JP2017090649A - Road characteristic determination device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a road characteristic correction device which corrects a road center, a lane center, etc. on the basis of travel information.SOLUTION: Travel data acquisition means 102 acquires travel data including a travel track of a plurality of vehicles and the like which actually travel. Grouping means 104 groups travel track lines of a plurality of vehicles by similarity and determines whether each group is associated with a center line on the basis of distance from the center line. Center line correction means 106 corrects the number of center lines on the basis of whether each group is associated with the center line. Thus, a center line estimated from a road shape and the like can be corrected by a travel track of a vehicle which actually travels and be made further correctly.SELECTED DRAWING: Figure 31

Description

  The present invention relates to an apparatus for determining road characteristics based on three-dimensional measurement data of a surface shape measured while traveling on a road or the like.

  If the shape of a road is specified by measurement and road shape data such as a road edge, a road center, and a lane center can be obtained, it can be used for automatic driving of a car, driving assistance control, and the like.

  For example, Patent Document 1 discloses a method that can accurately measure the slope of a road. According to this method, it is possible to measure the inclination depending on the location of the road and continuously obtain the change in inclination.

  Further, Patent Document 2 discloses a system that acquires the speed and steering angle of an automobile with a sensor and estimates the curvature of a road based on these data. Accordingly, the curvature of the road can be estimated and used for avoiding a collision.

  Further, Patent Document 3 discloses an apparatus that acquires movement on a road as three-dimensional trajectory data and connects a straight line and an arc in a curve portion of the road with a relaxation curve (clothoid curve).

JP-A-11-1000080 JP2012-131696 JP2014-160064

  In any of the above prior arts, correction of the road feature once generated to improve the accuracy is not taken into consideration, nor is there any suggestion for this.

  SUMMARY OF THE INVENTION An object of the present invention is to solve the above problems and provide an accurate road feature correction apparatus.

  Some independently applicable features of the present invention are listed below.

(1) (2) A road feature correction device according to the present invention is a road feature correction device that corrects a center line estimated based on a shape of a road, and includes a plurality of mobile bodies that have actually traveled on the road. Travel data acquisition means for acquiring travel data, and travel trajectory lines based on the travel data of the plurality of mobile objects are grouped together in close proximity, and each group is related to the center line based on the distance from the center line. Grouping means for determining whether or not to perform, and centerline correction means for correcting the number of the centerlines based on whether or not each group is associated with a centerline.

  Therefore, the number of center lines estimated based on the shape can be corrected.

(3) In the road feature correction device according to the present invention, when a center line correction unit finds a group that is not related to the center line, the center line correction unit generates a new center line based on the travel locus line of the group. It is a feature.

  Therefore, a correct center line can be added based on the traveling locus.

(4) The road feature correction device according to the present invention is characterized in that when a group related to two or more center lines is found, the center line correction means performs correction to make the center line in the group one. Yes.

  Therefore, it is possible to delete the center line that is erroneously estimated.

(5) In the road feature correcting apparatus according to the present invention, the center line correcting means may generate one center line by either generating a new center line or selecting one of the center lines. It is a feature.

  Therefore, the number of center lines can be corrected correctly.

(6) The road feature correction apparatus according to the present invention is characterized in that when the centerline correction means finds a group related to only one centerline, the centerline correction means does not correct the number of centerlines in the group. .

  Therefore, it is possible to maintain the number of centerlines that are correctly estimated.

(7) In the road feature correction device according to the present invention, the centerline correction means uses either the centerline of the group as it is or generates a new centerline based on the travel locus line belonging to the group. Therefore, the number of center lines is not changed.

  Therefore, it is possible to maintain the number of centerlines that are correctly estimated.

(8) The road feature correction device according to the present invention is characterized in that the center line correction means does not perform correction when the ratio or number of the group's travel locus lines occupies a predetermined value or less.

  Therefore, erroneous correction based on information with a small number of samples can be avoided.

(9) The road feature correction apparatus according to the present invention is characterized in that, when the center line correction means generates a new center line, the new center line is generated by offsetting the original center line.

  Therefore, an appropriate center line can be generated.

(10) The road feature correction apparatus according to the present invention is characterized in that the center line includes at least a road center line or a lane center line.

  Therefore, the road center and the lane center can be corrected correctly.

(11) (14) A road feature correction device according to the present invention is a road feature correction device that corrects a center line including a straight line portion, a clothoid curve portion, and an arc portion estimated based on the shape of a road. A travel data acquisition means for acquiring travel data of a plurality of mobile bodies that have traveled on the road, and a clothoid curve indicating the most frequent position of the direction change operation start of the plurality of mobile bodies indicated in the travel data of the plurality of mobile bodies Included is a clothoid curve start position calculation means for calculating the start position, and a clothoid curve correction means for correcting the estimated clothoid curve based on the calculated clothoid curve start position.

  Therefore, the clothoid curve can be corrected based on the actual travel information.

(12) (15) The road feature correction device according to the present invention is characterized in that the clothoid curve correction means corrects the estimated clothoid curve in consideration of the clothoid curve end position.

  Therefore, the clothoid curve can be corrected based on the actual travel information.

(13) (16) (17) (18) The road feature correction device according to the present invention includes the most frequent position of the direction change operation start and the brake start of the plurality of moving bodies indicated in the traveling data of the plurality of moving bodies. Attribute addition means for assigning the most frequent position as the attribute of the center line is further provided.

  Therefore, information suitable for automatic operation control and the like can be given.

(19) (20) A road feature correction device according to the present invention is a road feature correction device that corrects a center line of a branching portion or an intersection portion estimated on the basis of a shape of a road, and is actually a branching of the road. Traveling data acquisition means for acquiring traveling data of a plurality of moving bodies that have traveled a section or intersection, grouping means for grouping traveling trajectory lines indicated in the traveling data of the plurality of moving bodies, and the branching section Alternatively, center line correcting means for correcting the center line of the intersection with a representative traveling locus line generated based on the grouped traveling locus lines is provided.

  Therefore, it is possible to correct the center line of the branch part or the intersection part correctly.

(21) In the road feature correcting device according to the present invention, the grouping means generates a travel locus line from the departure lane toward the entry lane based on a combination of the departure lane that exits from the intersection and the entry lane that enters the intersection. It is characterized by grouping.

  Therefore, the correction based on the actual trajectory can be performed.

(22) The road feature correction apparatus according to the present invention is characterized in that the center line correction means generates a representative travel locus line based on the locus points of the travel locus lines in the group.

  Therefore, the correction based on the actual trajectory can be performed.

(23) The road feature correction apparatus according to the present invention is characterized in that a representative traveling locus in a right turn or left turn exclusive lane is generated.

  Therefore, the trajectory of the right turn or left turn lane at the intersection can be clarified.

(24) The road feature correction device according to the present invention is characterized in that the centerline correction means generates a representative travel locus line by generating a clothoid curve connecting the straight line portion and the straight line portion of the branch destination at the branch portion. It is said.

  Therefore, correction can be performed with a smooth locus.

(25) (26) The road feature correction apparatus according to the present invention includes a recording unit that records feature data, a reference unit that finds a portion having a road feature similar to the road feature of the correction target portion, and the center of the found portion. Center line correcting means for correcting or generating the center line of the correction target portion based on the line.

  Therefore, correction can be performed based on the already generated center line.

(27) In the road feature correcting apparatus according to the present invention, the road feature compared by the reference means includes at least one of a straight part, a clothoid curve part, a shape of an arc part, a shape in a transverse section, and a shape in a longitudinal section. It is characterized by.

  Therefore, the similarity can be appropriately determined.

  In the embodiment, “travel data acquisition means” corresponds to step S201.

  In the embodiment, “grouping means” corresponds to step S204 and step S286.

  In the embodiment, “center line correction means” corresponds to step S216, step S299, step S302, step S359, and the like.

  In the embodiment, “clothoid curve start position calculating means” corresponds to step S227.

  In the embodiment, “clothoid curve correcting means” corresponds to step S239.

  In the embodiment, “attribute assigning means” corresponds to step S231.

  In the embodiment, “reference means” corresponds to steps S354 and S355.

  The “program” is a concept that includes not only a program that can be directly executed by the CPU, but also a source format program, a compressed program, an encrypted program, and the like.

It is a functional block diagram of the road feature determination apparatus by 4th Embodiment of this invention. It is a hardware configuration of a road feature determination device. It is a flowchart of a road edge part / center determination process. It is a flowchart of a cross-section setting process. It is an example of three-dimensional measurement data. It is an example of the point cloud data projected on the cross section. It is a flowchart of a road end point extraction process. It is a flowchart of a road end point extraction process. It is a figure for demonstrating a road end point extraction process. It is a functional block diagram of the road characteristic determination apparatus by 5th Embodiment. It is a flowchart of a division line / lane center line determination process. It is a figure for demonstrating a division line extraction process. It is a figure for demonstrating the division line determination process by another example. It is a functional block diagram of the road characteristic determination apparatus by 6th Embodiment. It is a flowchart of a center line connection process. It is a flowchart of a center line connection process. It is a flowchart of a center line connection process. It is a figure for demonstrating the connection of the straight line in a plane. . It is a figure for demonstrating the connection of the straight line in a longitudinal cross section. . It is a figure for demonstrating the connection of a straight line and a circular arc. It is a figure for demonstrating the connection of a straight line and a circular arc. It is a figure for demonstrating the connection of an arc. It is a functional block diagram of the road characteristic determination apparatus by 7th Embodiment. It is a flowchart of a branch process. It is a flowchart of a branch part specification and center line complementation process. It is a flowchart of a branch part specification and center line complementation process. It is a figure for demonstrating the connection of the center line in a branch part. It is a figure for demonstrating the connection of the center line in a branch part. It is a figure for demonstrating the connection of the center line in a branch part. It is a figure for demonstrating the connection of the centerline in an intersection. It is a functional block diagram of the road feature correction device according to the first embodiment. It is a hardware configuration of a road feature correction device. It is a flowchart of a centerline correction process. It is a flowchart of a centerline correction process. It is a flowchart of a centerline correction process. It is a figure which shows the centerline C and the driving | running track which are estimated. It is a figure for demonstrating distance calculation of the centerline C and a driving | running | working locus | trajectory. It is a figure which shows the method of producing | generating a centerline from a running locus. It is a functional block diagram of the road feature correction device by a 2nd embodiment. It is a flowchart of a clothoid curve correction process. It is a flowchart of a clothoid curve correction process. It is a figure which shows the detail of the centerline of a curve part. It is a figure for demonstrating the determination process of a steering start position. It is a flowchart of a clothoid curve correction process. It is a flowchart of a clothoid curve correction process. It is a flowchart of a clothoid curve correction process. It is a figure which shows the representative locus | trajectory calculation by the least squares method. It is a figure which shows the shift of the starting position of a clothoid curve. It is a figure which shows the correction process of a clothoid curve. It is a functional block diagram of the road feature correction device by a 3rd embodiment. It is a flowchart of the centerline correction | amendment in a branch part and an intersection part. It is a flowchart of the centerline correction | amendment in a branch part and an intersection part. It is a flowchart of the centerline correction | amendment in a branch part and an intersection part. It is a figure which shows the index of a crossing part. It is a figure which shows the centerline production | generation of a right turn lane. It is a figure which shows correction | amendment of the centerline in a cross | intersection part and a branch part. It is a functional block diagram of the road feature correction device by a 4th embodiment. It is a flowchart of the correction process based on a similar part. It is a figure which shows the division of a center line. It is a figure which shows the comparison of a planar shape. It is a diagram showing a comparison of the shape in the longitudinal section, It is a figure which shows the production | generation method of a cross section.

1. First embodiment
1.1 Functional Block Diagram FIG. 31 shows a functional block diagram of the road feature correction apparatus according to one embodiment of the present invention. In this embodiment, the road feature correction device corrects road feature data including a center line estimated from a road shape or the like.

  The travel data acquisition means 102 acquires travel data including travel trajectories of a plurality of vehicles that have actually traveled. The grouping means 104 groups the traveling locus lines of a plurality of automobiles by those adjacent to each other. Further, whether each group is related to the center line is given based on the distance from the center line. Center line correction means 106 corrects the number of center lines based on whether each group is associated with a center line.

In this way, the center line estimated from the road shape or the like can be corrected with a travel locus of a car or the like that has actually traveled to be more accurate.

1.2 Hardware Configuration FIG. 32 shows the hardware configuration of the road feature determination apparatus. A memory 32, a display 34, a hard disk 36, a CD-ROM drive 38, and a keyboard / mouse 40 are connected to the CPU 30.

  An operating system 42 and a road feature correction program 45 are recorded on the hard disk 36. The road feature correction program 45 performs its function in cooperation with the operating system 42.

These programs are those recorded in the CD-ROM 46 and installed in the hard disk 36 via the CD-ROM drive 38. It may be downloaded and installed from a server device (not shown) via the Internet.

1.3 Centerline Correction Processing FIGS. 33 to 35 are flowcharts of the road feature correction program 45. The CPU 30 acquires the center line in the road feature data (step S201). In this embodiment, road feature data including a center line (road center line or lane center line) estimated based on the road shape is acquired. Here, the road center line means a line connecting the centers of the road widths as shown in the cross section of FIG. 13A, for example. The lane center line is a line connecting the centers of the lanes as shown in the cross section of FIG. 13D. What is necessary is just to acquire the road characteristic data recorded, for example on CD-ROM.

  Further, the CPU 30 acquires travel data when an automobile or the like actually travels on the road. For the correction process, it is preferable that there are a large number of vehicle driving data. In this embodiment, the travel data includes a travel locus (a data group of travel positions acquired at each time obtained by a GPS receiver), presence / absence of steering operation at each time and steering angle, presence / absence of brake operation at each time, and the like. Contains information. As the running data, data (CAN data or the like) recorded by a GPS receiver or a measuring device mounted on an automobile can be used.

  Next, the CPU 30 connects the point data of the traveling locus to generate a traveling locus line (step S203). For example, as shown in FIG. 36A, traveling locus points Pa, Pb, Pc... Are connected to generate a traveling locus line L3. Similarly, travel locus lines L1, L2, etc. are also generated. In FIG. 36A, only three travel trajectory lines are shown, but many travel trajectory lines are generated.

  The CPU 30 determines whether or not the generated travel locus line is related to the estimated center line C. An average distance obtained by averaging the vertical distance between the travel locus point of the travel locus line and the center line C over a predetermined range is obtained. FIG. 37 shows a method for calculating the average of the vertical distance between the travel locus line L and the center line C. The average value of the vertical distances is calculated by calculating the average value of the vertical distances d1, d2,... Di between the travel locus points Pf, Pg, Pn and the center line C.

  Further, if the average value of the vertical distance is within a predetermined distance (for example, within 1.5 m which is half of the lane width), the CPU 30 attaches the attribute of being related to the center line C. If the average value of the vertical distances is greater than the predetermined distance, the attribute that is not related to the center line C is added. In the case of FIG. 36A, the attributes of the traveling locus lines L1 and L3 are not related and the traveling locus line L2 is associated.

  As shown in FIG. 36B, the travel locus line L5 may be related to the two center lines C1 and C2.

  Next, the CPU 30 finds a group of a plurality of travel locus lines and groups them (step S204). For example, in the case shown in FIG. 36C, groups G1 and G2 are generated. The above process is performed for all the traveling tracks.

  Next, the CPU 30 counts the number of travel locus lines included in each group (step S207). If the number of travel trajectory lines (which may be a ratio with respect to the total number of travel trajectory lines) is less than a predetermined value, sample data is short, and the data of this group is not used for correction (step S208).

  If the value is equal to or greater than the predetermined value, the attribute of the group is determined (step S209). First, when it is not related to the center line, it can be determined that there is another center line at that position. Therefore, the CPU 30 generates a new center line in steps S210 to S212.

  First, the CPU 30 calculates the center line in the straight line portion for the travel locus lines belonging to the group. For example, as shown in FIG. 38A, it is assumed that there is a travel locus line. As shown in FIG. 38B, a cross section PS at a predetermined interval is set for the travel locus line. Further, an intersection point of the cross section PS and the travel locus line is obtained as a virtual point IP (step S210). Furthermore, as shown in FIG. 38C, the CPU 30 sets the maximum rectangle LC that can surround all the virtual points IP (step S211). A straight line DC at the center of the rectangle LC is set as a center line (step S212).

  Furthermore, as shown in FIG. 38D, the CPU 30 slides the existing center line C so as to overlap the generated center line DC in the straight line portion. If the curved portion is slid as it is, consistency such as curvature cannot be obtained. Therefore, the curved portion is reduced (enlarged) and slid so as to have an appropriate curvature.

  In step S209, if the group is associated with two or more center lines, it is determined that a plurality of center lines that should originally be one have been estimated. Therefore, the CPU 30 narrows the center line to one in steps S213 to S217.

  Also in this case, a new center line DC is generated as shown in FIGS. 38A to 38D (steps S213 to S216). Further, the CPU 30 deletes the associated original center line. In this way, the number and position of centerlines can be corrected.

  Instead of generating a new center line, only the center line closest to the generated center line DC as shown in FIG. 38C may be left and the other center lines in the group may be deleted.

In step S209, if the group is associated with only one center line, it is determined that the center line is correctly estimated, and no special processing is performed. Note that a new center line may be generated and the original center line may be deleted by the processing of FIGS. 38A to 38D.

1.4 Other
(1) In the above embodiment, traveling data is obtained from a CD-ROM or the like. However, you may make it acquire from a server apparatus via the internet etc.

(2) In the above-described embodiment, the road feature square device is configured as a stand-alone PC. However, you may comprise as a server apparatus. In this case, road feature data to be corrected (including centerline data) may be transmitted from a terminal device connected via the Internet or the like to a server device that is a road feature correction device. The corrected road feature data is transmitted from the server device to the terminal device.

(3) In the above-described embodiment, the description has been made on the automobile traveling on the road. However, it can be applied to all self-propelled moving bodies that move by power, such as motorcycles and motorbikes. Furthermore, the present invention can be applied to a mobile body having no power such as a bicycle or a human body. The same applies to other embodiments.

(4) The above-described embodiments and modifications can be implemented in combination with other embodiments as long as they do not contradict the essence.

2. Second embodiment
2.1 Functional Block Diagram FIG. 39 shows a functional block diagram of the road feature correction apparatus according to one embodiment of the present invention. In this embodiment, the road feature correction device corrects road feature data including a center line estimated from a road shape or the like.

  The travel data acquisition unit 102 acquires travel data including travel trajectories, steering angles, speeds, and the like of a plurality of automobiles that have actually traveled. The clothoid curve start position calculating means 108 calculates the most frequent steering start position indicated in the driving data of a plurality of automobiles as the clothoid curve start position. The clothoid curve correcting unit 110 corrects the estimated clothoid curve based on the calculated clothoid curve start position.

In this way, the clothoid curve on the center line estimated by the road shape or the like can be corrected with a travel locus of a car or the like that actually traveled to be more accurate.

2.2 Hardware Configuration The hardware configuration of the road feature correction apparatus in this embodiment is the same as that shown in FIG.

2.3 Clothoid Curve Correction Processing FIGS. 40 and 41 show a flowchart of the road feature correction program 45. Here, it is assumed that the travel data is grouped and associated with the center line by the method of FIG. 33, for example.

  The CPU 30 selects a center line to be corrected (step S221). Using a mouse or the like, a curve portion including a clothoid portion and straight portions at both ends thereof are selected. The selection may be made by a user operation, or the CPU 30 may make a selection automatically according to a predetermined rule. When the CPU 30 automatically selects, a range of a predetermined length (for example, 5 m) of the curve portion including the clothoid portion and the linear portions at both ends thereof is selected.

  Next, it is determined whether or not the number of travel locus lines in the group related to the target center line (or a ratio to the total number of travel locus lines) exceeds a predetermined value (step S223). If the predetermined value is not exceeded, the correction process based on the travel locus line of the group is not performed. This is because reliable correction cannot be performed if the number of travel locus lines is small.

  If it exceeds the predetermined value, the clothoid curve is corrected based on the traveling data of the group. FIG. 42 shows the structure of the center line estimated in the vicinity of the curve. The straight line portion LIN1, the clothoid curve portion CRS1, the arc portion CR, the clothoid curve portion CRS2, and the straight portion LIN2 are continuous. CSP1 and CSP2 are the start points of the clothoid curve, and CEP1 and CEP2 are the end points of the clothoid curve. The clothoid curve is a curve in which the radius of curvature gradually decreases, and is also called a relaxation curve. Since there are clothoid curves at the entrance and exit of the curve section, it is designed so that the handle can be turned slowly at the curve.

  The CPU 30 calculates the average traveling speed (the average traveling speed of the clothoid sections CRS1, CRS2, and the arc section CR) in the curve data in the group travel data (step S225). CPU30 judges whether the average speed of a curve section is in the predetermined range before and after the median value of all the travel data of this section about each run data (Step S226). If not, the running data is not used for correction. This is because there is a high possibility of an abnormal value.

  If within the range, the CPU 30 calculates the steering start position and the braking start position before entering the curve section from the travel data (step S227). The steering start position is calculated as follows. First, in each travel data in the group, a position (X coordinate in the figure) in the traveling direction in the straight line portion of the steering start position (position where the steering angle exceeds a predetermined value (for example, 2 degrees)) is acquired. This is performed for all travel data in the group. As a result, as shown in FIG. 43, it is possible to know in which section the steering is most frequently started by taking a section of a predetermined interval in the traveling direction of the straight line portion (step S229). In this embodiment, even when the steering is started after entering the curve section, the steering start position is acquired by the linear portion traveling method (X coordinate).

  A point on the estimated center line C (or the corrected center line C) corresponding to the most frequent X coordinate of the steering start is set as the steering start position ACSP1 and recorded as an attribute of the center line C (step S230). The braking start position is also recorded as the attribute of the center line C in the same manner as described above.

  Next, the CPU 30 calculates the X coordinate corresponding to the mode value of the steering end position (the position at which the steering angle is equal to or less than a predetermined value (for example, 2 degrees)) in the second clothoid curve CRS2 in the same manner as described above. Then, the steering end position ACEP2 (not shown) is determined on the center line C. The steering end position ACEP2 is also recorded as the attribute of the center line C in the same manner as described above.

  These pieces of position information can be used to control the start of turning of the steering wheel and the start of braking when performing automatic driving or driving assistance control.

  It should be noted that the steering start point ACSP1 should normally coincide with the start point CSP1 of the first clothoid curve CSR1. Similarly, the steering end point ACEP2 should coincide with the end point CEP2 of the second clothoid curve CSR2. However, as shown in FIG. 48, there are many cases where a deviation occurs between the starting point CSP1 of the clothoid curve estimated from the road shape, the steering starting point ACSP1, and the like. The estimated start point CSP1 and end point CEP2 of the clothoid curve may not be accurate. Therefore, in this embodiment, the estimated clothoid curve is corrected based on the steering start position ACSP1 and the steering end position ACEP2 determined by actual measurement by the following processing.

  44 to 46 show a flowchart of the road feature correction program 45. Here, a process of correcting the center line in the curve based on the steering start position ACSP1 and the steering end position ACEP2 calculated above will be described.

  CPU30 produces | generates the virtual point which is an intersection of the driving locus line of each vehicle shown by driving | running | working data, and the cross section of a predetermined space | interval (step S231). This process is the same as the process described in FIG. 38C. CPU30 calculates | requires the approximated curve KL by the least squares method as shown to FIG. 47A using the virtual point group produced | generated about the some vehicle (step S232). It can be said that this approximate curve is a center line derived from the actual travel locus of many vehicles. Note that the approximate curve may be obtained by a method other than the method of least squares.

  Next, as shown in FIG. 47B, the CPU 30 applies the RANSAC method to the generated approximate straight line KL, generates a circle KCR along the curve shape, and records the radius R ′ (step S233). Note that a method other than the RANSAC method may be used as the circle estimation method.

  Next, as shown in FIG. 48, the CPU 30 calculates a deviation a in the X coordinate direction between the steering start position ACSP1 and the clothoid curve CSP1 of the center line C estimated by the road shape (step S238). Here, the X coordinate direction is the direction of the straight line portion of the center line C. The CPU 30 corrects the clothoid curve using the deviation as the correction value a (step S239).

  Details of step S239 are shown in FIG. The CPU 30 shifts the clothoid curve start position CSP1 by the correction value a to match the steering start position ACSP1 (step S253). As shown in FIG. 49, the X parameter (X value) of the clothoid curve in the road feature data estimated from the shape is X. Since the starting point moves, this is corrected by the correction value a to be X ′ (in this case, X + a).

  The clothoid curve can be drawn if the straight line, the clothoid curve start position, the X parameter, and the radius of curvature of the clothoid end position are known. Now, the straight line is the first straight line LIN1 (see FIG. 42), the clothoid curve start position is determined as the steering start position ACSP1, the X parameter is calculated as X ′, and the curvature radius of the clothoid end position is the radius R of the circle KCR. '(See FIG. 47B). Therefore, the CPU 30 generates the first clothoid curve CSR1 (see FIG. 42) based on these (step S254).

  Next, the CPU 30 connects the circle generated in step S233 to the generated first clothoid curve CSR1 (step S255). That is, the center position of the arc is determined.

  Further, the CPU 30 generates a second clothoid curve CRS2 (see FIG. 42) connecting the circles forming the arc CR and the second straight line LIN2 (step S256).

  As described above, a corrected center line C as shown in FIG. 49B can be obtained. In FIG. 49B, CSP1 is the start position of the first clothoid curve (that is, the steering start position ACSP1), and CEP2 is the end position of the second clothoid curve.

  Next, the CPU 30 sets an error in the X coordinate direction between the end position CEP2 of the second clothoid curve of the center line C corrected in this way and the steering end position ACEP2 when passing through the curve as a new correction value a. (Step S257).

  Subsequently, the CPU 30 determines whether or not the end position CEP2 of the second clothoid curve matches the steering end position ACEP2 when exiting the curve (step S252). If it is within an error within a predetermined range, it is determined that they match.

  If not, based on the correction value a generated in step S257, the start position CSP1 of the first clothoid curve (that is, the steering start position ACSP1) is left as it is, and the value of the parameter X is set based on the correction value a. The clothoid end position CEP2 and the steering end position ACEP2 are corrected to coincide with each other (step S253). Hereinafter, based on the corrected X ′, the processing from step S254 is executed.

  In step S252, if the end position CEP2 of the second clothoid curve and the steering end position ACEP2 match (an error of a predetermined value or less), the CPU 30 ends the processing of loop 2.

  The centerline C in the vicinity of the curve obtained in this way is corrected so that the start position and end position of the clothoid curve match the steering start position ACSP1 and the steering end position ACEP2.

  Next, the CPU 30 determines the coincidence between the center line C of the curve corrected in this way and the travel locus KL calculated in FIG. 47A (step S240). For example, as shown in FIG. 49C, when the error between the two is large, the shape of the center line C is not appropriate.

  The CPU 30 calculates the degree of coincidence between the corrected center line C and the travel locus KL (see FIG. 47A) by using the method illustrated in FIG. Judging by calculating. That is, if the total value is equal to or less than the predetermined value, it is determined that the values match.

  If they match within a predetermined error, the CPU 30 determines the center line C of the corrected curve.

If they do not match, the CPU 30 calculates an average value of errors between the center line C and the travel locus KL in FIG. 49C (average value of errors in a cross section at a predetermined interval) (step S241). This average value is not an absolute value but an average including a sign. In accordance with this average value, the CPU 30 moves the clothoid curve start position CSP1 and end position CEP2 in the direction in which they match (step S242). Note that the movement is performed on a straight line or an extended line of the straight line. Thus, the start position CSP1 and the end position CEP2 are moved, and step S236 and subsequent steps are executed again. Repeat the above process to find an appropriate clothoid curve.

2.4 Other
(1) In the above embodiment, the steering start position CSP1, the end position CEP2, and the brake start position (not shown) shown in FIG.

  However, the steering change end position CEP1 and the steering change start position CSP2 may also be recorded as attributes.

(2) In the above embodiment, a steering operation in an automobile is used as an example of the direction changing operation. However, a steering wheel operation of a motorcycle or the like may be used as the direction change operation. The same applies to other embodiments.

(3) The above-described embodiments and modifications can be implemented in combination with other embodiments as long as they do not contradict the essence.

3. Third embodiment
3.1 Functional Block Diagram FIG. 50 is a functional block diagram of the road feature correction apparatus according to one embodiment of the present invention. In this embodiment, the road feature correction device corrects road feature data including a center line estimated from a road shape or the like.

  The travel data acquisition unit 102 acquires travel data including travel trajectories, steering angles, speeds, and the like of a plurality of automobiles that actually traveled at a branching portion or an intersection. The grouping means 112 groups the travel locus lines indicated in the plurality of travel data. The center line correction unit 114 generates a representative travel locus line based on the grouped travel locus lines, and corrects the center line of the branching portion or the intersection portion based on the representative traveling locus line.

In this way, the center line of the branch or intersection estimated by the road shape or the like can be corrected with a travel locus of a car or the like that has actually traveled to be more accurate. For example, a portion that has not been corrected by Embodiments 1 to 3 or a portion that has not been estimated such as a center line based on a road shape can be set as a correction target portion.

3.2 Hardware Configuration The hardware configuration of the road feature correction apparatus in this embodiment is the same as that shown in FIG.

3.3 Centerline Correction Processing at Branch / Intersections FIGS. 51 to 53 show a flowchart of the road feature correction program 45. In this embodiment, correction of the center line at the branch or intersection of the estimated road feature data is performed.

  The CPU 30 selects a branch / intersection to be corrected (step S281). The selection may be made by a user operation, or the CPU 30 may make a selection automatically according to a predetermined rule.

  Subsequently, the CPU 30 acquires travel data of the selected target portion (step S282). The CPU 30 determines whether or not the selected target location is an intersection (intersection) (step S283). For example, if four or more roads are joined, it is determined that it is an intersection.

  The CPU 30 assigns an index to each of the lane in which the vehicle moves in the direction of entering the intersection and the lane in which the vehicle moves in the direction of exiting the intersection on the center line of the intersection (step S284). For example, as shown in FIG. 54A, an index is attached to each lane.

  Next, the CPU 30 gives an index to each travel locus line within a predetermined distance from the center line of each lane (see FIG. 55A, preferably within the lane) (step S286). For example, in the case of a trajectory that entered the intersection from IN1, turned left, and traveled to OUT9, IN1-OUT9 is assigned.

  In the above description, the CPU 30 extracts a travel locus line not indexed with IN (see FIG. 54A). This occurs, for example, when a right turn lane is provided as shown in FIG. 55A. The CPU 30 generates the center line of the right turn lane by the least square method based on the traveling locus without the IN index (see FIG. 55B). Note that the approximate curve may be obtained by a method other than the method of least squares. Details of the following processing will be described. In this embodiment, a right turn lane (right turn exclusive lane) has been described. However, when there is a left turn lane (left turn exclusive lane) according to a country or a law, it can be similarly applied.

  First, a place outside a certain range of the lane center line is specified (step S291). The most frequent position (the position where the number of trajectories that have changed from the inside of the range to the outside of the range) is calculated (step S292). The center line C5 of the right turn lane is generated based on the travel locus after the most frequent position with respect to the traveling direction (for example, it can be performed by the method of FIG. 38C) (step S293).

  Next, an approximate curve is generated by the least square method, and the center line C5 and the original center line C1 are connected (step S294). Further, a clothoid curve is generated based on this approximate curve (step S295). An index is also given to the generated right turn lane. Therefore, an index is attached as shown in FIG. 54B. Note that the approximate curve may be generated by a method other than the method of least squares.

  Next, the CPU 30 groups the traveling locus lines with the same index (step S297). Further, based on these, an approximate curve is generated by the least square method (step S298). In order to connect the generated approximate curve to the existing center line C, an unnecessary portion of the approximate line is deleted (step S299).

  For example, a corrected center line C ′ as shown in FIG. 56A can be obtained from the traveling locus lines grouped as IN8-OUT1. The CPU 30 performs the same processing for other groups.

  On the other hand, if it is determined in step S290 that it is not an intersection but a branch, the CPU 30 executes step S300 and subsequent steps.

  In step S300, the CPU 30 sets a cross section with a predetermined interval for a plurality of travel trajectories in the branching section, and generates a virtual point where the travel trajectory and the cross section contact each other. Based on this virtual point, a travel locus KJ (FIG. 56B) is generated by the least square method (step S301). The starting point and the ending point of the branch are found from the generated traveling locus. Further, a clothoid curve CR connecting the two center lines C is generated based on the approximate line KJ (step S302). Note that the approximate curve may be generated by a method other than the method of least squares.

As described above, the centrality of the intersection or the branch can be corrected based on the actual travel locus.

3.4 Others The above-described embodiments and modifications can be implemented in combination with other embodiments as long as they do not contradict the essence.

4). Fourth embodiment
4.1 Functional Block Diagram FIG. 57 shows a functional block diagram of the road feature correction apparatus according to one embodiment of the present invention. In this embodiment, the road feature correction device corrects road feature data including a center line estimated from a road shape or the like.

  In the recording unit 120, road feature data is recorded. The road feature data is data generated and corrected based on the road shape, data actually traveled, and the like. The reference means 122 is another road part having characteristics similar to the characteristics (curve curvature, bank angle, etc.) of the road part for which correction (including generation) of road characteristic data is desired, and already having data Is specified as a reference part.

  The centerline correcting unit 114 corrects the road feature data of the portion to be corrected based on the found feature of the reference portion.

In this way, the road feature data such as the center line can be corrected by using the road feature data of other portions, and can be made more accurate. Here, the correction is a concept including not only the case of correcting original data but also the generation of data when there is no data.

4.2 Hardware Configuration The hardware configuration of the road feature correction apparatus in this embodiment is the same as that shown in FIG.

4.3 Centerline Correction FIG. 58 shows a flowchart of the road feature correction program 45. In this embodiment, a process for correcting the center line in the road feature data is performed.

  The CPU 30 selects a center line to be corrected (step S351). The selection may be made by a user operation, or the CPU 30 may make a selection automatically according to a predetermined rule. The selection is made over a predetermined range.

  Next, the CPU 30 divides the correction target portion into a straight line portion, a clothoid portion, and an arc portion (step S352). For example, if it is a location like FIG. 59A, it will be divided | segmented into the linear part L, the clothoid part CR, the circular arc part CC, the clothoid part CR, and the linear part L. 59B, the straight portion L, the clothoid portion CR, the clothoid portion CR, and the straight portion L are divided.

  Subsequently, road feature data in another road portion is acquired, and similarity is determined (step S354). In this embodiment, the similarity is determined from three main viewpoints.

  First, the shape similarity of the center line in a plane (view of the road as viewed from above) is determined. As a premise, it is determined whether or not the above categories are met. For example, when the clothoid part, the arc part, and the clothoid part are continuous as shown in FIG. 60A, the places where the clothoid part, the arc part, and the clothoid part are continuous are extracted similarly as shown in FIGS. 60B and 60C. . Further, the extracted ones are compared by rotating and the like, and the similarity as a figure is determined.

  Next, the shape similarity of the center line in the longitudinal section is determined (see FIG. 61). Note that the longitudinal section is a longitudinal section along the center line of the curve in the curved portion. This is also determined by the similarity as a figure.

  Furthermore, the similarity of the cross-sectional shape is determined. For example, when comparing the characteristics of a road where the center line in FIGS. 62A and 62B exists, the same number of cross sections are set in each of the L, CR, CC, CR, and L sections. For example, when comparing the arc portion CC of FIG. 62A and the arc portion of FIG. 62B, the same number of cross sections are set in both sections. The similarity of the shape of the road surface in this cross section is judged. The same applies to other parts.

  In all three cases, the CPU 30 sets a predetermined reference and calculates the similarity. If the similarity is greater than or equal to a predetermined value, it is recorded as having similar road characteristics (step S356). By repeating this, it is possible to record portions having similar road characteristics.

The CPU 30 determines whether there is a similar road portion extracted as described above (step S358). If there is, the correction target portion is corrected using the center line of the road portion having the highest similarity (step S359). For example, the clothoid start position of the correction target portion can be corrected according to the center line of the road portion having a high degree of similarity. Even if the correction target part does not have a center line, it can be generated with reference to the center line of the road part having a high degree of similarity.

4.4 Other
(1) In the above embodiment, the center line is corrected. However, other road features such as the number of lanes and the road width may be corrected.

(2) The above embodiments and modifications can be implemented in combination with other embodiments as long as they do not contradict the essence.

5. Fifth embodiment
5.1 Overall Configuration FIG. 1 shows a functional block diagram of a road feature determination device according to a fifth embodiment of the present invention.

  The road feature determination apparatus according to this embodiment receives three-dimensional measurement data from surface points measured while traveling on a road, and determines a road edge and a road center.

  The cross section setting means 2 sets a cross section perpendicular to the traveling direction at predetermined intervals in the three-dimensional measurement data. The traveling point determination means 4 determines the intersection of the traveling line connecting the traveling locus and the cross section as the traveling point.

  The structure lower end point extraction means 6 finds a surface point at a position moved by a predetermined distance shorter than the minimum sidewalk width in the horizontal direction from the apex of the end structure in the cross section. A straight line connecting the found surface point and the vertex is set. Furthermore, the surface point with the longest perpendicular to the straight line is extracted as the structure lower end point.

  The road edge point extraction means 8 determines an average point of surface points within a predetermined distance from the structure lower end point, and sets a straight line connecting the average point and the travel point. Furthermore, the surface point with the longest perpendicular to the straight line is extracted as the road end point. In this way, road end points are extracted in each cross section.

  The road edge determining means 10 generates a road edge line by connecting road edge points in each cross section, and determines the road edge. Thereby, the shape of a road edge part can be obtained continuously.

Furthermore, the road center point extraction means 12 extracts the midpoint between the left and right road end points in each cross section as the road center point. The road center determining means 14 determines the road center line by connecting the road center points in the respective cross sections.

5.2 Hardware configuration Fig. 2 shows the hardware configuration of the road feature determination apparatus. A memory 32, a display 34, a hard disk 36, a CD-ROM drive 38, and a keyboard / mouse 40 are connected to the CPU 30.

  An operating system 42 and a road feature determination program 44 are recorded on the hard disk 36. The road feature determination program 44 performs its function in cooperation with the operating system 42.

These programs are those recorded on the DVD-ROM 46 and installed on the hard disk 36 via the CD-ROM drive 38. It may be downloaded and installed from a server device (not shown) via the Internet.

5.3 Road edge / center determination processing
5.3.1 Overall Flowchart FIG. 3 shows an overall flowchart in the road edge / center determination process of the road feature determination program 44.

  The CPU 30 reads the three-dimensional measurement data from a DVD-ROM or the like and records it on the hard disk 36. The three-dimensional measurement data is obtained by mounting a radar distance measuring device on an automobile, an unmanned aerial vehicle (UAV), etc. and measuring while traveling, and is data indicating a surface shape near the road. In addition, the three-dimensional measurement data includes data of travel points that indicate the position of the automobile by time change. For example, MMS point cloud data can be used as the three-dimensional point cloud data.

  The CPU 30 reads the three-dimensional measurement data from the hard disk 36 and sets the cross section at a predetermined interval (step S1). Subsequently, the CPU 30 extracts the left end point of the road in each set cross section (step S3). Further, the right end point of the road is extracted from each set cross section (step S4). Next, the CPU 30 extracts the center of the left end point and the right end point as the center point in each cross section (step S5).

  CPU30 will extract a left end point, a right end point, and a center point about all the cross sections, will connect these and will determine a left end part line, a right end part line, and a center line (step S6).

  Hereinafter, details will be described for each process.

5.3.2 Setting of Cross Section FIG. 4 shows a detailed flowchart of the cross section setting process (step S1). FIG. 5 shows an example schematically showing three-dimensional measurement data. The surface shape of the road is represented by a large number of measurement points. In this embodiment, the measurement data of each point includes three-dimensional coordinates of X, Y, and Z, reflection intensity, and measurement time. Furthermore, the three-dimensional coordinates of X, Y, and Z of the travel position (travel point) of the vehicle and the measurement time are also included. The Z coordinate in the height direction is obtained as the sea level.

  CPU30 connects a travel point with a line in order of measurement time, and produces | generates a travel line (step S11-S14). Next, the CPU 30 draws a perpendicular to the travel line from each measurement point to generate an intersection (step S17). CPU30 makes each measurement point into one group for every predetermined distance (for example, every 10 cm) based on the distance from the starting point of a travel line to the said intersection (step S19). With the measurement points grouped, measurement points having a cross section (a plane perpendicular to the travel line) are obtained. Further, a point where the travel line is in contact with the cross section is obtained as a travel point.

  FIG. 6 shows an example of measurement points in the cross section. In this example, there is a case where there are a road portion and a sidewalk portion, and there is a structure at the end. However, in the measurement data, only the shape shown in FIG. Therefore, the CPU 30 obtains which part is a road part and which part is a sidewalk part by road end point extraction processing described later.

  In this embodiment, measurement points are grouped every 10 cm. However, a cross section may be set along the travel line at a predetermined interval, and a measurement point whose vertical distance to the cross section is within 5 cm may be vertically moved to the cross section.

5.3.3 Road End Point Extraction FIGS. 7 and 8 show detailed flowcharts of road end point extraction processing (steps S3 and S4). CPU30 extracts the vertex A of the left end part in each cross section (refer FIG. 9A). Further, a point B at a position moved in the X direction by a predetermined distance (for example, 0.5 m) from the vertex is extracted. The CPU 30 sets a straight line connecting the vertex A and the point B (step S31).

  CPU30 produces | generates the perpendicular with respect to the said straight line about each measurement point in the range of this vertex A and point B, and calculates the distance (step S34). Then, a measurement point with the longest vertical distance is found and set as a feature point C at the lower part of the structure (steps S35, S36, S37).

  As described above, the left feature point C is found. Similarly, the CPU 30 finds the right feature point C.

  Next, as shown in FIGS. 9B and 9C, the CPU 30 extracts measurement points within a predetermined distance (for example, 0.5 m) in the X direction from the feature point C and within a predetermined distance (for example, 0.1 m) in the Z direction. Then, an average value of the X, Y, and Z coordinates is calculated to obtain a temporary point D (step S39).

  The CPU 30 connects the temporary point D and the travel point with a straight line (step S40). Next, the CPU 30 calculates a vertical distance from the straight line for each measurement point between the temporary point D and the travel point E (step S43) (step S44). A measurement point with the longest vertical distance is found and is designated as a road end point F (steps S45, S46, S47). FIG. 9 illustrates the determination of the left road end point F, but the right road end point F is determined in the same manner.

5.3.4 Determination of Road Center Point Subsequently, as shown in FIG. 9D, the CPU 30 averages the coordinates of the left road end point and the right road end point in each cross section to obtain the road center point G (the X coordinate of both points). (Having an average value) is calculated (step S5 in FIG. 3).

  Through the above processes, the left road end point, right road end point, and road center point can be obtained in each cross section.

5.3.5 Determination of Road End Line / Road Center Line The CPU 30 connects the left road end point and the right road end point in each cross section with lines to obtain the left road end line and the right road end line. Further, the road center points are connected by a line to obtain a road center line (step S7).

5.4 Other
(1) In the above embodiment, a road center line is obtained in addition to the left and right road edge lines. However, only one of the road end line and the road center line may be obtained.

(2) In the above embodiment, the case where there are sidewalks at both ends of the road has been described. In the case of a road without a sidewalk, the feature point C may be extracted as a road end point as it is. Further, when the Z coordinate of the temporary point D is smaller than the Z coordinate of the traveling point E, or when the difference between the Z coordinates of the temporary point D and the traveling point E is below a predetermined value (for example, 1 cm), It can be determined that there is no sidewalk.

(3) In the above embodiment, the road end line and the road center line are determined. In addition to or instead of this, the crossing slope of the road may be determined. In the cross section, it can be determined by calculating the slope of a straight line connecting the left and right road edge lines.

(4) In the above embodiment, the road feature determination device is configured as a stand-alone PC. However, you may comprise as a server apparatus. In this case, the three-dimensional measurement data may be transmitted from a terminal device connected via the Internet or the like to a server device that is a road feature determination device. Further, the determined road edge line and road center line are transmitted from the server device to the terminal device.

(5) In FIG. 9A and FIG. 9B, the point for drawing a straight line is provided inside 0.5m. However, it may be larger or smaller as long as it is smaller than the width of the sidewalk.

(6) The above modifications can be implemented in combination with each other. Moreover, as long as it is not contrary to the essence, this embodiment and the modification can be applied to other embodiments.

6). Sixth embodiment
6.1 Overall Configuration FIG. 10 shows a functional block diagram of a road feature determination device according to the sixth embodiment of the present invention.

  The road feature determination apparatus according to this embodiment receives three-dimensional measurement data based on surface points measured while traveling on a road, and determines a lane line and a lane center line.

  Based on the three-dimensional measurement data, the lane marking extraction unit 20 extracts a portion where the reflection intensity (luminance) is a predetermined value or more and continues for a predetermined length as a lane marking. The lane marking determining means 22 complements the missing portion of the lane lane marking based on the intermittent lane lane marking and determines the lane marking.

  The road end line determining means 26 determines the end line of the road based on the three-dimensional measurement data. As the road edge line determination means 26, the method according to the first embodiment can be used. The lane marking determination unit 22 determines the lane marking based on the road width obtained based on the road edge line when the lane marking due to the luminance difference is not extracted.

  The lane center line determining means 24 determines the lane center line based on the lane line and the road end line.

The lane center line determined in this way can be used for automatic driving control of automobiles.

6.2 Hardware Configuration The hardware configuration of the road feature determination apparatus according to this embodiment is the same as that shown in FIG.

6.3 Marking Line Determination / Lane Center Determination Process The flowchart in the lane marking / lane center line determination process of the road feature determination program 44 is shown.

  CPU30 extracts a part larger than predetermined brightness | luminance about each point of three-dimensional measurement data. When a white line or a yellow line for dividing a lane on a road is drawn, the reflection at this portion increases and the brightness becomes higher than the surroundings. Therefore, it is possible to extract a lane marking by extracting a portion with high luminance over a predetermined length.

  For example, as shown in FIG. 12B, a white line or a yellow line can be extracted. In FIG. 12B, an intermittent lane segment area R is extracted. A cross-sectional view is as shown in FIG. 12A. In addition, when the part with high brightness | luminance does not continue over predetermined length like the area | region RE, it does not extract.

  As shown in FIG. 12B, when a white line or yellow line lane segmentation region R is detected (step S81), the CPU 30 sets the center of the region R in the road width direction as a lane segmentation point. CPU30 connects the lane division point in each cross section, and determines lane division line DL (step S82).

  When the white line or the yellow line is intermittent, in the part where the white line or the yellow line is not present, it is assumed that the white line or the yellow line is located at a distance d from the road edge to the white line / yellow line in the vicinity. Is determined (see FIG. 12C).

  In some cases, white and yellow lines are not drawn, and these cannot be extracted. In this case, the CPU 30 determines the lane marking DL based on the road width D as follows (step S83). First, based on the three-dimensional measurement data, the left and right road edge points in each cross section are determined based on the processing of FIG. Further, the road width D is calculated based on the left and right road end points (see FIG. 13A). In addition, what is necessary is just to use this, when the road edge point and the road width D are given.

  The CPU 30 calculates D / d based on the road width D and the predetermined minimum lane width d, rounds down the decimals, and calculates the lane number C. For example, if the road width D is 8.5 m and the set minimum lane width d is 2.75 m, D / d is 3.09 (see FIG. 13B). This is rounded down to 3 as the lane number C. Note that the minimum lane width d may be changed depending on the type of road (general road or highway).

  Next, the CPU 30 calculates the lane width by dividing the road width D by the number of lanes, thereby determining the lane division point (see FIG. 13C). A lane division line is determined by connecting the lane division points of each cross section.

  As described above, if there is a white line or a yellow line, the lane line is determined based on this, and if not, the lane line is determined based on the road width D. When the lane line is determined, the CPU 30 determines a lane center line at the center of each lane as shown in FIG. 13D (step S84).

6.4 Others (1) In the above embodiment, the lane markings are supplemented based on the distance d from the end of the road in the part where there is a white line / yellow line in the vicinity in the part without the white line / yellow line. . However, complementation may be performed by connecting lane markings in a portion where there is a white line or a yellow line.

(2) The above modifications can be implemented in combination with each other. Moreover, as long as it is not contrary to the essence, this embodiment and the modification can be applied to other embodiments.

7). Seventh embodiment
7.1 Overall Configuration FIG. 14 is a functional block diagram of a road feature determination device according to the seventh embodiment of the present invention.

  The road feature determination apparatus in this embodiment receives three-dimensional measurement data from surface points measured while traveling on a road, and determines a straight line and a clothoid curve of a lane center line.

  The straight line / arc extraction means 30 receives the three-dimensional measurement data and extracts a straight line and an arc of the lane center line. The clothoid curve determining means 32 sets a perpendicular to the straight line from the center of the arc, and changes the tangent angle with respect to the perpendicular with the center of the arc as the center of the distance ratio radius at the clothoid end point. A clothoid curve is generated and the clothoid end point coincides with the arc. The connecting means 34 determines the end point of the straight line and the end point of the arc based on the determined clothoid curve, and connects the straight line, the clothoid curve, and the arc.

  As described above, the degree of bending including the clothoid curve in the curve portion can be accurately determined.

7.2 Hardware Configuration The hardware configuration of the road feature determination apparatus according to this embodiment is the same as that shown in FIG.

7.3 Curve Part Determination Processing FIGS. 15 to 17 show flowcharts in the centerline connection process including the curve part determination process of the road feature determination program 44. FIG. CPU30 determines a road center point or a lane center point based on three-dimensional measurement data (step S91). This can be realized by, for example, the processing shown in the first embodiment and the second embodiment.

  Next, the CPU 30 extracts a straight line portion by Hough transform (step S92). The center point extracted as the straight line is removed from the determination target (step S93). Subsequently, the CPU 30 extracts an arc portion by the RANSAC method (step S94). Further, in order to remove noise, each line is grouped, and a group with a small number of points is deleted (step S95).

  Subsequently, the CPU 30 performs the following processing for each line. First, the CPU 30 determines whether or not the line to be processed is a straight line (step S97). If it is a straight line, the gradient (angle in the longitudinal section) is calculated (step S98). If it is an arc, the center point coordinates and radius of the circle are calculated (step S99).

  When the straight line gradient and the center coordinates / radius of the circle are calculated for all the lines as described above, the CPU 30 executes the following processing for each line. First, the CPU 30 determines whether or not the line to be processed is a straight line (step S103). If the target line is a straight line, it is determined whether the next adjacent line is a straight line (step S104). If the next line is a straight line, it means that the straight line and the straight line are continuous, and therefore, interpolation processing between the straight lines is performed (step S106).

  Complementary processing between straight lines is shown in FIGS. First, the CPU 30 obtains the intersection point by extending both straight lines (FIG. 18A). Furthermore, a perpendicular line is drawn from the end point of one straight line. Further, a straight line that bisects the angle formed by both straight lines is drawn from the intersection of both straight lines. A point where the perpendicular and the bisector intersect is obtained (FIG. 18B). An arc is drawn with this intersection as the center point (FIG. 18C). An arc is provided up to the point where the other straight line and the arc intersect. If the other straight line and the arc do not intersect, the other straight line is extended so that the other straight line and the arc intersect. In this way, the joint between the straight line and the straight line is complemented in the XY plane.

  Also, in the YZ plane (longitudinal cross section), a straight line and a straight line junction are complemented. The CPU 30 extends both straight lines in the longitudinal section and obtains the intersection (FIG. 19A). Furthermore, a parabola that passes through a point separated from the intersection by d and touches both straight lines is generated (FIG. 19B).

  When the target line is a straight line (YES in step S103) and the next line is a curve (NO in step S104), complementation is performed for joining the straight line and the curve with a clothoid curve (step S107). .

  As shown in FIG. 20A, the straight line portion does not contact the arc. This is because, in a road curve, a straight line and an arc are not connected, but a clothoid curve is provided between them. Therefore, the CPU 30 estimates this clothoid curve in step S107.

  First, as shown in FIG. 20B, the CPU 30 determines the most appropriate clothoid curve while changing the parameters of the clothoid curve. Furthermore, as shown in FIG. 20C, a straight line and an arc are connected by the determined clothoid curve.

  21A, B, and C show details of the process for showing an appropriate clothoid curve. First, the CPU 30 draws a perpendicular to the straight line from the center M of the arc (FIG. 21A). Next, as shown in FIG. 21B, a clothoid curve is generated with the point on the straight line as the clothoid start point and the position of the angle τ with the perpendicular as the clothoid end point. At this time, a clothoid curve is generated while changing the angle τ from 0 to 90 at intervals of 0.01.

  The CPU 30 finds a clothoid curve in which the distance Y from the clothoid start point of the clothoid end point of the clothoid curve generated by changing the angle τ matches the distance d from the straight line to the arc. Further, as shown in FIG. 21C, based on the found clothoid curve, the clothoid start point S is set as the end point of the straight line, and the straight line and the arc are joined by the clothoid curve.

  Further, when the target line is a curve (NO in step S103) and the next line is a curve (NO in step S104), complementation for joining the curve and the curve is performed (step S108). Details of the processing are shown in FIG.

  The CPU 30 sets a straight line connecting the arc and the center point of the arc. Further, this straight line is extended to the side of the arc having the smaller radius, and a point is set at a position D from the arc. D is determined by the following equation.

D = original straight line distance × small circle radius / (large circle radius−small circle radius)
The CPU 30 draws a straight line in contact with the two arcs from the set point. The arc is connected by this straight line.

7.4 Other
(1) In the above embodiment, the joining of the lane center line has been described. However, the same can be applied to the road center line and the road edge line.

(2) The above modifications can be implemented in combination with each other. Moreover, as long as it is not contrary to the essence, this embodiment and the modification can be applied to other embodiments.

8). Eighth embodiment
8.1 Overall Configuration FIG. 23 is a functional block diagram of a road feature determination device according to the eighth embodiment of the present invention.

  The road feature determination apparatus in this embodiment processes the center line at the branch portion. The classification means 40 classifies the road end line into a right road end line on the right side of the travel line and a left road end line on the left side of the travel line. The branch range determination means 42 sets the position where the right road end line and the left road end line are in contact as the branch start position. Furthermore, a straight line is extended from the branch start position, and a position where the straight line touches the road end line is defined as a branch saddle length position.

  The center line generation means 44 extends both road center lines or lane center lines from the branch start position to the branch end position. Furthermore, a road center line or a lane center line is generated so as to connect both road center lines at the branch end position.

8.2 Hardware Configuration The hardware configuration of the road feature determination apparatus according to this embodiment is the same as that shown in FIG.

8.3 Branch Process FIG. 24 shows a flowchart of the branch process of the road feature determination program. First, the CPU 30 specifies a branching unit (step S110). Furthermore, a branch section is specified for each specified branch portion (step S112). Subsequently, the center line is connected in the branch section (step S113). In this way, the center line at the branch portion can be complemented.

  25 and 26 show details of steps S112 and S113. The CPU 30 determines whether each road end line is on the right side or the left side of the travel line (step S120). As shown in FIG. 27A, it is recorded whether it is the right side or the left side. Next, each road edge part line is grouped by what is connected (step S121).

  The CPU 30 performs the following processing for each cluster generated above. First, it is determined whether there are both a right road end line and a left road end line in the cluster (step S123). As shown in FIG. 27B, since cluster 2 has both, it can be determined that the branch is a branch. Further, the right and left intersections Z (see FIG. 27C) are set as branch start points (step S124). A start point can be determined by extracting a branch as described above.

  For each branch, the CPU 30 determines whether the number of lanes changes at the branch (step S130). For example, as shown in FIG. 28A, if the number of lanes does not change at the branch portion, the center line is drawn well, so that no special processing is performed. However, as shown in FIG. 28B and FIG. 28C, if the number of lanes has changed in the branching section, the CPU 30 complements the center line as shown below.

  First, a straight road boundary line is extended from the branch start point Z as shown in FIGS. 29A and 29B (step S131). Furthermore, CPU30 calculates | requires the intersection Q of the extended straight line and another road boundary line, and makes it a branch end point (step S132).

  The CPU 30 extends both center lines at the branch from the branch start point Z to the branch end point Q (step S134). At the branch end point Q, the end points of both center lines are connected by a straight line K (see FIG. 29A). In addition, as shown in FIG. 29B, when both the center lines are connected only by extending the center line, it is left as it is.

  Also, as shown in FIG. 30, the road center line and the lane center line are interrupted at the intersection, but the connection can be made by the same method as described above.

8.4. Others The present embodiment can be applied to other embodiments as long as the essence is not violated.

Claims (27)

A road feature correction device for correcting a center line estimated based on a road shape,
Traveling data acquisition means for acquiring traveling data of a plurality of moving bodies actually traveling on the road;
Grouping means for grouping traveling locus lines based on the traveling data of the plurality of moving objects, and determining whether each group is associated with a center line based on a distance from the center line for each group;
Center line correction means for correcting the number of center lines based on whether each group is associated with a center line;
A road feature correction device comprising: A road feature correction program for realizing, by a computer, a road feature correction device that corrects a center line estimated based on the shape of a road.
Traveling data acquisition means for acquiring traveling data of a plurality of moving bodies actually traveling on the road;
Grouping means for grouping traveling locus lines based on the traveling data of the plurality of moving objects, and determining whether each group is associated with a center line based on a distance from the center line for each group;
A road feature correction program for functioning as centerline correction means for correcting the number of centerlines based on whether each group is associated with a centerline. In the apparatus of claim 1 or the program of claim 2,
When the center line correcting unit finds a group that is not related to the center line, the center line correcting unit generates a new center line based on the travel locus line of the group. In the apparatus or program in any one of Claims 1-3,
The center line correction means performs correction to make one center line in a group when a group related to two or more center lines is found. In the apparatus or program of Claim 4,
The center line correction means is a device or a program characterized in that one center line is generated by either generating a new center line or selecting one of the center lines. In the apparatus or program in any one of Claims 1-5,
The center line correcting means does not correct the number of center lines in a group when a group related to only one center line is found. In the apparatus or program of Claim 6,
The center line correction means does not change the number of center lines, either by using the center line of the group as it is or by generating a new center line based on a travel locus line belonging to the group. A device or program. In the apparatus or program in any one of Claims 1-7,
The center line correction means does not perform correction when the ratio or the number of the group traveling locus lines occupies a predetermined value or less. In the apparatus or program in any one of Claims 1-8,
The center line correction means generates a new center line by offsetting the original center line when generating a new center line. In the apparatus or program in any one of Claims 1-9,
The center line includes at least a road center line or a lane center line. A road feature correction device that corrects a center line including a straight line portion, a clothoid curve portion, and an arc portion estimated based on the shape of a road,
Traveling data acquisition means for acquiring traveling data of a plurality of moving bodies actually traveling on the road;
Clothoid curve start position calculation means for calculating the most frequent position of the direction change operation start of the plurality of moving bodies shown in the traveling data of the plurality of moving bodies as a clothoid curve start position;
Based on the calculated clothoid curve start position, clothoid curve correction means for correcting the estimated clothoid curve;
A road feature correction device comprising: The apparatus of claim 11.
The clothoid curve correcting means corrects the estimated clothoid curve in consideration of a clothoid curve end position. The apparatus of claim 11 or 12,
Road features further comprising attribute assigning means for assigning the most frequent position of the direction change operation start and the most frequent brake start position of the plurality of moving bodies indicated in the traveling data of the plurality of moving bodies as centerline attributes. Correction device. A road feature correction program for realizing, by a computer, a road feature correction device for correcting a center line including a straight line portion, a clothoid curve portion, and an arc portion estimated based on the shape of the road,
Traveling data acquisition means for acquiring traveling data of a plurality of moving bodies actually traveling on the road;
Clothoid curve start position calculation means for calculating the most frequent position of the direction change operation start of the plurality of moving bodies shown in the traveling data of the plurality of moving bodies as a clothoid curve start position;
A road feature correction program for realizing a clothoid curve correction means for correcting the estimated clothoid curve based on the calculated clothoid curve start position. 15. The program of claim 14, wherein
The program, wherein the clothoid curve correcting means corrects the estimated clothoid curve in consideration of a clothoid curve end position. The program according to claim 14 or 15, further comprising:
Road for functioning as attribute assigning means for assigning the most frequent position for starting the direction change operation and the most frequent position for starting the brake shown in the traveling data of the plurality of moving objects as attributes of the center line Feature correction program. A road feature correction device that corrects a center line including a straight line portion, a clothoid curve portion, and an arc portion estimated based on the shape of a road,
Traveling data acquisition means for acquiring traveling data of a plurality of moving bodies actually traveling on the road;
Attribute imparting means for imparting the most frequent position of the direction change operation start and the most frequent brake start position of the plurality of moving bodies indicated in the traveling data of the plurality of moving bodies as centerline attributes;
A road feature correction device comprising: A road feature correction program for realizing, by a computer, a road feature correction device that corrects a center line including a straight line portion, a clothoid curve portion, and an arc portion estimated based on the shape of the road, the computer actually executing the road Traveling data acquisition means for acquiring traveling data of a plurality of mobile bodies that have traveled the vehicle,
Road for functioning as attribute assigning means for assigning the most frequent position for starting the direction change operation and the most frequent position for starting the brake shown in the traveling data of the plurality of moving objects as attributes of the center line Feature correction program. A road feature correction device that corrects a center line of a branch or intersection estimated based on the shape of a road,
Travel data acquisition means for acquiring travel data of a plurality of moving bodies that actually traveled at the branching or intersection of the road;
Grouping means for grouping the travel locus lines shown in the travel data of the plurality of moving bodies;
Centerline correction means for correcting the centerline of the branching portion or the intersection with a representative traveling locus line generated based on the grouped traveling locus lines;
A road feature correction device comprising: A road feature correction program for realizing, by a computer, a road feature correction device that corrects a center line of a branch or intersection estimated based on the shape of the road, the computer actually executing the road branch or intersection Traveling data acquisition means for acquiring traveling data of a plurality of moving bodies that have traveled the section;
Grouping means for grouping the travel locus lines shown in the travel data of the plurality of moving bodies;
A road feature correction program for functioning as a centerline correction unit that corrects the centerline of the branch or intersection with a representative travel locus line generated based on a grouped travel locus line. The apparatus of claim 19 or the program of claim 20,
The grouping means groups the travel trajectory lines from the departure lane toward the entry lane based on the combination of the departure lane that exits from the intersection and the entry lane that enters the intersection. In the apparatus or program in any one of Claims 19-21,
The center line correction means generates a representative travel locus line based on the locus points of the travel locus lines in the group. The apparatus or program of claim 22
An apparatus or program for generating a representative traveling locus in a right turn or left turn lane. In the apparatus or program in any one of Claims 19-23,
The center line correction means generates a representative travel locus line by generating a clothoid curve connecting a straight line portion and a straight line portion at a branch destination in the branch portion. A recording unit that records road feature data;
A reference means for finding a portion having a road feature similar to the road feature of the correction target portion;
A center line correcting means for correcting or generating the center line of the correction target part based on the center line of the found part;
A road feature correction device comprising: A road feature correction program for realizing a road feature correction device by a computer, wherein the computer refers to a recording unit that records road feature data and finds a portion having a road feature similar to the road feature of the correction target portion. Reference means;
A road feature correction program for functioning as centerline correction means for correcting or generating a centerline of a correction target part based on a centerline of a found part. In the road feature correction apparatus of claim 25 or the road feature correction program of claim 26,
The road feature compared by the reference means includes at least one of a straight portion, a clothoid curve portion, a circular arc shape, a cross-sectional shape, and a vertical cross-sectional shape.