JP2016194816A - Road shape detection system, road shape detection metho, and computer program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a road shape detection system configured to properly and quickly identify a road shape, on the basis of travel information of a vehicle which can be operated by automatic driving control, as well as manual operation, a road shape detection method, and a computer program.SOLUTION: A road shape detection system acquires travel information of a vehicle which is operated by automatic driving control or manual operation of an occupant, identifies whether the travel information has been obtained by automatic driving control or manual operation, for each travel information acquired, corrects the acquired travel information by weighting based on a travel mode, accumulates the corrected travel information as learning values, and identifies a curvature radius of a curve, on the basis of the accumulated learning values.SELECTED DRAWING: Figure 2

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, as a driving form of a vehicle, in addition to manual driving that travels based on a user's driving operation, driving by automatic driving control in which the vehicle automatically travels along a preset route regardless of the user's driving operation. Newly proposed. In automatic driving control, for example, the current position of the vehicle, the lane in which the vehicle travels, the position of other vehicles in the vicinity are detected at any time, and vehicles such as a steering, a drive source, and a brake are driven so as to travel along a preset route. Control is automatic. Here, traveling by automatic driving control has an 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 appropriately perform driving by automatic driving control. For example, when traveling on a curved road by automatic driving control, it is necessary to specify the curvature radius of the curve in order to travel at an appropriate speed according to the curvature radius of the curve.

  Therefore, for example, Japanese Patent No. 4364228 discloses a curvature of a curved road 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. A technique for calculating the radius is described.

Japanese Patent No. 4364228 (pages 18-19)

  However, in a vehicle capable of running by automatic driving control in addition to the above-described manual driving, if the curvature radius of the curve is calculated from the running information of the vehicle as in Patent Document 1, the following problems occur. It was happening.

  Here, when traveling on a curve by manual driving, the vehicle does not necessarily travel in the center of the lane at a constant speed, and some drivers may travel out-in-out or in-out-in. That is, the driver's preference greatly affects the travel information. On the other hand, when traveling on a curve by automatic driving control, the vehicle travels according to the predetermined control contents without depending on the driver's preference, so the driver's preference hardly affects the traveling information. That is, the quality of the travel information varies greatly depending on whether the vehicle travels by manual driving or automatic driving control.

  And if it is set as the structure which calculates the curvature radius of a curve using the driving information at the time of driving | running | working by manual driving | operation, and the driving | running | working information at the time of driving | running | working by automatic driving | operation control, respectively, it will calculate with the driving information to be used. A large difference will occur in the radius of curvature. Therefore, there is a problem that an error in the calculated curvature radius becomes large. Further, in order to reduce the error, it is necessary to converge the value of the radius of curvature calculated by collecting more travel information, leading to an increase in processing time and processing load.

  The present invention has been made to solve the problems in the prior art, and based on the traveling information of a vehicle capable of traveling by automatic driving control in addition to manual driving, the road shape is accurately and quickly determined. It is an object to provide a road shape detection system, a road shape detection method, and a computer program that can be specified.

In order to achieve the above object, a road shape detection system according to the present invention includes a travel information acquisition unit that acquires travel information of a vehicle that travels by either automatic driving control or manual driving by an occupant's driving operation, and the traveling information acquisition For each of the travel information acquired by the means, a travel mode specifying means for specifying whether the travel information was traveled by automatic driving control or manual driving; and the travel information acquired by the travel information acquiring means, the travel A travel information correction unit that performs correction by weighting according to the travel mode specified by the mode specification unit, a learning unit that accumulates the travel information corrected by the travel information correction unit as a learning value, and an accumulation by the learning unit Road shape specifying means for specifying the road shape on which the vehicle has traveled based on the learned value.
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 travel information acquisition means acquires the travel information of the vehicle that travels by either automatic driving control or manual driving by the occupant's driving operation, and the travel mode specifying means includes the travel information acquiring means. For each of the acquired travel information, the step of identifying whether the travel information was traveled by automatic operation control or manual operation, and the travel information correction means, with respect to the travel information acquired by the travel information acquisition means, A step of performing correction by weighting according to the driving mode specified by the driving mode specifying unit, a step of accumulating the driving information corrected by the driving information correcting unit as a learning value, and a road shape specifying unit Identifying the shape of the road on which the vehicle has traveled based on the learning value accumulated by the learning means. And features.

  A computer program according to the present invention is a program for specifying a road shape based on vehicle travel information. Specifically, a computer is provided with a travel information acquisition unit that acquires travel information of a vehicle that travels by either automatic driving control or manual driving by an occupant's driving operation, and each of the travel information acquired by the travel information acquisition unit. A travel mode specifying means for specifying whether the travel information is traveled by automatic driving control or manual driving, and the travel specified by the travel mode specifying means for the travel information acquired by the travel information acquiring means. Based on the learning value accumulated by the learning means, the traveling information correcting means for performing correction by weighting according to the mode, the learning means for accumulating the traveling information corrected by the traveling information correcting means as a learning value, It functions as road shape specifying means for specifying the road shape on which the vehicle has traveled.

  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, the road shape is determined based on the travel information of a vehicle that can travel by automatic driving control in addition to manual driving. In the case of specifying, by weighting the travel information according to the travel mode of the vehicle, it is possible to specify the road shape from the travel information in consideration of the quality of each travel information. As a result, even if the degree of influence of the driver's preference differs for each travel information, the road shape can be specified accurately and quickly. For example, even if travel information inappropriate for specifying the road shape is acquired, it is possible to specify the road shape with less influence, so the accuracy of specifying the road shape can be improved. It becomes.

It is the block diagram which showed the navigation apparatus which concerns on this embodiment. It is the figure which showed an example of the correction table. It is the figure which showed the driving | running | working locus | trajectory in case a vehicle drive | works a curve area by manual operation. It is the figure which showed distribution of the vehicle position of the left-right direction in case a vehicle drive | works a curve area by manual operation. It is the figure which showed the driving | running | working locus | trajectory in case a vehicle drive | works a curve area by automatic driving | operation control. It is the figure which showed distribution of the vehicle position of the left-right direction in case a vehicle drive | works a curve area by automatic driving control. It is a flowchart of the sub process program of the travel information acquisition process which concerns on this embodiment. It is the figure which showed the point from which driving information is acquired at the time of curve driving | running | working. It is a flowchart of the road shape specific process program which concerns on this embodiment. It is a figure explaining the method of specifying a road shape based on a learning value.

  Hereinafter, a feature image recognition system according to the present invention will be described in detail with reference to the drawings based on an embodiment embodied in a navigation device. First, a schematic configuration of the navigation device 1 according to the present embodiment will be described with reference to FIG. FIG. 1 is a block diagram showing a navigation device 1 according to this embodiment.

  As shown in FIG. 1, the navigation device 1 according to the present embodiment includes a current position detection unit 11 that detects a current position of a vehicle on which the navigation device 1 is mounted, a data recording unit 12 that records various data, A navigation ECU 13 that performs various arithmetic processes based on the input information, an operation unit 14 that receives operations from the user, and a liquid crystal display 15 that displays a map around the vehicle and facility information related to the facility to the user. Communicating between a speaker 16 that outputs voice guidance regarding route guidance, a DVD drive 17 that reads a DVD as a storage medium, and an information center such as a probe center or a VICS (registered trademark: Vehicle Information and Communication System) center And a communication module 18 for performing. In addition, the navigation device 1 is connected to an outside camera 19 and various sensors 20 installed on a vehicle on which the navigation device 1 is mounted via an in-vehicle network such as CAN. Furthermore, the vehicle control ECU 21 that performs various controls on the vehicle on which the navigation device 1 is mounted is also connected so as to be capable of bidirectional communication. Various operation buttons 22 mounted on the vehicle such as an automatic driving start button are also connected.

Below, each component which comprises the navigation apparatus 1 is demonstrated in order.
The current position detection unit 11 includes a GPS 23, a vehicle speed sensor 24, a steering sensor 25, a gyro sensor 26, 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 24 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 13. And navigation ECU13 calculates the rotational speed and moving distance of a driving wheel by counting the generated pulse. Note that the navigation device 1 does not have to include all the four types of sensors, and the navigation device 1 may include only one or more types of sensors.

  In addition, the data recording unit 12 reads out an external storage device and a hard disk (not shown) as a recording medium, a map information DB 31, a learning DB 32, a correction table 33, a predetermined program, and the like recorded on the hard disk, and stores the predetermined program on the hard disk. And a recording head (not shown) which is a driver for writing the data. The data recording unit 12 may be constituted by a flash memory, a memory card, an optical disk such as a CD or a DVD, instead of the hard disk. Further, the map information DB 31 and the learning DB 32 may be stored in an external server, and the navigation device 1 may be configured to acquire by communication.

  Here, the map information DB 31 is, for example, link data related to roads (links), node data related to node points, search data used for processing related to route search, facility data related to facilities, and map display data for displaying a map. The storage means stores intersection data relating to each intersection, search data for searching for points, 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 approximate curvature radius of the curve is also stored.

  The learning DB 32 is a storage unit that accumulates and stores vehicle travel information. In this embodiment, in particular, the vehicle travel information such as the vehicle speed, the yaw rate, the travel locus, and the like is not directly specified, but the calculation result obtained by calculating the road shape from the vehicle speed, the yaw rate, the travel locus, etc. Remember as. Specifically, in the learning DB 32, when the vehicle travels on a curved road, the calculation result of the curvature radius of the curve calculated from the vehicle speed, yaw rate, travel locus, etc. of the vehicle is accumulated and stored as a learning value. It becomes. Then, the navigation ECU 13 specifies the road shape (more specifically, the curvature radius of the curved road) based on the learned value stored in the learning DB 32 as described later. Details of the learning value stored in the learning DB 32 will be described later.

  The correction table 33 is a table in which correction values for weighting the calculation results obtained by calculating the road shape from the vehicle speed, yaw rate, travel locus, and the like of the vehicle are defined.

  Hereinafter, the correction table 33 will be described in more detail with specific examples. FIG. 2 is a diagram showing an example of the correction table 33. As shown in FIG. 2, the correction table 33 defines a correction value in association with the traveling mode of the vehicle (in this embodiment, either automatic driving control or manual driving by the driving operation of the occupant). In addition, a coefficient to be multiplied is appropriately set as the correction value based on the reliability of the calculation result of the curvature radius of the curve. Specifically, the value after correction is high (i.e., the weighting is low) for automatic driving control that is expected to be less affected by the driver's preference and to be more reliable in the calculation result of the curvature radius of the curve than in manual driving. Set the correction value to be heavier.

  Here, as a traveling form of the vehicle, in addition to the manual driving traveling that travels based on the user's driving operation, the vehicle automatically travels along a predetermined route or road regardless of the user's driving operation. It is possible to travel by automatic operation control that performs In the automatic operation control, for example, the current position of the vehicle, the lane in which the vehicle travels, and the positions of other vehicles in the vicinity are detected at any time, and the vehicle control ECU 21 travels along a route or road set in advance. Vehicle control such as steering, drive source, and brake is automatically performed. In particular, when traveling on a curve, the vehicle speed and steering are controlled based on the curvature radius specified by a road shape specifying processing program (see FIG. 9) described later. Note that the lane change or right / left turn may be performed in the travel by the automatic driving control, the lane change or the right / left turn is not performed, and basically the vehicle is not operated unless the user performs the vehicle operation related to the lane change or the right / left turn. It may be traveling in the same lane. The details of the automatic operation control are already known, and the description thereof is omitted. In addition, automatic driving control may be performed for all road sections, but specific roads such as expressways with gates (whether manned, unmanned or paid free) at the boundary with other roads to be connected It is good also as a structure performed only with respect to an area. When the vehicle travels in a section where automatic driving can be performed (hereinafter referred to as automatic driving section), automatic driving control is not always performed, but the user selects automatic driving control, Moreover, it is performed only in a situation where it is determined that traveling can be performed by automatic driving control. In addition, as a situation in which traveling cannot be performed by automatic operation control, 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.

  Here, when traveling on a curve by manual driving, the vehicle does not necessarily travel in the center of the lane at a constant speed, and some drivers may travel out-in-out or in-out-in. That is, the driver's preference greatly affects the travel information. On the other hand, when traveling on a curve by automatic driving control, the vehicle travels according to the predetermined control contents without depending on the driver's preference, so the driver's preference hardly affects the traveling information. That is, the automatic operation control is expected to be more reliable in the calculation result of the curvature radius of the curve than in the manual operation, and the correction is performed so that the calculation result of the curvature radius of the curve is weighted according to the correction table 33.

  A method for setting an appropriate correction value for weighting will be described below with a specific example. In the following description, it is assumed that the vehicle 50 travels on a curved road having a lane width T (for example, 3.5 m) without changing the lane.

  First, when the vehicle 50 travels manually, as shown in FIG. 3, the vehicle 50 can travel freely in the lane according to the driver's intention, so the position of the vehicle in the left-right direction (road width direction) is the maximum. It is possible to move by the lane width T. Therefore, if it is assumed that the distribution of the traveling position of the vehicle during the curve traveling with the road width direction as the horizontal axis converges to a normal distribution centering on the lane center, as shown in FIG. The interval (that is, σ × 6) from the upper limit value D1 (D (lane center) + 3σ) to the lower limit value D2 (D-3σ) of the random variable that falls within the range corresponds to the lane width T.

  On the other hand, when the vehicle 50 travels under automatic driving control, the vehicle 50 travels according to predetermined vehicle control as shown in FIG. 5, so the position of the vehicle in the left-right direction (road width direction) is at most a lane. It is possible to move by X smaller than the width T. In traveling by automatic operation control, the vehicle is basically controlled to travel in the center of the lane, but it is difficult to always travel in the center of the lane, and a certain amount of deviation occurs in the left-right direction. Then, the maximum value of the estimated shift amount is X. X varies depending on the vehicle type and the type of the automatic driving control system, but is 1 m, for example. Therefore, assuming that the distribution of the travel position of the vehicle at the time of the curve travel with the road width direction as the horizontal axis converges to a normal distribution centered on the center of the lane, 99.7% of the random variable is as shown in FIG. The interval (that is, σ × 6) from the upper limit value D3 (D (lane center) + 3σ) to the lower limit value D4 (D-3σ) of the random variable that falls within the range corresponds to X.

When the vehicle 50 travels manually, the probability that the random variable is included in D3 to D4 is calculated to be 36.8% when T = 3.5 m and X = 1 m. On the other hand, when the vehicle 50 travels by automatic driving control, the probability that the random variable is included in D3 to D4 is 99.7% as described above. Therefore, the probability that the vehicle can travel with the same horizontal displacement as that of the automatic operation control during traveling by manual operation is 36.8% / 99.7% = 36.9%. The correction value is set assuming that this probability is proportional to the reliability of the calculation result of the curvature radius of the curve.
That is, the correction value of the weight for the calculation result of the curvature radius of the curve is “× 1 (no correction)” for the travel by the automatic operation control, and “× 0.369” so that the weight is light for the travel by the manual operation control. To do.

  The navigation ECU 13 weights the calculation result of the curvature radius of the curve based on the correction table 33 as will be described later. Specifically, a correction value corresponding to the traveling mode of the vehicle during curve driving is specified from the correction table 33, and the calculation result of the curvature radius of the curve is corrected by the specified correction value. Thereafter, the calculation result of the curvature radius of the curve after the weighting is performed is stored in the learning DB 32 as a learning value. As a result, the calculation result of the curvature radius of the curve, which is expected that the driver's preference does not affect the traveling information and the reliability of the calculation result is high, greatly affects the specification of the curvature radius of the curve.

  On the other hand, the navigation ECU (Electronic Control Unit) 13 is an electronic control unit that controls the entire navigation device 1. The CPU 41 as an arithmetic device and a control device, and a working memory when the CPU 41 performs various arithmetic processes. In addition to the RAM 42 for storing route data when a route is searched, a control program, a travel information acquisition processing program (see FIG. 7) described later, and a road shape specifying processing program (FIG. 9). And the like, and an internal storage device such as a flash memory 44 for storing a program read from the ROM 43. The navigation ECU 13 constitutes various means as processing algorithms. For example, the travel information acquisition means acquires travel information of a vehicle that travels by either automatic driving control or manual driving by a driving operation of a passenger. The travel mode specifying means specifies, for each travel information acquired by the travel information acquiring means, whether the travel information is traveled by automatic driving control or manual driving. The travel information correction unit performs correction by weighting according to the travel mode on the travel information acquired by the travel information acquisition unit. The learning means accumulates the corrected travel information in the learning DB 32 as a learning value. The road shape specifying means specifies the road shape on which the vehicle has traveled based on the learning value accumulated in the learning DB 32.

  The operation unit 14 is operated when inputting a departure point as a travel start point and a destination as a travel end point, and includes a plurality of operation switches (not shown) such as various keys and buttons. Then, the navigation ECU 13 performs control to execute various corresponding operations based on switch signals output by pressing the switches. The operation unit 14 can also be configured by a touch panel provided on the front surface of the liquid crystal display 15. Moreover, it can also be comprised with a microphone and a speech recognition apparatus.

  The liquid crystal display 15 displays map images including roads, traffic information, operation guidance, operation menus, key guidance, guidance information along the guidance route, news, weather forecast, time, mail, TV program, and the like. The In place of the liquid crystal display 15, HUD or HMD may be used.

  The speaker 16 outputs voice guidance for guiding traveling along the guidance route based on an instruction from the navigation ECU 13 and traffic information guidance.

  The DVD drive 17 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 31 is updated, and the like. A card slot for reading / writing a memory card may be provided instead of the DVD drive 17.

  The communication module 18 is a communication device for receiving traffic information, probe information, weather information, and the like transmitted from a traffic information center, for example, a VICS center or a probe center. . 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.

  The vehicle exterior camera 19 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 on the back side of the rear-view mirror and installed with the optical axis direction facing forward in the vehicle traveling direction. Is done. And the vehicle outside camera 19 images the front of the traveling direction of the vehicle when the vehicle travels in the automatic driving section. In addition, the vehicle control ECU 21 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. Perform operation control. In addition, you may comprise the vehicle exterior camera 19 so that it may arrange | position behind or a side other than the vehicle front. As a means for detecting other vehicles, various sensors 20, 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 20, an illuminance sensor or a rain sensor may be installed.

  The vehicle control ECU 21 is an electronic control unit that controls the vehicle on which the navigation device 1 is mounted. In addition, the vehicle control ECU 21 is connected to each drive unit of the vehicle such as a steering, a brake, and an accelerator. In the present embodiment, the vehicle control ECU 21 controls the drive unit particularly when the vehicle travels in an automatic driving section. Implement automatic operation control. In addition, the navigation ECU 13 transmits an instruction signal related to automatic driving control to the vehicle control ECU 21 via the CAN at the time when the planned travel route (guide route) of the vehicle is determined or after the start of travel. And vehicle control ECU21 implements the automatic driving | operation control after a driving | running | working start according to the received instruction signal. The contents of the instruction signal include the control contents of automatic driving control performed on the vehicle (for example, constant speed traveling, following traveling, speed management (deceleration and acceleration control), etc.), control start, stop, change, etc. It is information to instruct. In addition, it is good also as a structure which not the navigation ECU13 but vehicle control ECU21 sets the control content of automatic driving | operation control. In this case, the vehicle control ECU 21 is configured to acquire information necessary for setting automatic driving control such as a planned travel route (guide route), a vehicle state, and surrounding map information from the navigation device 1.

  Next, a travel information acquisition processing program executed by the navigation ECU 13 in the navigation device 1 having the above configuration will be described with reference to FIG. FIG. 7 is a flowchart of the travel information acquisition processing program according to the present embodiment. Here, the travel information acquisition processing program is a program that is executed after the ACC power supply of the vehicle is turned on, and acquires the travel information of the vehicle during the curve travel. Note that the programs shown in the flowcharts of FIGS. 7 and 9 below are stored in the RAM 42 and ROM 43 provided in the navigation device 1 and executed by the CPU 41.

  First, in the travel information acquisition processing program, in step (hereinafter abbreviated as S) 1, the CPU 41 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 S2, the CPU 41 communicates with the vehicle control ECU 21 via the CAN to acquire the control state of the automatic driving control, and whether the vehicle is traveling in the curve section by the automatic driving control or the manual driving. judge.

  Here, the automatic driving control is a case where the vehicle travels in an automatic driving section where automatic driving can be performed as described above, and the user selects to perform the automatic driving control, and the automatic driving control is performed. Implemented only in situations where it is possible to drive. In this embodiment, the automatic driving section is a highway provided with a gate (whether manned or unmanned or free of charge) at the boundary with another road. However, a general road etc. may be included as an automatic driving section. Whether or not automatic operation control is selected by the user is determined by whether or not an automatic operation start button is pressed, for example. Here, the automatic operation start button is arranged on an instrument panel or the like, and is pressed when the user desires switching between automatic operation control and manual operation. Specifically, automatic driving control is started when the vehicle is pressed in a state where the vehicle is driven by manual driving in the automatic driving zone, while the automatic driving zone is being driven when pressed during execution of the automatic driving control. However, the automatic operation control ends and the operation is switched to manual operation.

  And when it determines with the vehicle driving | running | working in the curve area by automatic driving | operation control (S2: YES), an automatic driving | running | working driving flag is set to ON (S3). The automatic driving travel flag is a flag for specifying a travel mode when the vehicle travels in a curve section, and is stored in the RAM 42 or the like. And when the vehicle travels in the curve section by automatic driving control, it is set to ON, and when it travels by manual driving, it is set to OFF.

  On the other hand, when it is determined that the vehicle is traveling in the curve section by manual driving (S2: NO), the automatic driving traveling flag is set to OFF (S4). Thereafter, the process proceeds to S5.

  In S5, the CPU 41 acquires the current position of the vehicle. 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 the 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. Further, map matching processing for moving the detected current position of the vehicle onto a map link is also performed.

  Next, in S6, the CPU 41 acquires vehicle travel information. Specifically, the vehicle speed, yaw rate, and travel locus of the vehicle are acquired from the detection results of the vehicle speed sensor 24, the steering sensor 25, and the gyro sensor 26. The travel locus is obtained by connecting the current vehicle positions acquired in S5 up to the present time as time elapses. However, when the curvature radius of the curve is calculated from the vehicle speed and yaw rate of the vehicle as will be described later, it is not always necessary to acquire the travel locus. On the other hand, when the curvature radius of the curve is calculated from the traveling locus of the vehicle, it is not always necessary to acquire the vehicle speed and yaw rate of the vehicle.

  Subsequently, in S7, the CPU 41 stores the travel information of the vehicle acquired in S6 in the flash memory 44 or the like in association with the current position of the vehicle acquired in S5. For example, as illustrated in FIG. 8, when the vehicle 50 travels in a curve section, when travel information is acquired at each point P1 to P8 in the curve section, the vehicle 50 is associated with each point P1 to P8. The travel information acquired at each point is stored.

  Thereafter, in S8, the CPU 41 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 41 assembles the automatic driving travel flag set in S3 or S4 to the series of vehicle travel information stored in S7. That is, information for identifying whether the traveling information of the vehicle when traveling by automatic driving control or the traveling information of the vehicle when traveling by manual driving is added to the stored traveling information of the vehicle.

  Next, a road shape specifying process program executed by the navigation ECU 13 in the navigation device 1 having the above configuration will be described with reference to FIG. FIG. 9 is a flowchart of the road shape specifying process program according to this embodiment. Here, the road shape specifying process program is executed every predetermined period (for example, every month or after collecting a predetermined number or more of travel information by the travel information acquisition process program), and the vehicle shape collected by the travel information acquisition process program. It is a program for identifying the road shape of the road on which the vehicle has traveled from the travel information.

  In addition, let the process after the following S11 be a structure performed for every curve area which comprises map information.

  First, in S <b> 11, the CPU 41 reads out all the travel information stored in S <b> 9 for the processing target curve from the flash memory 44 or the like. As described above, the travel information includes at least one of the combination of the vehicle speed and the yaw rate of the vehicle, or the travel locus, and the position of the vehicle and the travel mode of the vehicle (automatic operation control or manual operation) when the travel information is acquired. Is also memorized.

  In addition, the process of subsequent S12-S16 is performed for every driving | running | working information read by said S11 (each point P1-P8 in the example shown in FIG. 8). And after performing the process of S12-S16 with respect to all the driving | running | working information read by said S11, it transfers to S17.

  First, in S12, the CPU 41 calculates a curvature radius R of a curve on which the vehicle has traveled based on the travel information to be processed. The curvature radius R of the curve may be calculated from the vehicle speed and the yaw rate using an existing calculation formula, or the travel locus is expressed by a least square method, a spline curve, or the like from the point sequence of the travel locus, and then corresponds. You may calculate the curvature radius of a point (the position of the vehicle from which traveling information to be processed is acquired).

  Next, in S13, the CPU 41 determines whether or not the automatic driving traveling flag associated with the processing target traveling information is ON, that is, whether the processing target traveling information is traveling information of the vehicle when traveling by the automatic driving control. Then, it is determined whether the vehicle travel information when traveling by manual driving.

  And when it determines with the automatic driving | running | working driving flag matched with the driving | running | working information of a process target being ON (S13: YES), ie, driving | running | working of the vehicle when the driving | running | working information of a process drive | worked by automatic driving | operation control. If it is determined to be information, the process proceeds to S14. On the other hand, when it is determined that the automatic driving traveling flag associated with the traveling information to be processed is OFF (S13: NO), that is, when the traveling information to be processed travels by manual driving, When it determines with it being driving | running | working information, it transfers to S15.

  In S14 and S15, the CPU 41 executes a correction process for the calculation result (learning value) of the curvature radius R of the curve in S12. In addition, the correction process of the calculation result (learning value) of the curvature radius R of the curve depends on the vehicle travel mode (travel by automatic driving control or travel by manual driver) when travel information used for the calculation is acquired. This is a process of weighting accordingly. As described above, when driving on a curve by “manual driving”, the vehicle does not always travel in the center of the lane at a constant speed. Depending on the driver, the vehicle travels out-in-out or in-out-in. Some people. That is, the driver's preference greatly affects the travel information. On the other hand, when traveling on a curve by “automatic driving control”, the vehicle travels according to predetermined control contents without depending on the driver's preference, so the driver's preference hardly affects the traveling information. Therefore, the automatic operation control corrects the weighting of the calculation result of the curvature radius of the curve more heavily than the manual operation.

  Specifically, the calculation frequency of the curvature radius R of the curve is corrected based on the correction table 33 shown in FIG. In other words, the curvature radius R of the curve calculated when traveling on the curve by “automatic driving control” is set to 1 for the calculation result of 1 (S14). On the other hand, the curvature radius R of the curve calculated when traveling on the curve by “manual operation” is set to a frequency of 0.369 with respect to the calculation result of 1 (S15).

  Next, in S16, the CPU 41 accumulates and stores the calculation result (learning value) of the curvature radius R of the curve calculated in S12 in the learning DB 32 in association with the corrected calculation frequency. Note that it is desirable that old learning values (for example, one year or more before) be sequentially deleted from the learning DB 32.

  Thereafter, in S <b> 17, the CPU 41 specifies the radius of curvature of the curve to be processed based on the learning value stored in the learning DB 32. More specifically, by calculating the accumulated learning values, a frequency distribution is created with the horizontal axis representing R and the vertical axis representing frequency, as shown in FIG. Then, the most frequently used R value is specified as the curvature radius R of the curve to be processed. Note that the median value, not the mode value, may be specified as the curvature radius of the curve to be processed. Further, in S17, all learning values accumulated for one curve may be statistically determined, and one curvature radius may be specified for one curve, or in a curve section where travel information is acquired. The learning value accumulated for each of a plurality of points (for example, P1 to P8 in FIG. 8) may be statistically determined, and one curvature radius may be specified for one point. In addition, if it is set as the structure which specifies a curvature radius for every point, even if it is a curve area which has a complicated shape, it will also become possible to specify a more detailed curve shape.

  Here, as a result of the correction in S14 and S15, the driver's preference does not affect the travel information, and the calculation result of the curvature radius of the curve is expected to be highly reliable (travel by automatic driving control). The radius of curvature (learning value) of the curve calculated in (1) is heavily weighted (the calculation frequency is “1” for one calculation result). On the other hand, the curvature radius (learned value) of the curve calculated in a situation where the driver's preference greatly affects the driving information and the reliability of the calculation result of the curvature radius of the curve is expected to be low (running by manual driving) is The weighting becomes lighter (the calculation frequency is made smaller than “1” for one calculation result). In S17, even if the travel information inappropriate for calculating the curvature radius R of the curve is acquired by statistically calculating the corrected learning values obtained by weighting them, Thus, the curvature radius R of the curve can be specified by reducing the influence of the above, and the accuracy of specifying the curvature radius R of the curve can be improved.

  The curvature radius of the curve specified based on the learning value may be distributed as probe information to other vehicles via an external server. On the other hand, the traveling information stored in S9 is transmitted from each vehicle to an external server as probe information, and the external server executes the processing from S11 onward based on the probe information acquired from each vehicle. It is good also as a structure which specifies the curvature radius of a certain curve. In that case, the curvature radius of the curve specified in the external server is configured to be distributed to each vehicle thereafter.

  As described above in detail, according to the navigation device 1 according to the present embodiment, the road shape detection method using the navigation device 1 and the computer program executed by the navigation device 1, manual operation by automatic driving control or occupant driving operation is performed. The travel information of the vehicle traveling by either driving is acquired (S6), and for each acquired travel information, it is specified whether the travel information is traveled by automatic driving control or manual driving (S3, S4), and acquired. The travel information is corrected by weighting according to the travel mode (S14, S15), the corrected travel information is accumulated as a learned value (S16), and the curvature radius R of the curve is calculated based on the accumulated learned value. Since it identifies (S17), it becomes possible to identify the road shape from the travel information in consideration of the quality of each travel information. As a result, even if the degree of influence of the driver's preference differs for each travel information, the road shape can be specified accurately and quickly. For example, even if travel information that is inappropriate for calculating the curvature radius of a curve is acquired, it is possible to specify the curvature radius of the curve with less influence, so the accuracy of specifying the curvature radius of the curve Can be improved.

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 curvature radius R of the curve section is particularly specified as the road shape specified based on the learned value, but other road shapes can be used as long as the road shape can be specified based on the travel information of the vehicle. It is good also as a structure which specifies. For example, it is good also as a structure which specifies the bending angle etc. of a road. Moreover, it is good also as a structure which acquires information other than the vehicle speed of a vehicle, a yaw rate, and a travel locus as vehicle information used as acquisition object.

  Further, in the present embodiment, the curvature radius of the curve is calculated for each position of the vehicle (P1 to P8 shown in FIG. 8) when the travel information is acquired. It is good also as a structure which calculates a curvature radius. In that case, the configuration is such that a running locus is expressed by a least square method, a spline curve, or the like from a series of points of a running locus and a curvature radius is calculated.

  In the present embodiment, the calculation result obtained by calculating the curvature radius of the curve from the vehicle speed, yaw rate, travel locus, etc. of the vehicle is corrected. However, the vehicle speed, yaw rate, travel locus, etc. of the vehicle may be corrected. In that case, weighting is performed so that the travel information acquired during travel by automatic operation control is heavier than the travel information acquired during travel by manual operation.

  In the present embodiment, the navigation device 1 is configured to execute each step of the travel information acquisition processing program (FIG. 7) and the road shape identification processing program (FIG. 9). It is good also as a structure which performs one part or all part. In particular, the road shape identification processing program (FIG. 9) may be configured to be executed by an external server. In addition, when setting it as the structure which an external server performs, it may also be set as the structure which collects driving | running | working information not only from a specific vehicle but from the unspecified many vehicles which can communicate, and performs the process after S11. Is possible.

  Moreover, although the embodiment which actualized the road shape detection system according to the present invention has been described above, the feature image recognition 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.
A travel information acquisition unit that acquires travel information of a vehicle that travels by either automatic driving control or manual driving by an occupant's driving operation, and automatic driving control or manual driving for each of the traveling information acquired by the traveling information acquisition unit A travel mode specifying means for specifying which travel information is traveled, and correction by weighting according to the travel mode specified by the travel mode specifying means for the travel information acquired by the travel information acquiring means A travel information correction unit to perform, a learning unit to accumulate the travel information corrected by the travel information correction unit as a learning value, and a road shape on which the vehicle has traveled is identified based on the learning value accumulated by the learning unit Road shape specifying means.
According to the road shape detection system having the above configuration, in the case where the road shape is specified based on the travel information of the vehicle capable of performing the driving by the automatic driving control in addition to the manual driving, according to the driving mode of the vehicle. By weighting the travel information, the road shape can be specified from the travel information in consideration of the quality of each travel information. As a result, even if the degree of influence of the driver's preference differs for each travel information, the road shape can be specified accurately and quickly. For example, even if travel information inappropriate for specifying the road shape is acquired, it is possible to specify the road shape with less influence, so the accuracy of specifying the road shape can be improved. It becomes.

The second configuration is as follows.
The travel information correcting means corrects the travel information traveled by the automatic operation control so that the weight is larger than the travel information traveled by the manual operation.
According to the road shape detection system having the above-described configuration, the driving information acquired during the driving by the automatic driving control in which the driver's preference does not affect the driving information and the reliability of the road shape specifying result is expected to be high. Since the weighting is increased, it is possible to specify the road shape while reducing the influence of the travel information during manual driving, which greatly reflects the driver's preference. As a result, it is possible to improve the road shape specifying accuracy.

The third configuration is as follows.
When the vehicle travels in the same lane by manual operation, the manual operation travel width that is the maximum width that may move in the left-right direction in the lane, and the travel information correction means are configured so that the vehicle performs automatic operation control. When the vehicle travels in the same lane, weighting is performed by a correction value determined by comparison with the automatic driving travel width that is the maximum width that may move in the left-right direction in the lane.
According to the road shape detection system having the above configuration, the laterally movable width when traveling in the same lane by manual driving and the lateral movement when traveling in the same lane by automatic driving control are possible. By comparing the width, more accurate and detailed weighting can be performed for each traveling mode.

The fourth configuration is as follows.
The manual driving travel width is a width of a lane in which the vehicle travels, and the automatic driving travel width is a width smaller than a width of a lane in which the vehicle travels.
According to the road shape detection system having the above configuration, the driver's preference does not affect the width of movement in the left-right direction, and is acquired at the time of traveling by automatic driving control that is expected to have high reliability of the road shape specifying result. Since the weight of the travel information is increased, it is possible to specify the road shape while reducing the influence of the travel information during manual driving with a large lateral movement width depending on the driver's preference. As a result, it is possible to improve the road shape specifying accuracy.

The fifth configuration is as follows.
The road shape specifying means specifies a curvature radius in a road curve shape.
According to the road shape detection system having the above configuration, it is possible to specify the curvature radius accurately and quickly, particularly when the curvature radius in the curve shape of the road is specified from the travel information of the vehicle.

The sixth configuration is as follows.
A radius of curvature calculating means for calculating a radius of curvature of the curve traveled by the vehicle based on travel information of the vehicle from entering the curve to exiting the curve; The calculation frequency for the calculation result is corrected based on a correction value determined by the travel mode, the curvature radius and the calculated frequency after correction are accumulated as the learning value, and the road shape specifying unit is configured to statistically calculate the learning value. Thus, a frequency distribution is created based on the curvature radius and the calculation frequency, and the curvature radius having the highest frequency is specified as the curvature radius of the curve traveled by the vehicle.
According to the road shape detection system having the above-described configuration, it is possible to accurately specify the radius of curvature of the curve on which the vehicle has traveled by performing statistical processing using the learning result.

The seventh configuration is as follows.
The curvature radius calculation means calculates the curvature radius of the curve for each of a plurality of points in the curve section from entering the curve to leaving the curve based on the travel information of the vehicle at the point. The road shape specifying means specifies the curvature radius for each of the plurality of points by statistically calculating the learning value for each of the plurality of points, and determines the vehicle from the specified curvature radius for each of the plurality of points. It is characterized in that the curve shape on which the vehicle travels is specified.
According to the road shape detection system having the above configuration, by specifying the radius of curvature for each point included in the curve section, it is possible to specify a more detailed curve shape even in a curve section having a complicated shape. It becomes possible.

The eighth configuration is as follows.
The travel information includes any one of a vehicle speed, a yaw rate, and a travel locus of the vehicle.
According to the road shape detection system having the above configuration, when the road shape is specified using any one of the vehicle speed, the yaw rate, and the travel locus, the vehicle travels in consideration of the travel mode of the vehicle when each travel information is acquired. Since the information is weighted, the road shape can be specified accurately and quickly.

1 Navigation device 13 Navigation ECU
32 Learning DB
33 Correction table 41 CPU
42 RAM
43 ROM
50 vehicles

Claims (10)

Traveling information acquisition means for acquiring traveling information of a vehicle traveling by either automatic driving control or manual driving by an occupant's driving operation;
For each of the travel information acquired by the travel information acquisition means, a travel mode specifying means for specifying whether the travel information is traveled by automatic driving control or manual driving;
Travel information correction means for performing correction by weighting according to the travel mode specified by the travel mode specifying unit, with respect to the travel information acquired by the travel information acquisition unit;
Learning means for accumulating the travel information corrected by the travel information correction means as a learning value;
A road shape specifying means for specifying a road shape on which the vehicle has traveled based on a learning value accumulated by the learning means.   The road shape detection system according to claim 1, wherein the travel information correction unit corrects the travel information traveled by the automatic operation control so that the weight is larger than the travel information traveled by the manual operation. The travel information correction means includes
When the vehicle travels in the same lane by manual driving, the manual driving travel width that is the maximum width that may move in the left-right direction in the lane and the vehicle travels in the same lane by automatic driving control The weighting is performed according to a correction value determined by comparison with an automatic driving traveling width that is a maximum width that may move in the left-right direction in the lane in some cases. The described road shape detection system. The manual driving travel width is a width of a lane in which the vehicle travels,
The road shape detection system according to claim 3, wherein the automatic driving traveling width is smaller than a width of a lane in which the vehicle travels.   The road shape detection system according to any one of claims 1 to 4, wherein the road shape specifying means specifies a radius of curvature in a curve shape of the road. A radius of curvature calculating means for calculating a radius of curvature of the curve traveled by the vehicle based on travel information of the vehicle from entering the curve to exiting the curve;
The learning means corrects the calculation frequency for the calculation result of the curvature radius based on a correction value determined by the running mode, and accumulates the curvature radius and the corrected calculation frequency as the learning value,
The road shape specifying means creates a frequency distribution based on the curvature radius and the calculation frequency by statistically calculating the learning value, and specifies the curvature radius having the highest frequency as the curvature radius of the curve traveled by the vehicle. The road shape detection system according to claim 5, wherein the system is a road shape detection system. The curvature radius calculation means calculates the curvature radius of the curve for each of a plurality of points in the curve section from entering the curve to leaving the curve based on the travel information of the vehicle at the point. ,
The road shape specifying means is
By identifying the learning value for each of the plurality of points, the radius of curvature is specified for each of the plurality of points,
The road shape detection system according to claim 6, wherein a curve shape in which the vehicle has traveled is specified from the specified radius of curvature for each of the plurality of points.   The road shape detection system according to any one of claims 1 to 7, wherein the travel information includes any one of a vehicle speed, a yaw rate, and a travel locus of the vehicle. A step in which travel information acquisition means acquires travel information of a vehicle that travels by either automatic driving control or manual driving by an occupant's driving operation;
A step of identifying whether the travel mode identifying means is travel information traveled by automatic driving control or manual driving for each of the travel information acquired by the travel information acquiring means;
A travel information correcting unit performing correction by weighting according to the travel mode specified by the travel mode specifying unit with respect to the travel information acquired by the travel information acquiring unit;
A learning unit that accumulates the travel information corrected by the travel information correction unit as a learning value;
A road shape specifying means comprising: a step of specifying a road shape on which the vehicle has traveled based on a learning value accumulated by the learning means. Computer
Traveling information acquisition means for acquiring traveling information of a vehicle traveling by either automatic driving control or manual driving by an occupant's driving operation;
For each of the travel information acquired by the travel information acquisition means, a travel mode specifying means for specifying whether the travel information is traveled by automatic driving control or manual driving;
Travel information correction means for performing correction by weighting according to the travel mode specified by the travel mode specifying unit, with respect to the travel information acquired by the travel information acquisition unit;
Learning means for accumulating the travel information corrected by the travel information correction means as a learning value;
Road shape specifying means for specifying the road shape on which the vehicle has traveled based on the learning value accumulated by the learning means;
Computer program to make it function.

Images