CN110118564B - Data management system, management method, terminal and storage medium for high-precision map - Google Patents
Data management system, management method, terminal and storage medium for high-precision map Download PDFInfo
- Publication number
- CN110118564B CN110118564B CN201910220177.5A CN201910220177A CN110118564B CN 110118564 B CN110118564 B CN 110118564B CN 201910220177 A CN201910220177 A CN 201910220177A CN 110118564 B CN110118564 B CN 110118564B
- Authority
- CN
- China
- Prior art keywords
- road
- unit
- ground object
- module
- information
- 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.)
- Active
Links
- 238000013523 data management Methods 0.000 title claims abstract description 39
- 238000007726 management method Methods 0.000 title claims abstract description 16
- 238000013439 planning Methods 0.000 claims abstract description 93
- 238000006243 chemical reaction Methods 0.000 claims abstract description 20
- 238000000034 method Methods 0.000 claims description 26
- 230000003068 static effect Effects 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims 1
- 238000013459 approach Methods 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 7
- 238000002955 isolation Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000001105 regulatory effect Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000016776 visual perception Effects 0.000 description 2
- 230000004888 barrier function Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/28—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
-
- 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 provides a data management system, a management method, a terminal and a storage medium of a high-precision map, wherein the ground object elements in the high-precision map are classified and collected into a ground object element set according to the semantics thereof, the positions, geometric attributes, physical attributes and/or semantic attributes of the ground object elements are recorded, when an application layer calls the map, an engine integrates the ground object elements needing to be described around track coordinates, a description planning module plans the relative spatial relationship between a path and a road unit, and when a vehicle approaches the ground object elements, a corresponding decision/control reaction is made according to the coordinate positions of the ground object elements and the semantics auxiliary decision control module of the ground object elements. In addition, the ground object elements in the high-precision map are classified and collected into a ground object element set according to the semantics thereof, so that the classification updating and management of the high-precision map database are facilitated, namely, the classification of specific semantics can be updated preferentially or iterated at high frequency.
Description
Technical Field
The present invention relates to the field of automotive electronics, and in particular, to a data management system, a management method, a terminal, and a storage medium for a high-precision map.
Background
The fine map is used as an electronic map and comprises space vector data and attribute information, wherein the space vector data is a carrier of the attribute information of the electronic map. The traditional electronic map manufacturing method adopts a method for abstracting and extracting space vector data based on raster data or utilizes a GPS and a robot positioning and tracking device to record and collect the space position and visual field information of a region to process and produce space vector data. Such fine maps do not meet the requirements of L4 or even L5 level autopilot.
The high-precision map not only contains space vector data but also contains a plurality of semantic information, the map can report meanings of different colors on traffic lights, the speed limit of a road and the position of a left-turn lane can be indicated, one of important characteristics of the high-precision map is precision, navigation on a mobile phone can only reach meter-level precision, and the high-precision map can reach centimeter-level precision, so that the high-precision map is very important for an unmanned vehicle. Maintaining these maps updated is a significant task and the survey fleet needs to continually verify and update high-precision maps. In addition, these map accuracies can reach several centimeters, which is the highest level of map making accuracy. The high-precision map is specially designed for the unmanned vehicle and comprises road definition, intersections, traffic signals, lane rules and other elements for automobile navigation.
The existing high-precision map has the following defects: all traffic marks such as a plurality of anti-collision strips, barriers, storage positions and storage bit lines, forbidden parking areas, crosswalk, deceleration strips, stopping, letting vehicles and the like and ground-approaching objects such as road marks, road signs, telegraph poles, road edges, trees, shrubs, isolation strips, guardrails and the like can be removed, modified and added along with the time, which is unfavorable for high-precision map updating, classifies and gathers ground object element sets, is convenient for updating and managing, and is favorable for the ground object element elements with specific semantics in the scene
Disclosure of Invention
In order to solve the above and other potential technical problems, the invention provides a data management system, a management method, a terminal and a storage medium of a high-precision map, wherein the ground object elements in the high-precision map are classified and collected into a ground object element set according to the semantics thereof, the positions, geometric attributes, physical attributes and/or semantic attributes of the ground object elements are recorded, when an application layer calls the map, an engine integrates the ground object elements needing to be described around track coordinates, describes the relative spatial relationship between a planning path of a planning module and a road unit, and when a vehicle approaches the ground object elements, a corresponding decision/control reaction is made according to the coordinate positions of the ground object elements and the semantics auxiliary decision control module of the ground object elements. In addition, the ground object elements in the high-precision map are classified and collected into a ground object element set according to the semantics thereof, so that the classification updating and management of the high-precision map database are facilitated, namely, the classification of specific semantics can be updated preferentially or iterated at high frequency.
A data management system for a high-precision map, comprising:
the road module comprises one or more of a lane unit, a road boundary unit and a road semantic unit;
the planning module is used for outputting a current vehicle planning path;
the system comprises a ground object element set, a positioning module and a planning module, wherein the ground object element set comprises requirements of a sensing module, a positioning module and a planning module on geometric attributes, physical attributes and/or semantic attributes and position coordinates of static target elements;
the coverage unit describes the relative spatial relationship between the ground object elements and the road units through the track coordinates and the planning module plans the path;
the management service module is used for acquiring the planning module to output a current vehicle planning path, acquiring ground feature elements related in the current vehicle planning path and outputting the ground feature elements and the current vehicle planning path to the planning module.
Further, the system also comprises a local map unit, wherein the local map unit comprises an image data string, a local map list, a map connectivity list and a local map coordinate conversion list.
Further, the local map list data in the local map unit is a catalog of local maps [ localmap ], and this dataset describes some metadata information of each local map; localMapID is the unique ID of the local map in the gallery. The area code and the subarea code are names of map scenes and local maps (local sub-scenes), and are generally identified by english abbreviations. Path is a relative Path of local map data, such as faw/a5.ZLevel is floor information, an integer with sign. IsRamp is a channel attribute and ID, and when IsRamp is-1, the local map is a non-channel, and when it is a positive integer, it is a channel number ID. When the same channel is cut into two partial maps, the ramp numbers represented by IsRamp in the two partial maps should be the same.
Further, the connection relationship list [ mapjunction. Dbf ] between the partial maps describes the connection relationship between two partial maps having the connection relationship. Here, the two partial maps have a connected relation of two by two regardless of the direction in which the partial maps are connected. A unique number is connected to each two partial maps. LocalMap1/2 is the ID of two local maps. TransID is a spatial conversion relation between map links, the spatial conversion relation is that LocalMap1 is converted into LocalMap2, and in calculation, the conversion from LocalMap2 to LocalMap1 is inverse operation of matrix conversion.
Further, the road unit is further included, and the road unit describes road information of a road network level and comprises one or more of road level, road type, road speed limit information, road height limit information and road boundary.
Further, the road unit is further included, and the road unit describes road information of a road network level, including road level, road type, road speed limit information and road height limit information. Preferably, the road unit further comprises semantic information of a road boundary line, a region outside the boundary line of the specific region. For example, a tunnel is outside the boundary line of a certain road, a cliff is outside the boundary line of a certain road, and so on. For example, the road level is a national road of a certain number, a provincial road of a certain number, and a county road of a certain number. For example, the road speed limit information is 120 km/h of the speed limit of the upper sea road section of a certain national road. For example, a county aisle has a height-limiting cue in planning the journey, such as limiting the height of a car passing.
Further, the lane unit describes scene-level lane information including one or more of lane-level space, lane topology and physical information, semantic information including road linearity, and traffic information.
Further, the lane unit describes scene-level lane information, including lane-level space, lane topology and physical information, semantic information including road linearity, and traffic information, wherein the lane-level space includes geometric coordinate line representations of lane center lines of lanes, lane line edge geometric representations, and restrictions on lane height dimensions; the semantic system information and traffic information including the road route property include the driving rule of the lane regulated by the lane at the position close to the intersection and the driving rule of the lane prohibiting lane changing at the specific distance close to the intersection. For example, there is an intersection in front, a road on which a vehicle is traveling has 4 lanes, a white side broken line of each lane becomes a white side solid line at 50 meters from the intersection, the semantics of the lane route property are lane-changing prohibition of the vehicle in the lane, and the semantics of the lane-changing prohibition and the lane-changing prohibition position are recorded in the lane unit. For example, there is an intersection in front, a road on which a vehicle is traveling has 4 lanes, the leftmost lane has straight and left turn marks, the second lane from left to right has straight marks, the third lane from left to right has straight and right turn marks, the fourth lane from left to right has right turn marks, and the semantics and position of the turn marks per lane are recorded in a lane unit. For example, there are 4 lanes on the road, and the lane on the far right is a bus-specific lane, and the semantics and position of the bus-specific lane are recorded in the lane unit.
Further, when the vehicle is in a parking garage scene in an autonomous parking mode, the vehicle parking garage further comprises a parking space unit, wherein the parking space unit comprises one or more of space information of a parking space, background information of the parking space, geometric representation of a parking access point of the parking space and geometric representation of a parking access line of the parking space.
Further, when the vehicle is in a parking garage scene in an autonomous parking mode, one or more of space information of a parking space in the parking space unit, background information of the parking space, geometric representation of a parking access point of the parking space and geometric representation of a parking access line of the parking space are displayed; the space information of the parking space comprises floor information of the garage where the parking space is located, the number of the parking space in the garage, length and width size information of the parking space and depth information in the height direction; the geometric representation of the parking access point comprises a coordinate representation of the parking access point; the parking access line is a geometric representation of a parking rule formed between the parking access point and surrounding road lines and between the parking access point and surrounding driving landmarks.
Further, when the vehicle is in a parking garage scene in an autonomous parking mode, the vehicle parking system further comprises a crossing unit, wherein the crossing unit comprises a map intersection, a crossing point, a connection list of the intersection and a local map, and a junction list of the intersection and a lane. Preferably, the intersection point is a geometrical coordinate point representation of the junction point of the road. Preferably, the map intersection is scene-level information describing the physical environment and traffic environment of the intersection. For example, the physical environment includes size information of an intersection, whether there is a command booth in the center of the intersection, size information of the command booth, geographical position information of an isolation belt or a green belt in a scene of the intersection, whether there is a landscape building at the intersection, and geographical position information of the landscape building. Preferably, the connection list of the intersection and the local map describes the connection relation between the intersection local map and the road unit local map connected with the intersection local map. Preferably, the intersection and the lane connection list describe a connection relationship list between lanes contained in each road unit connected with the intersection and lanes contained in other road units of the intersection. Preferably, the intersection and lane connection list also includes a connection relationship between the lanes contained in each road unit and the reverse lane of the road unit.
Further, when the vehicle is in a parking garage scene in the autonomous parking mode, the interest points of the planning module further comprise one or more of a geometric coordinate representation of a garage entrance access point, a geometric coordinate representation of a garage exit access point, a geometric coordinate representation of an elevator entrance and a geometric coordinate representation of an elevator entrance in the map.
Further, the feature element set includes a sensing module, a positioning module, and a planning module for the requirements of the geometric attribute, the physical attribute and/or the semantic attribute of the static target element and the position coordinates, specifically, the name semantics of the feature element, the three-dimensional space geometric attribute, the physical and attribute information (color, classification, etc.) of the feature object, and so on. Preferably, the ground object elements are divided into different element layers according to large categories. For example, all traffic signs and road markings including traffic lights, ground-bank posts, walls, tollbooths and gates, bumper strips, obstacles, bank locations and bit lines, no-stop areas, crosswalks, speed-down zones, speed-down, parking, let-down lines, let-down vehicles, etc., road signs, utility poles, road edges, trees, bushes, isolation strips and guardrails, and the like. The sub-list under each category lists the number of individuals in each large category, the number of individuals, the location of the individual corresponding to each number (or the reference coordinates of the individual relative to other specific references), the geometric attribute of the individual corresponding to each number, the physical attribute of the individual corresponding to each number, the color of the individual corresponding to each number, the classification corresponding to each number, and so on.
Preferably, for the ground object element, the spatial information and traffic meaning thereof should be described in detail according to the difference of categories and the difference of represented and described traffic information. For example, a ground object element traffic light should be described in terms of its three-dimensional spatial location. For another example, the space information of ground objects such as parking lot posts, walls, anti-collision bars, ground wire lamp posts, guardrails, guideboards and the like which can assist in positioning the multiple sensors should be described.
Further, the update sources of the ground object element set include, but are not limited to, map-imported data, laser radar scanning, manually-processed imported data, and crowd-sourced vehicle-mounted visual perception devices to perceive new ground object elements at the location.
Further, when the coverage unit obtains the current path plan of the vehicle by the planning module, the path plan is obtained, the management service module invokes the road through which the road unit passes by the path plan, and invokes the feature element elements and the corresponding coordinate positions thereof on the passed road from the feature element set, and the coordinate positions of the feature elements are represented by the relative positions of the feature elements when the vehicle travels to the path position point closest to the feature element so as to represent the position of the feature element on the lane unit and the semantics of the feature element, so that the control decision module of the vehicle makes a corresponding response when approaching the feature element.
Further, the method also comprises a metadata unit, wherein the metadata module comprises the data resolution of each point in the point cloud, the coordinate origin of each point, the horizontal pixel of each point and the vertical pixel of each point.
Further, the planning module is used for outputting the current vehicle planning path to be a global planning path or a local planning path. When the planning module outputs the current vehicle local planning path, the coverage unit screens the coverage of the ground object elements corresponding to the local planning path in the ground object element set; when the planning module outputs the global path planning, the coverage unit covers the coverage of the ground object elements corresponding to the global planning path in the ground object element set.
A database of high-precision maps, comprising:
the road module comprises one or more of a lane unit, a road boundary unit and a road semantic unit;
the planning module is used for outputting a current vehicle planning path;
the system comprises a ground object element set, a positioning module and a planning module, wherein the ground object element set comprises requirements of a sensing module, a positioning module and a planning module on geometric attributes, physical attributes and/or semantic attributes and position coordinates of static target elements;
and the covering unit describes the relative spatial relationship between the ground object elements and the road units through the track coordinates and the planning module plans the path.
Further, the system also comprises a local map unit, wherein the local map module comprises an image data string, a local map list, a map connectivity list and a local map coordinate conversion list.
Further, the road unit is further included, and the road unit describes road information of a road network level and comprises one or more of road level, road type, road speed limit information, road height limit information and road boundary.
Further, the lane unit describes scene-level lane information including one or more of lane-level space, lane topology and physical information, semantic information including road linearity, and traffic information.
Further, the feature element set includes a sensing module, a positioning module, and a planning module for the requirements of the geometric attribute, the physical attribute and/or the semantic attribute of the static target element and the position coordinates, specifically, the name semantics of the feature element, the three-dimensional space geometric attribute, the physical and attribute information (color, classification, etc.) of the feature object, and so on.
A data management method of a high-precision map, applied to the data management system of any one of the above high-precision maps, wherein the method comprises:
the method comprises the steps that a current vehicle planning path is obtained from a planning module, and corresponding ground object elements are obtained according to the vehicle planning path;
the self-covering unit describes the relative spatial relationship between the ground object element through the track coordinates, the planning module plans the path and the road unit, and the management service module transmits the elements describing the ground object element and the relative spatial relationship between the ground object element and the road unit to the vehicle decision control module.
Further, when the decision control module of the vehicle approaches the ground feature element, a corresponding decision\control reaction is made according to the coordinate position of the ground feature element and the semantics of the ground feature element.
A terminal device such as a smart phone that can execute the data management method of the high-precision map described above or a vehicle-mounted terminal control device that can execute the data management method program of the high-precision map described above.
A server comprising a data management method for implementing the above-described high-precision map and/or a data management system of the high-precision map.
A computer storage medium for storing a software program corresponding to the data management method of the high-precision map and/or a data management system of the high-precision map.
As described above, the present invention has the following advantageous effects:
the method comprises the steps of classifying and collecting the ground object elements in a high-precision map into a ground object element set according to the semantics of the ground object elements, recording the positions, geometric attributes, physical attributes and/or semantic attributes of the ground object elements, planning a route by a current path of a vehicle, describing the relative spatial relationship between the ground object elements through track coordinates, planning the path and a road unit by a planning module, and making corresponding decision/control reaction according to the coordinate positions of the ground object elements and the semantic auxiliary decision control module of the ground object elements when the vehicle approaches the ground object elements. In addition, the ground object elements in the high-precision map are classified and collected into a ground object element set according to the semantics thereof, so that the classification updating and management of the high-precision map database are facilitated, namely, the classification of specific semantics can be updated preferentially or iterated at high frequency.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic diagram of a ground object element at a map intersection according to the present invention.
Fig. 2 shows a schematic view of the road element road route and the lane element according to the invention.
Fig. 3 shows a schematic diagram of the high-precision map structure and interactions of the present invention.
Fig. 4 is a schematic diagram of a high-precision map feature element set according to the present invention.
FIG. 5 is a schematic diagram of points of interest and road units, intersection features, display units and metadata units according to the present invention.
Fig. 6 shows a diagram of a grid map of the present invention.
Fig. 7 shows a diagram of a cross-layer parking map in another embodiment of the invention.
Fig. 8 is a schematic diagram showing the application layer extracting the ground object elements required by the road in the ground object element set.
Detailed Description
Other advantages and effects of the present invention will become apparent to those skilled in the art from the following disclosure, which describes the embodiments of the present invention with reference to specific examples. The invention may be practiced or carried out in other embodiments that depart from the specific details, and the details of the present description may be modified or varied from the spirit and scope of the present invention. It should be noted that the following embodiments and features in the embodiments may be combined with each other without conflict.
It should be understood that the structures, proportions, sizes, etc. shown in the drawings are for illustration purposes only and should not be construed as limiting the invention to the extent that it can be practiced, since modifications, changes in the proportions, or otherwise, used in the practice of the invention, are not intended to be critical to the essential characteristics of the invention, but are intended to fall within the spirit and scope of the invention. Also, the terms such as "upper," "lower," "left," "right," "middle," and "a" and the like recited in the present specification are merely for descriptive purposes and are not intended to limit the scope of the invention, but are intended to provide relative positional changes or modifications without materially altering the technical context in which the invention may be practiced.
With reference to figures 1 to 8 of the drawings,
a data management system for a high-precision map, comprising:
the road module comprises one or more of a lane unit, a road boundary unit and a road semantic unit;
the planning module is used for outputting a current vehicle planning path;
the system comprises a ground object element set, a positioning module and a planning module, wherein the ground object element set comprises requirements of a sensing module, a positioning module and a planning module on geometric attributes, physical attributes and/or semantic attributes and position coordinates of static target elements;
the coverage unit describes the relative spatial relationship between the ground object elements and the road units through the track coordinates and the planning module plans the path;
the management service module is used for acquiring the planning module to output a current vehicle planning path, acquiring ground feature elements related in the current vehicle planning path and outputting the ground feature elements and the current vehicle planning path to the planning module.
Further, the system also comprises a local map unit, wherein the local map unit comprises an image data string, a local map list, a map connectivity list and a local map coordinate conversion list.
Further, the local map list data in the local map unit is a catalog of local maps [ localmap ], and this dataset describes some metadata information of each local map; localMapID is the unique ID of the local map in the gallery. The area code and the subarea code are names of map scenes and local maps (local sub-scenes), and are generally identified by english abbreviations. Path is a relative Path of local map data, such as faw/a5.ZLevel is floor information, an integer with sign. IsRamp is a channel attribute and ID, and when IsRamp is-1, the local map is a non-channel, and when it is a positive integer, it is a channel number ID. When the same channel is cut into two partial maps, the ramp numbers represented by IsRamp in the two partial maps should be the same.
Further, the connection relationship list [ mapjunction. Dbf ] between the partial maps describes the connection relationship between two partial maps having the connection relationship. Here, the two partial maps have a connected relation of two by two regardless of the direction in which the partial maps are connected. A unique number is connected to each two partial maps. LocalMap1/2 is the ID of two local maps. TransID is a spatial conversion relation between map links, the spatial conversion relation is that LocalMap1 is converted into LocalMap2, and in calculation, the conversion from LocalMap2 to LocalMap1 is inverse operation of matrix conversion.
Further, the road unit is further included, and the road unit describes road information of a road network level and comprises one or more of road level, road type, road speed limit information, road height limit information and road boundary.
Further, the road unit is further included, and the road unit describes road information of a road network level, including road level, road type, road speed limit information and road height limit information. Preferably, the road unit further comprises semantic information of a road boundary line, a region outside the boundary line of the specific region. For example, a tunnel is outside the boundary line of a certain road, a cliff is outside the boundary line of a certain road, and so on. For example, the road level is a national road of a certain number, a provincial road of a certain number, and a county road of a certain number. For example, the road speed limit information is 120 km/h of the speed limit of the upper sea road section of a certain national road. For example, a county aisle has a height-limiting cue in planning the journey, such as limiting the height of a car passing.
Further, the lane unit describes scene-level lane information including one or more of lane-level space, lane topology and physical information, semantic information including road linearity, and traffic information.
Further, the lane unit describes scene-level lane information, including lane-level space, lane topology and physical information, semantic information including road linearity, and traffic information, wherein the lane-level space includes geometric coordinate line representations of lane center lines of lanes, lane line edge geometric representations, and restrictions on lane height dimensions; the semantic system information and traffic information including the road route property include the driving rule of the lane regulated by the lane at the position close to the intersection and the driving rule of the lane prohibiting lane changing at the specific distance close to the intersection. For example, there is an intersection in front, a road on which a vehicle is traveling has 4 lanes, a white side broken line of each lane becomes a white side solid line at 50 meters from the intersection, the semantics of the lane route property are lane-changing prohibition of the vehicle in the lane, and the semantics of the lane-changing prohibition and the lane-changing prohibition position are recorded in the lane unit. For example, there is an intersection in front, a road on which a vehicle is traveling has 4 lanes, the leftmost lane has straight and left turn marks, the second lane from left to right has straight marks, the third lane from left to right has straight and right turn marks, the fourth lane from left to right has right turn marks, and the semantics and position of the turn marks per lane are recorded in a lane unit. For example, there are 4 lanes on the road, and the lane on the far right is a bus-specific lane, and the semantics and position of the bus-specific lane are recorded in the lane unit.
Further, when the vehicle is in a parking garage scene in an autonomous parking mode, the vehicle parking garage further comprises a parking space unit, wherein the parking space unit comprises one or more of space information of a parking space, background information of the parking space, geometric representation of a parking access point of the parking space and geometric representation of a parking access line of the parking space.
Further, when the vehicle is in a parking garage scene in an autonomous parking mode, one or more of space information of a parking space in the parking space unit, background information of the parking space, geometric representation of a parking access point of the parking space and geometric representation of a parking access line of the parking space are displayed; the space information of the parking space comprises floor information of the garage where the parking space is located, the number of the parking space in the garage, length and width size information of the parking space and depth information in the height direction; the geometric representation of the parking access point comprises a coordinate representation of the parking access point; the parking access line is a geometric representation of a parking rule formed between the parking access point and surrounding road lines and between the parking access point and surrounding driving landmarks.
Further, when the vehicle is in a parking garage scene in an autonomous parking mode, the vehicle parking system further comprises a crossing unit, wherein the crossing unit comprises a map intersection, a crossing point, a connection list of the intersection and a local map, and a junction list of the intersection and a lane. Preferably, the intersection point is a geometrical coordinate point representation of the junction point of the road. Preferably, the map intersection is scene-level information describing the physical environment and traffic environment of the intersection. For example, the physical environment includes size information of an intersection, whether there is a command booth in the center of the intersection, size information of the command booth, geographical position information of an isolation belt or a green belt in a scene of the intersection, whether there is a landscape building at the intersection, and geographical position information of the landscape building. Preferably, the connection list of the intersection and the local map describes the connection relation between the intersection local map and the road unit local map connected with the intersection local map. Preferably, the intersection and the lane connection list describe a connection relationship list between lanes contained in each road unit connected with the intersection and lanes contained in other road units of the intersection. Preferably, the intersection and lane connection list also includes a connection relationship between the lanes contained in each road unit and the reverse lane of the road unit.
Further, when the vehicle is in a parking garage scene in the autonomous parking mode, the interest points of the planning module further comprise one or more of a geometric coordinate representation of a garage entrance access point, a geometric coordinate representation of a garage exit access point, a geometric coordinate representation of an elevator entrance and a geometric coordinate representation of an elevator entrance in the map.
Further, the feature element set includes a sensing module, a positioning module, and a planning module for the requirements of the geometric attribute, the physical attribute and/or the semantic attribute of the static target element and the position coordinates, specifically, the name semantics of the feature element, the three-dimensional space geometric attribute, the physical and attribute information (color, classification, etc.) of the feature object, and so on. Preferably, the ground object elements are divided into different element layers according to large categories. For example, all traffic signs and road markings including traffic lights, ground-bank posts, walls, tollbooths and gates, bumper strips, obstacles, bank locations and bit lines, no-stop areas, crosswalks, speed-down zones, speed-down, parking, let-down lines, let-down vehicles, etc., road signs, utility poles, road edges, trees, bushes, isolation strips and guardrails, and the like. The sub-list under each category lists the number of individuals in each large category, the number of individuals, the location of the individual corresponding to each number (or the reference coordinates of the individual relative to other specific references), the geometric attribute of the individual corresponding to each number, the physical attribute of the individual corresponding to each number, the color of the individual corresponding to each number, the classification corresponding to each number, and so on.
Preferably, for the ground object element, the spatial information and traffic meaning thereof should be described in detail according to the difference of categories and the difference of represented and described traffic information. For example, a ground object element traffic light should be described in terms of its three-dimensional spatial location. For another example, the space information of ground objects such as parking lot posts, walls, anti-collision bars, ground wire lamp posts, guardrails, guideboards and the like which can assist in positioning the multiple sensors should be described.
Further, the update sources of the ground object element set include, but are not limited to, map-imported data, laser radar scanning, manually-processed imported data, and crowd-sourced vehicle-mounted visual perception devices to perceive new ground object elements at the location.
Further, when the coverage unit obtains the current path plan of the vehicle by the planning module, the path plan is obtained, the management service module invokes the road through which the road unit passes by the path plan, and invokes the feature element elements and the corresponding coordinate positions thereof on the passed road from the feature element set, and the coordinate positions of the feature elements are represented by the relative positions of the feature elements when the vehicle travels to the path position point closest to the feature element so as to represent the position of the feature element on the lane unit and the semantics of the feature element, so that the control decision module of the vehicle makes a corresponding response when approaching the feature element.
Further, the method also comprises a metadata unit, wherein the metadata module comprises the data resolution of each point in the point cloud, the coordinate origin of each point, the horizontal pixel of each point and the vertical pixel of each point.
Further, the planning module is used for outputting the current vehicle planning path to be a global planning path or a local planning path. When the planning module outputs the current vehicle local planning path, the coverage unit screens the coverage of the ground object elements corresponding to the local planning path in the ground object element set; when the planning module outputs the global path planning, the coverage unit covers the coverage of the ground object elements corresponding to the global planning path in the ground object element set.
A database of high-precision maps, comprising:
the road module comprises one or more of a lane unit, a road boundary unit and a road semantic unit;
the planning module is used for outputting a current vehicle planning path;
the system comprises a ground object element set, a positioning module and a planning module, wherein the ground object element set comprises requirements of a sensing module, a positioning module and a planning module on geometric attributes, physical attributes and/or semantic attributes and position coordinates of static target elements;
and the covering unit describes the relative spatial relationship between the ground object elements and the road units through the track coordinates and the planning module plans the path.
Further, the system also comprises a local map unit, wherein the local map module comprises an image data string, a local map list, a map connectivity list and a local map coordinate conversion list.
Further, the road unit is further included, and the road unit describes road information of a road network level and comprises one or more of road level, road type, road speed limit information, road height limit information and road boundary.
Further, the lane unit describes scene-level lane information including one or more of lane-level space, lane topology and physical information, semantic information including road linearity, and traffic information.
Further, the feature element set includes a sensing module, a positioning module, and a planning module for the requirements of the geometric attribute, the physical attribute and/or the semantic attribute of the static target element and the position coordinates, specifically, the name semantics of the feature element, the three-dimensional space geometric attribute, the physical and attribute information (color, classification, etc.) of the feature object, and so on.
A data management method of a high-precision map, applied to the data management system of any one of the above high-precision maps, wherein the method comprises:
the method comprises the steps that a current vehicle planning path is obtained from a planning module, and corresponding ground object elements are obtained according to the vehicle planning path;
the self-covering unit describes the relative spatial relationship between the ground object element through the track coordinates, the planning module plans the path and the road unit, and the management service module transmits the elements describing the ground object element and the relative spatial relationship between the ground object element and the road unit to the vehicle decision control module.
Further, when the decision control module of the vehicle approaches the ground feature element, a corresponding decision\control reaction is made according to the coordinate position of the ground feature element and the semantics of the ground feature element.
A terminal device such as a smart phone that can execute the data management method of the high-precision map described above or a vehicle-mounted terminal control device that can execute the data management method program of the high-precision map described above.
As a preferred embodiment, the present embodiment further provides a terminal device, such as a smart phone, a tablet computer, a notebook computer, a desktop computer, a rack-mounted server, a blade server, a tower server, or a rack-mounted server (including an independent server, or a server cluster formed by a plurality of servers) that can execute a program, or the like. The terminal device of this embodiment at least includes: a memory, a processor, and the like, which may be communicatively coupled to each other via a system bus. It should be noted that a terminal device having a component memory, a processor, but it should be understood that not all of the illustrated components are required to be implemented, and that alternative methods of data management of high-precision maps may implement more or fewer components.
A server comprising a data management method for implementing the above-described high-precision map and/or a data management system of the high-precision map.
As a preferred embodiment, the memory (i.e., readable storage medium) includes flash memory, hard disk, multimedia card, card memory (e.g., SD or DX memory, etc.), random Access Memory (RAM), static Random Access Memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory may be an internal storage unit of a computer device, such as a hard disk or memory of the computer device. In other embodiments, the memory may also be an external storage device of a computer device, such as a plug-in hard disk, smart Media Card (SMC), secure Digital (SD) Card, flash Card (Flash Card) or the like, which are provided on the computer device. Of course, the memory may also include both internal storage units of the computer device and external storage devices. In this embodiment, the memory is typically used to store an operating system installed on the computer device and various types of application software, such as data management method program codes of the high-precision map in the embodiment, and the like. In addition, the memory can be used to temporarily store various types of data that have been output or are to be output.
A computer-readable storage medium having stored thereon a computer program, characterized by: the program, when executed by the processor, implements the steps in the data management method for a high-precision map described above.
The present embodiment also provides a computer-readable storage medium such as a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, a server, an App application store, etc., on which a computer program is stored, which when executed by a processor, performs the corresponding functions. The computer-readable storage medium of the present embodiment is for storing a high-precision map-based data management method program, which when executed by a processor, implements the high-precision map data management method in the high-precision map data management method embodiment.
The above embodiments are merely illustrative of the principles of the present invention and its effectiveness, and are not intended to limit the invention. Modifications and variations may be made to the above-described embodiments by those skilled in the art without departing from the spirit and scope of the invention. Accordingly, it is intended that all equivalent modifications and variations of the invention be covered by the claims of this invention, which are within the skill of those skilled in the art, be included within the spirit and scope of this invention.
Claims (13)
1. A data management system for a high-precision map, comprising:
the road module comprises one or more of a lane unit, a road boundary unit and a road semantic unit;
the planning module is used for outputting a current vehicle planning path;
the system comprises a ground object element set, a positioning module and a planning module, wherein the ground object element set comprises requirements of a sensing module, a positioning module and a planning module on geometric attributes, physical attributes and/or semantic attributes and position coordinates of static target elements;
the coverage unit describes the relative spatial relationship between the ground object elements and the road units through the track coordinates and the planning module plans the path;
the management service module is used for acquiring the planning module to output a current vehicle planning path, acquiring ground feature elements related in the current vehicle planning path and outputting the ground feature elements and the current vehicle planning path to the planning module.
2. The high-precision map data management system of claim 1, further comprising a local map unit comprising an image data string, a local map list, a map connectivity list, a local map coordinate conversion list.
3. The data management system of the high-precision map according to claim 1, further comprising a road unit describing road information of a road network level including one or more of a road level, a road type, road speed limit information, road height limit information, and a road boundary.
4. The data management system of the high-precision map according to claim 1, wherein the lane unit describes lane information of scene level including one or more of lane-level space, lane topology and physical information, semantic information including road linearity, and traffic information.
5. The data management system of the high-precision map according to claim 1, further comprising a parking space unit when the vehicle is in a parking garage scene in an autonomous parking mode, the parking space unit comprising one or more of space information of a parking space, background information of the parking space, geometric representation of a parking access point, and geometric representation of a parking access line.
6. The data management system of a high-precision map according to claim 1, wherein the feature element set extracts traffic information according to element semantics and classifies the traffic information individually.
7. A database of high-precision maps, comprising:
the road module comprises one or more of a lane unit, a road boundary unit and a road semantic unit;
the planning module is used for outputting a current vehicle planning path;
the system comprises a ground object element set, a positioning module and a planning module, wherein the ground object element set comprises requirements of a sensing module, a positioning module and a planning module on geometric attributes, physical attributes and/or semantic attributes and position coordinates of static target elements;
and the covering unit describes the relative spatial relationship between the ground object elements and the road units through the track coordinates and the planning module plans the path.
8. The database of high-precision maps of claim 7, further comprising a local map unit, the local map module comprising an image data string, a local map list, a map connectivity list, a local map coordinate conversion list; the road system further comprises a road unit, wherein the road unit describes road information of a road network level and comprises one or more of road level, road type, road speed limit information, road height limit information and road boundaries; the lane unit describes scene-level lane information, including one or more of lane-level space, lane topology and physical information, semantic information including road linearity, and traffic information.
9. A data management method of a high-precision map, applied to a data management system of a high-precision map as claimed in any one of claims 1 to 6, wherein the method comprises:
the method comprises the steps that a current vehicle planning path is obtained from a planning module, and corresponding ground object elements are obtained according to the vehicle planning path;
the self-covering unit describes the relative spatial relationship between the ground object element through the track coordinates, the planning module plans the path and the road unit, and the management service module transmits the elements describing the ground object element and the relative spatial relationship between the ground object element and the road unit to the vehicle decision control module.
10. The method for data management of a high-precision map according to claim 9, wherein the decision control module of the vehicle makes a corresponding decision/control reaction according to the coordinate position of the ground feature element and the semantics of the ground feature element when approaching the ground feature element.
11. A server comprising a data management system for implementing a data management method of a high precision map and/or a high precision map according to any of the preceding claims 9-10 or a server carrying a database according to claim 7.
12. A terminal device, characterized by: the terminal device is a vehicle-mounted terminal control device for scheduling a data management system of a high-precision map according to any one of claims 1 to 6.
13. A computer-readable storage medium having stored thereon a computer program, characterized by: the program, when executed by a processor, implements the steps of the method of any of claims 9 to 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910220177.5A CN110118564B (en) | 2019-03-22 | 2019-03-22 | Data management system, management method, terminal and storage medium for high-precision map |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910220177.5A CN110118564B (en) | 2019-03-22 | 2019-03-22 | Data management system, management method, terminal and storage medium for high-precision map |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110118564A CN110118564A (en) | 2019-08-13 |
| CN110118564B true CN110118564B (en) | 2024-02-23 |
Family
ID=67520516
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910220177.5A Active CN110118564B (en) | 2019-03-22 | 2019-03-22 | Data management system, management method, terminal and storage medium for high-precision map |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110118564B (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110688693B (en) * | 2019-09-05 | 2023-02-21 | 临沂大学 | Indoor thin-wall three-dimensional model reconstruction method considering topology and part of building component semantics |
| 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 |
| CN110793532A (en) * | 2019-11-06 | 2020-02-14 | 深圳创维数字技术有限公司 | Path navigation method, device and computer readable storage medium |
| CN110956838A (en) * | 2019-12-16 | 2020-04-03 | 驭势科技（北京）有限公司 | Intelligent driving method, vector map generation method, vehicle-mounted device and storage medium |
| CN111060117B (en) * | 2019-12-17 | 2022-02-08 | 苏州智加科技有限公司 | Local map construction method and device, computer equipment and storage medium |
| CN111221821B (en) * | 2019-12-31 | 2022-07-01 | 武汉中海庭数据技术有限公司 | AI model iterative updating method, electronic equipment and storage medium |
| CN111708857B (en) * | 2020-06-10 | 2023-10-03 | 北京百度网讯科技有限公司 | Processing method, device, equipment and storage medium for high-precision map data |
| CN114079884A (en) * | 2020-08-14 | 2022-02-22 | 大唐高鸿智联科技(重庆)有限公司 | Transmission control method, device, equipment and terminal for map data |
| CN112284402B (en) * | 2020-10-15 | 2021-12-07 | 广州小鹏自动驾驶科技有限公司 | Vehicle positioning method and device |
| CN113656525B (en) * | 2021-08-19 | 2024-04-16 | 广州小鹏自动驾驶科技有限公司 | Map processing method and device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106802954A (en) * | 2017-01-18 | 2017-06-06 | 中国科学院合肥物质科学研究院 | Unmanned vehicle semanteme cartographic model construction method and its application process on unmanned vehicle |
| 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 |
| CN109387208A (en) * | 2018-11-13 | 2019-02-26 | 百度在线网络技术（北京）有限公司 | A kind of processing method of map datum, device, equipment and medium |
| CN109410301A (en) * | 2018-10-16 | 2019-03-01 | 张亮 | High-precision semanteme map production method towards pilotless automobile |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7375728B2 (en) * | 2001-10-01 | 2008-05-20 | University Of Minnesota | Virtual mirror |
-
2019
- 2019-03-22 CN CN201910220177.5A patent/CN110118564B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106802954A (en) * | 2017-01-18 | 2017-06-06 | 中国科学院合肥物质科学研究院 | Unmanned vehicle semanteme cartographic model construction method and its application process on unmanned vehicle |
| 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 |
| CN109410301A (en) * | 2018-10-16 | 2019-03-01 | 张亮 | High-precision semanteme map production method towards pilotless automobile |
| CN109387208A (en) * | 2018-11-13 | 2019-02-26 | 百度在线网络技术（北京）有限公司 | A kind of processing method of map datum, device, equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110118564A (en) | 2019-08-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110118564B (en) | Data management system, management method, terminal and storage medium for high-precision map | |
| US11738770B2 (en) | Determination of lane connectivity at traffic intersections for high definition maps | |
| JP7176811B2 (en) | Sparse Maps for Autonomous Vehicle Navigation | |
| CN110832348B (en) | Point cloud data enrichment for high definition maps of autonomous vehicles | |
| US11874119B2 (en) | Traffic boundary mapping | |
| JP2022535351A (en) | System and method for vehicle navigation | |
| JP6785939B2 (en) | Systems and methods for generating surface map information in an emergency | |
| US11151394B2 (en) | Identifying dynamic objects in a point cloud | |
| DE112020006426T5 (en) | SYSTEMS AND METHODS FOR VEHICLE NAVIGATION | |
| US11590989B2 (en) | Training data generation for dynamic objects using high definition map data | |
| DE112018002143T5 (en) | SYSTEMS AND METHODS FOR COMPRESSING TRAFFIC DATA | |
| CN111542860A (en) | Sign and lane creation for high definition maps for autonomous vehicles | |
| WO2018113451A1 (en) | Map data system, method for generating and using same, and application thereof | |
| CN110715671B (en) | Three-dimensional map generation method and device, vehicle navigation equipment and unmanned vehicle | |
| CN109387208B (en) | Map data processing method, device, equipment and medium | |
| CN112325896B (en) | Navigation method, navigation device, intelligent driving equipment and storage medium | |
| CN113034566B (en) | High-precision map construction method and device, electronic equipment and storage medium | |
| JP2023106536A (en) | System for vehicle navigation based on image analysis | |
| DE112020002869T5 (en) | NAVIGATION SYSTEMS AND METHODS OF DETERMINING OBJECT DIMENSIONS | |
| DE102022100213A1 (en) | Machine learning based framework for annotation of driveable surfaces | |
| US20230121226A1 (en) | Determining weights of points of a point cloud based on geometric features | |
| CN116802461A (en) | System and method for map-based real world modeling | |
| Kang et al. | Hidam: A unified data model for high-definition (hd) map data | |
| Farrell et al. | Best practices for surveying and mapping roadways and intersections for connected vehicle applications | |
| CN116048067A (en) | Parking path planning method, device, vehicle and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |