WO2021145032A1 - 周辺車両位置推定システム、周辺車両位置推定プログラム - Google Patents

周辺車両位置推定システム、周辺車両位置推定プログラム Download PDF

Info

Publication number
WO2021145032A1
WO2021145032A1 PCT/JP2020/037491 JP2020037491W WO2021145032A1 WO 2021145032 A1 WO2021145032 A1 WO 2021145032A1 JP 2020037491 W JP2020037491 W JP 2020037491W WO 2021145032 A1 WO2021145032 A1 WO 2021145032A1
Authority
WO
WIPO (PCT)
Prior art keywords
vehicle
peripheral
road
position estimation
acquires
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/JP2020/037491
Other languages
English (en)
French (fr)
Japanese (ja)
Inventor
薫生 森部
敏史 道田
智明 廣田
亮介 東淵
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Aisin AW Co Ltd
Original Assignee
Aisin AW Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Aisin AW Co Ltd filed Critical Aisin AW Co Ltd
Priority to CN202080080219.0A priority Critical patent/CN114762020A/zh
Priority to US17/771,521 priority patent/US20220404166A1/en
Priority to EP20914424.5A priority patent/EP4092651A1/en
Priority to JP2021570645A priority patent/JPWO2021145032A1/ja
Publication of WO2021145032A1 publication Critical patent/WO2021145032A1/ja
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/36—Input/output arrangements for on-board computers
    • G01C21/3691—Retrieval, searching and output of information related to real-time traffic, weather, or environmental conditions
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/16—Anti-collision systems
    • G08G1/166—Anti-collision systems for active traffic, e.g. moving vehicles, pedestrians, bikes
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/36—Input/output arrangements for on-board computers
    • G01C21/3626—Details of the output of route guidance instructions
    • G01C21/3641—Personalized guidance, e.g. limited guidance on previously travelled routes
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/36—Input/output arrangements for on-board computers
    • G01C21/3626—Details of the output of route guidance instructions
    • G01C21/3652—Guidance using non-audiovisual output, e.g. tactile, haptic or electric stimuli

Definitions

  • the present invention relates to a peripheral vehicle position estimation system and a peripheral vehicle position estimation program.
  • Patent Document 1 the image recognition result of the image taken by the CCD camera and the detection result by the radar are used in combination to determine which lane the surrounding vehicle is on or outside the lane to improve the detection accuracy. It is stated that.
  • the present invention has been made in view of the above problems, and an object of the present invention is to provide a technique for improving the estimation accuracy of the position of a peripheral vehicle.
  • the peripheral vehicle position estimation system includes a relative position information acquisition unit that acquires the relative orientation of the peripheral vehicles existing in the vicinity of the own vehicle with respect to the own vehicle, and the vicinity of the current position of the own vehicle. Based on the map information, the map information acquisition unit that acquires the map information of the vehicle and the peripheral road that overlaps with the straight line extending from the own vehicle in the relative direction are acquired, and the position of the peripheral vehicle is estimated to be present on the peripheral road. It has a part and.
  • the peripheral vehicle position estimation program uses a computer as a relative position information acquisition unit for acquiring the relative orientation of the peripheral vehicles existing in the vicinity of the own vehicle with respect to the own vehicle, and the own vehicle. Based on the map information, the map information acquisition unit that acquires the map information around the current position of the vehicle acquires the peripheral road that overlaps with the straight line extending from the own vehicle in the relative direction, and estimates that there are peripheral vehicles on the peripheral road. It functions as a vehicle position estimation unit.
  • the peripheral road on which the peripheral vehicle is traveling is estimated based on the relative orientation of the peripheral vehicle and the map information around the current position of the own vehicle. Therefore, according to this configuration, the position of the peripheral vehicle is estimated based on the relative orientation of the peripheral vehicle based on the current position of the own vehicle without performing the position correction based on the map information. Even if the distance is more than a certain distance, the accuracy of estimating the position of surrounding vehicles can be improved.
  • FIG. 2A is a diagram showing an example of an image taken by a camera
  • FIG. 2B is a schematic diagram showing the positions of the road in front of the own vehicle and surrounding vehicles. Flowchart of peripheral vehicle position estimation processing.
  • FIG. 1 is a block diagram showing a configuration of a navigation system 10 including a peripheral vehicle position estimation system according to an embodiment of the present invention.
  • the navigation system 10 is provided in the vehicle, and includes a control unit 20 including a CPU, RAM, ROM, and the like, and a recording medium 30.
  • the control unit 20 can execute a program stored in the recording medium 30 or the ROM. Map information 30a is recorded in advance on the recording medium 30.
  • the map information 30a is information used for specifying the position of an intersection, route guidance, etc., and specifies node data indicating the position of a node set on the road on which the vehicle travels, and the shape of the road between the nodes. It includes shape interpolation point data indicating the position of the shape interpolation point for the purpose, link data indicating the connection between nodes, and feature data indicating the position and shape of the features existing on the road and its surroundings.
  • the nodes indicate intersections.
  • the link data is associated with information indicating the number of lanes existing in the road section indicated by the link data and the width of the lane.
  • the position indicated by the node or the shape interpolation point indicates the position of the center line on the road section, and the position of the lane and the range in which the lane exists can be specified by the position, the number of lanes, and the width of the lane. be.
  • the own vehicle in this embodiment includes a camera 40, a GNSS receiving unit 41, a vehicle speed sensor 42, a gyro sensor 43, and a user I / F unit 44.
  • the GNSS receiving unit 41 is a device that receives signals from the Global Navigation Satellite System, receives radio waves from navigation satellites, and outputs a signal for calculating the current position of the own vehicle via an interface (not shown).
  • the control unit 20 acquires this signal and acquires the current position (latitude, longitude, etc.) of the own vehicle in the coordinate system of the map.
  • the vehicle speed sensor 42 outputs a signal corresponding to the rotation speed of the wheels included in the own vehicle.
  • the control unit 20 acquires this signal via an interface (not shown) to acquire the vehicle speed.
  • the gyro sensor 43 detects the angular acceleration of the turning of the own vehicle in the horizontal plane, and outputs a signal corresponding to the direction of the own vehicle.
  • the control unit 20 acquires this signal and acquires the traveling direction of the own vehicle.
  • the vehicle speed sensor 42, the gyro sensor 43, and the like are used to identify the traveling locus of the own vehicle.
  • the current position is specified based on the starting point and the traveling locus of the own vehicle, and the starting place is concerned.
  • the current position of the own vehicle specified based on the travel locus and the travel locus is corrected based on the output signal of the GNSS receiving unit 41.
  • the camera 40 is a device that acquires an image in the field of view directed to the front of the own vehicle.
  • the optical axis of the camera 40 is fixed to the own vehicle, and the direction of the optical axis may be known in the navigation system 10.
  • the camera 40 is attached to the own vehicle in a posture in which the vehicle width direction of the own vehicle and the center of the optical axis are perpendicular to each other and the front in the traveling direction of the own vehicle is included in the field of view.
  • the control unit 20 can detect other vehicles (peripheral vehicles) existing in the vicinity of the own vehicle by acquiring the image output by the camera 40 and analyzing the image by extracting the feature amount or the like.
  • the user I / F unit 44 is an interface unit for inputting user instructions and providing various information to the user, and includes a touch panel type display, a speaker, and the like (not shown). That is, the user I / F unit 44 includes an image and sound output unit and an input unit for instructions by the user.
  • the control unit 20 accepts the input of the destination by the user via the input unit of the user I / F unit 44 (not shown) by the function of the navigation program (not shown), and based on the map information 30a, the control unit 20 starts from the current position of the own vehicle to the destination. Search for the planned travel route to. Further, the control unit 20 controls the user I / F unit 44 by the function of the navigation program, and executes guidance for traveling along the planned travel route. In the present embodiment, as an additional function of the navigation program, it is possible to estimate the position of a peripheral vehicle existing in the vicinity of the own vehicle and provide guidance based on the judgment result of the collision risk with the own vehicle. The guidance is realized by the peripheral vehicle position estimation program 21.
  • the peripheral vehicle position estimation program 21 may be executable regardless of whether or not the planned travel route is being guided.
  • the peripheral vehicle position estimation program 21 includes a relative position information acquisition unit 21a, a map information acquisition unit 21b, a peripheral vehicle position estimation unit 21c, and a risk determination unit 21d in order to realize the guidance.
  • the relative position information acquisition unit 21a is a program module that causes the control unit 20 to execute a function of acquiring the relative orientation of the peripheral vehicle existing in the vicinity of the own vehicle with respect to the own vehicle and the linear distance between the own vehicle and the peripheral vehicle. Is.
  • the control unit 20 acquires relative position information of peripheral vehicles with respect to the own vehicle based on an image taken by one camera 40 (monocular camera). Therefore, the cost can be suppressed as compared with the configuration in which a plurality of sensors are used in combination.
  • the control unit 20 acquires images continuously taken by the camera 40 and performs distortion correction or the like with a lens.
  • the control unit 20 includes features of a vehicle (for example, a freight vehicle, a passenger car, a two-wheeled vehicle, etc.) in the image. It determines whether or not the vehicle is used, and detects images of peripheral vehicles existing in the vicinity of the own vehicle.
  • a vehicle for example, a freight vehicle, a passenger car, a two-wheeled vehicle, etc.
  • FIG. 2A is a diagram showing an example of an image I taken by the camera 40 after distortion correction.
  • the bounding box B is a rectangular area surrounding the peripheral vehicle detected in the image I, and shows the size of the image showing the peripheral vehicle and the position of the peripheral vehicle in the image I.
  • the size and position of the bounding box B are represented by, for example, the coordinates of the upper left vertex and the coordinates of the lower right vertex of the bounding box B.
  • the control unit 20 acquires the height h (number of pixels) of the bounding box B and the representative coordinates Bo (x, y) of the bounding box B from the coordinates of the two diagonal vertices of the bounding box B.
  • the representative coordinate Bo may be, for example, the center coordinate of the bounding box B (midpoint in the width direction and the height direction).
  • Each coordinate in the image I is associated with a relative orientation of the object reflected in the coordinate with respect to the own vehicle, and information indicating the correspondence is stored in the recording medium 30. Based on this correspondence, the control unit 20 acquires the relative orientation of the peripheral vehicle reflected in the representative coordinates Bo with respect to the own vehicle.
  • a vehicle coordinate system based on the own vehicle is defined.
  • the vehicle coordinate system is a three-dimensional coordinate system defined by a vehicle width axis, a vehicle length axis, and a vehicle height axis that are orthogonal to each other.
  • FIG. 2B shows a plane including a vehicle width axis and a vehicle length axis.
  • the point O is the origin of the vehicle coordinate system in the own vehicle.
  • the vehicle length axis is parallel to the link L0 indicating the own vehicle driving road.
  • the relative orientation is, for example, the angle ( ⁇ ) formed by the straight line SL connecting the origin O of the vehicle coordinate system and the point corresponding to the representative coordinate Bo on the plane including the vehicle width axis and the vehicle length axis. It is expressed (for example, when ⁇ is a negative value, it indicates that it is on the left side of the vehicle length axis toward the front in the traveling direction, and when it is a positive value, it indicates that it is on the right side).
  • control unit 20 specifies the type of peripheral vehicles in the bounding box by image recognition processing.
  • the type of the vehicle may be any type indicating the size of the vehicle body, and may be classified into, for example, a freight vehicle, a passenger car, a two-wheeled vehicle, and the like.
  • a typical vehicle height (for example, 1.5 [m] in the case of a passenger car) is specified for each type of vehicle, and the straight line distance between the own vehicle and the relevant vehicle and the relevant vehicle with the camera of the own vehicle are specified.
  • the height of the bounding box when shooting is measured in advance.
  • Information indicating the correspondence between the height of the bounding box and the linear distance with respect to the origin of the vehicle coordinate system is stored in the recording medium 30 for each type of vehicle.
  • the linear distance is D1 [m]
  • the linear distance is D2. It is associated with [m].
  • Information indicating the correspondence between other types such as freight vehicles and two-wheeled vehicles is stored in the recording medium 30.
  • the control unit 20 calculates a linear distance D (see FIG. 2B) corresponding to the height h of the bounding box B based on this correspondence.
  • the control unit 20 acquires the relative orientation ⁇ of the surrounding vehicles included in the image and the linear distance D from the own vehicle based on the image taken by the camera 40.
  • the map information acquisition unit 21b is a program module that enables the control unit 20 to acquire the map information around the current position of the own vehicle.
  • the control unit 20 acquires the current position of the own vehicle in the coordinate system of the map based on the output signals of the GNSS receiving unit 41, the vehicle speed sensor 42, and the gyro sensor 43 and the map information 30a. Further, the control unit 20 acquires map information around the current position of the own vehicle.
  • the control unit 20 acquires, for example, map information of an area corresponding to an area included in the field of view of the camera 40 as map information around the current position of the own vehicle.
  • the control unit 20 is a fan-shaped area indicating a range of a predetermined radius at a predetermined angle to the left and right from the vehicle length axis of the own vehicle. You may get the map information of. Further, for example, the control unit 20 has an equal-passenger trapezoidal shape (the long axis of the own vehicle is orthogonal to the two opposing sides, the short side of the two opposing sides passes through the origin of the own vehicle, and the height is predetermined. The map information of the area of (value) may be acquired.
  • control unit 20 may acquire map information of a first distance ahead of the traveling direction of the own vehicle and a region of each second left and right distance in a direction orthogonal to the traveling direction.
  • the acquired map information includes road information (link data, shape interpolation point data, etc.) indicating the shape and position of the road included in the area.
  • the peripheral vehicle position estimation unit 21c acquires a peripheral road that overlaps with a straight line extending from the own vehicle in a relative direction, and gives the control unit 20 a function of estimating that a peripheral vehicle exists on the peripheral road. It is a program module to be realized.
  • the control unit 20 uses the function of the peripheral vehicle position estimation unit 21c to cause the control unit 20 to position the peripheral vehicle P in the coordinate system of the map based on the current position of the own vehicle, the linear distance D, and the relative orientation ⁇ (FIG. 2B). See) to get. Further, the control unit 20 identifies a road satisfying the following three conditions based on the map information 30a, and presumes that a peripheral vehicle exists on the road.
  • Condition 1 is that at least a part is included in the range A of the predetermined value distance centered on the position P of the surrounding vehicle.
  • the default value may be assumed to be, for example, about 10 m.
  • the control unit 20 refers to the positions of the nodes and shape interpolation points, the number of lanes, and the width of the lanes, and specifies the area occupied by the road on the map. That is, the control unit 20 regards the number of lanes ⁇ the width of the lane as the width of the road. Further, the control unit 20 identifies the central position of the road based on the node and the shape interpolation point, and considers that the range corresponding to the width of the road from the central position is the area occupied by the road on the map.
  • the control unit 20 identifies the road as a road existing in the range A.
  • this process is an example, and for example, a road whose center position of the road specified based on the node and the shape interpolation point is included in the range A may be specified.
  • Condition 2 is to intersect the own vehicle driving road on which the own vehicle travels.
  • the control unit 20 identifies a road that intersects with the own vehicle travel road in front of the own vehicle travel road (L0) in the traveling direction from the roads satisfying the condition 1. That is, based on the map information 30a, the control unit 20 traces the nodes existing on the road satisfying the condition 1 in order toward the own vehicle driving road side, and the nodes existing on the own vehicle traveling road are the own vehicles.
  • the control unit 20 considers that the road intersects with the own vehicle traveling road when a matching node exists in both nodes.
  • Condition 3 is that the angle between the traveling direction of surrounding vehicles and the extending direction of the road is within the reference value.
  • the control unit 20 calculates the traveling direction dd (see FIG. 2B) of the peripheral vehicle based on the time-series change in the position of the peripheral vehicle. For example, first, the control unit 20 calculates the positions of peripheral vehicles based on the images of the most recent several cycles taken by the camera 40 and the positions of the own vehicle at the time of shooting for the several cycles. That is, the control unit 20 specifies the position (origin of the vehicle coordinate system) and the attitude (direction of the long axis of the vehicle coordinate system) of the own vehicle in the coordinate system of the map at the time of taking an image by the camera 40.
  • control unit 20 acquires a position separated by a straight line distance D from the origin of the vehicle coordinate system on the line in the direction inclined by the relative direction ⁇ with respect to the vehicle length axis as the position of another vehicle in the coordinate system of the map. Further, the control unit 20 determines the traveling direction in the coordinate system of the map based on the direction connecting two adjacent positions among the positions of other vehicles acquired based on the images continuously taken by the camera 40. calculate. Then, the control unit 20 calculates the statistical values of these traveling directions as the traveling direction dd of the peripheral vehicle. Further, the control unit 20 calculates the direction in which the road satisfying the conditions 1 and 2 extends.
  • the "direction" can be defined by, for example, an inclination angle with respect to a reference (for example, a specific coordinate axis or the traveling direction of the own vehicle) in the coordinate system of the map (the same applies hereinafter).
  • the control unit 20 calculates the extending direction of the road satisfying the conditions 1 and 2 in the range A and its vicinity from the shape indicated by the node and the shape interpolation point of the road. For example, in the example of FIG. 2B, since the link L1 satisfies the condition 1 and the condition 2, the control unit 20 acquires the positions of both end points of the link L1 as information indicating the shape of the link L1 in and near the range A. The control unit 20 calculates the direction in which the link L1 extends from the positions of both end points. Then, the control unit 20 determines whether or not the angle (acute angle side) formed by the traveling direction dd of the peripheral vehicle and the extending direction of the link L1 is within the reference value.
  • the reference value is a threshold value for determining whether or not the two directions are substantially parallel.
  • the control unit 20 estimates that there are peripheral vehicles on the peripheral roads that satisfy the conditions 1, 2, and 3. When there are a plurality of roads satisfying the conditions 1, 2, and 3, the control unit 20 estimates the road closest to the position P of the peripheral vehicle as the peripheral road in which the peripheral vehicle exists.
  • control unit 20 calculates the position of the intersection of the peripheral road estimated to have the surrounding vehicle and the straight line extending from the own vehicle in the relative direction.
  • the control unit 20 calculates the position of the intersection P1 between the peripheral road (L1) and the straight line SL. Then, the control unit 20 corrects the position of the surrounding vehicle from P to P1. That is, in the present embodiment, the control unit 20 has a peripheral vehicle at an intersection of a straight line extending from the own vehicle in a relative direction and the peripheral road existing on the peripheral road satisfying the conditions 1, 2, and 3. I presume that.
  • the risk determination unit 21d is a program module that allows the control unit 20 to realize a function of determining the collision risk of a peripheral vehicle with its own vehicle based on the estimation result by the peripheral vehicle position estimation unit 21c.
  • the control unit 20 uses the current position of the own vehicle, the speed at which the own vehicle moves on the own vehicle driving road, the position of the intersection of the straight line and the surrounding road, and the peripheral vehicle moving on the surrounding road. Based on the speed to be used, the presence or absence of a collision risk between the own vehicle and surrounding vehicles is determined. That is, the control unit 20 calculates the speed at which the own vehicle moves on the own vehicle traveling road (L0) based on the time-series change of the current position of the own vehicle.
  • control unit 20 calculates the speed at which the peripheral vehicle moves on the peripheral road (L1) based on the time-series change in the position (P1) of the peripheral vehicle after the correction. Then, when the peripheral vehicle and the own vehicle maintain the speed, the control unit 20 determines the peripheral vehicle and the own vehicle in advance at the intersection (N1) between the peripheral road (L1) and the own vehicle traveling road (L0). It is determined whether or not the vehicle approaches within the distance. That is, the control unit 20 calculates the time T until the own vehicle reaches the intersection (N1) when the own vehicle travels on the own vehicle traveling road (L0) while maintaining the calculated speed.
  • the control unit 20 calculates a predicted point at which the peripheral vehicle will arrive at the time T when the vehicle travels on the peripheral road (L1) while maintaining the calculated speed.
  • the control unit 20 compares the distance between the intersection (N1) and the predicted point with a predetermined distance. In this way, the control unit 20 determines whether or not the peripheral vehicle and the own vehicle approach each other within a predetermined distance.
  • control unit 20 guides the determination result by the user I / F unit 44. For example, when it is determined that the own vehicle and the surrounding vehicles approach each other within a predetermined distance, the control unit 20 generates a warning sound in the speaker.
  • the peripheral road on which the peripheral vehicle is traveling is estimated based on the relative orientation of the peripheral vehicle and the map information around the current position of the own vehicle. Therefore, according to the present embodiment, the position of the peripheral vehicle is estimated based on the relative position of the peripheral vehicle based on the current position of the own vehicle without performing the position correction based on the map information. Even if the distance is more than a certain distance, the accuracy of estimating the position of surrounding vehicles can be improved. Therefore, according to the present embodiment, it is possible to improve the accuracy of determining the collision risk of neighboring vehicles with the own vehicle.
  • the control unit 20 executes an image recognition process for the captured image at each shooting cycle by the camera 40.
  • the control unit 20 acquires the coordinates of the two diagonal vertices of the bounding box surrounding the image of the vehicle (peripheral vehicle). Also, the type of peripheral vehicle in the bounding box is acquired. After passing through these processes, the control unit 20 executes the peripheral vehicle position estimation process for each peripheral vehicle included in the image I.
  • the control unit 20 acquires the relative orientation ⁇ and the straight line distance D of the peripheral vehicle with respect to the own vehicle by the function of the relative position information acquisition unit 21a (step S100). That is, the control unit 20 calculates the representative coordinate Bo from the coordinates of the two diagonal vertices of the bounding box B. Then, based on the correspondence between each coordinate in the image I and the relative direction with respect to the own vehicle, the control unit 20 acquires the relative direction of the peripheral vehicle reflected in the representative coordinate Bo of the bounding box B. Further, the control unit 20 calculates the height h of the bounding box B from the coordinates of the two diagonal vertices of the bounding box B.
  • control unit 20 acquires the type of the vehicle in the bounding box B. Then, the control unit 20 sets the bounding box based on the correspondence between the number of pixels indicating the height of the bounding box and the linear distance to the vehicle in the bounding box, and based on the correspondence according to the type of vehicle. The linear distance D corresponding to the height h of B is calculated.
  • the control unit 20 acquires the current position of the own vehicle by the function of the map information acquisition unit 21b (step S105), and acquires the road information around the current position of the own vehicle (step S110). That is, the control unit 20 acquires the current position of the own vehicle in the coordinate system of the map based on the output signals of the GNSS receiving unit 41, the vehicle speed sensor 42, and the gyro sensor 43 and the map information. The control unit 20 acquires map information around the current position of the own vehicle.
  • the acquired map information includes road information indicating the shape and position of the road included in the field of view of the camera 40.
  • the control unit 20 is a road that intersects with the own vehicle traveling road within the predetermined value distance of the position of the peripheral vehicle (condition 1) by the function of the peripheral vehicle position estimation unit 21c, and the peripheral vehicle. It is determined whether or not there is a road (condition 3) whose angle formed with the traveling direction of is within the reference value (step S115).
  • the control unit 20 calculates the position P (see FIG. 2B) of the peripheral vehicle based on the current position of the own vehicle, the linear distance D, and the relative direction ⁇ .
  • the control unit 20 determines whether or not there is a road satisfying the condition 1 based on the calculated position P of the surrounding vehicle, and if so, whether or not the road further satisfies the conditions 2 and 3. Is determined based on the road information around the own vehicle.
  • step S115 If it is not determined in step S115 that there is a road that satisfies all of the conditions 1, 2, and 3, the control unit 20 ends the peripheral vehicle position estimation process.
  • the control unit 20 uses the function of the peripheral vehicle position estimation unit 21c to form a straight line extending from the own vehicle toward the relative direction and step S115. It is estimated that there are peripheral vehicles at the intersection with the road satisfying the above conditions (step S120). That is, the control unit 20 identifies a road that satisfies all the conditions 1, 2, and 3.
  • control unit 20 calculates an intersection P1 between a straight line extending from the current position of the own vehicle toward the relative direction ⁇ and a road satisfying the conditions 1, 2, and 3. Then, the control unit 20 estimates that a peripheral vehicle exists at the intersection P1 and corrects the position of the peripheral vehicle from P to P1.
  • the control unit 20 determines the collision risk by the function of the risk determination unit 21d, and provides guidance based on the determination result (step S125).
  • the control unit 20 is based on the current position of the own vehicle, the speed at which the own vehicle moves on the own vehicle driving road, the position of the intersection of the straight line and the surrounding road, and the speed at which the peripheral vehicle moves on the surrounding road. , Determines whether or not the own vehicle and surrounding vehicles approach within a predetermined distance.
  • the control unit 20 informs that there is a risk of collision by, for example, generating a warning sound in the speaker.
  • the peripheral vehicle position estimation system may be a device mounted on a vehicle or the like, a device realized by a portable terminal, or a plurality of devices (for example, a client and a server, or It may be a system realized by a control unit in a navigation device and a control unit in a user I / F unit).
  • At least a part of the relative position information acquisition unit 21a, the map information acquisition unit 21b, the peripheral vehicle position estimation unit 21c, and the risk determination unit 21d constituting the peripheral vehicle position estimation system may be divided into a plurality of devices.
  • some configurations of the above-described embodiments may be omitted, and the order of processing may be changed or omitted.
  • the risk determination unit 21d may be omitted, and the corrected position of the surrounding vehicle may be provided to the map display processing unit.
  • the relative position information acquisition unit only needs to be able to acquire the relative orientation of the peripheral vehicles existing around the own vehicle with respect to the own vehicle.
  • the relative orientation with respect to the own vehicle is an angle defined in the own vehicle with respect to the axis penetrating the own vehicle.
  • the relative orientation of the surrounding vehicles with respect to the own vehicle may be expressed by, for example, the angle formed by the vehicle length axis in the plane including the vehicle length axis and the vehicle width axis of the vehicle coordinate system, and in addition to that. It may also be expressed as an angle formed by the vehicle length axis on a plane including the vehicle length axis and the vehicle height axis.
  • the relative orientation may be obtained from the outputs of various sensors such as cameras and radars (including LiDAR) that photograph the surroundings of the own vehicle. Further, the relative orientations of not only the front of the own vehicle but also the peripheral vehicles on the side and the rear side may be acquired. Further, the acquisition of the relative position of the surrounding vehicle from the image taken by the camera may be performed based on the size and position of the bounding box surrounding the peripheral vehicle in the image, or may be performed by another method. .. For example, it may be performed using a machine-learned model so as to output the distance to the vehicle and the relative direction included in the input image.
  • the camera 40 (FIG. 1) may be replaced with a stereo camera or radar, or these sensors may be combined.
  • the relative position information acquisition unit 21a can acquire a linear distance to a surrounding vehicle based on the transmitted wave transmitted from the radar and the reflected wave reflected from the object. By providing a plurality of receiving antennas and detecting the phase difference between the antennas, the relative position information acquisition unit 21a can acquire the relative orientation of the surrounding vehicle. Further, for example, by adopting 3D-LiDAR, the relative position information acquisition unit 21a can acquire the linear distance and the relative direction with the surrounding vehicle. Further, for example, a configuration may be adopted in which the linear distance to the surrounding vehicle is acquired from the two images taken by the stereo camera by the principle of triangulation. Of course, the relative orientation of the surrounding vehicles may be acquired from the image taken by the stereo camera.
  • the map information acquisition unit should be able to acquire map information around the current position of the own vehicle.
  • the road information (link data, shape interpolation point data, etc.) of the area corresponding to the detection range of the surrounding vehicle in the relative position information acquisition unit can be acquired.
  • the region corresponding to the detection range may be defined by, for example, the distance from the own vehicle, or may be determined by the distance and the angle.
  • facility data such as the position and shape of the facility existing in the detection range, and based on the feature data, the feature (for example, a building, a signboard, etc.) included in the image taken by the camera.
  • a configuration may be adopted in which the position of the vehicle is estimated from the relationship between the feature and the vehicle by specifying the parking lot, the pond, the river, etc.).
  • the estimated position of the surrounding vehicle may be a section in which the vehicle can travel, and may be a section in which a node is set in the map information. For example, when a node is set in the parking lot, it may be possible to detect the position of surrounding vehicles in the parking lot.
  • the peripheral vehicle position estimation unit should be able to acquire the peripheral road that overlaps with the straight line extending from the own vehicle in the relative direction based on the map information, and estimate that the peripheral vehicle exists on the peripheral road. For example, if there is only one peripheral road that overlaps with a straight line extending from the own vehicle in the relative direction within the detection range of the peripheral vehicle in the relative position information acquisition unit, it can be estimated that the peripheral vehicle exists on the peripheral road. .. Therefore, it suffices if the relative position information acquisition unit can acquire at least the relative direction. Specifically, for example, as in the example of FIG.
  • the peripheral vehicle exists on the peripheral road, and the position where the peripheral vehicle exists may or may not be on an extension line extending from the own vehicle in the relative direction. For example, it may be presumed that the peripheral vehicle exists at the intersection of the vertical line drawn on the peripheral road and the peripheral road from the relative position of the peripheral vehicle with respect to the own vehicle.
  • the peripheral vehicle position estimation unit does not have to adopt any of the above conditions 1, 2 and 3 (for example, conditions 1 and 2 are adopted, conditions 1 and 3 are adopted, or conditions 2 and 2 are adopted. Adopt 3 etc.).
  • the peripheral vehicle position estimation unit may adopt conditions other than the above-mentioned conditions 1, 2, and 3.
  • the peripheral road may be a road (condition 2) that intersects with the own vehicle traveling road on which the own vehicle travels, or may be a road that does not intersect.
  • the road may be parallel to the own vehicle driving road, or may be a road branching from the own vehicle traveling road.
  • the peripheral vehicle may be a vehicle running in parallel with the own vehicle, a vehicle preceding the own vehicle, a vehicle facing the own vehicle, or approaching the course of the own vehicle. It may be a vehicle that does, or it may be a vehicle that moves away from the course of its own vehicle.
  • the peripheral vehicle position estimation unit adopts a configuration (condition 3) in which it is estimated that a peripheral vehicle exists on the peripheral road if the angle between the traveling direction of the peripheral vehicle and the extending direction of the peripheral road is within the reference value. Therefore, when the angle formed by the traveling direction of the peripheral vehicle and the extending direction of the first peripheral road exceeds the reference value, it may be estimated that there is no peripheral vehicle on the first peripheral road. If there is a second peripheral road around the first peripheral road whose angle with the traveling direction of the peripheral vehicle is within the reference value, the road estimated to have the peripheral vehicle is the road from the first peripheral road to the second peripheral road. You may change to a road.
  • the risk determination unit should be able to determine the collision risk of surrounding vehicles with its own vehicle. For example, it may be possible to determine whether or not the distance between the intersection (N1) and the predicted point is less than the third distance and whether or not the distance is greater than or equal to the third distance and less than the fourth distance.
  • the guidance mode may be different depending on whether the former is determined to be affirmative or the latter is determined to be affirmative.
  • Various methods can be adopted as the guidance mode. For example, the driver may be guided by the display on the head-up display.
  • the determination result of the risk determination unit may be provided to the vehicle control ECU that controls the operation of the vehicle. As a result, the vehicle control ECU may control the operation of the vehicle so as to avoid a collision.
  • the collision risk may be determined for each of these patterns, and guidance and vehicle control may be performed according to the determination result.
  • the peripheral road overlapping the straight line extending from the own vehicle in the relative direction is acquired based on the map information, it is estimated that the peripheral vehicle exists on the peripheral road, and the own vehicle is determined based on the estimation result.
  • the method of determining the collision risk of surrounding vehicles can also be applied as a method or a program to be executed by a computer.
  • the above systems, programs, and methods may be realized as a single device or may be realized by using parts shared with each part provided in the vehicle, including various aspects. It is a program.
  • some of them are software and some of them are hardware, which can be changed as appropriate.
  • the invention is also established as a recording medium for a program that controls a system.
  • the recording medium of the program may be a magnetic recording medium or a semiconductor memory, and any recording medium to be developed in the future can be considered in exactly the same way.

Landscapes

  • Engineering & Computer Science (AREA)
  • Remote Sensing (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Automation & Control Theory (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Environmental Sciences (AREA)
  • Environmental & Geological Engineering (AREA)
  • Ecology (AREA)
  • Biodiversity & Conservation Biology (AREA)
  • Atmospheric Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Human Computer Interaction (AREA)
  • Multimedia (AREA)
  • Navigation (AREA)
  • Traffic Control Systems (AREA)
PCT/JP2020/037491 2020-01-17 2020-10-02 周辺車両位置推定システム、周辺車両位置推定プログラム Ceased WO2021145032A1 (ja)

Priority Applications (4)

Application Number Priority Date Filing Date Title
CN202080080219.0A CN114762020A (zh) 2020-01-17 2020-10-02 周边车辆位置推定系统、周边车辆位置推定程序
US17/771,521 US20220404166A1 (en) 2020-01-17 2020-10-02 Nearby vehicle position estimation system, and nearby vehicle position estimation program
EP20914424.5A EP4092651A1 (en) 2020-01-17 2020-10-02 Nearby vehicle position estimation system, and nearby vehicle position estimation program
JP2021570645A JPWO2021145032A1 (https=) 2020-01-17 2020-10-02

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2020-005646 2020-01-17
JP2020005646 2020-01-17

Publications (1)

Publication Number Publication Date
WO2021145032A1 true WO2021145032A1 (ja) 2021-07-22

Family

ID=76864248

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2020/037491 Ceased WO2021145032A1 (ja) 2020-01-17 2020-10-02 周辺車両位置推定システム、周辺車両位置推定プログラム

Country Status (5)

Country Link
US (1) US20220404166A1 (https=)
EP (1) EP4092651A1 (https=)
JP (1) JPWO2021145032A1 (https=)
CN (1) CN114762020A (https=)
WO (1) WO2021145032A1 (https=)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2025097571A (ja) * 2023-12-19 2025-07-01 トヨタ自動車株式会社 交差道路検出装置、交差道路検出方法及びプログラム

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH09166452A (ja) 1995-12-14 1997-06-24 Pioneer Electron Corp 運転支援装置
JP2005173899A (ja) * 2003-12-10 2005-06-30 Nissan Motor Co Ltd 周囲状況表示装置
JP2005257314A (ja) * 2004-03-09 2005-09-22 Honda Motor Co Ltd 車両位置検出装置
JP2011034436A (ja) * 2009-08-04 2011-02-17 Nissan Motor Co Ltd 車両位置演算装置及び車両位置演算方法
JP2012212337A (ja) * 2011-03-31 2012-11-01 Daihatsu Motor Co Ltd 車車間通信装置および車車間通信システム

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4506790B2 (ja) * 2007-07-05 2010-07-21 アイシン・エィ・ダブリュ株式会社 道路情報生成装置、道路情報生成方法および道路情報生成プログラム
JP5574789B2 (ja) * 2010-04-08 2014-08-20 株式会社東芝 車両周辺監視装置及び車両周辺監視方法
JP6635428B2 (ja) * 2015-05-20 2020-01-22 修一 田山 自動車周辺情報表示システム
MX364577B (es) * 2015-08-28 2019-05-02 Nissan Motor Dispositivo de estimacion de posicion de vehiculo, metodo de estimacion de posicion de vehiculo.
JP2021041758A (ja) * 2019-09-09 2021-03-18 本田技研工業株式会社 車両制御装置、車両制御方法、およびプログラム

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH09166452A (ja) 1995-12-14 1997-06-24 Pioneer Electron Corp 運転支援装置
JP2005173899A (ja) * 2003-12-10 2005-06-30 Nissan Motor Co Ltd 周囲状況表示装置
JP2005257314A (ja) * 2004-03-09 2005-09-22 Honda Motor Co Ltd 車両位置検出装置
JP2011034436A (ja) * 2009-08-04 2011-02-17 Nissan Motor Co Ltd 車両位置演算装置及び車両位置演算方法
JP2012212337A (ja) * 2011-03-31 2012-11-01 Daihatsu Motor Co Ltd 車車間通信装置および車車間通信システム

Also Published As

Publication number Publication date
CN114762020A (zh) 2022-07-15
EP4092651A1 (en) 2022-11-23
JPWO2021145032A1 (https=) 2021-07-22
US20220404166A1 (en) 2022-12-22

Similar Documents

Publication Publication Date Title
CN111066071B (zh) 驾驶辅助车辆的位置误差校正方法及位置误差校正装置
US11313976B2 (en) Host vehicle position estimation device
CN107646114B (zh) 用于估计车道的方法
US11300415B2 (en) Host vehicle position estimation device
US8363104B2 (en) Lane determining device and navigation system
CN111936364B (zh) 停车辅助装置
JP2021197009A (ja) リスク判定システム、リスク判定プログラム
US11042759B2 (en) Roadside object recognition apparatus
JP7573176B2 (ja) 先行車両判定システム
JP7449497B2 (ja) 障害物情報取得システム
JP2011012965A (ja) 車線判定装置及びナビゲーションシステム
JP6699728B2 (ja) 車間距離推定方法及び車間距離推定装置
JP2021114059A (ja) リスク判定システム、リスク判定プログラム
KR101588787B1 (ko) 전방차량의 횡방향 거리 결정 방법 및 이를 이용한 헤드 업 디스플레이 장치
JP2020129331A (ja) 逆走判定システム、逆走判定方法、及び逆走判定プログラム
JP6690510B2 (ja) 物体認識装置
JP5549468B2 (ja) 地物位置取得装置、方法およびプログラム
WO2021145032A1 (ja) 周辺車両位置推定システム、周辺車両位置推定プログラム
JP7325296B2 (ja) 物体認識方法及び物体認識システム
US10249056B2 (en) Vehicle position estimation system
US12277732B2 (en) Video camera calibration refinement for autonomous driving vehicles
CN114136328B (zh) 一种传感器信息融合方法及装置
JP2022007526A (ja) 周辺車両判別システム、周辺車両判別プログラム
US20240401964A1 (en) Path planning apparatus and path plan correction method of path planning apparatus
JP2021196614A (ja) 周辺車両検出システムおよび周辺車両検出プログラム

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20914424

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2021570645

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2020914424

Country of ref document: EP

Effective date: 20220817