WO2022077660A1 - 一种车辆定位的方法和装置 - Google Patents

一种车辆定位的方法和装置 Download PDF

Info

Publication number
WO2022077660A1
WO2022077660A1 PCT/CN2020/126931 CN2020126931W WO2022077660A1 WO 2022077660 A1 WO2022077660 A1 WO 2022077660A1 CN 2020126931 W CN2020126931 W CN 2020126931W WO 2022077660 A1 WO2022077660 A1 WO 2022077660A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
semantic element
semantic
position information
map data
Prior art date
Application number
PCT/CN2020/126931
Other languages
English (en)
French (fr)
Inventor
李红军
刘中元
柴文楠
黄亚
Original Assignee
广州小鹏自动驾驶科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 广州小鹏自动驾驶科技有限公司 filed Critical 广州小鹏自动驾驶科技有限公司
Priority to EP20957438.3A priority Critical patent/EP4123263A4/en
Publication of WO2022077660A1 publication Critical patent/WO2022077660A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01SRADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S7/00Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
    • G01S7/52Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S15/00
    • G01S7/523Details of pulse systems
    • G01S7/526Receivers
    • G01S7/53Means for transforming coordinates or for evaluating data, e.g. using computers
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01CMEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/28Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network with correlation of data from several navigational instruments
    • G01C21/30Map- or contour-matching
    • G01C21/32Structuring or formatting of map data
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01CMEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/005Navigation; 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
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01CMEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34Route searching; Route guidance
    • G01C21/3407Route searching; Route guidance specially adapted for specific applications
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01SRADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S15/00Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems
    • G01S15/02Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems using reflection of acoustic waves
    • G01S15/06Systems determining the position data of a target
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01SRADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S15/00Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems
    • G01S15/86Combinations of sonar systems with lidar systems; Combinations of sonar systems with systems not using wave reflection
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01SRADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S15/00Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems
    • G01S15/88Sonar systems specially adapted for specific applications
    • G01S15/89Sonar systems specially adapted for specific applications for mapping or imaging
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01SRADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S17/00Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/02Systems using the reflection of electromagnetic waves other than radio waves
    • G01S17/06Systems determining position data of a target
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01SRADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S17/00Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/86Combinations of lidar systems with systems other than lidar, radar or sonar, e.g. with direction finders
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01SRADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S19/00Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
    • G01S19/38Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
    • G01S19/39Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
    • G01S19/42Determining position
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01SRADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S5/00Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
    • G01S5/16Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using electromagnetic waves other than radio waves

Definitions

  • the present invention relates to the technical field of positioning, and in particular, to a method and device for vehicle positioning.
  • the vehicle can collect information around the vehicle, such as lane lines, parking spaces, etc., and then can locate according to the feature points in the collected information.
  • the collected feature points There are not many of them, which leads to deviations in positioning only based on feature points.
  • a feature point contains not much information, so it is difficult to completely represent the information collected by the vehicle, resulting in inaccurate positioning.
  • a method for locating a vehicle comprising:
  • the optimal position information of the vehicle is determined.
  • the first semantic element includes a first point semantic element
  • the determining the first direction information corresponding to the first semantic element includes:
  • the second semantic element includes a second point semantic element, and the determining the second direction information corresponding to the second semantic element includes:
  • second direction information corresponding to the second point semantic element is determined.
  • the first semantic element includes a first line semantic element
  • the first position information includes first lateral position information
  • the determining the first position information corresponding to the first semantic element includes:
  • the second semantic element includes a second line semantic element
  • the second position information includes second lateral position information
  • the determining the second position information corresponding to the second semantic element includes:
  • second lateral position information corresponding to the second line semantic element is determined.
  • the determining the optimal heading information of the vehicle according to the first direction information and the second direction information includes:
  • the first direction information and the second direction information determine the direction information for the point semantic element and the direction information for the line semantic element
  • the optimal heading information of the vehicle is determined by combining the direction information for the point semantic element, the direction information for the line semantic element, and the direction weight information.
  • the determining the optimal location information of the vehicle according to the first location information, the second location information, and the optimal heading information includes:
  • the first position information, the second position information, and the optimal heading information determine the position information for the point semantic element and the position information for the line semantic element
  • the optimal heading information of the vehicle is determined by combining the position information for the point semantic element, the position information for the line semantic element, and the position weight information.
  • determining the first semantic element according to the first map data includes:
  • For the first shape semantic element in the first map data generating a first point semantic element and a first line semantic element corresponding to the first shape semantic element;
  • the determining of the second semantic element according to the second map data includes:
  • a second point semantic element and a second line semantic element corresponding to the second shape semantic element are generated.
  • the optimal heading information and the optimal position information are updated according to the filtered first semantic element and the second semantic element.
  • a device for positioning a vehicle comprising:
  • a map data acquisition module for acquiring the preset first map data and the second map data collected in real time
  • a first semantic element determination module configured to determine a first semantic element according to the first map data, and determine first direction information and first location information corresponding to the first semantic element;
  • a second semantic element determination module configured to determine a second semantic element according to the second map data, and determine second direction information and second location information corresponding to the second semantic element;
  • an optimal heading information determination module configured to determine the optimal heading information of the vehicle according to the first direction information and the second direction information
  • the optimal position information determination module is configured to determine the optimal position information of the vehicle according to the first position information, the second position information, and the optimal heading information.
  • a vehicle comprising a processor, a memory, and a computer program stored on the memory and capable of running on the processor, the computer program being executed by the processor to implement the above-mentioned vehicle positioning method. method.
  • a computer-readable storage medium storing a computer program on the computer-readable storage medium, when the computer program is executed by a processor, implements the above-mentioned method for locating a vehicle.
  • the preset first map data and the second map data collected in real time are acquired; the first semantic element is determined according to the first map data, and the first direction information and the corresponding first semantic element are determined.
  • the first position information according to the second map data, determine the second semantic element, and determine the second direction information and the second position information corresponding to the second semantic element;
  • Optimal heading information according to the first position information, the second position information, and the optimal heading information, the optimal position information of the vehicle is determined, which realizes the determination of the optimal heading information and the optimal position information, and is based on the optimal heading information and the optimal heading information.
  • the optimal position information for positioning reduces the error of vehicle positioning and improves the accuracy of vehicle positioning.
  • FIG. 1a is a flowchart of steps of a method for vehicle positioning provided by an embodiment of the present invention
  • Fig. 1b is a schematic diagram of classification of semantic elements provided by an embodiment of the present invention.
  • FIG. 2 is a flowchart of steps of another vehicle positioning method provided by an embodiment of the present invention.
  • Fig. 3a is a flow chart of the steps of another vehicle positioning method provided by an embodiment of the present invention.
  • FIG. 3b is a schematic diagram of screening of semantic elements according to an embodiment of the present invention
  • FIG. 4 is a schematic diagram of an example of a method for positioning a vehicle according to an embodiment of the present invention.
  • FIG. 5 is a schematic structural diagram of an apparatus for positioning a vehicle according to an embodiment of the present invention.
  • FIG. 1a a flowchart of steps of a method for vehicle positioning provided by an embodiment of the present invention is shown, which may specifically include the following steps:
  • Step 101 obtaining preset first map data and real-time collected second map data
  • the first map data and the second map data may be map data for the parking lot
  • the first map data may be a semantic map that has undergone multiple fusions in the server
  • the second map data may be a semantic map collected by vehicles in real time.
  • the map may be a map including one or more semantic elements, and the semantic elements may include lane lines, parking spaces, roadblocks, speed bumps, and the like.
  • the first map data may be a static map
  • the second map data may be a real-time perception map
  • the location function in the vehicle such as GPS (Global Positioning System, Global Positioning System) function, can be used to determine the area where the vehicle is located, and then the semantic map of the area can be obtained from the server. Get multiple semantic maps to call the semantic map of the area after determining the area where the vehicle is located.
  • GPS Global Positioning System, Global Positioning System
  • the semantic elements of the area where the vehicle is located can be collected in real time through the sensing device in the vehicle, and then a semantic map can be generated according to the semantic elements, that is, the second map data is generated.
  • the sensing device may include an ultrasonic sensor, an infrared sensor, a camera, and the like.
  • the sensing device may have a certain collection range, for example, the collection range may be 25 meters, and the collected semantic elements may be semantic elements within 25 meters.
  • Step 102 Determine a first semantic element according to the first map data, and determine first direction information and first position information corresponding to the first semantic element;
  • all semantic elements in the second map data can be determined, and further, in the first map data, semantic elements matching the semantic elements in the second map data can be determined.
  • the first map data can be a map for the area where the vehicle is located, such as a parking lot
  • all semantic elements in the area where the vehicle is located can be determined
  • the second map data can be a map collected by the vehicle in real time. If the device has a certain perception range, the semantic elements within the perception range are determined in the map collected by the vehicle in real time, that is, the semantic elements in the second map data should be less than or equal to the semantic elements in the first map data, and then the semantic elements in the first map data can be Among all the semantic elements in the first map data, a semantic element matching the semantic element in the second map data is determined.
  • any one of the matched semantic elements in the first map data can be determined, and then the direction information and position information of the matched semantic element can be determined.
  • a coordinate system may be set in the first map data, and then the coordinate information of the semantic element in the coordinate system may be determined, and the direction information and position information of the semantic element may be determined according to the coordinate information, wherein the direction information may be The angle information of the semantic element in the coordinate system.
  • the semantic elements may include point semantic elements and line semantic elements.
  • a semantic point may be a point semantic element
  • a semantic line may be a line semantic element.
  • the first semantic element may include a first point semantic element, and the direction information and position information of the first point semantic element may be determined respectively, and step 102 may include the following sub-steps:
  • Sub-step 11 determining the first center of gravity information corresponding to a plurality of point semantic elements including the first point semantic element
  • the point semantic elements may include semantic elements such as corner points of the parking space, and the center of gravity information may be a point with the shortest distance from the multiple point semantic elements.
  • the first semantic element can include the first point semantic element
  • the first point semantic element in the first semantic element can be determined, and then all the point semantic elements in the first map data can be determined, And the corresponding center of gravity information is determined according to the coordinate information of all point semantic elements.
  • the center of gravity information can be determined by the following formula:
  • pi can be the coordinate information of the point semantic element i in the first map data
  • n can be expressed as the number of matching point semantic elements, that is, there can be n point semantic elements in the first map data
  • G can be expressed as The center of gravity of all point semantic elements in the first map data.
  • Sub-step 12 according to the first center of gravity information, determine first direction information corresponding to the first point semantic element.
  • the direction vector of the point semantic element can be determined according to the center of gravity information and the coordinate information of the point semantic element, that is, the direction information of the point semantic element. Specifically, it can be determined by the following formula:
  • qi may be vector information of point semantic element i in the first map data, that is, direction information.
  • the location information of the point semantic element in the first map data may be determined according to the coordinate information of the point semantic element in the first map data, for example, the location of the point semantic element in the first map data
  • the information may be coordinate information of point semantic elements in the first map data.
  • the first semantic element may include a first line semantic element, and the direction information and position information of the first line semantic element may be determined respectively, and step 102 may include the following sub-steps:
  • Sub-step 21 determining the first midpoint position information corresponding to the first line semantic element
  • the line semantic elements may include semantic elements such as a parking space's library line, roadblocks, and the like.
  • the first semantic element may include the first line semantic element
  • the first line semantic element in the first semantic element can be determined, and then the coordinates of the midpoint in the first line semantic element can be determined information, that is, the location information of the midpoint.
  • Sub-step 22 Determine first lateral position information corresponding to the first line semantic element according to the first midpoint position information.
  • the horizontal coordinate information of the midpoint can be determined according to the coordinate information of the midpoint.
  • the coordinate information of the midpoint can include abscissa information and ordinate information, and then the horizontal coordinate information of the midpoint can be determined.
  • the coordinate information is first lateral position information.
  • the direction information of the second line semantic element may be vector information of the line semantic element, and the vector information may be determined by position information of a plurality of points in the line semantic element.
  • the semantic element may further include a shape semantic element
  • step 102 may include the following sub-steps:
  • Sub-step 31 classify the semantic elements in the first map data
  • point semantic elements, line semantic elements, and shape semantic elements can be determined, and classified according to different types of semantic elements.
  • the semantic point shape may be a shape semantic element
  • the first map data may include point semantic element 1, point semantic element 2, line semantic element 1, line semantic element 2, shape semantic element 1, shape semantic element 2 , shape semantic element 3, and then it can be determined that point semantic element 1 and point semantic element 2 are one type, line semantic element 1 and line semantic element 2 are one type, and shape semantic element 1, shape semantic element 3 and shape semantic element 2 are one type.
  • Sub-step 32 for the first shape semantic element in the first map data, generate a first point semantic element and a first line semantic element corresponding to the first shape semantic element.
  • any shape semantic element can be decomposed to determine the point and line in the shape semantic element, and then point semantic element and line semantic element can be generated according to the point and line in the shape semantic element.
  • shape semantic element 1 can be a rectangle, and then the rectangle can be decomposed into 4 points and 4 lines, and 4 point semantic elements and 4 line semantic elements can be generated according to the 4 points and 4 lines.
  • the positioning is performed according to the feature points in the collected information. Even if the collected information is information of a specific shape, such as a rectangular parking space, only the feature points in the information of the specific shape are determined for positioning, such as Positioning is performed according to the center point of the rectangular parking space, and the positioning accuracy is low. However, by determining the points and lines in the information of a specific shape, and using the points and lines for positioning, the positioning accuracy can be improved.
  • Step 103 according to the second map data, determine the second semantic element, and determine the second direction information and the second position information corresponding to the second semantic element;
  • all semantic elements in the second map data can be determined, and further, in the first map data, semantic elements matching the semantic elements in the second map data can be determined.
  • the first map data can be a map for the area where the vehicle is located, such as a parking lot
  • all semantic elements in the area where the vehicle is located can be determined
  • the second map data can be a map collected by the vehicle in real time. If the device has a certain perception range, the semantic elements within the perception range are determined in the map collected by the vehicle in real time, that is, the semantic elements in the second map data should be less than or equal to the semantic elements in the first map data, and then the semantic elements in the first map data can be Among all the semantic elements in the first map data, a semantic element matching the semantic element in the second map data is determined.
  • any one of the matched semantic elements in the first map data can be determined, and then the direction information and position information of the matched semantic element can be determined.
  • a coordinate system may be set in the first map data, and then the coordinate information of the semantic element in the coordinate system may be determined, and the direction information and position information of the semantic element may be determined according to the coordinate information, wherein the direction information may be The angle information of the semantic element in the coordinate system.
  • the semantic elements may include point semantic elements and line semantic elements.
  • a semantic point may be a point semantic element
  • a semantic line may be a line semantic element.
  • the second semantic element may include a second point semantic element, and the direction information and position information of the second point semantic element may be determined respectively.
  • Step 102 may include the following sub-steps:
  • Sub-step 41 determining the second center of gravity information corresponding to a plurality of point semantic elements including the second point semantic element
  • the second semantic element can include the second point semantic element
  • the second point semantic element in the second semantic element can be determined, and then all the point semantic elements in the second map data can be determined, And the corresponding center of gravity information is determined according to the coordinate information of all point semantic elements.
  • the center of gravity information can be determined by the following formula:
  • p i ' can be the coordinate information of the point semantic element i in the second map data
  • n can be expressed as the number of matching point semantic elements, that is, there can be n point semantic elements in the first map data
  • G' can be Represented as the center of gravity of all point semantic elements in the second map data.
  • Sub-step 42 according to the second center of gravity information, determine second direction information corresponding to the second point semantic element.
  • the direction vector of the point semantic element can be determined according to the center of gravity information and the coordinate information of the point semantic element, that is, the direction information of the point semantic element. Specifically, it can be determined by the following formula:
  • qi ' may be the vector information of the point semantic element i in the second map data, that is, direction information
  • pi ' may be the coordinate information of the point semantic element i in the second map data.
  • the location information of the point semantic element in the second map data may be determined according to the coordinate information of the point semantic element in the second map data, for example, the location of the point semantic element in the second map data
  • the information may be coordinate information of point semantic elements in the second map data.
  • the second semantic element may include a second line semantic element, and the direction information and position information of the second line semantic element may be determined respectively, and step 102 may include the following sub-steps:
  • Sub-step 51 determining the second midpoint position information corresponding to the second line semantic element
  • the line semantic elements may include semantic elements such as a parking space's library line, roadblocks, and the like.
  • the second semantic element can include the second line semantic element
  • the second line semantic element in the second semantic element can be determined, and then the coordinate information of the midpoint in the second line semantic element can be determined, and the That is the location information of the midpoint.
  • Sub-step 52 Determine second lateral position information corresponding to the second line semantic element according to the second midpoint position information.
  • the horizontal coordinate information of the midpoint can be determined according to the coordinate information of the midpoint.
  • the coordinate information of the midpoint can include abscissa information and ordinate information, and then the horizontal coordinate information of the midpoint can be determined.
  • the coordinate information is the second lateral position information.
  • the direction information of the second line semantic element may be vector information of the line semantic element, and the vector information may be determined by position information of a plurality of points in the line semantic element.
  • the second semantic element includes a second point semantic element and a second line semantic element
  • step 103 may include the following sub-steps:
  • Sub-step 61 classify the semantic elements in the second map data
  • point semantic elements, line semantic elements, and shape semantic elements can be determined and classified according to different types of semantic elements.
  • Sub-step 62 for the second shape semantic element in the second map data, generate a second point semantic element and a second line semantic element corresponding to the second shape semantic element.
  • any shape semantic element can be decomposed to determine the point and line in the shape semantic element, and then point semantic element and line semantic element can be generated according to the point and line in the shape semantic element.
  • Step 104 Determine the optimal heading information of the vehicle according to the first direction information and the second direction information;
  • the first direction information and the second direction information can be combined to determine the angle deflection information of the second semantic element, that is, the semantics of real-time perception is determined.
  • the angle deflection information of the element, and then the second semantic element can be deflected according to the angle conversion information to determine the optimal heading information of the vehicle in the first map data.
  • the optimal heading information of the vehicle can be determined according to the direction information of the point semantic element, which can be determined by the following formula:
  • F p theta may be the optimal heading information of the point semantic element
  • pi ' may be the coordinate information of the point semantic element i in the second map data
  • pi may be the positional information of the point semantic element i in the first map data
  • G can be expressed as the center of gravity of all point semantic elements in the first map data
  • G' can be expressed as the center of gravity of all point semantic elements in the second map data
  • R can be for different matching point semantic elements
  • the transformation matrix of that is, the angle deflection information, the matrix can be determined according to the coordinate information of the point semantic elements
  • min J can be the overall error of the point semantic elements.
  • the transformation matrix when the overall error of the point semantic elements is the smallest can be determined, and then all the second semantic elements can be deflected according to the transformation matrix to determine the optimal heading information of the vehicle in the first map data .
  • the optimal heading information of the vehicle can be determined according to the direction information of the line semantic element, which can be determined by the following formula:
  • F l theta may be the optimal direction information of the line semantic element
  • v i may be the line semantic element i in the first map data
  • v i ' may be the line semantic element i in the second map data
  • n may represent is the number of matching line semantic elements
  • R can be the transformation matrix for different matching line semantic elements, that is, the angle deflection information, the matrix can be determined according to the position information of the line semantic elements
  • min J can be the line semantic element the overall error.
  • the conversion matrix when the overall error of the online semantic elements is the smallest can be determined, and then all the second semantic elements can be deflected according to the conversion matrix to determine the optimal heading information of the vehicle in the first map data.
  • Step 105 Determine the optimal position information of the vehicle according to the first position information, the second position information, and the optimal heading information.
  • the position offset information of the second semantic element can be determined by combining the first position information and the second position information of a plurality of matched semantic elements, that is, the real-time perception is determined.
  • the position offset information of the semantic element, and then the second semantic element can be displaced according to the position offset information to determine the optimal position information of the vehicle in the first map data.
  • the optimal position information of the vehicle can be determined according to the position information of the point semantic element, which can be determined by the following formula:
  • F p loc can be the optimal location information of point semantic elements
  • G can be expressed as the center of gravity of all point semantic elements in the first map data
  • G' can be expressed as the center of gravity of all point semantic elements in the second map data
  • R can be the transformation matrix for different matching point semantic elements, that is, angle deflection information
  • the matrix can be determined according to the coordinate information of the point semantic element
  • t can be the displacement amount for different matching point semantic elements , that is, the position offset information
  • the value of the displacement can be determined according to the coordinate information of the point semantic element
  • min J can be the overall error of the point semantic element.
  • the displacement amount when the overall error of the point semantic elements is the smallest can be determined, and then all the second semantic elements can be displaced according to the displacement amount to determine the optimal position information of the vehicle in the first map data .
  • the optimal position information of the vehicle can be determined according to the lateral position information of the line semantic element, which can be determined by the following formula:
  • F l loc can be the optimal horizontal position information of the line semantic element
  • a i can be the horizontal position information of the line semantic element in the first map data
  • a i ′ can be the horizontal position information of the line semantic element in the second map data
  • R can be the transformation matrix for different matching line semantic elements, that is, angle deflection information
  • the matrix can be determined according to the lateral position information of the line semantic elements
  • t can be the displacement amount for different matching point semantic elements , that is, the position offset information
  • the value of the displacement can be determined according to the coordinate information of the point semantic element
  • min J can be the overall error of the point semantic element.
  • the displacement amount when the overall error of the online semantic elements is the smallest can be determined, and then all the second semantic elements can be displaced according to the displacement amount to determine the optimal lateral position information of the vehicle in the first map data .
  • the preset first map data and the second map data collected in real time are acquired; the first semantic element is determined according to the first map data, and the first direction information and the first semantic element corresponding to the first semantic element are determined.
  • a position information according to the second map data, determine the second semantic element, and determine the second direction information and the second position information corresponding to the second semantic element; according to the first direction information and the second direction information, determine the optimal vehicle Heading information; according to the first position information, the second position information, and the optimal heading information, determine the optimal position information of the vehicle, realize the determination of the optimal heading information and the optimal position information, and based on the optimal heading information and the optimal heading information. Locating with optimal location information reduces the error of vehicle location and improves the accuracy of vehicle location.
  • FIG. 2 a flowchart of steps of another vehicle positioning method provided by an embodiment of the present invention is shown, which may specifically include the following steps:
  • Step 201 obtaining preset first map data and real-time collected second map data
  • Step 202 determining a first semantic element according to the first map data, and determining first direction information and first position information corresponding to the first semantic element;
  • Step 203 according to the second map data, determine the second semantic element, and determine the second direction information and the second position information corresponding to the second semantic element;
  • Step 204 determine the direction information for the point semantic element and the direction information for the line semantic element;
  • all matching point semantic elements in the first map data can be determined, and the corresponding center of gravity can be determined according to all the point semantic elements, and then the direction information of the point semantic element can be determined according to the center of gravity, which can be specifically F p theta .
  • the vector information of the line semantic element may be determined by the position information of multiple points in the line semantic element, which may be specifically F l theta .
  • Step 205 determining the direction weight information corresponding to the direction information of the line semantic element
  • the weight information of the direction information of the line semantic element can be determined according to the collection range of the sensing device in the vehicle. For example, if the collection range can be 25 meters, the weight information of the direction information of the line semantic element can be 1.5 .
  • Step 206 Determine the optimal heading information of the vehicle in combination with the direction information for the point semantic element, the direction information for the line semantic element, and the direction weight information;
  • the direction information of the point semantic element, the direction information for the line semantic element, and the direction weight information can be combined to determine the optimal heading information of the vehicle.
  • the optimal heading information can be determined by the following formula:
  • F theta may be the optimal heading information obtained based on the direction weight information
  • ⁇ 1 may be the direction weight information
  • Step 207 according to the first position information, the second position information, and the optimal heading information, determine the position information for the point semantic element and the position information for the line semantic element;
  • the location information of the point semantic element can be determined according to the coordinate information of the point semantic element and the optimal heading information, which can be specifically F p loc .
  • the heading information determines the lateral position information of the line semantic element, and may specifically be Fl loc .
  • Step 208 determining the position weight information corresponding to the position information of the line semantic element
  • the weight information of the lateral position information of the line semantic element can be determined according to the collection range of the sensing device in the vehicle.
  • the collection range can be 25 meters
  • the weight information of the direction information of the line semantic element can be is 1.
  • Step 209 Determine the optimal heading information of the vehicle by combining the position information for the point semantic element, the position information for the line semantic element, and the position weight information.
  • the position information of the point semantic element, the lateral position information for the line semantic element, and the position weight information can be combined to determine the optimal position information of the vehicle.
  • the optimal position information can be determined by the following formula:
  • F loc F p_loc + ⁇ 2*F l_loc
  • F loc may be the optimal position information obtained based on the direction weight information
  • ⁇ 2 may be the position weight information
  • the optimal heading information of the vehicle can be determined based on the optimal heading information and the optimal position information, that is, the positioning of the vehicle can be determined in the first map data according to the optimal heading information and the optimal position information information.
  • the preset first map data and the second map data collected in real time are acquired, the first semantic element is determined according to the first map data, and the first direction information and the first semantic element corresponding to the first semantic element are determined.
  • a position information according to the second map data, determine the second semantic element, and determine the second direction information and the second position information corresponding to the second semantic element, and determine the point semantic element according to the first direction information and the second direction information
  • the direction information for the line semantic element and the direction information for the line semantic element are determined, the direction weight information corresponding to the direction information for the line semantic element is determined, and the direction information for the point semantic element, the direction information for the line semantic element, and the direction weight information are combined to determine the vehicle.
  • the first position information, the second position information, and the optimal heading information determine the position information for the point semantic element and the position information for the line semantic element, and determine the corresponding
  • the position weight information combined with the position information for point semantic elements, the position information for line semantic elements, and the position weight information, determines the optimal heading information of the vehicle, and realizes the determination of optimal heading information and optimal position information based on points and lines. , which improves the accuracy of the optimal heading information and the optimal position information, and performs positioning based on the optimal heading information and the optimal position information, which reduces the error of vehicle positioning and improves the accuracy of vehicle positioning.
  • FIG. 3a a flow chart of steps of another vehicle positioning method provided by an embodiment of the present invention is shown, which may specifically include the following steps:
  • Step 301 obtaining preset first map data and real-time collected second map data
  • Step 302 Determine a first semantic element according to the first map data, and determine first direction information and first location information corresponding to the first semantic element;
  • Step 303 according to the second map data, determine the second semantic element, and determine the second direction information and the second position information corresponding to the second semantic element;
  • Step 304 Determine the optimal heading information of the vehicle according to the first direction information and the second direction information;
  • Step 305 Determine the optimal position information of the vehicle according to the first position information, the second position information, and the optimal heading information;
  • Step 306 determining the residual information between the first semantic element and the second semantic element
  • the residual information may be a position error and an orientation error between the first semantic element and the second semantic element.
  • the positioning information of the vehicle can be determined in the first map data according to the optimal heading information and the optimal position information.
  • the transformation matrix corresponding to the optimal heading information and The displacement amount corresponding to the optimal position information deflects and displaces all the semantic elements in the second map data.
  • the second map data that is basically consistent with the first map data cannot be obtained, and the first map data can be determined.
  • the residual information between the data and the second map data that is, the position error information and the orientation error information between the first semantic element and the second semantic element can be determined.
  • Step 307 filter the first semantic element and the second semantic element according to the residual information
  • the residual information After the residual information is determined, it can be determined whether the residual information is greater than the preset threshold. If the position error is greater than 0.5 meters and the orientation error is greater than 3 degrees, semantic elements whose residual information is greater than the preset threshold can be eliminated.
  • the solid black lines and solid black points may be line semantic elements and point semantic elements in the first map data
  • the black dotted lines and points containing the dotted lines may be line semantic elements in the second map data and point semantic elements
  • the residual information between point semantic element a in the first map data and point semantic element A in the second map data is greater than the preset threshold, then point semantic element a and point semantic element A can be eliminated .
  • Step 308 Update the optimal heading information and the optimal position information according to the filtered first semantic element and the second semantic element.
  • step 304 can be returned and executed to update the optimal heading information and the optimal position information until the residual information between the first semantic element and the second semantic element is smaller than the preset threshold, and then the optimal heading information and the optimal position information can be updated.
  • the positioning information of the vehicle is determined according to the updated optimal heading information and the optimal position information, and the position information and heading information of the vehicle are output externally.
  • the preset first map data and the second map data collected in real time are acquired, the first semantic element is determined according to the first map data, and the first direction information and the first semantic element corresponding to the first semantic element are determined.
  • a position information according to the second map data, determine the second semantic element, and determine the second direction information and the second position information corresponding to the second semantic element, and determine the optimal vehicle according to the first direction information and the second direction information Heading information, according to the first position information, the second position information, and the optimal heading information, determine the optimal position information of the vehicle, determine the residual information between the first semantic element and the second semantic element, and according to the residual information, Screen the first semantic element and the second semantic element, and update the optimal heading information and the optimal position information according to the filtered first semantic element and the second semantic element, so as to realize the optimal heading information and optimal position
  • the information update, and the positioning based on the optimal heading information and the optimal position information reduces the error of the vehicle positioning and improves the accuracy of the vehicle positioning.
  • the semantic elements in the map data can be classified respectively, such as point semantics as one class, line semantics as one class, shape semantics as one class, and shape semantics is decomposed into points Semantics and Line Semantics;
  • the semantic information in the semantic elements can be decomposed, such as determining the heading information and position information of the semantic elements in turn;
  • matching semantic elements can be determined in at least two map data, and for the heading information, an optimal heading calculation is performed on the matched semantic elements;
  • the matching semantic elements can be determined in at least two map data, and the optimal position calculation is performed for the matching semantic elements according to the position information;
  • the positioning of the vehicle can be determined according to the optimal heading and optimal position, and the residual information between semantic elements in at least two map data can be determined according to the positioning to eliminate residual information. Semantic elements whose difference information is greater than a preset threshold;
  • the optimal heading can be recalculated according to the matched semantic elements after the removal
  • the optimal position can be recalculated according to the matched semantic elements after the removal
  • the positioning of the vehicle can be determined according to the optimal heading and the optimal position, and the heading and position of the vehicle can be output externally.
  • FIG. 5 a schematic structural diagram of a vehicle positioning device provided by an embodiment of the present invention is shown, which may specifically include the following modules:
  • a map data acquisition module 501 configured to acquire preset first map data and real-time collected second map data
  • a first semantic element determining module 502 configured to determine a first semantic element according to the first map data, and determine first direction information and first location information corresponding to the first semantic element;
  • a second semantic element determining module 503, configured to determine a second semantic element according to the second map data, and determine second direction information and second location information corresponding to the second semantic element;
  • an optimal heading information determination module 504, configured to determine the optimal heading information of the vehicle according to the first direction information and the second direction information;
  • the optimal location information determination module 505 is configured to determine the optimal location information of the vehicle according to the first location information, the second location information, and the optimal heading information.
  • the first semantic element includes a first point semantic element
  • the first semantic element determining module 502 includes:
  • a first centroid information determination submodule configured to determine first centroid information corresponding to a plurality of point semantic elements including the first point semantic element
  • the first direction information determination sub-module is configured to determine the first direction information corresponding to the first point semantic element according to the first center of gravity information.
  • the second semantic element includes a second point semantic element
  • the second semantic element determining module 503 includes:
  • the second center of gravity information determination submodule is used to determine the second center of gravity information corresponding to a plurality of point semantic elements including the second point semantic element;
  • a second direction information determining submodule is configured to determine, according to the second center of gravity information, second direction information corresponding to the second point semantic element.
  • the first semantic element includes a first line semantic element
  • the first position information includes first lateral position information
  • the first semantic element determination module 502 includes:
  • a first midpoint position information determination submodule used for determining the first midpoint position information corresponding to the first line semantic element
  • the first lateral position information determination sub-module is configured to determine the first lateral position information corresponding to the first line semantic element according to the first midpoint position information.
  • the second semantic element includes a second line semantic element
  • the second position information includes second lateral position information
  • the second semantic element determination module 503 includes:
  • the second midpoint position information determination submodule is used to determine the second midpoint position information corresponding to the second line semantic element
  • the second lateral position information determination submodule is configured to determine the second lateral position information corresponding to the second line semantic element according to the second midpoint position information.
  • the optimal heading information determining module 504 includes:
  • a direction information determination submodule configured to determine the direction information for the point semantic element and the direction information for the line semantic element according to the first direction information and the second direction information;
  • a direction weight information determination submodule configured to determine the direction weight information corresponding to the direction information for the line semantic element
  • the direction information combining sub-module is configured to combine the direction information for the point semantic element, the direction information for the line semantic element, and the direction weight information to determine the optimal heading information of the vehicle.
  • the optimal location information determining module 505 includes:
  • a position information determination submodule configured to determine the position information for the point semantic element and the position information for the line semantic element according to the first position information, the second position information, and the optimal heading information;
  • a position weight information determination submodule configured to determine the position weight information corresponding to the position information for the line semantic element
  • the position information combining submodule is configured to combine the position information for the point semantic element, the position information for the line semantic element, and the position weight information to determine the optimal heading information of the vehicle.
  • the first semantic element determining module 502 includes:
  • a first semantic element classification sub-module for classifying semantic elements in the first map data
  • the first semantic element generation sub-module is configured to, for the first shape semantic element in the first map data, generate a first point semantic element and a first line semantic element corresponding to the first shape semantic element.
  • the second semantic element determining module 503 includes:
  • the second semantic element classification submodule is used to classify the semantic elements in the second map data
  • the second semantic element generation submodule is configured to, for the second shape semantic element in the second map data, generate a second point semantic element and a second line semantic element corresponding to the second shape semantic element.
  • it also includes:
  • a residual information determining module configured to determine residual information between the first semantic element and the second semantic element
  • a semantic element screening module configured to screen the first semantic element and the second semantic element according to the residual information
  • the updating module is configured to update the optimal heading information and the optimal position information according to the filtered first semantic element and the second semantic element.
  • the preset first map data and the second map data collected in real time are acquired, the first semantic element is determined according to the first map data, and the first direction information and the first semantic element corresponding to the first semantic element are determined.
  • a position information according to the second map data, determine the second semantic element, and determine the second direction information and the second position information corresponding to the second semantic element, and determine the optimal vehicle according to the first direction information and the second direction information Heading information, according to the first position information, the second position information, and the optimal heading information, determine the optimal position information of the vehicle, determine the residual information between the first semantic element and the second semantic element, and according to the residual information, Screen the first semantic element and the second semantic element, and update the optimal heading information and the optimal position information according to the filtered first semantic element and the second semantic element, so as to realize the optimal heading information and optimal position
  • the information is determined, and the positioning based on the optimal heading information and the optimal position information reduces the error of the vehicle positioning and improves the accuracy of the vehicle positioning.
  • An embodiment of the present invention also provides a vehicle, which may include a processor, a memory, and a computer program stored in the memory and capable of running on the processor.
  • the computer program is executed by the processor to implement the above method for vehicle positioning.
  • An embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the above method for vehicle positioning is implemented.
  • embodiments of the present invention may be provided as a method, an apparatus, or a 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 implemented on one or more computer-usable storage media having computer-usable program code embodied therein, including but not limited to disk storage, CD-ROM, optical storage, and the like.
  • Embodiments of the present invention are described with reference to flowcharts and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the present invention. It will be understood that each flow and/or block in the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to the processor of a general purpose computer, special purpose computer, embedded processor or other programmable data processing terminal equipment to produce a machine that causes the instructions to be executed by the processor of the computer or other programmable data processing terminal equipment Means are created for implementing the functions specified in the flow or flows of the flowcharts and/or the blocks or blocks of the block diagrams.
  • These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing terminal equipment to operate in a particular manner, such that the instructions stored in the computer readable memory result in an article of manufacture comprising instruction means, the The instruction means implement the functions specified in the flow or flow of the flowcharts and/or the block or blocks of the block diagrams.

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Electromagnetism (AREA)
  • Acoustics & Sound (AREA)
  • Automation & Control Theory (AREA)
  • Navigation (AREA)
  • Traffic Control Systems (AREA)
  • Instructional Devices (AREA)

Abstract

一种车辆定位的方法和装置,车辆定位的方法包括:获取预置的第一地图数据和实时采集的第二地图数据;根据第一地图数据,确定第一语义元素,并确定第一语义元素对应的第一方向信息和第一位置信息;根据第二地图数据,确定第二语义元素,并确定第二语义元素对应的第二方向信息和第二位置信息;根据第一方向信息和第二方向信息,确定车辆的最优航向信息;根据第一位置信息、第二位置信息,以及最优航向信息,确定车辆的最优位置信息。实现了最优航向信息和最优位置信息的确定,并基于最优航向信息和最优位置信息进行定位减少了车辆定位的误差,提高了车辆定位的准确性。

Description

一种车辆定位的方法和装置
相关申请的交叉引用
本申请要求于2020年10月15日提交的申请号为202011105411.9的中国申请的优先权,其在此处于所有目的通过引用将其全部内容并入本文。
技术领域
本发明涉及定位技术领域,特别是涉及一种车辆定位的方法和装置。
背景技术
在车辆行驶的过程中,往往需要对车辆进行定位,特别是对自动驾驶或无人驾驶的车辆来说,车辆定位的精确度会影响到车辆行驶的安全。
而在现有技术中,车辆可以采集车辆周边的信息,如车道线、车位等,进而可以根据所采集的信息中的特征点进行定位,然而,由于车辆的采集范围有限,所采集的特征点的数量不多,导致仅根据特征点进行定位容易出现偏差,而且,一个特征点所包含的信息不多,难以完整的表示车辆所采集的信息,导致定位不准确。
发明内容
鉴于上述问题,提出了以便提供克服上述问题或者至少部分地解决上述问题的一种车辆定位的方法和装置,包括:
一种车辆定位的方法,所述方法包括:
获取预置的第一地图数据和实时采集的第二地图数据;
根据所述第一地图数据,确定第一语义元素,并确定所述第一语义元素对应的第一方向信息和第一位置信息;
根据所述第二地图数据,确定第二语义元素,并确定所述第二语义元素对应的第二方向信息和第二位置信息;
根据所述第一方向信息和所述第二方向信息,确定所述车辆的最优航向信息;
根据所述第一位置信息、所述第二位置信息,以及所述最优航向信息,确定所述车辆的最优位置信息。
可选地,所述第一语义元素包括第一点语义元素,所述确定所述第一语义元素对应的第一方向信息,包括:
确定包含所述第一点语义元素的多个点语义元素对应的第一重心信息;
根据所述第一重心信息,确定所述第一点语义元素对应的第一方向信息;
所述第二语义元素包括第二点语义元素,所述确定所述第二语义元素对应的第二方向信息,包括:
确定包含所述第二点语义元素的多个点语义元素对应的第二重心信息;
根据所述第二重心信息,确定所述第二点语义元素对应的第二方向信息。
可选地,所述第一语义元素包括第一线语义元素,所述第一位置信息包括第一横向位置信息,所述确定所述第一语义元素对应的第一位置信息,包括:
确定所述第一线语义元素对应的第一中点位置信息;
根据所述第一中点位置信息,确定所述第一线语义元素对应的第一横向位置信息;
可选地,所述第二语义元素包括第二线语义元素,所述第二位置信息包括第二横向位置信息,所述确定所述第二语义元素对应的第二位置信息,包括:
确定所述第二线语义元素对应的第二中点位置信息;
根据所述第二中点位置信息,确定所述第二线语义元素对应的第二横向位置信息。
可选地,所述根据所述第一方向信息和所述第二方向信息,确定所述车辆的最优航向信息,包括:
根据所述第一方向信息和所述第二方向信息,确定针对点语义元素的方向信息和针对线语义元素的方向信息;
确定所述针对线语义元素的方向信息对应的方向权重信息;
结合所述针对点语义元素的方向信息、所述针对线语义元素的方向信息,以及所述方向权重信息,确定所述车辆的最优航向信息。
可选地,所述根据所述第一位置信息、所述第二位置信息,以及所述最优航向信息,确定所述车辆的最优位置信息,包括:
根据所述第一位置信息、所述第二位置信息,以及所述最优航向信息,确定针对点语义元素的位置信息和针对线语义元素的位置信息;
确定所述针对线语义元素的位置信息对应的位置权重信息;
结合所述针对点语义元素的位置信息、所述针对线语义元素的位置信息,以及所述位置权重信息,确定所述车辆的最优航向信息。
可选地,所述根据所述第一地图数据,确定第一语义元素,包括:
对所述第一地图数据中语义元素进行分类;
对于所述第一地图数据中的第一形状语义元素,生成所述第一形状语义元素对应的第一点语义元素和第一线语义元素;
所述根据所述第二地图数据,确定第二语义元素,包括:
对所述第二地图数据中语义元素进行分类;
对于所述第二地图数据中的第二形状语义元素,生成所述第二形状语义元素对应的第二点语义元素和第二线语义元素。
可选地,还包括:
确定所述第一语义元素和所述第二语义元素之间的残差信息;
根据所述残差信息,对所述第一语义元素和所述第二语义元素进行筛选;
根据筛选后的第一语义元素和第二语义元素,对所述最优航向信息和所述最优位置信息进行更新。
一种车辆定位的装置,所述装置包括:
地图数据获取模块,用于获取预置的第一地图数据和实时采集的第二地图数据;
第一语义元素确定模块,用于根据所述第一地图数据,确定第一语义元素,并确定所述第一语义元素对应的第一方向信息和第一位置信息;
第二语义元素确定模块,用于根据所述第二地图数据,确定第二语义元素,并确定所述第二语义元素对应的第二方向信息和第二位置信息;
最优航向信息确定模块,用于根据所述第一方向信息和所述第二方向信息,确定所述车辆的最优航向信息;
最优位置信息确定模块,用于根据所述第一位置信息、所述第二位置信息,以及所述最优航向信息,确定所述车辆的最优位置信息。
一种车辆,包括处理器、存储器及存储在所述存储器上并能够在所述处理器上运行的计算机程序,所述计算机程序被所述处理器执行时实现如上所述的一种车辆定位的方法。
一种计算机可读存储介质,所述计算机可读存储介质上存储计算机程序,所述计算机程序被处理器执行时实现如上所述的一种车辆定位的方法。
本发明实施例具有以下优点:
在本发明实施例中,通过获取预置的第一地图数据和实时采集的第二地图数据;根据第一地图数据,确定第一语义元素,并确定第一语义元素对应的第一方向信息和第一位置信息;根据第二地图数 据,确定第二语义元素,并确定第二语义元素对应的第二方向信息和第二位置信息;根据第一方向信息和第二方向信息,确定车辆的最优航向信息;根据第一位置信息、第二位置信息,以及最优航向信息,确定车辆的最优位置信息,实现了最优航向信息和最优位置信息的确定,并基于最优航向信息和最优位置信息进行定位减少了车辆定位的误差,提高了车辆定位的准确性。
附图说明
为了更清楚地说明本发明的技术方案,下面将对本发明的描述中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图仅仅是本发明的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动性的前提下,还可以根据这些附图获得其他的附图。
图1a是本发明一实施例提供的一种车辆定位的方法的步骤流程图;
图1b是本发明一实施例提供的一种语义元素的分类示意图;
图2是本发明一实施例提供的另一种车辆定位的方法的步骤流程图;
图3a是本发明一实施例提供的又一种车辆定位的方法的步骤流程图;
图3b是本发明一实施例提供的一种语义元素的筛选示意图
图4是本发明一实施例提供的一种车辆定位的方法的实例示意图;
图5是本发明一实施例提供的一种车辆定位的装置的结构示意图。
具体实施方式
为使本发明的上述目的、特征和优点能够更加明显易懂,下面结合附图和具体实施方式对本发明作进一步详细的说明。显然,所描述的实施例是本发明一部分实施例,而不是全部的实施例。基于本发明中的实施例,本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例,都属于本发明保护的范围。
参照图1a,示出了本发明一实施例提供的一种车辆定位的方法的步骤流程图,具体可以包括如下步骤:
步骤101,获取预置的第一地图数据和实时采集的第二地图数据;
其中,第一地图数据和第二地图数据可以为针对停车场的地图数据,第一地图数据可以为服务器中经过多次融合的语义地图,第二地图数据可以为车辆实时采集的语义地图,语义地图可以为包括一个或多个语义元素的地图,语义元素可以包括车道线、车位、路障、减速带等。
如图1b所示,第一地图数据可以为静态地图,第二地图数据可以为实时感知的地图。
在行驶过程中,可以通过车辆中的定位功能,如通过GPS(Global Positioning System,全球定位***)功能确定车辆所在的区域,进而可以从服务器中获取该区域的语义地图,也可以从服务器中预先获取多个语义地图,以在确定车辆所在的区域后,调用该区域的语义地图。
在获取第一地图数据后,可以通过车辆中的感知设备实时采集车辆所在区域的语义元素,进而可以根据语义元素生成语义地图,也即是生成第二地图数据。
其中,感知设备可以包括超声波传感器、红外线传感器、摄像头等。
在本发明一实施例中,感知设备可以具有一定的采集范围,例如,采集范围可以为25米,进而采集的语义元素可以为25米以内的语义元素。
步骤102,根据第一地图数据,确定第一语义元素,并确定第一语义元素对应的第一方向信息和第一位置信息;
在获取第一地图数据和第二地图数据后,可以确定第二地图数据中所有的语义元素,进而可以在第一地图数据中,确定与第二地图数据中的语义元素匹配的语义元素。
在实际应用中,由于第一地图数据可以是针对车辆所在区域的地图,如停车场,进而可以确定车辆所在区域中所有的语义元素,而第二地图数据可以是车辆实时采集的地图,由于感知设备具有一定的感知范围,则在车辆实时采集的地图中确定的是感知范围内的语义元素,即第二地图数据中的语义元素应当小于或等于第一地图数据中的语义元素,进而可以在第一地图数据的所有语义元素中,确定 与第二地图数据中的语义元素匹配的语义元素。
在确定匹配的语义元素后,可以确定第一地图数据中任意一个匹配的语义元素,进而可以确定该匹配的语义元素的方向信息和位置信息。
在实际应用中,第一地图数据中可以设有一坐标系,进而可以确定语义元素在该坐标系中的坐标信息,并根据坐标信息确定语义元素的方向信息和位置信息,其中,方向信息可以为语义元素在坐标系中的角度信息。
作为一示例,语义元素可以包括点语义元素和线语义元素,如图1b所示,语义点可以为点语义元素,语义线可以为线语义元素。
在本发明一实施例中,第一语义元素可以包括第一点语义元素,可以分别确定第一点语义元素的方向信息和位置信息,步骤102可以包括如下子步骤:
子步骤11,确定包含所述第一点语义元素的多个点语义元素对应的第一重心信息;
其中,点语义元素可以包括车位的角点等语义元素,重心信息可以为一个距离多个点语义元素最短的点。
由于第一语义元素可以包括第一点语义元素,则在确定第一语义元素后,可以确定第一语义元素中的第一点语义元素,进而可以确定第一地图数据中所有的点语义元素,并根据所有的点语义元素的坐标信息确定对应的重心信息。
在实际应用中,可以通过以下公式确定重心信息:
Figure PCTCN2020126931-appb-000001
其中,p i可以为第一地图数据中的点语义元素i的坐标信息,n可以表示为匹配的点语义元素的数量,即第一地图数据中可以有n个点语义元素,G可以表示为第一地图数据中的所有点语义元素的重心。
子步骤12,根据所述第一重心信息,确定所述第一点语义元素对应的第一方向信息。
在确定第一重心信息后,可以根据重心信息与点语义元素的坐标信息确定点语义元素的方向向量,也即是点语义元素的方向信息,具体可以通过以下公式确定:
q i=G-p i
其中,q i可以为第一地图数据中的点语义元素i的向量信息,即方向信息。
在本发明一实施例中,第一地图数据中的点语义元素的位置信息可以根据第一地图数据中的点语义元素的坐标信息进行确定,例如,第一地图数据中的点语义元素的位置信息可以为第一地图数据中的点语义元素的坐标信息。
在本发明一实施例中,第一语义元素可以包括第一线语义元素,可以分别确定第一线语义元素的方向信息和位置信息,步骤102可以包括如下子步骤:
子步骤21,确定所述第一线语义元素对应的第一中点位置信息;
其中,线语义元素可以包括车位的库线、路障等语义元素。
由于第一语义元素可以包括第一线语义元素,则在确定第一语义元素后,可以确定第一语义元素中的第一线语义元素,进而可以确定第一线语义元素中的中点的坐标信息,也即是中点的位置信息。
子步骤22,根据所述第一中点位置信息,确定所述第一线语义元素对应的第一横向位置信息。
在确定第一中点位置信息后,可以根据中点的坐标信息确定中点的横向坐标信息,例如,中点的坐标信息可以包括横坐标信息和纵坐标信息,进而可以确定该中点的横坐标信息为第一横向位置信息。
在本发明一实施例中,第二线语义元素的方向信息可以为线语义元素向量信息,该向量信息可以通过线语义元素中多个点的位置信息确定。
在本发明一实施例中,语义元素还可以包括形状语义元素,步骤102可以包括如下子步骤:
子步骤31,对第一地图数据中语义元素进行分类;
在获取第一地图数据后,可以确定点语义元素、线语义元素、形状语义元素,并根据不同类型的语义元素进行分类。
如图1b所示,语义点形状可以为形状语义元素,第一地图数据可以包括点语义元素1、点语义元素2、线语义元素1、线语义元素2、形状语义元素1、形状语义元素2、形状语义元素3,进而可以确定点语义元素1和点语义元素2为一类,线语义元素1和线语义元素2为一类,形状语义元素1、形状语义元素3以及形状语义元素2为一类。
子步骤32,对于第一地图数据中的第一形状语义元素,生成第一形状语义元素对应的第一点语义元素和第一线语义元素。
在对语义元素进行分类后,可以对任意一个形状语义元素进行分解,确定形状语义元素中的点、线,进而可以根据形状语义元素中的点、线生成点语义元素和线语义元素。
例如,形状语义元素1可以为矩形,进而可以将矩形分解为4个点和4条线,可以根据该4个点和4条线生成4个点语义元素和4个线语义元素。
在实际应用中,是根据所采集的信息中的特征点进行定位,即使所采集的信息为特定形状的信息,如矩形的车位,也仅仅确定该特定形状的信息中的特征点进行定位,如根据矩形的车位的中心点进行定位,定位的精度低,而通过确定特定形状的信息中的点和线,并利用点和线进行定位,能够提高定位的精度。
步骤103,根据第二地图数据,确定第二语义元素,并确定第二语义元素对应的第二方向信息和第二位置信息;
在获取第一地图数据和第二地图数据后,可以确定第二地图数据中所有的语义元素,进而可以在第一地图数据中,确定与第二地图数据中的语义元素匹配的语义元素。
在实际应用中,由于第一地图数据可以是针对车辆所在区域的地图,如停车场,进而可以确定车辆所在区域中所有的语义元素,而第二地图数据可以是车辆实时采集的地图,由于感知设备具有一定的感知范围,则在车辆实时采集的地图中确定的是感知范围内的语义元素,即第二地图数据中的语义元素应当小于或等于第一地图数据中的语义元素,进而可以在第一地图数据的所有语义元素中,确定与第二地图数据中的语义元素匹配的语义元素。
在确定匹配的语义元素后,可以确定第一地图数据中任意一个匹配的语义元素,进而可以确定该匹配的语义元素的方向信息和位置信息。
在实际应用中,第一地图数据中可以设有一坐标系,进而可以确定语义元素在该坐标系中的坐标信息,并根据坐标信息确定语义元素的方向信息和位置信息,其中,方向信息可以为语义元素在坐标系中的角度信息。
作为一示例,语义元素可以包括点语义元素和线语义元素,如图1b所示,语义点可以为点语义元素,语义线可以为线语义元素。
在本发明一实施例中,第二语义元素可以包括第二点语义元素,可以分别确定第二点语义元素的方向信息和位置信息,步骤102可以包括如下子步骤:
子步骤41,确定包含所述第二点语义元素的多个点语义元素对应的第二重心信息;
由于第二语义元素可以包括第二点语义元素,则在确定第二语义元素后,可以确定第二语义元素中的第二点语义元素,进而可以确定第二地图数据中所有的点语义元素,并根据所有的点语义元素的坐标信息确定对应的重心信息。
在实际应用中,可以通过以下公式确定重心信息:
Figure PCTCN2020126931-appb-000002
其中,p i'可以为第二地图数据中的点语义元素i的坐标信息,n可以表示为匹配的点语义元素的数量,即第一地图数据中可以有n个点语义元素,G'可以表示为第二地图数据中的所有点语义元素的重心。
子步骤42,根据所述第二重心信息,确定所述第二点语义元素对应的第二方向信息。
在确定第二重心信息后,可以根据重心信息与点语义元素的坐标信息确定点语义元素的方向向量,也即是点语义元素的方向信息,具体可以通过以下公式确定:
q i'=G'-p i'
其中,q i'可以为第二地图数据中的点语义元素i的向量信息,即方向信息,p i'可以为第二地图数据中的点语义元素i的坐标信息。
在本发明一实施例中,第二地图数据中的点语义元素的位置信息可以根据第二地图数据中的点语义元素的坐标信息进行确定,例如,第二地图数据中的点语义元素的位置信息可以为第二地图数据中的点语义元素的坐标信息。
在本发明一实施例中,第二语义元素可以包括第二线语义元素,可以分别确定第二线语义元素的方向信息和位置信息,步骤102可以包括如下子步骤:
子步骤51,确定所述第二线语义元素对应的第二中点位置信息;
其中,线语义元素可以包括车位的库线、路障等语义元素。
由于第二语义元素可以包括第二线语义元素,则在确定第二语义元素后,可以确定第二语义元素中的第二线语义元素,进而可以确定第二线语义元素中的中点的坐标信息,也即是中点的位置信息。
子步骤52,根据所述第二中点位置信息,确定所述第二线语义元素对应的第二横向位置信息。
在确定第二中点位置信息后,可以根据中点的坐标信息确定中点的横向坐标信息,例如,中点的坐标信息可以包括横坐标信息和纵坐标信息,进而可以确定该中点的横坐标信息为第二横向位置信息。
在本发明一实施例中,第二线语义元素的方向信息可以为线语义元素向量信息,该向量信息可以通过线语义元素中多个点的位置信息确定。
在本发明一实施例中,第二语义元素包括第二点语义元素和第二线语义元素,步骤103可以包括如下子步骤:
子步骤61,对第二地图数据中语义元素进行分类;
在获取第二地图数据后,可以确定点语义元素、线语义元素、形状语义元素,并根据不同类型的语义元素进行分类。
子步骤62,对于第二地图数据中的第二形状语义元素,生成第二形状语义元素对应的第二点语义元素和第二线语义元素。
在对语义元素进行分类后,可以对任意一个形状语义元素进行分解,确定形状语义元素中的点、线,进而可以根据形状语义元素中的点、线生成点语义元素和线语义元素。
步骤104,根据第一方向信息和第二方向信息,确定车辆的最优航向信息;
在确定第一方向信息和第二方向信息后,可以结合多个匹配的语义元素的第一方向信息和第二方向信息,确定第二语义元素的角度偏转信息,也即是确定实时感知的语义元素的角度偏转信息,进而可以根据角度转换信息对第二语义元素进行偏转,以确定车辆在第一地图数据中的最优航向信息。
在本发明一实施例中,可以针对点语义元素的方向信息,确定车辆的最优航向信息,具体可以通过以下公式进行确定:
Figure PCTCN2020126931-appb-000003
其中,F p theta可以为点语义元素的最优航向信息,p i'可以为第二地图数据中的点语义元素i的坐标信息,p i可以为第一地图数据中的点语义元素i的坐标信息,G可以表示为第一地图数据中的所有点语义元素的重心,G'可以表示为第二地图数据中的所有点语义元素的重心,R可以为针对不同的相互匹配的点语义元素的转换矩阵,即角度偏转信息,该矩阵可以根据点语义元素的坐标信息进行确定,min J可以为点语义元素的总体的误差。
在实际应用中,可以确定在点语义元素的总体的误差最小时的转换矩阵,进而可以根据转换矩阵 对全部的第二语义元素进行偏转,以确定车辆在第一地图数据中的最优航向信息。
在本发明一实施例中,可以针对线语义元素的方向信息,确定车辆的最优航向信息,具体可以通过以下公式进行确定:
Figure PCTCN2020126931-appb-000004
其中,F l theta可以为线语义元素的最优方向信息,v i可以为第一地图数据中的线语义元素i,v i'可以为第二地图数据中的线语义元素i,n可以表示为匹配的线语义元素的数量,R可以为针对不同的相互匹配的线语义元素的转换矩阵,即角度偏转信息,该矩阵可以根据线语义元素的位置信息进行确定,min J可以为线语义元素的总体的误差。
在实际应用中,可以确定在线语义元素的总体的误差最小时的转换矩阵,进而可以根据转换矩阵对全部的第二语义元素进行偏转,以确定车辆在第一地图数据中的最优航向信息。
步骤105,根据第一位置信息、第二位置信息,以及最优航向信息,确定车辆的最优位置信息。
在确定第一位置信息和第二位置信息后,可以结合多个匹配的语义元素的第一位置信息和第二位置信息,确定第二语义元素的位置偏移信息,也即是确定实时感知的语义元素的位置偏移信息,进而可以根据位置偏移信息对第二语义元素进行位移,以确定车辆在第一地图数据中的最优位置信息。
在本发明一实施例中,可以针对点语义元素的位置信息,确定车辆的最优位置信息,具体可以通过以下公式进行确定:
Figure PCTCN2020126931-appb-000005
其中,F p loc可以为点语义元素的最优位置信息,G可以表示为第一地图数据中的所有点语义元素的重心,G'可以表示为第二地图数据中的所有点语义元素的重心,R可以为针对不同的相互匹配的点语义元素的转换矩阵,即角度偏转信息,该矩阵可以根据点语义元素的坐标信息进行确定,t可以为针对不同的相互匹配的点语义元素的位移量,即位置偏移信息,该位移量的值可以根据点语义元素的坐标信息进行确定,min J可以为点语义元素的总体的误差。
在实际应用中,可以确定在点语义元素的总体的误差最小时的位移量,进而可以根据位移量对全部的第二语义元素进行位移,以确定车辆在第一地图数据中的最优位置信息。
在本发明一实施例中,可以针对线语义元素的横向位置信息,确定车辆的最优位置信息,具体可以通过以下公式进行确定:
Figure PCTCN2020126931-appb-000006
其中,F l loc可以为线语义元素的最优横向位置信息,A i可以为第一地图数据中线语义元素的横向位置信息,A i'可以为第二地图数据中线语义元素的横向位置信息,R可以为针对不同的相互匹配的线语义元素的转换矩阵,即角度偏转信息,该矩阵可以根据线语义元素的横向位置信息进行确定,t可以为针对不同的相互匹配的点语义元素的位移量,即位置偏移信息,该位移量的值可以根据点语义元素的坐标信息进行确定,min J可以为点语义元素的总体的误差。
在实际应用中,可以确定在线语义元素的总体的误差最小时的位移量,进而可以根据位移量对全部的第二语义元素进行位移,以确定车辆在第一地图数据中的最优横向位置信息。
在本发明实施例中,获取预置的第一地图数据和实时采集的第二地图数据;根据第一地图数据,确定第一语义元素,并确定第一语义元素对应的第一方向信息和第一位置信息;根据第二地图数据,确定第二语义元素,并确定第二语义元素对应的第二方向信息和第二位置信息;根据第一方向信息和第二方向信息,确定车辆的最优航向信息;根据第一位置信息、第二位置信息,以及最优航向信息,确定车辆的最优位置信息,实现了最优航向信息和最优位置信息的确定,并基于最优航向信息和最优位置信息进行定位减少了车辆定位的误差,提高了车辆定位的准确性。
参照图2,示出了本发明一实施例提供的另一种车辆定位的方法的步骤流程图,具体可以包括如下步骤:
步骤201,获取预置的第一地图数据和实时采集的第二地图数据;
步骤202,根据第一地图数据,确定第一语义元素,并确定第一语义元素对应的第一方向信息和第一位置信息;
步骤203,根据第二地图数据,确定第二语义元素,并确定第二语义元素对应的第二方向信息和第二位置信息;
步骤204,根据第一方向信息和第二方向信息,确定针对点语义元素的方向信息和针对线语义元素的方向信息;
在确定第一方向信息后,可以确定第一地图数据中所有匹配的点语义元素,并根据所有的点语义元素确定对应的重心,进而可以根据重心确定点语义元素的方向信息,具体可以为F p theta
在确定第二方向信息后,可以通过线语义元素中多个点的位置信息确定线语义元素的向量信息,也即是方向信息,具体可以为F l theta
步骤205,确定针对线语义元素的方向信息对应的方向权重信息;
在确定方向信息后,可以根据车辆中的感知设备的采集范围,确定线语义元素的方向信息的权重信息,例如,采集范围可以为25米,则线语义元素的方向信息的权重信息可以为1.5。
步骤206,结合针对点语义元素的方向信息、针对线语义元素的方向信息,以及方向权重信息,确定车辆的最优航向信息;
在确定方向权重信息后,可以结合点语义元素的方向信息、针对线语义元素的方向信息,以及方向权重信息,确定车辆的最优航向信息,具体可以通过以下公式确定最优航向信息:
F theta=F p_theta+λ1*F l_theta
其中,F theta可以为基于方向权重信息得到的最优航向信息,λ1可以为方向权重信息。
步骤207,根据第一位置信息、第二位置信息,以及最优航向信息,确定针对点语义元素的位置信息和针对线语义元素的位置信息;
在确定最优航向信息后,可以根据点语义元素的坐标信息以及最优航向信息确定点语义元素的位置信息,具体可以为F p loc,可以根据线语义元素的中点的位置信息以及最优航向信息确定线语义元素的横向位置信息,具体可以为F l loc
步骤208,确定针对线语义元素的位置信息对应的位置权重信息;
在确定横向位置信息后,可以根据车辆中的感知设备的采集范围,确定线语义元素的横向位置信息的权重信息,例如,采集范围可以为25米,则线语义元素的方向信息的权重信息可以为1。
步骤209,结合针对点语义元素的位置信息、针对线语义元素的位置信息,以及位置权重信息,确定车辆的最优航向信息。
在确定位置权重信息后,可以结合点语义元素的位置信息、针对线语义元素的横向位置信息,以及位置权重信息,确定车辆的最优位置信息,具体可以通过以下公式确定最优位置信息:
F loc=F p_loc+λ2*F l_loc
其中,F loc可以为基于方向权重信息得到的最优位置信息,λ2可以为位置权重信息。
在确定最优位置信息后,可以基于最优航向信息和最优位置信息确定车辆的最优航向信息,即可以根据最优航向信息和最优位置信息,在第一地图数据中确定车辆的定位信息。
在本发明实施例中,获取预置的第一地图数据和实时采集的第二地图数据,根据第一地图数据,确定第一语义元素,并确定第一语义元素对应的第一方向信息和第一位置信息,根据第二地图数据,确定第二语义元素,并确定第二语义元素对应的第二方向信息和第二位置信息,根据第一方向信息和第二方向信息,确定针对点语义元素的方向信息和针对线语义元素的方向信息,确定针对线语义元素的方向信息对应的方向权重信息,结合针对点语义元素的方向信息、针对线语义元素的方向信息,以 及方向权重信息,确定车辆的最优航向信息,根据第一位置信息、第二位置信息,以及最优航向信息,确定针对点语义元素的位置信息和针对线语义元素的位置信息,确定针对线语义元素的位置信息对应的位置权重信息,结合针对点语义元素的位置信息、针对线语义元素的位置信息,以及位置权重信息,确定车辆的最优航向信息,实现了基于点和线确定最优航向信息和最优位置信息,提高了最优航向信息和最优位置信息的准确性,并基于最优航向信息和最优位置信息进行定位,减少了车辆定位的误差,提高了车辆定位的准确性。
参照图3a,示出了本发明一实施例提供的又一种车辆定位的方法的步骤流程图,具体可以包括如下步骤:
步骤301,获取预置的第一地图数据和实时采集的第二地图数据;
步骤302,根据第一地图数据,确定第一语义元素,并确定第一语义元素对应的第一方向信息和第一位置信息;
步骤303,根据第二地图数据,确定第二语义元素,并确定第二语义元素对应的第二方向信息和第二位置信息;
步骤304,根据第一方向信息和第二方向信息,确定车辆的最优航向信息;
步骤305,根据第一位置信息、第二位置信息,以及最优航向信息,确定车辆的最优位置信息;
步骤306,确定第一语义元素和第二语义元素之间的残差信息;
其中,残差信息可以为第一语义元素和第二语义元素之间的位置误差和方向误差。
在确定最优航向信息和最优位置信息后,可以根据最优航向信息和最优位置信息,在第一地图数据中确定车辆的定位信息,例如,可以根据最优航向信息对应的转换矩阵以及最优位置信息对应的位移量对第二地图数据中全部的语义元素进行偏转和位移。
然而,由于车辆中感知设备的感知误差或地图的标注误差,导致在对全部的语义元素进行偏转和位移后,不能得到与第一地图数据基本吻合的第二地图数据,进而可以确定第一地图数据与第二地图数据之间的残差信息,也即是可以确定第一语义元素和第二语义元素之间的位置误差信息和方向误差信息。
步骤307,根据残差信息,对第一语义元素和第二语义元素进行筛选;
在确定残差信息后,可以确定残差信息是否大于预设阈值,如位置误差大于0.5米,方向误差大于3度,则可以剔除残差信息大于预设阈值的语义元素。
如图3b所示,纯黑色的线条和纯黑色的点可以为第一地图数据中的线语义元素和点语义元素,黑色的虚线和包含虚线的点可以为第二地图数据中的线语义元素和点语义元素,而第一地图数据中的点语义元素a与第二地图数据中的点语义元素A之间的残差信息大于预设阈值,则可以剔除点语义元素a与点语义元素A。
步骤308,根据筛选后的第一语义元素和第二语义元素,对最优航向信息和最优位置信息进行更新。
在筛选语义元素后,可以返回并执行步骤304,以对最优航向信息和最优位置信息进行更新,直至第一语义元素和第二语义元素之间的残差信息小于预设阈值,进而可以根据更新后的最优航向信息和最优位置信息确定车辆的定位信息,并对外输出车辆的位置信息和航向信息。
在本发明实施例中,获取预置的第一地图数据和实时采集的第二地图数据,根据第一地图数据,确定第一语义元素,并确定第一语义元素对应的第一方向信息和第一位置信息,根据第二地图数据,确定第二语义元素,并确定第二语义元素对应的第二方向信息和第二位置信息,根据第一方向信息和第二方向信息,确定车辆的最优航向信息,根据第一位置信息、第二位置信息,以及最优航向信息,确定车辆的最优位置信息,确定第一语义元素和第二语义元素之间的残差信息,根据残差信息,对第一语义元素和第二语义元素进行筛选,根据筛选后的第一语义元素和第二语义元素,对最优航向信息和最优位置信息进行更新,实现了最优航向信息和最优位置信息的更新,并基于最优航向信息和最优位置信息进行定位减少了车辆定位的误差,提高了车辆定位的准确性。
以下结合图4对本发明实施例进行示例性说明:
1、在获取至少两个地图数据后,可以分别对地图数据中的语义元素进行分类,如将点语义为一类,线语义为一类,形状语义为一类,并将形状语义分解为点语义与线语义;
2、在进行分类后,可以对语义元素中的语义信息进行分解,如依次确定语义元素的航向信息和位置信息;
3、在确定语义元素的航向信息后,可以在至少两个地图数据中确定匹配的语义元素,并针对航向信息,对匹配的语义元素进行最优航向计算;
4、在确定语义元素的航向信息和位置信息后,可以在至少两个地图数据中确定匹配的语义元素,并针对位置信息,对匹配的语义元素进行最优位置计算;
5、在计算最优航向和最优位置后,可以根据最优航向和最优位置确定车辆的定位,并根据该定位确定至少两个地图数据中语义元素之间的残差信息,以剔除残差信息大于预设阈值的语义元素;
6、在剔除语义元素后,可以根据剔除后的匹配的语义元素,重新计算最优航向;
7、在剔除语义元素后,可以根据剔除后的匹配的语义元素,重新计算最优位置;
8、在确定最优航向和最优位置后,可以根据该最优航向和最优位置确定车辆的定位,并对外输出车辆的航向和位置。
需要说明的是,对于方法实施例,为了简单描述,故将其都表述为一系列的动作组合,但是本领域技术人员应该知悉,本发明实施例并不受所描述的动作顺序的限制,因为依据本发明实施例,某些步骤可以采用其他顺序或者同时进行。其次,本领域技术人员也应该知悉,说明书中所描述的实施例均属于优选实施例,所涉及的动作并不一定是本发明实施例所必须的。
参照图5,示出了本发明一实施例提供的一种车辆定位的装置的结构示意图,具体可以包括如下模块:
地图数据获取模块501,用于获取预置的第一地图数据和实时采集的第二地图数据;
第一语义元素确定模块502,用于根据所述第一地图数据,确定第一语义元素,并确定所述第一语义元素对应的第一方向信息和第一位置信息;
第二语义元素确定模块503,用于根据所述第二地图数据,确定第二语义元素,并确定所述第二语义元素对应的第二方向信息和第二位置信息;
最优航向信息确定模块504,用于根据所述第一方向信息和所述第二方向信息,确定所述车辆的最优航向信息;
最优位置信息确定模块505,用于根据所述第一位置信息、所述第二位置信息,以及所述最优航向信息,确定所述车辆的最优位置信息。
在本发明一实施例中,所述第一语义元素包括第一点语义元素,所述第一语义元素确定模块502,包括:
第一重心信息确定子模块,用于确定包含所述第一点语义元素的多个点语义元素对应的第一重心信息;
第一方向信息确定子模块,用于根据所述第一重心信息,确定所述第一点语义元素对应的第一方向信息。
在本发明一实施例中,所述第二语义元素包括第二点语义元素,所述第二语义元素确定模块503,包括:
第二重心信息确定子模块,用于确定包含所述第二点语义元素的多个点语义元素对应的第二重心信息;
第二方向信息确定子模块,用于根据所述第二重心信息,确定所述第二点语义元素对应的第二方向信息。
在本发明一实施例中,所述第一语义元素包括第一线语义元素,所述第一位置信息包括第一横向位置信息,所述第一语义元素确定模块502,包括:
第一中点位置信息确定子模块,用于确定所述第一线语义元素对应的第一中点位置信息;
第一横向位置信息确定子模块,用于根据所述第一中点位置信息,确定所述第一线语义元素对应的第一横向位置信息。
在本发明一实施例中,所述第二语义元素包括第二线语义元素,所述第二位置信息包括第二横向位置信息,所述第二语义元素确定模块503,包括:
第二中点位置信息确定子模块,用于确定所述第二线语义元素对应的第二中点位置信息;
第二横向位置信息确定子模块,用于根据所述第二中点位置信息,确定所述第二线语义元素对应的第二横向位置信息。
在本发明一实施例中,所述最优航向信息确定模块504,包括:
方向信息确定子模块,用于根据所述第一方向信息和所述第二方向信息,确定针对点语义元素的方向信息和针对线语义元素的方向信息;
方向权重信息确定子模块,用于确定所述针对线语义元素的方向信息对应的方向权重信息;
方向信息结合子模块,用于结合所述针对点语义元素的方向信息、所述针对线语义元素的方向信息,以及所述方向权重信息,确定所述车辆的最优航向信息。
在本发明一实施例中,所述最优位置信息确定模块505,包括:
位置信息确定子模块,用于根据所述第一位置信息、所述第二位置信息,以及所述最优航向信息,确定针对点语义元素的位置信息和针对线语义元素的位置信息;
位置权重信息确定子模块,用于确定所述针对线语义元素的位置信息对应的位置权重信息;
位置信息结合子模块,用于结合所述针对点语义元素的位置信息、所述针对线语义元素的位置信息,以及所述位置权重信息,确定所述车辆的最优航向信息。
在本发明一实施例中,所述第一语义元素确定模块502,包括:
第一语义元素分类子模块,用于对所述第一地图数据中语义元素进行分类;
第一语义元素生成子模块,用于对于所述第一地图数据中的第一形状语义元素,生成所述第一形状语义元素对应的第一点语义元素和第一线语义元素。
在本发明一实施例中,所述第二语义元素确定模块503,包括:
第二语义元素分类子模块,用于对所述第二地图数据中语义元素进行分类;
第二语义元素生成子模块,用于对于所述第二地图数据中的第二形状语义元素,生成所述第二形状语义元素对应的第二点语义元素和第二线语义元素。
在本发明一实施例中,还包括:
残差信息确定模块,用于确定所述第一语义元素和所述第二语义元素之间的残差信息;
语义元素筛选模块,用于根据所述残差信息,对所述第一语义元素和所述第二语义元素进行筛选;
更新模块,用于根据筛选后的第一语义元素和第二语义元素,对所述最优航向信息和所述最优位置信息进行更新。
在本发明实施例中,获取预置的第一地图数据和实时采集的第二地图数据,根据第一地图数据,确定第一语义元素,并确定第一语义元素对应的第一方向信息和第一位置信息,根据第二地图数据,确定第二语义元素,并确定第二语义元素对应的第二方向信息和第二位置信息,根据第一方向信息和第二方向信息,确定车辆的最优航向信息,根据第一位置信息、第二位置信息,以及最优航向信息,确定车辆的最优位置信息,确定第一语义元素和第二语义元素之间的残差信息,根据残差信息,对第一语义元素和第二语义元素进行筛选,根据筛选后的第一语义元素和第二语义元素,对最优航向信息和最优位置信息进行更新,实现了最优航向信息和最优位置信息的确定,并基于最优航向信息和最优位置信息进行定位减少了车辆定位的误差,提高了车辆定位的准确性。
本发明一实施例还提供了一种车辆,可以包括处理器、存储器及存储在存储器上并能够在处理器 上运行的计算机程序,计算机程序被处理器执行时实现如上一种车辆定位的方法。
本发明一实施例还提供了一种计算机可读存储介质,计算机可读存储介质上存储计算机程序,计算机程序被处理器执行时实现如上一种车辆定位的方法。
对于装置实施例而言,由于其与方法实施例基本相似,所以描述的比较简单,相关之处参见方法实施例的部分说明即可。
本说明书中的各个实施例均采用递进的方式描述,每个实施例重点说明的都是与其他实施例的不同之处,各个实施例之间相同相似的部分互相参见即可。
本领域内的技术人员应明白,本发明实施例可提供为方法、装置、或计算机程序产品。因此,本发明实施例可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且,本发明实施例可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本发明实施例是参照根据本发明实施例的方法、终端设备(***)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理终端设备的处理器以产生一个机器,使得通过计算机或其他可编程数据处理终端设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理终端设备以特定方式工作的计算机可读存储器中,使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品,该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理终端设备上,使得在计算机或其他可编程终端设备上执行一系列操作步骤以产生计算机实现的处理,从而在计算机或其他可编程终端设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
尽管已描述了本发明实施例的优选实施例,但本领域内的技术人员一旦得知了基本创造性概念,则可对这些实施例做出另外的变更和修改。所以,所附权利要求意欲解释为包括优选实施例以及落入本发明实施例范围的所有变更和修改。
最后,还需要说明的是,在本文中,诸如第一和第二等之类的关系术语仅仅用来将一个实体或者操作与另一个实体或操作区分开来,而不一定要求或者暗示这些实体或操作之间存在任何这种实际的关系或者顺序。而且,术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含,从而使得包括一系列要素的过程、方法、物品或者终端设备不仅包括那些要素,而且还包括没有明确列出的其他要素,或者是还包括为这种过程、方法、物品或者终端设备所固有的要素。在没有更多限制的情况下,由语句“包括一个……”限定的要素,并不排除在包括所述要素的过程、方法、物品或者终端设备中还存在另外的相同要素。
以上对所提供的一种车辆定位的方法和装置,进行了详细介绍,本文中应用了具体个例对本发明的原理及实施方式进行了阐述,以上实施例的说明只是用于帮助理解本发明的方法及其核心思想;同时,对于本领域的一般技术人员,依据本发明的思想,在具体实施方式及应用范围上均会有改变之处,综上所述,本说明书内容不应理解为对本发明的限制。

Claims (12)

  1. 一种车辆定位的方法,其特征在于,所述方法包括:
    获取预置的第一地图数据和实时采集的第二地图数据;
    根据所述第一地图数据,确定第一语义元素,并确定所述第一语义元素对应的第一方向信息和第一位置信息;
    根据所述第二地图数据,确定第二语义元素,并确定所述第二语义元素对应的第二方向信息和第二位置信息;
    根据所述第一方向信息和所述第二方向信息,确定所述车辆的最优航向信息;
    根据所述第一位置信息、所述第二位置信息,以及所述最优航向信息,确定所述车辆的最优位置信息。
  2. 根据权利要求1所述的方法,其特征在于,所述第一语义元素包括第一点语义元素,所述确定所述第一语义元素对应的第一方向信息,包括:
    确定包含所述第一点语义元素的多个点语义元素对应的第一重心信息;
    根据所述第一重心信息,确定所述第一点语义元素对应的第一方向信息;
    所述第二语义元素包括第二点语义元素,所述确定所述第二语义元素对应的第二方向信息,包括:
    确定包含所述第二点语义元素的多个点语义元素对应的第二重心信息;
    根据所述第二重心信息,确定所述第二点语义元素对应的第二方向信息。
  3. 根据权利要求2所述的方法,其特征在于,所述第一语义元素包括第一线语义元素,所述第一位置信息包括第一横向位置信息,所述确定所述第一语义元素对应的第一位置信息,包括:
    确定所述第一线语义元素对应的第一中点位置信息;
    根据所述第一中点位置信息,确定所述第一线语义元素对应的第一横向位置信息;
    所述第二语义元素包括第二线语义元素,所述第二位置信息包括第二横向位置信息,所述确定所述第二语义元素对应的第二位置信息,包括:
    确定所述第二线语义元素对应的第二中点位置信息;
    根据所述第二中点位置信息,确定所述第二线语义元素对应的第二横向位置信息。
  4. 根据权利要求1或2或3所述的方法,其特征在于,所述根据所述第一方向信息和所述第二方向信息,确定所述车辆的最优航向信息,包括:
    根据所述第一方向信息和所述第二方向信息,确定针对点语义元素的方向信息和针对线语义元素 的方向信息;
    确定所述针对线语义元素的方向信息对应的方向权重信息;
    结合所述针对点语义元素的方向信息、所述针对线语义元素的方向信息,以及所述方向权重信息,确定所述车辆的最优航向信息。
  5. 根据权利要求4所述的方法,其特征在于,所述根据所述第一位置信息、所述第二位置信息,以及所述最优航向信息,确定所述车辆的最优位置信息,包括:
    根据所述第一位置信息、所述第二位置信息,以及所述最优航向信息,确定针对点语义元素的位置信息和针对线语义元素的位置信息;
    确定所述针对线语义元素的位置信息对应的位置权重信息;
    结合所述针对点语义元素的位置信息、所述针对线语义元素的位置信息,以及所述位置权重信息,确定所述车辆的最优航向信息。
  6. 根据权利要求4所述的方法,其特征在于,所述根据所述第一地图数据,确定第一语义元素,包括:
    对所述第一地图数据中语义元素进行分类;
    对于所述第一地图数据中的第一形状语义元素,生成所述第一形状语义元素对应的第一点语义元素和第一线语义元素;
    所述根据所述第二地图数据,确定第二语义元素,包括:
    对所述第二地图数据中语义元素进行分类;
    对于所述第二地图数据中的第二形状语义元素,生成所述第二形状语义元素对应的第二点语义元素和第二线语义元素。
  7. 根据权利要求1所述的方法,其特征在于,还包括:
    确定所述第一语义元素和所述第二语义元素之间的残差信息;
    根据所述残差信息,对所述第一语义元素和所述第二语义元素进行筛选;
    根据筛选后的第一语义元素和第二语义元素,对所述最优航向信息和所述最优位置信息进行更新。
  8. 一种车辆定位的装置,其特征在于,所述装置包括:
    地图数据获取模块,用于获取预置的第一地图数据和实时采集的第二地图数据;
    第一语义元素确定模块,用于根据所述第一地图数据,确定第一语义元素,并确定所述第一语义元素对应的第一方向信息和第一位置信息;
    第二语义元素确定模块,用于根据所述第二地图数据,确定第二语义元素,并确定所述第二语义元素对应的第二方向信息和第二位置信息;
    最优航向信息确定模块,用于根据所述第一方向信息和所述第二方向信息,确定所述车辆的最优航向信息;
    最优位置信息确定模块,用于根据所述第一位置信息、所述第二位置信息,以及所述最优航向信息,确定所述车辆的最优位置信息。
  9. 根据权利要求8所述的装置,其特征在于,所述最优航向信息确定模块,包括:
    方向信息确定子模块,用于根据所述第一方向信息和所述第二方向信息,确定针对点语义元素的方向信息和针对线语义元素的方向信息;
    方向权重信息确定子模块,用于确定所述针对线语义元素的方向信息对应的方向权重信息;
    方向信息结合子模块,用于结合所述针对点语义元素的方向信息、所述针对线语义元素的方向信息,以及所述方向权重信息,确定所述车辆的最优航向信息。
  10. 根据权利要求8所述的装置,其特征在于,所述最优位置信息确定模块,包括:
    位置信息确定子模块,用于根据所述第一位置信息、所述第二位置信息,以及所述最优航向信息,确定针对点语义元素的位置信息和针对线语义元素的位置信息;
    位置权重信息确定子模块,用于确定所述针对线语义元素的位置信息对应的位置权重信息;
    位置信息结合子模块,用于结合所述针对点语义元素的位置信息、所述针对线语义元素的位置信息,以及所述位置权重信息,确定所述车辆的最优航向信息。
  11. 一种车辆,其特征在于,包括处理器、存储器及存储在所述存储器上并能够在所述处理器上运行的计算机程序,所述计算机程序被所述处理器执行时实现如权利要求1至7中任一项所述的一种车辆定位的方法。
  12. 一种计算机可读存储介质,其特征在于,所述计算机可读存储介质上存储计算机程序,所述计算机程序被处理器执行时实现如权利要求1至7中任一项所述的一种车辆定位的方法。
PCT/CN2020/126931 2020-10-15 2020-11-06 一种车辆定位的方法和装置 WO2022077660A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
EP20957438.3A EP4123263A4 (en) 2020-10-15 2020-11-06 VEHICLE POSITIONING METHOD AND APPARATUS

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202011105411.9A CN112284402B (zh) 2020-10-15 2020-10-15 一种车辆定位的方法和装置
CN202011105411.9 2020-10-15

Publications (1)

Publication Number Publication Date
WO2022077660A1 true WO2022077660A1 (zh) 2022-04-21

Family

ID=74497103

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/126931 WO2022077660A1 (zh) 2020-10-15 2020-11-06 一种车辆定位的方法和装置

Country Status (3)

Country Link
EP (1) EP4123263A4 (zh)
CN (1) CN112284402B (zh)
WO (1) WO2022077660A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114088082B (zh) * 2021-11-01 2024-04-16 广州小鹏自动驾驶科技有限公司 一种地图数据的处理方法和装置

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109949609A (zh) * 2019-04-30 2019-06-28 广州小鹏汽车科技有限公司 一种车辆的定位修正方法及***、车辆
CN110118564A (zh) * 2019-03-22 2019-08-13 纵目科技(上海)股份有限公司 一种高精度地图的数据管理***、管理方法、终端和存储介质
CN110147705A (zh) * 2018-08-28 2019-08-20 北京初速度科技有限公司 一种基于视觉感知的车辆定位方法及电子设备
WO2020069126A1 (en) * 2018-09-28 2020-04-02 Zoox, Inc. Modifying map elements associated with map data
CN110967018A (zh) * 2019-11-25 2020-04-07 斑马网络技术有限公司 停车场定位方法、装置、电子设备及计算机可读介质
CN111220164A (zh) * 2020-01-21 2020-06-02 北京百度网讯科技有限公司 定位方法、装置、设备及存储介质
CN111351493A (zh) * 2018-12-24 2020-06-30 上海欧菲智能车联科技有限公司 一种定位方法和***
CN111508258A (zh) * 2020-04-17 2020-08-07 北京三快在线科技有限公司 一种定位方法及装置
CN111521186A (zh) * 2020-05-27 2020-08-11 广州小鹏车联网科技有限公司 一种车辆定位方法及装置、车辆、存储介质

Family Cites Families (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104809731B (zh) * 2015-05-05 2018-03-09 北京工业大学 一种基于梯度二值化的旋转尺度不变场景匹配方法
US10837773B2 (en) * 2016-12-30 2020-11-17 DeepMap Inc. Detection of vertical structures based on LiDAR scanner data for high-definition maps for autonomous vehicles
US10317220B2 (en) * 2017-08-30 2019-06-11 Aptiv Technologies Limited Alignment of multiple digital maps used in an automated vehicle
CN108537214B (zh) * 2018-08-09 2019-01-01 中国人民解放军国防科技大学 一种室内语义地图的自动化构建方法
CN109544636B (zh) * 2018-10-10 2022-03-15 广州大学 一种融合特征点法和直接法的快速单目视觉里程计导航定位方法
CN111098850A (zh) * 2018-10-25 2020-05-05 北京初速度科技有限公司 一种自动停车辅助***及自动泊车方法
CN111145248B (zh) * 2018-11-06 2023-06-27 北京地平线机器人技术研发有限公司 位姿信息确定方法、确定装置和电子设备
WO2020102946A1 (zh) * 2018-11-19 2020-05-28 珊口(深圳)智能科技有限公司 构建地图、定位、导航、控制方法及***、移动机器人
CN111507129B (zh) * 2019-01-31 2023-08-22 广州汽车集团股份有限公司 车道级定位方法及***、计算机设备、车辆、存储介质
CN109883434B (zh) * 2019-03-25 2022-08-19 魔视智能科技(上海)有限公司 限制场景下辅助无人车全局定位的场端及全局定位方法
CN110268354A (zh) * 2019-05-09 2019-09-20 珊口(深圳)智能科技有限公司 更新地图的方法及移动机器人
CN111260726A (zh) * 2020-02-07 2020-06-09 北京三快在线科技有限公司 一种视觉定位方法及装置
CN111553945B (zh) * 2020-04-13 2023-08-11 东风柳州汽车有限公司 一种车辆定位方法
CN111707275B (zh) * 2020-05-12 2022-04-29 驭势科技(北京)有限公司 一种定位方法、装置、电子设备及计算机可读存储介质

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110147705A (zh) * 2018-08-28 2019-08-20 北京初速度科技有限公司 一种基于视觉感知的车辆定位方法及电子设备
WO2020069126A1 (en) * 2018-09-28 2020-04-02 Zoox, Inc. Modifying map elements associated with map data
CN111351493A (zh) * 2018-12-24 2020-06-30 上海欧菲智能车联科技有限公司 一种定位方法和***
CN110118564A (zh) * 2019-03-22 2019-08-13 纵目科技(上海)股份有限公司 一种高精度地图的数据管理***、管理方法、终端和存储介质
CN109949609A (zh) * 2019-04-30 2019-06-28 广州小鹏汽车科技有限公司 一种车辆的定位修正方法及***、车辆
CN110967018A (zh) * 2019-11-25 2020-04-07 斑马网络技术有限公司 停车场定位方法、装置、电子设备及计算机可读介质
CN111220164A (zh) * 2020-01-21 2020-06-02 北京百度网讯科技有限公司 定位方法、装置、设备及存储介质
CN111508258A (zh) * 2020-04-17 2020-08-07 北京三快在线科技有限公司 一种定位方法及装置
CN111521186A (zh) * 2020-05-27 2020-08-11 广州小鹏车联网科技有限公司 一种车辆定位方法及装置、车辆、存储介质

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4123263A4 *

Also Published As

Publication number Publication date
CN112284402B (zh) 2021-12-07
EP4123263A1 (en) 2023-01-25
EP4123263A4 (en) 2024-01-10
CN112284402A (zh) 2021-01-29

Similar Documents

Publication Publication Date Title
US11328521B2 (en) Map construction method, electronic device and readable storage medium
EP3901826A2 (en) Vehicle position determining method, apparatus and electronic device
EP3517997A1 (en) Method and system for detecting obstacles by autonomous vehicles in real-time
CN104833370B (zh) 用于映射、定位和位姿校正的***和方法
US10395126B2 (en) Sign based localization
WO2021051344A1 (zh) 高精度地图中车道线的确定方法和装置
EP3620823A1 (en) Method and device for detecting precision of internal parameter of laser radar
EP3920003A1 (en) Positioning method and apparatus, autonomous driving vehicle, electronic device and storage medium
CN111986261B (zh) 一种车辆定位方法、装置、电子设备及存储介质
CN112232275B (zh) 基于双目识别的障碍物检测方法、***、设备及存储介质
CN111768489B (zh) 一种室内导航地图构建方法和***
Zou et al. Real-time full-stack traffic scene perception for autonomous driving with roadside cameras
EP3859661A2 (en) Three-dimensional object detection method, electronic device and readable storage medium
WO2021254019A1 (zh) 协同构建点云地图的方法、设备和***
CN110795978B (zh) 路面点云数据提取方法、装置、存储介质及电子设备
US20210233307A1 (en) Landmark location reconstruction in autonomous machine applications
WO2024077935A1 (zh) 一种基于视觉slam的车辆定位方法及装置
WO2022077660A1 (zh) 一种车辆定位的方法和装置
CN114428259A (zh) 一种基于地图车采集的地库激光点云中车辆自动提取方法
CN111783611B (zh) 无人车的定位方法、装置、无人车及存储介质
CN113189610A (zh) 地图增强的自动驾驶多目标追踪方法和相关设备
CN113469045B (zh) 无人集卡的视觉定位方法、***、电子设备和存储介质
Tummala et al. SmartDashCam: automatic live calibration for DashCams
Wong et al. Position interpolation using feature point scale for decimeter visual localization
JP7179687B2 (ja) 障害物検知装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20957438

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2020957438

Country of ref document: EP

Effective date: 20221017

NENP Non-entry into the national phase

Ref country code: DE