JP2024025040A - Vehicle location estimation device and vehicle location estimation method - Google Patents

Abstract

To enable more accurate estimation of a traveling position of an own vehicle on a road even at locations other than intersections.SOLUTION: A vehicle location estimation device includes: a traveling environment recognition unit 102 that is used in a vehicle to recognize a traveling environment including the number of lanes on a travel path for a vehicle from sensing results of a peripheral monitoring sensor 50 that monitors the periphery of the vehicle; a map data acquiring unit 104 that acquires map data including the number of lanes on a road for each area; and a position estimation unit 107 that estimates a traveling position of the vehicle on the road on the basis of the degree of similarity between the number of lanes on the travel path of the vehicle recognized by the traveling environment recognition unit 102 and the number of lanes in the area estimated to be a traveling area of the vehicle acquired by the map data acquiring unit 104.SELECTED DRAWING: Figure 1

Description

The present disclosure relates to a vehicle position estimating device and a vehicle position estimation method for estimating the traveling position of a vehicle on a road.

BACKGROUND ART There is a known technology for autonomous driving using high-precision maps that are more detailed than maps used for route guidance. It is conceivable that roads with high-definition maps (hereinafter referred to as mapped roads) and roads without high-definition maps (hereinafter referred to as unmapped roads) coexist. When a mapped road and an unmapped road are located close to each other, it is easy to misjudge which road the vehicle is located on. Moreover, when this misjudgment occurs, it becomes difficult to perform automatic driving with high accuracy.

On the other hand, Patent Document 1 discloses a technique that attempts to correctly determine whether the vehicle is traveling on an elevated road or an elevated road. Patent Document 1 discloses that it is determined whether the vehicle is traveling on an elevated road or a road under an elevated road based on whether the length of a discontinuous section of a marking line is equal to or greater than a threshold value. The length of the discontinuous section of the marking line is determined by pattern recognition processing from image data taken at an intersection. Further, Patent Document 1 discloses that it is determined whether the vehicle is traveling on an elevated road or an elevated road based on the consistency of intersection signs. The consistency of the intersection signs is determined by matching the pattern of the signs on the road at the intersection with the image data taken at the intersection.

Japanese Patent Application Publication No. 2008-164506

Since the technique disclosed in Patent Document 1 utilizes elements characteristic of intersections, the accuracy of determining whether the vehicle is traveling on an elevated road or an elevated road outside the intersection is reduced.

One purpose of this disclosure is to provide a vehicle position estimating device and a vehicle position estimation method that enable more accurate estimation of the traveling position of a vehicle on a road even at locations other than intersections. There is a particular thing.

The object is achieved by the combination of features recited in the independent claims, and the subclaims define further advantageous embodiments of the disclosure. The numerals in parentheses described in the claims indicate correspondence with specific means described in the embodiments described later as one aspect, and do not limit the technical scope of the present disclosure. .

In order to achieve the above object, a first vehicle position estimating device of the present disclosure calculates the number of lanes of the vehicle's driving route from the sensing results of a surroundings monitoring sensor (50) used in the vehicle to monitor the surroundings of the vehicle. a driving environment recognition unit (102) that recognizes the driving environment including the number of road lanes; a map data acquisition unit (104) that acquires map data including the number of road lanes for each region; a position estimation unit (107) that estimates the driving position of the vehicle on the road based on the degree of similarity between the number of lanes and the number of lanes in the area estimated to be the driving area of the vehicle acquired by the map data acquisition unit; Equipped with.

In order to achieve the above object, a first self-vehicle position estimating method of the present disclosure includes sensing using a surroundings monitoring sensor (50) that is used in a vehicle and is executed by at least one processor and that monitors the surroundings of the vehicle. A first driving environment recognition step that recognizes the driving environment including the number of lanes on the road on which the vehicle travels based on the results; a first map data acquisition step that acquires map data including the number of lanes on the road for each area; and a first driving environment. Based on the degree of similarity between the number of lanes on the vehicle's driving path recognized in the recognition process and the number of lanes in the area estimated to be the vehicle's driving area acquired in the first map data acquisition process, the number of lanes on the road is determined. and a first position estimation step of estimating the traveling position.

The number of lanes is a factor not limited to intersections. Therefore, by estimating the vehicle's driving position based on the degree of similarity between the number of lanes recognized from the sensing results of the surrounding monitoring sensor and the number of lanes for each area included in the map data, it is possible to estimate the vehicle's driving position at a location other than an intersection. This makes it possible to more accurately estimate the driving position of the own vehicle on the road.

In order to achieve the above object, a second own vehicle position estimating device of the present disclosure detects road markings on the route of the vehicle based on sensing results from a surroundings monitoring sensor (50) used in the vehicle to monitor the surroundings of the vehicle. a driving environment recognition unit (102a) that recognizes a driving environment including road markings, a map data acquisition unit (104a) that acquires map data including road markings for each region, and road markings of a vehicle running route recognized by the driving environment recognition unit. and a position estimating unit (107a) that estimates the driving position of the vehicle on the road based on the degree of similarity between the road marking in the area estimated to be the driving area of the vehicle, which is acquired by the map data acquisition unit. Be prepared.

In order to achieve the above object, a second self-vehicle position estimation method of the present disclosure includes sensing using a surroundings monitoring sensor (50) that is used in a vehicle and is executed by at least one processor and that monitors the surroundings of the vehicle. A second driving environment recognition step that recognizes the driving environment including road markings of the vehicle's route from the results, a second map data acquisition step that acquires map data including road markings for each area, and a second driving environment recognition step. The driving position of the vehicle on the road is determined based on the degree of similarity between the road markings on the route of the vehicle recognized in the second map data acquisition step and the road markings in the area estimated to be the driving area of the vehicle acquired in the second map data acquisition step. and a second position estimating step of estimating the position.

Road markings are elements that are not limited to intersections. Therefore, by estimating the vehicle's driving position based on the degree of similarity between the road markings recognized from the sensing results of the surrounding monitoring sensor and the road markings for each area included in the map data, it is possible to estimate the driving position of the vehicle based on the degree of similarity between the road markings recognized from the sensing results of the surrounding monitoring sensor and the road markings for each area included in the map data. Therefore, it becomes possible to estimate the driving position of the vehicle on the road with higher accuracy.

In order to achieve the above object, a third self-vehicle position estimating device of the present disclosure is used in a vehicle, and calculates the sky in the captured image on the running route of the vehicle from the captured image with a surrounding surveillance camera that captures the surroundings of the vehicle. a driving environment recognition unit (102b) that recognizes a driving environment that includes a target ratio that is at least one of a sky area ratio that is the ratio of the area in the captured image and a structure ratio that is the ratio of the structures in the captured image; A map data acquisition unit (104b) that acquires map data including the target ratio, the target ratio of the vehicle recognized by the driving environment recognition unit, and the target of the area estimated to be the vehicle driving area acquired by the map data acquisition unit. The vehicle includes a position estimating unit (107b) that estimates the traveling position of the vehicle on the road based on the degree of similarity with the ratio.

In order to achieve the above object, a third self-vehicle position estimating method of the present disclosure uses images captured by a surroundings monitoring camera that is used in a vehicle and executed by at least one processor, and captures images of the surroundings of the vehicle. A third run that recognizes a driving environment that includes a target ratio that is at least one of the empty area ratio that is the ratio of the sky area in the captured image on the vehicle travel path and the structure ratio that is the ratio of structures in the captured image. an environment recognition step, a third map data acquisition step for acquiring map data including target ratios for each area, target ratios of vehicles recognized in the third driving environment recognition step, and acquired in the third map data acquisition step; and a third position estimating step of estimating the driving position of the vehicle on the road based on the degree of similarity between the driving area of the vehicle and the target ratio of the estimated area.

The target ratio, which is at least one of the empty area ratio and the structure ratio, is a factor that is not limited to intersections. Therefore, by estimating the vehicle's driving position based on the degree of similarity between the target ratio recognized from the sensing results of the surrounding monitoring sensor and the target ratio for each area included in the map data, it is possible to estimate the vehicle's driving position at a location other than an intersection. Therefore, it becomes possible to estimate the traveling position of the vehicle on the road with higher accuracy. Furthermore, since the target ratio, which is the ratio within the image, is used instead of the captured image itself, it is also possible to reduce the amount of storage and processing.

1 is a diagram showing an example of a schematic configuration of a vehicle system 1. FIG. FIG. 3 is a diagram illustrating the identification of reliability by the reliability identification unit 106. FIG. FIG. 3 is a diagram illustrating the identification of reliability by the reliability identification unit 106. FIG. 3 is a flowchart illustrating an example of the flow of position estimation related processing in the own vehicle position estimation device 10. FIG. It is a figure showing an example of rough composition of system 1a for vehicles. It is a flowchart which shows an example of the flow of position estimation related processing in self-vehicle position estimation device 10a. It is a diagram showing an example of a schematic configuration of a vehicle system 1b. It is a flowchart which shows an example of the flow of position estimation related processing in self-vehicle position estimation device 10b.

Several embodiments for disclosure will be described with reference to the drawings. For convenience of explanation, parts having the same functions as those shown in the figures used in the previous explanations are given the same reference numerals in multiple embodiments, and the explanation thereof may be omitted. be. For parts with the same reference numerals, the descriptions in other embodiments can be referred to.

(Embodiment 1)
<Schematic configuration of vehicle system 1>
Embodiment 1 of the present disclosure will be described below with reference to the drawings. A vehicle system 1 shown in FIG. 1 is used in a vehicle equipped with a driving support function that supports a driver's driving operations. The driving support function referred to here may also include an automatic driving function that performs driving operations for the driver. An example of driving support includes steering correction for lane maintenance. Below, the case where the vehicle system 1 is used in an automatic driving vehicle having an automatic driving function as a driving support function will be described as an example.

As shown in FIG. 1, the vehicle system 1 includes a vehicle position estimation device 10, a GNSS receiver 20, a vehicle condition sensor 30, a communication module 40, a surrounding monitoring sensor 50, and an automatic driving ECU 60. The vehicle position estimation device 10 may be connected to other devices included in the vehicle system 1 via an in-vehicle LAN. Hereinafter, the vehicle using the vehicle system 1 will be referred to as the own vehicle. Although the vehicle using the vehicle system 1 is not necessarily limited to an automobile, the following description will be given using an example of use in an automobile.

The GNSS receiver 20 receives positioning signals from multiple positioning satellites. Based on this positioning signal, the GNSS receiver 20 sequentially identifies coordinate information indicating the current position of the own vehicle. The GNSS receiver 20 outputs the specified coordinate information to the own vehicle position estimation device 10. The coordinate information may be coordinate information indicating latitude, longitude, and altitude.

The vehicle condition sensor 30 is a group of sensors for detecting various conditions of the own vehicle. Examples of the vehicle condition sensor 30 include a vehicle speed sensor, a yaw rate sensor, and the like. The vehicle speed sensor detects the vehicle speed of the own vehicle. The yaw rate sensor detects the yaw rate, which is the rotational angular velocity of the own vehicle around the vertical axis.

The communication module 40 transmits and receives information to and from a server external to the own vehicle via a public communication network. The communication module 40 downloads map data from a server storing map data (hereinafter referred to as a map server). The communication module 40 may acquire so-called high-precision map data as the map data. The high-precision map data referred to here is map data that indicates the road structure and the position coordinates of features arranged along the road with an accuracy that can be used for automatic driving.

The high-precision map data includes, for example, three-dimensional shape data of roads, lane data, and the like. The three-dimensional shape data of roads includes node data regarding points (hereinafter referred to as nodes) where a plurality of roads intersect, merge, or diverge. The three-dimensional shape data of a road includes link data regarding road sections (hereinafter referred to as links) connecting the nodes. The link data shall include information such as road width. The lane data includes information such as the number of lanes, information on the installation position of partition lines for each lane, the direction of travel for each lane, and branching/merging points at the lane level. The positional information of the lane markings and road edges may be expressed as a coordinate group (that is, a point group). In addition, as another aspect, the position information of the lane markings and road edges may be expressed as polynomials.

The surroundings monitoring sensor 50 is an autonomous sensor that monitors the surroundings of the own vehicle. The surrounding monitoring sensor 50 may be a surrounding monitoring camera, millimeter wave radar, sonar, LIDAR (Light Detection and Ranging/Laser Imaging Detection and Ranging), or the like. The surrounding surveillance camera images a predetermined area around the vehicle. Millimeter wave radar, sonar, and LIDAR transmit search waves to a predetermined range around the vehicle. Hereinafter, millimeter wave radar, sonar, and LIDAR will be referred to as exploration wave sensors. The surrounding surveillance camera sequentially outputs captured images that are captured one after another to the own vehicle position estimation device 10 as sensing information. The search wave sensor sequentially outputs a scanning result based on a received signal obtained when receiving a reflected wave reflected by an obstacle to the own vehicle position estimating device 10 as sensing information. In this embodiment, a case where the surroundings monitoring sensor 50 is a surroundings monitoring camera will be described as an example. For example, the surroundings monitoring sensor 50 may be a front camera whose imaging range includes the road surface in front of the vehicle.

The automatic driving ECU 60 is an electronic control device that executes processes related to automatic driving. The automatic driving ECU 60 uses the detailed position of the own vehicle estimated by the own vehicle position estimating device 10 to execute processing related to automatic driving. An example of a process related to automatic driving is a process of automatically driving the own vehicle along a driving lane.

The own vehicle position estimating device 10 includes, for example, a processor, a memory, an I/O, and a bus that connects these. The own vehicle position estimating device 10 performs processing related to estimating the detailed position of the own vehicle (hereinafter referred to as detailed position estimation related processing) by executing a control program stored in a memory. Memory as used herein is a non-transitory tangible storage medium that non-temporarily stores computer-readable programs and data. Further, the non-transitional physical storage medium is realized by a semiconductor memory, a magnetic disk, or the like. The vehicle position estimation device 10 will be described in detail below.

<Schematic configuration of vehicle position estimation device 10>
Next, an example of a schematic configuration of the own vehicle position estimating device 10 will be explained. As shown in FIG. 1, the own vehicle position estimation device 10 includes a surrounding information acquisition unit 101, a driving environment recognition unit 102, a positioning unit 103, a map data acquisition unit 104, a map matching (hereinafter referred to as MM) unit 105, and a reliability identification unit. The unit 106 and the position estimation unit 107 are provided as functional blocks. Executing the processing of each functional block of the own vehicle position estimating device 10 by the computer corresponds to executing the own vehicle position estimation method. Note that some or all of the functions executed by the own vehicle position estimating device 10 may be configured in hardware using one or more ICs. Further, some or all of the functional blocks included in the own vehicle position estimating device 10 may be realized by a combination of software execution by a processor and hardware components.

The surrounding information acquisition unit 101 obtains sensing information detected by the surrounding monitoring sensor 50. In the example of this embodiment, a captured image captured by a surroundings monitoring camera is acquired. The driving environment recognition unit 102 recognizes the driving environment around the own vehicle from the sensing information acquired by the surrounding information acquisition unit 101. The driving environment recognition unit 102 recognizes obstacles on the driving path of the own vehicle from the sensing information acquired by the surrounding information acquisition unit 101. Obstacles include stationary objects and moving objects. Stationary objects include structures such as buildings and street lights. The driving environment recognition unit 102 recognizes road markings such as driving markings and road markings around the vehicle from the sensing information acquired by the surrounding information acquisition unit 101.

The driving environment recognition unit 102 may recognize road markings by performing pattern recognition processing on a captured image taken by a surrounding monitoring camera. The driving environment recognition unit 102 may recognize the number of lanes on the road on which the vehicle is traveling by recognizing the lane markings. It is preferable that the driving environment recognition unit 102 also recognizes the width of the road on which the vehicle is traveling by recognizing the lane markings. The road width corresponds to the so-called road width. Road width corresponds to the width of a road consisting of multiple lanes when multiple lanes exist on the road. This process in the driving environment recognition unit 102 corresponds to a first driving environment recognition step. It is preferable that the driving environment recognition unit 102 also recognizes the lane width of each lane on the driving path of the own vehicle by recognizing the driving lane markings. If a road does not have multiple lanes, the lane width may be the same as the road width.

The positioning unit 103 estimates the approximate current position of the own vehicle in the global coordinate system. The approximate current position of the own vehicle in the global coordinate system is hereinafter referred to as the approximate position. The positioning unit 103 may estimate the approximate position from the coordinate information obtained from the GNSS receiver 20 and the vehicle speed, yaw rate, etc. of the own vehicle obtained from the vehicle state sensor 30. Note that the positioning unit 103 may be configured not to be included in the own vehicle position estimation device 10. When adopting this configuration, the vehicle position estimation device 10 may acquire the approximate position from a unit provided outside the vehicle position estimation device 10 and having the function of the positioning section 103.

The map data acquisition unit 104 acquires map data including the number of road lanes for each area. By area, it may be by link, etc. This process in the map data acquisition unit 104 corresponds to a first map data acquisition step. It is preferable that the map data acquisition unit 104 acquires map data that also includes road widths for each region. It is preferable that the map data acquisition unit 104 acquires map data that also includes lane widths for each lane in each region.

The map data acquisition unit 104 may acquire map data around the vehicle from the map server via the communication module 40 . The map data acquisition unit 104 may acquire map data within a predetermined distance from the approximate position determined by the positioning unit 103. Furthermore, if the map data is managed by dividing it into sections, map data about the section including the approximate position of the own vehicle may be acquired. For example, if the vehicle is equipped with a database that stores map data, the map data acquisition unit 104 may acquire the map data from this database.

The MM unit 105 performs map matching processing based on the approximate position estimated by the positioning unit 103 and the map data acquired by the map data acquisition unit 104. In the map matching process, a travel trajectory identified from approximate positions arranged in chronological order is matched with roads on an electronic map. Then, the approximate position is calibrated so that it is located on the road on the electronic map, and a candidate position for the own vehicle on the road is determined. In the map matching process, if there are roads located close to each other, there is a risk that the candidate position of the vehicle will be determined on the wrong road. Examples of roads that are located close to each other include elevated roads and roads under elevated roads. Other examples include expressways, main roads, and their side roads.

The reliability specifying unit 106 specifies the reliability of the driving position of the own vehicle on the road. As an example, the reliability of the driving position of the own vehicle on the road, which has become a candidate in the matching process in the MM unit 105, is specified. Note that there may be roads that are not included in the map data acquired by the map data acquisition unit 104. In other words, there may be roads for which high-precision maps have not been developed (hereinafter referred to as unmapped roads). Therefore, the reliability specifying unit 106 assumes that an undeveloped road exists, and also specifies the reliability of the driving position of the own vehicle on this undeveloped road. The reliability may be expressed as a probability, for example.

The reliability specifying unit 106 specifies the degree of similarity between the number of lanes on the road on which the vehicle is running, which is recognized by the driving environment recognition unit 102, and the number of lanes on the road on which the vehicle is running, which is acquired by the map data acquisition unit 104. Then, based on the identified degree of similarity, the reliability of the driving position of the own vehicle on the road is determined. Hereinafter, the number of lanes on the road on which the host vehicle is traveling, which is recognized by the driving environment recognition unit 102, will be referred to as the number of recognized lanes. Hereinafter, the number of lanes on the road on which the host vehicle is traveling, which is acquired by the map data acquisition unit 104, will be referred to as the number of map lanes. The number of lanes on the driving path of the own vehicle acquired by the map data acquisition unit 104 is the number of lanes in the area estimated to be the driving area of the own vehicle, acquired by the map data acquisition unit 104. The area estimated to be the driving area of the own vehicle may be a candidate position determined by the MM unit 105. The reliability specifying unit 106 specifies a high degree of reliability as the degree of similarity between the number of recognized lanes and the number of map lanes increases.

Here, identification of reliability by the reliability identification unit 106 will be explained using FIGS. 2 and 3. In the examples shown in FIGS. 2 and 3, it is assumed that the MM unit 105 has both a two-lane road R2 and a three-lane road R3 as candidates. Road R2 and road R3 correspond to roads on which high-precision maps have been prepared (hereinafter referred to as map-prepared roads). Furthermore, the reliability specifying unit 106 also includes a one-lane unmapped road R1 as a temporary candidate. FIG. 2 is an example where the number of recognized lanes is two. FIG. 3 is an example where the number of recognized lanes is one.

As shown in FIG. 2, when the number of recognized lanes is two, the reliability identifying unit 106 identifies the two-lane road R2 as having the highest reliability. The reliability specifying unit 106 specifies that the reliability of the three-lane road R3 is the next highest. This is because even if the number of recognized lanes is two, there is a possibility of erroneous recognition of three lanes due to blurred lane markings or the like. When the number of recognized lanes is two, the reliability identifying unit 106 identifies the one-lane unmapped road R1 as having the lowest reliability. As shown in FIG. 3, when the number of recognized lanes is one, the reliability identifying unit 106 identifies the one-lane unmapped road R1 as having the highest reliability. On the other hand, the reliability specifying unit 106 specifies that the reliability of the two-lane road R2 and the three-lane road R3, which are multiple lanes, is low.

The reliability specifying unit 106 may also specify the degree of similarity between the road width of the road the own vehicle is running on, which is recognized by the driving environment recognition unit 102, and the road width of the road the own vehicle is running on, which is acquired by the map data obtaining unit 104. It is also preferable to use the identified degree of similarity to identify the reliability of the vehicle's traveling position on the road. Hereinafter, the road width of the road on which the host vehicle is running, which is recognized by the driving environment recognition unit 102, will be referred to as the recognized road width. Hereinafter, the road width of the road on which the host vehicle is traveling, which is obtained by the map data obtaining unit 104, will be referred to as a map road width. The road width of the driving path of the own vehicle acquired by the map data acquisition unit 104 is the road width of the area estimated to be the driving area of the own vehicle, acquired by the map data acquisition unit 104. The reliability specifying unit 106 may correct the reliability to be higher as the degree of similarity between the recognized road width and the map road width increases.

The reliability identification unit 106 uses the lane width pattern for each lane on the road the own vehicle is running on, which is recognized by the driving environment recognition unit 102, and the lane width pattern for each lane on the road the own vehicle is running on, which is acquired by the map data acquisition unit 104. It is sufficient to specify the degree of similarity between the two. The lane width pattern for each lane may be the lane width value for each lane and the order in which they are arranged. It is also preferable to use the identified degree of similarity to identify the reliability of the vehicle's traveling position on the road. Hereinafter, the lane width pattern for each lane of the road on which the host vehicle is traveling, which is recognized by the driving environment recognition unit 102, will be referred to as a recognized lane width pattern. Hereinafter, the lane width pattern for each lane of the road on which the host vehicle is traveling, which is acquired by the map data acquisition unit 104, will be referred to as a map lane width pattern. The lane width pattern for each lane on the driving path of the own vehicle acquired by the map data acquisition unit 104 is the lane width pattern for each lane in the area estimated to be the driving area of the own vehicle. The reliability specifying unit 106 may correct the reliability to be higher as the degree of similarity between the recognized lane width pattern and the map lane width pattern increases.

Note that the reliability specifying unit 106 may specify the reliability of which lane the vehicle is located on a multi-lane road by dividing it into individual lanes. In this case, the reliability level for each lane may be specified based on the arrangement of the lane markings around the vehicle recognized by the driving environment recognition unit 102.

The position estimation unit 107 estimates the driving position of the own vehicle on the road based on the degree of similarity between the number of recognized lanes and the number of map lanes. This process in the position estimating unit 107 corresponds to a first position estimating step. The number of lanes is a factor not limited to intersections. Therefore, by using the number of lanes, it is possible to estimate the driving position of the own vehicle on the road with higher accuracy even at locations other than intersections. Further, the number of lanes can be recognized from the sensing results of the sensing range including the road surface by the surrounding monitoring sensor 50, which is generally used in automatic driving. Therefore, it has higher versatility than a technology that uses a sensing range other than the general sensing range. In the example of FIG. 2, the position estimation unit 107 may estimate the matching candidate position on the road R2 as the driving position of the own vehicle on the road. In the example of FIG. 3, the position estimating unit 107 may estimate a candidate position, which is assumed to be on the map-undeveloped road R1, as the driving position of the own vehicle on the road. In other words, it is sufficient to estimate that the vehicle is located on the map-undeveloped road R1.

Preferably, the position estimating unit 107 estimates the driving position of the own vehicle on the road by also using the degree of similarity between the recognized road width and the map road width. According to this, even if it is difficult to narrow down to one driving position based only on the number of lanes, by using the lane width, it becomes easier to narrow down to one driving position. Furthermore, lane width is an element not limited to intersections. Therefore, according to the above configuration, it is possible to estimate the traveling position of the own vehicle on the road with higher accuracy even at a place other than an intersection.

Preferably, the position estimating unit 107 estimates the driving position of the own vehicle on the road by also using the degree of similarity between the recognized lane width pattern and the map lane width pattern. According to this, by using the lane width in addition to the number of lanes, it becomes easier to narrow down to one driving position. Furthermore, the lane width pattern for each lane is an element not limited to intersections. Therefore, according to the above configuration, it is possible to estimate the traveling position of the own vehicle on the road with high accuracy even at a place other than an intersection.

Preferably, the position estimating unit 107 uses the reliability specified by the reliability specifying unit 106 to estimate the traveling position of the own vehicle on the road. This is because the reliability can be used to determine whether or not to determine the driving position of the own vehicle.

The automatic driving ECU 60 uses the driving position of the own vehicle estimated by the position estimation unit 107 to execute processes related to automatic driving. When the automatic driving ECU 60 estimates the driving position of the own vehicle on the map-prepared road, the automatic driving ECU 60 may perform automatic driving using this driving position. When the automatic driving ECU 60 estimates the driving position of the own vehicle on a road without a map, the automatic driving ECU 60 may, for example, lower the level of executable automatic driving or cancel the automatic driving.

Note that the position estimating unit 107 may even estimate in which lane on a multi-lane road the own vehicle is located. In this case, the estimation may be made using the reliability of which lane on the multi-lane road the vehicle is located in, which is specified by the reliability identification unit 106. Specifically, it may be estimated that the vehicle is located in the lane with the highest reliability.

<Position estimation related processing in own vehicle position estimation device 10>
Next, an example of the flow of processing related to the traveling position of the own vehicle on the road (hereinafter referred to as position estimation related processing) in the own vehicle position estimation device 10 will be explained using FIG. 4. The flowchart of FIG. 4 may be configured to start, for example, when the power switch of the host vehicle is turned on. The power switch is a switch for starting the internal combustion engine or motor generator of the vehicle. Another condition may be that the self-driving function of the own vehicle is set to on.

First, in step S1, the positioning unit 103 estimates an approximate position. In step S2, the MM unit 105 performs map matching processing based on the approximate position estimated in S1 and the map data acquired by the map data acquisition unit 104. In step S3, the reliability specifying unit 106 specifies the reliability of the driving position of the own vehicle on the road. The reliability specifying unit 106 specifies the reliability of the driving position of the own vehicle on the road that became a candidate in the matching process in S2. The reliability specifying unit 106 also assumes that an undeveloped road exists, and also specifies the reliability of the driving position of the own vehicle on this undeveloped road.

In step S4, the position estimation unit 107 narrows down the driving position of the own vehicle on the road based on the degree of similarity between the number of recognized lanes and the number of map lanes. In step S5, if the driving position can be narrowed down to one in S4 (YES in S5), the process moves to step S9. On the other hand, if the driving position cannot be narrowed down to one in S4 (NO in S5), the process moves to step S6.

In step S6, the position estimating unit 107 further narrows down the driving position of the own vehicle on the road based on the degree of similarity between the recognized road width and the map road width. In step S7, if the travel position can be narrowed down to one in S6 (YES in S7), the process moves to step S9. On the other hand, if the driving position cannot be narrowed down to one in S6 (NO in S7), the process moves to step S8.

In step S8, the position estimation unit 107 further narrows down the driving position of the own vehicle on the road based on the degree of similarity between the recognized lane width pattern and the map lane width pattern. Even if it is not possible to narrow down the driving position to one in S8, the driving position can be narrowed down to the driving position on the road with the highest reliability. In step S9, the running position of the own vehicle on the road narrowed down to one in the processing up to that point is estimated as the running position of the own vehicle.

In step S10, if it is the end timing of the position estimation related process (YES in S10), the position estimation related process is ended. On the other hand, if it is not the end timing of the position estimation related process (NO in S10), the process returns to S1 and repeats the process. An example of the end timing of the position estimation related process is when the power switch of the own vehicle is turned off. An example of the end timing of the position estimation related process is when the automatic driving function is turned off.

In the example of FIG. 4, a configuration is shown in which the driving position of the own vehicle is sequentially narrowed down based on the number of lanes, road width, and degree of similarity of lane width patterns, but this is not necessarily the case. For example, the driving position of the own vehicle may be narrowed down and estimated by integrating the degree of similarity in the number of lanes, the degree of similarity in road width, and the degree of similarity in lane width patterns. According to a configuration in which the driving position of the vehicle is sequentially narrowed down based on the number of lanes, road width, and degree of similarity of lane width patterns, unnecessary processing can be more easily omitted than when processing is performed all at once.

(Embodiment 2)
The configuration is not limited to the configuration of the first embodiment, but may be the configuration of the second embodiment below. An example of the configuration of Embodiment 2 will be described below with reference to the drawings.

<Schematic configuration of vehicle system 1a>
As shown in FIG. 5, the vehicle system 1a includes a vehicle position estimation device 10a, a GNSS receiver 20, a vehicle status sensor 30, a communication module 40, a surrounding monitoring sensor 50, and an automatic driving ECU 60. The vehicle system 1a is the same as the vehicle system 1 of the first embodiment except that it includes a vehicle position estimation device 10a instead of the vehicle position estimation device 10.

<Schematic configuration of vehicle position estimation device 10a>
Next, an example of a schematic configuration of the own vehicle position estimating device 10a will be explained. As shown in FIG. 5, the vehicle position estimation device 10a includes a surrounding information acquisition section 101, a driving environment recognition section 102a, a positioning section 103, a map data acquisition section 104a, an MM section 105, a reliability identification section 106a, and a position estimation section. The unit 107a is provided as a functional block. The own vehicle position estimation device 10a includes a driving environment recognition section 102a instead of the driving environment recognition section 102. The own vehicle position estimation device 10a includes a map data acquisition section 104a instead of the map data acquisition section 104. The own vehicle position estimating device 10a includes a reliability specifying section 106a instead of the reliability specifying section 106. The own vehicle position estimating device 10a includes a position estimating section 107a instead of the position estimating section 107. The own vehicle position estimating device 10a is the same as the own vehicle position estimating device 10 of the first embodiment except for these points. Executing the processing of each functional block of the own vehicle position estimating device 10a by the computer also corresponds to executing the own vehicle position estimation method.

The driving environment recognition unit 102a is similar to the driving environment recognition unit 102 of the first embodiment, except that it is required to recognize road markings instead of recognizing the number of lanes. The road markings are included in the road markings described in the first embodiment. Road markings are drawn on the road surface using road marking paint, road studs, or the like. Road markings include regulation markings and instruction markings. A restriction sign restricts or specifies a specific way of travel. Directional signs indicate that a particular way of travel is allowed, the meaning of the section or location under the Road Traffic Act, and the part of the road that should be traveled. This process in the driving environment recognition unit 102a corresponds to a second driving environment recognition step. The road markings recognized by the driving environment recognition unit 102a are preferably road markings that are not limited to intersections. Examples of such road markings include maximum speed regulation displays.

The map data acquisition unit 104a acquires map data including road markings for each area. The map data acquisition unit 104a is similar to the map data acquisition unit 104 of the first embodiment, except that the map data must include road markings for each area. By area, it may be by link, by segment, etc. A segment is a unit in which a link is divided by shape points. This process in the map data acquisition unit 104a corresponds to a second map data acquisition step. The road markings included in the map data are of the same type as the road markings recognized by the driving environment recognition unit 102a.

The reliability specifying unit 106a is the same as the reliability specifying unit 106 of the first embodiment, except that the degree of similarity of road markings is used instead of the degree of similarity of the number of lanes. The reliability identifying unit 106a identifies the degree of similarity between the road markings on the route of the own vehicle recognized by the driving environment recognition unit 102a and the road markings on the route of the own vehicle acquired by the map data acquisition unit 104a. Then, based on the identified degree of similarity, the reliability of the driving position of the own vehicle on the road is determined. Hereinafter, the road markings of the driving route of the own vehicle recognized by the driving environment recognition unit 102a will be referred to as recognized road markings. Hereinafter, the road markings of the driving route of the own vehicle obtained by the map data obtaining unit 104a will be referred to as map road markings. The road marking of the driving route of the own vehicle acquired by the map data acquisition unit 104a is the road marking of the area estimated to be the driving area of the own vehicle, acquired by the map data acquisition unit 104a. The area estimated to be the driving area of the own vehicle may be a candidate position determined by the MM unit 105. The reliability specifying unit 106a specifies a higher reliability as the degree of similarity between the recognized road marking and the map road marking increases.

The position estimating unit 107a is similar to the position estimating unit 107 of the first embodiment, except that the degree of similarity between the recognized road markings and the map road markings is used instead of the degree of similarity between the number of recognized lanes and the number of map lanes. be. This process in the position estimating section 107a corresponds to a second position estimating step. Road markings are elements that are likely to be placed at locations other than intersections. Therefore, by using road markings, it is possible to estimate the driving position of the own vehicle on the road with higher accuracy even at locations other than intersections. Further, the road markings can be recognized from the sensing results of the sensing range including the road surface by the surrounding monitoring sensor 50, which is generally used in automatic driving. Therefore, it has higher versatility than a technology that uses a sensing range other than the general sensing range.

It is preferable that the position estimating unit 107a estimates the traveling position of the own vehicle on the road using the reliability specified by the reliability specifying unit 106a. This is because the reliability can be used to determine whether or not to determine the driving position of the own vehicle. Note that, similarly to the position estimation unit 107, the position estimation unit 107a may also estimate in which lane on a multi-lane road the own vehicle is located.

<Position estimation related processing in own vehicle position estimation device 10a>
Next, an example of the flow of position estimation related processing in the own vehicle position estimation device 10a will be explained using the flowchart of FIG. The flowchart of FIG. 6 may be configured to start, for example, when the power switch of the host vehicle is turned on. Another condition may be that the self-driving function of the own vehicle is set to on.

In steps S21 to S23, processes similar to those in S1 to S3 are performed. In step S24, the position estimation unit 107a narrows down the driving position of the own vehicle on the road based on the degree of similarity between the recognized road marking and the map road marking. Even if it is not possible to narrow down the driving position to one in S24, the driving position can be narrowed down to the driving position on the road with the highest reliability. In step S25, the driving position of the own vehicle on the road narrowed down to one in S24 is estimated as the driving position of the own vehicle.

In step S26, if it is the end timing of the position estimation related process (YES in S26), the position estimation related process is ended. On the other hand, if it is not the end timing of the position estimation related process (NO in S26), the process returns to S21 and repeats the process.

(Embodiment 3)
The present invention is not limited to the configuration of the above-described embodiment, but may be the configuration of Embodiment 3 below. An example of the configuration of Embodiment 3 will be described below with reference to the drawings.

<Schematic configuration of vehicle system 1b>
As shown in FIG. 7, the vehicle system 1b includes a vehicle position estimation device 10b, a GNSS receiver 20, a vehicle status sensor 30, a communication module 40, a surrounding monitoring sensor 50, and an automatic driving ECU 60. The vehicle system 1b is the same as the vehicle system 1 of the first embodiment except that it includes a vehicle position estimation device 10b instead of the vehicle position estimation device 10.

<Schematic configuration of vehicle position estimation device 10b>
Next, an example of a schematic configuration of the own vehicle position estimating device 10b will be explained. As shown in FIG. 7, the own vehicle position estimation device 10b includes a surrounding information acquisition section 101b, a driving environment recognition section 102b, a positioning section 103, a map data acquisition section 104b, an MM section 105, a reliability identification section 106b, and a position estimation section. The unit 107b is provided as a functional block. The own vehicle position estimation device 10b includes a surrounding information acquisition section 101b instead of the surrounding information acquisition section 101. The own vehicle position estimation device 10b includes a driving environment recognition section 102b instead of the driving environment recognition section 102. The own vehicle position estimation device 10b includes a map data acquisition section 104b instead of the map data acquisition section 104. The vehicle position estimating device 10b includes a reliability specifying section 106b instead of the reliability specifying section 106. The own vehicle position estimating device 10b includes a position estimating section 107b instead of the position estimating section 107. The own vehicle position estimating device 10b is the same as the own vehicle position estimating device 10 of the first embodiment except for these points. Executing the processing of each functional block of the own vehicle position estimating device 10b by the computer also corresponds to executing the own vehicle position estimation method.

The surrounding information acquisition unit 101b is the same as the surrounding information acquisition unit 101 of the first embodiment, except that it is essential to acquire a photographed image taken by a surrounding monitoring camera.

The driving environment recognition unit 102b is required to recognize the target ratio, which is at least one of the empty area ratio and the structure ratio, instead of recognizing the number of lanes. The driving environment recognition unit 102b is similar to the driving environment recognition unit 102 of the first embodiment except for this point. The sky area ratio is the ratio of the sky area in the photographed image. The structure ratio is the ratio of structures in the captured image. The driving environment recognition unit 102b may recognize the sky and structures in the captured image using a learning device that has learned to recognize the sky and structures through deep learning and machine learning. Next, the driving environment recognition unit 102b calculates the proportions of the recognized sky and structures in the photographed image as the sky area ratio and the structure ratio. Then, the calculated driving environment recognition unit 102b may recognize the calculated empty area ratio and structure ratio as the target ratio. The target ratio may be either the empty area ratio or the structure ratio. This process in the driving environment recognition unit 102b corresponds to a third driving environment recognition step.

The map data acquisition unit 104b acquires map data including target ratios for each region. The map data acquisition unit 104b is similar to the map data acquisition unit 104 of the first embodiment, except that the map data must include the target ratio for each area. This target ratio is set to the same type as the target ratio recognized by the driving environment recognition unit 102b. For example, if the target ratio recognized by the driving environment recognition unit 102b is a sky area ratio, the map data acquisition unit 104b may also acquire the sky area ratio as the target ratio. By area, it may be by segment, by point, etc. The map data may include target ratios for the uphill and downhill directions of the road, respectively, for the same area. This process by the map data acquisition unit 104b corresponds to a third map data acquisition step.

The reliability specifying unit 106b is similar to the reliability specifying unit 106 of the first embodiment, except that the degree of similarity of target ratios is used instead of the degree of similarity of the number of lanes. The reliability identifying unit 106b identifies the degree of similarity between the target ratio of the vehicle's route recognized by the driving environment recognition unit 102b and the target ratio of the vehicle's route acquired by the map data acquisition unit 104b. The target ratio acquired by the map data acquisition unit 104b is the target ratio for the same traveling direction as the own vehicle's traveling direction. The traveling direction of the own vehicle may be specified based on changes in the approximate position over time. Then, the reliability specifying unit 106b specifies the reliability of the driving position of the own vehicle on the road based on the specified degree of similarity. Hereinafter, the target ratio of the driving route of the own vehicle recognized by the driving environment recognition unit 102b will be referred to as a recognition target ratio. Hereinafter, the target ratio of the driving route of the own vehicle acquired by the map data acquisition unit 104b will be referred to as a map target ratio. The target ratio of the driving route of the own vehicle acquired by the map data acquiring unit 104b is the target ratio of the area estimated to be the driving area of the own vehicle, acquired by the map data acquiring unit 104b. The area estimated to be the driving area of the own vehicle may be a candidate position determined by the MM unit 105. The reliability specifying unit 106b specifies a high reliability as the similarity between the recognition target ratio and the map target ratio increases.

The reliability specifying unit 106b determines the change in the structure ratio of the route of the own vehicle, which is sequentially recognized by the driving environment recognition unit 102b, and the change in the structure ratio of the route of the own vehicle, which is acquired by the map data acquisition unit 104b. The degree of similarity may also be specified. The route taken by the own vehicle is a group of areas through which the own vehicle is presumed to have traveled. The area group may be a segment group or a point group. The route of the own vehicle may be specified from the approximate position sequentially estimated by the positioning unit 103. Preferably, the reliability specifying unit 106b also uses the specified degree of similarity to specify the reliability of the driving position of the own vehicle on the road. Hereinafter, the change in the structure ratio of the driving path of the own vehicle that is sequentially recognized by the driving environment recognition unit 102b will be referred to as a recognized structure ratio change. Hereinafter, the change in the structure ratio of the route taken by the host vehicle acquired by the map data acquisition unit 104b will be referred to as a map structure ratio change. The reliability specifying unit 106b may correct the reliability higher as the degree of similarity between the recognized structure rate change and the map structure rate change becomes higher.

The position estimation unit 107b uses the degree of similarity between the recognition target ratio and the map target ratio instead of the degree of similarity between the number of recognized lanes and the number of map lanes. The position estimating unit 107b is similar to the position estimating unit 107 of the first embodiment except for this point. This process in the position estimating unit 107b corresponds to a third position estimating step. Target ratios such as empty area ratio and structure ratio are factors not limited to intersections. Therefore, by using the target ratio, it becomes possible to estimate the driving position of the own vehicle on the road with higher accuracy even at a place other than an intersection.

Preferably, the position estimating unit 107b estimates the driving position of the own vehicle on the road by also using the degree of similarity between the change in the recognized structure ratio and the map structure ratio change. The change in the structure ratio differs depending on, for example, the presence or absence of periodically arranged structures. Examples of periodically arranged structures include streetlights arranged at equal intervals. According to the above configuration, even if it is difficult to narrow down to one running position using only the target ratio, it becomes easier to narrow down to one running position by using the change over time in the structure ratio.

It is preferable that the position estimating unit 107b estimates the traveling position of the own vehicle on the road using the reliability specified by the reliability specifying unit 106b. This is because the reliability can be used to determine whether or not to determine the driving position of the own vehicle. Note that, similarly to the position estimation unit 107, the position estimation unit 107b may also estimate in which lane on a multi-lane road the own vehicle is located.

<Position estimation related processing in own vehicle position estimation device 10b>
Next, an example of the flow of position estimation related processing in the own vehicle position estimation device 10b will be explained using the flowchart of FIG. 8. The flowchart of FIG. 8 may be configured to start, for example, when the power switch of the host vehicle is turned on. Another condition may be that the self-driving function of the own vehicle is set to on.

In steps S41 to S43, processes similar to those in S1 to S3 are performed. In step S44, the position estimation unit 107b narrows down the driving position of the own vehicle on the road based on the degree of similarity between the recognition target ratio and the map target ratio. In step S45, if the driving position can be narrowed down to one in S44 (YES in S45), the process moves to step S47. On the other hand, if the driving position cannot be narrowed down to one in S44 (NO in S45), the process moves to step S46.

In step S46, the position estimating unit 107b further narrows down the driving position of the own vehicle on the road based on the degree of similarity between the change in the recognized structure ratio and the map structure ratio change. Even if it is not possible to narrow down the driving position to one in S46, the driving position can be narrowed down to the driving position on the road with the highest reliability. In step S47, the running position of the own vehicle on the road narrowed down to one in the processing up to that point is estimated as the running position of the own vehicle.

In step S48, if it is the end timing of the position estimation related process (YES in S48), the position estimation related process is ended. On the other hand, if it is not the end timing of the position estimation related process (NO in S48), the process returns to S41 and repeats the process.

In the example of FIG. 8, a configuration is shown in which the driving position of the own vehicle is sequentially narrowed down based on the degree of similarity of changes in the target ratio and road structure ratio, but the present invention is not necessarily limited to this. For example, the driving position of the own vehicle may be narrowed down and estimated by combining the degree of similarity of target ratios and the degree of similarity of changes in road structure ratio. According to a configuration that sequentially narrows down the driving position of the own vehicle based on the degree of similarity of changes in the target ratio and road structure ratio, unnecessary processing can be more easily omitted than when processing is performed all at once.

Note that the present disclosure is not limited to the embodiments described above, and various changes can be made within the scope of the claims, and can be obtained by appropriately combining technical means disclosed in different embodiments. The embodiments are also included in the technical scope of the present disclosure. Further, the control unit and the method described in the present disclosure may be implemented by a dedicated computer constituting a processor programmed to perform one or more functions embodied by a computer program. Alternatively, the apparatus and techniques described in this disclosure may be implemented with dedicated hardware logic circuits. Alternatively, the apparatus and techniques described in this disclosure may be implemented by one or more special purpose computers configured by a combination of a processor executing a computer program and one or more hardware logic circuits. The computer program may also be stored as instructions executed by a computer on a computer-readable non-transitory tangible storage medium.

1, 1a, 1b vehicle system, 10, 10a, 10b vehicle position estimation device, 50 surroundings monitoring sensor, 102, 102a, 102b driving environment recognition unit, 104, 104a, 104b map data acquisition unit, 106, 106a, 106b Reliability identification unit, 107, 107a, 107b Position estimation unit

Claims (10)

used in vehicles,
a driving environment recognition unit (102) that recognizes a driving environment including the number of lanes on a running route of the vehicle from sensing results from a surroundings monitoring sensor (50) that monitors the surroundings of the vehicle;
a map data acquisition unit (104) that acquires map data including the number of road lanes for each region;
The road is determined based on the degree of similarity between the number of lanes of the vehicle's driving route recognized by the driving environment recognition unit and the number of lanes of the area estimated to be the vehicle's driving area acquired by the map data acquisition unit. An own vehicle position estimating device comprising: a position estimating section (107) for estimating a traveling position of the vehicle. The own vehicle position estimation device according to claim 1,
The driving environment recognition unit recognizes the driving environment including road width,
The map data acquisition unit acquires the map data including road width by area,
The position estimating unit determines the degree of similarity between the road width of the vehicle's driving route recognized by the driving environment recognition unit and the road width of the area estimated to be the vehicle's driving area acquired by the map data acquiring unit. A self-vehicle position estimating device that estimates the traveling position of the vehicle on a road using the following information. The own vehicle position estimation device according to claim 2,
The driving environment recognition unit recognizes the driving environment including the lane width of each lane,
The map data acquisition unit acquires the map data including lane widths for each lane in each region,
The position estimating unit is configured to use a lane width pattern for each lane of the vehicle's driving route recognized by the driving environment recognition unit and a lane-by-lane pattern of an area estimated to be a driving area of the vehicle, which is acquired by the map data acquiring unit. A self-vehicle position estimating device that estimates a traveling position of the vehicle on a road using a degree of similarity with a lane width pattern. used in vehicles,
a driving environment recognition unit (102a) that recognizes a driving environment including road markings on the route of the vehicle from sensing results from a surroundings monitoring sensor (50) that monitors the surroundings of the vehicle;
a map data acquisition unit (104a) that acquires map data including road markings for each area;
Based on the degree of similarity between the road markings on the route of the vehicle recognized by the driving environment recognition unit and the road markings in the area estimated to be the driving area of the vehicle acquired by the map data acquisition unit, A vehicle position estimating device comprising: a position estimating section (107a) for estimating a traveling position of the vehicle. used in vehicles,
From images taken by a surrounding surveillance camera that photographs the surroundings of the vehicle, a sky area ratio, which is the ratio of the sky area in the photographed image on the running route of the vehicle, and a structure ratio, which is the ratio of structures in the photographed image. a driving environment recognition unit (102b) that recognizes a driving environment including a target ratio that is at least one of the following;
a map data acquisition unit (104b) that acquires map data including the target ratio for each area;
Based on the degree of similarity between the target ratio of the vehicle recognized by the driving environment recognition unit and the target ratio of the area estimated to be the driving area of the vehicle acquired by the map data acquisition unit, road An own vehicle position estimating device comprising: a position estimating section (107b) for estimating a traveling position of the vehicle. The own vehicle position estimation device according to claim 5,
The driving environment recognition unit recognizes a driving environment including at least the structure ratio as the target ratio,
The map data acquisition unit acquires map data including at least the structure ratio by area as the target ratio by area,
The position estimating unit determines whether the vehicle is passing through based on changes in the structure ratio of the vehicle sequentially recognized by the driving environment recognition unit and the structure ratio acquired by the map data acquisition unit. A self-vehicle position estimating device that estimates a traveling position of the vehicle on a road using a degree of similarity with a change in the structure ratio in a group of regions to be estimated. The own vehicle position estimation device according to claim 1, 4, or 5,
a reliability identifying unit (106, 106a, 106b) that identifies the reliability of the traveling position of the vehicle on the road based on the degree of similarity;
The position estimating unit is a self-vehicle position estimating device that estimates the traveling position of the vehicle on the road using the reliability specified by the reliability specifying unit. used in vehicles,
executed by at least one processor;
a first driving environment recognition step of recognizing a driving environment including the number of lanes on a running route of the vehicle from sensing results from a surroundings monitoring sensor (50) that monitors the surroundings of the vehicle;
a first map data acquisition step of acquiring map data including the number of road lanes for each area;
The degree of similarity between the number of lanes of the vehicle's driving route recognized in the first driving environment recognition step and the number of lanes of the area estimated to be the vehicle's driving area acquired in the first map data acquiring step is also determined. and a first position estimation step of estimating a traveling position of the vehicle on a road. used in vehicles,
executed by at least one processor;
a second driving environment recognition step of recognizing a driving environment including road markings on a running path of the vehicle from sensing results from a surroundings monitoring sensor (50) that monitors the surroundings of the vehicle;
a second map data acquisition step of acquiring map data including road markings for each area;
The degree of similarity between the road markings on the route of the vehicle recognized in the second driving environment recognition step and the road markings in the area estimated to be the driving area of the vehicle acquired in the second map data acquisition step is also determined. and a second position estimation step of estimating the traveling position of the vehicle on the road. used in vehicles,
executed by at least one processor;
From images captured by a surrounding monitoring camera that captures the surroundings of the vehicle, an empty area ratio, which is the ratio of the empty area in the captured image on the running route of the vehicle, and a structure ratio, which is the ratio of structures in the captured image. a third driving environment recognition step of recognizing a driving environment including a target ratio that is at least one of the following;
a third map data acquisition step of acquiring map data including the target ratio for each area;
The degree of similarity between the target ratio of the vehicle recognized in the third driving environment recognition step and the target ratio of the area estimated to be the driving area of the vehicle acquired in the third map data acquisition step is also determined. and a third position estimation step of estimating the traveling position of the vehicle on the road.

Images