CN108645420A - A kind of creation method of the automatic driving vehicle multipath map based on differential navigation - Google Patents
A kind of creation method of the automatic driving vehicle multipath map based on differential navigation Download PDFInfo
- Publication number
- CN108645420A CN108645420A CN201810387336.6A CN201810387336A CN108645420A CN 108645420 A CN108645420 A CN 108645420A CN 201810387336 A CN201810387336 A CN 201810387336A CN 108645420 A CN108645420 A CN 108645420A
- Authority
- CN
- China
- Prior art keywords
- driving vehicle
- automatic driving
- landform
- creation method
- 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
- G01C21/28—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network with correlation of data from several navigational instruments
- G01C21/30—Map- or contour-matching
- G01C21/32—Structuring or formatting of map data
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)
Abstract
The present invention provides a kind of creation method of the automatic driving vehicle multipath map based on differential navigation, including defines automatic Pilot cartographic information, further comprising the steps of：Acquire multi-trace map；Generate automatic driving vehicle multi-trace；The multi-trace map includes regular landform and/or irregular landform.The present invention proposes a kind of creation methods of the automatic driving vehicle multipath map based on differential navigation of de, and can generate a plurality of map path simultaneously for the automatic Pilot region of rule supplies more automatic Pilot vehicles；For irregular path, a plurality of lane position information can be acquired simultaneously.
Description
Technical field
The present invention relates to the technical fields of computer vision and image procossing, especially a kind of based on the automatic of differential navigation
Drive the creation method of vehicle multipath map.
Background technology
Automatic driving vehicle technology is increasingly mature, navigation map at automatic Pilot foundation stone.Usually, automatic Pilot vehicle
By positioning device obtain real-time positioning information, and using the information matches navigation map progress path planning.Currently, navigation
Map, which is substantially the predominating path that the team of exploitation automatic Pilot is first collected before carrying out automatic Pilot, and preserves, to be believed
Breath is all latitude and longitude information, and such way only runs one and drive automatically to small-scale automatic Pilot, in other words Same Scene
It is that there is no problem, while map collecting work amount is in controlled range to sail vehicle.But if more automatic Pilots are run simultaneously
Vehicle and the route of operation difference, or once need to acquire the location information in multiple tracks, when this just needs acquire map early period
Multi collect work is done, especially for large-scale automatic Pilot, this will take a substantial amount of time cost and human cost.
Application No. is the patents of invention of CN201610846436.1 to disclose a kind of automatic driving vehicle track grade navigation ground
Map generalization system and method, wherein system include offline global map and online local map two parts, and off-line module refers to,
In the target area of automatic driving vehicle traveling, satellite photo (or aerial photograph), onboard sensor (laser radar are utilized
And camera), high-precision integrated positioning system (global position system and inertial navigation system) obtain original road data, then
Original road data is passed through into processed offline, extracts various roads information, finally generates road information extraction result fusion
Offline global map.Offline global map is stored using layered structure.Refer in wire module, when automatic driving vehicle is in target area
In domain when automatic Pilot, according to real-time positioning information, the road data in offline global map is extracted, is drawn out with vehicle
Centered on, the online local map in fixed distance.The system can not distinguishing rule landform and irregular terrain profiles, obtain
The world coordinates arrived is inaccurate.
Application No. is the patents of invention of CN201410202876.4 to disclose a kind of GPS navigation map of pilotless automobile
Accurate matching system and its operating method, wherein method include：Obtain road information；Determine starting point；Obtain vehicle location letter
Breath；The matching and screening of information；Step noted earlier is repeated, until successful match.The present invention can narrow down to navigation error
Two meters and within, adjusted in time when more than two meters, significantly reduce navigation error.The GPS navigation map of pilotless automobile
Fine matching method, automobile navigation exactly obtain GPS receiver for summarizing with the map match in positioning system
Corresponding position in GPS track location matches with error to the traffic map vector road with error, the map
Method of completing the square includes following steps：A obtains road information；B determines beginning and end；C obtains vehicle location information；D information
Matching and screening；It is characterized in that the map fine matching method also specifically includes：A acquisitions information, carries storage information
Win the confidence breath, map is made；B determines starting point and terminal using the longitude and latitude point of ordered arrangement；C obtains the data of GPS and is used to
The data of property navigation system INS；D removes incorrect information using GPS and KML screenings；E repeats step 1 and arrives step 4, obtains
Best travel route.This method is only capable of the cartographic information of one automatic Pilot of acquisition.
Application No. is the patents of invention of CN201610226020.X to disclose a kind of traveling suitable for pilotless automobile
The accurate generation method of route, including route determination step, also comprising path discrimination step for the first time；Step 2: positioning device signal
Detecting step；Step 3: the acquisition of visual signature object data and driving information sub-data recording step；Step 4: visual signature coordinate
Library generation step；Step 5: driving scheme forming step.The only driving path that this method ultimately generates.
Invention content
In order to solve the above technical problems, the present invention proposes a kind of automatic driving vehicle multipath based on differential navigation
The creation method of map can generate a plurality of map path for the automatic Pilot region of rule and supply more automatic Pilots simultaneously
Vehicle；For irregular path, a plurality of lane position information can be acquired simultaneously.
The present invention provides a kind of creation method of the automatic driving vehicle multipath map based on differential navigation, including definition
Automatic Pilot cartographic information, it is further comprising the steps of：
Step 1：Acquire multi-trace map；
Step 2：Generate automatic driving vehicle multi-trace；
The multi-trace map includes regular landform and/or irregular landform.
Preferably, the cartographic information includes acquisition time, longitude, latitude, azimuth, differential state, waypoint attribute 1
At least one of with waypoint attribute 2.
In any of the above-described scheme preferably, the rule landform refers to can be carried out according to a certain travel route
Landform respectively.
In any of the above-described scheme preferably, the irregular terrain profiles refer to the ground that cannot be divided equally with single travel route
Shape.
In any of the above-described scheme preferably, rule landform track acquisition method includes the following steps：
Step 11：Collecting vehicle is acquired according to specified path；
Step 12：Medium filtering and overstocked point deletion are carried out to the data collected.
In any of the above-described scheme preferably, the calculation formula in the step 12 is：
F (x, y)=med { g (x-k, y-l), (k, l ∈ w) }, wherein w is two dimension pattern plate.
In any of the above-described scheme preferably, the screening technique of the overstocked point is used as mark using set point spacing threshold
Standard is a little smaller than the point of threshold value to reject.
In any of the above-described scheme preferably, the rule landform multi-trace generation method can acquire benchmark road
Line and offline progress.
In any of the above-described scheme preferably, the rule landform multi-trace generation method includes the following steps：
Step 21：Inverse geodetic problem is carried out to the path point that each is obtained, assigns the point in the path of acquisition as A successively
Point, it is θ that the azimuth of the point in acquisition path, which is added and subtracted 90 degree as A points to B points azimuth, between the transverse direction for needing to generate track
Away from as A points to B point spherical distances be L；
Step 22：The longitude and latitude of the B points is obtained by inverse geodetic problem, azimuth, RTK states, the road of the B points
Road attribute 1 is consistent with the A points with road attribute 2.
In any of the above-described scheme preferably, the rule landform multi-trace generation method further includes generating mulitpath
Method.
In any of the above-described scheme preferably, the generations mulitpath method be to acquire path successively equidistantly into
The multiple inverse geodetic problem of row, obtains mulitpath.
In any of the above-described scheme preferably, the irregular landform multi-trace generation method is generated in real time using online
Track approach.
In any of the above-described scheme preferably, the irregular landform multi-trace generation method is when track changes or ties
When calculation spherical distance L needs to change, using the computational methods of on-line proving inverse geodetic problem parameter.
In any of the above-described scheme preferably, the real-time generation track approach includes the following steps：
Step 31：It is in the tracks M in the tracks N, label A point moments two tracks of left side and the right side in A point moment collecting vehicles
The spherical distance in one track of side；
Step 32：It is that current collecting vehicle course angle adds 90 degree that record left side, which resolves angle, and it is current course angle that right side, which resolves angle,
The degree that subtracts 90；
Step 33：In AtPoint moment marks AtThe spherical distance in a track and two track of right side on the left of point moment；
Step 34：Collecting vehicle carries out map acquisition on a track, and the generation of a plurality of track is carried out according to link change.
In any of the above-described scheme preferably, the real-time generation track approach further includes being carried out as track changes
Parameter real-time calibration, so that it may obtain accurately multilane navigation map.
The present invention proposes a kind of creation method of the automatic driving vehicle multipath map based on differential navigation, the method
Solution is provided for the generation of automatic Pilot multipath, the automatic Pilot region of rule can be generated simultaneously a plurality of
Figure path supplies more automatic Pilot vehicles；For irregular path, a plurality of lane position information can be acquired simultaneously.The present invention can
To apply to agriculture automatic Pilot large area map acquisition, the acquisition of urban road multilane, the acquisition of garden multilane, automatic Pilot
In the practices such as platooning's navigation.
Description of the drawings
Fig. 1 is the one excellent of the creation method of the automatic driving vehicle multipath map according to the invention based on differential navigation
Select the flow chart of embodiment.
Fig. 2 is the creation method of the automatic driving vehicle multipath map according to the invention based on differential navigation such as figure
The regular landform multi-trace generation method flow chart of 1 illustrated embodiment.
Fig. 2A be the automatic driving vehicle multipath map according to the invention based on differential navigation creation method as
The regular landform of embodiment illustrated in fig. 2 places an order a map route map.
Fig. 2 B be the automatic driving vehicle multipath map according to the invention based on differential navigation creation method as
The regular landform of embodiment illustrated in fig. 2 places an order a route azimuth view.
Fig. 2 C be the automatic driving vehicle multipath map according to the invention based on differential navigation creation method as
The longitude and latitude point schematic diagram of the new track of generation of embodiment illustrated in fig. 2.
Fig. 2 D be the automatic driving vehicle multipath map according to the invention based on differential navigation creation method as
The generation track schematic diagram of embodiment illustrated in fig. 2.
Fig. 2 E be the automatic driving vehicle multipath map according to the invention based on differential navigation creation method as
The both sides of embodiment illustrated in fig. 2 generate equidistant trajectory diagram.
Fig. 2 F be the automatic driving vehicle multipath map according to the invention based on differential navigation creation method as
The both sides of embodiment illustrated in fig. 2 generate a plurality of trajectory diagram.
Fig. 3 is the creation method of the automatic driving vehicle multipath map according to the invention based on differential navigation such as figure
The irregular landform multi-trace generation method flow chart of 1 illustrated embodiment.
Fig. 3 A be the automatic driving vehicle multipath map according to the invention based on differential navigation creation method as
The both sides of embodiment illustrated in fig. 3 generate a plurality of track trajectory diagram.
Fig. 3 B be the automatic driving vehicle multipath map according to the invention based on differential navigation creation method as
The irregular landform of embodiment illustrated in fig. 3 marks Geodetic Problem to resolve Parameter Map online.
Fig. 4 is the one excellent of the creation method of the automatic driving vehicle multipath map according to the invention based on differential navigation
The inverse geodetic problem coordinate of embodiment is selected to calculate schematic diagram.
Specific implementation mode
The present invention is further elaborated with specific embodiment below in conjunction with the accompanying drawings.
Embodiment one
As shown in Figure 1, executing step 100, automatic Pilot cartographic information is defined.As shown in table 1, single in automatic Pilot map
A waypoint information by：Acquisition time, longitude, latitude, azimuth (course angle of collecting vehicle when acquisition map), differential state (
Figure acquisition point location judging basis), (section marks waypoint attribute 1：Main mark section is longitudinally varying, such as bend, straight way, U_
Turn etc.) (section marks with waypoint attribute 2：Main mark section cross directional variations, such as one-way road, multilane) composition.
1 single waypoint information of table
Step 110 is executed, judges the type of multi-trace map.The acquisition of multi-trace map is divided into two kinds：Regular landform, it is non-
Regular landform.Regular landform refers to that the landform that can be carried out according to a certain travel route respectively can be used, such as rectangle, circle
Farmland, the consistent multilane etc. of quantity；Irregular landform refers to the landform that unavailable single travel route is divided equally, such as city track
The road of variation, garden unstructured road etc..
If it is regular landform, 120 are thened follow the steps, executing rule landform multi-trace generation method.The regular more rails of landform
Mark generation can offline carry out after having acquired reference route.As shown in Fig. 2, step 200 is executed, the acquisition of datum line navigation map.
Path acquisition is carried out according to table 1 with collecting vehicle, navigation movement station is installed, movement station is normal with base station communication in collecting vehicle.Acquisition
Complete data need to carry out data medium filtering and overstocked point deletion, and medium filtering uses 1 × 5 neighborhood template.F (x, y)=med
{ g (x-k, y-l), (k, l ∈ w) }, wherein w is two dimension pattern plate.Overstocked point screening is to accumulate overstocked ground to delete collection point
Side does so and is conducive to save memory space, while efficiency when accelerating map reference, screening mode use set point spacing threshold
Value rejects the point for being a little smaller than threshold value as standard.A smooth and equidistant map is can be obtained by above two step
Path, as shown in Fig. 2A, 2B.Step 210 is executed, calculates and generates trace bar number and direction.It is consistent for automatic Pilot path
Property, the path of generation is also required to store waypoint according to the format of table 1, and the longitude and latitude of B points is obtained by Fig. 2 C inverse geodetic problems,
The azimuth of B points, RTK states, road attribute 1 are consistent with the point of A with road attribute 2.Fig. 2A all the points carry out landlord's key to exercises
Calculation obtains Fig. 2 D.Execute step 220, the map path traversed.Step 230 is executed, judges whether to reach map tail portion.Such as
Fruit does not reach map tail portion, thens follow the steps 231, carries out Geodetic Problem clearing to the map collected, executes step
232, new route point will be assigned by resolving coordinate property value, course angle, RTK.Step 220, the map traversed are executed again
Path.If reaching map tail portion, 240 are thened follow the steps, preserves all paths.If desired mulitpath is generated, it only need to be right
Acquisition path equidistantly carries out inverse geodetic problem successively, as shown in Fig. 2 E, 2F.What wherein Fig. 2 E were indicated is according to offline acquisition
Track generates inside and outside each track；What Fig. 2 F were indicated is to generate an interior track and four according to that acquisition trajectories of interest
Track illustrates that according to the present invention a plurality of path line can be generated.
More automatic driving vehicles may be implemented in the case where only acquiring a map according to this method while running, or
One automatic driving vehicle of person run simultaneously it is multiple, greatly reduce that automatic Pilot navigation map under regular landform acquires when
Between cost.
If it is irregular landform, 130 are thened follow the steps, executes irregular landform multi-trace generation method, is taken online
The method for generating track in real time.When track changes, or spherical distance L is resolved when need to change, take on-line proving big
The method of ground theme back-calculation parameter.As shown in figure 3, executing step 300, start acquisition guidance path in real time.Step 310 is executed,
Acquisition waypoint reef knot calculates parameter in fact for calibration.Step 320 is executed, new route point is obtained.Step 330 is executed, whether judges section
Track variation occurs.Changing in case of track, then sequence executes step 335 and step 340, and real-time calibration reef knot calculates parameter,
And the map to collecting carries out Geodetic Problem resolving.If track variation does not occur, 340 are thened follow the steps, to acquisition
Obtained map carries out Geodetic Problem resolving.As shown in Figure 3A, A point moments collecting vehicle is in the third track in 4 tracks, needs
The spherical distance in left side two tracks and one track in right side at this time is marked, while it is current collecting vehicle course to resolve angle in accordance with left side
Angle adds 90 degree, and right side is the current course angle degree that subtracts 90.Similarly AtPoint needs one track in label left side, two, right side track, mark
Note method is the same as A points.Step 350 is executed, new route point will be assigned by resolving coordinate property value, course angle, RTK.Execute step
360, judge whether to terminate acquisition.If acquisition is not over, 320 are thened follow the steps, obtains new route point.If acquisition knot
Beam thens follow the steps 370, preserves all paths.According to the method, collecting vehicle carries out map acquisition on a track, simultaneously
A plurality of Track Pick-up can be carried out according to the variation of road, as shown in Figure 3B, as track changes, carry out parameter real-time calibration,
The storage organization of just available accurately multilane navigation map, each lane path point is consistent with table 1.
Embodiment two
As shown in figure 4, inverse geodetic problem solve the problems, such as be：Known A points latitude and longitude coordinatesA points are to B
Point spherical distance is L, and A points to B points azimuth are θ, seek B point longitudes and latitudes
The earth as a regular sphere, often degree arc length is Δ S (generally earth perimeter divided by 360 knot in engineering
Fruit is upper per arc length once as centre of sphere circle, generally approximately takes 111.199 kilometers).Arctic point N is taken, then ANB three-point shapes are at one
Spherical triangle.Corner relationship is as follows：
AN point-to-point transmission camber lines are a length of：And ∠ NBA and AN are an opposite side and angle.
BN point-to-point transmission camber lines are a length of：And ∠ NAB and BN are an opposite side and angle.
Camber line is a length of between AB：And<ANB and AB be an opposite side and angle, wherein
It can then be obtained by the spherical trigonometry cosine law：
Cos NB=cos NA cos AB+sin NA sin AB cos ∠ NAB
B point latitudes can be obtained above.It can be obtained further according to spherical trigonometry sine：
Since ∠ NBA are unknown, then only take first two to solve, can obtain：
By B point latitude and longitude coordinates can be obtained above.
For a better understanding of the present invention, it is described in detail above in association with specific embodiments of the present invention, but is not
Limitation of the present invention.Every any simple modification made to the above embodiment according to the technical essence of the invention, still belongs to
In the range of technical solution of the present invention.In this specification the highlights of each of the examples are it is different from other embodiments it
Locate, same or analogous part cross-reference between each embodiment.For system embodiments, due to itself and method
Embodiment corresponds to substantially, so description is fairly simple, the relevent part can refer to the partial explaination of embodiments of method.
Claims (10)
1. a kind of creation method of the automatic driving vehicle multipath map based on differential navigation, including define automatic Pilot map
Information, it is characterised in that：It is further comprising the steps of：
Step 1：Acquire multi-trace map；
Step 2：Generate automatic driving vehicle multi-trace；
The multi-trace map includes regular landform and/or irregular landform.
2. the creation method of the automatic driving vehicle multipath map based on differential navigation as described in claim 1, feature
It is：The cartographic information includes acquisition time, longitude, latitude, azimuth, differential state, waypoint attribute 1 and waypoint attribute 2
At least one of.
3. the creation method of the automatic driving vehicle multipath map based on differential navigation as described in claim 1, feature
It is：The rule landform refers to the landform that can be carried out according to a certain travel route respectively.
4. the creation method of the automatic driving vehicle multipath map based on differential navigation as described in claim 1, feature
It is：The irregular terrain profiles refer to the landform that cannot be divided equally with single travel route.
5. the creation method of the automatic driving vehicle multipath map based on differential navigation as claimed in claim 3, feature
It is：Rule landform track acquisition method includes the following steps：
Step 11：Collecting vehicle is acquired according to specified path；
Step 12：Medium filtering and overstocked point deletion are carried out to the data collected.
6. the creation method of the automatic driving vehicle multipath map based on differential navigation as claimed in claim 5, feature
It is：Calculation formula in the step 12 is：
F (x, y)=med { g (x-k, y-l), (k, l ∈ w) }, wherein w is two dimension pattern plate.
7. the creation method of the automatic driving vehicle multipath map based on differential navigation as claimed in claim 6, feature
It is：The screening technique of the overstocked point rejects the point for being a little smaller than threshold value using set point spacing threshold as standard.
8. the creation method of the automatic driving vehicle multipath map based on differential navigation as claimed in claim 7, feature
It is：The rule landform multi-trace generation method can acquire reference route and offline progress.
9. the creation method of the automatic driving vehicle multipath map based on differential navigation as claimed in claim 8, feature
It is：The rule landform multi-trace generation method includes the following steps：
Step 21：Inverse geodetic problem is carried out to the path point that each is obtained, assigns the point in the path of acquisition as A points successively,
It is θ that the azimuth of the point in acquisition path, which is added and subtracted 90 degree as A points to B points azimuth, the horizontal spacing for needing to generate track
It is L as A points to B point spherical distances；
Step 22：The longitude and latitude of the B points is obtained by inverse geodetic problem, the azimuth of the B points, RTK states, road category
Property 1 is consistent with the A points with road attribute 2.
10. the creation method of the automatic driving vehicle multipath map based on differential navigation as claimed in claim 5, feature
It is：The rule landform multi-trace generation method further includes generating mulitpath method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810387336.6A CN108645420B (en) | 2018-04-26 | 2018-04-26 | Method for creating multipath map of automatic driving vehicle based on differential navigation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810387336.6A CN108645420B (en) | 2018-04-26 | 2018-04-26 | Method for creating multipath map of automatic driving vehicle based on differential navigation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108645420A true CN108645420A (en) | 2018-10-12 |
| CN108645420B CN108645420B (en) | 2022-06-14 |
Family
ID=63747974
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810387336.6A Active CN108645420B (en) | 2018-04-26 | 2018-04-26 | Method for creating multipath map of automatic driving vehicle based on differential navigation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108645420B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109726676A (en) * | 2018-12-28 | 2019-05-07 | 苏州大学 | The planing method of automated driving system |
| CN109739225A (en) * | 2018-12-18 | 2019-05-10 | 北京百度网讯科技有限公司 | Location data processing method, device, equipment, storage medium and vehicle |
| CN110187372A (en) * | 2019-06-20 | 2019-08-30 | 北京联合大学 | Combinated navigation method and system in a kind of low speed unmanned vehicle garden |
| CN111076732A (en) * | 2018-10-19 | 2020-04-28 | 百度（美国）有限责任公司 | Track marking and high-definition map generation marking scheme based on vehicle running |
| WO2020125686A1 (en) * | 2018-12-19 | 2020-06-25 | 长沙智能驾驶研究院有限公司 | Method for generating real-time relative map, intelligent driving device and computer storage medium |
| CN112053592A (en) * | 2020-04-28 | 2020-12-08 | 上海波若智能科技有限公司 | Road network dynamic data acquisition method and road network dynamic data acquisition system |
| CN112579924A (en) * | 2020-12-29 | 2021-03-30 | 武汉中海庭数据技术有限公司 | Road generation method, electronic device, and storage medium |
| WO2021169993A1 (en) * | 2020-02-29 | 2021-09-02 | 华为技术有限公司 | Method for constructing self-driving map and related device |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008072963A (en) * | 2006-09-21 | 2008-04-03 | Yanmar Co Ltd | Agricultural working vehicle |
| EP1939589A1 (en) * | 2006-12-27 | 2008-07-02 | Aisin AW Co., Ltd. | Map information generating system |
| US20120221168A1 (en) * | 2011-02-28 | 2012-08-30 | GM Global Technology Operations LLC | Redundant lane sensing systems for fault-tolerant vehicular lateral controller |
| JP5522785B2 (en) * | 2010-03-19 | 2014-06-18 | 株式会社日立ソリューションズ | Agricultural work vehicle operation management system |
| CN104089619A (en) * | 2014-05-14 | 2014-10-08 | 北京联合大学 | GPS navigation map accurate matching system of pilotless automobile, and its operation method |
| CN104781633A (en) * | 2014-03-06 | 2015-07-15 | 日本集奥瑟甫有限公司 | Agricultural field navigation system and agricultural field navigation method, software and software storage equipment |
| CN106441319A (en) * | 2016-09-23 | 2017-02-22 | 中国科学院合肥物质科学研究院 | System and method for generating lane-level navigation map of unmanned vehicle |
| 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 |
| CN107613751A (en) * | 2015-09-14 | 2018-01-19 | 株式会社久保田 | Working truck support system |
-
2018
- 2018-04-26 CN CN201810387336.6A patent/CN108645420B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008072963A (en) * | 2006-09-21 | 2008-04-03 | Yanmar Co Ltd | Agricultural working vehicle |
| EP1939589A1 (en) * | 2006-12-27 | 2008-07-02 | Aisin AW Co., Ltd. | Map information generating system |
| JP5522785B2 (en) * | 2010-03-19 | 2014-06-18 | 株式会社日立ソリューションズ | Agricultural work vehicle operation management system |
| US20120221168A1 (en) * | 2011-02-28 | 2012-08-30 | GM Global Technology Operations LLC | Redundant lane sensing systems for fault-tolerant vehicular lateral controller |
| CN104781633A (en) * | 2014-03-06 | 2015-07-15 | 日本集奥瑟甫有限公司 | Agricultural field navigation system and agricultural field navigation method, software and software storage equipment |
| CN104089619A (en) * | 2014-05-14 | 2014-10-08 | 北京联合大学 | GPS navigation map accurate matching system of pilotless automobile, and its operation method |
| CN107613751A (en) * | 2015-09-14 | 2018-01-19 | 株式会社久保田 | Working truck support system |
| CN106441319A (en) * | 2016-09-23 | 2017-02-22 | 中国科学院合肥物质科学研究院 | System and method for generating lane-level navigation map of unmanned vehicle |
| 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 |
|---|
| CHUNLEI YU等: "Semantic evidential lane grids with prior maps for autonomous navigation", 《2016 IEEE 19TH INTERNATIONAL CONFERENCE ON INTELLIGENT TRANSPORTATION SYSTEMS (ITSC)》 * |
| 关泉珍等: "基于A*算法的驾驶地图路径规划实现", 《北京联合大学学报(自然科学版)》 * |
| 萨尔托夫: "《高等测量学教程》", 30 November 1956, 第72、74、96-97页 * |
| 高子萍等: "一种无人驾驶汽车的资产监控系统", 《中国计算机用户协会网络应用分会2017年第二十一届网络新技术与应用年会论文集》 * |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111076732B (en) * | 2018-10-19 | 2023-08-29 | 百度（美国）有限责任公司 | Track marking based on vehicle driving and marking scheme for generating high-definition map |
| CN111076732A (en) * | 2018-10-19 | 2020-04-28 | 百度（美国）有限责任公司 | Track marking and high-definition map generation marking scheme based on vehicle running |
| CN109739225B (en) * | 2018-12-18 | 2021-04-20 | 北京百度网讯科技有限公司 | Positioning data processing method, device, equipment, storage medium and vehicle |
| CN109739225A (en) * | 2018-12-18 | 2019-05-10 | 北京百度网讯科技有限公司 | Location data processing method, device, equipment, storage medium and vehicle |
| US11619515B2 (en) | 2018-12-18 | 2023-04-04 | Apollo Intelligent Driving Technology (Beijing) Co., Ltd. | Method and apparatus for processing positioning data, device, storage medium and vehicle |
| WO2020125686A1 (en) * | 2018-12-19 | 2020-06-25 | 长沙智能驾驶研究院有限公司 | Method for generating real-time relative map, intelligent driving device and computer storage medium |
| CN109726676A (en) * | 2018-12-28 | 2019-05-07 | 苏州大学 | The planing method of automated driving system |
| CN110187372B (en) * | 2019-06-20 | 2021-11-02 | 北京联合大学 | Combined navigation method and system in low-speed unmanned vehicle park |
| CN110187372A (en) * | 2019-06-20 | 2019-08-30 | 北京联合大学 | Combinated navigation method and system in a kind of low speed unmanned vehicle garden |
| WO2021169993A1 (en) * | 2020-02-29 | 2021-09-02 | 华为技术有限公司 | Method for constructing self-driving map and related device |
| CN112053592A (en) * | 2020-04-28 | 2020-12-08 | 上海波若智能科技有限公司 | Road network dynamic data acquisition method and road network dynamic data acquisition system |
| CN112579924A (en) * | 2020-12-29 | 2021-03-30 | 武汉中海庭数据技术有限公司 | Road generation method, electronic device, and storage medium |
| CN112579924B (en) * | 2020-12-29 | 2022-03-25 | 武汉中海庭数据技术有限公司 | Road generation method, electronic device, and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108645420B (en) | 2022-06-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108645420A (en) | A kind of creation method of the automatic driving vehicle multipath map based on differential navigation | |
| CN106441319B (en) | A kind of generation system and method for automatic driving vehicle lane grade navigation map | |
| US20210311490A1 (en) | Crowdsourcing a sparse map for autonomous vehicle navigation | |
| JP7127941B2 (en) | Method, system and program | |
| CN105588576B (en) | A kind of lane grade navigation methods and systems | |
| CN102208012B (en) | Landscape coupling reference data generation system and position measuring system | |
| CN102208036B (en) | Vehicle position detection system | |
| CN103499350B (en) | Vehicle high-precision localization method and the device of multi-source information is merged under GPS blind area | |
| CN110111566A (en) | Trajectory predictions method, apparatus and storage medium | |
| Brenner | Extraction of features from mobile laser scanning data for future driver assistance systems | |
| CN108303103A (en) | The determination method and apparatus in target track | |
| GB2614379A (en) | Systems and methods for vehicle navigation | |
| JP5388082B2 (en) | Stationary object map generator | |
| JP5404861B2 (en) | Stationary object map generator | |
| CN110146910A (en) | A kind of localization method and device merged based on GPS with laser radar data | |
| CN106980657A (en) | A kind of track level electronic map construction method based on information fusion | |
| CN105930819A (en) | System for real-time identifying urban traffic lights based on single eye vision and GPS integrated navigation system | |
| EP3671278B1 (en) | Road surface detection | |
| CN109357680A (en) | The unmanned container truck high-precision ground drawing generating method in harbour | |
| GB2621499A (en) | Systems and methods for vehicle navigation | |
| CN109544443A (en) | A kind of route drawing generating method and device | |
| CN110441760A (en) | A kind of large-scale seabed topographic map expansion patterning process based on priori topographic map | |
| CN115597593A (en) | Real-time navigation method and device based on high-precision map | |
| CN115546551A (en) | Deep learning-based geographic information extraction method and system | |
| CN112462401B (en) | Urban canyon rapid detection method and device based on floating vehicle track data |
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 |