CN111680113A - Intersection vector-grid map scheme suitable for small-sized automatic driving vehicle - Google Patents
Intersection vector-grid map scheme suitable for small-sized automatic driving vehicle Download PDFInfo
- Publication number
- CN111680113A CN111680113A CN201910246996.7A CN201910246996A CN111680113A CN 111680113 A CN111680113 A CN 111680113A CN 201910246996 A CN201910246996 A CN 201910246996A CN 111680113 A CN111680113 A CN 111680113A
- Authority
- CN
- China
- Prior art keywords
- map
- vector
- attributes
- grid map
- small
- 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.)
- Pending
Links
- 230000004888 barrier function Effects 0.000 claims 1
- 238000000034 method Methods 0.000 description 3
- 239000004575 stone Substances 0.000 description 3
- 230000004075 alteration Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
Abstract
The invention discloses an intersection vector-grid map scheme suitable for a small automatic driving vehicle. The map scheme can provide a basis for automatic vehicle driving decision by combining a vector map (shown in figure 1) and a grid map (shown in figure 2) under the environment of intersections or other unconventional roads, so that the high-precision map not only has rich semantic information and strict road rules, but also has sufficient and flexible passable areas, and can ensure that the small unmanned vehicle can smoothly run. The intersection vector-grid map suitable for the small automatic driving vehicle integrates the advantages of the vector map and the grid map, so that the small automatic driving vehicle can effectively run in more scenes.
Description
Technical Field
The invention relates to the field of maps required by automatic driving vehicles, in particular to a crossing vector-grid map scheme suitable for small automatic driving vehicles.
Background
The development of automatic driving technology has prompted the emergence of high-precision maps. The service object of the high-precision map is mainly an automatic driving vehicle, wherein the service object mainly comprises driving auxiliary information, including road surface geometric structure, lane information, road front and back connection information and semantic information, or only passable or not passable information in a certain range.
At present, the maps commonly used in the domestic and foreign industries are vector maps and grid maps. The vector map describes roads and their surroundings strictly according to the rules of the roads, and although it can accurately represent road information but limits the driving range of the autonomous vehicle, it is suitable for a conventional large autonomous vehicle, but not for a small autonomous vehicle where flexibility is more important. The grid map is represented by a gray level map, one map represents the environment by various gray levels, although the construction is simple and the passable area is flexible, the path planning efficiency under a long distance is not high, the road rule is neglected in the planned path, and the semantic information is seriously lacked.
Disclosure of Invention
The invention aims to provide a crossing vector-grid map scheme suitable for a small automatic driving vehicle, so as to solve the problems of the existing vector map and grid map respectively.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows:
an intersection vector-grid map scheme suitable for use with small autonomous vehicles, comprising: the vector map and the grid map are used in combination in the intersection environment, so that the high-precision map has rich semantic information and strict road rules, has sufficient and flexible passable areas, and can ensure the smooth running of the small unmanned vehicle. The vector map comprises two broad categories of object attributes and semantic information.
As a preferable intersection vector-grid map scheme suitable for small-sized autonomous vehicles, the object attributes of the vector map include discrete point type reference line attributes, lane attributes, and road connection attributes. The discrete point type reference line attribute is used to describe the shape and the trend of the road. And the lane attributes are used for describing the left lane and the right lane and comprise whether the lanes can pass or not, the lane width and whether the lane between the lanes can change or not. And the road connection attribute is used for describing the connection relationship between adjacent roads.
As a preferred intersection vector-grid map scheme suitable for small autonomous vehicles, semantic information of the vector map includes a curve attribute, a gradient attribute, a boundary distance attribute, an electronic fence attribute, a transverse crossing attribute, a traffic light attribute, and a fixed obstacle attribute. And a curve attribute for describing curve information on the road. And the gradient attribute is used for describing the information of the uphill and downhill of the road. And the boundary distance attribute is used for describing the distance from the road boundary required in the driving process of the unmanned vehicle. And the electronic fence attribute is generated by combining the reference line and the road width. And the transverse crossing attribute is used for describing whether a certain section of the lane has the non-crossing attribute, such as a railing. And the traffic light attribute is used for describing the position and the height information of the traffic light. And the fixed obstacle attribute is used for describing whether a certain object, such as stone balls, is arranged at a certain position of the lane.
As a preference for an intersection vector-grid map scheme suitable for small autonomous vehicles, the grid map contains both passable and impassable area attributes. The passable area attribute is represented by a gray value of 255 and the area in the surface map through which the small autonomous vehicle can pass. The attribute of the impassable area is represented by a gray value 0, which indicates that the small and medium-sized automatic driving vehicles in the map can not pass through the area, and covers objects such as steps, fixed obstacles and the like.
Drawings
The invention is further illustrated by the following figures and examples. The drawings in the following description are directed to merely some embodiments of the invention.
Fig. 1 shows a vector map in the high-precision map of the present invention, wherein 1 is a lane, 2 is a reference line, 3 is a fixed obstacle stone ball, and 4 is a traffic light.
Fig. 2 is a grid map in the high-precision map of the present invention, the range of which corresponds to the vector map of fig. 1, where 1 is a passable area and 2 is a non-passable area.
Detailed Description
The invention provides a vector map in an intersection vector-grid map scheme suitable for small-sized automatic driving vehicles, which accurately expresses road information and serves the automatic driving vehicles.
The automatic driving vehicle acquires the reference line attribute in the vector map, the attribute is represented by discrete points, and when the vehicle is in the road, the current position and the direction of the road to be driven are determined by judging which point is closest to the automatic driving vehicle. The autonomous vehicle acquires the lane attributes in the vector map, knows which lane is currently on which road, and knows whether the lane is passable and whether the lane can be crossed. The automatic driving vehicle obtains the connection attribute between roads in the vector map, and can plan the path between the starting point and the end point through the attribute, and automatically selects the optimal path which can be passed through.
The autonomous vehicle acquires a curve attribute in the vector map that marks whether the current position is in a sharp curve of the road. In the normal running process, when the vehicle receives a steering command, the vehicle is corrected by a small angle, and the vehicle is deflected by a large angle at a sharp turn. The automatic driving vehicle acquires gradient attributes in a vector map, and when the automatic driving vehicle runs to an upper slope or a lower slope, the automatic driving vehicle properly accelerates and decelerates to ensure the stability of speed and the safety of running. The automatic driving vehicle obtains the electronic fence attribute in the vector map, can quickly judge whether the vehicle is on a certain road, can screen the scanned environmental point cloud, and only keeps the point cloud in the road range. The automatic driving vehicle acquires the transverse crossing attribute in the vector map, so that whether the current road has an obstacle which cannot be crossed can be determined, and the section of the lane where the obstacle is located and how far away from the road boundary can be determined. By this attribute, the vehicle chooses to wait instead of driving to the opposite side of the road if the front is blocked while the vehicle is traversing the road segment. The automatic driving vehicle acquires the traffic light attribute in the vector map, when the vehicle runs to the intersection recorded with the attribute, the traffic light detection is started, and a proper decision is made according to the state of the traffic light. The automatic driving vehicle obtains the attribute of the obstacle in the vector map, and can determine whether the current road has some kind of obstacle and which section of the lane the obstacle is located in. For example, some roads have spaced stone balls placed on them, and by this property, the vehicle can choose to pass slowly as it passes through the road section.
The invention provides a grid map in an intersection vector-grid map scheme suitable for small automatic driving vehicles, which is generated by using binary maps of 0 and 255 directly based on a vector map, wherein the resolution of a unit pixel is 10cm, 0 represents an impassable area, and 255 represents a passable area. The automatic driving vehicle can obtain the information whether the automatic driving vehicle can pass in the grid map, and the local optimal path is planned to provide the local optimal path for the automatic driving vehicle.
The small-sized automatic driving vehicle can switch the vector map and the grid map in the driving process, can drive according to the requirements of the vector map strictly in the scene of normal driving, ensures the safe driving of the automatic driving vehicle, and can switch the grid map to use under the special scenes of failure of planning the path of the conventional map, serious blockage of the intersection, large-scale maintenance of the intersection and the like, so that the limitation of the road of the conventional map is broken, and the passable path is planned.
The above-described embodiments are merely preferred embodiments of the present invention, and should not be construed as limiting the present invention, and the embodiments and features of the embodiments in the present application may be arbitrarily combined with each other without conflict. The protection scope of the present invention is defined by the claims, and includes equivalents of technical features of the claims. I.e., equivalent alterations and modifications within the scope hereof, are also intended to be within the scope of the invention.
Claims (6)
1. An intersection vector-grid map scheme suitable for use with small autonomous vehicles, comprising: the vector map and the grid map are used in combination in the intersection environment.
2. The intersection vector-grid map for a small autonomous vehicle of claim 1, wherein: the vector map comprises two contents of object attributes and semantic information.
3. The vector map object property of claim 1, wherein: including discrete point reference line attributes, lane attributes, and connection attributes of roads and lanes.
4. The vector map semantic information of claim 1, wherein: including curve attributes, slope attributes, boundary distance attributes, electronic fence attributes, lateral crossing attributes, traffic light attributes, fixed barrier attributes.
5. The intersection vector-grid map for a small autonomous vehicle of claim 1, wherein: the grid map is represented by a binary image of 0 and 255, wherein 0 represents an unviable area and 255 represents a passable area.
6. An intersection vector-grid map scheme suitable for small autonomous vehicles, wherein the intersection vector-grid map suitable for small autonomous vehicles as claimed in claims 1-3 is used to provide guidance for small vehicular autonomous vehicle decision making. Under normal conditions, the vector map is used for strictly planning the path at the lane level under the small automatic driving vehicle, and when the conventional path planning fails, the road at the intersection is seriously blocked, and the road is maintained in a large range, the grid map is adopted for flexibly planning the local path.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910246996.7A CN111680113A (en) | 2019-03-11 | 2019-03-11 | Intersection vector-grid map scheme suitable for small-sized automatic driving vehicle |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910246996.7A CN111680113A (en) | 2019-03-11 | 2019-03-11 | Intersection vector-grid map scheme suitable for small-sized automatic driving vehicle |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111680113A true CN111680113A (en) | 2020-09-18 |
Family
ID=72451311
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910246996.7A Pending CN111680113A (en) | 2019-03-11 | 2019-03-11 | Intersection vector-grid map scheme suitable for small-sized automatic driving vehicle |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111680113A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112896181A (en) * | 2021-01-14 | 2021-06-04 | 重庆长安汽车股份有限公司 | Electronic fence control method, system, vehicle and storage medium |
CN114563014A (en) * | 2021-12-15 | 2022-05-31 | 武汉中海庭数据技术有限公司 | Opendrive map automatic detection method and device based on simulation image |
CN116105742A (en) * | 2023-04-14 | 2023-05-12 | 季华实验室 | Composite scene inspection navigation method, system and related equipment |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101158966A (en) * | 2007-11-01 | 2008-04-09 | 北京航空航天大学 | City environment quantized data organization method based on vector and lattice mixed representing |
CN107144288A (en) * | 2017-05-19 | 2017-09-08 | 北京旋极伏羲大数据技术有限公司 | The method and its device of a kind of path planning under orographic condition without road network |
US20180164811A1 (en) * | 2016-12-14 | 2018-06-14 | Hyundai Motor Company | Automated driving control device, system including the same, and method thereof |
CN108981726A (en) * | 2018-06-09 | 2018-12-11 | 安徽宇锋智能科技有限公司 | Unmanned vehicle semanteme Map building and building application method based on perceptual positioning monitoring |
-
2019
- 2019-03-11 CN CN201910246996.7A patent/CN111680113A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101158966A (en) * | 2007-11-01 | 2008-04-09 | 北京航空航天大学 | City environment quantized data organization method based on vector and lattice mixed representing |
US20180164811A1 (en) * | 2016-12-14 | 2018-06-14 | Hyundai Motor Company | Automated driving control device, system including the same, and method thereof |
CN107144288A (en) * | 2017-05-19 | 2017-09-08 | 北京旋极伏羲大数据技术有限公司 | The method and its device of a kind of path planning under orographic condition without road network |
CN108981726A (en) * | 2018-06-09 | 2018-12-11 | 安徽宇锋智能科技有限公司 | Unmanned vehicle semanteme Map building and building application method based on perceptual positioning monitoring |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112896181A (en) * | 2021-01-14 | 2021-06-04 | 重庆长安汽车股份有限公司 | Electronic fence control method, system, vehicle and storage medium |
CN112896181B (en) * | 2021-01-14 | 2022-07-08 | 重庆长安汽车股份有限公司 | Electronic fence control method, system, vehicle and storage medium |
CN114563014A (en) * | 2021-12-15 | 2022-05-31 | 武汉中海庭数据技术有限公司 | Opendrive map automatic detection method and device based on simulation image |
CN114563014B (en) * | 2021-12-15 | 2023-08-04 | 武汉中海庭数据技术有限公司 | Opendrive map automatic detection method based on simulation image |
CN116105742A (en) * | 2023-04-14 | 2023-05-12 | 季华实验室 | Composite scene inspection navigation method, system and related equipment |
CN116105742B (en) * | 2023-04-14 | 2023-07-04 | 季华实验室 | Composite scene inspection navigation method, system and related equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110667578B (en) | Lateral decision making system and lateral decision making determination method for automatic driving vehicle | |
US10948924B2 (en) | Method and apparatus for controlling an autonomous vehicle | |
CN110962843B (en) | Automatic parking control decision method and system | |
KR102408743B1 (en) | Method and system for determining whether a vehicle can enter a road | |
CN111680113A (en) | Intersection vector-grid map scheme suitable for small-sized automatic driving vehicle | |
JP6180928B2 (en) | How to find an elongate passage | |
CN101469991B (en) | All-day structured road multi-lane line detection method | |
CN104276075B (en) | Method for controlling the light distribution of headlight before motor vehicles | |
KR102613822B1 (en) | Control of vehicles throughout multi-lane turns | |
EP3822945B1 (en) | Driving environment information generation method, driving control method, driving environment information generation device | |
JP4614098B2 (en) | Peripheral situation recognition device and method | |
KR20170040620A (en) | Device for autonomous navigation assistant of vehicle and method thereof | |
CN110673595B (en) | Method and system for avoiding obstacle during automatic driving of vehicle and vehicle | |
CN110733504B (en) | Driving method of automatic driving vehicle with backup path | |
JP2007182151A (en) | Vehicular headlamp and method of controlling same | |
US20230054145A1 (en) | Methods and systems for monitoring vehicle motion with driver safety alerts | |
JP6297482B2 (en) | Information processing device | |
US11354912B2 (en) | Detecting potentially occluded objects for autonomous vehicles | |
US11347231B2 (en) | Object localization for autonomous driving by visual tracking and image reprojection | |
JP2007266975A (en) | Peripheral state recognition apparatus and method | |
CN113126635B (en) | Unmanned aerial vehicle-based highway lighting method and system | |
CN114509077A (en) | Method, device, system and computer program product for generating navigation guide line | |
CN110696827A (en) | Control method for autonomous vehicle | |
CN115457786B (en) | Method for passing through intersection of unmanned low-speed vehicle | |
KR20200060631A (en) | Apparatus for guiding vehicle driving |
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 | ||
DD01 | Delivery of document by public notice |
Addressee: Cheng Lingfeng Document name: Notice of First Examination Opinion |
|
DD01 | Delivery of document by public notice |