CN108519094A - Local paths planning method and cloud processing end - Google Patents
Local paths planning method and cloud processing end Download PDFInfo
- Publication number
- CN108519094A CN108519094A CN201810142721.4A CN201810142721A CN108519094A CN 108519094 A CN108519094 A CN 108519094A CN 201810142721 A CN201810142721 A CN 201810142721A CN 108519094 A CN108519094 A CN 108519094A
- Authority
- CN
- China
- Prior art keywords
- track
- driving
- point
- points
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000000605 extraction Methods 0.000 claims abstract description 10
- 238000010586 diagram Methods 0.000 claims description 73
- 238000009499 grossing Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000010438 heat treatment Methods 0.000 abstract 1
- 238000003860 storage Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 4
- 238000011022 operating instruction Methods 0.000 description 3
- 238000009825 accumulation Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3453—Special cost functions, i.e. other than distance or default speed limit of road segments
- G01C21/3492—Special cost functions, i.e. other than distance or default speed limit of road segments employing speed data or traffic data, e.g. real-time or historical
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Processing Or Creating Images (AREA)
- Navigation (AREA)
Abstract
This application provides a kind of local paths planning methods, including：A plurality of driving trace is projected into the plane of delineation respectively, obtains the trace image of a plurality of driving trace；Wherein, a plurality of driving trace includes identical starting point and destination；The trace image is smoothed, track density thermodynamic chart is obtained；In the track density thermodynamic chart, taken aim at a little in advance according to key point extraction；Wherein, the key point is to reflect the tracing point of the driving trace shape；The pre- attribute value taken aim at a little is calculated, the pre- attribute taken aim at a little includes coordinate, head is directed toward and curvature.From the above process it can be seen that：Extraction obtains pre- take aim at a little in the track heating power density thermodynamic chart obtained from according to a plurality of driving trace, it can solve the problems, such as to take aim at the driving path that can not a little generate and adapt to complicated road structure and changeable traffic in advance caused by there is no high-precision map to avoid high-precision map is used.
Description
Technical Field
The application relates to the technical field of navigation, in particular to a local path planning technology.
Background
With the continuous and intensive research of artificial intelligence technology, automatic traveling apparatuses such as unmanned automobiles, autonomous mobile robots, and the like are widely used in daily life and industrial production of people.
In the related technical research of automatic driving equipment such as unmanned automobiles, autonomous mobile robots and the like, a navigation technology is the core of the research, and local path planning is an important link and a component in the research of the navigation technology. Specifically, the local path planning refers to generating an optimal driving path according to the current road environment and the self state of the equipment.
In the current local path planning method, a preview point needs to be obtained before an optimal driving path is obtained, and the generation of the preview point needs to rely on a high-precision map. If the map information accuracy is not sufficient, the obtained preview point cannot meet the requirement of generating a driving path suitable for a complex road structure and variable traffic conditions.
Disclosure of Invention
The application provides a local path planning method and a cloud processing terminal, which are used for solving the problem that a driving path suitable for a complex road structure and a variable traffic condition cannot be generated at a pre-aiming point obtained without a high-precision map.
In order to achieve the above object, the following solutions are proposed:
a first aspect of the present application provides a local path planning method, including: projecting the plurality of driving tracks to an image plane respectively to obtain track images of the plurality of driving tracks; wherein the plurality of travel tracks comprise the same origin and destination; smoothing the track image to obtain a track density thermodynamic diagram; extracting a preview point according to a key point in the track density thermodynamic diagram; wherein the key points are track points reflecting the shape of the driving track; and calculating to obtain the attribute value of the preview point, wherein the attribute of the preview point comprises a coordinate, a head direction and a curvature.
From the above process, it can be seen that: the pre-aiming point is extracted from the track thermodynamic density thermodynamic diagram obtained according to the plurality of driving tracks, so that a high-precision map can be avoided, and the problem that the pre-aiming point cannot generate a driving path suitable for a complex road structure and a variable traffic condition due to the absence of the high-precision map is solved.
In one implementation, the projecting the plurality of driving tracks onto an image plane to obtain a track image of the plurality of driving tracks includes: respectively selecting a plurality of track points on each driving track; converting the coordinates of the track points selected on each driving track into coordinates under an image coordinate system; and projecting the track points selected on each driving track to an image plane according to the coordinates of the track points selected on each driving track under the image coordinate system to obtain the track image.
In one implementation manner, a gray value of a track point selected on each driving track in the track image is used for representing a weight value of the driving track.
In one implementation, the extracting a preview point in the track density thermodynamic diagram includes: taking key points of a point-taking driving track as dividing points, and transversely dividing the track density thermodynamic diagram; the point-taking driving track is one or more driving tracks in the track image, and the key points are any one or two of two track points with zero curvature difference in the point-taking driving track; and selecting a point of which the density heat force value is a wave peak value from the points of the track density thermodynamic diagram on the transverse dividing line as the preview point.
In one implementation, the extracting a preview point in the track density thermodynamic diagram includes: extracting a road junction boundary line in the track density thermodynamic diagram; and selecting a point of which the density heat value is a wave peak value from the points of the track density thermodynamic diagram on the boundary line of the road junction as the preview point.
In one implementation, the method further comprises: calculating to obtain a plurality of driving paths between the front and rear pre-aiming points according to the attribute values of the front and rear pre-aiming points on the same driving track; and respectively calculating the cost value of each driving path, and selecting the driving path with the minimum cost value in the driving paths as an optimal driving path.
A second aspect of the present application provides a cloud processing terminal, including: the projection unit is used for projecting the plurality of driving tracks to an image plane respectively to obtain track images of the plurality of driving tracks; wherein the plurality of travel tracks comprise the same origin and destination; the processing unit is used for smoothing the track image to obtain a track density thermodynamic diagram; the extraction unit is used for extracting a preview point according to a key point in the track density thermodynamic diagram; wherein the key points are track points reflecting the shape of the driving track; and the first calculating unit is used for calculating and obtaining the attribute value of the preview point, wherein the attribute of the preview point comprises coordinates, head direction and curvature.
In one implementation, the projection unit includes: the selection unit is used for respectively selecting a plurality of track points on each driving track; the conversion unit is used for converting the coordinates of the track points selected on each driving track into coordinates under an image coordinate system; and the shadow projecting unit is used for projecting the track points selected on each running track to an image plane according to the coordinates of the track points selected on each running track under the image coordinate system to obtain the track image.
In one implementation manner, a gray value of a track point selected on each driving track in the track image is used for representing a weight value of the driving track.
In one implementation, the extraction unit includes: the dividing unit is used for transversely dividing the track density thermodynamic diagram by taking key points of the point-taking driving track as dividing points; the point-taking driving track is one or more driving tracks in the track image, and the key points are any one or two of two track points with zero curvature difference in the point-taking driving track; and the first point taking unit is used for selecting a point of which the density heat force value is a wave peak value from the points of the track density thermodynamic diagram on the transverse dividing line as the preview point.
In one implementation, the extraction unit includes: the line taking unit is used for extracting a road junction boundary line in the track density thermodynamic diagram; and the second point taking unit is used for selecting a point of which the density heat value is a wave peak value from the points of the track density thermodynamic diagram on the boundary line of the intersection as the preview point.
In one implementation, the method further comprises: the second calculation unit is used for calculating and obtaining a plurality of driving paths between the front and rear pre-aiming points according to the attribute values of the front and rear pre-aiming points on the same driving track; and the preference unit is used for respectively calculating the cost value of each driving path and selecting the driving path with the minimum cost value in the driving paths as the optimal driving path.
A third aspect of the present application provides a cloud processing terminal, including: a processor and a memory, wherein: the memory for storing computer program code; the processor is configured to execute the codes stored in the memory to perform the local path planning method described above.
A fourth aspect of the present application provides a computer program product for performing the above-described method of local path planning when the computer program product is executed.
The fifth aspect of the present application further provides a computer-readable storage medium, in which instructions are stored, and the instructions are used to execute the above-mentioned local path planning method.
Drawings
Fig. 1 is a schematic diagram of a local path planning system disclosed in an embodiment of the present application;
fig. 2 is a flowchart of a local path planning method disclosed in an embodiment of the present application;
FIG. 3 is a flowchart of a method according to an embodiment of step S201 in the present application;
FIG. 4 is a diagram illustrating a track image according to an embodiment of the present disclosure;
FIG. 5 is a diagram showing a track density thermodynamic diagram disclosed in an embodiment of the present application;
FIG. 6 is a flowchart of a method of one embodiment of step S203 disclosed in the examples of the present application;
FIG. 7 is a diagram showing a transverse partitioning of a track density thermodynamic diagram as disclosed in an embodiment of the present application;
FIG. 8 is a display diagram of the locations of points on the transverse split lines and corresponding density heat force values disclosed in an embodiment of the present application;
FIG. 9 is a flowchart of a method of another embodiment of step S203 disclosed in the examples of the present application;
FIG. 10 is a diagram showing another track density thermodynamic diagram disclosed in an embodiment of the present application;
fig. 11 is an illustration of a circle drawn with a preview point as a center to find a track point, disclosed in an embodiment of the present application;
fig. 12 is a flowchart of a local path planning method disclosed in another embodiment of the present application;
FIG. 13 is a diagram showing a plurality of driving paths between two pre-aiming points in front and behind according to an embodiment of the disclosure;
fig. 14 is a schematic structural diagram of a cloud processing end disclosed in an embodiment of the present application;
fig. 15 is a schematic structural diagram of a cloud processing end disclosed in another embodiment of the present application.
Detailed Description
The embodiment of the application discloses a local path planning system, as shown in fig. 1, including: the system comprises a collection device 101, a cloud processing terminal 102 and an automatic traveling device 103, wherein the collection device 101 comprises, for example: urban taxi system, on-vehicle navigation, remove navigation and high accuracy collection car, gather driving track and traffic information, wherein, driving track includes: coordinates and travel directions of the respective trace points. The acquisition device 101 uploads the acquired driving track and traffic information to the cloud processing terminal 102 through a network. The cloud processing terminal 102 calculates a preview point according to the vehicle running track and the traffic information, calculates a track cluster including a plurality of running paths according to the preview point, and selects an optimal running path from the track cluster. Or the transport processing terminal 102 calculates a preview point according to the vehicle running track and the traffic information, and then sends the preview point to the automatic running device 103, and the automatic running device 103 calculates a track cluster including a plurality of running paths according to the preview point, and selects an optimal running path from the track cluster.
The local path planning method disclosed by the embodiment of the application is applied to a cloud processing end. Referring to fig. 2, the method comprises the steps of:
s201, projecting the multiple driving tracks onto an image plane to obtain track images of the multiple driving tracks.
The cloud processing terminal 102 receives the driving tracks uploaded by the acquisition device 101, and classifies the driving tracks according to the principle that the driving tracks with the same starting place and the same destination are classified into one class. The same type of travel locus is projected onto an image plane to form a locus image of the travel locus. Alternatively, the driving tracks can be projected to an image plane according to the weight of each driving track to form a track image of the driving tracks.
Optionally, in another embodiment of the present application, as shown in fig. 3, an implementation manner of step S201 includes:
s301, selecting a plurality of track points on each driving track respectively.
Wherein, the track point is selected on one driving track, namely the coordinate of the track point on the driving track is obtained. Moreover, each driving track can select the same number of track points, and certainly, different numbers of track points can be selected. Under general conditions, the running track is smoother, and the number of selected track points is less. And the number of selected track points is large in a more tortuous running track.
And S302, converting the coordinates of the track points selected on each driving track into coordinates in an image coordinate system.
The coordinates of the track points on the travel track are coordinates in the global coordinate system, and data in the image coordinates are used when the local path is generated, so that the coordinates of the track points on the travel track are converted into coordinates in the image coordinate system.
And S303, projecting the track points selected on each driving track to an image plane according to the coordinates of the track points selected on each driving track in the image coordinate system to obtain a track image of the driving track.
The trajectory points selected from the plurality of travel trajectories are projected onto the image plane, and the obtained trajectory image can be as shown in fig. 4.
Optionally, in the track image of the driving tracks, the grayscale value of the track point selected on each driving track on the image plane may also be used to represent the weight value of the driving track. The darker the gradation indicates a larger weight value.
Therefore, before the trajectory points selected on the driving trajectory are projected onto the image plane, the weight value of each driving trajectory needs to be known. Hereinafter, a method of calculating the weight value of the travel locus will be described in detail, taking the calculation of the weight value of the travel locus a as an example.
And performing least square fitting on the driving track A, as a formula I:
y＝a0+a1x+a2x2+...+amxmformula one
Establishing an m-order polynomial for coordinates x and y of the driving track A, wherein the m-order polynomial is as shown in a formula two:
n track points are respectively selected from the running track A, the x and y coordinate values of the n track points are respectively substituted into a formula II, and each coefficient a in the formula II can be solved0,a1,a2,...,am，xi、yiDenotes the coordinates of the ith point, i ═ 1, 2.
And calculating the medium error of the track point of the driving track A by using a formula III.
In the third formula, upsiloniActual values y of the track points representing the driving track aiAnd the calculated valueDifference of σxyRepresents the median error of the locus points in the running locus a.
And similarly, respectively calculating by adopting a least square fitting method to obtain a medium error of head pointing direction, a medium error of curvature and a medium error of speed of the driving track A.
And finally, calculating to obtain a weight value Pi of the driving track A by using a formula IV.
In the formula IV, σxyA median error of the track points representing the travel track a; sigmaθA median error representing the head orientation of the travel trajectory a; sigmakA median error indicating the curvature of the travel locus a; sigmaVThe median error indicating the speed of the travel track A;. oc, β, gamma,Is a constant.
Optionally, if the driving tracks acquired and uploaded by the acquisition device 101 are very long, each driving track may be segmented according to mileage, for example, segmentation is performed once every 1 km to obtain a track sub-segment, and then step S201 is performed on the track sub-segments including the same starting location and the same destination.
And S202, smoothing the track image to obtain a track density thermodynamic diagram.
And smoothing the track image by using a Gaussian convolution template to obtain a track density thermodynamic diagram.
Optionally, if, in the track image, the grayscale of the projection of each driving track is used to represent the weight value of the driving track, and then after the track image is subjected to smoothing processing, the obtained track density thermodynamic diagram is as shown in fig. 5, where the darker the color in the diagram indicates that the density thermodynamic value is higher, indicating that the track points at that position are denser, and the weight values of the track points are also higher, which indicates that these track points are the track points that are most frequently passed by manual driving.
Specifically, a 20 × 20 convolution template can be generated by using a two-dimensional gaussian function, and a convolution operation with a step size of 1 is performed on the track image to obtain a track density thermodynamic diagram.
And S203, extracting a preview point in the track density thermodynamic diagram.
In the track density thermodynamic diagram, a preview point is extracted according to a key point. Wherein, the key point is the track point that reflects the orbit shape of traveling, if the track density thermodynamic diagram includes the curve section, then the key point includes: track points with zero curvature difference in the driving track; if the track density thermodynamic diagram comprises crossed driving tracks, the key points comprise: and reflecting the track points of the intersection in the driving track.
The pre-aiming point is extracted from the track thermodynamic density thermodynamic diagram obtained according to the plurality of driving tracks, so that a high-precision map can be avoided, and the problem that the pre-aiming point cannot generate a driving path suitable for a complex road structure and a variable traffic condition due to the absence of the high-precision map is solved.
And the preview point is a track point of which the density heat value is a wave peak value in the track density thermodynamic diagram, so that the preview point is a track point in a running track with a higher weight value in the track image, and the point is indicated to be frequently passed by during manual driving. And generating a track cluster comprising a plurality of driving paths according to the preview point, wherein each driving path in the track cluster can be used as an option of an optimal driving path in local path planning, so that the driving paths are closer to the manual driving path and accord with the manual driving habit.
Optionally, in another embodiment of the present application, referring to fig. 6, an implementation manner of step S203 includes:
and S601, taking key points of the point-taking driving track as dividing points, and transversely dividing the track density thermodynamic diagram.
Wherein, the point-taking driving track is one or more driving tracks in the track image. Optionally, the running track with the highest weight in the track image is selected as the point-taking running track, or several running tracks with higher weight values in the track image are selected as the point-taking running tracks. The key point of the point-taking driving track is any one or two of two track points with zero curvature difference in the point-taking driving track.
The track density thermodynamic diagram is transversely divided along a direction perpendicular to a tangent line of a dividing point, which is a key point of the point-taking travel track, to form a transverse dividing line of the track density thermodynamic diagram. And, the lateral direction means: and has a direction intersecting with the direction of the travel locus.
It should be noted that, in a point-taking travel track, there may be a plurality of track points with zero curvature difference, and therefore, the track density thermodynamic diagram may be divided laterally at different positions.
And S602, taking a point of which the density heat force value is a wave peak value in points of the track density thermodynamic diagram on the transverse dividing line as a preview point.
Referring to fig. 7, the track density thermodynamic diagram is divided transversely by using key points of the point-taking travel track as dividing points, so that transverse dividing lines are formed on the track density thermodynamic diagram. And a plurality of points belonging to the track density thermodynamic diagram are distributed on the transverse dividing line, and each point has a corresponding density heat value. Referring to fig. 8, the horizontal axis in the figure represents the position of a point on the horizontal dividing line, and the horizontal axis represents the density heat value of the point on the horizontal dividing line. And selecting a point with the density heat value being a wave peak value, namely a round point in the graph, wherein the point is a pre-aiming point, and the position of the point is the position of the pre-aiming point. Specifically, the coordinates of the point on the track density thermodynamic diagram are calculated according to the value on the horizontal axis of the point with the density heat value as the peak value, and then the coordinates are converted into the coordinates under the global coordinate system.
Optionally, in another embodiment of the present application, referring to fig. 9, another implementation manner of step S203 includes:
s901, extracting a road boundary line in the track density thermodynamic diagram.
Intersection regions in the trajectory density thermodynamic diagram can be determined by means of the expanded, edge-detected images, and boundary lines of the intersection regions, i.e., intersection boundary lines, are extracted as shown by straight lines in fig. 10.
And S902, taking a point of which the density heat value is a wave peak value in points of the track density thermodynamic diagram on the boundary line of the intersection as a preview point.
The specific implementation process of this step can refer to the content of step S602 in the embodiment corresponding to fig. 6, and is not described herein again.
And S204, calculating to obtain the attribute value of the preview point.
Wherein the properties of the preview point include coordinates, head pointing direction and curvature.
In step S203, a pre-pointing point is extracted from the track density thermodynamic diagram, specifically, a position, i.e., a coordinate, in the track density thermodynamic diagram is found. In addition, the coordinates of the preview point in the track density thermodynamic diagram are image coordinates, and after the image coordinates are obtained, the image coordinates need to be converted into global coordinates.
And drawing a circle by taking the pre-aiming point as the center of the circle and a preset distance (such as 0.5 meter) as the radius, wherein the formed circle is the search range. And correspondingly generating the head direction and the curvature of the pre-aiming point according to the head direction and the curvature of the track point falling in the search range.
Specifically, the head direction of the preview point is calculated as an example. Assuming that there are N track points falling in the circle, the head direction of the pre-aiming point can be calculated by using a formula five or a formula six according to the head directions of the N track points.
In the formula five and the formula six, m is a preset numerical value and is used for representing the number of divided segments, and the adjustment can be carried out according to the actual precision requirement, and the pointed interval of the head is generally ensured to be less than 1 degree. j is 0, 1.
And calculating by using a formula seven to obtain a weight value corresponding to the head direction.
Wherein, if the calculated head points to the corresponding weight valueIf the value is less than the threshold value, the value is regarded as thetajFor gross errors, they need to be rejected.
The following is a detailed description of an example. Referring to fig. 11, a circle is drawn by taking the preview point P as the center of the circle and 0.5 m as the radius, and the circle has 10 track points. And the minimum value and the maximum value of the head orientation of 10 points are 88.6 ° and 92.2 °, respectively, and m is 4.
Then
5(m +1) head direction values corresponding to the preview point P are obtained by calculation according to a formula V and are respectively as follows:
θ0＝0·0.9+88.6＝88.6
θ1＝1·0.9+88.6＝89.5
θ2＝2·0.9+88.6＝90.4
θ3＝3·0.9+88.6＝91.3
θ4＝4·0.9+88.6＝92.2
reuse formulaCalculating the corresponding weight value as:
wherein,less than a threshold of 0.05, consider θ4For gross error, it is removed.
Similarly, the curvature k is used for replacing theta in the formulas five to seven, and the value of the curvature of the preview point and the corresponding weight value can be calculated.
It should be noted that after the preview points are extracted, a topological relationship between every two preview points needs to be calculated, and it can be determined through the topological relationship which of the extracted preview points belong to the same driving track. Specifically, if 10% of track points in the search range of the two preview points are on the same track, the two preview points are considered to be communicated with each other and belong to the same driving track.
After the attribute value of the preview point is obtained through calculation, the driving path needs to be calculated according to the attribute value of the preview point. If the generation process of the driving path is executed by the automatic driving equipment, after the cloud processing end calculates the attribute value of the pre-aiming point, the pre-aiming point comprising the attribute value is sent to the automatic driving equipment, and the automatic driving equipment calculates the driving path according to the attribute value of the pre-aiming point. If the generation process of the driving path is executed by the cloud processing end, the cloud processing end calculates to obtain the attribute of the pre-aiming point, and then calculates to obtain the driving path according to the attribute value of the pre-aiming point. Reference is made in detail to the following examples.
A local path planning method disclosed in another embodiment of the present application, referring to fig. 12, includes the steps of: s1201 to S1204, wherein S1201 to S1204 may refer to steps S201 to S204 in the embodiment corresponding to fig. 2, which is not described herein again; the local path planning method disclosed in this embodiment further includes the steps of:
and S1205, calculating to obtain a plurality of driving paths between the front and rear preview points according to the attribute values of the front and rear preview points on the same driving track.
Two preview points at front and back positions are selected, and a plurality of smooth curves between the two preview points are calculated according to the coordinates, the head direction and the curvature of the two preview points in the global coordinate system, as shown in fig. 13.
It should be further noted that, in step S1204, each preview point calculates the obtained multiple values of the head direction and the multiple values of the curvature, so that when a smooth curve between two preview points at front and rear positions is obtained, the multiple values of the head direction and the multiple values of the curvature may be cross-combined, and each combination and the coordinate of the preview point in the global coordinate system can generate a curve.
Specifically, in the driving process of the automatic driving device, a current track point of the automatic driving device is determined, a pre-aiming point (which may be called a previous pre-aiming point) corresponding to the track point is determined, and values of various attributes of the pre-aiming point are obtained. And selecting the next preview point on the running track to which the preview point corresponding to the current track point of the automatic driving equipment belongs. And calculating to obtain a plurality of smooth curves between the two preview points according to different attribute values of the previous preview point and the next preview point. And by analogy, continuously determining the next preview point in the driving track where the previous preview point is located, and calculating the driving path between the two preview points.
And S1206, respectively calculating the cost value of each driving path, and selecting the driving path with the minimum cost value in the plurality of driving paths as the optimal driving path.
Calculating the cost value C of each driving path by using a formula eightostAnd selecting the running path with the minimum cost value as the optimal running path.
In the formula VIII, CcolRepresenting the cost of collision with an obstacle, if there is a collision with an obstacle in the path of travel, Ccol3000, otherwise Ccol＝0。CsThe mileage cost of each driving path, specifically the total length of each driving path. CθThe cost is caused by the excessive change rate of the head direction and the head direction, and particularly the accumulation of the head direction difference between two preview points in each driving path. CkThe cost of excessive curvature and rate of change of curvature is expressed, specifically, the accumulation of curvature difference between two preview points in each driving path.Respectively is the inverse of the weight value corresponding to the head direction and the curvature of the next preview point in each driving path.
Another embodiment of the present application discloses a cloud processing terminal, as shown in fig. 14, including:
a projection unit 1401 for projecting the plurality of travel trajectories to an image plane, respectively, to obtain trajectory images of the plurality of travel trajectories; wherein the plurality of travel tracks include the same origin and destination.
Optionally, in another embodiment of the present application, the projection unit 1401 includes:
and the selection unit is used for respectively selecting a plurality of track points on each driving track.
And the conversion unit is used for converting the coordinates of the track points selected on each driving track into coordinates under an image coordinate system.
And the shadow projecting unit is used for projecting the track points selected on each driving track to an image plane according to the coordinates of the track points selected on each driving track under the image coordinate system to obtain a track image. Optionally, a gray value of a track point selected on each of the driving tracks in the track image is used for representing a weight value of the driving track.
For a specific working process of the unit included in the projection unit disclosed in the embodiment of the present application, reference may be made to the content of the embodiment corresponding to fig. 3, which is not described herein again.
The processing unit 1402 is configured to perform smoothing processing on the trajectory image to obtain a trajectory density thermodynamic diagram.
An extracting unit 1403, configured to extract a preview point according to the key point in the trajectory density thermodynamic diagram; wherein, the key points are track points reflecting the shape of the driving track.
Optionally, in another embodiment of the present application, the extracting unit 1403 includes:
the dividing unit is used for transversely dividing the track density thermodynamic diagram by taking key points of the point-taking driving track as dividing points; the point-taking driving track is one or more driving tracks in the track image, and the key points are any one or two of two track points with zero curvature difference in the point-taking driving track.
And the first point taking unit is used for selecting a point of which the density heat force value is a wave peak value from points of the track density thermodynamic diagram on the transverse dividing line as a preview point.
For a specific working process of the unit included in the extraction unit disclosed in the embodiment of the present application, reference may be made to the content of the embodiment corresponding to fig. 6, which is not described herein again.
Optionally, in another embodiment of the present application, the extracting unit 1403 includes:
and the line taking unit is used for extracting the intersection boundary line in the track density thermodynamic diagram.
And the second point taking unit is used for selecting a point of which the density heat value is a wave peak value from the points of the track density thermodynamic diagram on the boundary line of the intersection as a preview point.
For a specific working process of the unit included in the extraction unit disclosed in the embodiment of the present application, reference may be made to the content of the embodiment corresponding to fig. 9, and details are not described here again.
The first calculating unit 1404 is configured to calculate attribute values of the pre-aiming point, where the attributes of the pre-aiming point include coordinates, head orientation, and curvature.
For a specific working process of a unit in a cloud processing end disclosed in the embodiment of the present application, reference may be made to the content of the embodiment corresponding to fig. 2, which is not described herein again.
Optionally, in another embodiment of the present application, referring to fig. 14, the cloud processing end further includes:
the second calculating unit 1405 is configured to calculate, according to the attribute values of the front and rear preview points on the same driving track, multiple driving paths between the front and rear preview points.
And the preference unit 1406 is configured to calculate a cost value of each driving route, and select a driving route with the smallest cost value from the multiple driving routes as the optimal driving route.
In this embodiment, the specific working processes of the two units can refer to the content of the embodiment corresponding to fig. 12, and are not described herein again.
Another embodiment of the present application discloses a cloud processing terminal, as shown in fig. 15, including: the processor 1501 and the memory 1502 further include a power supply, an operating system installed on hardware, and the like, which are not specifically listed in fig. 15, but do not limit the network device in the embodiment of the present application. In some embodiments of the present application, the processor 1501 and the memory 1502 may be connected by a bus or other means, which is not limited herein. Fig. 15 illustrates an example in which the processor 1501 and the memory 1502 are connected to each other via a bus.
The processor 1501 is used for controlling the operation of the cloud processing side, and may also be called a Central Processing Unit (CPU).
The memory 1502 may include read-only memory (ROM) and Random Access Memory (RAM), and may also be other memory or storage media and provide instructions and data to the processor 1501. A portion of the memory 1502 may also include non-volatile random access memory (NVRAM). The memory 1502 stores an operating system and operating instructions, executable modules or data structures, or a subset or an expanded set thereof, wherein the operating instructions can include various operating instructions for performing various operations. The operating system may include various system programs for implementing various basic services and for handling hardware-based tasks. The memory 1502 also stores data, programs, and the like according to the embodiments of the present application. The processor 1501 is configured to execute the program in the memory 1502 to perform the method executed by the cloud processing side in each of the above embodiments.
Processor 1501 may be an integrated circuit chip having signal processing capabilities. In the implementation process of the embodiment of the present application, each step executed by the cloud processing end in the embodiment of the present application may be completed by an integrated logic circuit of hardware in the processor 1501 or an instruction in the form of software. The processor 1501 may be a general-purpose processor, a Digital Signal Processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component. The various methods, steps, and logic blocks disclosed in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present application may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The storage medium is located in the memory 1502 or the processor 1501, and the processor 1501 reads information in the memory 1502 or itself, and completes the steps of the configuration method of the network device according to the embodiment of the present application in combination with hardware thereof.
In the above-described embodiments of the present application, the implementation may be wholly or partially realized by software, hardware, or a combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. The procedures or functions described in accordance with the embodiments of the present application are all or partially generated when the computer program instructions are loaded and executed on a computer, which may be through a computer, a special purpose computer, a computer network, or other editable device. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another computer-readable storage medium, such as: the computer instructions may be transmitted from one website site, computer, server, or data center to another website site, computer, server, or data center by wire (e.g., coaxial cable, twisted pair, fiber optics) or wirelessly (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device including one or more available media integrated servers, data centers, and the like. The usable medium may be a magnetic medium (e.g., floppy disks, hard disks, magnetic tape), an optical medium (e.g., compact disks), or a semiconductor medium (e.g., Solid State Disks (SSDs)), among others.
Claims (13)
1. A method of local path planning, comprising:
projecting the plurality of driving tracks to an image plane respectively to obtain track images of the plurality of driving tracks; wherein the plurality of travel tracks comprise the same origin and destination;
smoothing the track image to obtain a track density thermodynamic diagram;
extracting a preview point according to a key point in the track density thermodynamic diagram; wherein the key points are track points reflecting the shape of the driving track;
and calculating to obtain the attribute value of the preview point, wherein the attribute of the preview point comprises a coordinate, a head direction and a curvature.
2. The method of claim 1, wherein projecting the plurality of travel paths onto an image plane to obtain a path image of the plurality of travel paths comprises:
respectively selecting a plurality of track points on each driving track;
converting the coordinates of the track points selected on each driving track into coordinates under an image coordinate system;
and projecting the track points selected on each driving track to an image plane according to the coordinates of the track points selected on each driving track under the image coordinate system to obtain the track image.
3. The method according to claim 2, characterized in that the gray value of the selected track point on each driving track in the track image is used for representing the weight value of the driving track.
4. The method according to any one of claims 1-3, wherein the extracting the pre-target point in the trajectory density thermodynamic diagram comprises:
taking key points of a point-taking driving track as dividing points, and transversely dividing the track density thermodynamic diagram; the point-taking driving track is one or more driving tracks in the track image, and the key points are any one or two of two track points with zero curvature difference in the point-taking driving track;
and selecting a point of which the density heat force value is a wave peak value from the points of the track density thermodynamic diagram on the transverse dividing line as the preview point.
5. The method according to any one of claims 1-4, wherein the extracting the pre-target point in the trajectory density thermodynamic diagram comprises:
extracting a road junction boundary line in the track density thermodynamic diagram;
and selecting a point of which the density heat value is a wave peak value from the points of the track density thermodynamic diagram on the boundary line of the road junction as the preview point.
6. The method according to any one of claims 1-5, further comprising:
calculating to obtain a plurality of driving paths between the front and rear pre-aiming points according to the attribute values of the front and rear pre-aiming points on the same driving track;
and respectively calculating the cost value of each driving path, and selecting the driving path with the minimum cost value in the driving paths as an optimal driving path.
7. A cloud processing terminal, comprising:
the projection unit is used for projecting the plurality of driving tracks to an image plane respectively to obtain track images of the plurality of driving tracks; wherein the plurality of travel tracks comprise the same origin and destination;
the processing unit is used for smoothing the track image to obtain a track density thermodynamic diagram;
the extraction unit is used for extracting a preview point according to a key point in the track density thermodynamic diagram; wherein the key points are track points reflecting the shape of the driving track;
and the first calculating unit is used for calculating and obtaining the attribute value of the preview point, wherein the attribute of the preview point comprises coordinates, head direction and curvature.
8. The cloud processing terminal according to claim 7, wherein the projection unit comprises:
the selection unit is used for respectively selecting a plurality of track points on each driving track;
the conversion unit is used for converting the coordinates of the track points selected on each driving track into coordinates under an image coordinate system;
and the shadow projecting unit is used for projecting the track points selected on each running track to an image plane according to the coordinates of the track points selected on each running track under the image coordinate system to obtain the track image.
9. The cloud processing terminal according to claim 8, wherein a gray value of a selected track point on each driving track in the track image is used to represent a weight value of the driving track.
10. The cloud processing terminal according to any one of claims 7 to 9, wherein the extraction unit includes:
the dividing unit is used for transversely dividing the track density thermodynamic diagram by taking key points of the point-taking driving track as dividing points; the point-taking driving track is one or more driving tracks in the track image, and the key points are any one or two of two track points with zero curvature difference in the point-taking driving track;
and the first point taking unit is used for selecting a point of which the density heat force value is a wave peak value from the points of the track density thermodynamic diagram on the transverse dividing line as the preview point.
11. The cloud processing terminal according to any one of claims 7 to 10, wherein the extraction unit includes:
the line taking unit is used for extracting a road junction boundary line in the track density thermodynamic diagram;
and the second point taking unit is used for selecting a point of which the density heat value is a wave peak value from the points of the track density thermodynamic diagram on the boundary line of the intersection as the preview point.
12. The cloud processing terminal according to any one of claims 7 to 11, further comprising:
the second calculation unit is used for calculating and obtaining a plurality of driving paths between the front and rear pre-aiming points according to the attribute values of the front and rear pre-aiming points on the same driving track;
and the preference unit is used for respectively calculating the cost value of each driving path and selecting the driving path with the minimum cost value in the driving paths as the optimal driving path.
13. A cloud processing terminal, comprising: a processor and a memory, wherein:
the memory for storing computer program code;
the processor is configured to execute the memory-stored code to perform the method of any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810142721.4A CN108519094B (en) | 2018-02-11 | 2018-02-11 | Local path planning method and cloud processing terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810142721.4A CN108519094B (en) | 2018-02-11 | 2018-02-11 | Local path planning method and cloud processing terminal |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108519094A true CN108519094A (en) | 2018-09-11 |
| CN108519094B CN108519094B (en) | 2022-03-25 |
Family
ID=63433218
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810142721.4A Active CN108519094B (en) | 2018-02-11 | 2018-02-11 | Local path planning method and cloud processing terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108519094B (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109059944A (en) * | 2018-06-06 | 2018-12-21 | 上海国际汽车城（集团）有限公司 | Motion planning method based on driving habit study |
| CN109324620A (en) * | 2018-09-25 | 2019-02-12 | 北京主线科技有限公司 | The dynamic trajectory planing method for carrying out avoidance based on lane line parallel offset and overtaking other vehicles |
| CN109635053A (en) * | 2018-10-31 | 2019-04-16 | 百度在线网络技术（北京）有限公司 | Quality detecting method, device, system and the storage medium of map |
| CN109871016A (en) * | 2019-02-20 | 2019-06-11 | 百度在线网络技术（北京）有限公司 | A kind of steered reference line generation method, device, vehicle and server |
| CN111062970A (en) * | 2019-12-10 | 2020-04-24 | 广州电力工程监理有限公司 | Track generation method and system based on thermodynamic diagram |
| CN111401767A (en) * | 2020-03-25 | 2020-07-10 | 沈树新 | Logistics distribution hotspot pushing method and device, logistics distribution system and server |
| CN111462015A (en) * | 2020-04-08 | 2020-07-28 | Oppo广东移动通信有限公司 | Map track processing method and device, electronic equipment and storage medium |
| CN111615618A (en) * | 2018-12-26 | 2020-09-01 | 百度时代网络技术（北京）有限公司 | Polynomial fitting based reference line smoothing method for high speed planning of autonomous vehicles |
| CN112101490A (en) * | 2020-11-20 | 2020-12-18 | 支付宝(杭州)信息技术有限公司 | Thermodynamic diagram conversion model training method and device |
| CN112198964A (en) * | 2020-11-03 | 2021-01-08 | 北京歌尔泰克科技有限公司 | Function implementation method and device on wearable device |
| CN112669340A (en) * | 2020-12-23 | 2021-04-16 | 佛山市城市规划设计研究院 | GIS big data analysis-based public facility site selection method and system |
| CN113365211A (en) * | 2021-04-19 | 2021-09-07 | 中科劲点（北京）科技有限公司 | Epidemic situation forecasting method based on activity track, device, medium and electronic equipment thereof |
| CN113393694A (en) * | 2021-05-07 | 2021-09-14 | 杭州数知梦科技有限公司 | Bus backbone line grabbing method |
| CN113844460A (en) * | 2020-06-28 | 2021-12-28 | 华为技术有限公司 | Vehicle control method and device and vehicle |
| CN114392928A (en) * | 2021-12-20 | 2022-04-26 | 武汉华工赛百数据系统有限公司 | Robot sorting center control system based on visual identification |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104732789A (en) * | 2015-04-08 | 2015-06-24 | 山东大学 | Method for generating road network map based on bus GPS data |
| CN104990551A (en) * | 2015-06-19 | 2015-10-21 | 中国人民解放军国防科学技术大学 | Indoor and outdoor co-navigation method and system based on trajectory extraction |
| CN105788273A (en) * | 2016-05-18 | 2016-07-20 | 武汉大学 | Urban intersection automatic identification method based on low precision space-time trajectory data |
| US20160253707A1 (en) * | 2014-02-19 | 2016-09-01 | Fuel Signal | Methods and systems for tracking users |
| CN106227726A (en) * | 2016-06-30 | 2016-12-14 | 北京航空航天大学 | A kind of path extraction method based on track of vehicle data |
| CN106383868A (en) * | 2016-09-05 | 2017-02-08 | 电子科技大学 | Road network-based spatio-temporal trajectory clustering method |
| CN107358314A (en) * | 2017-06-20 | 2017-11-17 | 深圳中兴网信科技有限公司 | The processing method and system of a kind of thermodynamic chart |
| CN107462243A (en) * | 2017-08-04 | 2017-12-12 | 浙江大学 | A kind of cloud control automatic Pilot task creating method based on high-precision map |
-
2018
- 2018-02-11 CN CN201810142721.4A patent/CN108519094B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160253707A1 (en) * | 2014-02-19 | 2016-09-01 | Fuel Signal | Methods and systems for tracking users |
| CN104732789A (en) * | 2015-04-08 | 2015-06-24 | 山东大学 | Method for generating road network map based on bus GPS data |
| CN104990551A (en) * | 2015-06-19 | 2015-10-21 | 中国人民解放军国防科学技术大学 | Indoor and outdoor co-navigation method and system based on trajectory extraction |
| CN105788273A (en) * | 2016-05-18 | 2016-07-20 | 武汉大学 | Urban intersection automatic identification method based on low precision space-time trajectory data |
| CN106227726A (en) * | 2016-06-30 | 2016-12-14 | 北京航空航天大学 | A kind of path extraction method based on track of vehicle data |
| CN106383868A (en) * | 2016-09-05 | 2017-02-08 | 电子科技大学 | Road network-based spatio-temporal trajectory clustering method |
| CN107358314A (en) * | 2017-06-20 | 2017-11-17 | 深圳中兴网信科技有限公司 | The processing method and system of a kind of thermodynamic chart |
| CN107462243A (en) * | 2017-08-04 | 2017-12-12 | 浙江大学 | A kind of cloud control automatic Pilot task creating method based on high-precision map |
Non-Patent Citations (4)
| Title |
|---|
| 崔邓: "基于智能手机轨迹提取停留点的时空聚类算法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 张忠怀: "《自动化应用技术》", 31 July 2001, 兵器工业出版社 * |
| 欧阳鸿等: "基于步行GPS轨迹的路网提取方法", 《计算机与现代化》 * |
| 袁满等: "《移动计算》", 31 August 2015, 哈尔滨工业大学出版社 * |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109059944B (en) * | 2018-06-06 | 2021-08-06 | 上海国际汽车城（集团）有限公司 | Motion planning method based on driving habit learning |
| CN109059944A (en) * | 2018-06-06 | 2018-12-21 | 上海国际汽车城（集团）有限公司 | Motion planning method based on driving habit study |
| CN109324620A (en) * | 2018-09-25 | 2019-02-12 | 北京主线科技有限公司 | The dynamic trajectory planing method for carrying out avoidance based on lane line parallel offset and overtaking other vehicles |
| CN109635053A (en) * | 2018-10-31 | 2019-04-16 | 百度在线网络技术（北京）有限公司 | Quality detecting method, device, system and the storage medium of map |
| CN111615618A (en) * | 2018-12-26 | 2020-09-01 | 百度时代网络技术（北京）有限公司 | Polynomial fitting based reference line smoothing method for high speed planning of autonomous vehicles |
| CN111615618B (en) * | 2018-12-26 | 2023-08-29 | 百度时代网络技术（北京）有限公司 | Polynomial fitting-based reference line smoothing method for high-speed planning of autonomous vehicles |
| CN109871016A (en) * | 2019-02-20 | 2019-06-11 | 百度在线网络技术（北京）有限公司 | A kind of steered reference line generation method, device, vehicle and server |
| CN111062970A (en) * | 2019-12-10 | 2020-04-24 | 广州电力工程监理有限公司 | Track generation method and system based on thermodynamic diagram |
| CN111401767A (en) * | 2020-03-25 | 2020-07-10 | 沈树新 | Logistics distribution hotspot pushing method and device, logistics distribution system and server |
| CN111462015A (en) * | 2020-04-08 | 2020-07-28 | Oppo广东移动通信有限公司 | Map track processing method and device, electronic equipment and storage medium |
| CN113844460A (en) * | 2020-06-28 | 2021-12-28 | 华为技术有限公司 | Vehicle control method and device and vehicle |
| CN113844460B (en) * | 2020-06-28 | 2024-04-12 | 华为技术有限公司 | Vehicle control method and device and vehicle |
| CN112198964A (en) * | 2020-11-03 | 2021-01-08 | 北京歌尔泰克科技有限公司 | Function implementation method and device on wearable device |
| CN112101490B (en) * | 2020-11-20 | 2021-03-02 | 支付宝(杭州)信息技术有限公司 | Thermodynamic diagram conversion model training method and device |
| CN112101490A (en) * | 2020-11-20 | 2020-12-18 | 支付宝(杭州)信息技术有限公司 | Thermodynamic diagram conversion model training method and device |
| CN112669340A (en) * | 2020-12-23 | 2021-04-16 | 佛山市城市规划设计研究院 | GIS big data analysis-based public facility site selection method and system |
| CN113365211A (en) * | 2021-04-19 | 2021-09-07 | 中科劲点（北京）科技有限公司 | Epidemic situation forecasting method based on activity track, device, medium and electronic equipment thereof |
| CN113393694A (en) * | 2021-05-07 | 2021-09-14 | 杭州数知梦科技有限公司 | Bus backbone line grabbing method |
| CN113393694B (en) * | 2021-05-07 | 2022-10-14 | 杭州数知梦科技有限公司 | Bus backbone line grabbing method |
| CN114392928A (en) * | 2021-12-20 | 2022-04-26 | 武汉华工赛百数据系统有限公司 | Robot sorting center control system based on visual identification |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108519094B (en) | 2022-03-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108519094B (en) | Local path planning method and cloud processing terminal | |
| US11086016B2 (en) | Method and apparatus for tracking obstacle | |
| CN109739926B (en) | Method for predicting destination of moving object based on convolutional neural network | |
| CN113593017B (en) | Method, device, equipment and storage medium for constructing surface three-dimensional model of strip mine | |
| CN109270927B (en) | Road data generation method and device | |
| JP6997211B2 (en) | Methods and devices for reducing midpoints in polygons | |
| CN107703945A (en) | A kind of intelligent farm machinery paths planning method of multiple targets fusion | |
| CN108763287A (en) | On a large scale can traffic areas driving map construction method and its unmanned application process | |
| CN114051628B (en) | Method and device for determining target object point cloud set | |
| CN112747755B (en) | Method and device for determining road route, readable storage medium and map updating system | |
| CN112348848A (en) | Information generation method and system for traffic participants | |
| CN110705385B (en) | Method, device, equipment and medium for detecting angle of obstacle | |
| CN113252027B (en) | Underground unmanned vehicle local path planning method, device, equipment and storage medium | |
| WO2024149060A1 (en) | Free space and road edge detection method and apparatus, and related device | |
| CN111738040A (en) | Deceleration strip identification method and system | |
| CN114234991A (en) | Navigation path planning method and device, computer equipment and storage medium | |
| CN111414804B (en) | Identification frame determining method, identification frame determining device, computer equipment, vehicle and storage medium | |
| CN114419877B (en) | Vehicle track prediction data processing method and device based on road characteristics | |
| CN114357843A (en) | Method for carrying out numerical collision experiment simulation aiming at wind power equipment transportation | |
| CN113682322A (en) | Method and device for determining vehicle running path | |
| CN116147653B (en) | Three-dimensional reference path planning method for unmanned vehicle | |
| CN116136417B (en) | Unmanned vehicle local path planning method facing off-road environment | |
| CN113138594A (en) | Automatic driving method and device | |
| CN111337036B (en) | Overlap region data optimization method and device and terminal equipment | |
| CN114705180A (en) | Data correction method, device and equipment for high-precision map and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |