JP6564618B2 - Road shape detection system, road shape detection method, and computer program - Google Patents

Description

  The present invention relates to a road shape detection system, a road shape detection method, and a computer program that specify a road shape based on travel information of a vehicle.

  In recent years, automatic driving that assists the user in driving the vehicle by executing part or all of the user's driving operation on the vehicle side, in addition to manual driving that travels based on the user's driving operation, as the driving mode of the vehicle. A new support system has been proposed. In the automatic driving support system, for example, vehicle control such as steering, drive source, and brake is performed so that the vehicle continuously travels in the vicinity of the center of the same lane while maintaining a predetermined speed and a certain distance from the preceding vehicle. Done automatically. Here, driving with the automatic driving support system has the advantage of reducing the burden on the user's driving, but it is important to obtain more detailed information on the road shape in order to properly run with automatic driving support . In particular, in order to appropriately travel in a lane in a section having a complicated shape such as a curve shape, it is necessary to specify in more detail what shape the lane in which the vehicle travels has.

  Thus, for example, Japanese Patent No. 4364338 discloses a technique for specifying a curve shape on which a vehicle has traveled using travel information such as vehicle speed, angular velocity, centrifugal force, vehicle body tilt angle, and steering angle in addition to the vehicle travel locus. Is described.

Japanese Patent No. 4364338 (pages 15-17)

  However, in order to accurately specify the shape of the curve from the traveling locus of the vehicle as in Patent Document 1, it is assumed that the vehicle is traveling in the center of the lane. However, the vehicle does not always travel in the center of the lane, and may travel near the inside of the lane or travel near the outside. Some drivers travel out-in-out or travel in-out. And even if a curve shape is specified based on such a travel locus, there is a problem that an accurate curve shape cannot be specified.

  Moreover, although the shape of the curve can be specified with the technique of the above-mentioned Patent Document 1, it is possible to specify what shape (for example, the position of the boundary of the lane) the lane on which the vehicle travels has. I can't. Here, the map information also stores the width information indicating the width of the road, but the width of the lane often changes locally, and the width information is simply combined with the specified curve shape. Even so, the shape of the lane in which the vehicle is traveling cannot be accurately specified.

  The present invention has been made in order to solve the above-described problems of the prior art, and travel information of a vehicle that travels in a state in which automatic driving assistance is performed, and a vehicle that travels in a state in which automatic driving support is not performed. It is an object of the present invention to provide a road shape detection system, a road shape detection method, and a computer program that can accurately specify the shape of a lane by combining with travel information.

In order to achieve the above object, a road shape detection system according to the present invention includes an automatic driving travel information acquisition unit that acquires traveling information of a vehicle that travels in a state in which automatic driving support related to lane maintaining traveling is performed, and lane maintaining traveling. The vehicle travels on the basis of manual driving travel information acquisition means for acquiring travel information of a vehicle traveling in a state where the automatic driving support is not implemented, and the travel information acquired by the automatic driving travel information acquisition means. The vehicle is based on the center line specifying means for specifying the center line of the lane, the travel information acquired by the manual driving travel information acquiring means, and the center line of the lane specified by the center line specifying means. boundary specifying means for specifying the boundaries of traveling lane, was closed, the boundary specifying unit, based on the distribution state of the travel information relative to the center line of the lane Serial vehicle to identify the boundaries of the traveling lane.
Note that the “travel information” includes information directly calculated using the vehicle speed, yaw rate, travel trajectory, and the like, as well as information calculated using the information.

The road shape detection method according to the present invention is a method for specifying a road shape based on vehicle travel information. Specifically, the step of acquiring automatic driving travel information acquisition means for acquiring traveling information of a vehicle traveling in a state in which automatic driving support related to lane maintenance driving is performed, and the manual driving travel information acquisition means of lane maintenance traveling The vehicle is traveling based on the travel information acquired by the automatic driving travel information acquisition means by the step of acquiring the travel information of the vehicle traveling in a state where the automatic driving support is not implemented. The step of specifying the center line of the lane that has traveled, and the boundary specifying means based on the travel information acquired by the manual driving travel information acquisition means and the center line of the lane specified by the center line specifying means, have a, and identifying the boundaries of the lane in which the vehicle has traveled, the boundary specifying unit based on the distribution state of the travel information relative to the center line of the lane Identifying the boundaries of the lane in which the vehicle has traveled.

A computer program according to the present invention is a program for specifying a road shape based on vehicle travel information. Specifically, automatic driving travel information acquisition means for acquiring traveling information of a vehicle traveling on a computer in a state where automatic driving support related to lane maintenance driving is performed, and automatic driving support related to lane maintenance driving are performed. The center line of the lane in which the vehicle has traveled is specified based on the travel information acquired by the manual operation travel information acquisition means that acquires travel information of the vehicle that travels in a state where the vehicle has not traveled. Based on the center line specifying means, the travel information acquired by the manual driving travel information acquiring means, and the center line of the lane specified by the center line specifying means, the boundary of the lane in which the vehicle has traveled is specified. and boundary identification means, a computer program for causing the functions to the boundary specifying unit, the distribution shape of the travel information relative to the center line of the lane The vehicle to identify the boundaries of traveling lane on the basis of.

  According to the road shape detection system, the road shape detection method, and the computer program according to the present invention having the above-described configuration, traveling information of a vehicle that travels in a state in which automatic driving support is performed, and a state in which automatic driving support is not performed By combining with the travel information of the vehicle traveling at, it is possible to accurately specify the center line of the lane and the boundary of the lane. Then, the shape of the lane, that is, the range in which the vehicle can travel can be accurately specified from the specified center line and boundary shape. In particular, it is possible to accurately specify the lane shape even in a section where the lane width is locally changed. As a result, automatic driving support can be appropriately performed even in a section having a complicated shape such as a curve shape. In addition, even in a section where the lane marking has disappeared, it is possible to continue the automatic driving support without stopping by using the information regarding the boundary between the center line of the specified lane and the lane.

It is a schematic structure figure showing a road shape detection system concerning this embodiment. It is the block diagram which showed the structure of the road shape detection system which concerns on this embodiment. It is the figure which showed an example of the probe information memorize | stored in probe information DB. It is the figure which showed an example of the probe statistical information memorize | stored in probe statistical information DB. It is the block diagram which showed the navigation apparatus which concerns on this embodiment. It is a flowchart of the travel information acquisition process program which concerns on this embodiment. It is the figure which showed the point from which driving information is acquired in a curve area. It is a flowchart of the road shape detection processing program which concerns on this embodiment. It is a flowchart of the road shape detection processing program which concerns on this embodiment. It is a figure explaining the identification method of the centerline of a lane. It is a figure explaining the calculation method of the distance from the detection point of a present position to the center line of a lane. It is the figure which showed the frequency distribution which set the distance with respect to the centerline along the road width direction of a road as a horizontal axis and frequency as a vertical axis | shaft. It is the figure which showed the example of the frequency distribution without a distribution bias. It is the figure which showed the example of frequency distribution with the distribution bias. It is a figure explaining the calculation method of lane width in case there is no distribution bias. It is a figure explaining the calculation method of the boundary point of a lane. It is a figure explaining the calculation method of the lane width in case distribution is biased to the right (positive) side. It is a figure explaining the calculation method of lane width in case distribution is biased to the left (negative) side. It is a figure explaining the identification method of the boundary of a lane.

  DETAILED DESCRIPTION Hereinafter, a road shape detection system according to the present invention will be described in detail with reference to the drawings based on an embodiment that is embodied. First, a schematic configuration of the road shape detection system 1 according to the present embodiment will be described with reference to FIGS. 1 and 2. FIG. 1 is a schematic configuration diagram showing a road shape detection system 1 according to the present embodiment. FIG. 2 is a block diagram showing the configuration of the road shape detection system 1 according to this embodiment.

  As shown in FIG. 1, the road shape detection system 1 according to the present embodiment collects probe information from each vehicle 3 equipped with a navigation device 2 and each vehicle 3, such as traffic information based on the collected probe information. The probe server 5 is basically composed of a probe server 5 provided in the probe center 4 that performs creation and distribution. In addition, it is good also as a structure which uses communication terminals, such as a smart phone and a tablet-type terminal, instead of the navigation apparatus 2. FIG.

  The vehicle 3 is a vehicle that travels on roads throughout the country, and constitutes a probe car system together with a probe server 5 described later as a probe car. Here, the probe car system is a system that collects information using a vehicle as a sensor. Specifically, the vehicle 3 includes the speed data and the operation status of each system such as the steering operation and the shift position together with the GPS position information. Hereinafter, it refers to a system that periodically transmits to the probe server 5 via a communication module) and reuses the collected data as various information on the server side.

  In addition, the probe server 5 collects and accumulates probe information including the current time and travel information transmitted from each vehicle 3 traveling all over the country, and information that identifies the shape of the road from the accumulated probe information. This is an information distribution server that generates distribution information (probe statistical information) such as (specifically, information that specifies a center line or a boundary of a lane) and distributes the generated distribution information to the vehicle 3.

  Further, as a travel mode of the vehicle 3 in the road shape detection system 1 of the present embodiment, in addition to the manual driving travel that travels based on the user's driving operation, the route in which the vehicle is set in advance regardless of the user's driving operation. It is configured to be able to run with automatic driving assistance that automatically runs along the road. In the driving by the automatic driving support, for example, the current position of the vehicle 3, the lane in which the vehicle 3 travels, and the positions of other vehicles in the vicinity are detected at any time, and the vehicle travels along a preset route or road. Vehicle control such as steering, drive source, and brake is automatically performed. However, in the driving with the automatic driving support of the present embodiment, the lane change and the right / left turn are not performed, and the vehicle 3 basically travels in the same lane unless the user performs the vehicle operation for the lane change or the right / left turn. .

In the present embodiment, the following three types of automatic driving assistance are performed.
(1) “Constant speed travel”... Travels in the same lane at a predetermined set speed (for example, 90% of the speed limit of the road on which the vehicle travels, or speed according to the curvature radius of the curve when traveling on a curve)
(2) “Follow-up traveling”: The distance between the vehicle and the vehicle ahead is a fixed distance with the set speed (for example, 90% of the speed limit of the road on which the vehicle is traveling or the speed according to the curvature radius of the curve when traveling on a curve) as the upper limit. Drive in the same lane with the distance maintained (for example, 10 m).
(3) “Land maintenance”: The vehicle travels near the center of the lane without departing from the lane (for example, lane keeping assist).

  In addition, the control related to the automatic driving support described in (1) to (3) above may be performed for all road sections, but a gate (manned, unmanned, free of charge is not required) at the boundary with other roads to be connected. It is good also as a structure performed only during driving | running | working on the highway provided. When the vehicle 3 travels in a section where automatic driving can be performed (hereinafter referred to as automatic driving section), automatic driving support is not always performed, but the user selects automatic driving support. In addition, it is performed only in a situation where it is determined that automatic luck support can be implemented. As a situation where the automatic driving support cannot be performed, there is a bad weather situation or the like when traveling in a section where the lane markings have disappeared or become thin enough to be unrecognizable by the camera.

  A navigation device 2 is installed in the vehicle 3. The navigation device 2 displays a map around the vehicle position based on the stored map data, displays the current position of the vehicle on the map image, and uses distribution information and map information distributed from the probe server 5. This is an in-vehicle device that transmits an instruction signal related to automatic driving support to the control device of the vehicle 3. And the control apparatus of the vehicle 3 implements the automatic driving assistance after a driving | running | working start according to the received instruction signal. Note that the content of the instruction signal is information for instructing control content (for example, any one of the above (1) to (3)) of automatic driving assistance performed on the vehicle, control start, stop, change or the like. Moreover, it is good also as a structure which sets the control content of automatic driving assistance not by the navigation apparatus 2 but by the control apparatus of the vehicle 3. In that case, the control device of the vehicle 3 is configured to acquire information necessary for setting automatic driving assistance such as distribution information and surrounding map information from the navigation device 2. The details of the navigation device 2 will be described later.

  Next, the configuration of the probe server 5 constituting the road shape detection system 1 will be described in more detail with reference to FIG.

  As shown in FIG. 2, the probe server 5 basically includes a server control ECU 11, a probe information DB 12 as information recording means connected to the server control ECU 11, a probe statistical information DB 13, and a center communication device 14. ing.

  The server control ECU 11 (electronic control unit) is an electronic control unit that performs overall control of the probe server 5, and is used as a working memory when the CPU 21 performs various types of arithmetic processing as well as the arithmetic unit and the control unit. In addition to the RAM 22 and the control program, an internal storage device such as a ROM 23 in which a road shape detection processing program (see FIGS. 8 and 9) described later is recorded, a flash memory 24 that stores a program read from the ROM 23, and the like. I have. The server control ECU 11 constitutes various means as processing algorithms together with an ECU of the navigation device 2 described later. For example, the automatic driving travel information acquisition unit acquires travel information of a vehicle that travels in a state where the automatic driving support related to the lane keeping traveling is performed. The manual driving travel information acquisition means acquires travel information of a vehicle that travels in a state in which automatic driving support related to lane keeping traveling is not performed. The center line specifying means specifies the center line of the lane in which the vehicle has traveled based on the travel information acquired by the automatic driving travel information acquiring means. The boundary specifying means specifies the boundary of the lane in which the vehicle has traveled based on the travel information acquired by the manual driving travel information acquiring means and the center line of the lane specified by the center line specifying means.

  The probe information DB 12 is a storage unit that cumulatively stores probe information collected from each vehicle 3 traveling throughout the country. In the present embodiment, the probe information collected from the vehicle 3 includes (a) the date and time, (b) the link on which the vehicle 3 travels, (c), the traveling direction of the vehicle 3, and (d) the vehicle 3 It includes the history of detection points at which the current position is detected, and whether or not (e) automatic driving support related to “lane keeping” is performed. However, the probe information does not necessarily include all the information related to the above (a) to (e). For example, only the information related to (d) and (e) may be included. Further, in the road shape detection system 1 according to the present embodiment, as described later, the road shape of each road in the whole country, particularly the road shape of the curve section, is detected, so that only the probe information that has traveled the curve section is collected. May be.

  Hereinafter, probe information stored in the probe information DB 12 will be described in more detail with reference to FIG. FIG. 3 is a diagram showing an example of probe information stored in the probe information DB 12.

  As shown in FIG. 3, the probe information includes a vehicle ID for identifying the transmission source vehicle, information on the above (a) to (e), and the like. For example, the probe information shown in FIG. 3 is an automatic driving support in which the vehicle 3 with ID “A” is in the upward direction of the link with ID “100001” at 10:00 on April 10, 2015. It is memorized that the history of the detected points that detected the current position at that time was (x1, y1), (x2, y2), ... (x10, y10). ing. The presence or absence of automatic driving support for “lane keeping” is specified by the added flag information. If the automatic driving travel flag is ON, the detection point when the automatic driving support for “lane keeping” is executed Indicates that this is a history. Similarly, other probe information is also stored.

  And the probe center 4 calculates the road shape of each road of the whole country by statistics of the probe information memorize | stored in probe information DB12. However, in this embodiment, the road shape of the curve section is calculated among the roads in the whole country. Specifically, the probe information stored in the probe information DB 12 is extracted by extracting the probe information associated with the same condition (for example, the links constituting the same curve and the same traveling direction). The center line of the lane and the boundary of the lane in the target curve section are calculated by performing statistical processing on the probe information. And the information regarding the calculated center line of a curve section and the boundary of a lane is memorize | stored in probe statistical information DB13. The details of the calculation method of the lane center line and the lane boundary will be described later.

  Next, probe statistical information (distribution information) created by the probe center 4 and stored in the probe statistical information DB 13 will be described in detail with reference to FIG. FIG. 4 is a diagram showing an example of probe statistical information stored in the probe statistical information DB 13.

  As shown in FIG. 4, the probe statistical information is composed of information specifying the center line of the lane and the boundary of the lane calculated for each link corresponding to the curve section and for each traveling direction among the links in the whole country. . The center line and the boundary may be specified by a mathematical expression indicating a straight line or a curve, or may be specified by point sequence data constituting the straight line or the curve. Further, the right and left boundaries of the lane boundary are specified with respect to the traveling direction. Further, when there are a plurality of lanes in one traveling direction, information for specifying the center line of the lane and the boundary of the lane is stored for each lane.

  Then, the probe center 4 distributes the probe statistical information stored in the probe statistical information DB 13 to the navigation device 2 in response to a request from the navigation device 2. On the other hand, the navigation apparatus 2 to which the probe statistical information is distributed executes various processes related to the automatic driving support described above using the distributed probe statistical information.

  The center communication device 14 is a communication device for communicating with the vehicle 3 and the VICS (registered trademark) center via the network 15. In the present embodiment, probe information and distribution information are transmitted to and received from each vehicle 3 via the center communication device 14.

  Next, a schematic configuration of the navigation device 2 mounted on the vehicle 3 will be described with reference to FIG. FIG. 5 is a block diagram showing the navigation device 2 according to the present embodiment.

  As shown in FIG. 5, the navigation device 2 according to the present embodiment includes a current position detection unit 31 that detects a current position of a vehicle on which the navigation device 2 is mounted, a data recording unit 32 that records various data, Based on the input information, the navigation ECU 33 that performs various arithmetic processes, the operation unit 34 that receives operations from the user, and a guidance route (vehicles) set on the map around the vehicle and the navigation device 2 for the user Liquid crystal display 35 for displaying information related to the scheduled travel route), a speaker 36 for outputting voice guidance for route guidance, a DVD drive 37 for reading DVD as a storage medium, the probe server 5 and VICS (registered trademark: Vehicle). Information and Communication System) A communication module that communicates with an information center such as a center. 38, and a. The navigation device 2 is connected to an outside camera 39 and various sensors 40 installed on the vehicle 3 via an in-vehicle network such as CAN. Furthermore, the vehicle control ECU 41 that performs various controls on the vehicle 3 on which the navigation device 2 is mounted is also connected so as to be capable of bidirectional communication. Various operation buttons 42 mounted on the vehicle such as an automatic driving start button are also connected.

Below, each component which comprises the navigation apparatus 2 is demonstrated in order.
The current position detection unit 31 includes a GPS 43, a vehicle speed sensor 44, a steering sensor 45, a gyro sensor 46, and the like, and can detect the current vehicle position, direction, vehicle traveling speed, current time, and the like. . Here, in particular, the vehicle speed sensor 44 is a sensor for detecting a moving distance and a vehicle speed of the vehicle, generates a pulse according to the rotation of the driving wheel of the vehicle, and outputs a pulse signal to the navigation ECU 33. And navigation ECU33 calculates the rotational speed and moving distance of a driving wheel by counting the pulse which generate | occur | produces. In addition, it is not necessary for the navigation device 2 to include all of the four types of sensors, and the navigation device 2 may include only one or more of these types of sensors.

  The data recording unit 32 reads an external storage device and a hard disk (not shown) as a recording medium, a map information DB 51, a travel history DB 52, a distribution information DB 53, a predetermined program, and the like recorded on the hard disk and stores them in the hard disk. And a recording head (not shown) as a driver for writing predetermined data. The data recording unit 32 may be configured by an optical disk such as a flash memory, a memory card, a CD, or a DVD instead of the hard disk. Further, the map information DB 51, the travel history DB 52, and the distribution information DB 53 may be stored in an external server and acquired by the navigation device 2 through communication.

  Here, the map information DB 51 is, for example, link data relating to roads (links), node data relating to node points, search data used for processing relating to route search or change, facility data relating to facilities, and a map for displaying a map. The storage means stores display data, intersection data regarding each intersection, search data for searching for a point, and the like. In addition, for each curve section on the road in particular, information for specifying the start point at which the curve section starts, the end point at which the curve section ends, and the curvature radius of the curve is also stored.

  The travel history DB 52 is a storage unit that accumulates and stores travel information of the vehicle 3. In the present embodiment, a history of detection points of the current position of the vehicle 3 (that is, a traveling locus) is stored particularly with time. Note that the current position of the vehicle 3 may be detected using the GPS 43 or the vehicle speed sensor 44, but it is desirable to specify it in detail using a high-precision location technique. In the travel history DB 52, detection points detected in a state where the automatic driving support related to “lane keeping” is implemented in the vehicle, or detected in a state where the automatic driving assistance related to “lane keeping” is not implemented. Information for identifying the detected point is also stored. The travel information stored in the travel history DB 52 is periodically transmitted to the probe server 5 as probe information.

  The distribution information DB 53 is a storage unit in which distribution information (probe statistical information) distributed from the probe server 5 is stored.

  On the other hand, the navigation ECU (Electronic Control Unit) 33 is an electronic control unit that controls the entire navigation device 2. The CPU 61 as an arithmetic device and a control device, and a working memory when the CPU 61 performs various arithmetic processes. As well as a RAM 62 for storing route data when a route is searched, a control program, and a ROM 63 and a ROM 63 in which a travel information acquisition processing program (see FIG. 6) described later is recorded. An internal storage device such as a flash memory 64 for storing the read program is provided.

  The operation unit 34 is operated when inputting a departure point as a travel start point and a destination point as a travel end point, and includes a plurality of operation switches (not shown) such as various keys and buttons. Then, the navigation ECU 33 performs control to execute various corresponding operations based on switch signals output by pressing the switches. The operation unit 34 can also be configured by a touch panel provided on the front surface of the liquid crystal display 35. Moreover, it can also be comprised with a microphone and a speech recognition apparatus.

  In addition, the liquid crystal display 35 includes a map image including a road, traffic information, operation guidance, operation menu, key guidance, guidance information along a guidance route (planned travel route), news, weather forecast, time, mail, television. Programs etc. are displayed. In the present embodiment, when automatic driving support is performed or when automatic driving support is finished, guidance to that effect is also displayed. Instead of the liquid crystal display 35, HUD or HMD may be used.

  The speaker 36 outputs voice guidance for guiding traveling along a guidance route (planned traveling route) or traffic information guidance based on an instruction from the navigation ECU 33. In the present embodiment, when automatic driving support is performed or when automatic driving support is ended, voice guidance to that effect is also output.

  The DVD drive 37 is a drive that can read data recorded on a recording medium such as a DVD or a CD. Based on the read data, music and video are reproduced, the map information DB 51 is updated, and the like. A card slot for reading / writing a memory card may be provided in place of the DVD drive 37.

  The communication module 38 is a communication device for receiving traffic information, weather information, and the like transmitted from a traffic information center, for example, a VICS center or other external center, and corresponds to, for example, a mobile phone or DCM. In addition, a vehicle-to-vehicle communication device that performs communication between vehicles and a road-to-vehicle communication device that performs communication with roadside devices are also included. It is also used for transmitting / receiving probe information and distribution information to / from the probe server 5.

  The vehicle exterior camera 39 is constituted by a camera using a solid-state image sensor such as a CCD, for example, and is installed above the front bumper of the vehicle or behind the room mirror and installed with the optical axis direction forward in the traveling direction of the vehicle. Is done. The outside camera 39 captures an image in front of the traveling direction of the vehicle when the vehicle travels in the automatic driving section. In addition, the vehicle control ECU 41 performs image processing on the captured image to detect a lane line drawn on the road on which the vehicle travels, other vehicles in the vicinity, and the like, and automatically detects the vehicle based on the detection result. Implement driving assistance. In addition, you may comprise the camera 39 outside a vehicle so that it may arrange | position behind or a side other than the vehicle front. As a means for detecting other vehicles, various sensors 40 such as millimeter wave radar, vehicle-to-vehicle communication, and road-to-vehicle communication may be used instead of the camera. Further, as the various sensors 40, an illuminance sensor or a rain sensor may be installed.

  The vehicle control ECU 41 is an electronic control unit that controls a vehicle on which the navigation device 2 is mounted. Further, the vehicle control ECU 41 is connected to each drive unit of the vehicle such as a steering, a brake, and an accelerator. In this embodiment, the vehicle is controlled by controlling each drive unit after the automatic driving support is started in the vehicle. Carry out automatic driving support. Further, when an override such as a steering operation or a brake operation is performed by the user during automatic driving support, the vehicle control ECU 41 detects that the override has been performed.

  In particular, when performing automatic driving support related to “lane keeping” during traveling in a curve section, the vehicle 3 appropriately travels in the lane using the distribution information (FIG. 4) stored in the distribution information DB 53. So as to support autonomous driving. Specifically, the range surrounded by the lane boundary specified by the distribution information is specified as the travelable range in which the vehicle 3 can travel. Basically, automatic driving support is performed so that the vehicle 3 travels along the center of the lane within the travelable range. The center of the lane may be specified by detecting the lane marking, or may be specified by the center line of the lane specified by the distribution information. However, under certain circumstances (for example, when there is an obstacle or the like that hinders traveling on one side of the lane), the vehicle may travel outside the center of the lane. In this embodiment, the boundary line and the center line of the lane can be specified from the distribution information without detecting the lane line of the lane by the camera 39 outside the vehicle. Even in the unrecognizable section, it is possible to continue to support automatic driving. In addition, since the boundary and center line of the lane can be specified even outside the imaging range of the camera 39 outside the vehicle (for example, a section away from the current position of the vehicle), a control plan for automatic driving assistance for the curve section can be made before entering the curve section. It is possible to stand.

  Next, a travel information acquisition processing program executed by the navigation ECU 33 in the navigation device 2 configuring the road shape detection system 1 according to the present embodiment having the above configuration will be described with reference to FIG. FIG. 6 is a flowchart of the travel information acquisition processing program according to this embodiment. Here, the travel information acquisition processing program is a program that is executed after the ACC power supply (accessory power supply) of the vehicle is turned on, and acquires the travel information of the vehicle during the curve travel. Note that the program shown in the flowchart of FIG. 6 below is stored in the RAM 62 and the ROM 63 provided in the navigation device 2 and is executed by the CPU 61.

  First, in step (hereinafter abbreviated as S) 1 in the travel information acquisition processing program, the CPU 61 determines whether or not the vehicle has entered a curve. Specifically, when the vehicle passes the starting point of the curve section included in the map information, it is determined that the vehicle has entered the curve. Further, the radius of curvature of the travel locus drawn by the vehicle may be calculated from the vehicle speed and yaw rate of the vehicle, and it may be determined that the vehicle has entered the curve when the calculated radius of curvature is smaller than a threshold value (for example, 500 m). .

  When it is determined that the vehicle has entered the curve (S1: YES), the process proceeds to S2. On the other hand, when it is determined that the vehicle has not entered the curve (S1: NO), the travel information acquisition processing program is terminated without acquiring the travel information.

  Next, in S <b> 2, the CPU 61 acquires the control state of automatic driving support by communicating with the vehicle control ECU 41 via the CAN, and the vehicle performs automatic driving support particularly related to “lane keeping” in the curve section. It is determined whether or not.

  Here, as described above, the automatic driving support is performed only in a situation where the user selects to perform the automatic driving support and can perform the automatic driving support. Note that whether or not the user has selected to support automatic driving is determined by whether or not the automatic driving start button has been pressed, for example. Here, the automatic driving start button is arranged on an instrument panel or the like, and is pressed when the user desires to perform automatic driving support or when the user desires to end the automatic driving support.

  When it is determined that the vehicle is performing automatic driving support related to “lane keeping” in the curve section (S2: YES), the automatic driving travel flag is set to ON (S3). The automatic driving traveling flag is a flag for specifying a traveling mode when the vehicle travels in a curve section, and is stored in the RAM 62 or the like. If the vehicle is performing automatic driving support related to “lane keeping” in the curve section, it is set to ON, and if the vehicle is not performing automatic driving support related to “lane keeping” (for example, by manual driving) When traveling), it is set to OFF.

  On the other hand, when it is determined that the vehicle does not perform the automatic driving support related to “lane keeping” in the curve section (S2: NO), the automatic driving traveling flag is set to OFF (S4). Thereafter, the process proceeds to S5.

  In S <b> 5, the CPU 61 acquires the current position of the vehicle detected by the current position detection unit 31. Note that it is desirable to specify the current position of the vehicle in detail using a high-precision location technology. Here, the high-accuracy location technology detects white lines and road surface paint information captured from a camera installed in a vehicle by image recognition, and further compares the white lines and road surface paint information with a previously stored map information DB. This is a technology that makes it possible to detect a traveling lane and a highly accurate vehicle position. The details of the high-accuracy location technology are already known and will be omitted. In S5, the CPU 61 also performs map matching processing for moving the detected current position of the vehicle onto the map link. That is, what is acquired in S5 is a position obtained by correcting the current position of the vehicle detected by a sensor or the like so as to be positioned on the link.

  In S6, the CPU 61 acquires vehicle travel information. Specifically, the detection point of the current position of the vehicle detected by the current position detection unit 31 is acquired. Note that it is desirable to specify the current position of the vehicle in detail using the high-precision location technology as in S5. In S6, the CPU 61 does not perform the map matching process unlike S5. That is, what is acquired in S6 is information on the detection point (latitude and longitude) of the current position of the vehicle detected by a sensor or the like that has not been corrected.

  Subsequently, in S7, the CPU 61 stores the travel information of the vehicle acquired in S6 in the flash memory 64 or the like in association with the current position of the vehicle acquired in S5. For example, as shown in FIG. 7, when the vehicle 3 travels in a curve section, if travel information is acquired at each point P1 to P8 in the curve section, it is associated with each point P1 to P8. Travel information (detection point of the current position) acquired at each point is stored.

  Thereafter, in S8, the CPU 61 determines whether or not the vehicle has left the curve. Specifically, when the vehicle passes through the end point of the curve section included in the map information, it is determined that the vehicle has left the curve. Further, the radius of curvature of the travel locus drawn by the vehicle may be calculated from the vehicle speed and yaw rate of the vehicle, and it may be determined that the vehicle has left the curve when the calculated radius of curvature is greater than a threshold value (for example, 500 m). .

  If it is determined that the vehicle has left the curve (S8: YES), the process proceeds to S9. On the other hand, when it is determined that the vehicle is traveling continuously in the curve section (S8: NO), the process returns to S5. Then, the current position of the new vehicle and travel information are acquired.

  In S9, the CPU 61 assembles the automatic driving travel flag set in S3 or S4 to the series of vehicle travel information stored in S7. That is, for the saved vehicle travel information, the vehicle travel information in the state where the automatic driving support related to “lane keeping” is performed or the vehicle driving information in the state where the automatic driving support related to “lane keeping” is not performed. Information identifying whether it is traveling information is added. And the driving | running | working information which assembled | attached the automatic driving | running | working flag is preserve | saved in driving | running history DB52 along a time series. As a result, the travel history DB 52 stores, as travel information, the history of detection points of the current position of the vehicle over time along with the presence or absence of automatic driving support related to “lane keeping”.

  After that, in S10, the CPU 61 transmits the travel information stored in the travel history DB 52 to the probe server 5 periodically as probe information (for example, every 24 hours when the travel of the curve section is completed). The probe server 5 that has received the probe information from each vehicle 3 determines the road shape of the curve section (specifically, the center line of the lane and the boundary of the lane of the curve section) based on the probe information collected as described later. To detect. Note that the travel information transmitted in S10 is deleted from the travel history DB 52.

  Next, a road shape detection processing program executed by the CPU 21 in the probe server 5 constituting the road shape detection system 1 according to this embodiment having the above-described configuration will be described with reference to FIGS. 8 and 9 are flowcharts of the road shape detection processing program according to this embodiment. Here, the road shape detection processing program is executed at a predetermined time interval (for example, every 24 hours), and the probe shape collected from each vehicle 3 is statistically calculated to obtain the road shape (specifically, the curve shape of each road in the country). This is a program for detecting a lane center line and a lane boundary in a curve section. The programs shown in the flowcharts of FIGS. 8 and 9 below are stored in the RAM 22 and the ROM 23 provided in the probe server 5, and are executed by the CPU 21.

  In addition, let the process after the following S11 be a structure performed for every curve section of every road of the whole country which comprises map information, and every advancing direction.

  First, in S11, the CPU 21 collects information from each vehicle 3 and saves it in the probe information DB 12 and saves the vehicle 3 in the curve section to be processed. The obtained travel information (that is, travel information acquired in a state where the automatic driving support related to “lane keeping” is performed) is read out. When there are a plurality of corresponding traveling information, all the corresponding traveling information is read out. Note that the probe information is stored as travel information of the vehicle 3, as described above, the history of detection points of the current position of the vehicle 3 with the passage of time is stored together with the presence or absence of automatic driving support related to “lane keeping”. (Fig. 3).

  Next, in S12, the CPU 21 calculates an approximate curve of the detection point of the current position of the vehicle 3 over time based on the travel information acquired in S11. The approximate curve is calculated using a least square method, a spline curve, or the like.

  Subsequently, in S13, the CPU 21 specifies the approximate curve calculated in S12 as the lane center line of the curve section to be processed. Here, when the vehicle 3 travels in a curved section in a state where the automatic driving support related to “lane keeping” is performed, the vehicle 3 is basically controlled to travel along the vicinity of the center of the lane as described above. The Accordingly, as shown in FIG. 10, the approximate curve of the detection point at the current position coincides with the center line 70 of the lane. When there are a plurality of lanes in one traveling direction for the curve section to be processed, the center line of the lane is specified for each lane.

  Next, in S13, the CPU 21 is the traveling information of the vehicle 3 in the curve section to be processed among the probe information collected from each vehicle 3 and stored in the probe information DB 12, and the automatic driving traveling flag OFF is set. The assembled traveling information (that is, traveling information acquired in a state where the automatic driving support related to “lane keeping” is not performed) is read out. When there are a plurality of corresponding traveling information, all the corresponding traveling information is read out. Note that the probe information is stored as travel information of the vehicle 3, as described above, the history of detection points of the current position of the vehicle 3 with the passage of time is stored together with the presence or absence of automatic driving support related to “lane keeping”. (Fig. 3).

  The subsequent processes in S14 to S16 are performed for each detection point of the current position included in the travel information read out in S13. And after performing the process of S14-S16 with respect to the detection point of the present position contained in all the driving | running | working information read by said S13, it transfers to S17.

  First, in S14, the CPU 21 draws a perpendicular to the center line specified in S12 for the detection point to be processed.

  Next, in S15, the CPU 21 calculates the distance from the detection point to be processed to the center line of the lane. Specifically, as shown in FIG. 11, the length h from the detection point of the vertical line 71 drawn in S14 to the center line 70 is the distance from the detection point to the center line 70 of the lane. The calculated distance is a positive value when the detection point is on the right side of the traveling direction of the center line with respect to the traveling direction, and a negative value when the detection point is on the left side of the traveling direction. For example, the detection point at a position 1 m away from the center line to the right in the traveling direction has a calculated distance “+1 m”, and the detection point at a position 0.5 m away from the center line to the left in the traveling direction is the calculated distance. Becomes “−0.5 m”. The left and right signs may be reversed. The calculated distance [m] is rounded to the first decimal place to the nearest 0.1 m.

  Thereafter, in S16, the CPU 21 stores the distance calculated in S15 in association with the position where the detection point to be processed is acquired. For example, as shown in FIG. 7, when the detection points of the current position of the vehicle 3 are acquired at eight locations P1 to P8 along the lane, the points are associated with the respective positions P1 to P8 along the lane. The distance calculated in S15 based on the detection point acquired at that point is stored. Therefore, a plurality of distances are stored in association with each other at positions where a plurality of detection points are acquired.

  The subsequent processing of S17 to S27 is performed for each position where the detection point of the current position of the vehicle 3 is acquired (that is, the position stored in association with the distance in S16). For example, in the example shown in FIG. 7, each position of P1 to P8 is performed. And after performing the process of S17-S27 with respect to all the positions from which the detection point of the present position of the vehicle 3 was acquired, it transfers to S28.

  First, in S17, the CPU 21 statistically calculates all the distances associated with the position to be processed in S16, the distance to the center line along the road width direction of the road is the horizontal axis, and the frequency is the vertical axis. Create a frequency distribution. As described above, the distance to the center line is a positive value when the detection point is on the right side of the center line with respect to the traveling direction, and a negative value when the detection point is on the left side. For example, FIG. 12 is an example of the frequency distribution created in S17.

  Subsequently, in S18, the CPU 21 calculates an average value of the distribution created in S17 (that is, all the distances associated in S16 with respect to the position to be processed).

  Thereafter, in S19, the CPU 21 determines whether or not the absolute value of the distance from the average value of the distribution calculated in S18 to the center line of the lane is less than a predetermined distance. The predetermined distance may be a fixed value (for example, 1 m), or may be a value different depending on the road type. Here, as shown in FIG. 13, when the distance D from the average value of the distribution to the center line of the lane is less than a predetermined distance, the distribution is concentrated near the center line of the lane, and the distribution bias It corresponds to the case where there is no. On the other hand, as shown in FIG. 14, when the distance D from the average value of the distribution to the center line of the lane is equal to or greater than a predetermined distance, the distribution is concentrated outside the vicinity of the center line of the lane, On the other hand, this corresponds to a case where the distribution is biased on the right or left side.

  When it is determined that the absolute value of the distance from the average value of the distribution calculated in S18 to the center line of the lane is less than a predetermined distance (S19: YES), that is, when there is no distribution bias, The process proceeds to S20. On the other hand, when it is determined that the absolute value of the distance from the average value of the distribution calculated in S18 to the center line of the lane is equal to or greater than a predetermined distance (S19: NO), that is, on the right side of the center line or If there is a distribution bias on the left side, the process proceeds to S23.

  In S20, the CPU 21 calculates the standard deviation σ of the distribution created in S17. Since the method for calculating the standard deviation σ is known, the description thereof is omitted.

  Subsequently, in S21, the CPU 21 specifies a distance three times the standard deviation σ calculated in S20 as 1/2 of the lane width W at the position to be processed. Here, assuming that the distribution of the traveling position of the vehicle at the time of curve traveling with the road width direction as the horizontal axis created in S17 converges to a normal distribution centered around the lane center as shown in FIG. The probability that a random variable is included in the range from −3σ to + 3σ is about 99.7%, and almost all the vehicles are traveling in the range from −3σ to + 3σ. Therefore, the range from −3σ to + 3σ can be estimated as the range in the lane where the vehicle can travel, and the distance of 3σ corresponds to ½ of the lane width W.

  After that, in S22, the CPU 21 sets a point on the right side of the lane width W calculated in S21 on the right side in the traveling direction with respect to the center line 70 of the lane at the processing target position as shown in FIG. Record as boundary point 72. Similarly, a point that is 1/2 of the lane width W calculated in S21 is recorded as a left boundary point 73 on the left side in the traveling direction. Similarly, the boundary points 72 and 73 are specified for each position where the detection point of the current position of the vehicle 3 is acquired (that is, the position stored in association with the distance in S16). Thereafter, the process proceeds to S28.

  On the other hand, in S23, the CPU 21 determines whether or not the average value of the distribution calculated in S18 is on the right (positive) side of the center line of the lane.

  If it is determined that the average value of the distribution calculated in S18 is on the right (positive) side of the center line of the lane (S23: YES), that is, the distribution is right (positive) in the traveling direction with respect to the center line. If it is biased to the side, the process proceeds to S24. On the other hand, when it is determined that the average value of the distribution calculated in S18 is on the left (negative) side of the lane center line (S23: NO), that is, the distribution is left in the traveling direction with respect to the center line ( If it is biased to the negative side, the process proceeds to S25.

  In S24, the CPU 21 determines that the probability that a random variable is included in the distribution in the range in which the horizontal axis is positive in the distribution created in S17 is included in ± 3σ of the normal distribution (that is, about 99.99). 7%) is calculated using the inverse function of the probability calculation formula or the like. After that, in S26, the CPU 21 specifies the distance from the center line (0 position) to the end point calculated in S24 as 1/2 of the lane width W at the processing target position.

  Here, as shown in FIG. 17, in the case where the distribution of the vehicle traveling position during the curve traveling with the horizontal axis as the road width direction created in S17 is biased to the right side, the irregular center line is used. Also, the travel information of the vehicle traveling on the left side is excluded, and the lane width is specified using the travel information of the vehicle traveling on the right side of the main center line. Therefore, first, the upper limit (lower limit is 0 position (center line)) of the range including almost all the vehicles traveling on the right side of the center line is calculated in S24. As a result, the range from the 0 position to the end point calculated in S24 can be estimated as the range in the lane where the vehicle can travel on the right side of the center line. The distance from the 0 position indicating the range width to the end point calculated in S24 corresponds to ½ of the lane width W.

  On the other hand, in S25, the CPU 21 determines that the probability that the random variable is included in the distribution in the range in which the horizontal axis is negative in the distribution created in S17 is included in ± 3σ of the normal distribution (that is, approximately 99.7%) is calculated using the inverse function of the probability calculation formula or the like in the range starting from the 0 position having the same probability. Thereafter, in S26, the CPU 21 specifies the distance from the center line (0 position) to the end point calculated in S25 as ½ of the lane width W at the processing target position.

  Here, as shown in FIG. 18, in the case where the vehicle travel position distribution during the curve travel with the horizontal axis in the road width direction created in S17 is biased to the left side, Also, the travel information of the vehicle traveling on the right side is excluded, and the lane width is specified using the travel information of the vehicle traveling on the left side of the main center line. Therefore, first, the lower limit (upper limit is 0 position (center line)) of the range including almost all the vehicles traveling on the left side of the center line is calculated in S25. As a result, the range from the 0 position to the end point calculated in S25 can be estimated as the range in the lane where the vehicle can travel on the left side of the center line. Then, the distance from the 0 position indicating the range width to the end point calculated in S25 corresponds to ½ of the lane width W. In S24 and S25, the end point of the range having the probability of being included within ± 3σ of the normal distribution is specified, but the range reference may be ± 2σ or ± 4σ instead of ± 3σ.

  After that, in S27, the CPU 21 sets a point on the right side of the lane width W calculated in S26 on the right side in the traveling direction with respect to the center line 70 of the lane at the processing target position as shown in FIG. Record as boundary point 72. Similarly, a point that is 1/2 the lane width W calculated in S26 is recorded as a left boundary point 73 on the left side in the traveling direction. Similarly, the boundary points 72 and 73 are specified for each position where the detection point of the current position of the vehicle 3 is acquired (that is, the position stored in association with the distance in S16). Thereafter, the process proceeds to S28.

  In S28, the CPU 21 calculates an approximate curve of the boundary point recorded on the right side in the traveling direction with respect to the center line in S22 or S27, and specifies it as the boundary on the right side in the traveling direction of the curve section to be processed. Similarly, an approximate curve of the boundary point recorded on the left in the traveling direction with respect to the center line in S22 or S27 is calculated and specified as the boundary on the left in the traveling direction of the curve section to be processed. As a result, as shown in FIG. 19, in the curve section to be processed, a boundary 75 on the right side in the traveling direction and a boundary 76 on the left side in the traveling direction are specified with respect to the center line 70, respectively. Further, a range surrounded by the boundaries 75 and 76 is a travelable range in which the vehicle 3 can travel in the curve section to be processed. The approximate curve is calculated using a least square method, a spline curve, or the like. Further, when there are a plurality of lanes in one traveling direction for the curve section to be processed, the lane boundary is specified for each lane.

  Here, when driving on a curve in a state where automatic driving support related to “lane keeping” is not performed (for example, driving by manual driving), the vehicle does not necessarily travel near the center of the lane, and the driver It travels in various ways (for example, out-in-out and in-out-in). Therefore, it is possible to estimate the range in which the vehicle can travel in the lane, that is, the boundary of the lane, as described above, by specifying the range in which each vehicle that does not perform the automatic driving support related to “lane keeping” is specified. Become.

  Further, information on the center line and the boundary of the lane in the curve section specified in S12 or S28 is stored in the probe statistical information DB 13 as probe statistical information (FIG. 4). And the probe server 5 is comprised so that it may deliver to each vehicle 3 according to the request | requirement from the vehicle 3. FIG. As a result, the vehicle 3 can perform more appropriate automatic driving support using the information about the center line and the boundary of the lane distributed from the probe server 5.

  As described above in detail, according to the road shape detection system 1, the road shape detection method using the road shape detection system 1, and the computer program executed by the road shape detection system 1 according to the present embodiment, the lane keeping running can be performed. On the other hand, the travel information of the vehicle traveling in a state where the automatic driving support is performed is acquired (S11), and the center line of the lane in which the vehicle has traveled is specified based on the acquired travel information of the vehicle (S12). The travel information of the vehicle traveling in a state where the automatic driving support related to the lane maintaining travel is not performed is acquired (S13), and the boundary of the lane in which the vehicle travels is based on the acquired travel information and the center line of the lane. (S14 to S28), so that traveling information of a vehicle that travels in a state in which automatic driving assistance is implemented and a vehicle that travels in a state in which automatic driving assistance is not implemented By combining the travel information and makes it possible to identify the center line and the boundary of the lane of the lane accurately respectively. Then, the shape of the lane, that is, the range in which the vehicle can travel can be accurately specified from the specified center line and boundary shape. In particular, it is possible to accurately specify the lane shape even in a section where the lane width is locally changed. As a result, automatic driving support can be appropriately performed even in a section having a complicated shape such as a curve shape. In addition, even in a section where the lane marking has disappeared, it is possible to continue the automatic driving support without stopping by using the information regarding the boundary between the center line of the specified lane and the lane.

Note that the present invention is not limited to the above-described embodiment, and various improvements and modifications can be made without departing from the scope of the present invention.
For example, in the present embodiment, the center line and the boundary of the lane of the curve section are particularly specified as the road shape specified based on the vehicle travel information, but the lanes other than the curve section are not limited to the curve section. It is also possible to specify the center line and the boundary.

  In the present embodiment, it is determined whether or not the frequency distribution created in S17 is biased. When there is a bias, the lane boundary is specified by the processing of S20 to S22, and when there is no bias. Although the lane boundary is specified by the processing of S23 to S27, the lane boundary may be specified by the processing of S20 to S22 regardless of whether there is a bias. Further, in this embodiment, it is determined whether or not the distribution is biased by the distance from the center line of the lane to the average value of the distribution, but “distortion” may be used as a means for determining the distribution bias. good.

  In the present embodiment, the probe server 5 is configured to execute each step of the road shape detection processing program (FIGS. 8 and 9). However, the navigation device 2, the vehicle control ECU 41, and other on-vehicle devices are partially or It is good also as a structure which performs all. In the case where the navigation device 2 or the like is configured to execute, the traveling information of the own vehicle is collected, and the processes after S11 are executed using the collected traveling information of the own vehicle.

  In the present embodiment, the lane change is manually performed by the user even while the automatic driving support is being performed. However, the lane change may be automatically performed by the automatic driving support. Further, it may be configured to be able to implement right / left turn, stop, start, etc. with automatic driving support.

  In the present embodiment, the vehicle control ECU 41 automatically controls all of the accelerator operation, the brake operation, and the handle operation, which are operations related to the behavior of the vehicle, among the operations of the vehicle, regardless of the driving operation of the user. It has been explained as an automatic driving support for running. However, the vehicle control ECU 41 may control the automatic driving support by controlling at least one of the accelerator operation, the brake operation, and the steering wheel operation, which is an operation related to the behavior of the vehicle among the operations of the vehicle. On the other hand, manual driving by the user's driving operation will be described as a case where the user performs all of the accelerator operation, the brake operation, and the steering wheel operation, which are operations related to the behavior of the vehicle, among the operations of the vehicle.

  Moreover, although the embodiment which actualized the road shape detection system according to the present invention has been described above, the road shape detection system can also have the following configuration, and in that case, the following effects can be obtained.

For example, the first configuration is as follows.
Automatic driving travel information acquisition means (21, 61) for acquiring traveling information of the vehicle (3) traveling in a state where the automatic driving support related to the lane maintaining driving is performed, and the automatic driving support related to the lane maintaining driving are performed. Based on the travel information acquired by the manual driving travel information acquisition means (21, 61) and the automatic driving travel information acquisition means for acquiring travel information of the vehicle traveling in a state where the vehicle is traveling, Based on the center line specifying means (21, 61) for specifying the center line (70), the travel information acquired by the manual driving travel information acquiring means, and the center line of the lane specified by the center line specifying means. Te, have a, the boundary identifying means (21, 61) for specifying the boundary (75, 76) of the lane in which the vehicle has traveled, the boundary specifying unit, the run relative to the center line of the lane The vehicle to identify the boundaries of traveling lane based on the distribution state of the information.
According to the road shape detection system having the above configuration, by combining traveling information of a vehicle that travels in a state where automatic driving assistance is performed and traveling information of a vehicle that travels in a state where automatic driving support is not performed The lane center line and the lane boundary can be accurately identified. Then, the shape of the lane, that is, the range in which the vehicle can travel can be accurately specified from the specified center line and boundary shape. In particular, it is possible to accurately specify the lane shape even in a section where the lane width is locally changed. As a result, automatic driving support can be appropriately performed even in a section having a complicated shape such as a curve shape. In addition, even in a section where the lane marking has disappeared, it is possible to continue the automatic driving support without stopping by using the information regarding the boundary between the center line of the specified lane and the lane.

The second configuration is as follows.
Travelable range specifying means (21, 61) for specifying a range surrounded by the boundaries (75, 76) specified by the boundary specifying means (21, 61) as a travelable range in which the vehicle (3) can travel Have.
According to the road shape detection system having the above configuration, it is possible to accurately specify the range in which the vehicle can travel from the shape of the boundary of the lane. As a result, automatic driving support can be appropriately performed even in a section having a complicated shape such as a curve shape.

The third configuration is as follows.
The automatic driving travel information acquisition means (21, 61) acquires a history of detection points of the current position of the vehicle (3) over time as the travel information, and the center line specifying means (21, 61) The approximate curve of the detection point acquired by the automatic driving travel information acquisition means is calculated, and the calculated approximate curve is specified as the center line (70) of the lane on which the vehicle has traveled.
According to the road shape detection system having the above configuration, it is possible to accurately identify the center line of the lane based on the travel information of the vehicle in the state where the automatic driving support for traveling as close to the center of the lane as possible is performed. It becomes possible.

The fourth configuration is as follows.
The manual driving travel information acquisition means (21, 61) acquires a history of detection points of the current position of the vehicle (3) over time as the travel information, and the boundary specifying means (21, 61) For each detection point acquired by the manual driving travel information acquisition means, a distance to the center line (70) of the lane specified by the center line specifying means (21, 61) is calculated, and for each detection point The lane boundaries (75, 76) are specified based on a distribution obtained by statistically calculating the distance calculated in (1).
According to the road shape detection system having the above-described configuration, the driving information of the vehicle in a state where the automatic driving support for driving as close to the center of the lane as possible is not implemented and the user can freely drive in the lane with the intention of the user. It is possible to accurately identify the boundary of the lane.

The fifth configuration is as follows.
The boundary specifying means (21, 61) calculates a standard deviation of the distribution, and each of the standard on both sides separated from the center line (70) of the lane specified by the center line specifying means (21, 61). A position that is three times the deviation is specified as the lane boundary (75, 76).
According to the road shape detection system having the above-described configuration, most of the vehicles for which automatic driving support is not performed using the standard deviation of the distribution that statistically calculates the distance from the center line of the detection point of the current position It is possible to specify a boundary and accurately specify the boundary as a lane boundary.

The sixth configuration is as follows.
The boundary specifying means (21, 61) calculates an average value of the distribution, and is specified by the center line specifying means (21, 61) in a distribution obtained by statistically calculating a distance calculated for each detection point. A distance that is ½ of the lane width of the lane in which the vehicle (3) has traveled is calculated from the distribution that is located on the average value side of the distribution from the center line (70) of the lane, and the center line specifying means Positions that are one-half of the lane width on both sides away from the identified center line of the lane are identified as the lane boundaries (75, 76).
According to the road shape detection system having the above-described configuration, when there is a bias in the distribution obtained by statistically measuring the distance from the center line of the detection point of the current position, the lane width of the lane from the distribution on the side that is biased with respect to the center line. By calculating the lane boundary, it is possible to accurately identify the lane boundary even when the distribution is biased.

The seventh configuration is as follows.
The distribution is a frequency distribution in which the distance from the center line along the road width direction of the road is the horizontal axis and the frequency is the vertical axis, and is specified by the center line specifying means (21, 61) with respect to the traveling direction. The detection point located on one side of the center line (70) of the lane is positive from the center line, and the detection point located on the other side is negative from the center line. If the average value of the distribution is positive, the probability that the random variable is included in the distribution in the range in which the horizontal axis is positive in the distribution is the same probability as the probability included in ± 3σ of the normal distribution. If the end point of the range starting from the 0 position is calculated and the average value of the distribution is negative, the probability that the random variable is included in the distribution in the range where the horizontal axis is negative is ±± of the normal distribution. 0th with the same probability as included in 3σ The calculating the end point of the range in which a starting point, and calculates the distance from the 0 position to the end point as a half to become distance lane width of the lane in which the vehicle has traveled.
According to the road shape detection system having the above configuration, when there is a bias in the statistical distribution of the distance from the center line of the detection point of the current position, the automatic driving support is performed on the side with the bias relative to the center line. It is possible to specify a range in which most of the vehicles that are not traveling travel as a range in which the vehicle on the side biased with respect to the center line can travel, and to calculate the lane width of the lane based on the range. As a result, it is possible to accurately identify the lane boundary even when the distribution is biased.

The eighth configuration is as follows.
Distortion determining means (21, 61) for determining whether the distance from the average value of the distribution to the center line (70) of the lane is less than a predetermined distance, and the boundary specifying means (21, 61) The lane boundaries (75, 76) are specified based on the determination result of the distortion determination means and the distribution.
According to the road shape detection system having the above-described configuration, it is possible to specify the lane boundary by an appropriate method based on the determination result of whether or not the distribution of the detection points at the current position is biased.

The ninth configuration is as follows.
The boundary specifying means (21, 61) calculates a standard deviation of the distribution when it is determined that the distance from the average value of the distribution to the center line (70) of the lane is less than a predetermined distance. While specifying the positions separated from the center line of the lane specified by the center line specifying means (21, 61) by three times the standard deviation on both sides as the boundary (75, 76) of the lane When it is determined that the distance from the average value of the distribution to the center line of the lane is equal to or greater than a predetermined distance, the center line specifying means is a statistical distribution of the distance calculated for each detection point. A distance that is ½ of the lane width of the lane in which the vehicle has traveled is calculated from a distribution that is located on the average value side of the distribution from the center line of the lane specified by, and specified by the center line specifying means. The center line of the lane Identifying a half away of each lane width on both sides away as a boundary of the lane.
According to the road shape detection system having the above configuration, when there is no bias in the distribution of detection points at the current position, the boundary of the lane is specified using the standard deviation of the entire distribution, and there is a bias in the distribution. By calculating the lane width of the lane from the distribution that is biased with respect to the center line, it is possible to accurately identify the lane boundary even when the distribution is biased.

The tenth configuration is as follows.
The boundary specifying means (21, 61) creates the distribution for each position where the detection point is acquired along the lane, and creates the distribution created at the position for each position where the distribution is created. Based on the lane boundary (75, 76) is specified.
According to the road shape detection system having the above configuration, the lane shape can be accurately specified even for the section where the lane width is locally changed.

DESCRIPTION OF SYMBOLS 1 Road shape detection system 2 Navigation apparatus 3 Vehicle 4 Probe center 5 Probe server 11 Server control ECU
12 Probe information DB
13 Probe statistics DB
33 Navigation ECU
70 Center line 72, 73 Boundary point 75, 76 Boundary

Claims (12)

Automatic driving traveling information acquisition means for acquiring traveling information of a vehicle traveling in a state where the automatic driving support related to lane maintenance traveling is implemented;
Manual driving travel information acquisition means for acquiring travel information of a vehicle that travels in a state where automatic driving support related to lane maintenance traveling is not implemented;
Center line specifying means for specifying the center line of the lane on which the vehicle has traveled based on the travel information acquired by the automatic driving travel information acquiring means;
Boundary specifying means for specifying a boundary of a lane on which the vehicle has traveled based on the travel information acquired by the manual driving travel information acquiring means and the center line of the lane specified by the center line specifying means; Yes, and
The boundary specifying unit is a road shape detection system that specifies a boundary of a lane in which the vehicle has traveled based on a distribution state of the travel information based on a center line of the lane .   The road shape detection system according to claim 1, further comprising a travelable range identifying unit that identifies a range surrounded by the boundary identified by the boundary identifying unit as a travelable range in which the vehicle can travel. The automatic driving travel information acquisition means acquires a history of detection points of the current position of the vehicle over time as the travel information,
The center line specifying means includes
Calculate an approximate curve of the detection points acquired by the automatic driving travel information acquisition means,
The road shape detection system according to claim 1 or 2, wherein the calculated approximate curve is specified as a center line of a lane in which the vehicle has traveled. The manual driving travel information acquisition means acquires a history of detection points of the current position of the vehicle over time as the travel information,
The boundary specifying means includes
For each detection point acquired by the manual driving travel information acquisition means, calculate the distance to the center line of the lane specified by the center line specifying means,
The road shape detection system according to any one of claims 1 to 3, wherein a boundary of the lane is specified based on a distribution obtained by statistically calculating a distance calculated for each detection point. The boundary specifying means includes
Calculate the standard deviation of the distribution,
5. The road shape detection system according to claim 4, wherein a position that is three times the standard deviation on each side of the lane that is separated from the center line of the lane specified by the center line specifying means is specified as a boundary of the lane. The boundary specifying means includes
Calculate the mean of the distribution,
Of the distribution obtained by statistically calculating the distance calculated for each detection point, the lane in which the vehicle has traveled from the distribution located on the average value side of the distribution with respect to the center line of the lane specified by the center line specifying means. Calculate the distance that is half the lane width,
5. The road shape detection system according to claim 4, wherein a position that is 1/2 of the lane width on each side of the lane that is separated from the center line of the lane specified by the center line specifying means is specified as a boundary of the lane. The distribution is a frequency distribution with the horizontal axis as the distance from the center line along the road width direction of the road and the vertical axis as the frequency,
For detection points located on one side of the lane center line specified by the center line specifying means with respect to the traveling direction, the distance from the center line is positive, and for detection points located on the other side from the center line The distance of
The boundary specifying means includes
If the average value of the distribution is positive, the 0 position where the probability that the random variable is included in the distribution in the range where the horizontal axis is positive is the same as the probability included in ± 3σ of the normal distribution Calculate the end point of the range starting from
If the average value of the distribution is negative, 0 position where the probability that the random variable is included in the distribution in the range where the horizontal axis is negative is the same as the probability included in ± 3σ of the normal distribution Calculate the end point of the range starting from
The road shape detection system according to claim 6, wherein the distance from the 0 position to the end point is calculated as a distance that is ½ of the lane width of the lane in which the vehicle has traveled. Distortion determination means for determining whether the distance from the average value of the distribution to the center line of the lane is less than a predetermined distance;
The road shape detection system according to claim 4, wherein the boundary specifying unit specifies a boundary of the lane based on a determination result of the distortion determination unit and the distribution. The boundary specifying means includes
When it is determined that the distance from the average value of the distribution to the center line of the lane is less than a predetermined distance, a standard deviation of the distribution is calculated, and the center of the lane specified by the center line specifying means While identifying the position of three times the standard deviation on both sides separated from the line as the boundary of the lane,
When it is determined that the distance from the average value of the distribution to the center line of the lane is equal to or greater than a predetermined distance, the distribution of the distance calculated for each detection point is statistically calculated by the center line specifying unit. The distance which becomes 1/2 of the lane width of the lane in which the vehicle has traveled is calculated from the distribution located on the average value side of the distribution from the center line of the specified lane, and is specified by the center line specifying means 9. The road shape detection system according to claim 8, wherein positions on both sides of the lane that are separated from a center line of the lane are separated from each other by ½ of the lane width as boundaries of the lane. The boundary specifying means includes
Create the distribution for each position where the detection points are acquired along the lane,
The road shape detection system according to any one of claims 4 to 9, wherein, for each position where the distribution is created, a boundary of the lane is specified based on the distribution created at the position. An automatic driving travel information acquisition means for acquiring travel information of a vehicle that travels in a state in which automatic driving support related to lane maintenance traveling is implemented;
The manual driving travel information acquisition means acquires the travel information of the vehicle traveling in a state where the automatic driving support related to the lane maintenance traveling is not performed,
A step of identifying a center line of a lane in which the vehicle has traveled based on the travel information acquired by the automatic driving travel information acquiring unit;
A step of specifying a boundary of a lane in which the vehicle has traveled based on the travel information acquired by the manual driving travel information acquisition unit and the center line of the lane specified by the center line specifying unit; and, the possess,
The road boundary detection unit is a road shape detection method in which the boundary of the lane on which the vehicle has traveled is identified based on a distribution state of the travel information based on a center line of the lane . Computer
Automatic driving traveling information acquisition means for acquiring traveling information of a vehicle traveling in a state where the automatic driving support related to lane maintenance traveling is implemented;
Manual driving travel information acquisition means for acquiring travel information of a vehicle that travels in a state where automatic driving support related to lane maintenance traveling is not implemented;
Center line specifying means for specifying the center line of the lane on which the vehicle has traveled based on the travel information acquired by the automatic driving travel information acquiring means;
Boundary specifying means for specifying the boundary of the lane on which the vehicle has traveled based on the travel information acquired by the manual driving travel information acquiring means and the center line of the lane specified by the center line specifying means;
A computer program to make it function ,
The boundary specifying unit is a computer program that specifies a boundary of a lane in which the vehicle has traveled based on a distribution state of the travel information based on a center line of the lane .

Images