WO2022052567A1 - 一种车辆定位的方法及装置、车辆、存储介质 - Google Patents

一种车辆定位的方法及装置、车辆、存储介质 Download PDF

Info

Publication number
WO2022052567A1
WO2022052567A1 PCT/CN2021/102161 CN2021102161W WO2022052567A1 WO 2022052567 A1 WO2022052567 A1 WO 2022052567A1 CN 2021102161 W CN2021102161 W CN 2021102161W WO 2022052567 A1 WO2022052567 A1 WO 2022052567A1
Authority
WO
WIPO (PCT)
Prior art keywords
road information
map
real
time
information
Prior art date
Application number
PCT/CN2021/102161
Other languages
English (en)
French (fr)
Inventor
刘中元
李红军
柴文楠
黄亚
蒋少峰
肖志光
欧阳湛
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 EP21798542.3A priority Critical patent/EP3988968A4/en
Publication of WO2022052567A1 publication Critical patent/WO2022052567A1/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
    • 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
    • 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
    • G01C21/38Electronic maps specially adapted for navigation; Updating thereof
    • G01C21/3804Creation or updating of map data
    • G01C21/3807Creation or updating of map data characterised by the type of data
    • G01C21/3815Road data
    • G01C21/3819Road shape data, e.g. outline of a route
    • 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
    • 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
    • G01C21/38Electronic maps specially adapted for navigation; Updating thereof
    • G01C21/3885Transmission of map data to client devices; Reception of map data by client devices
    • G01C21/3889Transmission of selected map data, e.g. depending on route

Definitions

  • the present invention relates to the technical field of positioning, and in particular, to a method and device for positioning a vehicle, a vehicle, and a storage medium.
  • positioning can be carried out through satellite maps.
  • positioning through maps is easily affected by the accuracy of the map, so the positioning accuracy cannot be guaranteed.
  • the vehicle is on a different type of road, such as a curve, It will make the trajectory law of the vehicle in the map complicated, and it is difficult to achieve accurate positioning on different types of roads, reducing the accuracy of dead reckoning and reducing the safety of vehicle driving.
  • a method for locating a vehicle comprising:
  • map data and from the map data, determine a plurality of map road information
  • the positioning of the vehicle is corrected.
  • determining a plurality of map road information from the map data including:
  • a plurality of map road information is determined.
  • determining a plurality of map road information according to the positioning road information including:
  • a plurality of map road information corresponding to the positioning road information is determined.
  • determining the target map road information matching the real-time road information from the plurality of map road information includes:
  • target map road information matching the real-time road information is determined.
  • performing a positioning correction on the vehicle according to the real-time road information and the target map road information including:
  • positioning correction is performed on the vehicle.
  • the method before acquiring real-time road information when it is detected that the vehicle is on a road of the target road type, the method further includes:
  • the road type of the road on which the vehicle is located is determined.
  • the target road type is a curve type.
  • a device for positioning a vehicle comprising:
  • the real-time road information late module is used to obtain real-time road information when it is detected that the vehicle is on the road of the target road type;
  • a map road information determination module used for acquiring map data, and determining a plurality of map road information from the map data
  • a target map road information determination module configured to determine target map road information matching the real-time road information from the plurality of map road information
  • a correction module configured to correct the positioning of the vehicle according to the real-time road information and the target map road 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 stores a computer program on the computer-readable storage medium, and when the computer program is executed by a processor, implements the above-mentioned method for locating a vehicle.
  • FIG. 1 is a flow chart of steps of a method for positioning a vehicle according to an embodiment of the present invention
  • Fig. 2a is a flow chart of steps of another method for vehicle positioning provided by an embodiment of the present invention.
  • 2b is a schematic diagram of an example of lane line determination 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.
  • 3b is a schematic diagram of an example of a lane line in a map provided by an embodiment of the present invention.
  • 3c is a schematic diagram of an example of a real-time perception of lane lines provided by an embodiment of the present invention.
  • FIG. 4 is a flowchart of an example of lane line matching provided by 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. 1 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 acquiring real-time road information when it is detected that the vehicle is on a road of the target road type
  • the road type can include straight road type, curve type, branch road type
  • the target road type can be curve type
  • real-time road information can include but not limited to lane line information, shoulder line information, information along the wall
  • shoulder line information can be is the edge line information of the road shoulder in the road
  • the wall edge information may be the edge line information of the wall when the vehicle is in the parking lot.
  • the road type of the road the vehicle is currently on can be detected, and when it is detected that the vehicle is on a curved road, the real-time road information of the road the vehicle is currently on can be obtained through the perception system in the vehicle .
  • the positioning can be performed by a navigation and positioning system in the vehicle.
  • step 101 the following steps may be further included:
  • map data determine the road type of the road where the vehicle is located
  • the map data may be semantic map data
  • the semantic map data may include semantic information
  • the semantic information may include but not limited to road information and parking space information
  • the road information may include but not limited to road lane line information and wall information .
  • the map data can be downloaded from the cloud in real time, or the map data can be obtained in real time from the map database preset in the vehicle, and then the map data of the road where the current vehicle is located can be determined in the map data.
  • lane line information of the current road can be obtained, and then a linear correlation coefficient of the current road can be calculated according to the lane line information to determine whether the current road is a curved road.
  • the linear correlation coefficient may be used to represent the degree that the current road is a straight line, and the linear correlation coefficient may be the Pearson correlation coefficient.
  • the position information of at least two points in the lane line information of the current road such as the position information of the endpoints, can be obtained, and then the linear correlation coefficient between the points can be calculated according to the position information of the at least two points.
  • Set the linear correlation coefficient threshold to 0.9.
  • the linear correlation coefficient is 0.7, which is less than the linear correlation coefficient threshold, it can be determined that the current road is a curved road.
  • the linear correlation coefficient is 0.99, which is greater than the linear correlation coefficient threshold, the current road can be determined.
  • the road is a straight type road.
  • the lane line information of the road where the vehicle is currently located can be obtained through a perception module in the vehicle.
  • the current vehicle can be obtained through a camera in the vehicle.
  • the image of the road where the vehicle is located, and then the image can be processed to obtain the lane line information of the road where the vehicle is currently located, or a coordinate system for the current road can be established based on the vehicle, and then the lane can be determined according to the image.
  • the coordinates of the line information in the coordinate system to determine the lane line information of the road where the vehicle is currently located in the coordinate system.
  • the information along the wall or shoulder of the road where the vehicle is currently located can be obtained through the perception module in the vehicle, and the information along the wall can be obtained.
  • the information or the shoulder information is used as the lane line information of the road where the vehicle is currently located.
  • the linear correlation coefficient of the current road can be calculated according to the lane line information, so as to determine whether the current road is a curved road.
  • the sensing system may also use, but is not limited to, ultrasonic waves and/or infrared rays for sensing.
  • Step 102 acquiring map data, and determining a plurality of map road information from the map data;
  • the map road information may be road information in the map data.
  • the map data for the current road can be downloaded from the cloud, or the map data for the current road can be obtained from the map database preset in the vehicle, and then the location in the map data can be determined according to the location in the map data.
  • the accuracy information determines the road information of the current road from the map data.
  • the positioning accuracy information of the map data is 200 cm
  • the length of the lane line corresponding to the lane line information of the real-time road information can be 500 cm, and then the current road within the accuracy range can be determined from the map data according to the positioning accuracy information.
  • the lane line information that is, the lane line of 700 cm can be determined from the map data.
  • the road information of the current road After the road information of the current road is determined, the road information can be divided, and then multiple map road information can be determined.
  • lane line information of the current road may be determined, and further lane lines corresponding to the lane line information may be divided to determine multiple pieces of lane line information.
  • Step 103 from a plurality of map road information, determine the target map road information that matches the real-time road information;
  • the multiple map road information can be matched with the real-time road information, and then the map road information matching the real-time road information among the multiple map road information can be determined, that is, the target map road information.
  • the multiple map road information may include A map road information, B map road information, and C map road information, and the A map road information, B map road information, and C map road information can be matched with real-time road information, and it can be determined that B The map road information is map road information matched with real-time road information.
  • Step 104 correcting the positioning of the vehicle according to the real-time road information and the target map road information.
  • the positioning of the vehicle may be determining the current positioning of the vehicle in the map data through a navigation and positioning system in the vehicle.
  • the correction information of the vehicle positioning can be determined according to the real-time road information and the road information on the target map, and then the positioning of the vehicle can be corrected according to the correction information in the map data, such as by displacement and/or rotation. The positioning of the vehicle is corrected.
  • the map data may include road information on map A, road information on map B, and road information on map C. It can be determined by the navigation and positioning system in the vehicle that the current vehicle is positioned in the map data as road A corresponding to the road information on map A, and it can be determined
  • the road information of the target map is the road information of the B map, and then the correction information of the vehicle positioning can be determined according to the road information of the A map and the B map road information, and the vehicle can be displaced and rotated according to the correction information in the map data to locate the vehicle. Make corrections.
  • FIG. 2a there is shown a flow chart of the steps of another vehicle positioning method provided by an embodiment of the present invention, which may specifically include the following steps:
  • Step 201 obtaining real-time road information when it is detected that the vehicle is on a road of the target road type
  • Step 202 obtaining map data, and obtaining the positioning information of the vehicle
  • the positioning information may be the positioning information of the vehicle in the map data.
  • the map data for the current road can be downloaded from the cloud, or the map data for the current road can be obtained from the map database preset in the vehicle, and then the vehicle can be determined in real time according to the navigation and positioning system in the vehicle. Location information in map data.
  • Step 203 from the map data, determine the location road information corresponding to the location information;
  • the positioning road information may be road information corresponding to the positioning information in the map data.
  • the road information on which the vehicle is located in the map data can be determined according to the positioning information and the positioning accuracy information in the map data.
  • the current road information of the vehicle can be determined from the map data according to the positioning accuracy information in the map data, that is, the range of the lane line intercepted in the map data can be determined, and then the ratio can be determined from the map data.
  • the length of the lane line of the real-time road information is longer, that is, the length of the lane line in the map is greater than the length of the lane line perceived in real time.
  • the length of the lane lines in the real-time road information may be 5 meters
  • the length of the lane lines in the map data may be 7 meters, that is, the length of the lane lines in the positioning road information may be 7 meters.
  • Step 204 according to the positioning road information, determine a plurality of map road information
  • the location road information can be divided, and then a plurality of road information in the map data can be determined.
  • the lane line information in the positioning road information can be determined, and then the lane lines corresponding to the lane line information can be divided to determine multiple pieces of lane line information.
  • step 204 may include the following sub-steps:
  • Sub-step 11 determine the real-time lane line length corresponding to the real-time road information
  • the lane line information in the real-time road information can be determined, and then the corresponding lane line can be determined, and the length of the lane line can be determined in real time.
  • the perception system in the vehicle has a certain perception range, that is, the perceived lane line should be within a certain length range, it is necessary to determine the perceived length of the lane line in real time.
  • the sensing range can be 5 meters. If the actual lane line length is 6 meters, the lane line sensed by the sensing system should be 5 meters. If the actual lane line length is 4 meters, the lane line sensed by the sensing system Should be 4 meters.
  • Sub-step 12 determine the lane line segment information for locating the road information
  • the lane line segment information may be the division of the lane lines corresponding to the lane line information in the positioning road information.
  • the lane lines corresponding to the lane line information in the positioning road information can be divided according to the preset length, or the lane lines can be divided equidistantly according to the preset number of segments, and then the positioning road can be obtained.
  • Information for lane line segmentation information can be obtained.
  • the length of the lane line in the positioning road information can be 7 meters, and the preset number of segments can be 10 segments, the lane lines can be divided equally, and then the lane lines can be determined.
  • the segment information is divided every 0.5 meters, and the lane line information of 14 segments of 0.5-meter lane lines can be obtained.
  • the real-time lane line length can be 5 meters
  • the length of the lane line in the positioning road information can be 7 meters
  • the preset length can be 2 meters
  • the lane lines can be divided according to the preset length, That is, the segment information of the lane line can be divided into every 2 meters, and then the road information of 3 sections of 2-meter lane lines and 1 section of 1-meter lane lines can be obtained.
  • the lane lines corresponding to the real-time road information may be divided according to the preset length, or the lane lines corresponding to the real-time road information may be divided according to the preset number of segments, etc. Distance division, and then the lane line segmentation information of real-time road information can be obtained.
  • the lane line segment information of the real-time road information may be the same as the lane line segment information of the positioning road information.
  • Sub-step 13 Determine a plurality of map road information corresponding to the location road information according to the lane line segment information.
  • the lane lines corresponding to the lane line information in the locating road information may be divided according to the lane line segment information, and then multiple lane lines may be determined.
  • the multi-segment lane lines can be combined according to the real-time lane line length and the sequence of the multi-segment lane lines, and then a plurality of lane-line combinations with the same length as the real-time lane line can be obtained.
  • 14 lane lines can be combined in the order of lane lines, and then the 1st to 11th lane combinations, the 2nd to 12th lane combinations, and the 3rd to 13th lane lines can be determined.
  • Combinations, 4th to 14th lane line combinations, and the length of each lane line combination is equal to the real-time lane line length.
  • Step 205 from a plurality of map road information, determine the target map road information that matches the real-time road information;
  • Step 206 correcting the positioning of the vehicle according to the real-time road information and the target map road information.
  • the vehicle when it is detected that the vehicle is on a road of the target road type, real-time road information is obtained, map data is obtained, and positioning information of the vehicle is obtained, and the positioning road information corresponding to the positioning information is determined from the map data, According to the positioning road information, multiple map road information is determined, from the multiple map road information, the target map road information matching the real-time road information is determined, and the vehicle positioning is corrected according to the real-time road information and the target map road information to achieve In order to carry out accurate positioning and correction in different road types, the accuracy of positioning is ensured, and the accuracy of dead reckoning is improved based on precise positioning, and the safety of vehicle driving is improved.
  • 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 acquiring real-time road information when it is detected that the vehicle is on a road of the target road type
  • Step 302 obtaining map data, and determining a plurality of map road information from the map data;
  • Step 303 from the map lane line corresponding to the map road information, determine the first map target point, and determine the map relative positions of other positions in the map lane line and the first map target point;
  • the map target point can be any point of the lane line in the map data, such as an endpoint.
  • the location information of any target point in the lane line combination can be determined respectively, such as the location information of the starting endpoint of the lane line combination, and the lane line can be determined.
  • the position information of another point in the combination such as determining the position information of the end point of the lane line combination, and then the relative position information of the target point and another point can be determined according to the position information.
  • the position information of the starting endpoint of the combination of lane lines can be determined, and a coordinate system can be established with the starting endpoint as the origin.
  • the lane lines can be combined, that is, line_i is placed in the coordinate system Rotate so that the end point of the combination of lane lines is located on the coordinate axis of the coordinate system, such as the x-axis of the abscissa, and then the relative position of any point in the combination of lane lines and the start point can be determined according to the coordinate system, and the relative position can be The ordinate of any point in the coordinate system.
  • Step 304 from the real-time lane line corresponding to the real-time road information, determine the first real-time target point, and determine the real-time relative positions of other positions in the real-time lane line and the first real-time target point;
  • the real-time target point may be any point in the lane line corresponding to the real-time lane line, such as an endpoint.
  • the lane line corresponding to the lane line information in the real-time road information can be determined, the position information of any target point in the lane line can be determined, such as the position information of the starting end point, and the position of another point in the lane line can be determined. information, such as the position information of another endpoint, and then the relative position information of the target point and another point can be determined according to the position information.
  • the position information of the starting endpoint of the lane line in the real-time road information can be determined, and a coordinate system can be established with the starting endpoint as the origin.
  • the lane line that is, line_1 can be placed in the coordinate system. so that the end point of the lane line is located on the coordinate axis of the coordinate system, such as the x-axis of the abscissa, and then the relative position of any point in the lane line and the start point of the lane line can be determined according to the coordinate system, and the relative position can be The ordinate of any point in the coordinate system.
  • Step 305 Determine the target map road information matching the real-time road information according to the map relative position and the real-time relative position;
  • the relative positions on the map of the first target point on the map and multiple other endpoints in the map data can be determined, and the relative positions between the first real-time target point and the multiple other endpoints in the real-time road information can be determined.
  • Real-time relative position which in turn can determine multiple map relative positions and real-time relative positions.
  • the endpoints in the combination of multiple lane lines can be the same as the real-time road information.
  • the end points of the middle lane line are in one-to-one correspondence, and then the end points corresponding to the real-time relative position in the relative position of the map can be determined.
  • the lane line segment information of the real-time road information can be the same as the lane line segment information of the positioning road information, that is, the lane lines of the real-time road information can be divided into 14 lane lines, and the lane line combination can include 14 lane lines , then the first segment of the lane line in the real-time road information can correspond to the first segment of the lane line combination, and the end point of the first segment of the lane line in the real-time road information can also be the same as the first segment in the lane line combination.
  • the endpoints of the segment lane lines correspond to.
  • the matching error value between the map relative position and the real-time relative position can be iteratively calculated, and the map lane line corresponding to the map relative position when the matching error value is the smallest and the real-time lane line corresponding to the real-time relative position can be used as a match. , that is, determine the target map road information that matches the real-time road information.
  • the ordinates of multiple points in the coordinate system in multiple lane line combinations can be determined respectively, the ordinates of multiple points in the coordinate system of lane lines in real-time road information can be determined, and then the corresponding endpoints can be calculated iteratively The matching error value of the ordinate between them is determined, so that when the matching error value is the smallest, the corresponding lane line combination is determined as the lane line combination matching the lane lines in the real-time road information.
  • the matching error value of the first segment of the lane line in the lane line of the real-time road information and the first segment of the lane line in the combination of the lane line can be calculated, and the matching error value up to the fourteenth segment of the lane line can be calculated continuously.
  • the matching error value is summed and divided by the length of the lane line, and then the matching error value of the combination of the lane line and the lane line of the real-time road information can be determined, and the combination of the lane line and the lane line of the real-time road information with the smallest matching error value can be determined as: matching lane lines.
  • Step 306 from the real-time road information, determine the second real-time target point, and from the target map road information, determine the second map target point that matches the second real-time target point;
  • the lane line corresponding to the lane line information in the real-time road information can be determined, and the position information of any point in the lane line can be determined.
  • the position information of any point in the matched lane line combination can be determined.
  • the location information of the end endpoints in the lane lines corresponding to the real-time road information can be determined, and the location information of the end endpoints in the matched lane line combination can be determined.
  • Step 307 performing positioning correction on the vehicle according to the second real-time target point and the second map target point.
  • the difference value between the second real-time target point and the second map target point can be calculated, and then the correction information of the vehicle positioning information can be calculated according to the difference value to The correction information corrects the positioning information of the vehicle, such as correcting the positioning information of the vehicle by displacement and/or rotation.
  • the correction information may include position correction information and deflection correction information.
  • correction information can be calculated by the following formula:
  • P i and P i ' may be the lane line combination in the map data and the position information of the end point of the lane line matching in the real-time road information, respectively, R may be the position correction information, t may be the deflection correction information, and J may be The cost function is used for determining multiple values according to the position information of the endpoint, determining the smallest value among the multiple values, and determining R and t corresponding to the smallest value as correction information.
  • the real-time relative position of other positions in the lane line and the first real-time target point determine the target map road information that matches the real-time road information, and determine the second real-time target point from the real-time road information, And from the target map road information, determine the second map target point that matches the second real-time target point, according to the second real-time target point and the second map target point, carry out the positioning correction of the vehicle, and realize the road in different road types.
  • the positioning accuracy of the vehicle is ensured, the accuracy of dead reckoning is improved, and the driving safety of the vehicle is improved.
  • the current lane line of the vehicle can be sensed in real time through the perception system in the vehicle, and then the length L of the lane line_1 perceived in real time can be calculated through image processing, ultrasonic ranging, etc.;
  • the lane line within the accuracy range can be intercepted from the lane line corresponding to the map data, and then the lane line perceived in real time and the intercepted map data can be compared according to the preset length.
  • the lane line is divided, for example, the real-time perceived lane line and the lane line in the intercepted map data can be divided into multiple points according to the distance d on the lane line for division;
  • the lane lines in the divided map data can be combined according to the real-time lane line length and the order of the lane lines;
  • the end point of one segment of the lane line in the divided map data can be determined as the starting point.
  • the end point of the first segment of the lane line can be determined as the starting point, and then a sliding window of length L can be used to slide from the starting point to the end point. That is, the distance of length L is slid from the starting point, and the lane line in the sliding window can be determined as line_i;
  • the lane line line_i of different starting points can be determined, and then the matching degree of each line_i and the real-time lane line line_1 can be calculated. As shown in Figure 3b, it can be based on the starting point of line_i and line_1 respectively.
  • the ordinates of the points corresponding to each other in line_i and line_1 can be made difference, and the absolute value of the difference can be taken, the absolute value can be summed, and divided by the real-time perceived length L of the lane line line_1 , and then the matching error value M can be obtained.
  • the window with the smallest M value can be selected, that is, the corresponding line_i can be selected, and then it can be determined that line_i is the lane line matching line_1.
  • 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:
  • the real-time road information late module 501 is used to obtain real-time road information when it is detected that the vehicle is on a road of the target road type;
  • a map road information determination module 502 configured to acquire map data, and from the map data, determine a plurality of map road information
  • a target map road information determining module 503, configured to determine target map road information matching the real-time road information from the plurality of map road information;
  • the correction module 504 is configured to correct the positioning of the vehicle according to the real-time road information and the target map road information.
  • the map road information determining module 502 further includes:
  • a positioning information acquisition sub-module for acquiring the positioning information of the vehicle
  • a positioning road information determination submodule configured to determine the positioning road information corresponding to the positioning information from the map data
  • a plurality of map road information determining sub-modules are used for determining a plurality of map road information according to the positioning road information.
  • the multiple map road information determination submodules further include:
  • a real-time lane line length determination unit configured to determine the real-time lane line length corresponding to the real-time road information
  • a segment information determining unit configured to determine lane line segment information for the positioning road information according to the real-time lane line length
  • a corresponding map road information determining unit configured to determine a plurality of map road information corresponding to the positioning road information according to the lane line segment information.
  • the target map road information determination module 503 further includes:
  • a map relative position determination sub-module used to determine the first map target point from the map lane line corresponding to the map road information, and determine that other positions in the map lane line are relative to the map of the first map target point Location;
  • the real-time relative position determination submodule is used to determine the first real-time target point from the real-time lane line corresponding to the real-time road information, and determine the real-time relative position between other positions in the real-time lane line and the first real-time target point Location;
  • the matched target map road information determination submodule is configured to determine the target map road information matched with the real-time road information according to the map relative position and the real-time relative position.
  • the correction module 504 further includes:
  • the second map target point determination submodule is configured to determine a second real-time target point from the real-time road information, and determine a second map matching the second real-time target point from the target map road information Target;
  • a positioning correction sub-module configured to perform positioning correction on the vehicle according to the second real-time target point and the second map target point.
  • the device further includes:
  • a road type determination module configured to determine the road type of the road where the vehicle is located in the map data.
  • the real-time relative position of other positions in the lane line and the first real-time target point determine the target map road information that matches the real-time road information, and determine the second real-time target point from the real-time road information, And from the target map road information, determine the second map target point that matches the second real-time target point, according to the second real-time target point and the second map target point, carry out the positioning correction of the vehicle, and realize the road in different road types.
  • the positioning accuracy of the vehicle is ensured, the accuracy of dead reckoning is improved, and the driving safety of the vehicle is improved.
  • 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 locating a vehicle.
  • 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 locating a vehicle 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)
  • Automation & Control Theory (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Navigation (AREA)
  • Traffic Control Systems (AREA)

Abstract

提供了一种车辆定位的方法及装置、车辆、存储介质,该方法包括:在检测到车辆处于目标道路类型的道路时,获取实时道路信息(101);获取地图数据,并从地图数据中,确定多个地图道路信息(102);从多个地图道路信息中,确定与实时道路信息匹配的目标地图道路信息(103);根据实时道路信息和目标地图道路信息,对车辆的定位进行修正(104)。该方法实现了在不同道路类型的道路中进行准确地定位修正,保证了定位的精确度,提供了航位推算的准确性,提高了车辆行驶的安全性。

Description

一种车辆定位的方法及装置、车辆、存储介质
交叉引用
本申请要求2020年9月8日递交的发明名称为“一种车辆定位的方法及装置、车辆、存储介质”的申请号为202010936807.1的在先申请优先权,上述在先申请的内容以引入的方式并入本文本中。
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及装置、车辆、存储介质。
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。
在现有技术中,可以通过卫星地图进行定位,然而,通过地图进行定位容易受到地图精度的影响,进而不能保证定位的精确度,而且,当车辆处于不同类型的道路,如处于弯道时,会使得车辆在地图中的轨迹规律变得复杂,难以在不同类型的道路中实现准确定位,降低了航位推算的准确性,降低了车辆行驶的安全性。
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及装置、车辆、存储介质,包括:
一种车辆定位的方法,所述方法包括:
在检测到车辆处于目标道路类型的道路时,获取实时道路信息;
获取地图数据,并从所述地图数据中,确定多个地图道路信息;
从所述多个地图道路信息中,确定与所述实时道路信息匹配的目标地图道路信息;
根据所述实时道路信息和所述目标地图道路信息,对所述车辆的定位进行修正。
可选地,所述从所述地图数据中,确定多个地图道路信息,包括:
获取所述车辆的定位信息;
从所述地图数据中,确定所述定位信息对应的定位道路信息;
根据所述定位道路信息,确定多个地图道路信息。
可选地,所述根据所述定位道路信息,确定多个地图道路信息,包括:
确定所述实时道路信息对应的实时车道线长度;
根据所述实时车道线长度,确定针对所述定位道路信息的车道线分段信息;
根据所述车道线分段信息,确定所述定位道路信息对应的多个地图道路信息。
可选地,所述从所述多个地图道路信息中,确定与所述实时道路信息匹配的目标地图道路信息,包括:
从所述地图道路信息对应的地图车道线中,确定第一地图目标点,并确定所述地图车道线中其他位置与所述第一地图目标点的地图相对位置;
从所述实时道路信息对应的实时车道线中,确定第一实时目标点,并确定所述实时车道线中其他位置与所述第一实时目标点的实时相对位置;
根据所述地图相对位置和所述实时相对位置,确定与所述实时道路信息匹配的目标地图道路信息。
可选地,所述根据所述实时道路信息和所述目标地图道路信息,对所述车辆进行定位修正,包括:
从所述实时道路信息中,确定第二实时目标点,并从所述目标地图道路信息中,确定与所述第二实时目标点匹配的第二地图目标点;
根据所述第二实时目标点和所述第二地图目标点,对所述车辆进行定位修正。
可选地,所述在检测到车辆处于目标道路类型的道路时,获取实时道路信息之前,还包括:
在所述地图数据中,确定所述车辆所处道路的道路类型。
可选地,所述目标道路类型为弯道类型。
一种车辆定位的装置,所述装置包括:
实时道路信息后期模块,用于在检测到车辆处于目标道路类型的道路时,获取实时道路信息;
地图道路信息确定模块,用于获取地图数据,并从所述地图数据中,确定多个地图道路信息;
目标地图道路信息确定模块,用于从所述多个地图道路信息中,确定与所述实时道路信息匹配的目标地图道路信息;
修正模块,用于根据所述实时道路信息和所述目标地图道路信息,对所述车辆的定位进行修正。
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,通过在检测到车辆处于目标道路类型的道路时,获取实时道路信息,获取地图数据,并从地图数据中,确定多个地图道路信息,从多个地图道路信息中,确定与实时道路信息匹配的目标地图道路信息,根据实时道路信息和目标地图道路信息,对车辆的定位进行修正,实现了在不同道路类型的道路中进行准确地定位修正,保证了定位的精确度,提供了航位推算的准确性,提高了车辆行驶的安全性。
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1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2a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2b是本发明一实施例提供的一种车道线确定的实例的示意图;
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地图中的车道线的实例的示意图;
图3c是本发明一实施例提供的一种实时感知的车道线的实例的示意图;
图4是本发明一实施例提供的一种车道线匹配的实例的流程图;
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1,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,在检测到车辆处于目标道路类型的道路时,获取实时道路信息;
其中,道路类型可以包括直道类型、弯道类型、岔道类型,目标道路类型可以为弯道类型,实时道路信息可以包括但不仅仅限于车道线信息、路肩线信息、墙沿线信息,路肩线信息可以为道路中的路肩的边缘线信息,墙沿信息可以为当车辆处于停车场时的墙壁的边缘线信息。
在实际的行驶过程中,可以检测车辆当前所处的道路的道路类型,在检测到车辆处于弯道类型的道路时,可以通过车辆中的感知系统来获取车辆当前所处的道路的实时道路信息。
在检测到车辆处于非弯道类型的道路时,例如,当车辆处于直道类型的道路时,可以通过车辆中的导航定位系统进行定位。
在本发明一实施例中,在步骤101之前,还可以包括如下步骤:
在地图数据中,确定车辆所处道路的道路类型;
其中,地图数据可以为语义地图数据,语义地图数据可以包括语义信息,语义信息可以包括但不仅仅限于道路信息、停车位信息,道路信息可以包括但不仅仅限于道路的车道线信息、墙沿线信息。
在实际的行驶过程中,可以从云端实时下载地图数据,也可以从车辆中预置的地图数据库中实时获取地图数据,进而可以在地图数据中确定当前车辆所处的道路的地图数据。
在确定针对当前道路的地图数据后,可以获取当前道路的车道线信息,进而可以根据车道线信息计算当前道路的线性相关系数,以确定当前道路是否为弯道类型的道路。
其中,线性相关系数可以用于表示当前道路为直线的程度,线性相关系数可以为皮尔逊相关系数。
在实际应用中,可以获取当前道路的车道线信息中至少两个点的位置信息,如端点的位置信息,进而可以根据至少两个点的位置信息计算点与点之间的线性相关系数,可以设置线性相关系数阈值为0.9,当线性相关系数为0.7,小于线性相关系数阈值时,可以确定当前道路为弯道类型的道路,当线性相关系数为0.99,大于线性相关系数阈值时,可以确定当前道路为直道类型的道路。
在本发明一实施例中,在确定针对当前道路的地图数据后,可以通过车辆中的感知模块来获取车辆当前所处的道路的车道线信息,例如,可以通过车辆中的摄像头来获取车辆当前所处的道路的图像,进而可以对该图像进行处理,以获取车辆当前所处的道路的车道线信息,也可以基于车辆建立针对当前所处的道路的坐标系,进而可以根据该图像确定车道线信息在坐标系中的坐标,以在坐标系中确定车辆当前所处的道路的车道线信息。
当车辆当前所处的道路中没有车道线时,如地下停车场的道路或乡村道路,可以通过车辆中的感知模块来获取车辆当前所处的道路的墙沿线信息或路肩信息,并将墙沿线信息或路肩信息作为车辆当前所处的道路的车道线信息。
在获取当前道路的车道线信息后,可以根据车道线信息计算当前道路的线性相关系数,以确定当前道路是否为弯道类型的道路。
作为一示例,感知系统还可以采用但不仅仅限于超声波和/或红外线进行感知。
步骤102,获取地图数据,并从地图数据中,确定多个地图道路信息;
其中,地图道路信息可以为地图数据中的道路信息。
由于在确定车辆所处道路的道路类型时,可以从云端下载针对当前道路的地图数据,也可以从车辆中预置的地图数据库中获取针对当前道路的地图数据,进而可以根据地图数据中的定位精度信息从地图数据中确定当前道路的道路信息。
例如,可以确定地图数据的定位精度信息为200厘米,而实时道路信息的车道线信息对应的车道线的长度可以为500厘米,进而可以根据定位精度信息从地图数据中确定精度范围内的当前道路的车道线信息,也就是可以从地图数据中确定700厘米的车道线。
在确定当前道路的道路信息后,可以将道路信息进行划分,进而可以确定多个地图 道路信息。
例如,可以确定当前道路的车道线信息,进而可以对车道线信息所对应的车道线进行划分,以确定多段车道线信息。
步骤103,从多个地图道路信息中,确定与实时道路信息匹配的目标地图道路信息;
在确定多个地图道路信息后,可以将多个地图道路信息与实时道路信息进行匹配,进而可以确定多个地图道路信息中与实时道路信息匹配的地图道路信息,即目标地图道路信息。
例如,多个地图道路信息可以包括A地图道路信息、B地图道路信息以及C地图道路信息,可以将A地图道路信息、B地图道路信息以及C地图道路信息与实时道路信息进行匹配,可以确定B地图道路信息为与实时道路信息匹配的地图道路信息。
步骤104,根据实时道路信息和目标地图道路信息,对车辆的定位进行修正。
其中,车辆的定位可以为通过车辆中的导航定位系统确定当前车辆在地图数据中的定位。
在确定目标地图道路信息后,可以根据实时道路信息和目标地图道路信息确定车辆定位的修正信息,进而可以在地图数据中根据该修正信息对车辆的定位进行修正,如通过位移和/或旋转对车辆的定位进行修正。
例如,地图数据可以包括A地图道路信息、B地图道路信息以及C地图道路信息,可以通过车辆中的导航定位系统确定当前车辆在地图数据中的定位为A地图道路信息对应的A道路,可以确定目标地图道路信息为B地图道路信息,进而可以根据A地图道路信息和B地图道路信息确定车辆定位的修正信息,可以在地图数据中根据该修正信息对车辆进行位移和旋转,以对车辆的定位进行修正。
在本发明实施例中,通过在检测到车辆处于目标道路类型的道路时,获取实时道路信息,获取地图数据,并从地图数据中,确定多个地图道路信息,从多个地图道路信息中,确定与实时道路信息匹配的目标地图道路信息,根据实时道路信息和目标地图道路信息,对车辆的定位进行修正,实现了在不同道路类型的道路中进行准确地定位修正,保证了定位的精确度,提高了航位推算的准确性,提高了车辆行驶的安全性。
参照图2a,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,在检测到车辆处于目标道路类型的道路时,获取实时道路信息;
步骤202,获取地图数据,并获取车辆的定位信息;
其中,定位信息可以为车辆在地图数据中的定位信息。
在获取实时道路信息后,可以从云端下载针对当前道路的地图数据,也可以从车辆中预置的地图数据库中获取针对当前道路的地图数据,进而可以根据车辆中的导航定位系统实时确定车辆在地图数据中的定位信息。
步骤203,从地图数据中,确定定位信息对应的定位道路信息;
其中,定位道路信息可以为在地图数据中与定位信息对应的道路信息。
在获取车辆的定位信息后,可以根据定位信息和地图数据中的定位精度信息确定车辆在地图数据中所处的道路信息。
如2b所示,可以根据地图数据中的定位精度信息从地图数据中确定车辆当前所处的道路信息,也即是可以确定地图数据中截取的车道线的范围,进而可以从地图数据中确定比实时道路信息的车道线的长度更长的车道线,也即是地图中的车道线的长度大于实时感知的车道线的长度。
例如,实时道路信息的车道线的长度可以为5米,地图数据中的车道线的长度可以为7米,也即是定位道路信息中的车道线的长度可以为7米。
步骤204,根据定位道路信息,确定多个地图道路信息;
在确定定位道路信息后,可以将定位道路信息进行划分,进而可以确定地图数据中多个道路信息。
例如,可以确定定位道路信息中的车道线信息,进而可以对车道线信息所对应的车道线进行划分,以确定多段车道线信息。
在本发明一实施例中,步骤204可以包括如下子步骤:
子步骤11,确定实时道路信息对应的实时车道线长度;
在确定定位道路信息后,可以确定实时道路信息中的车道线信息,进而可以确定对应的车道线,并实时确定车道线的长度。
在实际应用中,由于车辆中的感知系统具有一定感知范围,也即是感知到的车道线应当是在一定的长度范围内,则需要实时确定感知到的车道线的长度,例如,感知系统 的感知范围可以是5米,若实际的车道线长度为6米,则感知系统所感知到的车道线应当是5米,若实际的车道线长度为4米,则感知系统所感知到的车道线应当是4米。
子步骤12,根据实时车道线长度,确定针对定位道路信息的车道线分段信息;
其中,车道线分段信息可以是对定位道路信息中车道线信息所对应的车道线进行划分。
在确定实时车道线长度后,可以按照预置的长度对定位道路信息中车道线信息对应的车道线进行划分,也可以按照预置的段数对该车道线进行等距划分,进而可以得到定位道路信息的车道线分段信息。
例如,若实时车道线长度为5米,定位道路信息中的车道线的长度可以为7米,而预置的段数可以为10段,则可以对车道线进行等距划分,进而可以确定车道线分段信息为每隔0.5米进行划分,可以得到14段0.5米的车道线的车道线信息。
又如,若实时车道线长度可以为5米,定位道路信息中的车道线的长度可以为7米,而预置的长度可以为2米,则可以按照预置的长度对车道线进行划分,即对车道线分段信息可以为每隔2米进行划分,进而可以得到3段2米的车道线和1段1米的车道线的道路信息。
在本发明一实施例中,在确定实时车道线长度后,可以按照预置的长度对实时道路信息对应的车道线进行划分,也可以按照预置的段数对实时道路信息对应的车道线进行等距划分,进而可以得到实时道路信息的车道线分段信息。
其中,实时道路信息的车道线分段信息可以与定位道路信息的车道线分段信息相同。
子步骤13,根据车道线分段信息,确定定位道路信息对应的多个地图道路信息。
在确定定位道路信息的车道线分段信息后,可以按照车道线分段信息对定位道路信息中车道线信息对应的车道线进行划分,进而可以确定多段车道线。
在得到多段车道线后,可以根据实时车道线长度和多段车道线的顺序对多段车道线进行组合,进而可以得到多个与实时车道线长度相等的车道线组合。
例如,可以按照车道线的顺序对14段车道线进行组合,进而可以确定第1段至第11段车道线组合、第2段至第12段车道线组合、第3段至第13段车道线组合、第4段至第14段车道线组合,且每一个车道线组合的长度均与实时车道线长度相等。
步骤205,从多个地图道路信息中,确定与实时道路信息匹配的目标地图道路信息;
步骤206,根据实时道路信息和目标地图道路信息,对车辆的定位进行修正。
在本发明实施例中,通过在检测到车辆处于目标道路类型的道路时,获取实时道路信息,获取地图数据,并获取车辆的定位信息,从地图数据中,确定定位信息对应的定位道路信息,根据定位道路信息,确定多个地图道路信息,从多个地图道路信息中,确定与实时道路信息匹配的目标地图道路信息,根据实时道路信息和目标地图道路信息,对车辆的定位进行修正,实现了在不同道路类型的道路中进行准确地定位修正,保证了定位的精确度,并基于精确的定位提高了航位推算的准确性,提高了车辆行驶的安全性。
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,在检测到车辆处于目标道路类型的道路时,获取实时道路信息;
步骤302,获取地图数据,并从地图数据中,确定多个地图道路信息;
步骤303,从地图道路信息对应的地图车道线中,确定第一地图目标点,并确定地图车道线中其他位置与第一地图目标点的地图相对位置;
其中,地图目标点可以为地图数据中车道线的任意一点,如端点。
在确定多个地图道路信息后,如在确定多段车道线组合后,可以分别确定车道线组合中任意一目标点的位置信息,如确定车道线组合的开端端点的位置信息,并确定该车道线组合中另外一点的位置信息,如确定车道线组合的末端端点的位置信息,进而可以根据位置信息确定该目标点与另外一点的相对位置信息。
在实际应用中,可以确定车道线组合的开端端点的位置信息,并以该开端端点为原点建立坐标系,如图3b所示,可以将该车道线组合,也即是将line_i在坐标系中进行旋转,以使得该车道线组合的末端端点位于坐标系的坐标轴上,如横坐标x轴,进而可以根据坐标系确定该车道线组合中任意一点与开端端点的相对位置,相对位置可以为任意一点在坐标系中的纵坐标。
步骤304,从实时道路信息对应的实时车道线中,确定第一实时目标点,并确定实时车道线中其他位置与第一实时目标点的实时相对位置;
其中,实时目标点可以为实时车道线对应的车道线中的任意一点,如端点。
在确定地图相对位置后,可以确定实时道路信息中车道线信息对应的车道线,可以 确定车道线中任意一目标点的位置信息,如开端端点的位置信息,并确定车道线中另外一点的位置信息,如另外一个端点的位置信息,进而可以根据位置信息确定该目标点与另外一点的相对位置信息。
在实际应用中,可以确定实时道路信息中车道线的开端端点的位置信息,并以该开端端点为原点建立坐标系,如图3c所示,可以将车道线,也即是将line_1在坐标系中进行旋转,以使得车道线的末端端点位于坐标系的坐标轴上,如横坐标x轴,进而可以根据坐标系确定车道线中任意一点与车道线的开端端点的相对位置,相对位置可以为任意一点在坐标系中的纵坐标。
步骤305,根据地图相对位置和实时相对位置,确定与实时道路信息匹配的目标地图道路信息;
由于在确定地图相对位置和实时相对位置时,可以确定地图数据中第一地图目标点与多个其他端点的地图相对位置,以及可以确定实时道路信息中第一实时目标点与多个其他端点的实时相对位置,进而可以确定多个地图相对位置和实时相对位置。
在确定多个地图相对位置和实时相对位置后,由于实时道路信息的车道线分段信息可以与定位道路信息的车道线分段信息相同,则多个车道线组合中的端点可以与实时道路信息中车道线的端点一一对应,进而可以确定地图相对位置中与实时相对位置对应的端点。
例如,由于实时道路信息的车道线分段信息可以与定位道路信息的车道线分段信息相同,即实时道路信息的车道线可以划分为14段车道线,车道线组合中可以包括14段车道线,则实时道路信息的车道线中第一段车道线可以与车道线组合中第一段车道线对应,实时道路信息的车道线中第一段车道线的端点也可以与车道线组合中第一段车道线的端点对应。
在确定对应的端点后,可以迭代计算地图相对位置和实时相对位置之间的匹配误差值,可以将匹配误差值最小时地图相对位置对应的地图车道线与实时相对位置对应的实时车道线作为匹配的车道线,即确定与实时道路信息匹配的目标地图道路信息。
在实际应用中,可以分别确定多个车道线组合中多点在坐标系中的纵坐标,可以确定实时道路信息中车道线的多点在坐标系中的纵坐标,进而可以迭代计算对应的端点之间纵坐标的匹配误差值,以在匹配误差值最小时,确定对应的车道线组合为与实时道路 信息中的车道线匹配的车道线组合。
例如,可以计算实时道路信息的车道线中第一段车道线与车道线组合中第一段车道线的匹配误差值,并继续计算至第十四段车道线的匹配误差值,可以对多个匹配误差值进行求和并除以车道线的长度,进而可以确定实时道路信息的车道线与车道线组合的匹配误差值,以确定匹配误差值最小的实时道路信息的车道线与车道线组合为匹配的车道线。
步骤306,从实时道路信息中,确定第二实时目标点,并从目标地图道路信息中,确定与第二实时目标点匹配的第二地图目标点;
在确定与实时道路信息匹配的目标地图道路信息后,可以确定实时道路信息中车道线信息对应的车道线,可以确定车道线中任意一点的位置信息。
在确定实时道路信息对应的车道线中的任意一点后,可以确定匹配的车道线组合中的任意一点的位置信息。
在实际应用中,可以确定实时道路信息对应的车道线中的末端端点的位置信息,以及确定匹配的车道线组合中的末端端点的位置信息。
步骤307,根据第二实时目标点和第二地图目标点,对车辆进行定位修正。
在确定第二实时目标点和第二地图目标点后,可以计算第二实时目标点和第二地图目标点之间的差异值,进而可以根据该差异值计算车辆定位信息的修正信息,以根据该修正信息对车辆的定位信息进行修正,如通过位移和/或旋转对车辆的定位信息进行修正。
作为一示例,修正信息可以包括位置修正信息、偏转修正信息。
在实际应用中,修正信息可以通过以下公式进行计算:
Figure PCTCN2021102161-appb-000001
其中,P i和P i’可以分别为地图数据中的车道线组合和实时道路信息中的车道线匹配的端点的位置信息,R可以为位置修正信息,t可以为偏转修正信息,J可以为代价函数,用于根据端点的位置信息确定多个值,并确定多个值中最小的值,以及确定最小的值所对应的R和t确定为修正信息。
在本发明实施例中,通过在检测到车辆处于目标道路类型的道路时,获取实时道路 信息,获取地图数据,并从地图数据中,确定多个地图道路信息,从地图道路信息对应的地图车道线中,确定第一地图目标点,并确定地图车道线中其他位置与第一地图目标点的地图相对位置,从实时道路信息对应的实时车道线中,确定第一实时目标点,并确定实时车道线中其他位置与第一实时目标点的实时相对位置,根据地图相对位置和实时相对位置,确定与实时道路信息匹配的目标地图道路信息,从实时道路信息中,确定第二实时目标点,并从目标地图道路信息中,确定与第二实时目标点匹配的第二地图目标点,根据第二实时目标点和第二地图目标点,对车辆进行定位修正,实现了在不同道路类型的道路中进行准确地定位,并基于实时目标点和地图目标点对车辆的定位进行修正,保证了定位的精确度,提高了航位推算的准确性,提高了车辆行驶的安全性。
以下结合图4对本发明一车道线匹配的实施例进行示例性说明:
1、在实际匹配的过程中,可以通过车辆中的感知系统实时感知车辆当前所处的车道线,进而可以通过图像处理、超声波测距等方式计算实时感知的车道线line_1的长度L;
2、在计算实时感知的车道线的长度后,可以从地图数据对应的车道线中截取精度范围内的车道线,进而可以按照预置的长度对实时感知的车道线和截取的地图数据中的车道线进行划分,例如,可以按照车道线上的距离d将实时感知的车道线和截取的地图数据中的车道线等分成多个点,以进行划分;
3、在对实时感知的车道线和截取的地图数据中的车道线进行划分后,可以根据实时车道线长度和车道线的顺序对划分后的地图数据中的车道线进行组合;
在实际应用中,可以确定划分后的地图数据中其中一段的车道线的端点为起点,如确定第1段车道线的端点为起点,进而可以用长度为L的滑动窗口从起点滑动到终点,即从起点开始滑动了长度为L的距离,可以将滑动窗口内的车道线确定为line_i;
4、由于在确定地图数据中的line_i时,可以确定不同起点的车道线line_i,进而可以计算每个line_i与实时车道线line_1的匹配度,如图3b所示,可以分别基于line_i与line_1的起点,也即是基于近端点建立坐标系,并分别将line_i与line_1在坐标系中进行旋转,以使得line_i与line_1的末端端点,也即是远端点位于坐标系的横坐标x轴上,进而可以确定line_i与line_1中互相对应的点的纵坐标,以对纵坐标进行计算,得到匹配误差值;
在实际应用中,可以对line_i与line_1中互相对应的点的纵坐标进行做差,并取差值的绝对值,可以对绝对值进行求和,并除以实时感知的车道线line_1的长度L,进而可以得到匹配误差值M。
5、在得到匹配误差值M后,可以选取M值最小的窗口,也即是选取对应的line_i,进而可以确定line_i为与line_1匹配的车道线。
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:
实时道路信息后期模块501,用于在检测到车辆处于目标道路类型的道路时,获取实时道路信息;
地图道路信息确定模块502,用于获取地图数据,并从所述地图数据中,确定多个地图道路信息;
目标地图道路信息确定模块503,用于从所述多个地图道路信息中,确定与所述实时道路信息匹配的目标地图道路信息;
修正模块504,用于根据所述实时道路信息和所述目标地图道路信息,对所述车辆的定位进行修正。
在本发明一实施例中,所述地图道路信息确定模块502还包括:
定位信息获取子模块,用于获取所述车辆的定位信息;
定位道路信息确定子模块,用于从所述地图数据中,确定所述定位信息对应的定位道路信息;
多个地图道路信息确定子模块,用于根据所述定位道路信息,确定多个地图道路信息。
在本发明一实施例中,所述多个地图道路信息确定子模块,还包括:
实时车道线长度确定单元,用于确定所述实时道路信息对应的实时车道线长度;
分段信息确定单元,用于根据所述实时车道线长度,确定针对所述定位道路信息的车道线分段信息;
对应地图道路信息确定单元,用于根据所述车道线分段信息,确定所述定位道路信息对应的多个地图道路信息。
在本发明一实施例中,所述目标地图道路信息确定模块503,还包括:
地图相对位置确定子模块,用于从所述地图道路信息对应的地图车道线中,确定第一地图目标点,并确定所述地图车道线中其他位置与所述第一地图目标点的地图相对位置;
实时相对位置确定子模块,用于从所述实时道路信息对应的实时车道线中,确定第一实时目标点,并确定所述实时车道线中其他位置与所述第一实时目标点的实时相对位置;
匹配的目标地图道路信息确定子模块,用于根据所述地图相对位置和所述实时相对位置,确定与所述实时道路信息匹配的目标地图道路信息。
在本发明一实施例中,所述修正模块504,还包括:
第二地图目标点确定子模块,用于从所述实时道路信息中,确定第二实时目标点,并从所述目标地图道路信息中,确定与所述第二实时目标点匹配的第二地图目标点;
定位修正子模块,用于根据所述第二实时目标点和所述第二地图目标点,对所述车辆进行定位修正。
在本发明一实施例中,所述装置还包括:
道路类型确定模块,用于在所述地图数据中,确定所述车辆所处道路的道路类型。
在本发明实施例中,通过在检测到车辆处于目标道路类型的道路时,获取实时道路信息,获取地图数据,并从地图数据中,确定多个地图道路信息,从地图道路信息对应的地图车道线中,确定第一地图目标点,并确定地图车道线中其他位置与第一地图目标点的地图相对位置,从实时道路信息对应的实时车道线中,确定第一实时目标点,并确定实时车道线中其他位置与第一实时目标点的实时相对位置,根据地图相对位置和实时相对位置,确定与实时道路信息匹配的目标地图道路信息,从实时道路信息中,确定第 二实时目标点,并从目标地图道路信息中,确定与第二实时目标点匹配的第二地图目标点,根据第二实时目标点和第二地图目标点,对车辆进行定位修正,实现了在不同道路类型的道路中进行准确地定位,并基于实时目标点和地图目标点对车辆的定位进行修正,保证了定位的精确度,提高了航位推算的准确性,提高了车辆行驶的安全性。
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(系统)、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及装置、车辆、存储介质,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 (10)

  1. 一种车辆定位的方法,其特征在于,所述方法包括:
    在检测到车辆处于目标道路类型的道路时,获取实时道路信息;
    获取地图数据,并从所述地图数据中,确定多个地图道路信息;
    从所述多个地图道路信息中,确定与所述实时道路信息匹配的目标地图道路信息;
    根据所述实时道路信息和所述目标地图道路信息,对所述车辆的定位进行修正。
  2. 根据权利要求1所述的方法,其特征在于,所述从所述地图数据中,确定多个地图道路信息,包括:
    获取所述车辆的定位信息;
    从所述地图数据中,确定所述定位信息对应的定位道路信息;
    根据所述定位道路信息,确定多个地图道路信息。
  3. 根据权利要求2所述的方法,其特征在于,所述根据所述定位道路信息,确定多个地图道路信息,包括:
    确定所述实时道路信息对应的实时车道线长度;
    根据所述实时车道线长度,确定针对所述定位道路信息的车道线分段信息;
    根据所述车道线分段信息,确定所述定位道路信息对应的多个地图道路信息。
  4. 根据权利要求1或2或3所述的方法,其特征在于,所述从所述多个地图道路信息中,确定与所述实时道路信息匹配的目标地图道路信息,包括:
    从所述地图道路信息对应的地图车道线中,确定第一地图目标点,并确定所述地图车道线中其他位置与所述第一地图目标点的地图相对位置;
    从所述实时道路信息对应的实时车道线中,确定第一实时目标点,并确定所述实时车道线中其他位置与所述第一实时目标点的实时相对位置;
    根据所述地图相对位置和所述实时相对位置,确定与所述实时道路信息匹配的目标地图道路信息。
  5. 根据权利要求4所述的方法,其特征在于,所述根据所述实时道路信息和所述目标地图道路信息,对所述车辆进行定位修正,包括:
    从所述实时道路信息中,确定第二实时目标点,并从所述目标地图道路信息中,确定与所述第二实时目标点匹配的第二地图目标点;
    根据所述第二实时目标点和所述第二地图目标点,对所述车辆进行定位修正。
  6. 根据权利要求1所述的方法,其特征在于,在所述在检测到车辆处于目标道路类型的道路时,获取实时道路信息之前,还包括:
    在所述地图数据中,确定所述车辆所处道路的道路类型。
  7. 根据权利要求1所述的方法,其特征在于,所述目标道路类型为弯道类型。
  8. 一种车辆定位的装置,其特征在于,所述装置包括:
    实时道路信息后期模块,用于在检测到车辆处于目标道路类型的道路时,获取实时道路信息;
    地图道路信息确定模块,用于获取地图数据,并从所述地图数据中,确定多个地图道路信息;
    目标地图道路信息确定模块,用于从所述多个地图道路信息中,确定与所述实时道路信息匹配的目标地图道路信息;
    修正模块,用于根据所述实时道路信息和所述目标地图道路信息,对所述车辆的定位进行修正。
  9. 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。
  10. 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/CN2021/102161 2020-09-08 2021-06-24 一种车辆定位的方法及装置、车辆、存储介质 WO2022052567A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
EP21798542.3A EP3988968A4 (en) 2020-09-08 2021-06-24 VEHICLE POSITIONING METHOD AND APPARATUS, VEHICLE AND STORAGE MEDIA

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010936807.1 2020-09-08
CN202010936807.1A CN112068171B (zh) 2020-09-08 2020-09-08 一种车辆定位的方法及装置、车辆、存储介质

Publications (1)

Publication Number Publication Date
WO2022052567A1 true WO2022052567A1 (zh) 2022-03-17

Family

ID=73664427

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/102161 WO2022052567A1 (zh) 2020-09-08 2021-06-24 一种车辆定位的方法及装置、车辆、存储介质

Country Status (3)

Country Link
EP (1) EP3988968A4 (zh)
CN (1) CN112068171B (zh)
WO (1) WO2022052567A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114743174A (zh) * 2022-03-21 2022-07-12 北京地平线机器人技术研发有限公司 观测车道线的确定方法、装置、电子设备和存储介质
CN115457769A (zh) * 2022-08-31 2022-12-09 东风商用车有限公司 一种数据修正方法、装置、设备及可读存储介质

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112068171B (zh) * 2020-09-08 2022-02-01 广州小鹏自动驾驶科技有限公司 一种车辆定位的方法及装置、车辆、存储介质
CN112650772B (zh) * 2021-01-08 2022-02-25 腾讯科技(深圳)有限公司 数据处理方法、装置、存储介质及计算机设备
CN112883058A (zh) * 2021-03-23 2021-06-01 北京车和家信息技术有限公司 用于车辆定位的标定方法、装置、设备、车辆和介质
CN115808179A (zh) * 2021-09-14 2023-03-17 华为技术有限公司 一种交通信息获取方法、装置及存储介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2005119177A1 (ja) * 2004-06-02 2005-12-15 Xanavi Informatics Corporation 車載ナビゲーション装置、自車位置補正方法
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
CN111381269A (zh) * 2018-12-28 2020-07-07 沈阳美行科技有限公司 车辆定位方法、装置、电子设备、计算机可读存储介质
CN111507130A (zh) * 2019-01-31 2020-08-07 广州汽车集团股份有限公司 车道级定位方法及系统、计算机设备、车辆、存储介质
CN111524185A (zh) * 2020-04-21 2020-08-11 上海商汤临港智能科技有限公司 定位方法及装置、电子设备和存储介质
CN112068171A (zh) * 2020-09-08 2020-12-11 广州小鹏自动驾驶科技有限公司 一种车辆定位的方法及装置、车辆、存储介质

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4680131B2 (ja) * 2006-05-29 2011-05-11 トヨタ自動車株式会社 自車位置測定装置
CN105910611A (zh) * 2016-06-27 2016-08-31 江苏迪纳数字科技股份有限公司 基于匹配度反馈的道路匹配方法
JP6982430B2 (ja) * 2017-08-03 2021-12-17 株式会社Subaru 車両の走行車線特定装置
KR102441075B1 (ko) * 2017-10-31 2022-09-06 현대자동차주식회사 노면표시기반 차량의 위치추정 방법 및 장치
CN110657812A (zh) * 2018-06-29 2020-01-07 比亚迪股份有限公司 车辆定位方法、装置及车辆
CN109816980A (zh) * 2019-02-20 2019-05-28 东软睿驰汽车技术(沈阳)有限公司 一种确定车辆所处车道的方法及相关装置
CN110207715B (zh) * 2019-06-28 2021-07-13 广州小鹏自动驾驶科技有限公司 车辆定位的修正方法及修正系统
CN110967038B (zh) * 2019-11-25 2021-08-27 广州小鹏自动驾驶科技有限公司 车辆定位方法、车辆定位装置和车辆

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2005119177A1 (ja) * 2004-06-02 2005-12-15 Xanavi Informatics Corporation 車載ナビゲーション装置、自車位置補正方法
CN111381269A (zh) * 2018-12-28 2020-07-07 沈阳美行科技有限公司 车辆定位方法、装置、电子设备、计算机可读存储介质
CN111507130A (zh) * 2019-01-31 2020-08-07 广州汽车集团股份有限公司 车道级定位方法及系统、计算机设备、车辆、存储介质
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
CN111524185A (zh) * 2020-04-21 2020-08-11 上海商汤临港智能科技有限公司 定位方法及装置、电子设备和存储介质
CN112068171A (zh) * 2020-09-08 2020-12-11 广州小鹏自动驾驶科技有限公司 一种车辆定位的方法及装置、车辆、存储介质

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3988968A4 *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114743174A (zh) * 2022-03-21 2022-07-12 北京地平线机器人技术研发有限公司 观测车道线的确定方法、装置、电子设备和存储介质
CN115457769A (zh) * 2022-08-31 2022-12-09 东风商用车有限公司 一种数据修正方法、装置、设备及可读存储介质
CN115457769B (zh) * 2022-08-31 2023-10-13 东风商用车有限公司 一种数据修正方法、装置、设备及可读存储介质

Also Published As

Publication number Publication date
CN112068171B (zh) 2022-02-01
EP3988968A4 (en) 2022-10-19
CN112068171A (zh) 2020-12-11
EP3988968A1 (en) 2022-04-27

Similar Documents

Publication Publication Date Title
WO2022052567A1 (zh) 一种车辆定位的方法及装置、车辆、存储介质
US10288434B2 (en) Map-centric map matching method and apparatus
CN109324337B (zh) 无人飞行器的航线生成及定位方法、装置及无人飞行器
US20230143687A1 (en) Method of estimating three-dimensional coordinate value for each pixel of two-dimensional image, and method of estimating autonomous driving information using the same
US20150199556A1 (en) Method of using image warping for geo-registration feature matching in vision-aided positioning
CN106919567B (zh) 一种兴趣点poi地址的处理方法及装置
CN112232275B (zh) 基于双目识别的障碍物检测方法、系统、设备及存储介质
US10607364B2 (en) Position and attitude determination method and system using edge images
CN110390639A (zh) 正射影像的处理拼接方法、装置、设备及存储介质
EP4012342A1 (en) Data processing method and device
WO2023169337A1 (zh) 目标物速度的估计方法及装置、车辆和存储介质
Han et al. Robust ego-motion estimation and map matching technique for autonomous vehicle localization with high definition digital map
JP2013032953A (ja) 位置判定装置およびナビゲーション装置並びに位置判定方法,プログラム
KR102231563B1 (ko) 고정밀 지도의 항법 링크 매칭 방법
CN109115232B (zh) 导航的方法和装置
CN113984039A (zh) 运动轨迹的校正方法、装置、系统和存储介质
CN113566817B (zh) 一种车辆定位方法及装置
WO2022078301A1 (zh) 一种数据处理的方法和装置
CN111739079A (zh) 一种基于语义特征多源低空立体像对快速匹配方法
CN108197531A (zh) 一种道路曲线检测方法、装置和终端
CN109916417A (zh) 一种地图建立方法、装置、计算机设备及其存储介质
Wong et al. Single camera vehicle localization using SURF scale and dynamic time warping
CN116105755A (zh) 一种车辆定位修正方法、存储介质及终端设备
WO2022077660A1 (zh) 一种车辆定位的方法和装置
CN115507752A (zh) 基于平行环境元素的单目视觉测距方法和系统

Legal Events

Date Code Title Description
ENP Entry into the national phase

Ref document number: 2021798542

Country of ref document: EP

Effective date: 20211110

NENP Non-entry into the national phase

Ref country code: DE