CN114111758A - Map data processing method and device - Google Patents

Map data processing method and device Download PDF

Info

Publication number
CN114111758A
CN114111758A CN202111291451.1A CN202111291451A CN114111758A CN 114111758 A CN114111758 A CN 114111758A CN 202111291451 A CN202111291451 A CN 202111291451A CN 114111758 A CN114111758 A CN 114111758A
Authority
CN
China
Prior art keywords
semantic element
semantic
target
determining
path object
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
Application number
CN202111291451.1A
Other languages
Chinese (zh)
Other versions
CN114111758B (en
Inventor
范云凤
刘中元
黄亚
李红军
周建
柴文楠
蒋少峰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangzhou Xiaopeng Autopilot Technology Co Ltd
Original Assignee
Guangzhou Xiaopeng Autopilot Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guangzhou Xiaopeng Autopilot Technology Co Ltd filed Critical Guangzhou Xiaopeng Autopilot Technology Co Ltd
Priority to CN202111291451.1A priority Critical patent/CN114111758B/en
Publication of CN114111758A publication Critical patent/CN114111758A/en
Priority to PCT/CN2022/081454 priority patent/WO2023071029A1/en
Application granted granted Critical
Publication of CN114111758B publication Critical patent/CN114111758B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

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
    • G01C21/38—Electronic maps specially adapted for navigation; Updating thereof
    • G01C21/3863—Structures 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)
  • Image Analysis (AREA)
  • Navigation (AREA)

Abstract

The embodiment of the invention provides a method and a device for processing map data, wherein the method comprises the following steps: acquiring map data, and determining a matched path object set from the map data; aiming at a target path object in a path object set, determining a coordinate parameter and a target description parameter of a first semantic element contained in the target path object, wherein the target description parameter is associated with a relative position relationship between the first semantic element and a semantic element adjacent to the first semantic element; according to the coordinate parameters and the target description parameters, determining a second semantic element matched with the first semantic element from semantic elements contained in other path objects of the path object set; and fusing the first semantic element and the second semantic element to obtain fused map data. By the embodiment of the invention, map fusion is optimized by combining relative positions, the fusion of the path objects with longer path length can be adapted, the map fusion effect is improved, and the automatic driving capability is further improved.

Description

Map data processing method and device
Technical Field
The present invention relates to the field of map technologies, and in particular, to a method and an apparatus for processing map data.
Background
In an automatic driving technology, such as an Automatic Parking System (APS), a semantic map is an important component, and plays an important role in positioning, reference line generation, path planning, and the like, and for the semantic map, map fusion is usually involved.
For example, when there are a plurality of map data for the same parking lot, or there are a plurality of acquisition results for the same area in a single map data for the same parking lot, the map data needs to be fused.
However, in the conventional map fusion technology, when semantic elements on a path object (Link) in map data are fused, particularly for a path object with a long path length (i.e., "long Link"), due to the problem of "scale drift", a situation of "looking at the head without looking at the tail" may occur during fusion, that is, a front part of the path is fused but a rear part of the path cannot be fused, so that the map fusion effect is affected.
Disclosure of Invention
In view of the above problems, it is proposed to provide a method and apparatus for processing map data that overcomes or at least partially solves the above problems, comprising:
a method of processing map data, the method comprising:
acquiring map data, and determining a matched path object set from the map data;
aiming at a target path object in the path object set, determining a coordinate parameter and a target description parameter of a first semantic element contained in the target path object, wherein the target description parameter is associated with a relative position relationship between the first semantic element and a semantic element adjacent to the first semantic element;
according to the coordinate parameters and the target description parameters, determining a second semantic element matched with the first semantic element from semantic elements contained in other path objects of the path object set;
and fusing the first semantic element and the second semantic element to obtain fused map data.
Optionally, determining, from semantic elements included in other path objects of the path object set according to the coordinate parameter and the target description parameter, a second semantic element matching the first semantic element, including:
determining candidate semantic elements from semantic elements contained in other path objects of the path object set according to the coordinate parameters and the target description parameters;
determining rotation information and translation information of the candidate semantic element relative to the first semantic element;
and when the rotation information and the translation information meet the preset conditions, determining the candidate semantic element as a second semantic element matched with the first semantic element.
Optionally, the method further comprises:
and adding semantic elements which cannot be matched with the semantic elements in the target path object in other path objects into the fused map data.
Optionally, the determining, by the target path object in the path object set, the target description parameter of the first semantic element included in the target path object includes:
aiming at a target path object in the path object set, determining the relative position relation between a first semantic element contained in the target path object and the semantic elements adjacent to the first semantic element;
and determining a relative position description parameter of the first semantic element according to the relative position relation.
Optionally, the determining the relative position description parameter of the first semantic element according to the relative position relationship includes:
determining an average relative distance between adjacent semantic elements aiming at the target path object, and determining a target relative distance according to the average relative distance;
and determining a relative position description parameter of the first semantic element according to the first relative distance, the second relative distance and the target relative distance.
Optionally, the determining, by the target path object in the path object set, the target description parameters of the first semantic element included in the target path object includes:
determining a semantic element type of a first semantic element;
and determining a type description parameter of the first semantic element according to the semantic element type.
Optionally, the first semantic element and the second semantic element are parking space elements.
An apparatus for processing map data, the apparatus comprising:
the path object set determining module is used for acquiring map data and determining a matched path object set from the map data;
the parameter determination module is used for determining a coordinate parameter and a target description parameter of a first semantic element contained in a target path object aiming at the target path object in the path object set, wherein the target description parameter is associated with a relative position relationship between the first semantic element and an adjacent semantic element;
the second semantic element determining module is used for determining a second semantic element matched with the first semantic element from semantic elements contained in other path objects of the path object set according to the coordinate parameters and the target description parameters;
and the semantic element fusion module is used for fusing the first semantic element and the second semantic element to obtain fused map data.
An electronic device comprising a processor, a memory and a computer program stored on the memory and capable of running on the processor, the computer program, when executed by the processor, implementing a method of processing map data as described above.
A computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, implements a method of processing map data as described above.
The embodiment of the invention has the following advantages:
in the embodiment of the invention, by acquiring map data, determining a matched path object set from the map data, and determining a coordinate parameter and a target description parameter of a first semantic element contained in a target path object aiming at the target path object in the path object set, wherein the target description parameter is associated with the relative position relationship between the first semantic element and the semantic elements adjacent to the first semantic element, then according to the coordinate parameter and the target description parameter, determining a second semantic element matched with the first semantic element from the semantic elements contained in other path objects of the path object set, the first semantic element and the second semantic element are fused to obtain fused map data, the map fusion is optimized by combining relative positions, the fusion of the path objects with long path lengths can be adapted, the map fusion effect is improved, and the automatic driving capability is further improved.
Drawings
In order to more clearly illustrate the technical solution of the present invention, the drawings needed to be used in the description of the present invention will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
FIG. 1 is a flowchart illustrating steps of a method for processing map data according to an embodiment of the present invention;
FIG. 2 is a diagram of a semantic map provided by an embodiment of the present invention;
FIG. 3a is a schematic diagram of a relative position provided by an embodiment of the present invention;
FIG. 3b is a schematic illustration of another relative position provided by an embodiment of the present invention;
FIG. 3c is a schematic illustration of another relative position provided by an embodiment of the present invention;
FIG. 3d is a schematic illustration of another relative position provided by an embodiment of the present invention;
FIG. 4 is a flowchart illustrating steps of another method for processing map data according to an embodiment of the present invention;
fig. 5 is a block diagram of a processing apparatus for processing map data according to an embodiment of the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below. It is to be understood that the embodiments described are only a few embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, a flowchart illustrating steps of a method for processing map data according to an embodiment of the present invention is shown, which may specifically include the following steps:
step 101, obtaining map data, and determining a matched path object set from the map data.
The map data may be a semantic map, for example, the map data may be a semantic map for a parking lot, the map data may include a plurality of semantic elements, for example, as shown in fig. 2, the semantic map of the indoor parking lot scene includes semantic landmark information associated with road waypoints, such as semantic elements of a parking lot entrance, a deceleration strip, an entrance/exit bend/slope point, a road node, and a parking space.
In the automatic driving technology, in order to improve the automatic driving capability, map data may be acquired for map fusion, where the map data may be a semantic map and have a repeated portion to be fused, for example, the map data may include a plurality of map data to be fused with each other between maps, where the plurality of map data are map data for the same area, or may be a single map data to be self-fused within a map, and the single map data has multiple acquisition results for the same area.
For example, in an automatic parking system, in order to improve a parking success rate of the automatic parking system, map data may be acquired for map fusion, where the map data may be multiple map data for a same parking lot, or may be a single map data for the same parking lot, and the single map data has multiple acquisition results for the same location.
After obtaining the map data, the path objects in the map data may be preliminarily matched to obtain a matched set of path objects, i.e., repeated path objects in the map data.
Step 102, aiming at the target path object in the path object set, determining a coordinate parameter and a target description parameter of a first semantic element contained in the target path object, wherein the target description parameter is associated with a relative position relationship between the first semantic element and an adjacent semantic element.
In the map data, a plurality of path objects may be included, and a path object may correspond to a path from one location to another location in the map data, which may contain a plurality of semantic elements.
For a target path object in the map data, the target path object may be a path object whose path length is greater than a preset path length, that is, "long Link," and the path object set path object may be a linear path object or a curvilinear path object, and a first semantic element included in the target path object may be determined, where the first semantic element may be a parking space element, and the precision of subsequent fusion of the parking space elements may be improved by further refining the description of the parking space element.
After the first semantic element is determined, the coordinate parameter of the first semantic element can be obtained, the coordinate parameter can be the coordinate value of the first semantic element, the target description parameter of the first semantic element can be determined according to the relative position relation between the first semantic element and the adjacent semantic elements, the relative distance is added into the description of the semantic elements, on one hand, the problem of 'scale drift' during fusion can be effectively avoided, even if the 'end-of-sight' condition occurs due to the scale problem when the absolute position is used, on the other hand, the independence of data can be enhanced, and therefore the quality of matching and fusion is improved.
In an embodiment of the present invention, the target description parameter may include a relative position description parameter of the first semantic element, and step 102 may include:
and a substep 11, aiming at the target path object in the path object set, determining the relative position relationship between the first semantic element contained in the target path object and the adjacent semantic elements.
For each first semantic element, a semantic element adjacent to the first semantic element may be further determined, the semantic element adjacent to the first semantic element may include semantic elements adjacent to the left and right sides of the first semantic element, and the adjacent semantic elements may be semantic elements of the same type as the first semantic element.
After determining the semantic elements adjacent to the first semantic element, a relative positional relationship between the first semantic element and the semantic elements adjacent to the first semantic element may be determined, and the relative positional relationship may include a first relative distance and a second relative distance between the first semantic element and the semantic elements adjacent to both sides of the first semantic element.
For example, the first semantic element is a parking space element B, the semantic elements adjacent to the first semantic element may be a parking space element a on the left side of the parking space element B and a parking space element C on the right side of the parking space element B, and the relative position relationship may be a relative distance between the parking space element a and the parking space element B and a relative distance between the parking space element B and the parking space element C.
In an embodiment of the present invention, the substep 11 may comprise:
the substep 111, for the target path object in the map data, determines a first relative distance between the first semantic element and the adjacent semantic element in case that only one side of the first semantic element included in the target path object has the adjacent semantic element.
In some cases, there is a first semantic element having adjacent semantic elements on only one side and no adjacent semantic elements on the other side, and if the first semantic element is the first semantic element or the last semantic element, that is, the semantic elements located at the head and the tail, a first relative distance between the first semantic element and the adjacent semantic element on one side may be determined first.
And a substep 112, establishing a virtual semantic element adjacent to the first semantic element on the side of the first semantic element without the adjacent semantic element, and determining a second relative distance between the first semantic element and the virtual semantic element according to the first relative distance.
Because only one side has an adjacent semantic element, a virtual semantic element adjacent to the first semantic element may be established on the side where the first semantic element does not have the adjacent semantic element, as shown in fig. 3a, where the first semantic element is a parking space element a1, which is a first parking space element, a virtual parking space element is established on the left side of the parking space element a1, and then a second relative distance between the first semantic element and the virtual semantic element may be determined according to the first relative distance, where the second relative distance may be equal to the first relative distance, for example.
And a substep 12 of determining a relative position description parameter of the first semantic element based on the relative position relationship.
After the relative position relationship is determined, the relative position description parameters of the first semantic element can be determined in different modes according to different relative position relationships, and further the description of the semantic elements is refined.
In an embodiment of the present invention, substep 12 may comprise:
the substep 121, for the target path object, determines an average relative distance between adjacent semantic elements and determines a target relative distance based on the average relative distance.
Specifically, the sum of the relative distances between all adjacent semantic elements in the target path object may be determined, where all adjacent semantic elements may be semantic elements of the same type as the first semantic element, such as all adjacent parking space elements, and the average of the sum of the relative distances is obtained to obtain an average relative distance.
After the average relative distance is obtained, the target relative distance may be determined according to the average relative distance, and the target relative distance may be equal to the average relative distance or may be increased or decreased based on the average relative distance.
A substep 122 of determining a relative position describing parameter of the first semantic element based on the first relative distance, the second relative distance, and the target relative distance.
Since the relative position relationship may include a first relative distance and a second relative distance between the first semantic element and the semantic elements adjacent to both sides of the first semantic element, the relative position description parameter of the first semantic element may be determined according to the first relative distance, the second relative distance, and the relationship between the target relative distances.
The relative position describing parameter can be determined as follows:
Figure BDA0003332073760000071
wherein, betakA relative position describing parameter representing the kth semantic element,
Figure BDA0003332073760000072
in the form of an average relative distance,
Figure BDA0003332073760000073
beta is a preset distance, delta is a weight coefficient (which can be preset by a user), and beta is a target relative distancek(left) is the relative distance between the kth semantic element and its left-side neighboring semantic element, βk(right) is the relative distance between the kth semantic element and its right-side neighbor, skip indicating not to participate in the operation.
In an embodiment of the present invention, the substep 122 may comprise:
and under the condition that the average value of the first relative distance and the second relative distance is smaller than or equal to the target relative distance, determining the relative position description parameter of the first semantic element according to the average value of the first relative distance and the second relative distance.
In some cases, the average value of the relative distances between the first semantic element and the semantic elements adjacent to both sides of the first semantic element is smaller than or equal to the target relative distance, as shown in fig. 3b, the first semantic element may be a space element a2, and the average value of the relative distances between the space element a2 and the space elements on both left and right sides of the space element is smaller than the target relative distance, and then the relative position description parameter of the first semantic element may be determined according to the average value of the first relative distance and the second relative distance, for example, the average value of the first relative distance and the second relative distance is used as the relative position description parameter of the first semantic element.
In an embodiment of the present invention, the substep 122 may comprise:
and under the condition that the average value of the first relative distance and the second relative distance is greater than the target relative distance and the first relative distance is smaller than the target relative distance, determining the relative position description parameter of the first semantic element according to the first relative distance.
In some cases, the average value of the relative distances between the first semantic element and the semantic elements adjacent to both sides of the first semantic element is greater than the target relative distance, and the first relative distance is smaller than the target relative distance, then the second relative distance is inevitably greater than the target relative distance, as shown in fig. 3c, the first semantic element may be a parking space element A3, the relative distance between the parking space element A3 and the left parking space element thereof is smaller than the target relative distance, and the relative distance between the parking space element A3 and the right parking space element thereof is greater than the target relative distance, then the relative position description parameter of the first semantic element may be determined according to the first relative distance, and if the first relative distance is used as the relative position description parameter of the first semantic element.
In an example, in some cases, an average value of relative distances between a first semantic element and semantic elements adjacent to both sides of the first semantic element is greater than a target relative distance, and both the first relative distance and the second relative distance are greater than the target relative distance, as shown in fig. 3d, the first semantic element may be a space element a4, and the relative distances between a space element a4 and space elements on both left and right sides of the first semantic element are greater than the target relative distance, so that the first semantic element may be skipped without calculating a relative position description parameter of the first semantic element.
In an embodiment of the present invention, the target description parameter may further include a type description parameter of the first semantic element, and step 102 may include:
sub-step 21, determining the semantic element type of the first semantic element.
A substep 22 of determining a type description parameter of the first semantic element based on the semantic element type.
In order to take into account the type of the semantic element, the semantic element type of the first semantic element may be determined, and then the type description parameter of the first semantic element may be determined according to the semantic element type.
After the relative position description parameter and the type description parameter are determined, a target description parameter of the first semantic element can be obtained according to the relative position description parameter and the type description parameter, and both the relative position description parameter and the type description parameter can be used as a weight of the target description parameter, as shown in the following formula:
gammak＝ωi+βk
wherein gamma can be an object description parameter, omegaiA parameter, β, may be described for the type of the ith element typekParameters may be described for the relative position of the kth semantic element.
And 103, determining a second semantic element matched with the first semantic element from the semantic elements contained in other path objects of the path object set according to the coordinate parameters and the target description parameters.
The second semantic element may be a semantic element of the same type as the first semantic element, and for example, the second semantic element is a parking space element.
After the coordinate parameter and the target description parameter are obtained, a second semantic element, namely a repeated semantic element, matched with the first semantic element can be screened out from semantic elements contained in other path objects of the path object set according to the coordinate parameter and the target description parameter.
In an embodiment of the present invention, step 103 may include:
substep 31, determining candidate semantic elements from semantic elements contained in other path objects of the path object set according to the coordinate parameters and the target description parameters.
Specifically, according to the coordinate parameter and the target description parameter, the semantic element may be constructed as a 3D point (x, y, gamma), where x and y are the coordinate parameter and gamma is the target description parameter.
It should be noted that, for the semantic elements included in the other path objects, the process of determining the coordinate parameter and the target description parameter may refer to the process of determining the coordinate parameter and the target description information of the first semantic element, and will not be repeated here.
Further, candidate semantic elements may be determined from semantic elements contained in other path objects of the set of path objects, forming "3D point pairs" with the first semantic element.
Sub-step 32, determining rotation information and translation information of the candidate semantic element with respect to the first semantic element.
After determining the candidate semantic element, an analytical algorithm may be employed to calculate rotation information and translation information of the candidate semantic element with respect to the first semantic element.
In one example, the obtained rotation information and translation information are used as initial values, and are optimized by an optimization algorithm to remove errors caused by measurement.
And a substep 33 of determining the candidate semantic element as a second semantic element matched with the first semantic element when the rotation information and the translation information satisfy a preset condition.
After the rotation information and the translation information are obtained, it may be determined whether the rotation information and the translation information satisfy a preset condition, for example, whether a rotation angle in the rotation information is smaller than a preset rotation angle and a translation distance in the translation information is smaller than a preset translation distance, and when both are satisfied, it is determined that the preset condition is satisfied, and when either is not satisfied, it is determined that the preset condition is not satisfied.
When the preset condition is met, the candidate semantic element can be judged to be a second semantic element matched with the first semantic element, the candidate semantic element and the first semantic element are marked as a matching pair, and when the preset condition is not met, the representation matching is unsuccessful, and the candidate semantic element and the first semantic element are marked as unsuccessful matching.
In an example, as described above, for a part of the first semantic elements, the first semantic element may be skipped, and the relative position description parameter of the first semantic element is not calculated, so that after completing the matching of other first semantic elements, the processing of the first semantic element which is skipped previously as described above may be returned to be continued to find the matching second semantic element.
And 104, fusing the first semantic element and the second semantic element to obtain fused map data.
After the matched semantic elements are determined, the matched semantic elements can be fused, so that a new path object is obtained and written into the map data, and the fused map data is obtained.
In an embodiment of the present invention, the method may further include:
and adding semantic elements which cannot be matched with the semantic elements in the target path object in other path objects into the fused map data.
Because the matching is not successful, the semantic elements which cannot be matched with the semantic elements in the target path object in other path objects can be determined, and then the semantic elements are added into the fused map data, the information which is not observed by the current map is expanded, and the map content is enriched.
In the embodiment of the invention, by acquiring map data, determining a matched path object set from the map data, and determining a coordinate parameter and a target description parameter of a first semantic element contained in a target path object aiming at the target path object in the path object set, wherein the target description parameter is associated with the relative position relationship between the first semantic element and the semantic elements adjacent to the first semantic element, then according to the coordinate parameter and the target description parameter, determining a second semantic element matched with the first semantic element from the semantic elements contained in other path objects of the path object set, the first semantic element and the second semantic element are fused to obtain fused map data, the map fusion is optimized by combining relative positions, the fusion of the path objects with long path lengths can be adapted, the map fusion effect is improved, and the automatic driving capability is further improved.
Referring to fig. 4, a flowchart illustrating steps of another map data processing method according to an embodiment of the present invention is shown, which may specifically include the following steps:
step 401, obtaining map data, and determining a matched path object set from the map data.
Step 402, aiming at the target path object in the path object set, determining a coordinate parameter and a target description parameter of a first semantic element contained in the target path object, wherein the target description parameter is associated with a relative position relationship between the first semantic element and a semantic element adjacent to the first semantic element.
Step 403, according to the coordinate parameter and the target description parameter, determining candidate semantic elements from semantic elements contained in other path objects in the path object set.
At step 404, rotation information and translation information of the candidate semantic element relative to the first semantic element are determined.
And 405, when the rotation information and the translation information meet the preset conditions, determining the candidate semantic element as a second semantic element matched with the first semantic element.
And 406, fusing the first semantic element and the second semantic element to obtain fused map data.
Step 407, add the semantic elements which cannot be matched with the semantic elements in the target path object in other path objects into the fused map data.
It should be noted that, for simplicity of description, the method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present invention is not limited by the illustrated order of acts, as some steps may occur in other orders or concurrently in accordance with the embodiments of the present invention. Further, those skilled in the art will appreciate that the embodiments described in the specification are presently preferred and that no particular act is required to implement the invention.
Referring to fig. 5, a schematic structural diagram of a processing apparatus for map data according to an embodiment of the present invention is shown, which may specifically include the following modules:
a path object set determining module 501, configured to obtain map data, and determine a matching path object set from the map data.
A parameter determining module 502, configured to determine, for a target path object in the path object set, a coordinate parameter and a target description parameter of a first semantic element included in the target path object, where the target description parameter is associated with a relative position relationship between the first semantic element and a semantic element adjacent to the first semantic element.
The second semantic element determining module 503 is configured to determine, according to the coordinate parameter and the target description parameter, a second semantic element that matches the first semantic element from semantic elements included in other path objects of the path object set.
And the semantic element fusion module 504 is configured to fuse the first semantic element and the second semantic element to obtain fused map data.
In an embodiment of the present invention, the second semantic element determining module 503 may include:
and the candidate semantic element determining submodule is used for determining candidate semantic elements from semantic elements contained in other path objects of the path object set according to the coordinate parameters and the target description parameters.
And the rotation and translation information determining submodule is used for determining the rotation information and the translation information of the candidate semantic element relative to the first semantic element.
And the rotation and translation information determining matching element submodule is used for determining the candidate semantic element as a second semantic element matched with the first semantic element when the rotation information and the translation information meet the preset conditions.
In an embodiment of the present invention, the method may further include:
and the unmatched fusion module is used for adding the semantic elements which cannot be matched with the semantic elements in the target path object in other path objects into the fused map data.
In an embodiment of the present invention, the target description parameter may include a relative position description parameter of the first semantic element, and the parameter determining module 502 may include:
and the relative position relation determining submodule is used for determining the relative position relation between the first semantic element contained in the target path object and the semantic elements adjacent to the first semantic element aiming at the target path object in the path object set.
And the relative position description parameter determining submodule is used for determining the relative position description parameter of the first semantic element according to the relative position relation.
In an embodiment of the present invention, the relative position relationship may include a first relative distance and a second relative distance between the first semantic element and the semantic elements adjacent to both sides of the first semantic element, and the relative position description parameter determining sub-module may include:
and the target relative distance determining unit is used for determining the average relative distance between the adjacent semantic elements aiming at the target path object and determining the target relative distance according to the average relative distance.
And the distance determination parameter unit is used for determining the relative position description parameter of the first semantic element according to the first relative distance, the second relative distance and the target relative distance.
In an embodiment of the present invention, the target description parameter may further include a type description parameter of the first semantic element, and the parameter determining module 502 may include:
and the semantic element type determining submodule is used for determining the semantic element type of the first semantic element.
And the type description parameter determining submodule is used for determining the type description parameter of the first semantic element according to the semantic element type.
In an embodiment of the present invention, the first semantic element and the second semantic element are parking space elements.
An embodiment of the present invention also provides an electronic device, which may include a processor, a memory, and a computer program stored on the memory and capable of running on the processor, wherein when the computer program is executed by the processor, the computer program implements the processing method of the map data.
An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, implements the processing method of the map data as above.
For the device embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, refer to the partial description of the method embodiment.
The embodiments in the present specification are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
Embodiments of the present invention are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing terminal to cause a series of operational steps to be performed on the computer or other programmable terminal to produce a computer implemented process such that the instructions which execute on the computer or other programmable terminal provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications of these embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the embodiments of the invention.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or terminal that comprises the element.
The method and the apparatus for processing map data provided above are described in detail, and a specific example is applied herein to illustrate the principle and the implementation of the present invention, and the above description of the embodiment is only used to help understanding the method and the core idea of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.

Claims (10)

1. A method for processing map data, the method comprising:
acquiring map data, and determining a matched path object set from the map data;
for a target path object in the path object set, determining a coordinate parameter and a target description parameter of a first semantic element contained in the target path object, wherein the target description parameter is associated with a relative position relationship between the first semantic element and a semantic element adjacent to the first semantic element;
according to the coordinate parameters and the target description parameters, determining a second semantic element matched with the first semantic element from semantic elements contained in other path objects of the path object set;
and fusing the first semantic element and the second semantic element to obtain fused map data.
2. The method according to claim 1, wherein the determining, from semantic elements included in other path objects of the set of path objects according to the coordinate parameters and the target description parameters, a second semantic element matching the first semantic element comprises:
determining candidate semantic elements from semantic elements contained in other path objects of the path object set according to the coordinate parameters and the target description parameters;
determining rotation information and translation information of the candidate semantic element relative to the first semantic element;
and when the rotation information and the translation information meet a preset condition, determining the candidate semantic element as a second semantic element matched with the first semantic element.
3. The method of claim 1, further comprising:
and adding the semantic elements which cannot be matched with the semantic elements in the target path object in the other path objects into the fused map data.
4. The method according to any one of claims 1-3, wherein the target description parameters include a relative position description parameter of the first semantic element, and wherein the determining, for the target path object in the set of path objects, the target description parameters of the first semantic element included in the target path object comprises:
for a target path object in the path object set, determining a relative position relationship between a first semantic element contained in the target path object and a semantic element adjacent to the first semantic element;
and determining a relative position description parameter of the first semantic element according to the relative position relation.
5. The method according to claim 4, wherein the relative position relationship includes a first relative distance and a second relative distance between the first semantic element and semantic elements adjacent to both sides of the first semantic element, and the determining the relative position description parameter of the first semantic element according to the relative position relationship includes:
aiming at the target path object, determining an average relative distance between adjacent semantic elements, and determining a target relative distance according to the average relative distance;
and determining a relative position description parameter of the first semantic element according to the first relative distance, the second relative distance and the target relative distance.
6. The method according to claim 4, wherein the target description parameters further include a type description parameter of the first semantic element, and the determining, for the target path object in the path object set, the target description parameters of the first semantic element included in the target path object includes:
determining a semantic element type of the first semantic element;
and determining the type description parameter of the first semantic element according to the semantic element type.
7. The method of claim 1, wherein the first semantic element and the second semantic element are parking space elements.
8. An apparatus for processing map data, the apparatus comprising:
the system comprises a path object set determining module, a path object set determining module and a path object set matching module, wherein the path object set determining module is used for acquiring map data and determining a matched path object set from the map data;
a parameter determining module, configured to determine, for a target path object in the path object set, a coordinate parameter and a target description parameter of a first semantic element included in the target path object, where the target description parameter is associated with a relative position relationship between the first semantic element and a semantic element adjacent to the first semantic element;
the second semantic element determining module is used for determining a second semantic element matched with the first semantic element from semantic elements contained in other path objects of the path object set according to the coordinate parameters and the target description parameters;
and the semantic element fusion module is used for fusing the first semantic element and the second semantic element to obtain fused map data.
9. An electronic device, comprising a processor, a memory, and a computer program stored on the memory and capable of running on the processor, the computer program, when executed by the processor, implementing a method of processing map data according to any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that a computer program is stored thereon, which, when being executed by a processor, implements a processing method of map data according to any one of claims 1 to 7.
CN202111291451.1A 2021-11-01 2021-11-01 Map data processing method and device Active CN114111758B (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN202111291451.1A CN114111758B (en) 2021-11-01 2021-11-01 Map data processing method and device
PCT/CN2022/081454 WO2023071029A1 (en) 2021-11-01 2022-03-17 Map data processing method and apparatus, and electronic device and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111291451.1A CN114111758B (en) 2021-11-01 2021-11-01 Map data processing method and device

Publications (2)

Publication Number Publication Date
CN114111758A true CN114111758A (en) 2022-03-01
CN114111758B CN114111758B (en) 2024-06-04

Family

ID=80380447

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111291451.1A Active CN114111758B (en) 2021-11-01 2021-11-01 Map data processing method and device

Country Status (2)

Country Link
CN (1) CN114111758B (en)
WO (1) WO2023071029A1 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2023071029A1 (en) * 2021-11-01 2023-05-04 广州小鹏自动驾驶科技有限公司 Map data processing method and apparatus, and electronic device and storage medium

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117131150B (en) * 2023-10-26 2023-12-26 毫末智行科技有限公司 Electronic map generation method, device, vehicle and storage medium

Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110268354A (en) * 2019-05-09 2019-09-20 珊口（深圳）智能科技有限公司 Update the method and mobile robot of map
CN110392908A (en) * 2017-03-07 2019-10-29 三星电子株式会社 For generating the electronic equipment and its operating method of map datum
CN110704562A (en) * 2019-09-27 2020-01-17 Oppo广东移动通信有限公司 Map fusion method and device, equipment and storage medium
KR20200103582A (en) * 2020-08-18 2020-09-02 네이버랩스 주식회사 Method, apparatus and computer program for translating location
CN111639148A (en) * 2020-05-13 2020-09-08 广州小鹏车联网科技有限公司 Picture construction method, system and storage medium
CN111831771A (en) * 2020-07-09 2020-10-27 广州小鹏车联网科技有限公司 Map fusion method and vehicle
CN112068172A (en) * 2020-09-08 2020-12-11 广州小鹏自动驾驶科技有限公司 Vehicle positioning method and device
WO2020248614A1 (en) * 2019-06-10 2020-12-17 商汤集团有限公司 Map generation method, drive control method and apparatus, electronic equipment and system
CN112292581A (en) * 2018-03-29 2021-01-29 欧若拉创新公司 Relative atlas for autonomous vehicles and generation thereof
CN113155141A (en) * 2021-04-09 2021-07-23 阿波罗智联(北京)科技有限公司 Map generation method and device, electronic equipment and storage medium
CN113205118A (en) * 2021-04-13 2021-08-03 北京嘀嘀无限科技发展有限公司 Map matching method, and method and device for determining map matching model
CN113392169A (en) * 2020-03-13 2021-09-14 阿里巴巴集团控股有限公司 High-precision map updating method and device and server
CN113506368A (en) * 2021-07-13 2021-10-15 阿波罗智能技术(北京)有限公司 Map data fusion method, map data fusion device, electronic device, map data fusion medium, and program product

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11280622B2 (en) * 2019-03-13 2022-03-22 Here Global B.V. Maplets for maintaining and updating a self-healing high definition map
CN111220164A (en) * 2020-01-21 2020-06-02 北京百度网讯科技有限公司 Positioning method, device, equipment and storage medium
CN114111815B (en) * 2021-11-01 2023-02-03 广州小鹏自动驾驶科技有限公司 Map data processing method and device
CN114111758B (en) * 2021-11-01 2024-06-04 广州小鹏自动驾驶科技有限公司 Map data processing method and device

Patent Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110392908A (en) * 2017-03-07 2019-10-29 三星电子株式会社 For generating the electronic equipment and its operating method of map datum
CN112292581A (en) * 2018-03-29 2021-01-29 欧若拉创新公司 Relative atlas for autonomous vehicles and generation thereof
CN110268354A (en) * 2019-05-09 2019-09-20 珊口（深圳）智能科技有限公司 Update the method and mobile robot of map
WO2020248614A1 (en) * 2019-06-10 2020-12-17 商汤集团有限公司 Map generation method, drive control method and apparatus, electronic equipment and system
CN110704562A (en) * 2019-09-27 2020-01-17 Oppo广东移动通信有限公司 Map fusion method and device, equipment and storage medium
CN113392169A (en) * 2020-03-13 2021-09-14 阿里巴巴集团控股有限公司 High-precision map updating method and device and server
CN111639148A (en) * 2020-05-13 2020-09-08 广州小鹏车联网科技有限公司 Picture construction method, system and storage medium
CN111831771A (en) * 2020-07-09 2020-10-27 广州小鹏车联网科技有限公司 Map fusion method and vehicle
KR20200103582A (en) * 2020-08-18 2020-09-02 네이버랩스 주식회사 Method, apparatus and computer program for translating location
CN112068172A (en) * 2020-09-08 2020-12-11 广州小鹏自动驾驶科技有限公司 Vehicle positioning method and device
CN113155141A (en) * 2021-04-09 2021-07-23 阿波罗智联(北京)科技有限公司 Map generation method and device, electronic equipment and storage medium
CN113205118A (en) * 2021-04-13 2021-08-03 北京嘀嘀无限科技发展有限公司 Map matching method, and method and device for determining map matching model
CN113506368A (en) * 2021-07-13 2021-10-15 阿波罗智能技术(北京)有限公司 Map data fusion method, map data fusion device, electronic device, map data fusion medium, and program product

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2023071029A1 (en) * 2021-11-01 2023-05-04 广州小鹏自动驾驶科技有限公司 Map data processing method and apparatus, and electronic device and storage medium

Also Published As

Publication number Publication date
WO2023071029A1 (en) 2023-05-04
CN114111758B (en) 2024-06-04

Similar Documents

Publication Publication Date Title
US10576976B2 (en) Drivable area setting device and drivable area setting method
CN109785667B (en) Lane departure recognition method, apparatus, device, and storage medium
CN109813328B (en) Driving path planning method and device and vehicle
CN114111758A (en) Map data processing method and device
KR20190090393A (en) Lane determining method, device and storage medium
CN111102988A (en) Map-based path planning method, server, vehicle-mounted terminal, and storage medium
CN111158365A (en) Path planning method and device, robot and storage medium
CN114111815B (en) Map data processing method and device
CN112946612B (en) External parameter calibration method and device, electronic equipment and storage medium
US20130223725A1 (en) Apparatus and method for estimating disparity using visibility energy model
CN112131327A (en) Motion trail generation method and device
CN116543271A (en) Method, device, electronic equipment and medium for determining target detection evaluation index
JP2007072011A (en) Device for creating road network data, method for creating road network data, and data structure of road network data
CN110705330A (en) Lane line detection method, lane line detection apparatus, and computer-readable storage medium
CN112749458B (en) Cable path planning method, device, equipment and storage medium
JP6936673B2 (en) Map data update system and map data update program
CN112949358A (en) Road description file generation method and equipment
CN112562391A (en) Parking space updating method and device
CN107339995B (en) Navigation device and traffic information matching method thereof
CN110986989A (en) Hybrid vehicle type path planning method and related device
CN114396933B (en) Lane topology construction method and device, vehicle and storage medium
CN115993124B (en) Virtual lane line generation method, device, equipment and computer readable storage medium
CN115128655B (en) Positioning method and device for automatic driving vehicle, electronic equipment and storage medium
CN117232548B (en) Path planning method and device, electronic equipment and storage medium
CN117570965A (en) Lane data processing method, device, equipment 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