CN109871016A - A kind of steered reference line generation method, device, vehicle and server - Google Patents
A kind of steered reference line generation method, device, vehicle and server Download PDFInfo
- Publication number
- CN109871016A CN109871016A CN201910127261.2A CN201910127261A CN109871016A CN 109871016 A CN109871016 A CN 109871016A CN 201910127261 A CN201910127261 A CN 201910127261A CN 109871016 A CN109871016 A CN 109871016A
- Authority
- CN
- China
- Prior art keywords
- lane
- reference line
- steered reference
- precision map
- map
- 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
Landscapes
- Traffic Control Systems (AREA)
Abstract
The embodiment of the present invention proposes a kind of steered reference line generation method, device, vehicle and server, the described method includes: the duplicate track data section to be processed based on each lane at least one lane collected, generates the smooth trajectory curve for each lane at least one described lane；The smooth trajectory curve in each lane at least one described lane is mapped into high-precision map, obtains the steered reference line at least partly lane in high-precision map；Based at least partly the steered reference line in lane, generation cover the complete steered reference line in whole lanes in high-precision map in the high-precision map.Solve the problems, such as that the steered reference line flatness in automatic driving vehicle is insufficient and does not meet user driving habits.
Description
Technical field
The present invention relates to unmanned control technology field more particularly to a kind of steered reference line generation methods, device, vehicle
And server.
Background technique
Automatic Pilot reference line is the basis that unmanned vehicle completes trajectory planning, the steered reference line based on high quality, track
Planning could generate the planned trajectory of high comprehensive performance.Currently, it is insufficient for unpiloted steered reference line flatness, it is difficult
To guarantee continuous and derivable and meet mankind's driving habit, to influence the quality of trajectory planning result, and then unmanned vehicle is influenced
Drive body-sensing.
Summary of the invention
The embodiment of the present invention provides a kind of steered reference line generation method, device, vehicle and server, to solve existing skill
Steered reference line flatness in art is insufficient, it is difficult to the problem of guaranteeing continuous and derivable and meeting mankind's driving habit.
In a first aspect, the embodiment of the invention provides a kind of steered reference line generation methods, comprising:
Based on the duplicate track data section to be processed in each lane at least one lane collected, needle is generated
To the smooth trajectory curve in each lane at least one described lane；
The smooth trajectory curve in each lane at least one described lane is mapped into high-precision map, is obtained high-precisionly
At least partly steered reference line in lane in figure；
Based at least partly the steered reference line in lane, generation cover whole lanes in high-precision map in the high-precision map
Complete steered reference line.
In one embodiment, the method also includes:
Acquire at least one track data of at least one vehicle；It wherein, include at least one in the track data
Value at the time of at position and each position；
Obtain N number of track data section that the same lane is covered at least one track data；N is more than or equal to 1
Integer；
When N is more than predetermined threshold value, using N number of track data section in the same lane as duplicate rail to be processed
Mark data segment.
In one embodiment, the smooth trajectory curve by each lane at least one described lane maps
To high-precision map, the steered reference line at least partly lane in high-precision map is obtained, comprising:
By the smooth trajectory curve in each lane at least one described lane map in high-precision map it is corresponding extremely
Small part lane；
It deletes after being located at the part outside road range in smooth trajectory curve, obtains in high-precision map at least partly lane
Steered reference line.
In one embodiment, the method also includes:
In the high-precision map at least partly in the steered reference line in lane, for the lane in the steered reference line
Steered reference line is spliced using polynomial curve fitting algorithm in the position of bifurcated and remittance.
In one embodiment, the method also includes:
For at least one lane without steered reference line in the high-precision map, described at least one is joined without driving
The center line in the lane of line is examined as steered reference line to be replaced；
The steered reference line to be replaced and the high-precision map in the lane based on described at least one without steered reference line
In at least partly lane steered reference line, generate the complete steered reference line that whole lanes are covered in high-precision map.
Second aspect, the embodiment of the invention provides a kind of steered reference line generating means, described device includes:
Trajectory processing unit, for based at least one lane collected each lane it is duplicate to be processed
Track data section generates the smooth trajectory curve for each lane at least one described lane；
Map unit, for mapping to high-precisionly the smooth trajectory curve in each lane at least one described lane
Figure, obtains the steered reference line at least partly lane in high-precision map；
Map handling unit, for based at least partly the steered reference line in lane, generation cover in the high-precision map
The complete steered reference line in whole lanes in high-precision map.
In one embodiment, the trajectory processing unit, for acquiring at least one track of at least one vehicle
Data；It wherein, include value at the time of at least one position and each position in the track data；Described in acquisition
N number of track data section in the same lane is covered at least one track data；It, will be described same when N is more than predetermined threshold value
N number of track data section in one lane is as duplicate track data section to be processed；N is the integer more than or equal to 1.
In one embodiment, the map unit, for by least one described lane each lane it is flat
Sliding rail trace curve maps to corresponding at least partly lane in high-precision map；It deletes in smooth trajectory curve and is located at outside road range
Part after, obtain the steered reference line at least partly lane in high-precision map.
In one embodiment, the map handling unit, for at least partly lane in the high-precision map
In steered reference line, for the position of lane bifurcated and remittance in the steered reference line, using polynomial curve fitting
Algorithm splices steered reference line.
In one embodiment, the map handling unit, for at least one nothing in the high-precision map
The lane of steered reference line, using the center line in described at least one lane without steered reference line as steered reference to be replaced
Line；In the steered reference line to be replaced and the high-precision map in the lane based on described at least one without steered reference line extremely
The steered reference line in small part lane generates the complete steered reference line that whole lanes are covered in high-precision map.
The third aspect, the embodiment of the invention provides a kind of vehicle, the function of the vehicle can by hardware realization,
Corresponding software realization can be executed by hardware.The hardware or software include one or more corresponding with above-mentioned function
Module.
It include first processor and first memory in the structure of the vehicle in a possible design, described the
One memory is used to store the program for supporting described device to execute above-mentioned driving control method, and the first processor is configured as
For executing the program stored in the memory.Described device can also include the first communication interface, be used for and other equipment
Or communication.
Fourth aspect, the embodiment of the invention provides a kind of server, the function of the server can pass through hardware reality
It is existing, corresponding software realization can also be executed by hardware.The hardware or software include one or more and above-mentioned function phase
Corresponding module.
It is described including second processor and second memory in the structure of the server in a possible design
Second memory is used to store the program for supporting described device to execute above-mentioned driving control method, and the second processor is configured
For for executing the program stored in the memory.Described device can also include the second communication interface, for setting with other
Standby or communication.
5th aspect, the embodiment of the invention provides a kind of computer readable storage mediums, are stored with computer program,
The program realizes any method in above-described embodiment when being executed by processor.
A technical solution in above-mentioned technical proposal has the following advantages that or the utility model has the advantages that based on that can cover at least one
The track data section to be processed in each lane in a lane reflects smooth trajectory curve after processing obtains smooth trajectory curve
It is mapped to high-precision map and obtains the steered reference line in part lane, and then the steered reference line based on part lane generates high-precision map
In whole lanes steered reference line.Track data section to be processed due to covering multiple lanes collects in advance,
Therefore, when carrying out the steered reference line in the high-precision map of mapping generation, it can guarantee the reasonability of reference line, and protect
The driving habit that steered reference line expresses the mankind is demonstrate,proved.
Above-mentioned general introduction is merely to illustrate that the purpose of book, it is not intended to be limited in any way.Except foregoing description
Schematical aspect, except embodiment and feature, by reference to attached drawing and the following detailed description, the present invention is further
Aspect, embodiment and feature, which will be, to be readily apparent that.
Detailed description of the invention
In the accompanying drawings, unless specified otherwise herein, otherwise indicate the same or similar through the identical appended drawing reference of multiple attached drawings
Component or element.What these attached drawings were not necessarily to scale.It should be understood that these attached drawings depict only according to the present invention
Disclosed some embodiments, and should not serve to limit the scope of the present invention.
Fig. 1-1 shows the flow chart one of steered reference line generation method according to an embodiment of the present invention.
Fig. 1-2 shows the flowchart 2 of steered reference line generation method according to an embodiment of the present invention.
Fig. 1-3 shows the flow chart 3 of steered reference line generation method according to an embodiment of the present invention.
Fig. 2 shows high-precision maps according to an embodiment of the present invention and ordinary electronic navigation map schematic diagram.
Fig. 3 shows the schematic diagram of a scenario according to an embodiment of the present invention for deleting redundance.
Fig. 4 shows splicing schematic diagram of a scenario according to an embodiment of the present invention.
Fig. 5 shows steered reference line processing schematic diagram of a scenario according to an embodiment of the present invention.
Fig. 6 shows a kind of steered reference line generating means composed structure schematic diagram according to an embodiment of the present invention.
Fig. 7 shows vehicle structure block diagram according to an embodiment of the present invention.
Fig. 8 shows server architecture block diagram according to an embodiment of the present invention.
Specific embodiment
Hereinafter, certain exemplary embodiments are simply just described.As one skilled in the art will recognize that
Like that, without departing from the spirit or scope of the present invention, described embodiment can be modified by various different modes.
Therefore, attached drawing and description are considered essentially illustrative rather than restrictive.
The embodiment of the present invention provides a kind of driving control method, according to the repetition in each lane in existing multiple lanes
Track data section to be processed, generate the corresponding smooth trajectory curve in each lane；The smooth trajectory curve is reflected
It is incident upon high-precision map, obtains the steered reference line at least partly lane in high-precision map, high-precision map can be covered by finally obtaining
Whole lanes steered reference line.
In one embodiment, as Figure 1-1, a kind of steered reference line generation method is provided, which comprises
Step 101: the duplicate track data to be processed based on each lane at least one lane collected
Section generates the smooth trajectory curve for each lane at least one described lane；
Step 102: the smooth trajectory curve in each lane at least one described lane being mapped into high-precision map, is obtained
At least partly steered reference line in lane into high-precision map；
Step 103: based at least partly the steered reference line in lane, generation cover in high-precision map in the high-precision map
The complete steered reference line in whole lanes.
First against abovementioned steps 101, needs first to acquire at least one track data before execution, specifically may be used
With are as follows:
Acquire at least one track data of at least one vehicle；It wherein, include at least one in the track data
Value at the time of at position and each position；
Obtain duplicate N number of track data section that the same lane is covered at least one track data；N be greater than
Integer equal to 1；
When N is more than predetermined threshold value, using N number of track data section in the same lane as duplicate rail to be processed
Mark data segment.
Specifically, at least one track data for acquiring at least one vehicle, may include have at least one position with
And value at the time of each position；In addition, can also include status information at that time in track data.
Wherein, the position can be the coordinate based on world coordinate system, and acquisition mode can be for by each vehicle
In GPS unit be acquired；Acquisition interval can be configured according to the actual situation, for example, can be primary for every 1s, or
Can be primary for every 0.5s, certainly exhaustion only can not be done in the present embodiment with larger or smaller.The status information can
To include speed and/or acceleration of the vehicle at the corresponding moment.For example, the track data can be at least one
(x, y, t), (x, y) indicate geographical location information, value at the time of t is then when collecting the track data；Alternatively, track number
According to can be at least one (x, y, t may further include a) namely in addition to the above-described information the acceleration for having the moment
Value, acceleration can may be negative for positive number.
It is described to obtain duplicate N number of track data section that the same lane is covered at least one track data, it can
With to be compared according to the namely location information of (x, y) at least one track data, selection is obtained by same
N number of track data section in lane；For example, there are 4 track datas, wherein being directed to some lane, there are 3 track datas, and remains
Then there is a track data section in remaining lane respectively, then three track datas for the same lane are effective track number
According to.
In addition, predetermined threshold value can be arranged according to the actual situation, it certainly can also be 3 for example, can be 10, or
It can also be 50, the present embodiment is no longer exhaustive.That is, being chosen when having 3 track datas by the same lane
The multiple track data sections for being repeated 3 times or more in the lane are covered as duplicate track data section to be processed.
It should be pointed out that the present embodiment chooses multiple track datas that multiple mankind drive practical lane, then therefrom
Choose that number of repetition is more, that is, track data section corresponding to the more certain lanes of the number passed by is as the present embodiment
Used track data section to be processed.For scene may include have various types of scene crossroads, turning, point
Track etc. in fork, common Through Lane.Duplicate track can be the more track data section of acquisition number of repetition；
Because actual conditions cannot once be reflected by only opening on a map, certain stretch be repeatedly pass by may be considered effectively
's.
In abovementioned steps 101, the smooth trajectory curve for each lane at least one described lane is generated, it can be with
It is defeated at least one sampled point of pilot steering track data section to be processed to be handled for track data section to be processed
Enter, with segmentation dimensional gaussian distribution fitting, generates the smooth trajectory curve of reflection mankind's driving habit.
Wherein, at least one collected sampled point when at least one sampled point can be for acquisition trajectories data,
It certainly can also be at least one sampled point based on preset interval selection, for example, the rail to be processed in some original lane
There are 10 collection points in mark data segment can therefrom choose 5 acquisitions when carrying out segmentation dimensional gaussian distribution fitting
Point eventually passes through segmentation dimensional gaussian distribution fitting algorithm and generates corresponding smooth trajectory curve as input.
In abovementioned steps 102, the smooth trajectory curve by each lane at least one described lane is mapped to
High-precision map obtains the steered reference line at least partly lane in high-precision map, comprising:
By the smooth trajectory curve in each lane at least one described lane map in high-precision map it is corresponding extremely
Small part lane；It deletes after being located at the part outside road range in smooth trajectory curve, obtains in high-precision map at least partly vehicle
The steered reference line in road.
That is, by all curve mappings to corresponding lane of fitting generation, deleting road in conjunction with high-precision map
Redundance other than range obtains a plurality of steered reference line.It is to be understood that after on curve mapping to lane, it may
It is fallen in there are a part of curve except the road range where lane；Further, may exist in parallel extremely in one section of road
A few lane, for example, may exist 4 parallel lanes in one section of road, this step can will be fallen in outside road range
Redundance is deleted.
It in high-precision map, will be mapped for the smooth trajectory curve in multiple lanes, wherein the mode of mapping can be with
To be mapped based on position, for example, multiple elements present in high-precision map are also the setting carried out with position, according to smooth
The positional relationship of geometric locus maps that in high-precision map.
For user perspective, the main distinction of high-precision map and conditional electronic map is: the user of high-precision map is
Automated driving system, the user of conditional electronic map are then human drivers.
Referring to fig. 2, traditional common navigation electronic map (left side in figure) can depict road, and part road can distinguish vehicle
Road, and high-precision map (right side in figure) can not only describe road, also can accurately describe to how many lane on a road,
The practical pattern in lane can be truly reflected out.
Conditional electronic map will not show completely the details of lane shape, and high-precision map is in order to allow automated driving system
It preferably identifies traffic conditions, to make traveling scheme in advance, the details of lane shape in detail, accurately show,
Which place broadens, narrows, can be completely the same with true lane.
As shown in Fig. 2, including multiple lanes in high-precision map, in map, for example, including lane (Lane) 1- in figure
10.At least one lane can form a road, for example, a road, lane can be formed with lane (Lane) 1,2,3
(Lane) 4,5,6,7 another road is formed, other building forms are similar, repeat no more.It is to be appreciated that Fig. 2 is only
Example can also have more expressive elements, such as road shoulder, traffic lights etc. in actual high-precision map, only the present embodiment
In it is no longer exhaustive.
It is located at the part outside road range in aforementioned deletion smooth trajectory curve, may refer to Fig. 3, it is assumed that is currently directed to vehicle
There are smooth trajectory curves 1 in road, but wherein there is the outside that a part of curve is located at routes coverage, such as the void in figure
Line part, then just deleting as redundance, the part then remained is as the steered reference line for being directed to lane.
As it can be seen that by using above scheme, it will be able to based on can cover each lane at least one lane to
Track data section is handled smooth trajectory curve is mapped to high-precision map and obtains part vehicle after processing obtains smooth trajectory curve
The steered reference line in road, and then the steered reference line based on part lane generates the steered reference in whole lanes in high-precision map
Line.Track data section to be processed due to covering multiple lanes collects in advance, carrying out, mapping generation is high-precision
When steered reference line in map, it can guarantee the reasonability of reference line, and ensure that steered reference line expresses people
Driving habit of class, such as more smooth completion doubling, the turning radius completion crossing inside turn driven with the closer mankind etc..
In one embodiment, a kind of steered reference line generation method, in the present embodiment mode, mapping smoothing drives bent
Processing of the line to high-precision map and its before is identical as the description of previous embodiment step 101- step 102, therefore repeats no more.
The present embodiment is directed to abovementioned steps 103, raw based on at least partly steered reference line in lane in the high-precision map
At the complete steered reference line for covering whole lanes in high-precision map, it is described in detail.
It wherein, include the processing of the splicing at least partly steered reference line in lane, and then joined based on spliced driving
Examine the complete steered reference line in whole lanes that line is generated for entire high-precision map.Specifically, referring to Fig. 1-2, in Fig. 1
On the basis of middle step 101- step 102, step 103 can be divided into following steps execution, specifically include:
Step 1031: in the high-precision map at least partly in the steered reference line in lane, for the steered reference
Steered reference line is spliced using polynomial curve fitting algorithm in the position of lane bifurcated in line and remittance；
Step 1032: being based on spliced steered reference line, generate the complete driving for covering whole lanes in high-precision map
Reference line.
Further, the place of bifurcated, remittance is found on high-precision map；And it is directed to the lane of bifurcated, it is possible that
Different situation, for example, certain once acquires left bifurcated, the route of another one acquisition has walked right bifurcated；The portion of centre linking
Divide and needs to link up；That is, road can there are many ways to get there, for the first time and may collect for second different
Route.Wherein, the collected route of homogeneous does not have common part and different parts, is calculated using polynomial curve fitting
Common part is stitched together by method.
For example, referring to fig. 4, it is assumed that having two steered reference lines for lane is respectively a, b, wherein in steered reference line a
Some has walked the lane on the left side, and a part has walked the lane on the right in steered reference line b, the two are bifurcated, this two
There are common grounds for bar steered reference line；Additionally there are steered reference line c, and steered reference line c is located at after bifurcated, then can
To splice the common ground of steered reference line a, b and steered reference line c, wherein the part spliced is in figure with dotted line
It shows, finally obtains spliced steered reference line.It can be handled based on the processing mode in entire high-precision map.
In addition, being based on aforementioned schemes, can may also there be a part of lane and not obtain steered reference line, the place of this part
Reason can be with as shown in Figure 1-3, specifically include:
Step 1033: at least one lane without steered reference line in the high-precision map, by described at least one
The center line in lane of the item without steered reference line is as steered reference line to be replaced；
Step 1034: steered reference line to be replaced, Yi Jisuo based on described at least one lane without steered reference line
The steered reference line for stating at least partly lane in high-precision map generates the complete steered reference that whole lanes are covered in high-precision map
Line.
That is, steered reference line can incrementally generate in the present embodiment mode, height can be used in non-pickup area
The included lane center of smart map replaces.For example, being illustrated by taking road 1-5 as an example referring to Fig. 5, wherein there are roads 1,2
In part lane steered reference line, but remaining road 3,4,5 is there is no steered reference line, can be by road 3,4,5
In at least one lane center line as its steered reference line, to there is the solid line of arrow to indicate in figure, so with road 1,2
Complete steered reference line is obtained after steered reference splicing.
It may also be noted that finally obtained complete steered reference line is lane rank, that is, high-precision map
In whole lanes be provided with corresponding steered reference line.
Further, if using steered reference line to be replaced for the lane not collected originally with reference to route
Lane can be after acquiring to the original people in the lane when having resurveyed duplicate driving track data
The data of work mark are replaced.That is, can be the data manually marked as ginseng if not acquiring mankind's route
Line is examined, if there is the acquisition of mankind's route, just uses mankind's route.
It is to be appreciated that the processing mode for the lane of no steered reference line can be the step shown in Fig. 1-2
It is executed on the basis of 1031, that is to say, that the specific embodiment party after the splicing for completing steered reference line, as step 1032
Formula, the extension that the part lane without steered reference line is carried out on the basis of spliced steered reference line are completely driven
Reference line, that is, specific process flow are abovementioned steps 101- step 102- step 1031- step 1033- step 1034,
It is not discussed here；
Alternatively, can also be executed after the step 102 in Fig. 1-1, that is to say, that in at least portion of generation step 102
After the steered reference line of divided lane, begin to execute step 103, and the processing of step 103 is exactly by no steered reference line
Steered reference line of the center line in lane as the lane, process flow are step 101- step 102- step 1033- step
1034, it is not discussed here.
Preceding method can also be handled to execute in the processor of vehicle in server side；Wherein, it takes
Business device can be the server side of high-precision map.
When each step of preceding method server side execute when, acquire at least one track of at least one vehicle
The processing of data, it can be understood as, it is acquired by least one vehicle, at least one track data collected is sent
To server side；Then abovementioned steps 101- step 102- step 1031- step 1033- step 1034 is executed by server side,
Alternatively, executing abovementioned steps 101- step 102- step 1033- step 1034 by server side.
Further, when aforementioned each method and step is executed in server side and after generate complete steered reference line,
The server can be with: the complete steered reference line for covering whole lanes in high-precision map is sent at least one vehicle.
It is, may finally will be provided in the high-precision map merging automatic driving vehicle of complete steered reference line, so that vehicle is accurate
Control vehicle carries out automatic running on specific lane in the road.
As it can be seen that by using above scheme, it will be able to based on the N number of of each lane at least one lane can be covered
Smooth trajectory curve is mapped to high-precision map and obtains part by track data section to be processed after processing obtains smooth trajectory curve
The steered reference line in lane, and then the steered reference line based on part lane generates the driving ginseng in whole lanes in high-precision map
Examine line.Track data section to be processed due to covering multiple lanes collects in advance, height is generated carrying out mapping
When steered reference line in smart map, it can guarantee the reasonability of reference line, and ensure that steered reference line expresses
Driving habit of the mankind, such as more smooth completion doubling, the turning radius completion crossing inside turn driven with the closer mankind etc..
It may also be noted that due to the steered reference line that can obtain lane rank using the above scheme, at least
Compared to common navigation maps, steered reference line provided by scheme provided in this embodiment is more accurate.
In one embodiment, Fig. 6 shows a kind of steering control device, and described device includes:
Trajectory processing unit 61, for based at least one lane collected each lane it is duplicate wait locate
Track data section is managed, the smooth trajectory curve for each lane at least one described lane is generated；
Map unit 62, it is high-precision for mapping to the smooth trajectory curve in each lane at least one described lane
Map obtains the steered reference line at least partly lane in high-precision map；
Map handling unit 63, for based at least partly the steered reference line in lane, generation are covered in the high-precision map
Cover the complete steered reference line in whole lanes in high-precision map.
The present embodiment is applied in the vehicle for carrying out automatic Pilot.
The trajectory processing unit, for acquiring at least one track data of at least one vehicle；Wherein, the track
Value at the time of including at least one position and each position in data；It obtains at least one track data
Cover N number of track data section in the same lane；When N is more than predetermined threshold value, by N number of track number in the same lane
According to section as duplicate track data section to be processed.
The map unit, for the smooth trajectory curve mapping in each lane at least one described lane is supreme
Corresponding at least partly lane in smart map；Delete the part being located at outside at least partly lane range in smooth trajectory curve
Afterwards, the steered reference line at least partly lane in high-precision map is obtained.
The map handling unit, in the high-precision map at least partly in the steered reference line in lane, for
The position of lane bifurcated and remittance in the steered reference line, using polynomial curve fitting algorithm to steered reference line into
Row splicing.
The map handling unit, at least one lane without steered reference line for being directed in the high-precision map,
Using the center line in described at least one lane without steered reference line as steered reference line to be replaced；Based on described at least one
At least partly steered reference in lane in the steered reference line to be replaced and the high-precision map in the lane without steered reference line
Line generates the complete steered reference line that whole lanes are covered in high-precision map.
The function of each module in the device of that embodiment of the invention specifically may refer to the corresponding description in the above method, herein
It repeats no more.
Aforementioned each unit can be in the car, can also be in the server.
It can also include communication unit when being arranged when server；The communication unit is collected for obtaining
At least one track data.
Further, the communication unit can be also used for cover the complete driving ginseng in whole lanes in high-precision map
It examines line and is sent at least one vehicle.It is, the high-precision map that may finally will be provided with complete steered reference line is placed in nobody
It drives in vehicle, carries out automatic running on specific lane in the road so that vehicle accurately controls vehicle.
As it can be seen that by using above scheme, it will be able to based on can cover each lane at least one lane to
Track data section is handled smooth trajectory curve is mapped to high-precision map and obtains part vehicle after processing obtains smooth trajectory curve
The steered reference line in road, and then the steered reference line based on part lane generates the steered reference in whole lanes in high-precision map
Line.Track data section to be processed due to covering multiple lanes collects in advance, carrying out, mapping generation is high-precision
When steered reference line in map, it can guarantee the reasonability of reference line, and ensure that steered reference line expresses people
Driving habit of class, such as more smooth completion doubling, the turning radius completion crossing inside turn driven with the closer mankind etc..
Fig. 7 shows the structural block diagram of vehicle according to an embodiment of the present invention.As shown in fig. 7, the vehicle includes: the first storage
Device 710 and first processor 720 are stored with the computer journey that can be run on first processor 720 in first memory 710
Sequence.The first processor 720 realizes the driving control method in above-described embodiment when executing the computer program.Described
The quantity of one memory 710 and first processor 720 can be one or more.
The vehicle further include:
First communication interface 730 carries out data interaction for being communicated with external device.
First memory 710 may include high speed RAM memory, it is also possible to further include nonvolatile memory (non-
Volatile memory), a for example, at least magnetic disk storage.
If first memory 710, first processor 720 and the independent realization of the first communication interface 730, first memory
710, first processor 720 and the first communication interface 730 can be connected with each other by bus and complete mutual communication.It is described
It is mutual that bus can be industry standard architecture (ISA, Industry Standard Architecture) bus, external equipment
Even (PCI, Peripheral Component Interconnect) bus or extended industry-standard architecture (EISA,
Extended Industry Standard Architecture) bus etc..The bus can be divided into address bus, data
Bus, control bus etc..Only to be indicated with a thick line in Fig. 7, it is not intended that an only bus or one kind convenient for indicating
The bus of type.
Optionally, in specific implementation, if first memory 710, first processor 720 and the first communication interface 730
It integrates on one chip, then first memory 710, first processor 720 and the first communication interface 730 can be connect by inside
Mouth completes mutual communication.
Fig. 8 shows the structural block diagram of server according to an embodiment of the present invention.As shown in figure 8, the server includes: second
Memory 810 and second processor 820 are stored with the computer that can be run in second processor 820 in second memory 810
Program.The second processor 820 realizes the driving control method in above-described embodiment when executing the computer program.It is described
The quantity of second memory 810 and second processor 820 can be one or more.
The vehicle or server further include:
Second communication interface 830 carries out data interaction for being communicated with external device.
Second memory 810 may include high speed RAM memory, it is also possible to further include nonvolatile memory (non-
Volatile memory), a for example, at least magnetic disk storage.
If second memory 810, second processor 820 and the independent realization of the second communication interface 830, second memory
810, second processor 820 and the second communication interface 830 can be connected with each other by bus and complete mutual communication.It is described
It is mutual that bus can be industry standard architecture (ISA, Industry Standard Architecture) bus, external equipment
Even (PCI, Peripheral Component) bus or extended industry-standard architecture (EISA, Extended Industry
Standard Component) bus etc..The bus can be divided into address bus, data/address bus, control bus etc..For convenient for
It indicates, is only indicated with a thick line in Fig. 8, it is not intended that an only bus or a type of bus.
Optionally, in specific implementation, if second memory 810, second processor 820 and the second communication interface 830
It integrates on one chip, then second memory 810, second processor 820 and the second communication interface 830 can be connect by inside
Mouth completes mutual communication.
The embodiment of the invention provides a kind of computer readable storage mediums, are stored with computer program, the program quilt
Processor realizes any method in above-described embodiment when executing.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or spy described in conjunction with this embodiment or example
Point is included at least one embodiment or example of the invention.Moreover, particular features, structures, materials, or characteristics described
It may be combined in any suitable manner in any one or more of the embodiments or examples.In addition, without conflicting with each other, this
The technical staff in field can be by the spy of different embodiments or examples described in this specification and different embodiments or examples
Sign is combined.
In addition, term " first ", " second " are used for descriptive purposes only and cannot be understood as indicating or suggesting relative importance
Or implicitly indicate the quantity of indicated technical characteristic." first " is defined as a result, the feature of " second " can be expressed or hidden
It include at least one this feature containing ground.In the description of the present invention, the meaning of " plurality " is two or more, unless otherwise
Clear specific restriction.
Any process described otherwise above or method description are construed as in flow chart or herein, and expression includes
It is one or more for realizing specific logical function or process the step of executable instruction code module, segment or portion
Point, and the range of the preferred embodiment of the present invention includes other realization, wherein can not press shown or discussed suitable
Sequence, including according to related function by it is basic simultaneously in the way of or in the opposite order, Lai Zhihang function, this should be of the invention
Embodiment person of ordinary skill in the field understood.
Expression or logic and/or step described otherwise above herein in flow charts, for example, being considered use
In the order list for the executable instruction for realizing logic function, may be embodied in any computer-readable medium, for
Instruction execution system, device or equipment (such as computer based system, including the system of processor or other can be held from instruction
The instruction fetch of row system, device or equipment and the system executed instruction) it uses, or combine these instruction execution systems, device or set
It is standby and use.For the purpose of this specification, " computer-readable medium ", which can be, any may include, stores, communicates, propagates or pass
Defeated program is for instruction execution system, device or equipment or the dress used in conjunction with these instruction execution systems, device or equipment
It sets.The more specific example (non-exhaustive list) of computer-readable medium include the following: there is the electricity of one or more wirings
Interconnecting piece (electronic device), portable computer diskette box (magnetic device), random access memory (RAM), read-only memory
(ROM), erasable edit read-only storage (EPROM or flash memory), fiber device and portable read-only memory
(CDROM).In addition, computer-readable medium can even is that the paper that can print described program on it or other suitable Jie
Matter, because can then be edited, be interpreted or when necessary with other for example by carrying out optical scanner to paper or other media
Suitable method is handled electronically to obtain described program, is then stored in computer storage.
It should be appreciated that each section of the invention can be realized with hardware, software, firmware or their combination.Above-mentioned
In embodiment, software that multiple steps or method can be executed in memory and by suitable instruction execution system with storage
Or firmware is realized.It, and in another embodiment, can be under well known in the art for example, if realized with hardware
Any one of column technology or their combination are realized: having a logic gates for realizing logic function to data-signal
Discrete logic, with suitable combinational logic gate circuit specific integrated circuit, programmable gate array (PGA), scene
Programmable gate array (FPGA) etc..
Those skilled in the art are understood that realize all or part of step that above-described embodiment method carries
It suddenly is that relevant hardware can be instructed to complete by program, the program can store in a kind of computer-readable storage medium
In matter, which when being executed, includes the steps that one or a combination set of embodiment of the method.
It, can also be in addition, each functional unit in each embodiment of the present invention can integrate in a processing module
It is that each unit physically exists alone, can also be integrated in two or more units in a module.Above-mentioned integrated mould
Block both can take the form of hardware realization, can also be realized in the form of software function module.The integrated module is such as
Fruit is realized and when sold or used as an independent product in the form of software function module, also can store in a computer
In readable storage medium storing program for executing.The storage medium can be read-only memory, disk or CD etc..
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can readily occur in its various change or replacement,
These should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention should be with the guarantor of the claim
It protects subject to range.
Claims (12)
1. a kind of steered reference line generation method, which is characterized in that the described method includes:
Based on the duplicate track data section to be processed in each lane at least one lane collected, generates and be directed to institute
State the smooth trajectory curve in each lane at least one lane；
The smooth trajectory curve in each lane at least one described lane is mapped into high-precision map, is obtained in high-precision map
At least partly steered reference line in lane；
Based on at least partly steered reference line in lane in the high-precision map, generates and cover the complete of whole lanes in high-precision map
Whole steered reference line.
2. the method according to claim 1, wherein the method also includes:
Acquire at least one track data of at least one vehicle；Wherein, include in the track data at least one position,
And value at the time of at each position；
Obtain N number of track data section that the same lane is covered at least one track data；N is whole more than or equal to 1
Number；
When N is more than predetermined threshold value, using N number of track data section in the same lane as duplicate track number to be processed
According to section.
3. the method according to claim 1, wherein described by each lane at least one described lane
Smooth trajectory curve maps to high-precision map, obtains the steered reference line at least partly lane in high-precision map, comprising:
The smooth trajectory curve in each lane at least one described lane is mapped into corresponding at least portion in high-precision map
Divided lane；
It deletes after being located at the part outside road range in smooth trajectory curve, obtains at least partly driving in lane in high-precision map
Reference line.
4. the method according to claim 1, wherein the method also includes:
In the high-precision map at least partly in the steered reference line in lane, for the lane bifurcated in the steered reference line
And the position imported, steered reference line is spliced using polynomial curve fitting algorithm.
5. method according to claim 1 or 4, which is characterized in that the method also includes:
For at least one lane without steered reference line in the high-precision map, by described at least one without steered reference line
Lane center line as steered reference line to be replaced；
In the steered reference line to be replaced and the high-precision map in the lane based on described at least one without steered reference line extremely
The steered reference line in small part lane generates the complete steered reference line that whole lanes are covered in high-precision map.
6. a kind of steered reference line generating means, which is characterized in that described device includes:
Trajectory processing unit, for the duplicate track to be processed based on each lane at least one lane collected
Data segment generates the smooth trajectory curve for each lane at least one described lane；
Map unit, for the smooth trajectory curve in each lane at least one described lane to be mapped to high-precision map,
Obtain the steered reference line at least partly lane in high-precision map；
Map handling unit, for based at least partly the steered reference line in lane, generation covering are high-precision in the high-precision map
The complete steered reference line in whole lanes in map.
7. device according to claim 6, which is characterized in that the trajectory processing unit, for acquiring at least one vehicle
At least one track data；It wherein, include at least one position and each position in the track data
Moment value；Obtain N number of track data section that the same lane is covered at least one track data；When N is more than pre- gating
When limit value, using N number of track data section in the same lane as duplicate track data section to be processed；N is more than or equal to 1
Integer.
8. device according to claim 6, which is characterized in that the map unit, at least one lane by described in
In the smooth trajectory curve in each lane map to corresponding at least partly lane in high-precision map；Delete smooth trajectory curve
In be located at the part outside at least partly lane range after, obtain the steered reference line at least partly lane in high-precision map.
9. device according to claim 6, which is characterized in that the map handling unit, in the high-precision map
In at least partly in the steered reference line in lane, for the position of lane bifurcated and remittance in the steered reference line, adopt
Steered reference line is spliced with polynomial curve fitting algorithm.
10. device according to claim 6 or 9, which is characterized in that the map handling unit, for being directed to the height
At least one lane without steered reference line in smart map, by the center line in described at least one lane without steered reference line
As steered reference line to be replaced；The steered reference line to be replaced in the lane based on described at least one without steered reference line, with
And at least partly steered reference line in lane in the high-precision map, generate the complete driving that whole lanes are covered in high-precision map
Reference line.
11. a kind of vehicle characterized by comprising
One or more first processors；
First storage device, for storing one or more programs；
When one or more of programs are executed by one or more of first processors, so that one or more of
One processor realizes the method as described in any one of claims 1 to 5.
12. a kind of server characterized by comprising
One or more second processors；
Second storage device, for storing one or more programs；
When one or more of programs are executed by one or more of second processors, so that one or more of
Two processors realize the method as described in any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910127261.2A CN109871016B (en) | 2019-02-20 | 2019-02-20 | Automatic driving reference line generation method and device, vehicle and server |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910127261.2A CN109871016B (en) | 2019-02-20 | 2019-02-20 | Automatic driving reference line generation method and device, vehicle and server |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109871016A true CN109871016A (en) | 2019-06-11 |
| CN109871016B CN109871016B (en) | 2022-07-22 |
Family
ID=66918953
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910127261.2A Active CN109871016B (en) | 2019-02-20 | 2019-02-20 | Automatic driving reference line generation method and device, vehicle and server |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109871016B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110288675A (en) * | 2019-06-30 | 2019-09-27 | 武汉中海庭数据技术有限公司 | Lane reference line construction method and device and storage medium |
| CN110377041A (en) * | 2019-08-08 | 2019-10-25 | 腾讯科技（深圳）有限公司 | Reference line generation method, device, terminal device and storage medium |
| CN110634291A (en) * | 2019-09-17 | 2019-12-31 | 武汉中海庭数据技术有限公司 | High-precision map topology automatic construction method and system based on crowdsourcing data |
| CN111177927A (en) * | 2019-12-31 | 2020-05-19 | 武汉中海庭数据技术有限公司 | Vehicle reference driving line construction method, electronic device and storage medium |
| CN116698059A (en) * | 2023-07-27 | 2023-09-05 | 宁波路特斯机器人有限公司 | Processing method, storage medium and equipment for high-precision map reference line |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010237158A (en) * | 2009-03-31 | 2010-10-21 | Xanavi Informatics Corp | Method, system for navigating car, center device and car navigation device |
| US20160075280A1 (en) * | 2014-09-12 | 2016-03-17 | Hyundai Motor Company | System for estimating lane and method thereof |
| CN105513405A (en) * | 2016-01-12 | 2016-04-20 | 北京中交兴路车联网科技有限公司 | Vehicle trajectory analysis method and device |
| CN106525033A (en) * | 2016-09-22 | 2017-03-22 | 深圳市元征科技股份有限公司 | Running track determination method and device thereof |
| US20170192436A1 (en) * | 2016-01-05 | 2017-07-06 | Electronics And Telecommunications Research Institute | Autonomous driving service system for autonomous driving vehicle, cloud server for the same, and method for operating the cloud server |
| US20170269605A1 (en) * | 2016-03-21 | 2017-09-21 | Ford Global Technologies, Llc | Systems, Methods, And Devices For Fusion Of Predicted Path Attributes And Drive History |
| 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 |
| CN108519094A (en) * | 2018-02-11 | 2018-09-11 | 华为技术有限公司 | Local paths planning method and cloud processing end |
| US20180348761A1 (en) * | 2017-05-31 | 2018-12-06 | Baidu Usa Llc | Scalable smooth reference path generator for autonomous driving vehicles |
| 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 |
| CN109154821A (en) * | 2017-11-30 | 2019-01-04 | 深圳市大疆创新科技有限公司 | Orbit generation method, device and unmanned ground vehicle |
-
2019
- 2019-02-20 CN CN201910127261.2A patent/CN109871016B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010237158A (en) * | 2009-03-31 | 2010-10-21 | Xanavi Informatics Corp | Method, system for navigating car, center device and car navigation device |
| US20160075280A1 (en) * | 2014-09-12 | 2016-03-17 | Hyundai Motor Company | System for estimating lane and method thereof |
| US20170192436A1 (en) * | 2016-01-05 | 2017-07-06 | Electronics And Telecommunications Research Institute | Autonomous driving service system for autonomous driving vehicle, cloud server for the same, and method for operating the cloud server |
| CN105513405A (en) * | 2016-01-12 | 2016-04-20 | 北京中交兴路车联网科技有限公司 | Vehicle trajectory analysis method and device |
| US20170269605A1 (en) * | 2016-03-21 | 2017-09-21 | Ford Global Technologies, Llc | Systems, Methods, And Devices For Fusion Of Predicted Path Attributes And Drive History |
| CN106525033A (en) * | 2016-09-22 | 2017-03-22 | 深圳市元征科技股份有限公司 | Running track determination method and device thereof |
| US20180348761A1 (en) * | 2017-05-31 | 2018-12-06 | Baidu Usa Llc | Scalable smooth reference path generator for autonomous driving vehicles |
| 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 |
| CN109154821A (en) * | 2017-11-30 | 2019-01-04 | 深圳市大疆创新科技有限公司 | Orbit generation method, device and unmanned ground vehicle |
| CN108519094A (en) * | 2018-02-11 | 2018-09-11 | 华为技术有限公司 | Local paths planning method and cloud processing end |
| 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 |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110288675A (en) * | 2019-06-30 | 2019-09-27 | 武汉中海庭数据技术有限公司 | Lane reference line construction method and device and storage medium |
| CN110288675B (en) * | 2019-06-30 | 2022-05-13 | 武汉中海庭数据技术有限公司 | Lane reference line construction method and device and storage medium |
| CN110377041A (en) * | 2019-08-08 | 2019-10-25 | 腾讯科技（深圳）有限公司 | Reference line generation method, device, terminal device and storage medium |
| CN110377041B (en) * | 2019-08-08 | 2022-03-29 | 腾讯科技（深圳）有限公司 | Reference line generation method and device, terminal equipment and storage medium |
| CN110634291A (en) * | 2019-09-17 | 2019-12-31 | 武汉中海庭数据技术有限公司 | High-precision map topology automatic construction method and system based on crowdsourcing data |
| CN110634291B (en) * | 2019-09-17 | 2020-12-29 | 武汉中海庭数据技术有限公司 | High-precision map topology automatic construction method and system based on crowdsourcing data |
| CN111177927A (en) * | 2019-12-31 | 2020-05-19 | 武汉中海庭数据技术有限公司 | Vehicle reference driving line construction method, electronic device and storage medium |
| CN116698059A (en) * | 2023-07-27 | 2023-09-05 | 宁波路特斯机器人有限公司 | Processing method, storage medium and equipment for high-precision map reference line |
| CN116698059B (en) * | 2023-07-27 | 2023-11-28 | 宁波路特斯机器人有限公司 | Processing method, storage medium and equipment for high-precision map reference line |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109871016B (en) | 2022-07-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109871016A (en) | A kind of steered reference line generation method, device, vehicle and server | |
| CN109470254B (en) | Map lane line generation method, device, system and storage medium | |
| CN111238497B (en) | High-precision map construction method and device | |
| CN108871368B (en) | Method and system for constructing transverse topological relation of high-precision map lane and memory | |
| CN109472844B (en) | Method and device for marking lane lines in road junction and storage medium | |
| CN108519094A (en) | Local paths planning method and cloud processing end | |
| CN106980657A (en) | A kind of track level electronic map construction method based on information fusion | |
| CN109164785B (en) | Emulation test method, device, equipment and the storage medium of automatic driving vehicle | |
| CN108981730A (en) | For generating the method and system of reference path for operation automatic driving vehicle | |
| CN103292816A (en) | Electronic map generation method and device as well as route planning method and device | |
| JP2019135544A (en) | Method and apparatus for identifying intersection in electronic map | |
| WO2020125686A1 (en) | Method for generating real-time relative map, intelligent driving device and computer storage medium | |
| CN112212874A (en) | Vehicle track prediction method and device, electronic equipment and computer readable medium | |
| CN108332761B (en) | Method and equipment for using and creating road network map information | |
| CN110009741B (en) | A method of the build environment point cloud map in Unity | |
| CN112614365B (en) | Electronic map processing method and device | |
| CN105806349B (en) | A kind of true three-dimensional navigation turns to abductive approach and turns to induction navigation equipment | |
| JP7435483B2 (en) | Map generation device, map generation method, and map generation computer program | |
| CN108801289A (en) | Induce arrow planing method, device, navigation system and storage medium | |
| CN114518122A (en) | Driving navigation method, driving navigation device, computer equipment, storage medium and computer program product | |
| CN105023431A (en) | Method and device for determining traffic restriction information | |
| CN104634355B (en) | Air navigation aid and navigation equipment | |
| CN116105717A (en) | Lane-level high-precision map construction method and system | |
| CN116360417A (en) | Robot path planning method, device and equipment | |
| EP4124828B1 (en) | Map processing method and apparatus |
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 |