JP2004078334A - Traveling route generation device - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a traveling route generation device which can continue an automatic steering control when the state in which the route is missed intermittently continues and ensure enough time for a driver to respond even when the state in which the route is missed continues. <P>SOLUTION: The traveling route generation device 12 is provided with a scene vector string recognition means 14 that recognizes a vector string, which connects characteristic points in an imaging scene, as the scene vector string; a route reproduction data computing means 15 which computes positional/directional relations between the recognized scene vector string and a fixed route as the route reproduction data; a fixed route recognition determining means 13 which determines whether the fixed route is recognized; and a fixed route presuming means 16 which presumes the location/posture of the fixed route on the basis of the scene vector string thus recognized and route reproduction data thus computed. <P>COPYRIGHT: (C)2004,JPO

Description

[0001]
TECHNICAL FIELD OF THE INVENTION
The present invention relates to a technical field of a traveling route generation device for guiding a vehicle that automatically performs automatic steering by performing automatic steering along a certain route.
[0002]
[Prior art]
2. Description of the Related Art Conventionally, there has been known an automatically steered vehicle that travels following a route by automatically steering a route given by white line recognition or the like. However, when these automatic steering vehicles lose the route guidance means, acquisition of reference information for performing automatic steering control stops.
[0003]
For example, Japanese Unexamined Patent Publication No. Hei 10-31799 describes a technology that has a means for detecting the distance to a side wall in addition to a CCD camera for detecting a white line, and performs steering control along the side wall when the white line cannot be detected. Have been. However, when steering control is performed along the side wall, only the lateral deviation is observed, and it is not possible to know in advance whether or not the side wall is continuous. It is desired to obtain
[0004]
[Problems to be solved by the invention]
When white line recognition by a CCD camera is used as a route for guiding an auto-steering vehicle as described above, especially at night, the visibility of the white line depends on the lighting conditions of the road, so that it is difficult to see far away. On the other hand, when the road surface is wet, the recognition of the white line tends to be interrupted due to the reflection of illumination, and the route may be intermittently lost.
[0005]
The present invention has been made in view of the above-mentioned problems, and its purpose is to make it easy to recognize even when the route for automatic steering is lost, even at night or when the road surface is damp. By estimating the route based on the vehicle, the automatic steering control can be continued when the condition of losing the route continues intermittently, and the driver has enough time to respond even if the condition of losing the route continues It is an object of the present invention to provide a traveling route generating device capable of performing the following.
[0006]
[Means for Solving the Problems]
In order to achieve the above object, according to the present invention, there is provided an image pickup means for picking up an image of a scene ahead of a host vehicle, a default path recognizing means for recognizing a predetermined path from the image pickup scene, and a steering angle of the host vehicle based on the recognized default path. An automatic steering control means for controlling a vehicle, and performing a follow-up traveling by automatic steering along a traveling road in a traveling route generating apparatus for a vehicle. A landscape vector sequence recognizing means for recognizing as a route, a route reproduction data calculating means for calculating the position / direction relationship between the recognized landscape vector sequence and the default route as route replay data, and a default for judging whether or not the default route has been recognized. The route recognition determining means, and when it is determined that the default route is not recognized, the position / form of the default route based on the recognized scenery vector sequence and the calculated route reproduction data. Characterized in that a, a default path estimation means for estimating a.
[0007]
【The invention's effect】
Therefore, according to the present invention, even when the vehicle that is automatically steering based on the recognized default route loses track of the automatic steering route, the estimated route is supplied, so that the vehicle loses track. When the vehicle continues intermittently, the automatic steering control can be continued, and even when the state of losing sight of the route continues, it is possible to secure a margin time that the driver can cope with.
[0008]
BEST MODE FOR CARRYING OUT THE INVENTION
(First embodiment)
First, the configuration will be described.
FIG. 1 is a configuration diagram illustrating a vehicle to which the traveling route generation device according to the first embodiment is applied.
[0009]
In the figure, 1 is a CCD camera, 2 is an image processing CPU, 3 is a GPS antenna, 4 is map data, 5 is a gyro sensor, 6 is a wheel speed sensor, 7 is a steering angle sensor, 8 is an own-vehicle traveling information detecting device, 9 is a navigation system device, 10 is an automatic steering controller, 11 is a vehicle control CPU, and 12 is a travel route generation device.
[0010]
The CCD camera 1 recognizes a predetermined route ahead through the image processing CPU 2 and calculates a yaw angle and a position shift of the own vehicle with respect to the predetermined route. Although not particularly shown, usually, these values measured by the image processing CPU 2 are transmitted to the vehicle control CPU 11, and a command is output to the automatic steering controller 10 so as to control the following of the predetermined route.
[0011]
The predetermined route and the landscape vector are recognized by the landscape vector sequence recognizing means 14 in the travel route generating device 12 by a series of processes of the CCD camera 1 and the image processing CPU 2. The default route recognizing means 13 in the travel route generating device 12 may be configured to be supplied by a known device different from the CCD camera 1 and the image processing CPU 2.
[0012]
The information acquired by the GPS antenna 3 and the map data 4 is supplied to the route reproduction data calculation means 15 of the traveling route generation device 12 through the navigation system device 9 to provide the shape of the road ahead and the approximate position on the road.
[0013]
The gyro sensor 5, the wheel speed sensor 6, and the steering angle sensor 7 measure the change in the yaw angle of the own vehicle and the displacement in the vertical and horizontal directions by the own vehicle running information detecting device 8 and supply them to the running route generating device 12. The vehicle control CPU 11 is a part that performs calculations of various logics required for the automatic steering control vehicle.
[0014]
The route reproduction data calculation unit 15 calculates, as the route reproduction data, the position / direction relationship between the scenery vector sequence recognized by the landscape vector sequence recognition unit 14 and the default route recognized by the default route recognition unit 13 as the route reproduction data. Output to the estimating means 16. Then, the estimated route estimating unit 16 estimates a default route based on the landscape vector sequence and the route reproduction data, and outputs the default route to the vehicle control CPU 11.
[0015]
Next, the operation will be described.
[Traveling route generation control processing]
The travel route generation control processing by the travel route generation device 12 will be described based on the flowchart of FIG.
[0016]
In step SA1, the driving of the traveling route generation device 12 is started.
[0017]
In step SA2, the center of the white line imaged by the CCD camera 1 is set as the traveling route, and the traveling route normally recognized by the default route recognizing means 13 is recognized as the default route.
[0018]
In step SA3, the scenery vector sequence recognizing means 14 uses the feature points Gn-2, Gn-1, Gn, Gn + 1, Gn + 2,. . . , Gn + n are detected. The detection of these three-dimensional positions may be obtained by a triangular method using a stereo camera, or may be obtained in a pseudo manner based on a difference between two frames captured by a monocular camera as described below.
[0019]
For example, a method of obtaining the position of the same one-point street lamp shown in FIGS. 4 and 5 from the imaging result at time t and the imaging result at time t + 1 will be described.
[0020]
Here, for the sake of simplicity, the deviation from the predetermined route of the own vehicle at time t and the yaw angle are both 0, and the vertical axis of the vehicle coordinate system is set to the x axis and the horizontal direction is set to the y axis. An equal situation will be described.
[0021]
In FIG. 4, the position of the vehicle at time t and the position at time t + 1 are shown based on the coordinate system at time t. The values to be obtained are the horizontal distance y at time t and the vertical distance x with the streetlight at time t + 1.
[0022]
θ1 is an angle around the yaw angle with the streetlight at time t, and is obtained from the lens specification of the CCD camera 1 in correspondence with the point at which the streetlight is recognized, as shown in FIG.
[0023]
θ2 is the angle around the yaw angle with the streetlight at time t + 1, and is obtained in the same manner as θ1.
[0024]
θ3 is a yaw angle change at time t and time t + 1 of the own vehicle, and is obtained by a yaw rate sensor mounted on the own vehicle. It should be noted that θ3 is the number of streetlight points (eg, Gn + 10, Gn + 11, Gn + 12) that are considered to be sufficiently far away from the point sequence extending toward the vanishing point when a plurality of streetlights are recognized, and at times t and t + 1, A street lamp point where the difference between the yaw angles obtained on the imaging screen between Gn + 10 and Gn + 11 and between Gn + 11 and Gn + 12 does not change within the imaging resolution), and sees the amount simultaneously moved in the imaging screen between times t and t + 1. You may ask for it.
[0025]
X corresponds to the distance traveled in the x-axis direction at time t at time t and time t + 1. If θ2 is sufficiently small, it may be approximated as the distance traveled, but ΔX / cos Δθ is integrated by the yaw angle change Δθ every minute time from time t to time t + 1 and the travel distance ΔX. Calculate by value. However, when a clear steering is being performed, it is assumed that the vehicle is performing a circular motion, and the steering angle, the lateral G, the yaw rate sensor and the like are used to approximate a steady circular turning state at every minute time and widely known. May be determined by the vehicle motion.
[0026]
The lateral distance Yoffset is the amount of movement in the y-axis direction at times t and t + 1, and is detected based on the amount of movement of the vehicle in the y-axis direction within the default route during recognition of the default route, and is relative to the vehicle route during non-recognition of the default route. Xysin θy is obtained by calculating the yaw angle θy and the traveling distance Xy of the vehicle one by one.
[0027]
These values are represented by the following equations (1) and (2).
Tanθ1 = y / (X + x). . . (1)
Tan (θ2 + θ3) = (y-Yoffset) / x. . . (2)
By solving this simultaneous equation, x and y are obtained.
[0028]
Similarly, in the height direction, the following equations (3) and (4) are established from FIG. What is obtained is the height z and the distance x, and θz1 and θz2 are angles in the pitch angle direction obtained from the vertical position in the imaging screen at times t and t + 1, respectively. It should be noted that the effect of determining θz1 and θz2 may be removed by referring to the pitch rate sensor and the sufficiently distant street lamps Gn + 10, Gn + 11, and Gn + 12 in the same manner as described above.
tan θz1 = z / (X + x). . . (3)
tan θz2 = z / x. . . (4)
X and z are obtained by solving this simultaneous equation.
[0029]
Note that x must be the same as the one calculated when calculating the position of the streetlight in the horizontal direction y and the one calculated when calculating the position of the streetlight in the height direction z. If θ1 and θ2 in the equations (1) and (2) are close to 0 depending on the positional relationship, the change between the time t and the time t + 1 is not sufficient. The magnitudes of θ1 and θ2 in equation (2) are compared with the absolute angles of θz1 and θz2 in equations (3) and (4), and x calculated using the larger angle is given priority. Used for For example, when the streetlight is almost directly above the vehicle, θ1 and θ2 are close to 0, and it is determined that θz1> θ1, θz2> θ2, and is calculated by the equations (3) and (4) using θz1 and θz2. That is, y is obtained by substituting the obtained x into the equations (1) and (2).
[0030]
The streetlights Gn, Gn + 1, Gn + 2,. . . The vertical positions xGn, xGn + 1, xGn + 2, xGn + 3,. . . , XGn + n and horizontal positions yGn, yGn + 1, yGn + 2, yGn + 3,. . . , YGn + n and heights zGn, zGn + 1, zGn + 3,. . . , ZGn + n.
[0031]
Note that, on the still screen, between the streetlights Gn and Gn + 1, between Gn + 1 and Gn + 2, between Gn + 2 and Gn + 3,. . . Is determined to be a continuous streetlight train by determining whether or not the yaw angle difference and the pitch angle difference continuously change smoothly, and the streetlights Gn, Gn + 1, Gn + 2,. . . Assuming that the vertical distances in the x-direction are equal and the heights in the z-direction are equal, a streetlight model may be provided in the screen to improve the accuracy.
[0032]
Specifically, Gn, Gn + 1, Gn + 2 closest to the vehicle among the street lights, x and z calculated from some street lights, and a change amount in the y direction according to the detected distance of the predetermined route (or the navigation system) The amount of change obtained by the map data 4 obtained from the device 9) is Gn, Gn + 1, Gn + 2, Gn + 3,. . . , Gn + n, the variation due to the recognition accuracy of the detected streetlight is corrected.
[0033]
The street lamps are Gn, Gn + 1, Gn + 2, Gn + 3,. . . , Gn + n, the values of Gn, Gn + 1, Gn + 2 closest to the vehicle among the streetlights and the values of x and z calculated from some of the streetlights are slightly changed as shown in FIG. Accurate identification of the value of x may be performed by calculating the position error with respect to the streetlight point sequence in the screen according to the added minute change as shown in FIG. Also, by comparing the horizontal position shift to the streetlight vector caused by the change in the curvature in the y-axis direction with the streetlight row on the screen, the curvature of the streetlight row is matched by performing the curvature matching with the streetlight vector in the same manner as when the white line is recognized. It may be identified.
[0034]
The streetlights Gn, Gn + 1, Gn + 2,. . . , The vector connecting Gn and Gn + 1 is GVn, and the vector connecting Gn + 1 and Gn + 2 is GVn + 1. . . And so on, the streetlight vectors GVn, GVn + 1, GVn + 2, GVn + 3,. . . , Gvn + n are obtained as shown in FIG.
[0035]
Returning to FIG. 2, in step SA4, the route reproduction data calculation means 15 obtains the xyz position, the yaw angle, and the pitch angle with respect to the predetermined route of each streetlight vector, and stores the route difference matrix as the route reproduction data.
[0036]
In addition, a vector difference matrix indicating the relationship between the vector GVn following the streetlight Gn closest to the host vehicle and GVn + 1 and the relationship between GVn + 1 and GVn + 2 is obtained and stored.
[0037]
Since this vector difference matrix always has a streetlight vector in the longitudinal direction of the own vehicle, that is, the x-axis direction 0, when one end of GVn is out of the imaging range, it is virtually based on the vector difference matrix from GVn + 1. Used to reproduce GVn. The reproduction of the streetlight vector outside the imaging range is performed one by one using the vector difference matrix and the streetlight vector within the imaging range.
[0038]
At step SA5, the route reproduction difference vector calculated at the previous step is stored in preparation for use in the processing after the next routine.
[0039]
In step SA6, the recognized streetlight vectors GVn, GVn + 1,. . . On the other hand, based on the difference matrix indicating the relationship between the default route obtained as the route reproduction data and the streetlight vector in step SA4, the default route is reproduced as shown in FIG. By comparing the vehicle position with the vehicle position, the vehicle position deviation and the yaw angle with respect to the predetermined route are calculated.
[0040]
In step SA7, it is determined based on a signal sent from the default route recognizing means 13 whether the automatic steering vehicle has lost (or lost) the default route for performing the follow-up control. If the route has not been lost, the process proceeds to step SA8. If the route has been lost, the process proceeds to step SA9.
[0041]
In step SA8, based on the predetermined route, the route information and the displacement of the vehicle relative to the route and the yaw angle are output as usual.
[0042]
In step SA9, the route information (curve start point and curvature information) obtained in step SA6, the lateral position deviation with respect to the own vehicle, and the yaw angle are output. For example, when the default route recognizing unit 13 recognizes only the lateral position deviation close to the own vehicle, the default route recognizing unit 13 supplies the yaw angle and the route information of the estimated route to the lateral position deviation of the default route. Only information that cannot be recognized may be supplied.
[0043]
Next, effects will be described.
In the travel route generation device according to the first embodiment, the following effects can be obtained.
[0044]
(1) When the default route is lost, the default route is reproduced for the recognized streetlight vector based on the difference matrix indicating the relationship between the default route and the streetlight vector obtained as route reproduction data. Since the position deviation and the yaw angle of the own vehicle with respect to the predetermined route are calculated, the vehicle that is performing the automatic steering based on the predetermined route that recognizes the position and direction relationship with the recognized default route is used as the automatic steering route. Even if you lose track of the route, the estimated route is supplied, so if the condition of losing the route continues intermittently, automatic steering control can be continued, and the driver can respond even if the condition of losing the route continues A sufficient spare time can be secured.
[0045]
(2) Recognized streetlight vectors Gn, Gn + 1, Gn + 2,. . . , The vector connecting Gn and Gn + 1 is GVn, and the vector connecting Gn + 1 and Gn + 2 is GVn + 1. . . Thus, the streetlight vectors GVn, GVn + 1, GVn + 2, GVn + 3,. . . , Gvn + n. These streetlight vectors GVn, GVn + 1, GVn + 2, GVn + 3,. . . , Gvn + n can be recognized even in a state where the recognition of the default route is interrupted, such as at night when the predetermined route has uneven illumination or when the road surface is wet and the illumination is reflected, and can be recognized in the extension of the imaging scene. Since a long distance such as a streetlight can be seen, effective route estimation information can be supplied while the route is lost. Also, the streetlight vectors GVn, GVn + 1, GVn + 2, GVn + 3,. . . , Gvn + n, the object to be imaged is hard to be blocked by an obstacle, and hard to deviate from the imaging range. Therefore, when the route is lost, the vehicle can be easily deviated from the predetermined route and evacuated and guided.
[0046]
(3) When a plurality of streetlight vector sequences are recognized, the distance from the default route, the continuity of the streetlight vector change, and the degree of matching of the shape with the default route are each evaluated, and the result of multiplying the results is evaluated. The suitability of each streetlight vector sequence is calculated based on the above, and priorities are assigned to the streetlight vectors in the order of higher suitability, so that it is possible to reduce the recognition of streetlight sequences that are drawn into unnecessary branches, Even when the streetlight train is drawn into the evacuation space installed on one side, it is possible to select a streetlight train having the shape closest to the predetermined route, for example, a streetlight train parallel to the predetermined route along the center of the road or the opposite lane.
[0047]
(4) The default route is reproduced based on the difference matrix indicating the relationship between the streetlight vector and the default route obtained as route reproduction data for the recognized streetlight vector. By comparing the own vehicle position with the own vehicle position, the own vehicle position deviation and the yaw angle with respect to the predetermined route are calculated, so that a continuous route can be estimated when the predetermined route is lost.
[0048]
(Second embodiment)
The configuration of the travel route generation device according to the second embodiment is the same as that of the first embodiment, and a description thereof will be omitted.
[0049]
Next, the operation will be described.
[Traveling route generation control processing]
Next, a traveling route generation control process performed by the traveling route generation device 12 will be described with reference to a flowchart of FIG.
[0050]
Steps SB1 and SB2 are the same as SA1 and SA2 in FIG.
[0051]
In step SB3, the scenery vector sequence recognizing means 14 causes the streetlight vector sequences GVn, GVn + 1, GVn + 2,. . . , GVn + n, and when there are a plurality of streetlight vector columns, the plurality of streetlight vector columns. . . 1GVn + n,. . . , 2GVn + n,. . . , NGVn + n.
[0052]
In step SB4, the streetlight vectors GVn, GVn + 1,. . . It is determined whether or not a situation occurs in which the streetlight associated with the vector is concealed by a signboard or the like as shown in FIG. If concealment has occurred, the process proceeds to step SB5. If concealment has not occurred, the process proceeds to step SB6.
[0053]
In step SB5, if the object concealing the streetlight vector is a signboard, its edge is recognized, and if it is a round sign, the most recognizable point such as its center point is recognized as a temporary streetlight point GVn + atemp. A streetlight vector, a difference matrix between the temporary streetlight vectors shown in FIG. 13, and a route difference matrix between the temporary streetlight vector and the predetermined route are obtained, and the processing is performed in the same manner as the streetlight vector.
[0054]
At the time when the signboard or the like is recognized, the positional relationship between the streetlight that is expected to be concealed and the streetlight concealed object such as the signboard is detected before the concealment of the streetlight, and the position of the signboard and other recognizable streetlights is detected. By reproducing the street lamp concealed from the relationship, the process may proceed by virtually recognizing the street lamp vector.
[0055]
In step SB6, of the streetlight vectors recognized in step SB3, recalculation is performed in order to maintain the calculation processing relating to the streetlight vector already calculated in the previous loop with high accuracy, and recognition in which recognition accuracy is improved can be performed. In this case, the stored various information is updated.
[0056]
In step SA7, when a plurality of streetlight vector sequences are recognized, the distance from the default route, the continuity of the streetlight vector change, and the degree of matching of the shape with the default route are evaluated, and the evaluation results are multiplied. The suitability of each streetlight vector sequence is calculated based on the result. Then, priorities are assigned to the streetlight vectors in the order of higher suitability.
[0057]
When the map data 4 is recognized, the street light vector sequence may be prioritized based on the road shape of the extension of the predetermined route and the recognition result of the street light vector sequence.
[0058]
In step SB8, it is determined whether or not the recognized streetlight vector sequence is a section in which a route difference vector from the predetermined route has been obtained. The process proceeds to step SB9 for the streetlight vector for which the route difference vector has been determined, and proceeds to steps S12 and S18 for the streetlight vector for which the route difference vector has not been determined.
[0059]
Steps SB9, SB10, and SB11 are the same as steps SA4, SA5, and SA6 in FIG.
[0060]
In step SB12, the streetlight vector sequence obtained in step SB3 is compared with the map data 4 to determine the degree of coincidence. As for the degree of coincidence, the degree of coincidence is recalculated only for a section in which a path difference vector from the default path cannot be calculated for a streetlight vector sequence having a degree of conformity that is equal to or greater than the predetermined degree in the path for which the degree of conformity has been calculated in step SB7. Alternatively, a result obtained by calculating a streetlight vector sequence having the highest matching degree may be used.
[0061]
In step SB13, if the degree of coincidence obtained in step SB12 is high, the reliability of the streetlight vector is determined to be high, and the process proceeds to step SB14. If the degree of coincidence is low, the reliability of the streetlight vector is determined to be low, and the process proceeds to step SB20.
[0062]
In step SB14, it is determined whether or not the route selected as a target as a result of the matching in step SB12 is a straight line. If it is a straight line, the process proceeds to step SB17. If it is not a straight line, the process proceeds to step S15.
[0063]
In step BS15, the street light train selected in step SB12 and the map data 4 are further shifted longitudinally back and forth to obtain a cross-correlation to determine a point having the highest correlation, thereby setting a corner start point on the navigation map. To detect.
[0064]
In step SB16, the one with higher accuracy is selected from the road curvature information estimated by the streetlight train and the curvature information included in the map data 4. Specifically, the recognition interval of the streetlight is compared with the interval data of the position point sequence of the navigation, and the narrower interval is selected as having higher accuracy. However, if the map data 4 already knows information corresponding to the road curvature information, the map data 4 is selected.
[0065]
In step SB17, using the route reproduction data calculated in step SB10, the predetermined route is reproduced by the recognized streetlight vector which is the target of the route estimation.
[0066]
In step SB18, the height of the road is estimated based on the fact that z described in step SA3 is constant.
[0067]
In step SB19, when the climax is detected in step SB18, it is determined that the top of the uphill is approaching, and the process proceeds to step SB20. If it is detected that there is a swell in the height of the road, the pitch angle of the CCD camera 1 should be adjusted so as to keep track of the results of the white line and streetlight imaging results by the CCD camera 1 when passing through the swell. It is stored as reference information to be adjusted.
[0068]
In step SB20, it is determined whether or not a traveling route for a predetermined time is secured by combining the default route and the estimated route. The traveling route here indicates information on the minimum lateral position deviation and the yaw angle, and with respect to the estimated route, at least one streetlight vector or a correction vector based on a signboard or sign always stays completely in the screen. Say. If the traveling route has been secured, the process proceeds to step SB22, and if not, the process proceeds to step SB21.
[0069]
In step SB21, a warning is issued to the driver because it is predicted that the route will be lost. The warning may be changed according to the remaining distance (or remaining time), or may be instructed one by one to the automatic steering controller 10 that controls the automatic steering in order to take appropriate measures for the remaining distance (remaining time).
[0070]
Steps SB22, SB23 and SB24 are the same as steps SA7, SA8 and SA9 in FIG.
[0071]
Next, effects will be described.
In the travel route generation device of the second embodiment, the following effects can be obtained in addition to the effects of the first embodiment.
[0072]
(5) Since the streetlight vector is compared with the map data 4, it is possible to select and determine a highly reliable landscape vector including the default route and the streetlight vector of the unmatched portion. In addition, the accuracy of the path estimation of the uncollated part is improved.
[0073]
(6) The streetlight vector sequence is compared with the map data 4 to determine the degree of coincidence between the streetlight vector sequence and the road curvature information estimated from the streetlight sequence. Since the information with the higher accuracy is selected, even if the route ahead is lost, the road curvature information that works effectively to ensure the following performance of the auto-steering vehicle is continuously and accurately supplied. Becomes possible.
[0074]
(7) The most recognizable point of the concealed object concealing the streetlight vector is recognized as a temporary streetlight point GVn + atemp, and a route difference matrix between the temporary streetlight vector and the predetermined route is determined. In this case, the once-recognized scenery vector can be geometrically reproduced, and the estimated route based on the scenery vector can be continuously reproduced even when the predetermined route is lost.
[0075]
(8) Since the predetermined height of the recognized streetlight vector is stored and the height of the road is estimated, a change in the pitch angle of the vehicle is predicted in advance, and the pitch angle of the CCD camera 1 is set. It can be adjusted, and it is possible to prevent the scenery vector from being out of the imaging range together with the recognition of the landscape vector at the top of the undulation where it is difficult to recognize the white line.
[0076]
(9) When it is predicted that the traveling route will be lost, a warning is issued to the driver and a command is transmitted to the automatic steering controller 10, so that the automatic steering operation is canceled before the route supply is actually stopped. It is possible to secure a margin time for prompting the user.
[0077]
(Other embodiments)
Although the embodiment of the present invention has been described based on the first and second embodiments, the specific configuration of the present invention is not limited to the present embodiment, and the gist of the invention is described. Even a design change or the like within a range not departing from the present invention is included in the present invention.
[Brief description of the drawings]
FIG. 1 is a configuration diagram illustrating a vehicle to which a traveling route generation device according to a first embodiment is applied.
FIG. 2 is a flowchart illustrating a flow of a traveling route generation control process according to the first embodiment.
FIG. 3 is a perspective view showing a method for detecting a feature point such as a street lamp in a landscape.
FIG. 4 is an explanatory diagram showing a method for calculating a streetlight vector.
FIG. 5 is an explanatory diagram showing a method of calculating a streetlight vector.
FIG. 6 is an explanatory diagram showing lens specifications of a CCD camera.
FIG. 7 is an explanatory diagram showing a method of calculating a streetlight vector.
FIG. 8 is an explanatory diagram showing a method of calculating a streetlight vector.
FIG. 9 is an explanatory diagram showing a method of reproducing a default route.
FIG. 10 is an explanatory diagram showing a method of reproducing a default route.
FIG. 11 is a flowchart illustrating a flow of a traveling route generation control process according to the second embodiment.
FIG. 12 is an explanatory diagram showing a method of reproducing a predetermined route when a streetlight is hidden by a signboard.
FIG. 13 is an explanatory diagram illustrating a method of reproducing a predetermined route when a streetlight is hidden by a signboard.
[Explanation of symbols]
1 CCD camera
2 Image processing CPU
3 GPS antenna
4 Map data
5 Gyro sensor
6 Wheel speed sensor
7 Steering angle sensor
8 Self-vehicle traveling information detection device
9 Navigation system device
10 Automatic steering controller
11 Vehicle control CPU
12 Travel route generation device
13 Default route recognition means
14 Landscape vector sequence recognition means
15 Route reproduction data calculation means
16 Default route estimation means

Claims (9)

Imaging means for imaging a scene in front of the vehicle;
A default route recognizing means for recognizing a default route from an imaging scene;
Automatic steering control means for controlling the steering angle of the vehicle based on the recognized default route;
With
In a traveling route generation device of a vehicle that performs a following traveling by automatic steering along a traveling road,
Landscape vector sequence recognition means for recognizing a vector sequence connecting characteristic points in the imaged landscape as a landscape vector sequence;
Route reproduction data calculation means for calculating the position / direction relationship between the recognized landscape vector sequence and the predetermined route as route reproduction data;
A default route recognition determining means for determining whether or not the default route has been recognized;
Default route estimating means for estimating the position and orientation of the default route based on the recognized landscape vector sequence and the calculated route reproduction data when it is determined that the default route is not recognized;
A travel route generation device, comprising: The travel route generating device according to claim 1,
The scenery vector sequence recognition means limits an area to be recognized based on a traveling road, captures a characteristic point sequence arranged in a predetermined route extension direction in an imaging scene, and forms a line connecting the point sequence. A travel route generating device, which is a means for recognizing a scene vector sequence. The travel route generating device according to claim 1 or 2,
When there are a plurality of landscape vector strings extending in the direction of the default route of the vehicle in parallel, the route reproduction data calculation means processes a recognized landscape vector string having a high degree of conformity with the default route among the recognized scene vector strings. A travel route generating apparatus for calculating a position / posture relationship between each landscape vector in the selected landscape vector sequence and a predetermined route. The travel route generation device according to any one of claims 1 to 3,
When it is determined that the default route is not recognized, the default route estimating unit estimates the default route based on the recognized landscape vector sequence and the calculated route reproduction data, and determines a lateral position of the own vehicle with respect to the default route. A travel route generation device, which is means for estimating a deviation and a yaw angle. The travel route generation device according to any one of claims 1 to 4,
A navigation system that identifies a road shape around the own vehicle and a position of the own vehicle on the road;
A scene vector trust that compares the obtained road shape with the shape of the recognized scene vector sequence to determine whether the scene vector sequence extending beyond the recognized predetermined route is along the traveling road. Gender determination means,
A travel route generation device, comprising: The travel route generating device according to claim 5,
The landscape vector reliability determining means detects a corner start point based on a result of comparing the shape of the landscape vector with the information on the shape of the road ahead, and uses the street lamp as curvature information of a curve following the detected corner start point. A travel route generating device, which is a means for selecting one of the curvature information estimated from the column and the curvature information estimated from the information on the shape of the road ahead with higher accuracy. The travel route generation device according to any one of claims 1 to 6,
The landscape vector column recognition means, a landscape vector concealed object detection unit that detects a landscape vector concealed object that blocks the landscape vector column,
A scenery vector concealment object feature point recognition unit that temporarily recognizes a detected characteristic point of the scenery vector concealment object as a calculation target point of the scenery vector sequence,
A travel route generation device comprising: The travel route generation device according to any one of claims 1 to 7,
The landscape vector sequence recognizing means stores a predetermined height of a recognized landscape point, and estimates a road undulation shape based on the information, and a road undulation shape estimation unit;
An imaging angle adjustment unit that adjusts the imaging angle of the imaging unit based on the estimated undulating shape of the road,
A travel route generation device comprising: The travel route generation device according to any one of claims 1 to 8,
The predetermined route estimating means predicts that the supply of the traveling route will be stopped based on the recognized visibility distance of the predetermined route and the visibility distance combined with the recognition state of the estimated route based on the landscape vector, and transmits the result to the automatic steering control means. A driving route generating device.

Images