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
- trace
- little
- driving trace
- driving
- point
- 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
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)
- Navigation (AREA)
- Processing Or Creating Images (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
This application involves field of navigation technology more particularly to local paths planning technologies.
Background technology
With the research that deepens continuously of artificial intelligence technology, pilotless automobile, autonomous mobile robot etc. are automatic
Traveling apparatus is widely applied in the production of daily life and industry.
And in the relation technological researching of the automatic runnings equipment such as pilotless automobile, autonomous mobile robot, airmanship
It is its core, and local paths planning is an important link and component part in airmanship research.Specifically, part
Path planning refers to generating an optimal driving path according to the oneself state of current road environment and equipment.
In current local paths planning method, need first to obtain before obtaining optimal driving path it is pre- take aim at a little, and it is pre-
The generation taken aim at a little needs to rely on high-precision map.If cartographic information precision is inadequate, obtained pre- take aim at a little then cannot be satisfied generation
Adapt to the demand of complicated road structure and the driving path of changeable traffic.
Invention content
This application provides a kind of local paths planning method and cloud processing ends, to solve to obtain in no high-precision map
To it is pre- take aim at can not a little generate the driving path for adapting to complicated road structure and changeable traffic the problem of.
To achieve the goals above, it is proposed that scheme it is as follows：
The first aspect of the application provides a kind of local paths planning method, including：A plurality of driving trace is thrown respectively
Shadow obtains the trace image of a plurality of driving trace to the plane of delineation；Wherein, a plurality of driving trace includes identical starting point
The destination and；The trace image is smoothed, track density thermodynamic chart is obtained；In the track density thermodynamic chart
In, it is 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；It calculates
To the pre- attribute value taken aim at a little, 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：It is extracted in the track heating power density thermodynamic chart obtained from according to a plurality of driving trace
Obtain it is pre- take aim at a little, can be to avoid high-precision map be used, solving to take aim in advance caused by not having high-precision map can not a little give birth to
The problem of at the driving path for adapting to complicated road structure and changeable traffic.
In one implementation, described to project to a plurality of driving trace on the plane of delineation, obtain a plurality of driving trace
Trace image, including：Multiple tracing points are chosen respectively on every driving trace；It will be selected on every driving trace
The coordinate of the tracing point taken is converted into the coordinate under image coordinate system；Exist according to the tracing point chosen on driving trace described in every
The tracing point chosen on every driving trace is projected to the plane of delineation, obtains the rail by the coordinate under image coordinate system
Mark image.
In one implementation, gray scale of the tracing point chosen on every driving trace in the trace image
Weighted value of the value for indicating the driving trace.
In one implementation, pre- in the extraction track density thermodynamic chart is taken aim at a little, including：To take a traveling
The key point of track is cut-point, and horizontal partition is carried out to the track density thermodynamic chart；Wherein, described to take the driving trace to be
One or more of driving traces in the trace image, the key point are described to take the driving trace mean curvature difference to be
Any one in zero two tracing points or two；It chooses in the point that the track density thermodynamic chart is located on horizontal partition line
Density heating power value is the point of crest value, pre- is taken aim at a little as described.
In one implementation, pre- in the extraction track density thermodynamic chart is taken aim at a little, including：Extract the rail
Crossing boundary line in mark density thermodynamic chart；Choose density heat in the point that the track density thermodynamic chart is located on the boundary line of crossing
Force value is the point of crest value, pre- is taken aim at a little as described.
In one implementation, further include：According to former and later two pre- categories taken aim at a little on the same driving trace
Property value, be calculated it is described former and later two it is pre- take aim at a little between a plurality of driving path；It calculates separately to obtain every traveling road
The cost value of diameter, and select the driving path of cost value minimum in a plurality of driving path as optimal driving path.
The second aspect of the application provides a kind of cloud processing end, including：Projecting cell, for dividing a plurality of driving trace
The plane of delineation is not projected to, obtains the trace image of a plurality of driving trace；Wherein, a plurality of driving trace includes identical
Begin ground and destination；Processing unit obtains track density thermodynamic chart for being smoothed to the trace image；Extraction
Unit, in the track density thermodynamic chart, being taken aim at a little in advance according to key point extraction；Wherein, the key point is reflection institute
State the tracing point of driving trace shape；First computing unit, it is described pre- to take aim at a little for being calculated the pre- attribute value taken aim at a little
Attribute include coordinate, head be directed toward and curvature.
In one implementation, the projecting cell, including：Selection unit, in every driving trace
Multiple tracing points are chosen respectively；Converting unit, for the coordinate for the tracing point chosen on every driving trace to be converted into
Coordinate under image coordinate system；Subelement is projected, for being sat in image according to the tracing point chosen on driving trace described in every
Coordinate under mark system, projects to the plane of delineation by the tracing point chosen on every driving trace, obtains the trace image.
In one implementation, gray scale of the tracing point chosen on every driving trace in the trace image
Weighted value of the value for indicating the driving trace.
In one implementation, the extraction unit, including：Cutting unit, for take the key of a driving trace
Point is cut-point, and horizontal partition is carried out to the track density thermodynamic chart；Wherein, described to take a driving trace for the trajectory diagram
One or more of driving traces as in, the key point are described to take two rails that a driving trace mean curvature difference is zero
Any one in mark point or two；First takes dot element, is located at horizontal partition line for choosing the track density thermodynamic chart
On point in density heating power value be crest value point, pre- taken aim at a little as described.
In one implementation, the extraction unit, including：Line taking unit, for extracting the track density heating power
Crossing boundary line in figure；Second takes dot element, the point being located on the boundary line of crossing for choosing the track density thermodynamic chart
Middle density heating power value is the point of crest value, pre- is taken aim at a little as described.
In one implementation, further include：Second computing unit, for according to before on the same driving trace
Latter two pre- attribute value taken aim at a little, be calculated it is described former and later two it is pre- take aim at a little between a plurality of driving path；Preferentially unit is used
In calculating separately to obtain the cost value of every driving path, and select the row of cost value minimum in a plurality of driving path
Path is sailed as optimal driving path.
The third aspect of the application provides a kind of cloud processing end, including：Processor and memory, wherein：The storage
Device is for storing computer program code；The processor is used to execute the code of the memory storage, to execute above-mentioned institute
The local paths planning method of introduction.
The fourth aspect of the application provides a kind of computer program product, when the computer product is performed, uses
In above-mentioned the introduced local paths planning method of execution.
The 5th aspect of the application additionally provides a kind of computer readable storage medium, the computer readable storage medium
In be stored with instruction, described instruction is for executing above-mentioned introduced local paths planning method.
Description of the drawings
Fig. 1 is a kind of schematic diagram of local paths planning system disclosed in the embodiment of the present application；
Fig. 2 is a kind of flow chart of local paths planning method disclosed in the embodiment of the present application；
Fig. 3 is a kind of method flow diagram of embodiment of step S201 in the embodiment of the present application；
Fig. 4 is the display diagram of trace image disclosed in the embodiment of the present application；
Fig. 5 is the display diagram of track density thermodynamic chart disclosed in the embodiment of the present application；
Fig. 6 is a kind of method flow diagram of the embodiment for the step S203 that the embodiment of the present application discloses；
Fig. 7 is the disclosed display diagram that horizontal partition is carried out to track density thermodynamic chart of the embodiment of the present application；
Fig. 8 is the displaying of the position and corresponding density heating power value of the point on horizontal partition line disclosed in the embodiment of the present application
Figure；
Fig. 9 is the method flow diagram of the another embodiment for the step S203 that the embodiment of the present application discloses；
Figure 10 is the display diagram of another track density thermodynamic chart disclosed in the embodiment of the present application；
Figure 11 be the embodiment of the present application it is disclosed to take aim in advance be a little that the center of circle draws and justifies the display diagram for looking for tracing point；
Figure 12 is the flow chart of local paths planning method disclosed in another embodiment of the application；
Figure 13 be the embodiment of the present application it is disclosed former and later two it is pre- take aim at a little between a plurality of driving path display diagram；
Figure 14 is the structural schematic diagram of cloud processing end disclosed in the embodiment of the present application；
Figure 15 is the structural schematic diagram of cloud processing end disclosed in another embodiment of the application.
Specific implementation mode
The embodiment of the present application discloses a kind of local paths planning system, as shown in Figure 1, including：Collecting device 101, cloud
Processing end 102 and automatic running equipment 103, wherein collecting device 101, such as：Urban taxi system, onboard navigation system,
Mobile navigation system and high precision collecting vehicle acquire driving trace and traffic information, wherein driving trace includes：Each rail
The coordinate and stroke directions of mark point.The driving trace collected and traffic information are uploaded to by collecting device 101 by network
Cloud processing end 102.Cloud processing end 102 according to vehicle driving trace and traffic information, be calculated it is pre- take aim at a little, and according to taking aim at a little in advance
The track cluster including a plurality of driving path is calculated, and selects optimal driving path from the cluster of track.Alternatively, fortune processing end
102 according to vehicle driving trace and traffic informations, be calculated it is pre- take aim at a little, then pre- take aim at a little is sent to automatic running equipment 103,
The track cluster including a plurality of driving path is a little calculated according to taking aim in advance by automatic running equipment 103, and is selected from the cluster of track
Optimal driving path.
Wherein, local paths planning method disclosed in the embodiment of the present application is applied to cloud processing end.Referring to Fig. 2, including step
Suddenly：
S201, a plurality of driving trace is projected on the plane of delineation, obtains the trace image of a plurality of driving trace.
Cloud processing end 102 receives the driving trace that collecting device 101 uploads, according to identical starting point and identical purpose
The driving trace on ground is classified as a kind of principle, and driving trace is sorted out.For same category of driving trace, projected
To the plane of delineation, the trace image of driving trace is formed.Optionally, it can also will go according to the weight of each driving trace
It sails track and projects to the plane of delineation, form the trace image of driving trace.
Optionally, in another embodiment of the application, as shown in figure 3, a kind of embodiment of step S201 includes：
S301, multiple tracing points are chosen respectively on every driving trace.
Wherein, tracing point is chosen on a driving trace, is the coordinate for obtaining the tracing point on driving trace.And
And each driving trace, same amount of tracing point can be chosen, naturally it is also possible to choose the tracing point of different number.One
As in the case of, the driving trace more smoothed out, the negligible amounts of the tracing point of selection.More tortuous driving trace, selection
The quantity of tracing point is more.
S302, the coordinate for the tracing point chosen on every driving trace is converted into the coordinate under image coordinate system.
Wherein, the coordinate of the tracing point on driving trace is the coordinate under global coordinate system, is carrying out generation local path
When, it needs that therefore the coordinate of the tracing point on driving trace is converted under image coordinate system using the data under image coordinate
Coordinate.
S303, the coordinate according to the tracing point chosen on every driving trace under image coordinate system, by every traveling rail
The tracing point chosen on mark projects to the plane of delineation, obtains the trace image of driving trace.
Wherein, the tracing point chosen on a plurality of driving trace is projected into the plane of delineation respectively, obtained trace image can
As shown in Figure 4.
Optionally, in the trace image of driving trace, the tracing point chosen on every driving trace is on the image plane
Gray value can be also used for indicate driving trace weighted value.Also, gray scale shows that weighted value is bigger more deeply feeling.
Therefore, it before the tracing point chosen on driving trace is projected to the plane of delineation, needs to know every traveling rail
The weighted value of mark.Below for calculating the weighted value of driving trace A, the computational methods of the weighted value of driving trace are carried out detailed
It describes in detail bright.
Least square fitting is carried out to driving trace A, such as formula one：
Y=a0+a1x+a2x2+...+amxmFormula one
Polynomial of order m is established to coordinate x, y of driving trace A, such as formula two：
N tracing point is chosen respectively in driving trace A, and the x of n tracing point, y-coordinate value are substituted into respectively in formula two,
Each coefficient a in formula two can be solved0,a1,a2,...,am, xi、yiIndicate i-th point of coordinate, i=1,2 ..., n.
The middle error of the tracing point of driving trace A is calculated using formula three.
In formula three, υiIndicate the actual value y of the tracing point of driving trace AiWith calculated valueDifference, σxyIndicate traveling rail
The middle error of tracing point in mark A.
Similarly, it is respectively calculated using the method for least square fitting, obtains the middle mistake that the head of driving trace A is directed toward
Difference, the middle error of the middle error of curvature and speed.
Finally, the weighted value Pi of driving trace A is calculated using formula four.
In formula four, σxyIndicate the middle error of the tracing point of driving trace A；σθIn indicating that the head of driving trace A is directed toward
Error；σkIndicate the middle error of the curvature of driving trace A；σVIndicate the middle error of the speed of driving trace A；∝、β、γ、For
Constant.
Optionally, if collecting device 101 acquires and the driving trace uploaded is very long, that can be equal to each driving trace
It is segmented according to mileage, is such as once segmented for every 1 kilometer, obtains trajectory subsections, then to including same starting point and same
The trajectory subsections of destination execute step S201.
S202, trace image is smoothed, obtains track density thermodynamic chart.
Wherein, trace image is smoothed using Gaussian convolution template, obtained track density thermodynamic chart.
Optionally, if in trace image, the gray scale of the projection of each driving trace is used to indicate the driving trace
Weighted value, trace image after being smoothed by that, and obtained track density thermodynamic chart is as shown in figure 5, color is got in figure
It deeply feels and shows that density heating power value is higher, show that the tracing point at this is more intensive, and the weighted value of tracing point is also higher, illustrate these rails
Mark point is the tracing point of the most frequent process of pilot steering.
Specifically, generating the convolution mask of 20*20 using two-dimensional Gaussian function, the volume that step-length is 1 is done to trace image
Product operation, obtains track density thermodynamic chart.
Pre- taking aim at a little in S203, extraction track density thermodynamic chart.
Wherein, it in the density thermodynamic chart of track, is taken aim at a little in advance according to key point extraction.Wherein, key point is reflection traveling rail
The tracing point of mark shape, if track density thermodynamic chart includes curved section, key point includes：Driving trace mean curvature difference is
Zero tracing point；If track density thermodynamic chart includes the driving trace intersected, key point includes：Reflect driving trace Road
The tracing point of mouth.
In the track heating power density thermodynamic chart obtained from according to a plurality of driving trace extraction obtain it is pre- take aim at a little, can be to avoid
Using high-precision map, solves the road knot for being taken aim in advance caused by not having high-precision map and can not a little generating and adapting to complexity
The problem of structure and the driving path of changeable traffic.
Also, it is that density heating power value is the tracing point of crest value in the density thermodynamic chart of track to take aim in advance a little, and therefore, taking aim in advance is a little
Tracing point in trace image in the higher driving trace of weighted value shows frequently to pass through the point when pilot steering.Foundation is taken aim in advance
Point generation includes the track cluster of a plurality of driving path, and each driving path in the cluster of track can be used as in local paths planning
Optimal driving path option, driving path can be made closer to pilot steering track, meet pilot steering custom.
Optionally, in another embodiment of the application, referring to Fig. 6, a kind of embodiment of step S203 includes：
S601, to take the key point of a driving trace as cut-point, to track density thermodynamic chart carry out horizontal partition.
Wherein, it is the one or more of driving traces in trace image to take a driving trace.Optionally, trajectory diagram is chosen
The highest driving trace of weight as in is to take a driving trace, alternatively, the weighted value chosen in trace image is several higher
Driving trace is used as and takes a driving trace.It is that take a driving trace mean curvature difference be zero to take the key point of a driving trace
Any one in two tracing points or two.
To take the key point of a driving trace as cut-point, along the direction perpendicular with the tangent line of the cut-point to track
Density thermodynamic chart carries out horizontal partition, forms the horizontal partition line of track density thermodynamic chart.Also, refer to laterally：With traveling
There is the direction of intersection in the direction of track.
It should also be noted that, in one takes a driving trace, tracing point that curvature difference is zero may have it is multiple, because
This, different location that can be on the density thermodynamic chart of track carries out horizontal partition.
S602, the point for taking density heating power value in the point that track density thermodynamic chart is located on horizontal partition line to be crest value are
It takes aim at a little in advance.
Referring to Fig. 7, to take the key point of a driving trace as cut-point, horizontal partition is carried out to track density thermodynamic chart,
Horizontal partition line can be formed on the density thermodynamic chart of track.It is distributed on horizontal partition line and is under the jurisdiction of the more of track density thermodynamic chart
A, each point has corresponding density heating power value.Referring to Fig. 8, horizontal axis indicates the point on horizontal partition line at lateral minute in figure
Position on secant, horizontal axis indicate the corresponding density heating power value of point on horizontal partition line.Selection density heating power value is crest value
Point, i.e. dot in figure, which as takes aim at a little in advance, and position a little is as taken aim in the position of the point in advance.Specifically, according to density
Heating power value is the value on the horizontal axis of the point of crest value, the coordinate on the density thermodynamic chart of track of the point is calculated, then should
Coordinate is converted into the coordinate under global coordinate system.
Optionally, in another embodiment of the application, referring to Fig. 9, the another embodiment of step S203 includes：
Crossing boundary line in S901, extraction track density thermodynamic chart.
The crossing region in the density thermodynamic chart of track, extraction can be determined expanding, by way of the image of edge detection
The boundary line in outlet region, i.e. crossing boundary line, as shown in the straight line in Figure 10.
S902, the point for taking density heating power value in the point that track density thermodynamic chart is located on the boundary line of crossing to be crest value are
It takes aim at a little in advance.
Wherein, the specific implementation process of this step can be found in the content of step S602 in the embodiment of corresponding diagram 6, herein not
It repeats again.
S204, the pre- attribute value taken aim at a little is calculated.
Wherein, the attribute taken aim in advance a little includes coordinate, head direction and curvature.
In step S203, in the density thermodynamic chart of track extraction obtain pre- taking aim at a little, in particular to looking in track density heating power
Position in figure, i.e. coordinate.Also, take aim at a little that coordinate is image coordinate in the density thermodynamic chart of track in advance, after obtaining image coordinate,
It also needs to be converted into world coordinates.
Taken aim in advance a little for the center of circle, pre-determined distance (such as 0.5 meter) is that radius draws circle, and the circle of formation is search range.Foundation
The head for falling the tracing point in search range is directed toward and curvature, corresponding to generate head direction and the curvature taken aim in advance a little.
Specifically, being illustrated for calculating the head direction taken aim in advance a little.Assuming that the tracing point fallen in circle have it is N number of, according to
It is directed toward according to the head of N number of tracing point, using formula five or formula six, the pre- head taken aim at a little can be calculated and be directed toward.
In formula five and formula six, m is default value, the hop count for indicating to divide, can be according to available accuracy needs
It is adjusted, the interval that general warranty head is directed toward is less than 1 °.J=0,1 ..., m.
Head is calculated using formula seven and is directed toward corresponding weighted value.
Wherein, if the head being calculated is directed toward corresponding weighted valueLess than threshold value, then it is assumed that θjFor rough error, need by
It is rejected.
It is described in detail below with an example.Referring to Figure 11, to take aim at point P in advance as the center of circle, 0.5 meter is drawn circle for radius,
10 tracing points are shared in circle.Also, the minimum value and maximum value that the head of 10 points is directed toward are respectively 88.6 ° and 92.2 °, if m
=4.
Then
Pre- corresponding 5 (m+1) head direction values of point P of taking aim at, which are calculated, using formula five is respectively：
θ0=00.9+88.6=88.6
θ1=10.9+88.6=89.5
θ2=20.9+88.6=90.4
θ3=30.9+88.6=91.3
θ4=40.9+88.6=92.2
Recycle formulaCalculating corresponding weighted value is：
Wherein,Less than threshold value 0.05, it is believed that θ4For rough error, rejected.
Similarly, the θ in five~formula of formula seven is replaced with curvature k respectively, taking for the pre- curvature taken aim at a little can be calculated
Value and its corresponding weighted value.
It should also be noted that, after extracting pre- take aim at a little, it is also necessary to opening up between in addition calculating each two is taken aim at a little in advance
Flutter relationship, by the topological relation can determine to extract it is pre- take aim at a little in which has be to belong to a driving trace.Tool
Body, judge there is 10% tracing point in two pre- search ranges taken aim at a little in identical strip path curve, then it is assumed that the two are pre-
It takes aim at and is a little interconnected, belong to a driving trace.
After the pre- attribute value taken aim at a little is calculated, need, according to the attribute value taken aim in advance a little, to calculate driving path.If traveling
The generating process in path is executed by automatic running equipment, then cloud processing end is calculated after the pre- attribute value taken aim at a little, can will be wrapped
Pre- take aim at for including attribute value is a little sent to automatic running equipment, and row is calculated according to the attribute value taken aim in advance a little by automatic running equipment
Sail path.If the generating process of driving path is executed by cloud processing end itself, the pre- attribute taken aim at a little is calculated in that cloud processing end
And then driving path is calculated according to the attribute value taken aim in advance a little.For details, reference can be made to the contents of following embodiments.
A kind of local paths planning method disclosed in another embodiment of the application, referring to Figure 12, including step：S1201~
S1204, wherein S1201~S1204 can be found in step S201~S204 in the embodiment of corresponding diagram 2, and details are not described herein again；
Local paths planning method disclosed in the present embodiment further includes step：
S1205, according to former and later two pre- attribute values taken aim at a little on the same driving trace, it is pre- that former and later two are calculated
A plurality of driving path between taking aim at a little.
Wherein, two in front and back position are selected to take aim at a little in advance, the pre- coordinates taken aim at a little under global coordinate system of foundation two,
Head is directed toward and curvature, be calculated two it is pre- take aim at a little between a plurality of smoothed curve, as shown in figure 13.
It should also be noted that, in step S1204, the multiple values and song that the head being a little calculated is directed toward each are taken aim in advance
Multiple values of rate, therefore, obtain two of front and back position it is pre- take aim at a little between smoothed curve when, multiple values of head direction
With the multiple values of curvature can be with combined crosswise, each coordinate for combining and taking aim in advance a little under global coordinate system can generate one
Curve.
Specifically, autopilot facility is in the process of moving, it is first determined autopilot facility current trace points, determining should
Tracing point it is corresponding it is pre- take aim at point (can be referred to as previous pre- take aim at a little), and obtain the pre- value for taking aim at each attribute a little.Certainly
Dynamic steer current trace points it is corresponding it is pre- take aim at a little belonging to driving trace on selection obtain the latter and take aim in advance a little.According to previous
It is a it is pre- take aim at a little and the latter takes aim at different attribute values a little in advance, be calculated two take aim at a little in advance between a plurality of smoothed curve.With
This analogizes, and constantly determines that previous pre- the latter taken aim in a driving trace at place is taken aim at a little in advance, carries out two and take aim at point in advance
Between driving path calculating.
S1206, it calculates separately to obtain the cost value of every driving path, and selects cost value in a plurality of driving path minimum
Driving path as optimal driving path.
Wherein, the cost value C of every driving path is calculated using formula eightost, and select the traveling of cost value minimum
Path is optimal driving path.
In formula eight, CcolThe collision cost of barrier is indicated, if there is the collision with barrier, C in driving pathcol
=3000, otherwise Ccol=0.CsIt is the mileage cost of every driving path, the total length of specially every driving path.CθFor head
It is directed toward the cost for the excessive generation of change rate being directed toward with head, the head between two in specially every driving path take aim at a little in advance refers to
To the cumulative of difference.CkIndicate the cost of the excessive generation of change rate of curvature and curvature, two in specially every driving path
It is a it is pre- take aim at a little between curvature difference it is cumulative.The latter is taken aim at a little in advance in respectively every driving path
Head be directed toward corresponding with curvature weighted value inverse.
Another embodiment of the application discloses a kind of cloud processing end, as shown in figure 14, including：
Projecting cell 1401 obtains a plurality of driving trace for a plurality of driving trace to be projected to the plane of delineation respectively
Trace image；Wherein, a plurality of driving trace includes identical starting point and destination.
Optionally, in another embodiment of the application, projecting cell 1401, including：
Selection unit, for choosing multiple tracing points respectively on every driving trace.
Converting unit, the seat for being converted into the coordinate for the tracing point chosen on every driving trace under image coordinate system
Mark.
Subelement is projected, it, will for the coordinate according to the tracing point chosen on every driving trace under image coordinate system
The tracing point chosen on every driving trace projects to the plane of delineation, obtains trace image.Optionally, every driving trace
Gray value of the tracing point of upper selection in trace image is used to indicate the weighted value of driving trace.
The specific work process for the unit that projecting cell disclosed in the embodiment of the present application includes can be found in the implementation of corresponding diagram 3
The content of example, details are not described herein again.
Processing unit 1402 obtains track density thermodynamic chart for being smoothed to trace image.
Extraction unit 1403, in the density thermodynamic chart of track, being taken aim at a little in advance according to key point extraction；Wherein, key point
It is the tracing point for reflecting driving trace shape.
Optionally, in another embodiment of the application, extraction unit 1403, including：
Cutting unit, for take the key point of a driving trace as cut-point, being carried out laterally to track density thermodynamic chart
Segmentation；Wherein, it is the one or more of driving traces in trace image to take a driving trace, and key point is to take a driving trace
Any one in two tracing points that mean curvature difference is zero or two.
First takes dot element, is for choosing density heating power value in the point that track density thermodynamic chart is located on horizontal partition line
The point of crest value, as taking aim at a little in advance.
The specific work process for the unit that extraction unit disclosed in the embodiment of the present application includes can be found in the implementation of corresponding diagram 6
The content of example, details are not described herein again.
Optionally, in another embodiment of the application, extraction unit 1403, including：
Line taking unit, for extracting the crossing boundary line in the density thermodynamic chart of track.
Second takes dot element, is for choosing density heating power value in the point that track density thermodynamic chart is located on the boundary line of crossing
The point of crest value, as taking aim at a little in advance.
The specific work process for the unit that extraction unit disclosed in the embodiment of the present application includes can be found in the implementation of corresponding diagram 9
The content of example, details are not described herein again.
First computing unit 1404, for the pre- attribute value taken aim at a little to be calculated, the attribute of taking aim in advance a little includes that coordinate, head refer to
To and curvature.
The specific work process of unit in cloud processing end disclosed in the embodiment of the present application, reference can be made to the implementation of corresponding diagram 2
The content of example, details are not described herein again.
Optionally, in another embodiment of the application, referring to Figure 14, cloud processing end further includes：
Second computing unit 1405, for according to former and later two pre- attribute values taken aim at a little on the same driving trace, meter
Calculate obtain former and later two it is pre- take aim at a little between a plurality of driving path.
Preferentially unit 1406 obtain the cost value of every driving path for calculating separately, and select a plurality of driving path
The driving path of middle cost value minimum is as optimal driving path.
In the present embodiment, the specific work process of said two units can be found in the content of the embodiment of corresponding diagram 12, this
Place repeats no more.
Another embodiment of the application discloses a kind of cloud processing end, as shown in figure 15, including：Processor 1501 and memory
1502, further include the parts such as power supply and the operating system on hardware, specifically does not enumerate out in fig.15,
But the network equipment in the embodiment of the present application is not constituted and limited.In some embodiments of the present application, 1501 He of processor
Memory 1502 can be attached by bus or other means, not limited herein specifically.Wherein, with processor in Figure 15
1501 connected by bus with memory 1502 for illustrated.
Processor 1501 is used to control the operation of cloud processing end, can also be known as central processing unit (English：central
Processing unit, CPU).
Memory 1502 may include read-only memory (English：Read-only memory, ROM) and arbitrary access deposit
Reservoir (English：Random access memory, RAM), it can be with other memories either storage medium, and to processor
1501 provide instruction and data.The a part of of memory 1502 can also include nonvolatile RAM (English：
Non-volatile random access memory, NVRAM).Memory 1502 be stored with operating system and operational order,
Executable modules or data structures either their subset or their superset, wherein operational order may include respectively
Kind operational order, various operational orders are for realizing various operations.Operating system may include various system programs, for realizing each
Kind basic business and the hardware based task of processing.Memory 1502 be also stored with data involved by the embodiment of the present application,
Program etc..Processor 1501 is by the program in run memory 1502, for completing at each above-mentioned embodiment medium cloud
Manage the method that end executes.
Processor 1501 can be a kind of IC chip, the processing capacity with signal.In the embodiment of the present application reality
During now, each step performed by the embodiment of the present application medium cloud processing end can pass through the integrated of the hardware in processor 1501
The instruction of logic circuit or software form is completed.Above-mentioned processor 1501 can be general processor, Digital Signal Processing
Device (English：Digital signal processing, DSP), application-specific integrated circuit (English：application-specific
Integrated circuit, ASIC), field programmable gate array (English：Field-programmable gate array,
FPGA) either other programmable logic device, discrete gate or transistor logic, discrete hardware components.May be implemented or
Person executes disclosed each method, step and logic diagram in the embodiment of the present application.General processor can be microprocessor or
Person's processor can also be any conventional processor etc..The step of method in conjunction with disclosed in the embodiment of the present application, can be straight
Connect and be presented as that hardware decoding processor executes completion, or in decoding processor hardware and software module combination executed
At.Software module can be located at random access memory, and flash memory, read-only memory, programmable read only memory or electrically-erasable can
In the storage medium of this fields such as programmable memory, register maturation.The storage medium is located at memory 1502 or processor
1501, processor 1501 reads memory 1502 or the information in itself, and the network of the embodiment of the present application is completed in conjunction with its hardware
The step of configuration method of equipment.
In the above embodiments of the present application, can in whole or in part by software, hardware or a combination thereof realize.
When implemented in software, it can realize in the form of a computer program product in whole or in part.The computer program
Product includes one or more computer instruction.When loading on computers and executing the computer program instructions, all
Or partly generate according to the flow or function described in the embodiment of the present application, the computer can be by computer, specially
With computer, computer network or other editable devices.The computer instruction can be stored in computer-readable storage
In medium, or from a computer readable storage medium to the transmission of another computer readable storage medium, such as：The meter
The instruction of calculation machine can pass through wired (such as coaxial cable, multiple twin from a web-site, computer, server or data center
Line, optical fiber) or wireless (such as infrared, wireless, microwave etc.) mode to another web-site, computer, server or number
It is transmitted according to center.The computer readable storage medium can be any usable medium that can access of computer either
The data storage devices such as server, the data center integrated including one or more usable medium.The usable medium can be with
It is magnetic medium, (such as：Floppy disk, hard disk, tape), optical medium (such as：CD) or semiconductor medium (such as solid-state is hard
Disk (SSD)) etc..
Claims (13)
1. a kind of local paths planning method, which is characterized in that 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, described 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 the reflection traveling
The tracing point of trajectory 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.
2. according to the method described in claim 1, it is characterized in that, described project to a plurality of driving trace on the plane of delineation,
The trace image of a plurality of driving trace is obtained, including：
Multiple tracing points are chosen respectively on every driving trace；
The coordinate coordinate for the tracing point chosen on every driving trace being converted under image coordinate system；
According to coordinate of the tracing point chosen on driving trace described in every under image coordinate system, by every driving trace
The tracing point of upper selection projects to the plane of delineation, obtains the trace image.
3. according to the method described in claim 2, it is characterized in that, the tracing point chosen on every driving trace is in the track
Gray value in image is used to indicate the weighted value of the driving trace.
4. according to the method described in any one of claim 1-3, which is characterized in that the extraction track density heating power
Pre- in figure is taken aim at a little, including：
To take the key point of a driving trace as cut-point, horizontal partition is carried out to the track density thermodynamic chart；Wherein, described
It is the one or more of driving traces in the trace image to take a driving trace, and the key point takes a traveling rail to be described
Any one in two tracing points that mark mean curvature difference is zero or two；
The point that density heating power value in the point that the track density thermodynamic chart is located on horizontal partition line is crest value is chosen, as institute
State pre- take aim at a little.
5. according to the method described in any one of claim 1-4, which is characterized in that the extraction track density heating power
Pre- in figure is taken aim at a little, including：
Extract the crossing boundary line in the track density thermodynamic chart；
The point that density heating power value in the point that the track density thermodynamic chart is located on the boundary line of crossing is crest value is chosen, as institute
State pre- take aim at a little.
6. according to the method described in any one of claim 1-5, which is characterized in that further include：
According to former and later two pre- attribute values taken aim at a little on the same driving trace, former and later two described pre- points of taking aim at are calculated
Between a plurality of driving path；
It calculates separately to obtain the cost value of every driving path, and selects cost value minimum in a plurality of driving path
Driving path is as optimal driving path.
7. a kind of cloud processing end, which is characterized in that including：
Projecting cell obtains the trace image of a plurality of driving trace for a plurality of driving trace to be projected to the plane of delineation respectively；
Wherein, a plurality of driving trace includes identical starting point and destination；
Processing unit obtains track density thermodynamic chart for being smoothed to the trace image；
Extraction unit, in the track density thermodynamic chart, being taken aim at a little in advance according to key point extraction；Wherein, the key point
It is the tracing point for reflecting the driving trace shape；
First computing unit, for being calculated the pre- attribute value taken aim at a little, the pre- attribute taken aim at a little includes that coordinate, head refer to
To and curvature.
8. cloud processing end according to claim 7, which is characterized in that the projecting cell, including：
Selection unit, for choosing multiple tracing points respectively on every driving trace；
Converting unit, the seat for being converted into the coordinate for the tracing point chosen on every driving trace under image coordinate system
Mark；
Subelement is projected, it, will for the coordinate according to the tracing point chosen on driving trace described in every under image coordinate system
The tracing point chosen on every driving trace projects to the plane of delineation, obtains the trace image.
9. cloud processing end according to claim 8, which is characterized in that the tracing point chosen on every driving trace is described
Gray value in trace image is used to indicate the weighted value of the driving trace.
10. the cloud processing end according to any one of claim 7-9, which is characterized in that the extraction unit, including：
Cutting unit, for take the key point of a driving trace as cut-point, being carried out laterally to the track density thermodynamic chart
Segmentation；Wherein, described to take a driving trace for the one or more of driving traces in the trace image, the key point is
Any one or two taken in two tracing points that a driving trace mean curvature difference is zero；
First takes dot element, is for choosing density heating power value in the point that the track density thermodynamic chart is located on horizontal partition line
The point of crest value pre- is taken aim at a little as described.
11. cloud processing end according to any one of claims of claim 7-10, which is characterized in that the extraction unit, including：
Line taking unit, for extracting the crossing boundary line in the track density thermodynamic chart；
Second takes dot element, is for choosing density heating power value in the point that the track density thermodynamic chart is located on the boundary line of crossing
The point of crest value pre- is taken aim at a little as described.
12. the cloud processing end according to any one of claim 7-11, which is characterized in that further include：
Second computing unit, for according to former and later two pre- attribute values taken aim at a little on the same driving trace, calculating
To it is described former and later two it is pre- take aim at a little between a plurality of driving path；
Preferentially unit obtains the cost value of every driving path for calculating separately, and selects a plurality of driving path
The driving path of middle cost value minimum is as optimal driving path.
13. a kind of cloud processing end, which is characterized in that including：Processor and memory, wherein：
The memory is for storing computer program code；
The processor is used to execute the code of the memory storage, to execute as claimed in any one of claims 1 to 6
Method.
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***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***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 |
|---|---|---|
| CN108519094A (en) | Local paths planning method and cloud processing end | |
| WO2020029601A1 (en) | Method and system for constructing transverse topological relationship of lanes in map, and memory | |
| EP3361278B1 (en) | Autonomous vehicle localization based on walsh kernel projection technique | |
| EP3109842B1 (en) | Map-centric map matching method and apparatus | |
| JP5062498B2 (en) | Reference data generation system and position positioning system for landscape matching | |
| CN110388931A (en) | The two-dimentional bounding box of object is converted into the method for the three-dimensional position of automatic driving vehicle | |
| EP1855263B1 (en) | Map display device | |
| CN110386142A (en) | Pitch angle calibration method for automatic driving vehicle | |
| JP2018084573A (en) | Robust and efficient algorithm for vehicle positioning and infrastructure | |
| CN110389583A (en) | The method for generating the track of automatic driving vehicle | |
| CN109947090A (en) | Non- chocking limit for automatic driving vehicle planning | |
| JP2020201649A (en) | Map generation device, map generation method and computer program for map generation | |
| CN110906940B (en) | Lane sideline aggregation method based on track direction | |
| CN112344947B (en) | Map matching method, map matching device, electronic equipment and computer readable storage medium | |
| CN112154446B (en) | Stereo lane line determining method and device and electronic equipment | |
| CN112017262B (en) | Pavement marker generation method and device, storage medium and electronic equipment | |
| CN109101743A (en) | A kind of construction method of high-precision road net model | |
| CN109871016A (en) | A kind of steered reference line generation method, device, vehicle and server | |
| CN110363771A (en) | A kind of isolation guardrail form point extracting method and device based on three dimensional point cloud | |
| JP6912251B2 (en) | Lane information generator, lane information generation method, and lane information generation program | |
| CN114777799A (en) | Intersection high-precision map generation method and device, electronic equipment and storage medium | |
| CN110389992B (en) | Visualization method, device and equipment of navigation vector data and storage medium | |
| JP2018173512A (en) | Traffic lane information generation device, traffic lane information generation method, and program for traffic lane information generation | |
| JP2018173511A (en) | Traffic lane information generation device, traffic lane information generation method, and program for traffic lane information generation | |
| CN115631476A (en) | Lane data processing method, system, electronic device 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 |