JP2012242937A - Vehicular road shape recognition method and device, and recording medium - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a vehicular road shape recognition method and device capable of frequently calculating a more accurate road shape, and a recording medium.SOLUTION: The vehicular road shape recognition method includes: determining the recognition classification as to whether an object is a moving object or a stationary object on the basis of relative speed of the object and self-vehicle speed; extracting object unit data effective to recognize a road shape on the basis of a determination result of the recognition classification; extracting a horizontal position of a stationary object with the shortest distance, in the vehicle width direction, to the self-vehicle side from among the extracted object unit data and determining a stationary object, which is positioned within a range apart from the horizontal position of the stationary object closest to the self-vehicle in the vehicle width direction by a predetermined distance and has the shortest direct distance from the self-vehicle, as an original point; then forming data on a road side object group by connecting data pieces where the distance monotonously increases as a connection condition from the original point and grouping them; and recognizing a road edge on the basis of the formed data on the road side object group.

Description

  The present invention relates to a vehicle road shape recognition method and apparatus, and a recording medium.

  Conventionally, for example, Patent Document 1 proposes a method for recognizing a road on which the vehicle travels. Specifically, in Patent Document 1, segmented measurement data is sorted in the order of angle, and after eliminating excess data under the condition of the shape of the segment and the vicinity of the moving object, a segment effective for road shape recognition is selected. Based on the roadside object group (left) and the roadside object group (right) obtained after grouping from the left angle direction to the right angle direction and from the right angle direction to the left angle direction, and further excluding suspicious things about the farthest segment, Recognize the road edge.

Japanese Patent No. 3427809

  However, in the above conventional technique, the base point for grouping roadside objects may not be correct, and the grouping of roadside objects may not be accurately performed. As a result, it is not possible to calculate the road edge more accurately and frequently, and it is desirable to recognize a more accurate road shape.

  In view of the above points, an object of the present invention is to provide a vehicular road shape recognition method and apparatus, and a recording medium that can calculate a more accurate road shape frequently.

  In order to achieve the above object, according to the first aspect of the present invention, when transmitting a transmission wave over a predetermined angle range in the vehicle width direction and recognizing the road shape around the vehicle based on the reflected wave, To recognize. That is, based on the reflected wave, object unit data including at least the distance to the object is acquired corresponding to the vehicle width direction angle, and the moving object is obtained based on the relative speed of the object obtained based on the reflected wave and the own vehicle speed. Or the recognition type of stop object. Then, based on the determination result of the recognition type, object unit data effective for recognizing the road shape is extracted. After that, from the extracted object unit data, the lateral position of the stopped object whose distance in the vehicle width direction is closest to the own vehicle side is extracted, and the lateral position of the stopped object closest to the own vehicle side in the vehicle width direction is extracted. A stop object that is located within a predetermined distance and that has the smallest direct distance from the vehicle is determined as a starting point. Then, in both directions from the left angle direction to the right angle direction and from the right angle direction to the left angle direction, the data for which the distance is monotonously increasing as connection conditions are connected from the starting point and grouped to form roadside object group data. The road edge is recognized based on the data of the formed roadside object group.

  As a result, it is possible to prevent the start of group connection starting from a stopped object having the smallest angle with respect to the vehicle width direction as a reference and further located away from the host vehicle. In addition, when the roadside is seen double, it is possible to form a roadside object group by preferentially grouping from an inner stop object without starting from a distant stop object. For this reason, the accuracy of recognition of the road edge is improved, and as a result, a more accurate road shape can be calculated frequently.

  In the invention according to claim 2, when forming the data of the roadside object group, it is included in the first connection condition range (a) and the first connection condition range, and the range is smaller than the first connection condition range. The second connection condition range (b) is set, and the stop object included in both the first connection condition range and the second connection condition range starting from the starting point is connected to the starting point. Then, by connecting the stopped objects included in both the first connection condition range and the second connection condition range with the stopped object after the connection as the next base point, and repeating this to group the stopped objects, Form data.

  As described above, since the first connection condition range and the second connection condition range are set at the time of grouping, even if the stop objects are not included in the second connection condition range even if included in the first connection condition range, Not connected. For this reason, it is possible to prevent the stationary object having a large distance difference but a small angular difference from being compared and connected in advance by comparing the angular order of the stationary objects. Therefore, the group connection can be made closer to the actual road shape, and as a result, the accuracy of road edge recognition can be improved.

  In the invention according to claim 3, when recognizing a road edge based on roadside object group data, after forming a plurality of roadside object group data, an intersection of a circle passing through the roadside object group and an axis in the vehicle width direction Is recognized for each of a plurality of roadside object groups, and road edges are recognized using only roadside object groups corresponding to intersections located within a predetermined threshold distance from the intersection on the own vehicle side in the vehicle width direction. .

  Thereby, the roadside object group far from the own vehicle in the vehicle width direction can be excluded from the road end recognition. Therefore, since the calculated average road edge is recognized so as to pass through each road side group on the own vehicle side, the accuracy of road edge recognition can be improved.

  On the other hand, the invention according to claim 4 is an example of an apparatus for realizing the vehicle road shape recognition method according to claim 1. The invention according to claim 5 is an example of an apparatus for realizing the vehicle road shape recognition method according to claim 2, and the invention according to claim 6 is an object for the vehicle according to claim 3. It is an example as an apparatus for implement | achieving a road shape recognition method. These vehicle road shape recognition apparatuses can also exhibit the same effects as described above.

  Further, as in the seventh aspect of the invention, the function of realizing the recognition means of the vehicle road shape recognition device by the computer system can be provided as a program that is activated on the computer system side, for example. In the case of such a program, for example, it is recorded on a computer-readable recording medium such as a magneto-optical disk, a CD-ROM, a hard disk, a flash memory, etc., and is used by being loaded into a computer system and started as required. it can. In addition, the ROM or backup RAM may be recorded as a computer-readable recording medium, and the ROM or backup RAM may be incorporated into a computer system and used.

  In addition, the code | symbol in the bracket | parenthesis of each means described in this column and the claim shows the correspondence with the specific means as described in embodiment mentioned later.

It is a block diagram which shows the structure of the vehicle control apparatus with which this invention was applied. It is explanatory drawing which shows the outline | summary of a road shape recognition process. (A) is explanatory drawing which shows the content of segmentation of measurement data, (b) is explanatory drawing which shows the content of grouping of segment data. It is explanatory drawing which shows the content which connects a stop object in order from the stop object of a starting point. It is explanatory drawing which shows the response | compatibility to the farthest segment in a roadside thing group (left). It is explanatory drawing which shows a countermeasure when the farthest segment of a roadside thing group (left) and a roadside thing group (right) overlaps. It is explanatory drawing which shows the content which recognizes a road edge as a set of line segments. (A) is explanatory drawing which shows the content which recognizes a road edge using all the segments, (b) is explanatory drawing which shows the content which recognizes a road edge using the segment below a threshold value.

(First embodiment)
Next, a vehicle control device 1 to which the present invention is applied will be described with reference to the drawings. This vehicle control device 1 is mounted on an automobile and outputs a warning when an obstacle exists in a predetermined area in a predetermined situation, or controls the vehicle speed according to the preceding vehicle (preceding vehicle). It is.

  FIG. 1 is a block diagram of the system. The vehicle control device 1 is configured around a computer 3. The computer 3 mainly includes a microcomputer and includes an input / output interface (I / O) and various drive circuits and detection circuits. Since these hardware configurations are general, detailed description thereof is omitted.

  The computer 3 inputs predetermined detection data from a distance / angle measuring device 5, a vehicle speed sensor 7, a brake switch 9, and a throttle opening sensor 11 as an obstacle detection device for a vehicle. Further, the computer 3 outputs predetermined drive signals to the alarm sound generator 13, the distance indicator 15, the sensor abnormality indicator 17, the brake driver 19, the throttle driver 21 and the automatic transmission controller 23.

  The computer 3 further includes an alarm volume setting unit 24 for setting an alarm volume, an alarm sensitivity setting unit 25 for setting sensitivity in an alarm determination process to be described later, a cruise control switch 26, and a steering sensor 27 for detecting an operation amount of a steering wheel (not shown). And a yaw rate sensor 28. Further, the computer 3 includes a power switch 29, and starts predetermined processing when the power switch 29 is turned on.

  Here, the distance / angle measuring device 5 includes a transmission / reception unit 5a and a distance / angle calculation unit 5b. From the transmission / reception unit 5a, laser light is transmitted forward of the vehicle around a predetermined optical axis (center axis). Based on the time until the reflected light is detected by the distance / angle calculation unit 5b, the distance to the object ahead is detected based on the discontinuous sweep irradiation (scanning) in the predetermined angle range and output. It is a device that detects the distance r. In addition to those using laser light, radio waves such as millimeter waves, ultrasonic waves, or the like may be used. Also, the scanning method is not limited to scanning the transmission unit. For example, the reception unit It may be one that scans.

  With this configuration, the computer 3 performs an alarm determination process for alarming when an obstacle exists in a predetermined alarm area for a predetermined time. Examples of the obstacle include a front vehicle traveling in front of the host vehicle, a front vehicle that is stopped, or an object on the roadside (such as a guardrail or a column object). The computer 3 also performs so-called inter-vehicle control, which controls the vehicle speed according to the situation of the preceding vehicle by outputting drive signals to the brake driver 19, the throttle driver 21, and the automatic transmission controller 23. ing.

  Next, the internal configuration of the computer 3 will be described as a control block. The data of the distance r and the scan angle θ output from the distance / angle calculator 5b of the distance / angle measuring device 5 is sent to the data grouping block 41, and the center of the laser radar is set to the origin (0, 0), and the vehicle After being converted into XZ Cartesian coordinates where the width direction is the X axis and the vehicle forward direction is the Z axis, the converted data is grouped to form a segment. This segmentation will be described later. The data of the object unit segmented by the data grouping block 41 is output to the object recognition block 43 and the road shape recognition block 45.

  In the object recognition block 43, the relative speed (Vx, Vz) of the obstacle such as the front vehicle based on the own vehicle position based on the temporal change of the center position of the object output from the data grouping block 41. Is required. Further, in the object recognition block 43, the object is a stop object from the vehicle speed (own vehicle speed) V output from the vehicle speed calculation block 47 based on the detection value of the vehicle speed sensor 7 and the above obtained relative speed (Vx, Vz). A recognition type as to whether the vehicle is a moving object is obtained, and an object that affects the traveling of the host vehicle is selected based on the recognition type and the center position of the object, and the distance indicator 15 displays the distance. Note that (W, D) indicating the size of the object is (width, depth), respectively.

  Whether or not the data obtained in the object recognition block 43 is an abnormal range value is detected by the sensor abnormality detection block 44. If the data is an abnormal range value, the sensor abnormality indicator 17 displays that fact. Is made. On the other hand, the road shape recognition block 45 recognizes the road shape based on the data of the center position of the object output from the grouping block 41 and the data obtained in the object recognition block 43. Details of this road shape recognition processing will be described later. The data obtained in the road shape recognition block 45 is output to the preceding vehicle determination block 53.

  Further, the steering angle is calculated by the steering angle calculation block 49 based on the signal from the steering sensor 27, and the yaw rate is calculated by the yaw rate calculation block 51 based on the signal from the yaw rate sensor 28. In a curve radius (curvature radius) calculation block 63, a curve radius (curvature radius) R is calculated based on the vehicle speed from the vehicle speed calculation block 47, the steering angle from the steering angle calculation block 49, and the yaw rate from the yaw rate calculation block 51. To do. In the preceding vehicle determination block 53, the curve radius R and the recognition type obtained in the object recognition block 43, the center position coordinates (X, Z), the object size (W, D), and the relative speed (Vx, Vz). And the preceding vehicle is selected based on the road shape data obtained in the road shape recognition block 45, and the distance Z and relative speed Vz for the preceding vehicle are obtained.

  Then, the inter-vehicle distance control unit and the alarm determination unit block 55 include the distance Z to the preceding vehicle, the relative speed Vz, the host vehicle speed Vn, the preceding vehicle acceleration, the object center position, the object width, the recognition type, and the setting state of the cruise control switch 26. On the basis of the depression state of the brake switch 9, the opening from the throttle opening sensor 11, and the sensitivity set value by the alarm sensitivity setting unit 25, it is determined whether or not to issue an alarm if it is an alarm determination, and vehicle speed control if it is a cruise determination. Determine the contents. As a result, if an alarm is required, an alarm generation signal is output to the alarm sound generator 13. If the cruise is determined, a control signal is output to the automatic transmission controller 23, the brake driver 19 and the throttle driver 21 to perform necessary control. When these controls are executed, necessary display signals are output to the distance indicator 15 to notify the driver of the situation.

  Next, the operation | movement concerning recognition of the road shape performed in the vehicle control apparatus 1 comprised as mentioned above is demonstrated according to the flowchart of FIG. In S1000, which is the first step in FIG. 2, distance / angle measurement data is read. This processing is executed by the distance / angle measuring device 5, but the distance / angle measurement data for one scan is taken in. The scan cycle is 100 msec, and data is taken every 100 msec.

  In subsequent S2000, segmentation of stop object data (object unit data) is performed. This segmentation is executed by the data grouping block 41. As described above, the distance / angle measurement data is converted from the polar coordinate system to the XZ orthogonal coordinate system, and the converted data is grouped to create a segment. (Roadside group) is formed.

  Specifically, as shown on the left side of FIG. 3A, a starting point selection process for generating a roadside object group as a segment is performed. This starting point selection process is a process of selecting which stop object among the stop objects sorted in the order of angles is to be the starting point of segment formation.

Specifically, after sorting in angular order, in the left angle direction,
(1) The lateral position of the innermost (own side) stop object is extracted in the left area. (2) The lateral position is close to (1) and the direct distance to the own vehicle is the shortest. With respect to the above condition (1) starting from the stopped object, the lateral position of the stopped object whose distance in the vehicle width direction is closest to the host vehicle is extracted. As for the condition (2), the “direct distance from the own vehicle” is not the distance from the own vehicle in the vehicle width direction but the shortest distance from the own vehicle to the stop object.

  On the other hand, the right angle direction is the reverse of the above conditions. That is, in (1), the lateral position of the innermost roadside stop group with respect to the own vehicle in the right area is extracted.

  As shown on the left side of FIG. 3 (a), for example, in the right angle direction of the host vehicle, the host vehicle is in the X-axis direction within a range on the right side of the tilt of 6 ° with respect to the Z-axis direction around the host vehicle. In addition, there are stop objects from “0” to “8” in a range of 1 m to 8 m in width and a distance from the own vehicle to 30 m in the Z-axis direction. This range is indicated by point hatching on the left side of FIG.

  Among the stopped objects, the “0” stopped object has the smallest angle with respect to the X axis, but the distance in the X axis direction is the farthest from the own vehicle. In addition, each stationary object from “1” to “8” exists within a range from the position (X_min) of “8” having the smallest distance in the X-axis direction to a position 2 m away, for example. .

  When such a situation is applied to the above conditions (1) and (2), the lateral position (X_min) in the X-axis direction of the “8” stop object is extracted (condition (1)). Then, the stop object of “1” whose lateral position is close to “8” and the distance from the own vehicle is the smallest is determined (condition (2)). As a result, it is possible to prevent the start of group connection from a place away from the host vehicle, such as a “0” stop object. Moreover, when the road side is seen double, it can group preferentially from an inner road side row | line | column.

  Then, a roadside group (segment) is formed with the starting point determined as described above as a starting point. This will be described with reference to FIG. FIG. 4 shows an example of connection of each stationary object located in the right angle direction with respect to the own vehicle.

  As shown in FIG. 4, the starting point is the stop object closest to the host vehicle (“1” on the left side of FIG. 3A). The stop objects included in both the connection condition range b having a small value are connected in order. That is, the stopped objects are compared in order of angle, and when a stopped object satisfying the connection condition range a is found, a stopped object satisfying the connection condition range b is further searched and connected. Then, the stopped object included in the connection condition range a and the connection condition range b is searched and connected using the connected stopped object as the next base point. In this way, the stopped objects included in the connection condition range a and the connection condition range b are sequentially searched and connected using the stopped object after connection as a base point.

  In FIG. 4, there are two stopped objects in the connection condition range a. However, since there are stopped objects included in the connection condition range b, the stopped objects are connected. By repeating this, stationary objects are connected one after another to form a roadside object group.

  In FIG. 4, the connection condition range b is located on the left side (Z-axis side) of the connection condition range a, but this is an example of the position of the connection condition range b with respect to the connection condition range a. For example, the connection condition range b may be located at the center of the connection condition range a in the vehicle width direction (X-axis direction). Thus, what is necessary is just to set suitably about where the connection condition range b is located in the connection condition range a.

  As described above, the point data of the stationary object are integrated to obtain the segment data. This segment data is a rectangular area having two sides parallel to the X-axis and the Z-axis and set to a size including an integrated point set, as shown on the right side of FIG. The data content is the data (W, D) of two sides for indicating the center coordinates (X, Z) and the size. Note that the coordinates of the left and right ends of this area are also stored as data.

  In subsequent S3000, object recognition is performed. This object recognition is executed by the object recognition block 43, and the contents thereof are as described above. The subsequent processing after S4000 is processing executed by the road shape recognition block 45. In S4000, the center position of the segment obtained in S2000 is converted into polar coordinates and sorted in angular order.

  In subsequent S5000, based on the angle obtained in S4100, the segments meeting the conditions are grouped from the left angle direction to the right angle direction to form a roadside object group (left). This will be described with reference to FIG. In this embodiment, since the road shape is recognized based on the delineator installed on the roadside, first, for example, in order to eliminate segment data other than the delineator such as an extra signboard or a vehicle, either one of the following: Segments that satisfy the exclusion conditions are judged to be signs or vehicles and are eliminated.

Segment exclusion condition with large width W: width W ≧ 1.2 m and aspect ratio D / W <5
Segment exclusion condition when recognition type is near moving object: center distance is ΔX ≦ 2m, ΔZ ≦ 2m
Next, there is a segment that satisfies the following connection condition that the distance Z is monotonically increasing and satisfies the following connection condition from the left angle direction to the right angle direction with respect to the segment remaining after being excluded using this exclusion condition. In the meantime, they are connected and grouped in order to form a roadside group (left).

Connection conditions: Center-to-center distance is ΔX ≦ 3.5m, ΔZ ≦ 55m
When the distance decreases or when the distance does not satisfy the connection condition even if the distance increases monotonically, another new roadside object group (left) is formed. Here, even if there is only one component segment, the roadside object group (left) is used. However, when the road edge is recognized, only the roadside object group (left) having three or more component segments is used. Therefore, in the situation shown in FIG. 3 (b), as a result of grouping the data remaining after exclusion under the above exclusion conditions, No.1 to No.4 roadside object groups (left) were obtained. Since the roadside object group (left) having three or more constituent segments is only No.1, this roadside object group (left) No.1 is used for road edge recognition.

  In S5100, the distance Z is the largest among the segments constituting the roadside object group (left) (in this case, the roadside object group (left) means No. 1), that is, the farthest segment. Determines if it is on the left or right side of the road. Although details of this determination will be described later, if it is determined that the road is on the right side, it is excluded from the roadside object group (left). FIG. 5A shows an example of a roadside object group (left) having three or more constituent segments and a segment on the right side of the road mixed. As you can see from this figure, when grouping from the left angle direction to the right angle direction while the distance increases monotonically, it is almost always a problem if you determine whether the farthest segment is really the left side of the road. Absent. This is because it is almost impossible to assume a situation in which the segment immediately before the farthest segment (hereinafter referred to as “second farthest segment”) is also on the right side.

  Therefore, the following determination is made for this farthest segment. As shown in FIG. 5B, first, the remaining constituent segments excluding the farthest segment are connected by a smooth curve, and it is determined whether or not the farthest segment exists in the vicinity of this curve. Here, the curve passes through two points of the “most recent segment” having the smallest distance Z and the second farthest segment and obtains a circle orthogonal to the X axis. Since the center for orthogonal to the X-axis exists on the X-axis and two points on the circumference are known, a circle equation can be derived.

  If the distance ΔX between the circle and the farthest segment in the X-axis direction is less than 1.5 m, it is determined that the segment is on the left side of the road and is included in the roadside object group (left). Is 1.5 or more, it is determined that the segment is on the right side of the road, and is excluded from the roadside object group (left). The distance between the farthest segment and the circle, that is, the length of the perpendicular line from the farthest segment to the circle, may be determined, but in reality, the distance in the X-axis direction as described above. There is no particular problem if only ΔX is considered.

  In subsequent S6000 and S6100, the contents executed in S5000 and S5100 are executed in the left-right direction. That is, in S6000, the roadside object group (right) is formed by grouping segments that meet conditions from the right angle direction to the left angle direction based on the angle obtained in S4000. The conditions for excluding unnecessary signs are the same as those on the left. Then, from the right angle direction to the left angle direction with respect to the segment remaining after exclusion, the distance Z monotonically increasing and sequentially satisfying the connection condition are connected and grouped to form a roadside object group (right) To do. The connection conditions are the same as in the left case, and only the road segment group (right) having three or more constituent segments is used for road edge recognition.

  In S6100, for the farthest segment in the roadside object group (right), the left side or right side of the road is determined in the same manner as in the left side. Exclude from group (right). When the roadside object group (left) and the roadside object group (right) are obtained in this way, in the subsequent S7000, the farthest segment in the roadside object group (left) and the farthest segment in the roadside object group (right) are determined. In the same case, that is, as shown in FIG. 6 (a), when one farthest segment belongs to the roadside object group (left) and also belongs to the roadside object group (right), As shown in 6 (b), the farthest segment is excluded. Of course, if there is no overlap, such processing is not performed.

  In S8000, the right and left ends of the road are recognized based on the roadside object group (left) and the roadside object group (right) having three or more constituent segments. In the present embodiment, as shown in FIG. 7, the left and right ends of the road are recognized as a set of line segments by interpolating between the constituent segments of each roadside object group. Furthermore, by calculating the intersection with the X-axis using the interpolation result between roadside object group data, and interpolating to this intersection, the road shape from the vicinity of the vehicle position is recognized as a set of line segments. I am doing so.

  As described above, in the vehicle control device 1 of the present embodiment, in the road shape recognition process, the lateral position of the innermost (own vehicle side) stop object is extracted from the extracted stop objects, and this is extracted from the own vehicle. The feature is that the starting point is a stationary object that is close to the lateral position and has the smallest direct distance to the vehicle. This makes it possible to prevent the start of group connection starting from a stopped object that is the smallest in order of the sort angle and is located away from the vehicle. In addition, when the roadside is seen double, the grouping can be performed preferentially from the inner roadside row. For this reason, the accuracy of recognition of the road edge is improved, and as a result, a more accurate road shape can be calculated frequently.

  Further, it is characterized in that the stop object included in the connection condition ranges a and b is connected using the stop object as the starting point determined as described above as a starting point. In this way, since the stopped objects included in the narrow connection condition range b are connected, the group connection can be made closer to the actual road shape. For this reason, the accuracy of road edge recognition can be improved. Further, by comparing the stop objects in the order of angles, it is possible to prevent a stop object having a large distance difference but a small angle difference from being compared and connected first. Of course, since two connection condition ranges are provided to double the connection conditions, the current performance can be maintained.

  And since a preceding vehicle is determined using the road shape recognized well in this way and the inter-vehicle distance control and the inter-vehicle distance warning are performed, these controls will be carried out satisfactorily.

  In the present embodiment, the distance / angle measuring device 5 corresponds to a radar unit, and the data grouping block 41, the object recognition block 43, and the road shape recognition block 45 of the computer 3 correspond to a recognition unit. However, the grouping block 41 and the object recognition block 43 of the data among them correspond to the object recognition means, and the road shape recognition block 45 serves as the effective data extraction means, the starting point selection means, the roadside object group data formation means, and the road edge recognition means. Equivalent to.

  Further, the connection condition range a corresponds to the first connection condition range, and the connection condition range b corresponds to the second connection condition range.

(Second Embodiment)
In the present embodiment, parts different from the first embodiment will be described. The present embodiment is characterized in that a segment (stop object group) on the own vehicle side is preferentially used to connect the segments, thereby generating a road edge table.

  For example, when the average road edge is obtained using all the segments, the average of the road edge varies in the vehicle width direction (X-axis direction) as shown in FIG. Therefore, in the present embodiment, grouping is performed using the vehicle side (inner side) segment. Note that the grouping according to the present embodiment corresponds to the processing of S5000 and S6000 of the first embodiment.

  Specifically, as shown in FIG. 8 (b), the intersection of the circle passing through each segment and the X axis is obtained, and only the segment having the intersection within a range away from the innermost intersection by a predetermined threshold is obtained. To perform grouping. As a result, the segment farthest from the vehicle in the X-axis direction in FIG. 8B is excluded from grouping. Therefore, the calculated average road edge is recognized so as to pass through each segment on the inner side (vehicle side).

  As described above, in this embodiment, the roadside object group on the same curve on the own vehicle side (inside) is preferentially used for grouping. In other words, because the road edge table that preferentially uses the vehicle side (inner side) segment is generated, when there are multiple segments in the vehicle width direction (X-axis direction) and the road side looks double Even in such situations, the accuracy of road edge recognition is improved. Therefore, a more accurate road shape can be calculated frequently.

(Other embodiments)
The present invention is not limited to the above embodiment, and can be implemented in various forms without departing from the gist of the present invention. For example, it can be changed as the following (1) to (4).

  (1) For example, in the above embodiment, the farthest segment belonging to both roadside object groups is excluded in S7000, but there is a possibility that the overlapping farthest segment may belong to any of the roadside object group data in both the left and right directions. You may determine whether it is high and may include it in the roadside thing group data of the side with the high possibility of belonging. In this way, the duplicated farthest data can be utilized as much as possible. For the determination, for example, the technique in S5100 and S6100 may be used. That is, the magnitude of the distance ΔX in the X-axis direction between the position of the farthest segment and each circle corresponding to both roadside object groups is determined, and included in the smaller distance ΔX. For example, a dead zone may be provided between both circles, and may be included in the roadside object group closer to the dead zone.

  (2) The content of the above embodiment or the above (1) is a countermeasure from the viewpoint of utilizing the farthest data as much as possible. However, from the viewpoint of avoiding erroneous determination as much as possible, the farthest in S5100 and S6100 It is also possible to exclude a segment unconditionally. In this way, erroneous determination due to using the farthest data can be reliably avoided.

  (3) In the above embodiment, the road edges are recognized as a set of line segments by interpolating between the segments constituting the roadside object group. However, the interpolation method is not limited to this, for example, the segment It is also possible to interpolate between them with a curve and recognize the road edge as a smooth curve.

  (4) In the above embodiment, the distance / angle measuring device 5 using laser light is employed as the “radar means”, but it has already been described that a millimeter wave or the like may be used. For example, when a millimeter wave FMCW radar or Doppler radar is used, the distance information from the reflected wave (received wave) to the preceding vehicle and the relative speed information of the preceding vehicle can be obtained at a time. As in the case, the process of calculating the relative speed based on the distance information becomes unnecessary.

DESCRIPTION OF SYMBOLS 1 Vehicle control apparatus 3 Computer 5 Distance and angle measuring device 41 Grouping block 43 Object recognition block 45 Road shape recognition block

Claims (7)

A vehicle road shape recognition method for irradiating a transmission wave over a predetermined angle range in the vehicle width direction and recognizing a road shape around the vehicle based on the reflected wave,
Based on the reflected wave, object unit data including at least the distance to the object is acquired corresponding to the vehicle width direction angle,
Effective for recognizing a road shape based on a determination result of the recognition type based on a determination result of the recognition type by determining a recognition type of a moving object or a stopped object based on the relative speed of the object obtained based on the reflected wave and the own vehicle speed. Extract object unit data,
From the extracted object unit data, the lateral position of the stopped object whose distance in the vehicle width direction is located closest to the own vehicle is extracted, and from the lateral position of the stopped object closest to the own vehicle in the vehicle width direction. The starting point is a stationary object that is located within a predetermined distance and has the smallest direct distance from the vehicle.
For both directions from the left angle direction to the right angle direction and from the right angle direction to the left angle direction, the data for the monotonically increasing distance as connection conditions are connected from the starting point to form grouping data of roadside objects, A road shape recognition method for a vehicle, wherein a road edge is recognized based on data of the formed roadside object group.   When forming the data of the roadside object group, a first connection condition range (a) and a second connection condition range that is included in the first connection condition range and whose range is smaller than the first connection condition range ( b) is set, the stop object included in both the first connection condition range and the second connection condition range starting from the starting point as a starting point and connected to the starting point is connected to the starting point. By connecting stop objects included in both the first connection condition range and the second connection condition range with the next stop object as the next base point, and repeating this, grouping the stop objects, the data of the roadside object group is obtained. The vehicle road shape recognition method according to claim 1, wherein the vehicle road shape recognition method is formed.   When recognizing the road edge based on the roadside object group data, after forming a plurality of the roadside object group data, the intersection of the circle passing through the roadside object group and the axis in the vehicle width direction is Recognizing the road edge using only a roadside object group corresponding to an intersection located within a range that is a predetermined threshold away from the intersection on the own vehicle side in the vehicle width direction. The vehicle road shape recognition method according to claim 1, wherein the vehicle road shape recognition method is performed. Radar means (5) for irradiating a transmission wave within a predetermined angle range in the vehicle width direction and detecting an object based on the reflected wave;
Recognizing means (41, 43, 45) for recognizing the road shape ahead of the vehicle based on the detection result by the radar means (5),
The radar means (5) acquires object unit data including at least a distance to the object based on the reflected wave, corresponding to the vehicle width direction angle,
The recognition means (41, 43, 45)
Object recognition means (41, 43) for determining a recognition type of a moving object or a stopped object based on the relative speed of the object obtained based on the reflected wave and the own vehicle speed;
Effective data extraction means (45) for extracting the object unit data effective for recognizing the road shape based on the recognition result by the object recognition means (41, 43);
From the object unit data extracted by the effective data extraction means (45), the lateral position of the stopped object whose distance in the vehicle width direction is located closest to the own vehicle is extracted, and the highest in the vehicle width direction. Start point selection means (45) for determining a stop object that is located within a predetermined distance from the lateral position of the stop object on the own vehicle side and has the smallest direct distance from the own vehicle as a start point;
For both the left angle direction to the right angle direction and the right angle direction to the left angle direction, data whose distances are monotonously increased as connection conditions are connected from the starting point determined by the starting point selecting means (45) and grouped. Roadside object group data forming means (45) for forming roadside object group data,
Road edge recognition means (41, 43, 45) for recognizing the road edge based on the roadside object group data in both directions formed by the roadside object group data formation means (45). A vehicle road shape recognition device.   The roadside object group data forming means (45) includes a first connection condition range and a second connection condition range that is included in the first connection condition range and whose range is smaller than the first connection condition range. The stop object included in both the first connection condition range and the second connection condition range starting from the starting point determined by the starting point selecting means (45) and starting from the starting point is connected to the starting point. The roadside object is formed by connecting the stopped objects included in both of the first connection condition range and the second connection condition range by using the stopped object after the connection as the next base point, and grouping the stopped objects by repeating this. The vehicle road shape recognition apparatus according to claim 4, wherein group data is formed. The roadside object group data forming means (45) forms a plurality of data of the roadside object group,
The road edge recognizing means (41, 43, 45) obtains an intersection between a circle passing through the roadside object group and an axis in the vehicle width direction for each of the plurality of roadside object groups, and most automatically in the vehicle width direction. 6. The vehicle road according to claim 4 or 5, wherein the road edge is recognized using only a roadside object group corresponding to an intersection located within a range away from a vehicle-side intersection by a predetermined threshold. Shape recognition device.   A computer-readable recording medium storing a program for causing a computer system to function as recognition means of the vehicle road shape recognition apparatus according to claim 4.

Images