CN111323004A - Initial position determining method and vehicle-mounted terminal - Google Patents
Initial position determining method and vehicle-mounted terminal Download PDFInfo
- Publication number
- CN111323004A CN111323004A CN201811538402.1A CN201811538402A CN111323004A CN 111323004 A CN111323004 A CN 111323004A CN 201811538402 A CN201811538402 A CN 201811538402A CN 111323004 A CN111323004 A CN 111323004A
- Authority
- CN
- China
- Prior art keywords
- information
- semantic information
- map
- geographic
- vehicle
- 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 36
- 230000001413 cellular effect Effects 0.000 claims description 6
- 230000008569 process Effects 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000006467 substitution reaction Methods 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
- G01C21/005—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 with correlation of navigation data from several sources, e.g. map or contour matching
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
- Navigation (AREA)
Abstract
The specification discloses a method for determining an initial position and a vehicle-mounted terminal, wherein the method for determining the initial position comprises the following steps: acquiring a rough position of a current vehicle, and determining an initialization range and first map semantic information and first geographic information corresponding to the initialization range according to the rough position; acquiring second geographic semantic information and second geographic information near the current vehicle; matching the first map semantic information and the first geographic information with the second map semantic information and the second geographic information respectively to obtain a possible position in the initialization range and third map semantic information and third geographic information near the possible position; and matching the third map semantic information and the third geographic information with the second map semantic information and the second geographic information respectively to determine the initial position of the current vehicle.
Description
Technical Field
The specification relates to the field of automatic driving, in particular to a method for determining an initial position and a vehicle-mounted terminal.
Background
In auto park scenarios, a high precision map based positioning system is typically required to provide accurate positioning of the vehicle. The determination of the initial position of the positioning system is a major difficulty. When the system is just started, means for acquiring an accurate position are limited (such as a GPS, and the like), and especially for application scenarios with limited GPS, such as underground garages and closed parks, the initial position is more difficult to determine.
Disclosure of Invention
The present specification provides a method for determining an initial position and a vehicle-mounted terminal, so as to overcome at least one technical problem in the prior art.
According to a first aspect of embodiments herein, there is provided a method for determining an initial position, including the steps of:
acquiring a rough position of a current vehicle, and determining an initialization range and first map semantic information and first geographic information corresponding to the initialization range according to the rough position;
acquiring second geographic semantic information and second geographic information near the current vehicle;
matching the first map semantic information and the first geographic information with the second map semantic information and the second geographic information respectively to obtain a possible position in the initialization range and third map semantic information and third geographic information near the possible position;
and matching the third map semantic information and the third geographic information with the second map semantic information and the second geographic information respectively to determine the initial position of the current vehicle.
Optionally, the rough location is a location obtained through GPS, WIFI, bluetooth, or a cellular base station; or
The rough position is a pre-saved position before the vehicle stops; or
The coarse position is a preset position; or
The coarse location is a location of a user input.
Optionally, the determining an initialization range according to the rough position and the first map semantic information and the first geographic information corresponding to the initialization range include:
determining an initial search area according to the rough position and an error range corresponding to the type of the rough position;
setting a candidate position at intervals of a set distance in the search area, extracting map information of each candidate position from a map, and constructing a corresponding local semantic information map based on the extracted map information, wherein the local semantic information map comprises map semantics and geographic information near the corresponding candidate position.
Optionally, the obtaining second geographic semantic information and second geographic information about the current vehicle includes:
acquiring sensing data of a vehicle sensor;
and extracting semantic information from the sensing data to obtain a semantic information map actually observed nearby the vehicle, wherein the semantic information map comprises second geographic semantic information and second geographic information.
Optionally, the vehicle sensor includes at least one of a visible light camera, an infrared camera, a laser radar, a millimeter wave radar, and an ultrasonic sensor.
Optionally, the matching the first map semantic information and the first geographic information with the second map semantic information and the second geographic information respectively to obtain a possible position within the initialization range and third map semantic information and third geographic information near the possible position includes:
aligning semantic information in the local semantic information map of each candidate position with the semantic information of the second map according to the category of the semantic information;
and judging whether the error of the two is within an allowable range according to the alignment result, if so, taking the corresponding candidate position as the possible position of the current vehicle, and taking the local map semantic information and the geographic information near the corresponding candidate position as the third map semantic information and the third geographic information near the possible position.
Optionally, when the semantic information in the local semantic information map of each candidate position and the second semantic information are aligned according to the category of the semantic information, the resolution of the semantic information maps is not greater than the set resolution.
Optionally, the matching the third map semantic information and the third geographic information with the second map semantic information and the second geographic information, respectively, and determining the initial position of the current vehicle includes:
aligning the third map semantic information and the second map semantic information near each possible position according to the category of the semantic information, and aligning the third geographic information and the second geographic information near the possible position according to the category of the geographic information;
and judging whether the error of the alignment result and the error of the alignment result is within an allowable range, and if so, taking the corresponding possible position as the initial position of the current vehicle.
Optionally, when the semantic information in the local semantic information map of each possible location and the second semantic information are aligned according to the category of the semantic information, the resolution of the semantic information maps is greater than the set resolution.
According to a second aspect of the embodiments of the present specification, there is also provided a vehicle-mounted terminal including:
the first position information acquisition module is configured to acquire a rough position of a current vehicle, and determine an initialization range and first map semantic information and first geographic information corresponding to the initialization range according to the rough position;
the second position information acquisition module is configured to acquire second map semantic information and second geographic information near the current vehicle;
a first position determination module configured to match the first map semantic information and the first geographic information with the second map semantic information and the second geographic information, respectively, to obtain a possible position within the initialization range and third map semantic information and third geographic information near the possible position;
and the second position determining module is configured to match the third map semantic information and the third geographic information with the second map semantic information and the second geographic information respectively, and determine an initial position of the current vehicle.
Optionally, the rough location is a location obtained through GPS, WIFI, bluetooth, or a cellular base station; or
The rough position is a pre-saved position before the vehicle stops; or
The coarse position is a preset position; or
The coarse location is a location of a user input.
Optionally, the first location information obtaining module includes:
a search area determining unit configured to determine an initial search area according to the coarse position and an error range corresponding to a type to which the coarse position belongs;
the candidate position determining unit is configured to set a candidate position in the search area at intervals of a set distance, extract map information of each candidate position from a map, and construct a corresponding local semantic information map based on the extracted map information, wherein the local semantic information map comprises map semantics and geographic information near the corresponding candidate position.
Optionally, the second position information obtaining module includes:
a sensing data acquisition unit configured to acquire sensing data of a vehicle sensor;
and the position information extraction unit is configured to extract semantic information of the sensing data to obtain a semantic information map actually observed nearby the vehicle, wherein the semantic information map comprises second geographic semantic information and second geographic information.
Optionally, the vehicle sensor includes at least one of a visible light camera, an infrared camera, a laser radar, a millimeter wave radar, and an ultrasonic sensor.
Optionally, the first position determining module includes:
a first alignment unit configured to align semantic information in the local semantic information map of each of the candidate positions and the second geographic semantic information according to a category of semantic information;
and the first position determining unit is configured to judge whether the error of the two is within an allowable range according to the alignment result, if so, the corresponding candidate position is taken as the possible position of the current vehicle, and the local map semantic information and the geographic information near the corresponding candidate position are taken as the third map semantic information and the third geographic information near the possible position.
Optionally, when the semantic information in the local semantic information map of each candidate position and the second semantic information are aligned according to the category of the semantic information, the resolution of the semantic information maps is not greater than the set resolution.
Optionally, the second position determining module includes:
a second alignment unit configured to align third map semantic information and the second map semantic information near each of the possible locations according to categories of semantic information, and align third geographic information and the second geographic information near the possible locations according to categories of geographic information;
and the second position determining unit is configured to judge whether the error of the two is within an allowable range according to the alignment result, and if so, the corresponding possible position is taken as the position of the current vehicle.
Optionally, when the semantic information in the local semantic information map of each possible location and the second semantic information are aligned according to the category of the semantic information, the resolution of the semantic information maps is greater than the set resolution.
In the embodiment of the description, the initial position of the current vehicle is obtained by acquiring the rough position of the vehicle, the corresponding map semantic information and geographic information, the position of the vehicle and the map semantic information and geographic information near the vehicle, and matching the map semantic information and the geographic information of the vehicle and the map semantic information and the geographic information of the vehicle. The embodiment of the specification can complete positioning only by the surrounding environment information of the initial position of the vehicle, does not need to wait for a certain distance to run, and is high in matching efficiency.
The invention of the embodiment of the present specification at least includes:
1. the rough position of the vehicle, the corresponding map semantic information and geographic information, the position of the vehicle, the map semantic information and the geographic information near the vehicle are obtained, and the map semantic information and the geographic information of the rough position and the geographic information are matched, so that the initial position of the current vehicle can be obtained only by the surrounding environment information of the initial position of the vehicle, and the method is one of the invention points of the embodiments of the specification.
2. In the matching process of the semantic information graph, the possible position of the vehicle is determined by a low-resolution matching mode, and then the accurate position of the vehicle is determined by a high-resolution matching mode.
3. When the possible position of the current vehicle is determined according to the candidate position in the initial range to narrow the search range of the initial position of the vehicle, only the semantic information in the local semantic information map of each candidate position and the semantic information of the second map near the vehicle are aligned according to the category of the semantic information to improve the efficiency of position matching, which is one of the inventions of the embodiments of the present specification.
Drawings
In order to more clearly illustrate the embodiments of the present specification or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present specification, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart of a method for initial position determination according to one embodiment of the present disclosure;
FIG. 2 is a flow chart illustrating initialization of a positioning system according to one embodiment of the present disclosure;
fig. 3 is a block diagram of a vehicle-mounted terminal according to an embodiment of the present disclosure.
Detailed Description
The technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the drawings in the embodiments of the present disclosure, and it is obvious that the described embodiments are only a part of the embodiments of the present disclosure, and not all of the embodiments. All other embodiments obtained by a person skilled in the art based on the embodiments in the present specification without any inventive step are within the scope of the present specification.
It should be noted that the terms "including" and "having" and any variations thereof in the embodiments of the present specification and the drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.
The embodiment of the specification discloses a method for determining an initial position and a vehicle-mounted terminal. The following are detailed below.
FIG. 1 is a flow chart of a method for initial position determination according to one embodiment of the present disclosure; as shown in fig. 1, the method for determining the initial position includes the following steps:
s110, acquiring a rough position of a current vehicle, and determining an initialization range and first map semantic information and first geographic information corresponding to the initialization range according to the rough position;
in one implementation, the coarse location may be obtained via GPS, WIFI, bluetooth, or cellular base station; or the rough position may be a pre-saved position before the vehicle stops; or the rough location may be a location preset by a user; or the coarse location may also be a user-entered location. For example, in an underground garage automatic parking application scenario, a preset underground garage entrance position can be used as the vehicle rough position.
In a specific implementation, the determining of the initialization range according to the rough position and the first map semantic information and the first geographic information corresponding to the initialization range may be implemented in the following manner: determining an initial search area according to the rough position and an error range corresponding to the type of the rough position; setting a candidate position every a set distance in the search area, extracting map information of each candidate position from a map, and constructing a corresponding local semantic information map based on the extracted map information, wherein the local semantic information map comprises map semantics and geographic information near the corresponding candidate position, and the geographic information refers to geographic position information of various semantic information relative to vehicles.
When determining the initial search range, the initial search range may be determined according to an error range corresponding to the position type to which the rough position belongs. The error range for each position type may be set based on test data or experience.
And S120, acquiring second geographic semantic information and second geographic information near the current vehicle.
In one implementation, the obtaining of the second geographic semantic information and the second geographic information in the vicinity of the current vehicle may be implemented by: acquiring sensing data of a vehicle sensor; and extracting semantic information from the sensing data to obtain a semantic information map actually observed nearby the vehicle, wherein the semantic information map comprises second geographic semantic information and second geographic information.
Wherein the vehicle sensor may be at least one of a visible light camera, an infrared camera, a laser radar, a millimeter wave radar, and an ultrasonic sensor.
The local semantic information graph represents semantic information and corresponding geographic position information content which are calculated according to map information and contained in the environment around the position. The semantic information depends on information contained in the high-precision map, including but not limited to information of road surfaces, lane lines, road signs, buildings, sidewalks, and the like. For example, in the scenario of an underground garage automatic parking application, the high-precision map contains all semantic information such as lane lines, garage lines, road signs, indicating arrows, sidewalks, and the like in the garage, and the precise geographic positions corresponding to the semantic information. Therefore, for any candidate position, a local semantic information map can be constructed, which represents the content of the semantic information of the area near the candidate position and the corresponding geographic position.
S130, the first map semantic information and the first geographic information are respectively matched with the second map semantic information and the second geographic information, and a possible position in the initialization range and third map semantic information and third geographic information near the possible position are obtained.
In one implementation, the matching the first map semantic information and the first geographic information with the second map semantic information and the second geographic information respectively to obtain a possible location within the initialization range and third map semantic information and third geographic information near the possible location may be implemented by the following steps: aligning semantic information in the local semantic information map of each candidate position with the semantic information of the second map according to the category of the semantic information; and judging whether the error of the two is within an allowable range according to the alignment result, if so, taking the corresponding candidate position as the possible position of the current vehicle, and taking the local map semantic information and the geographic information near the corresponding candidate position as the third map semantic information and the third geographic information near the possible position.
In order to improve the calculation efficiency, when the semantic information in the local semantic information map of each candidate position and the second geographic semantic information are aligned according to the category of the semantic information, the resolution of the semantic information maps is not greater than the set resolution. According to the embodiment, the low-resolution matching mode is adopted, so that the operation amount can be reduced, and the matching efficiency is improved.
And S140, matching the third map semantic information and the third geographic information with the second map semantic information and the second geographic information respectively, and determining the initial position of the current vehicle.
In one implementation, the matching the third map semantic information and the third geographic information with the second map semantic information and the second geographic information, respectively, and determining the initial position of the current vehicle may be implemented by: aligning the third map semantic information and the second map semantic information near each possible position according to the category of the semantic information, and aligning the third geographic information and the second geographic information near the possible position according to the category of the geographic information; and judging whether the error of the alignment result and the error of the alignment result is within an allowable range, and if so, taking the corresponding possible position as the initial position of the current vehicle.
In order to improve the accuracy of the determined initial position, when the semantic information in the local semantic information map of each possible position and the semantic information of the second map are aligned according to the category of the semantic information, the resolution of the semantic information maps can be set to be greater than the set resolution, so as to improve the accuracy of the determined initial position.
In the embodiment of the description, the initial position of the current vehicle is obtained by acquiring the rough position of the vehicle, the corresponding map semantic information and geographic information, the position of the vehicle and the map semantic information and geographic information near the vehicle, and matching the map semantic information and the geographic information of the vehicle and the map semantic information and the geographic information of the vehicle. The embodiment of the specification can complete positioning only by the surrounding environment information of the initial position of the vehicle, does not need to wait for a certain distance to run, and is high in matching efficiency.
FIG. 2 is a flow chart illustrating initialization of a vehicle locating system according to one embodiment of the present disclosure; as shown in fig. 2, the initialization process of the vehicle positioning system includes:
s1, starting the vehicle:
in response to a vehicle start, the positioning system is turned on and an initialization process is performed to determine the initial position of the vehicle.
S2, coarse position acquisition:
in acquiring the rough position of the vehicle, the rough position may be acquired by a sensor system equipped with the vehicle, including but not limited to: a method of using GPS satellite positioning, acquiring a position using WIFI, bluetooth, a cellular base station, or the like, using a position before a vehicle stops, using a preset position, or manually inputting a location of a trip to a user in a product function, or the like. Note that the above-mentioned means for obtaining the coarse position all include the coarse position and the corresponding possible error range.
For example, in the application scenario of automatic parking in an underground garage, a preset entrance position of the underground garage is used as the rough position of the vehicle.
S3, determining the initialization range and the corresponding map semantics and geographic information:
according to the rough position and the error range of the vehicle, an initialization algorithm search area is determined, a candidate position is set in the search area at intervals, high-precision map information in a map is extracted from each candidate position, and a local semantic information map is constructed. The local semantic information graph represents semantic information and corresponding geographic position information content included in the environment around the position calculated according to the map information. The semantic information depends on information contained in the high-precision map, including but not limited to information of road surfaces, lane lines, road signs, buildings, sidewalks, and the like. For example, in the scenario of an underground garage automatic parking application, the high-precision map contains all semantic information such as lane lines, garage lines, road signs, indicating arrows, sidewalks, and the like in the garage, and the precise geographic positions corresponding to the semantic information. Therefore, for any candidate position, a local semantic information map can be constructed, which represents the content of the semantic information of the area near the candidate position and the corresponding geographic position.
S4, extracting the map semantic information and the geographic information near the current vehicle:
when the method is implemented, data of a vehicle sensor can be acquired firstly, wherein the data comprises but is not limited to sensors such as a visible light camera, an infrared camera, a laser radar, a millimeter wave radar and ultrasonic waves; and then, semantic information is extracted by using the contents of the sensors to obtain a semantic information graph of actual observation. The content of the semantic information map is unified with the content of the semantic information map acquired in S2. For example, in an application scenario of automatic parking in an underground garage, a vehicle uses 4 fisheye cameras (1 in each of front, rear, left, and right) around the vehicle body as main sensors, and after semantic information and geographic position information thereof observed in each camera are obtained through machine learning and other manners, lane lines, garage lines, road signs, indication arrows, sidewalks of the surrounding environment actually observed by the vehicle at present can be obtained, and the semantic information graph actually observed by the vehicle is obtained as the geographic position information of various types of semantic information relative to the vehicle. In the prior art, the position of a vehicle in a map is often acquired by adopting GPS positioning and/or an inertial meter on the vehicle, on one hand, the positioning precision is not high, and on the other hand, in the environment such as an underground garage, the GPS signal is poor, so that accurate real-time geographic position information of the vehicle cannot be acquired. The invention adopts the mode of collecting the surrounding semantics of the vehicle to determine the geographical position information when acquiring the geographical position information, effectively overcomes the defects of low positioning precision and limited application, and is one of the innovation points of the invention.
And S5, roughly matching semantic information and geographic information (acquired by S4) near the vehicle with semantic information and geographic information (acquired by S3) of candidate positions in the initialization range, and narrowing the position range of the vehicle.
"matching" refers to attempting to align the semantic information of the same type in the semantic information map obtained at S3/S4, and finally evaluating the similarity thereof by the error between the two. The implementation of the matching algorithm set forth in the embodiments of the present description may be various and generally corresponds to a method in which the positioning system itself calculates its position from a map.
Since the search range may be very large at initialization, and it is very inefficient to perform exact matching one by one, it is necessary to narrow the location range of the vehicle using a rough but fast matching method. The present embodiment completes coarse matching by using low resolution matching. For example, it is assumed that the semantic information map acquired in step S4 is an image of 1000 × 1000 resolution (100 ten thousand pixels), and the semantic information map generated in the vicinity of each candidate position acquired in step S3 is also an image of 1000 × 1000 resolution. If there are 100 candidate positions, 100 times of registration of 100 ten thousand pixel images needs to be completed, and the calculation amount is large. During the course of the rough matching, down-sampling all pictures to 1/100 pixels (or other scales), i.e. 100 × 100(1 ten thousand pixels), can greatly improve the matching speed. Due to the reduction of the map precision, the precise position of the vehicle cannot be directly obtained, but 1 or more optimal matching candidate positions can be screened out through rough matching of the semantic information graph in the step.
S6, precisely matching the semantic information and the geographic information near the vehicle with the semantic information and the geographic information near the initialized candidate position, and determining the accurate position of the vehicle
On the basis of S5, the position of the vehicle is accurately measured by a method similar to S5, but using no lower resolution matching, but using a higher resolution matching calculation.
And S7, completing the initialization of the positioning system.
The present embodiment can acquire the initial accurate position of the vehicle in the high-accuracy map under various conditions. The method is not limited to some specific sensors, such as GPS, WIFI, Bluetooth and the like. Meanwhile, the positioning can be completed only by the surrounding environment information of the initial position, the vehicle does not need to wait for running for a distance, and the matching efficiency is high.
In accordance with the foregoing embodiment of the method for determining an initial position, fig. 3 is a block diagram of a vehicle-mounted terminal according to an embodiment of the present disclosure. As shown in fig. 3, the in-vehicle terminal 300 includes:
the first position information acquiring module 310 is configured to acquire a rough position of a current vehicle, and determine an initialization range and first map semantic information and first geographic information corresponding to the initialization range according to the rough position;
a second location information acquiring module 320 configured to acquire second geographic semantic information and second geographic information in the vicinity of the current vehicle;
a first location determining module 330, configured to match the first map semantic information and the first geographic information with the second map semantic information and the second geographic information, respectively, to obtain a possible location within the initialization range and third map semantic information and third geographic information near the possible location;
the second position determining module 340 is configured to match the third map semantic information and the third geographic information with the second map semantic information and the second geographic information, respectively, and determine an initial position of the current vehicle.
Optionally, the rough location is a location obtained through GPS, WIFI, bluetooth, or a cellular base station; or
The rough position is a pre-saved position before the vehicle stops; or
The coarse position is a preset position; or
The coarse location is a location of a user input.
Optionally, the first location information obtaining module includes:
a search area determining unit configured to determine an initial search area according to the coarse position and an error range corresponding to a type to which the coarse position belongs;
the candidate position determining unit is configured to set a candidate position in the search area at intervals of a set distance, extract map information of each candidate position from a map, and construct a corresponding local semantic information map based on the extracted map information, wherein the local semantic information map comprises map semantics and geographic information near the corresponding candidate position.
Optionally, the second position information obtaining module includes:
a sensing data acquisition unit configured to acquire sensing data of a vehicle sensor;
and the position information extraction unit is configured to extract semantic information of the sensing data to obtain a semantic information map actually observed nearby the vehicle, wherein the semantic information map comprises second geographic semantic information and second geographic information.
Optionally, the vehicle sensor includes at least one of a visible light camera, an infrared camera, a laser radar, a millimeter wave radar, and an ultrasonic sensor.
Optionally, the first position determining module includes:
a first alignment unit configured to align semantic information in the local semantic information map of each of the candidate positions and the second geographic semantic information according to a category of semantic information;
and the first position determining unit is configured to judge whether the error of the two is within an allowable range according to the alignment result, if so, the corresponding candidate position is taken as the possible position of the current vehicle, and the local map semantic information and the geographic information near the corresponding candidate position are taken as the third map semantic information and the third geographic information near the possible position.
Optionally, when the semantic information in the local semantic information map of each candidate position and the second semantic information are aligned according to the category of the semantic information, the resolution of the semantic information maps is not greater than the set resolution.
Optionally, the second position determining module includes:
a second alignment unit configured to align third map semantic information and the second map semantic information near each of the possible locations according to categories of semantic information, and align third geographic information and the second geographic information near the possible locations according to categories of geographic information;
and the second position determining unit is configured to judge whether the error of the two is within an allowable range according to the alignment result, and if so, the corresponding possible position is taken as the position of the current vehicle.
Optionally, when the semantic information in the local semantic information map of each possible location and the second semantic information are aligned according to the category of the semantic information, the resolution of the semantic information maps is greater than the set resolution.
In the embodiment of the description, the initial position of the current vehicle is obtained by acquiring the rough position of the vehicle, the corresponding map semantic information and geographic information, the position of the vehicle and the map semantic information and geographic information near the vehicle, and matching the map semantic information and the geographic information of the vehicle and the map semantic information and the geographic information of the vehicle. The embodiment of the specification can complete positioning only by the surrounding environment information of the initial position of the vehicle, does not need to wait for a certain distance to run, and is high in matching efficiency.
Those of ordinary skill in the art will understand that: the figures are merely schematic representations of one embodiment, and the blocks or processes in the figures are not necessarily required to practice this description.
Those of ordinary skill in the art will understand that: modules in the devices in the embodiments may be distributed in the devices in the embodiments according to the description of the embodiments, or may be located in one or more devices different from the embodiments with corresponding changes. The modules of the above embodiments may be combined into one module, or further split into multiple sub-modules.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solutions of the present specification, and not to limit them; although the present description has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the spirit and scope of the technical solutions of the embodiments of the present specification.
Claims (10)
1. A method for determining an initial position, comprising the steps of:
acquiring a rough position of a current vehicle, and determining an initialization range and first map semantic information and first geographic information corresponding to the initialization range according to the rough position;
acquiring second geographic semantic information and second geographic information near the current vehicle;
matching the first map semantic information and the first geographic information with the second map semantic information and the second geographic information respectively to obtain a possible position in the initialization range and third map semantic information and third geographic information near the possible position;
and matching the third map semantic information and the third geographic information with the second map semantic information and the second geographic information respectively to determine the initial position of the current vehicle.
2. The determination method according to claim 1, wherein the rough location is a location acquired through GPS, WIFI, bluetooth or cellular base station; or
The rough position is a pre-saved position before the vehicle stops; or
The coarse position is a preset position; or
The coarse location is a location of a user input.
3. The method according to any one of claims 1-2, wherein the determining an initialization range and first map semantic information and first geographic information corresponding to the initialization range according to the rough location comprises:
determining an initial search area according to the rough position and an error range corresponding to the type of the rough position;
setting a candidate position at intervals of a set distance in the search area, extracting map information of each candidate position from a map, and constructing a corresponding local semantic information map based on the extracted map information, wherein the local semantic information map comprises map semantics and geographic information near the corresponding candidate position.
4. The determination method according to any one of claims 1 to 3, wherein the acquiring of the second geographic semantic information and the second geographic information in the vicinity of the current vehicle includes:
acquiring sensing data of a vehicle sensor;
and extracting semantic information from the sensing data to obtain a semantic information map actually observed nearby the vehicle, wherein the semantic information map comprises second geographic semantic information and second geographic information.
5. The determination method according to any one of claims 1 to 4, characterized in that the vehicle sensor comprises at least one of a visible light camera, an infrared camera, a lidar, a millimeter wave radar, an ultrasonic sensor.
6. The method according to any one of claims 1 to 5, wherein the matching the first map semantic information and the first geographic information with the second map semantic information and the second geographic information respectively to obtain a possible location within the initialization range and third map semantic information and third geographic information near the possible location comprises:
aligning semantic information in the local semantic information map of each candidate position with the semantic information of the second map according to the category of the semantic information;
and judging whether the error of the two is within an allowable range according to the alignment result, if so, taking the corresponding candidate position as the possible position of the current vehicle, and taking the local map semantic information and the geographic information near the corresponding candidate position as the third map semantic information and the third geographic information near the possible position.
7. The method according to any one of claims 1 to 6, wherein when the semantic information in the local semantic information map of each of the candidate locations and the second semantic information are aligned according to the category of the semantic information, the resolution of the semantic information maps is not greater than a set resolution.
8. The method according to any one of claims 1 to 7, wherein the matching the third map semantic information and the third geographic information with the second map semantic information and the second geographic information respectively, and the determining the initial position of the current vehicle comprises:
aligning the third map semantic information and the second map semantic information near each possible position according to the category of the semantic information, and aligning the third geographic information and the second geographic information near the possible position according to the category of the geographic information;
and judging whether the error of the alignment result and the error of the alignment result is within an allowable range, and if so, taking the corresponding possible position as the initial position of the current vehicle.
9. The method according to any one of claims 1 to 8, wherein when the semantic information in the local semantic information map of each of the possible locations and the second semantic information are aligned according to the category of the semantic information, the resolution of the semantic information maps is greater than a set resolution.
10. A vehicle-mounted terminal characterized by comprising:
the first position information acquisition module is configured to acquire a rough position of a current vehicle, and determine an initialization range and first map semantic information and first geographic information corresponding to the initialization range according to the rough position;
the second position information acquisition module is configured to acquire second map semantic information and second geographic information near the current vehicle;
a first position determination module configured to match the first map semantic information and the first geographic information with the second map semantic information and the second geographic information, respectively, to obtain a possible position within the initialization range and third map semantic information and third geographic information near the possible position;
and the second position determining module is configured to match the third map semantic information and the third geographic information with the second map semantic information and the second geographic information respectively, and determine an initial position of the current vehicle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811538402.1A CN111323004B (en) | 2018-12-16 | 2018-12-16 | Initial position determining method and vehicle-mounted terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811538402.1A CN111323004B (en) | 2018-12-16 | 2018-12-16 | Initial position determining method and vehicle-mounted terminal |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111323004A true CN111323004A (en) | 2020-06-23 |
| CN111323004B CN111323004B (en) | 2022-05-13 |
Family
ID=71166700
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811538402.1A Active CN111323004B (en) | 2018-12-16 | 2018-12-16 | Initial position determining method and vehicle-mounted terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111323004B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113515126A (en) * | 2021-07-12 | 2021-10-19 | 北京经纬恒润科技股份有限公司 | Vehicle positioning method and device |
| DE102020134119B3 (en) | 2020-12-18 | 2021-12-23 | Audi Aktiengesellschaft | Method for localizing a motor vehicle in an assistance card, motor vehicle, computer program and electronically readable data carrier |
| WO2022041706A1 (en) * | 2020-08-28 | 2022-03-03 | 华为技术有限公司 | Positioning method, positioning system, and vehicle |
| WO2022062019A1 (en) * | 2020-09-27 | 2022-03-31 | 驭势科技（北京）有限公司 | Map matching method and apparatus, and electronic device and storage medium |
| CN113515126B (en) * | 2021-07-12 | 2024-05-10 | 北京经纬恒润科技股份有限公司 | Vehicle positioning method and device |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102542302A (en) * | 2010-12-21 | 2012-07-04 | 中国科学院电子学研究所 | Automatic complicated target identification method based on hierarchical object semantic graph |
| CN106525025A (en) * | 2016-10-28 | 2017-03-22 | 武汉大学 | Transformer substation inspection robot path planning navigation method |
| CN107144285A (en) * | 2017-05-08 | 2017-09-08 | 深圳地平线机器人科技有限公司 | Posture information determines method, device and movable equipment |
| CN107831765A (en) * | 2017-10-23 | 2018-03-23 | 广州视源电子科技股份有限公司 | Localization method, device, equipment and storage medium |
| CN108089572A (en) * | 2016-11-23 | 2018-05-29 | 百度（美国）有限责任公司 | For the algorithm and infrastructure of steady and effective vehicle location |
| US20180268566A1 (en) * | 2017-03-14 | 2018-09-20 | Ford Global Technologies, Llc | Vehicle Localization Using Cameras |
| CN108759833A (en) * | 2018-04-25 | 2018-11-06 | 中国科学院合肥物质科学研究院 | A kind of intelligent vehicle localization method based on priori map |
| CN108920584A (en) * | 2018-06-25 | 2018-11-30 | 广州视源电子科技股份有限公司 | A kind of semanteme grating map generation method and its device |
-
2018
- 2018-12-16 CN CN201811538402.1A patent/CN111323004B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102542302A (en) * | 2010-12-21 | 2012-07-04 | 中国科学院电子学研究所 | Automatic complicated target identification method based on hierarchical object semantic graph |
| CN106525025A (en) * | 2016-10-28 | 2017-03-22 | 武汉大学 | Transformer substation inspection robot path planning navigation method |
| CN108089572A (en) * | 2016-11-23 | 2018-05-29 | 百度（美国）有限责任公司 | For the algorithm and infrastructure of steady and effective vehicle location |
| US20180268566A1 (en) * | 2017-03-14 | 2018-09-20 | Ford Global Technologies, Llc | Vehicle Localization Using Cameras |
| CN107144285A (en) * | 2017-05-08 | 2017-09-08 | 深圳地平线机器人科技有限公司 | Posture information determines method, device and movable equipment |
| CN107831765A (en) * | 2017-10-23 | 2018-03-23 | 广州视源电子科技股份有限公司 | Localization method, device, equipment and storage medium |
| CN108759833A (en) * | 2018-04-25 | 2018-11-06 | 中国科学院合肥物质科学研究院 | A kind of intelligent vehicle localization method based on priori map |
| CN108920584A (en) * | 2018-06-25 | 2018-11-30 | 广州视源电子科技股份有限公司 | A kind of semanteme grating map generation method and its device |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022041706A1 (en) * | 2020-08-28 | 2022-03-03 | 华为技术有限公司 | Positioning method, positioning system, and vehicle |
| WO2022062019A1 (en) * | 2020-09-27 | 2022-03-31 | 驭势科技（北京）有限公司 | Map matching method and apparatus, and electronic device and storage medium |
| DE102020134119B3 (en) | 2020-12-18 | 2021-12-23 | Audi Aktiengesellschaft | Method for localizing a motor vehicle in an assistance card, motor vehicle, computer program and electronically readable data carrier |
| CN113515126A (en) * | 2021-07-12 | 2021-10-19 | 北京经纬恒润科技股份有限公司 | Vehicle positioning method and device |
| CN113515126B (en) * | 2021-07-12 | 2024-05-10 | 北京经纬恒润科技股份有限公司 | Vehicle positioning method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111323004B (en) | 2022-05-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3637371B1 (en) | Map data correcting method and device | |
| CN107643086B (en) | Vehicle positioning method, device and system | |
| JP5901779B2 (en) | How to move data from image database map service into assist system | |
| JP4847090B2 (en) | Position positioning device and position positioning method | |
| US9396541B2 (en) | Positioning control method | |
| CN111323004B (en) | Initial position determining method and vehicle-mounted terminal | |
| US10996072B2 (en) | Systems and methods for updating a high-definition map | |
| US10928819B2 (en) | Method and apparatus for comparing relevant information between sensor measurements | |
| CN111275960A (en) | Traffic road condition analysis method, system and camera | |
| CN110906939A (en) | Automatic driving positioning method and device, electronic equipment, storage medium and automobile | |
| CN109983303B (en) | Updating method of electronic map | |
| KR20120079341A (en) | Method, electronic device and recorded medium for updating map data | |
| CN110018503B (en) | Vehicle positioning method and positioning system | |
| CN115164918B (en) | Semantic point cloud map construction method and device and electronic equipment | |
| CN111323029B (en) | Navigation method and vehicle-mounted terminal | |
| CN113892275A (en) | Positioning method, positioning device, electronic equipment and storage medium | |
| US20210375135A1 (en) | Method for indicating parking position and vehicle-mounted device | |
| CN106840181B (en) | System and method for determining vehicle position | |
| JP4312093B2 (en) | Navigation device, navigation method, and navigation program | |
| CN112837365B (en) | Image-based vehicle positioning method and device | |
| CN113566824A (en) | Vehicle positioning method and device, electronic equipment and storage medium | |
| CN114761830A (en) | Global positioning system positioning method and computer program product | |
| CN115187762B (en) | Vehicle map rendering method and device, vehicle and storage medium | |
| CN116503482B (en) | Vehicle position acquisition method and device and electronic equipment | |
| JP5644634B2 (en) | Vehicle information acquisition device, vehicle information acquisition method and program |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220303 Address after: 100083 unit 501, block AB, Dongsheng building, No. 8, Zhongguancun East Road, Haidian District, Beijing Applicant after: BEIJING MOMENTA TECHNOLOGY Co.,Ltd. Address before: Room 28, 4 / F, block a, Dongsheng building, No. 8, Zhongguancun East Road, Haidian District, Beijing 100089 Applicant before: BEIJING CHUSUDU TECHNOLOGY Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |