechanism so that the host vehicle 1 travels along the route Ld estimated by the route estimation unit 44. The process then ends.

(Effects of embodiment)
(1) The positioning device 11 detects the own vehicle position, which is the current position of the own vehicle 1. The controller 16 extracts a first road shape that is the road shape of a first road on which the host vehicle 1 is traveling from map data in which the road shape is expressed for each road by an array of a plurality of nodes; A road boundary shape that is a shape along the extension direction of the first road at the end of the road in the road width direction is detected, it is determined whether the first road shape and the road boundary shape match, and the first road boundary shape is detected. When the road shape and the road boundary shape match, a travel route that is a travel trajectory along the first road is estimated based on the first road shape or the road boundary shape, and the first road shape and the road boundary shape are If they do not match, the travel route is estimated without using the first road shape.

For example, when the road boundary shape of at least one of both ends of the first road in the road width direction matches the first road shape, the controller 16 controls the controller 16 based on the first road shape or the above-mentioned at least one road boundary shape. If the road boundary shapes at both ends do not match the first road shape, the travel route may be estimated without using the first road shape.
As a result, if the first road shape stored in the map database 12 as the road shape of the first road on which the own vehicle 1 is traveling matches the detected road boundary shape of at least one of the left and right road boundaries EL and ER. Since the first road shape is used for the first road shape, it is possible to suppress erroneous estimation (decrease in accuracy) of driving route estimation due to an incorrect first road shape.

(2) The controller 16 may detect the road boundary shape based on curbs, white lines, guardrails, poles, fences, cat's eyes, or blocks that indicate road boundaries.
This makes it possible to obtain the shape of the boundary of the driveable area.
(3) The controller 16 selects the first road shape and the road boundary shape based on the parallelism or matching score between the first road shape and the road boundary shape, or the curvature of the first road shape and the curvature of the road boundary shape. It may be determined whether or not the shapes match.
By comparing these parallelism, curvature, and matching score with predetermined values, it is possible to determine whether or not the first road shape and the road boundary shape match.

(4) If it is determined that the first road shape and the road boundary shape do not match in the section before the intersection, the controller 16 estimates the driving route without using the first road shape even within the intersection. good.
Inside a cross intersection, there are often no road boundaries such as curbs to indicate the direction of travel of the vehicle, and if the road shape is not correct before the intersection, it is considered that the road shape is also incorrect within the intersection. Therefore, by estimating the travel route without using the first road shape, incorrect travel route estimation within an intersection can be suppressed.

(5) When it is determined that the first road shape and the road boundary shape do not match, the controller 16 generates a second road shape that is the road shape of the second road that is the road on which the oncoming vehicle of the host vehicle 1 is traveling. may be extracted from the map data and the driving route may be estimated using the second road shape.
For example, if it is determined that the second road shape and the road boundary shape match, the driving route is estimated using the second road shape, and if it is determined that the second road shape and the road boundary shape do not match, then , the driving route may be estimated without using either the first road shape or the second road shape.
There is a possibility that the first road shape is incorrect due to the increase in lanes near the intersection, but there is a high possibility that the second road shape is correct because there is no increase in lanes on the oncoming road. Therefore, the correct travel route can be estimated by using the second road shape.

(6) The controller 16 may detect the surrounding environment of the own vehicle 1 and estimate the driving route based on the detected surrounding environment when the first road shape and the road boundary shape do not match. For example, lane markings around the host vehicle 1 or travel trajectories of other vehicles around the host vehicle 1 may be detected as the surrounding environment.
As a result, a more accurate driving route can be estimated by using the surrounding environment such as white lines and vehicle trajectory.

DESCRIPTION OF SYMBOLS 1... Own vehicle, 10... Driving control device, 12... Map database, 14... External world sensor, 15... Vehicle sensor, 16... Controller, 17... Actuator, 20... Processor, 21... Storage device, 40... Own vehicle position estimation part , 41... Road shape acquisition section, 42... Road boundary detection section, 43... Shape matching determination section, 44... Driving route estimation section, 45... Vehicle control section

Claims (10)

Detects the own vehicle position, which is the current position of the own vehicle,
extracting a first road shape that is a road shape of a first road on which the host vehicle travels from map data in which the road shape is expressed for each road by an array of a plurality of nodes;
detecting a road boundary shape that is a shape along the extending direction of the first road at an end in the road width direction of the first road;
determining whether the first road shape and the road boundary shape match;
When the first road shape and the road boundary shape match, estimating a travel route that is a travel trajectory along the first road based on the first road shape or the road boundary shape;
estimating the driving route without using the first road shape when the first road shape and the road boundary shape do not match;
A route estimation method characterized by the following. When the road boundary shape of at least one of both ends of the first road in the road width direction matches the first road shape, the running route is determined based on the first road shape or the at least one road boundary shape. Estimate
estimating the driving route without using the first road shape when neither of the road boundary shapes at both ends match the first road shape;
The route estimation method according to claim 1, characterized in that: 3. The driving route estimation method according to claim 1, wherein the road boundary shape is detected based on a curb, a white line, a guardrail, a pole, a fence, a cat's eye, or a block that indicates a road boundary. The first road shape and the road boundary shape based on the parallelism or matching score between the first road shape and the road boundary shape, or the curvature of the first road shape and the curvature of the road boundary shape. The route estimation method according to any one of claims 1 to 3, characterized in that it is determined whether or not they match. If it is determined that the first road shape and the road boundary shape do not match in the section before the intersection, the driving route is estimated without using the first road shape even within the intersection. The running route estimation method according to any one of claims 1 to 4. If it is determined that the first road shape and the road boundary shape do not match, a second road shape that is a road shape of a second road on which an oncoming vehicle of the host vehicle travels is determined from the map data. 6. The driving route estimation method according to claim 1, wherein the driving route is estimated using the second road shape. If it is determined that the second road shape and the road boundary shape match, the driving route is estimated using the second road shape, and if it is determined that the second road shape and the road boundary shape do not match, 7. The driving route estimation method according to claim 6, wherein the driving route is estimated without using either the first road shape or the second road shape. detecting the surrounding environment of the own vehicle;
estimating the driving route based on the detected surrounding environment when the first road shape and the road boundary shape do not match;
The route estimation method according to claim 1, characterized in that: 9. The driving route estimation method according to claim 8, wherein lane markings around the host vehicle or travel trajectories of other vehicles around the host vehicle are detected as the surrounding environment. comprising a positioning device that detects the current position of the own vehicle, a sensor that detects objects around the own vehicle, and a controller;
The controller includes:
extracting a first road shape that is a road shape of a first road on which the host vehicle travels from map data in which the road shape is expressed for each road by an array of a plurality of nodes;
Based on the output of the sensor, detecting a road boundary shape that is a shape along the extending direction of the first road at an end of the first road in the road width direction;
determining whether the first road shape and the road boundary shape match;
When the first road shape and the road boundary shape match, estimating a travel route that is a travel trajectory along the first road based on the first road shape or the road boundary shape;
estimating the driving route without using the first road shape when the first road shape and the road boundary shape do not match;
A running route estimation device characterized by the following.

Images