CN113932794A - Semantic map updating method and device - Google Patents
Semantic map updating method and device Download PDFInfo
- Publication number
- CN113932794A CN113932794A CN202111192989.7A CN202111192989A CN113932794A CN 113932794 A CN113932794 A CN 113932794A CN 202111192989 A CN202111192989 A CN 202111192989A CN 113932794 A CN113932794 A CN 113932794A
- Authority
- CN
- China
- Prior art keywords
- information
- curved track
- track
- curved
- determining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000004590 computer program Methods 0.000 claims description 18
- 238000000605 extraction Methods 0.000 abstract description 6
- 238000001514 detection method Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 11
- 230000008569 process Effects 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
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
- G01C21/3804—Creation or updating of map data
- G01C21/3807—Creation or updating of map data characterised by the type of data
- G01C21/3815—Road data
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Navigation (AREA)
- Traffic Control Systems (AREA)
Abstract
The embodiment of the invention provides a semantic map updating method and a semantic map updating device, wherein the method comprises the following steps: when the vehicle collects the driving track information with a curved track area, acquiring a plurality of curved track information corresponding to the curved track area; determining a target curved track type of a curved track area according to the information of the plurality of curved tracks; and determining target road semantic information aiming at the curved track area based on the type of the target curved track, and updating the target road semantic information to a semantic map. According to the embodiment of the invention, the road semantic information of different curved track types is determined according to the plurality of curved track information of the curved track area, so that the extraction of the semantics of the curved track areas of different types is realized, and the detection diversity is improved.
Description
Technical Field
The invention relates to the technical field of vehicles, in particular to a semantic map updating method and device.
Background
In recent years, unmanned driving has attracted extensive attention in academic circles and industrial circles at home and abroad, and related supporting technologies thereof have rapidly developed.
The existing unmanned autonomous positioning navigation implementation method comprises the following steps: early magnetic stripe ribbon and other tracking navigation, outdoor satellite navigation, synchronous positioning and map building navigation, and semantic map navigation. In the current unmanned driving field at home and abroad, semantic map navigation is used in a specified scene and is a mainstream technology.
The semantic map is generally generated based on collected environment information and driving track information after collecting the environment of a specified area when a vehicle runs in a specified scene.
When semantic extraction is performed on curved track areas such as curves and ramps, a sliding window is firstly adopted to find out the position with obvious change in the driving track information, and then road semantic information is extracted according to the position.
However, this extraction method is only performed for a position with a significant change, which may result in that only a curve can be extracted, but the road semantic information of what type of curve cannot be extracted; and, only the ramp can be extracted, but the road semantic information of what type of ramp cannot be extracted.
Disclosure of Invention
In view of the above, it is proposed to provide an updating method and apparatus of a semantic map that overcomes or at least partially solves the above problems, comprising:
a semantic map updating method comprises the following steps:
when the vehicle collects the driving track information with a curved track area, acquiring a plurality of curved track information corresponding to the curved track area;
determining a target curved track type of a curved track area according to the information of the plurality of curved tracks;
and determining target road semantic information aiming at the curved track area based on the type of the target curved track, and updating the target road semantic information to a semantic map.
Optionally, the determining the target curved track type of the curved track region according to the plurality of pieces of curved track information includes:
determining a total angle value for the curved track area according to the plurality of track angle information; determining the average value of the plurality of track radius information;
and determining the type of the target curved track according to the mean value and the total angle value.
Optionally, updating the semantic information of the target road to the semantic map includes:
acquiring a plurality of track radius information in the curved track information;
and determining a target position corresponding to the minimum value of the track radius information, and updating the semantic information of the target road to the target position in the semantic map.
Optionally, the obtaining of multiple pieces of curved track information corresponding to a curved track area in the driving track information includes:
when the vehicle is detected to travel to the curved track area, starting to collect curved track information of the curved track area;
and stopping collecting the curved track information of the curved track area when the vehicle is detected to drive away from the curved track area.
Optionally, before starting/stopping collecting the curved trajectory information of the curved trajectory region, the method further comprises:
determining running radius information according to the running track information;
when the running radius information is lower than a preset radius threshold value, judging that the vehicle runs to a curved track area;
and when the running radius information is higher than a preset radius threshold value, judging that the vehicle runs away from the curved track area.
Optionally, the method further comprises:
when the vehicle collects the running track information, judging whether the length of the track in the preset sliding window exceeds a preset length threshold value or not;
and when the length of the track in the preset sliding window exceeds a preset length threshold value, acquiring a plurality of curved track information corresponding to the curved track area.
The embodiment of the invention also provides a semantic map updating device, which comprises:
the device comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring a plurality of pieces of curved track information corresponding to a curved track area when the vehicle collects the running track information with the curved track area;
the determining module is used for determining the type of the target curved track in the curved track area according to the information of the plurality of curved tracks;
and the updating module is used for determining the semantic information of the target road aiming at the curved track area based on the type of the target curved track and updating the semantic information of the target road to the semantic map.
Optionally, the curved track information includes track radius information and track angle information, and the determining module includes:
the digital determination submodule is used for determining a total angle value of a plurality of track angle information and determining a mean value of a plurality of estimated radius information;
and the track type determining submodule is used for determining the type of the target curved track according to the mean value and the total angle value.
Optionally, the update module includes:
the radius obtaining submodule is used for obtaining a plurality of pieces of track radius information in the curved track information;
and the semantic updating submodule is used for determining a target position corresponding to the minimum value of the track radius information and updating the semantic information of the target road to the target position in the semantic map.
Optionally, the obtaining module includes:
the starting and collecting sub-module is used for starting to collect the curved track information of the curved track area when the fact that the vehicle runs to the curved track area is detected;
and the ending collection submodule is used for stopping collecting the curved track information of the curved track area when the vehicle is detected to drive away from the curved track area.
Optionally, the apparatus further comprises:
the first judgment module is used for determining running radius information according to the running track information before starting/stopping collecting the curved track information of the curved track area; when the running radius information is lower than a preset radius threshold value, judging that the vehicle runs to a curved track area; and when the running radius information is higher than a preset radius threshold value, judging that the vehicle runs away from the curved track area.
Optionally, the apparatus further comprises:
and the second judgment module is used for judging whether the length of the track in the preset sliding window exceeds a preset length threshold value or not when the vehicle collects the running track information.
The embodiment of the invention also provides a vehicle, which comprises 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 semantic map updating method is realized.
The embodiment of the invention also provides a computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, and when being executed by a processor, the computer program realizes the above updating method of the semantic map.
The embodiment of the invention has the following advantages:
in the embodiment of the invention, when the vehicle collects the driving track information with a curved track area, a plurality of curved track information corresponding to the curved track area are obtained; determining a target curved track type of a curved track area according to the information of the plurality of curved tracks; and determining target road semantic information aiming at the curved track area based on the type of the target curved track, and updating the target road semantic information to a semantic map. According to the embodiment of the invention, the road semantic information of different curved track types is determined according to the plurality of curved track information of the curved track area, so that the extraction of the semantics of the curved track areas of different types is realized, and the detection diversity is 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 semantic map updating method according to an embodiment of the present invention;
FIG. 2 is a flow chart of steps of another semantic map updating method according to an embodiment of the present invention;
FIG. 3 is a flow diagram of semantic map updates of an embodiment of the present invention;
fig. 4 is a block diagram of a semantic map updating apparatus 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 semantic map updating method according to an embodiment of the present invention is shown, which may specifically include the following steps:
the curved track area may refer to an area in which a track of the vehicle is curved when the vehicle travels, for example: curves, ramps, etc.; the curved track information may refer to information related to a degree of deformation of the track, among the vehicle track information corresponding to the curved track area, for example: the radius of the curved trajectory, the angle of the curved trajectory, etc., which are not limited in this respect.
In order to obtain a semantic map for unmanned driving, a vehicle can be driven by a tester to run in a specified scene; the designated scene may be an area where a semantic map needs to be generated, such as an indoor parking lot, an outdoor parking lot, a cell ground road, and the like, which is not limited in this embodiment of the present invention.
When the vehicle travels in a specified scene, the driving track information may be generated according to the traveling track, and the driving track information may include the position where the vehicle has traveled and the change in the position.
In practical application, when the vehicle collects the trajectory information, the trajectory information collected by the vehicle is detected to determine whether the trajectory information of the curved trajectory region exists. The driving track information of the curved track area may be generated when the vehicle passes through a curve or when the vehicle passes through a slope, which is not limited in this embodiment of the present invention.
When it is detected that the vehicle trajectory information collected by the vehicle includes the vehicle trajectory information of the curved trajectory region, the plurality of curved trajectory information of the curved trajectory region may be acquired from the corresponding vehicle trajectory information.
102, determining a target curved track type of a curved track area according to a plurality of pieces of curved track information;
after the plurality of pieces of curved track information are acquired, the target curved track type of the curved track area can be determined according to the plurality of pieces of curved track information.
Specifically, since the curved track information corresponding to different curved track types is different, the corresponding relationship between the curved track information and the curved track types may be set in advance. Therefore, after the plurality of pieces of curved track information corresponding to the curved track area are obtained, the curved track type corresponding to the plurality of pieces of curved track information can be determined from the corresponding relationship, and the curved track type can be used as the target curved track type of the curved track area.
And 103, determining target road semantic information aiming at the curved track area based on the target curved track type, and updating the target road semantic information to a semantic map.
After determining the target curved track type of the curved track region, the target road semantic information of the curved track region may be extracted based on the target curved track type, for example: and if the target curved track type is a right-angle curve, the semantic information of the target road in the curved track area can be extracted to be the right-angle curve.
After the semantic information of the target road in the curved track area is determined, the semantic information of the target road can be written to the position of the curved track area in the semantic map, so that the semantic information of the target road is updated to the semantic map.
In the embodiment of the invention, when the vehicle collects the driving track information with a curved track area, a plurality of curved track information corresponding to the curved track area are obtained; determining a target curved track type of a curved track area according to the information of the plurality of curved tracks; and determining target road semantic information aiming at the curved track area based on the type of the target curved track, and updating the target road semantic information to a semantic map. According to the embodiment of the invention, the road semantic information of different curved track types is determined according to the plurality of curved track information of the curved track area, so that the extraction of the semantics of the curved track areas of different types is realized, and the detection diversity is improved.
Referring to fig. 2, a flowchart illustrating steps of another semantic map updating method according to an embodiment of the present invention is shown, which may specifically include the following steps:
in practical application, when the vehicle collects the trajectory information, the trajectory information collected by the vehicle is detected to determine whether the trajectory information of the curved trajectory region exists.
When it is detected that the vehicle trajectory information collected by the vehicle includes the vehicle trajectory information of the curved trajectory region, the plurality of curved trajectory information of the curved trajectory region may be acquired from the corresponding vehicle trajectory information.
In an embodiment of the present invention, before obtaining the curved track information, the following steps may be further performed:
when the vehicle collects the running track information, judging whether the length of the track in the preset sliding window exceeds a preset length threshold value or not; and when the length of the track in the preset sliding window exceeds a preset length threshold value, acquiring a plurality of curved track information corresponding to the curved track area.
When the driving track information is collected, a preset sliding window can be adopted to collect the driving track information; then, the subsequent steps can be performed for the traffic track information in the preset sliding window.
Between the same two points, the length of the straight trajectory is shorter than the length of the curved trajectory; therefore, whether the driving track information of the curved track area exists can be preliminarily judged according to the length of the track in the preset sliding window; if the length of the track in the preset sliding window exceeds a preset length threshold, the vehicle running track information with the curved track area can be collected, and at this time, the step of obtaining a plurality of curved track information corresponding to the curved track area can be executed. The preset length threshold may be determined based on a size of the preset sliding window, for example, if the size of the preset sliding window is 1cm × 2cm, the preset length threshold may be set to 2cm, which is not limited in this embodiment of the present invention.
If the length of the track in the preset sliding window does not exceed the preset length threshold, it can indicate that the running track information of the curved track area is not collected; at this time, the preset sliding window may be continuously slid.
In an embodiment of the present invention, the curved track information may be obtained by:
when the vehicle is detected to travel to the curved track area, starting to collect curved track information of the curved track area; and stopping collecting the curved track information of the curved track area when the vehicle is detected to drive away from the curved track area.
In practical application, whether the vehicle runs to a curved track area or not can be detected firstly; if the vehicle is detected to travel to the curved track area, collection of the curved track information of the curved track area through a preset sliding window can be started.
In addition, when it is detected that the vehicle has left the curved track area, collection of the curved track information in the curved track area may be stopped in order to avoid the influence of invalid information on the subsequent generation of the road semantic information.
It should be noted that the collection process may be continuous; thus, a plurality of curved trajectory information of the curved trajectory region can be collected.
In an example, after the curved track information is collected, the embodiment of the present invention may determine the curved track information in advance to determine whether the information is preset road semantic information that needs to be updated; if so, continuing to execute the subsequent steps, and if not, deleting the previous data, and continuing to slide the preset sliding window for data acquisition, which is not limited in the embodiment of the present invention.
In an embodiment of the present invention, before starting/stopping collecting the curved track information of the curved track region, the following steps may be further included:
determining running radius information according to the running track information; when the running radius information is lower than a preset radius threshold value, judging that the vehicle runs to a curved track area; and when the running radius information is higher than a preset radius threshold value, judging that the vehicle runs away from the curved track area.
In practical application, the running radius information of the vehicle is different when the vehicle runs through a curved track area and when the vehicle runs through a straight track area; the travel radius information in the curved track area is smaller than the travel radius information in the straight track area. Therefore, it is possible to determine whether the vehicle travels to the curved track area based on the travel radius information; and, whether the vehicle is driven out of the curved track area may be determined based on the driving radius information.
As an example, the running radius information of the track on which the vehicle is currently running may be obtained from the running track information; and then comparing the relation between the running radius information and a preset radius threshold value. The preset radius threshold may be set according to an actual situation, which is not limited in the embodiment of the present invention.
When it is detected that the traveling radius information is lower than the preset radius threshold, it may indicate that the vehicle is entering the curved track area. At this time, the collection of the curved trajectory information may be started through a preset sliding window.
Then, the monitoring of the relation between the traveling radius information and the preset radius threshold may be continued, and when it is detected that the traveling radius information becomes more than the preset radius threshold, it may be indicated that the vehicle is traveling out of the curved track area. At this point, collection of curved trajectory information may be stopped.
the track radius information may refer to a radius of a track of the vehicle when the vehicle travels in the curved track area, and the track angle information may refer to an angle of the track from entering the curved track area to traveling out of the curved track area. Specifically, the track angle information may be obtained from the trajectory information, and then the track length may be obtained from the trajectory information, and then the track radius information may be calculated based on the track angle information and the track length.
In order to avoid that the type of the corresponding curved track may not be extracted due to the fact that only a place with obvious change is adopted to extract the road semantic information, the embodiment of the invention can adopt the preset sliding window to collect the curved track information in a sliding mode, and therefore a plurality of pieces of curved track information aiming at the curved track area are collected.
After the curved track information is obtained, determining a total angle value of a track from the curved track area to the curved track area of the vehicle according to the plurality of track angle information; meanwhile, the average value of a plurality of track radius information can be calculated.
different radii and angles are provided due to different curved trajectory types; therefore, the corresponding relation between the radius and the angle and the type of the curved track can be preset; then, after obtaining the radius mean value and the total angle value of the curved track region, the corresponding curved track type can be determined from the corresponding relationship, and the corresponding curved track type can be used as the target curved track type of the curved track region.
after the target curved track type of the curved track area is determined, the target road semantic information of the curved track area can be extracted based on the target curved track type.
when the semantic information of the target road is updated into the semantic map, in order to ensure the accuracy of writing the semantic information position of the target road, a plurality of track radius information in the curved track information can be obtained first, so that the target position where the semantic information of the target road is written can be determined based on the track radius information.
And step 206, determining a target position corresponding to the minimum value of the track radius information, and updating the semantic information of the target road to the target position in the semantic map.
In practical application, the track radius information of the curved track area generally changes from big to small and then from small to big; therefore, the embodiment of the invention can take the position corresponding to the minimum value of the track radius information as the target position for writing the semantic information of the target road.
After the target position is determined, the semantic information of the target road can be updated to the target position in the semantic map; therefore, the consistency between the written position of the road semantic information and the actual position of the road semantic information is ensured.
In an example, after the above steps are completed, the embodiment of the present invention may further delete the previous data, and continue to execute the above steps 201 to 206 until the semantic map creation is completed, which is not limited in this embodiment of the present invention.
As shown in fig. 3, the driving track information may be collected in a preset sliding window; and then judging whether the track length in the preset sliding window exceeds a preset length threshold value or not.
And when the track length in the preset sliding window does not exceed the preset length threshold, continuously collecting the traveling track information in the preset sliding window. When the track length in the preset sliding window exceeds a preset length threshold, whether the track length is preset road semantic information needing to be updated or not can be judged according to the curved track information.
And if the road semantic information is not preset road semantic information needing to be updated, continuously sliding a preset sliding window for data acquisition. If the road semantic information is preset and needs to be updated, determining the type of the curved track according to the curved track information, extracting the semantic information of the target road and determining the position of the target; and then, updating the semantic information of the target road to a semantic map, and continuously sliding a preset sliding window for data acquisition.
In the embodiment of the invention, when the vehicle collects the driving track information with a curved track area, a plurality of curved track information corresponding to the curved track area are obtained; the curved track information comprises track radius information and track angle information; determining a total angle value for the curved track area according to the plurality of track angle information; determining the average value of the plurality of track radius information; determining the type of the target curved track according to the mean value and the total angle value; determining target road semantic information aiming at a curved track area based on the type of the target curved track; acquiring a plurality of track radius information in the curved track information; and determining a target position corresponding to the minimum value of the track radius information, and updating the semantic information of the target road to the target position in the semantic map. By the embodiment of the invention, the target road semantic information is updated to the position with the minimum track radius, and the consistency between the position written by the road semantic information and the actual position of the road semantic information is ensured.
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. 4, a schematic structural diagram of an updating apparatus of a semantic map according to an embodiment of the present invention is shown, and the updating apparatus may specifically include the following modules:
the acquiring module 401 is configured to acquire a plurality of pieces of curved track information corresponding to a curved track area when a vehicle collects piece of driving track information in which the curved track area exists;
a determining module 402, configured to determine a target curved track type of the curved track region according to the plurality of pieces of curved track information;
and an updating module 403, configured to determine, based on the type of the target curved track, target road semantic information for the curved track area, and update the target road semantic information to a semantic map.
In an alternative embodiment of the present invention, the curved track information includes track radius information and track angle information, and the determining module 402 includes:
the digital determination submodule is used for determining a total angle value of a plurality of track angle information and determining a mean value of a plurality of estimated radius information;
and the track type determining submodule is used for determining the type of the target curved track according to the mean value and the total angle value.
In an optional embodiment of the present invention, the update module 403 includes:
the radius obtaining submodule is used for obtaining a plurality of pieces of track radius information in the curved track information;
and the semantic updating submodule is used for determining a target position corresponding to the minimum value of the track radius information and updating the semantic information of the target road to the target position in the semantic map.
In an optional embodiment of the present invention, the obtaining module 401 includes:
the starting and collecting sub-module is used for starting to collect the curved track information of the curved track area when the fact that the vehicle runs to the curved track area is detected;
and the ending collection submodule is used for stopping collecting the curved track information of the curved track area when the vehicle is detected to drive away from the curved track area.
In an optional embodiment of the invention, the apparatus further comprises:
the first judgment module is used for determining running radius information according to the running track information before starting/stopping collecting the curved track information of the curved track area; when the running radius information is lower than a preset radius threshold value, judging that the vehicle runs to a curved track area; and when the running radius information is higher than a preset radius threshold value, judging that the vehicle runs away from the curved track area.
In an optional embodiment of the invention, the apparatus further comprises:
and the second judgment module is used for judging whether the length of the track in the preset sliding window exceeds a preset length threshold value or not when the vehicle collects the running track information.
In the embodiment of the invention, when the vehicle collects the driving track information with a curved track area, a plurality of curved track information corresponding to the curved track area are obtained; determining a target curved track type of a curved track area according to the information of the plurality of curved tracks; and determining target road semantic information aiming at the curved track area based on the type of the target curved track, and updating the target road semantic information to a semantic map. According to the embodiment of the invention, the road semantic information of different curved track types is determined according to the plurality of curved track information of the curved track area, so that the extraction of the semantics of the curved track areas of different types is realized, and the detection diversity is improved.
The embodiment of the invention also provides a vehicle, 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 method for updating the semantic map is implemented.
The embodiment of the invention also provides a computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, and when being executed by a processor, the computer program realizes the above updating method of the semantic map.
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 above provides a semantic map updating method and apparatus, which are introduced in detail, and the principle and implementation of the present invention are explained in this document by applying specific examples, and the description of the above embodiments is only used to help understanding the method and core ideas 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 semantic map updating method is characterized by comprising the following steps:
when a vehicle collects driving track information with a curved track area, acquiring a plurality of curved track information corresponding to the curved track area;
determining a target curved track type of the curved track area according to the plurality of pieces of curved track information;
and determining target road semantic information aiming at the curved track area based on the target curved track type, and updating the target road semantic information to the semantic map.
2. The method of claim 1, wherein the curved track information includes track radius information and track angle information, and wherein determining the target curved track type for the curved track region based on the plurality of curved track information comprises:
determining a total angle value for the curved track area according to the plurality of track angle information; determining the average value of the plurality of track radius information;
and determining the type of the target curved track according to the mean value and the total angle value.
3. The method of claim 1, wherein the updating the target road semantic information to the semantic map comprises:
acquiring a plurality of track radius information in the curved track information;
and determining a target position corresponding to the minimum value of the track radius information, and updating the semantic information of the target road to the target position in the semantic map.
4. The method according to claim 1, wherein the obtaining a plurality of curved track information corresponding to a curved track area in the driving track information comprises:
when the vehicle is detected to travel to a curved track area, starting to collect curved track information of the curved track area;
and stopping collecting the curved track information of the curved track area when the vehicle is detected to drive away from the curved track area.
5. The method of claim 4, wherein prior to starting/stopping collecting the curved trajectory information for the curved trajectory region, the method further comprises:
determining running radius information according to the running track information;
when the running radius information is lower than a preset radius threshold value, judging that the vehicle runs to a curved track area;
and when the running radius information is higher than the preset radius threshold value, judging that the vehicle runs out of the curved track area.
6. The method according to any one of claims 1-5, further comprising:
when the vehicle collects the running track information, judging whether the length of the track in the preset sliding window exceeds a preset length threshold value or not;
and when the length of the track in the preset sliding window exceeds a preset length threshold value, acquiring a plurality of curved track information corresponding to the curved track area.
7. An apparatus for updating semantic map, the apparatus comprising:
the device comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring a plurality of pieces of curved track information corresponding to a curved track area when a vehicle collects the running track information with the curved track area;
a determining module, configured to determine a target curved track type of the curved track region according to the plurality of pieces of curved track information;
and the updating module is used for determining the semantic information of the target road aiming at the curved track area based on the type of the target curved track and updating the semantic information of the target road to the semantic map.
8. The apparatus of claim 7, wherein the curved track information comprises track radius information and track angle information, and wherein the determining module comprises:
the digital determination submodule is used for determining a total angle value of a plurality of track angle information and determining a mean value of a plurality of estimated radius information;
and the track type determining submodule is used for determining the type of the target curved track according to the mean value and the total angle value.
9. A vehicle comprising a processor, a memory and a computer program stored on the memory and executable on the processor, the computer program, when executed by the processor, implementing the method of updating a semantic map according to any one of claims 1 to 6.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, implements the method for updating a semantic map according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111192989.7A CN113932794B (en) | 2021-10-13 | 2021-10-13 | Semantic map updating method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111192989.7A CN113932794B (en) | 2021-10-13 | 2021-10-13 | Semantic map updating method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113932794A true CN113932794A (en) | 2022-01-14 |
| CN113932794B CN113932794B (en) | 2022-12-13 |
Family
ID=79278897
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111192989.7A Active CN113932794B (en) | 2021-10-13 | 2021-10-13 | Semantic map updating method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113932794B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116821266A (en) * | 2022-12-30 | 2023-09-29 | 北京易航远智科技有限公司 | Semantic map construction method and automatic driving system with acquaintance road mode |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160282126A1 (en) * | 2015-03-24 | 2016-09-29 | Google Inc. | Associating Semantic Location Data with Automated Environment Mapping |
| CN107462243A (en) * | 2017-08-04 | 2017-12-12 | 浙江大学 | A kind of cloud control automatic Pilot task creating method based on high-precision map |
| CN108036794A (en) * | 2017-11-24 | 2018-05-15 | 华域汽车系统股份有限公司 | A kind of high accuracy map generation system and generation method |
| US20200182630A1 (en) * | 2018-12-10 | 2020-06-11 | Toyota Jidosha Kabushiki Kaisha | Map generation system |
| CN111797187A (en) * | 2020-06-22 | 2020-10-20 | 北京百度网讯科技有限公司 | Map data updating method and device, electronic equipment and storage medium |
| CN112328730A (en) * | 2021-01-04 | 2021-02-05 | 腾讯科技（深圳）有限公司 | Map data updating method, related device, equipment and storage medium |
| CN112668153A (en) * | 2020-12-11 | 2021-04-16 | 国汽(北京)智能网联汽车研究院有限公司 | Method, device and equipment for generating automatic driving simulation scene |
| CN113128326A (en) * | 2019-12-31 | 2021-07-16 | 百度（美国）有限责任公司 | Vehicle trajectory prediction model with semantic map and LSTM |
-
2021
- 2021-10-13 CN CN202111192989.7A patent/CN113932794B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160282126A1 (en) * | 2015-03-24 | 2016-09-29 | Google Inc. | Associating Semantic Location Data with Automated Environment Mapping |
| CN107462243A (en) * | 2017-08-04 | 2017-12-12 | 浙江大学 | A kind of cloud control automatic Pilot task creating method based on high-precision map |
| CN108036794A (en) * | 2017-11-24 | 2018-05-15 | 华域汽车系统股份有限公司 | A kind of high accuracy map generation system and generation method |
| US20200182630A1 (en) * | 2018-12-10 | 2020-06-11 | Toyota Jidosha Kabushiki Kaisha | Map generation system |
| CN113128326A (en) * | 2019-12-31 | 2021-07-16 | 百度（美国）有限责任公司 | Vehicle trajectory prediction model with semantic map and LSTM |
| CN111797187A (en) * | 2020-06-22 | 2020-10-20 | 北京百度网讯科技有限公司 | Map data updating method and device, electronic equipment and storage medium |
| CN112668153A (en) * | 2020-12-11 | 2021-04-16 | 国汽(北京)智能网联汽车研究院有限公司 | Method, device and equipment for generating automatic driving simulation scene |
| CN112328730A (en) * | 2021-01-04 | 2021-02-05 | 腾讯科技（深圳）有限公司 | Map data updating method, related device, equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 赵斌等: "语义轨迹建模与挖掘研究进展", 《地球信息科学学报》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116821266A (en) * | 2022-12-30 | 2023-09-29 | 北京易航远智科技有限公司 | Semantic map construction method and automatic driving system with acquaintance road mode |
| CN116821266B (en) * | 2022-12-30 | 2024-03-29 | 北京易航远智科技有限公司 | Semantic map construction method and automatic driving system with acquaintance road mode |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113932794B (en) | 2022-12-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109606384B (en) | Vehicle control method, device, equipment and storage medium | |
| CN111824130A (en) | Parking control method and device, vehicle and storage medium | |
| CN112013831B (en) | Map boundary automatic extraction method and device based on terrain analysis | |
| US20190147257A1 (en) | Method for detecting traffic signs | |
| CN113932794B (en) | Semantic map updating method and device | |
| CN113799770B (en) | Data processing method and device based on automatic driving | |
| CN112836003A (en) | Map processing method and device | |
| CN106970613A (en) | Method and apparatus for running vehicle that at least one portion is automated or supermatic | |
| CN112319464B (en) | Automatic parking method, device, equipment and storage medium | |
| CN112229411B (en) | Data processing method and device | |
| CN112644478A (en) | Parking control method and device | |
| CN104168444A (en) | Target tracking method of tracking ball machine and tracking ball machine | |
| CN115311229A (en) | Laser radar-based pavement disease detection and classification method and system and storage medium | |
| CN115962774A (en) | Point cloud map updating method and device, electronic equipment and storage medium | |
| CN113465615B (en) | Lane line generation method and related device | |
| CN112767740B (en) | Parking lot selection method and device | |
| CN111475591A (en) | Road association method and equipment for interest point acquisition | |
| CN112309004B (en) | Virtual deceleration strip generation method and device, vehicle and storage medium | |
| CN111292292A (en) | Pipeline obstacle detection method and device, pipeline robot and readable storage medium | |
| CN112572421B (en) | Automatic parking method and device for vehicle, vehicle and storage medium | |
| CN114580574A (en) | Method and device for constructing high-precision map | |
| CN114906154A (en) | Method and system for judging vehicle driving road type, electronic device and storage medium | |
| CN114528365A (en) | Method and device for identifying parking area on highway, electronic equipment and medium | |
| CN113587943A (en) | Map processing method and device | |
| Certad et al. | Road Markings Segmentation from LIDAR Point Clouds using Reflectivity Information |
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 | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20240228 Address after: 510000 No.8 Songgang street, Cencun, Tianhe District, Guangzhou City, Guangdong Province Patentee after: GUANGZHOU XIAOPENG MOTORS TECHNOLOGY Co.,Ltd. Country or region after: China Address before: Room 46, room 406, No. 1, Yichuang street, Zhongxin knowledge city, Huangpu District, Guangzhou, Guangdong 510725 Patentee before: Guangzhou Xiaopeng Automatic Driving Technology Co.,Ltd. Country or region before: China |
|
| TR01 | Transfer of patent right |