WO2022007602A1 - 确定车辆位置的方法和装置 - Google Patents

确定车辆位置的方法和装置 Download PDF

Info

Publication number
WO2022007602A1
WO2022007602A1 PCT/CN2021/100288 CN2021100288W WO2022007602A1 WO 2022007602 A1 WO2022007602 A1 WO 2022007602A1 CN 2021100288 W CN2021100288 W CN 2021100288W WO 2022007602 A1 WO2022007602 A1 WO 2022007602A1
Authority
WO
WIPO (PCT)
Prior art keywords
cloud data
point cloud
point
vehicle
ground
Prior art date
Application number
PCT/CN2021/100288
Other languages
English (en)
French (fr)
Inventor
孔旗
张金凤
Original Assignee
北京京东乾石科技有限公司
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 北京京东乾石科技有限公司 filed Critical 北京京东乾石科技有限公司
Priority to EP21837352.0A priority Critical patent/EP4130800A4/en
Priority to US18/000,050 priority patent/US20230204384A1/en
Publication of WO2022007602A1 publication Critical patent/WO2022007602A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO 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
    • G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
    • G01S19/38—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
    • G01S19/39—Determining 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
    • G01S19/42—Determining position
    • G01S19/48—Determining position by combining or switching between position solutions derived from the satellite radio beacon positioning system and position solutions derived from a further system
    • G01S19/485—Determining position by combining or switching between position solutions derived from the satellite radio beacon positioning system and position solutions derived from a further system whereby the further system is an optical system or imaging system
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/38—Electronic maps specially adapted for navigation; Updating thereof
    • G01C21/3804—Creation or updating of map data
    • G01C21/3833—Creation or updating of map data characterised by the source of data
    • G01C21/3848—Data obtained from both position sensors and additional sensors
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO 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
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/02—Systems using the reflection of electromagnetic waves other than radio waves
    • G01S17/06—Systems determining position data of a target
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO 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
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/86—Combinations of lidar systems with systems other than lidar, radar or sonar, e.g. with direction finders
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO 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
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/88—Lidar systems specially adapted for specific applications
    • G01S17/93—Lidar systems specially adapted for specific applications for anti-collision purposes
    • G01S17/931—Lidar systems specially adapted for specific applications for anti-collision purposes of land vehicles
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO 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
    • G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
    • G01S19/01—Satellite radio beacon positioning systems transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
    • G01S19/13—Receivers
    • G01S19/14—Receivers specially adapted for specific applications
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO 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
    • G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
    • G01S19/38—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
    • G01S19/39—Determining 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
    • G01S19/42—Determining position
    • G01S19/48—Determining position by combining or switching between position solutions derived from the satellite radio beacon positioning system and position solutions derived from a further system
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO 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
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/88—Lidar systems specially adapted for specific applications
    • G01S17/89—Lidar systems specially adapted for specific applications for mapping or imaging

Definitions

  • the present disclosure relates to the technical field of automatic driving, and in particular, to a method and apparatus for determining the position of a vehicle.
  • determining the real-time position of the vehicle is a very important part. For scenarios where the vehicle may depart from any location, how to determine the real-time location of the vehicle is an urgent problem to be solved.
  • vehicles generally use GPS (Global Positioning System, global positioning system) or GPS/INS (Inertial Navigation System, inertial navigation system) combined equipment to determine the position of the vehicle.
  • GPS Global Positioning System, global positioning system
  • GPS/INS Inertial Navigation System, inertial navigation system
  • a method of determining the location of a vehicle comprising:
  • determining the current location point of the vehicle includes:
  • the first position point currently measured by the GPS is used as the current position point.
  • determining the current location point of the vehicle includes:
  • the predicted value is corrected by using the measured value of the position point at the current moment, a second position point is determined, and the second position point is used as the current position point of the vehicle.
  • the acquiring the measurement value of the position point at the current moment includes:
  • the information of the position point of the laser point cloud data measured by the lidar at the current moment in the point cloud map is taken as the measurement value of the position point at the current moment;
  • the information of the position point measured by the GPS at the current time is used as the measurement value of the position point at the current time.
  • determining the current location point of the vehicle includes:
  • the third position point manually set in the point cloud map is used as the current position point of the vehicle.
  • the matching of the first point cloud data with the second point cloud data, and determining the transformation matrix between the first point cloud data and the second point cloud data includes:
  • a second transformation matrix is determined.
  • the determining the first transformation matrix according to the ground second point cloud data and the ground first point cloud data includes:
  • determining the second transformation matrix according to the first transformation matrix, the non-ground second point cloud data and the non-ground first point cloud data includes:
  • the determining the coordinate information of the current position point according to the coordinate information of the preset starting point and the transformation matrix includes:
  • it also includes:
  • an apparatus for determining the position of a vehicle comprising:
  • the current location point determination module is configured to determine the current location point of the vehicle according to the GPS positioning state of the vehicle;
  • the first point cloud data determination module is configured to acquire the laser point cloud data measured at the current position of the vehicle as the first point cloud data
  • the second point cloud data determination module is configured to obtain the point cloud data corresponding to the preset departure point of the vehicle in the point cloud map, as the second point cloud data;
  • a transformation matrix determination module configured to match the first point cloud data with the second point cloud data, and determine a transformation matrix between the first point cloud data and the second point cloud data
  • the coordinate determination module is configured to determine the coordinate information of the current position point according to the coordinate information of the preset starting point and the transformation matrix.
  • an apparatus for determining a position of a vehicle comprising: a memory; and a processor coupled to the memory, the processor configured to, based on instructions stored in the memory, The method of determining the position of a vehicle as described in any one of the embodiments is performed.
  • a non-transitory computer-readable storage medium having stored thereon a computer program that, when executed by a processor, implements the method for determining a vehicle position described in any one of the embodiments.
  • FIG. 1 shows a schematic flowchart of a method for determining a vehicle position according to some embodiments of the present disclosure.
  • FIG. 2 shows a schematic flowchart of a method for determining a current location point according to some embodiments of the present disclosure.
  • FIG. 3 shows a schematic diagram of an apparatus for determining the position of a vehicle according to some embodiments of the present disclosure.
  • FIG. 4 shows a schematic diagram of an apparatus for determining the position of a vehicle according to other embodiments of the present disclosure.
  • the accuracy of the determined real-time position of the vehicle depends heavily on the quality of the GPS signal.
  • the GPS signal is poor or even no signal, there will be a large error in the position determined according to the GPS or the position information cannot be given, which will cause the vehicle to fail to drive normally, and even subsequent automatic driving will bring safety problems.
  • the present disclosure provides a method capable of improving the accuracy of the determined vehicle position.
  • the current position point of the vehicle is determined according to the positioning state of the GPS of the vehicle; the laser point cloud data measured by the vehicle at the current position point is obtained as the first point cloud data; The point cloud data corresponding to the preset starting point in the point cloud map is used as the second point cloud data; the first point cloud data and the second point cloud data are matched to determine the difference between the first point cloud data and the second point cloud data According to the coordinate information of the preset starting point and the transformation matrix, the coordinate information of the current position point is determined.
  • the transformation matrix is determined by the method of point cloud registration, and then the coordinate information of the current position point is determined, so that the vehicle can quickly obtain the accurate current position in various complex environments, without relying on GPS equipment, avoiding Poor or even no GPS signal leads to the problem that the position of the vehicle cannot be determined, and the accuracy of determining the position of the vehicle is improved.
  • FIG. 1 shows a schematic flowchart of a method for determining a vehicle position according to some embodiments of the present disclosure. The method can be performed, for example, by a device for determining the position of the vehicle.
  • the method of this embodiment includes steps 101-105.
  • step 101 the current position point of the vehicle is determined according to the positioning state of the global positioning system GPS of the vehicle.
  • the positioning state of the GPS can be determined by, for example, the positioning accuracy given on the GPS board.
  • the positioning accuracy of the GPS board is greater than the preset accuracy threshold, it is determined that the positioning state of the GPS is better than the preset condition.
  • the predicted value of the position point at the current moment is calculated according to the information of the position point at the previous moment measured by the sensor; The measured value of the position point; the predicted value is corrected by the measured value of the position point at the current moment, the second position point is determined, and the second position point is used as the current position point of the vehicle.
  • the sensors include an IMU (Inertial Measurement Unit, inertial measurement unit) and a wheel speedometer.
  • IMU Inertial Measurement Unit, inertial measurement unit
  • the wheel speedometer and the accelerometer in the IMU measure the speed and acceleration of each axis of the vehicle and the rotational speed and acceleration of each axis
  • the gyroscope, accelerometer in the IMU and algorithm processing The unit obtains the motion trajectory and attitude angle of the vehicle by measuring the acceleration and rotation angle.
  • the IMU calculates the position information and attitude information of the position point at the current moment through the position information of the origin and the information of the position point of the accumulated vehicle at the previous moment.
  • the position at the current moment can be calculated by using the dead reckoning algorithm.
  • the pose information of the point includes, for example, the accumulated velocity of each axis of the vehicle and the variation of its acceleration, the variation of the rotational speed and its acceleration, and the variation of the attitude angle, and the like.
  • Obtaining the measurement value of the position point at the current moment includes: taking the information of the position point of the laser point cloud data measured by the lidar at the current moment in the point cloud map as the measurement value of the position point at the current moment; The information of the measured position point is used as the measurement value of the position point at the current moment. Finally, the predicted value is corrected by using the measured value of the position point at the current moment.
  • the Extended Kalman Filter Extended Kalman Filter (Extended Kalman Filter) algorithm can be used for correction to obtain the second position point, and the second position point is used as the current position point of the vehicle.
  • the third position point manually set in the point cloud map is used as the current position point of the vehicle.
  • FIG. 2 shows a schematic flowchart of a method for determining a current location point according to some embodiments of the present disclosure.
  • step 201 it is determined whether the GPS positioning state is better than a preset condition.
  • step 202 the first position point currently measured by the GPS is used as the current position point.
  • step 203 it is determined whether the second position point can be obtained.
  • the information of the second location point can be stored in a memory location file, for example.
  • the real-time pose data of the vehicle can be written to the memory position file at a frequency of 10 Hz, and the current pose data overwrites the previous frame of pose data.
  • the frequency of writing the real-time pose of the vehicle to the memory position file can be set according to the speed of the vehicle, for example, it can be set to ensure that the displacement of the vehicle within the time interval between two samplings (that is, writing to the memory position file) is not greater than the vehicle's displacement.
  • the error requirement of the current position input by the positioning initialization module. Therefore, the position before the power failure of the vehicle can be obtained by reading the memory position file, which is used to determine the current position point.
  • the method for calculating the second position point written in the memory position file may, for example, include: first, according to the information of the position point at the previous moment measured by the sensor, calculate the predicted value of the position point at the current moment; The measured value of the position point at the moment; the predicted value is corrected by the measured value of the position point at the current moment, the second position point is determined, and the second position point is used as the current position point of the vehicle.
  • step 204 the second position point is used as the current position point of the vehicle.
  • the information of the second location information stored in the memory location file cannot be obtained.
  • step 205 the third position point manually set in the point cloud map is used as the current position point of the vehicle.
  • the above embodiment can provide a variety of methods to determine the approximate current position point according to the different GPS positioning states when the GPS signal of the vehicle is too poor or there is no signal, so that the current position of the vehicle can be determined without relying on the GPS signal. point, which lays the foundation for the subsequent accurate determination of the vehicle's position.
  • step 102 the laser point cloud data measured by the vehicle at the current position point is acquired as the first point cloud data.
  • laser point cloud data measured by scanning the surrounding environment with a lidar can be used as the first point cloud data. If the coordinate system of the laser point cloud data measured by the vehicle at the current position is different from the point cloud map coordinate system, such as the lidar coordinate system, the laser point cloud data can be converted from the lidar coordinate system to the point cloud map coordinate system as the first point cloud data.
  • step 103 the point cloud data corresponding to the preset departure point of the vehicle in the point cloud map is acquired as the second point cloud data.
  • the location information of the preset departure point may be converted to the coordinate system of the point cloud map first.
  • the location information of the preset departure point can be measured in advance, and only needs to be measured once and can be used permanently.
  • the position information of the preset departure point is represented in different ways according to the coordinate system used by the vehicle. For example, if the vehicle uses the WGS84 (World Geodetic System 1984) coordinate system, the location information of the preset departure point can be expressed in the form of latitude and longitude.
  • the location information can be represented by the relative position of the vehicle relative to the origin of the map.
  • step 104 the first point cloud data and the second point cloud data are matched to determine a transformation matrix between the first point cloud data and the second point cloud data.
  • a point cloud registration algorithm may be used to match the first point cloud data with the second point cloud data.
  • the point cloud registration algorithm may include, for example, an ICP (Iterative Closest Point, the most recent iteration) algorithm, a GICP (Generalized Iterative Closest Point, a generalized closest point) algorithm. Iterative) algorithm, NDT (Normal Distribution Transform, normal distribution transform) algorithm or multi-resolution Gaussian mixture mapping-based positioning algorithm, etc., are not limited to the examples.
  • a transformation matrix from the second point cloud data to the first point cloud data can be obtained.
  • the transformation matrix may be a 4 ⁇ 4 rotation and translation matrix, and the error between the second point cloud data and the first point cloud data after the rotation and translation transformation is performed according to the transformation matrix satisfies a preset condition.
  • the second point cloud data is divided into ground second point cloud data and non-ground second point cloud data
  • the first point cloud data is divided into ground first point cloud data and non-ground first point cloud data data
  • determining the first transformation matrix includes: firstly performing down-sampling processing on the first point cloud data on the ground; matching the second point cloud data on the ground with the down-sampled first point cloud data on the ground to obtain the second point cloud on the ground
  • the rotation and translation matrix of the downsampled ground first point cloud data from the data is used as the first transformation matrix.
  • the down-sampled ground first point cloud data can be matched with the density of the ground second point cloud data, the distance between points, and the like.
  • the ICP algorithm may be used to match the ground second point cloud data with the downsampled ground first point cloud data to obtain the first transformation matrix M 1 .
  • determining the second transformation matrix includes: firstly transforming the non-ground second point cloud data according to the first transformation matrix to obtain the transformed non-ground second point cloud data; performing downsampling processing on the non-ground first point cloud data ; Match the transformed non-ground second point cloud data with the down-sampled non-ground first point cloud data to obtain the transformed non-ground second point cloud data to the down-sampled non-ground first point cloud The rotation-translation matrix of the data, as the second transformation matrix. After the non-ground second point cloud data is transformed by the first transformation matrix, it is closer to the non-ground first point cloud data. The transformed non-ground second point cloud data is further matched with the down-sampled non-ground first point cloud data, and the accuracy is higher.
  • Algorithms such as positioning algorithms based on Multiresolution Gaussian Mixture Maps can be used to match the transformed non-ground second point cloud data with the down-sampled non-ground first point cloud data to obtain the second transformation.
  • matrix M 2 .
  • step 105 the coordinate information of the current position point is determined according to the coordinate information of the preset starting point and the transformation matrix.
  • the transformation matrix is transformed to obtain second coordinate information, and the x-axis coordinate value and the y-axis coordinate value in the second coordinate information are used as the x-axis coordinate value and the y-axis coordinate value of the current position point.
  • the coordinate information of the preset starting point is expressed as (x, y, z), and the transformation matrix is expressed as Then the coordinate information (x', y', z') of the current position point can be based on Sure.
  • the coordinate values (x, y, z) and (x', y', z') of the x, y, and z axes in the map coordinate system can, for example, represent longitude, latitude, and altitude, respectively.
  • it also includes determining the attitude information of the current position point of the vehicle. For example, first, the attitude information corresponding to the preset starting point is transformed according to the first transformation matrix to obtain the first attitude information, and the roll angle value and the pitch angle value in the first attitude information are used as the current roll angle value of the vehicle and the pitch angle value; then, transform the first attitude information and the second transformation matrix to obtain the second attitude information, and use the heading angle value in the second attitude information as the current heading angle value of the vehicle.
  • the first transformation matrix M 1 is used to determine the current position point.
  • the z-axis coordinate value and the current roll and pitch angle values of the vehicle are more accurate.
  • the preset attitude information corresponding to the preset starting point may be attitude information when the point cloud data corresponding to the preset starting point in the point cloud map is generated.
  • the pose matrix is a 4 ⁇ 4 matrix, and the first pose matrix of the current position can be obtained by multiplying it with the first transformation matrix M 1 , and the first coordinate information and the first pose information can be obtained according to the first pose matrix, thereby obtaining The z-axis coordinate value of the current position point, and the current roll and pitch angle values of the vehicle.
  • the first pose matrix and the second transformation matrix M 2 can be multiplied to obtain the second pose matrix, and the second coordinate information and the second pose information can be obtained according to the second pose matrix, so as to obtain the x-axis coordinate of the current position point. value, the y-axis coordinate value and the current heading angle value of the vehicle.
  • the transformation of longitude, latitude and heading angle can be more accurately determined. Therefore, according to the second transformation matrix M 2 , determine the x of the current position point
  • the axis coordinate value, the y-axis coordinate value and the current heading angle value of the vehicle are more accurate.
  • the transformation matrix can be determined by the method of point cloud registration, and then the coordinate information of the current position point can be determined, so that the vehicle can quickly obtain the accurate current position in various complex environments. Without relying on the GPS device, the problem that the position of the vehicle cannot be determined due to poor GPS signal or even no signal is avoided, and the accuracy of determining the position of the vehicle is improved.
  • the changes in the height, pitch angle and roll angle of the preset starting point and the current position point can be more accurately determined, and the changes in the height, pitch angle and roll angle of the preset starting point and the current position point can be determined more accurately.
  • the matching of the data and the non-ground second point cloud data can more accurately determine the changes in the latitude, longitude and heading of the preset departure point and the current position. Therefore, the method according to the above embodiment can more accurately determine the coordinate information and attitude information of the vehicle at the current position point.
  • FIG. 3 shows a schematic diagram of an apparatus for determining the position of a vehicle according to some embodiments of the present disclosure.
  • the apparatus 300 for determining the vehicle position in this embodiment includes: a current position point determination module 301, a first point cloud data determination module 302, a second point cloud data determination module 303, a transformation matrix determination module 304, and Coordinate determination module 305 .
  • the current location point determination module 301 is configured to determine the current location point of the vehicle according to the GPS positioning state of the vehicle.
  • the current location point determination module 301 is configured to use the first location point currently measured by the GPS as the current location point when the GPS positioning state of the vehicle is better than a preset condition.
  • the current position point determination module 301 is configured to calculate the current position point information according to the position point information of the previous moment measured by the sensor under the condition that the GPS positioning state of the vehicle is not better than the preset condition. The predicted value of the position point; the measurement value of the position point at the current moment is obtained; the predicted value is corrected by the measurement value of the position point at the current moment, the second position point is determined, and the second position point is used as the current position point of the vehicle.
  • obtaining the measurement value of the position point at the current moment includes: taking the position point information of the laser point cloud data measured by the lidar at the current moment in the point cloud map as the measurement value of the position point at the current moment; The information of the position point measured at the current moment is used as the measurement value of the position point at the current moment.
  • the current position point determination module 301 is configured to use the third position point manually set in the point cloud map as the current position of the vehicle under the condition that the GPS positioning state of the vehicle is not better than a preset condition location point.
  • the first point cloud data determination module 302 is configured to acquire laser point cloud data measured at the current position of the vehicle as the first point cloud data.
  • the second point cloud data determination module 303 is configured to acquire point cloud data corresponding to the preset departure point of the vehicle in the point cloud map, as the second point cloud data.
  • the transformation matrix determination module 304 is configured to match the first point cloud data with the second point cloud data, and determine the transformation matrix between the first point cloud data and the second point cloud data.
  • the transformation matrix determining module 304 is configured to divide the second point cloud data into ground second point cloud data and non-ground second point cloud data, and divide the first point cloud data into ground first points Cloud data and non-ground first point cloud data; according to ground second point cloud data and ground first point cloud data, determine the first transformation matrix; according to the first transformation matrix, non-ground second point cloud data and non-ground first point cloud data Point cloud data, determine the second transformation matrix.
  • determining the first transformation matrix includes: performing down-sampling processing on the first point cloud data on the ground; matching the second point cloud data on the ground with the down-sampled first point cloud data on the ground to obtain the second point cloud data on the ground.
  • the rotation and translation matrix of the downsampled ground first point cloud data is used as the first transformation matrix.
  • determining the second transformation matrix includes: transforming the non-ground second point cloud data according to the first transformation matrix to obtain the transformed non-ground second point cloud data; performing downsampling processing on the non-ground first point cloud data; Match the transformed non-ground second point cloud data with the down-sampled non-ground first point cloud data to obtain from the transformed non-ground second point cloud data to the down-sampled non-ground first point cloud data The rotation-translation matrix of , as the second transformation matrix.
  • the coordinate determination module 305 is configured to determine the coordinate information of the current position point according to the coordinate information of the preset starting point and the transformation matrix.
  • the coordinate determination module 305 is configured to transform the coordinate information of the preset starting point according to the first transformation matrix to obtain the first coordinate information, and use the z-axis coordinate value in the first coordinate information as the z-axis coordinate value of the current position point; Transform the first coordinate information according to the second transformation matrix to obtain the second coordinate information, and use the x-axis coordinate value and the y-axis coordinate value in the second coordinate information as the x-axis coordinate value and the y-axis coordinate value of the current position point .
  • the coordinate determination module 305 is further configured to determine the attitude information of the current position point of the vehicle. For example, first, the attitude information corresponding to the preset starting point is transformed according to the first transformation matrix to obtain the first attitude information, and the roll angle value and the pitch angle value in the first attitude information are used as the current roll angle value of the vehicle and the pitch angle value; then, transform the first attitude information and the second transformation matrix to obtain the second attitude information, and use the heading angle value in the second attitude information as the current heading angle value of the vehicle.
  • the above embodiment can enable the vehicle to quickly determine the precise current position in various complex environments without relying on the GPS device, avoid the problem that the position of the vehicle cannot be determined due to poor GPS signal or even no signal, and improve the accuracy of Accuracy of vehicle location.
  • the changes in the altitude, pitch angle and roll angle of the preset departure point and the current position point, as well as the latitude and longitude of the preset departure point and the current position point can be more accurately determined.
  • the change of the heading can achieve the effect of accurately determining the coordinate information and attitude information of the vehicle at the current position.
  • FIG. 4 shows a schematic diagram of an apparatus for determining the position of a vehicle according to other embodiments of the present disclosure.
  • the apparatus 400 for determining the vehicle position of this embodiment includes: a memory 401 and a processor 402 coupled to the memory 401 , and the processor 402 is configured to execute the present disclosure based on instructions stored in the memory 401 A method of determining vehicle location in any of some embodiments.
  • the memory 401 may include, for example, a system memory, a fixed non-volatile storage medium, and the like.
  • the system memory stores, for example, an operating system, an application program, a boot loader (Boot Loader), and other programs.
  • the apparatus 400 for determining the position of the vehicle may further include an input-output interface 403, a network interface 404, a storage interface 405, and the like. These interfaces 403, 404, 405 as well as the memory 401 and the processor 402 can be connected, for example, by a bus 406.
  • the input and output interface 403 provides a connection interface for input and output devices such as a display, a mouse, a keyboard, and a touch screen.
  • Network interface 404 provides a connection interface for various networked devices.
  • the storage interface 405 provides a connection interface for external storage devices such as SD cards and U disks.
  • embodiments of the present disclosure may be provided as a method, system, or computer program product. Accordingly, the present disclosure may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present disclosure may take the form of a computer program product embodied on one or more computer non-transitory readable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer program code embodied therein .
  • These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory result in an article of manufacture comprising instruction means, the instructions
  • the apparatus implements 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)
  • Remote Sensing (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Electromagnetism (AREA)
  • Automation & Control Theory (AREA)
  • Navigation (AREA)

Abstract

一种确定车辆位置的方法和装置，涉及自动驾驶技术领域。包括：根据车辆的GPS的定位状态，确定车辆的当前位置点（101）；获取车辆在当前位置点测得的激光点云数据，作为第一点云数据（102）；获取车辆的预设出发点在点云地图中对应的点云数据，作为第二点云数据（103）；将第一点云数据与第二点云数据进行匹配，确定第一点云数据与第二点云数据之间的变换矩阵（104）；根据预设出发点的坐标信息和变换矩阵，确定当前位置点的坐标信息（105）。该方法和装置使得车辆在各种复杂环境下都可以快速准确地获得精确的当前位置，不依赖GPS设备，避免GPS信号较差甚至无信号导致无法确定车辆的位置的问题，并且，提高了确定车辆位置的准确性。

Description

确定车辆位置的方法和装置
相关申请的交叉引用
本申请是以CN申请号为202010657188.2，申请日为2020年7月9日的申请为基础，并主张其优先权，该CN申请的公开内容在此作为整体引入本申请中。
技术领域
本公开涉及自动驾驶技术领域，特别涉及一种确定车辆位置的方法和装置。
背景技术
在自动驾驶领域，确定车辆的实时位置是非常重要的一个环节。针对车辆可能在任意位置出发的场景，如何确定车辆的实时位置是急需解决的问题。
在一些相关技术中，车辆一般都采用GPS(Global Positioning System，全球定位系统)或者GPS/INS(Inertial Navigation System，惯性导航系统)组合设备来确定车辆的位置。
发明内容
根据本公开的一些实施例，提供一种确定车辆位置的方法，包括：
根据车辆的全球定位系统GPS的定位状态，确定所述车辆的当前位置点；
获取所述车辆在当前位置点测得的激光点云数据，作为第一点云数据；
获取所述车辆的预设出发点在点云地图中对应的点云数据，作为第二点云数据；
将所述第一点云数据与所述第二点云数据进行匹配，确定所述第一点云数据与所述第二点云数据之间的变换矩阵；
根据所述预设出发点的坐标信息和所述变换矩阵，确定所述当前位置点的坐标信息。
在一些实施例中，确定所述车辆的当前位置点包括：
在车辆的GPS的定位状态优于预设条件的情况下，将GPS当前测量的第一位置点作为当前位置点。
在一些实施例中，确定所述车辆的当前位置点包括：
在车辆的GPS的定位状态不优于预设条件的情况下，根据传感器测量的上一时刻 的位置点的信息，计算当前时刻的位置点的预测值；
获取当前时刻的位置点的测量值；
利用当前时刻的位置点的所述测量值对所述预测值进行修正，确定第二位置点，将所述第二位置点作为所述车辆的当前位置点。
在一些实施例中，所述获取当前时刻的位置点的测量值包括：
将激光雷达在当前时刻测量的激光点云数据在点云地图中的位置点的信息作为当前时刻的位置点的测量值；
或者，将GPS在当前时刻测量的位置点的信息作为当前时刻的位置点的测量值。
在一些实施例中，确定所述车辆的当前位置点包括：
在车辆的GPS的定位状态不优于预设条件的情况下，将在点云地图中人工设置的第三位置点作为所述车辆的当前位置点。
在一些实施例中，所述将所述第一点云数据与所述第二点云数据进行匹配，确定所述第一点云数据与所述第二点云数据之间的变换矩阵包括：
将所述第二点云数据划分为地面第二点云数据和非地面第二点云数据，将所述第一点云数据划分为地面第一点云数据和非地面第一点云数据；
根据所述地面第二点云数据和地面第一点云数据，确定第一变换矩阵；
根据所述第一变换矩阵，所述非地面第二点云数据和所述非地面第一点云数据，确定第二变换矩阵。
在一些实施例中，所述根据所述地面第二点云数据和地面第一点云数据，确定第一变换矩阵包括：
对所述地面第一点云数据进行降采样处理；
将所述地面第二点云数据和降采样后的地面第一点云数据进行匹配，得到由所述地面第二点云数据到降采样后的地面第一点云数据的旋转平移矩阵，作为所述第一变换矩阵。
在一些实施例中，所述根据所述第一变换矩阵，所述非地面第二点云数据和所述非地面第一点云数据，确定第二变换矩阵包括：
将所述非地面第二点云数据根据所述第一变换矩阵进行变换，得到变换后的非地面第二点云数据；
将所述非地面第一点云数据进行降采样处理；
将变换后的非地面第二点云数据和降采样后的非地面第一点云数据进行匹配，得 到由所述变换后的非地面第二点云数据到降采样后的非地面第一点云数据的旋转平移矩阵，作为所述第二变换矩阵。
在一些实施例中，所述根据所述预设出发点的坐标信息和所述变换矩阵，确定所述当前位置点的坐标信息包括：
将所述预设出发点的坐标信息根据所述第一变换矩阵进行变换，得到第一坐标信息，将所述第一坐标信息中z轴坐标值，作为所述当前位置点的z轴坐标值；
将所述第一坐标信息根据所述第二变换矩阵进行变换，得到第二坐标信息，将所述第二坐标信息中的x轴坐标值和y轴坐标值，作为所述当前位置点的x轴坐标值和y轴坐标值。
在一些实施例中，还包括：
将所述预设出发点对应的姿态信息根据所述第一变换矩阵进行变换，得到第一姿态信息，将所述第一姿态信息中的横滚角值和俯仰角值，作为所述车辆当前的横滚角值和俯仰角值；
将所述第一姿态信息所述第二变换矩阵进行变换，得到第二姿态信息，将所述第二姿态信息中的航向角值，作为所述车辆当前的航向角值。
根据本公开的另一些实施例，提供一种确定车辆位置的装置，包括：
当前位置点确定模块，被配置为根据车辆的GPS的定位状态，确定所述车辆的当前位置点；
第一点云数据确定模块，被配置为获取所述车辆在当前位置点测得的激光点云数据，作为第一点云数据；
第二点云数据确定模块，被配置为获取所述车辆的预设出发点在点云地图中对应的点云数据，作为第二点云数据；
变换矩阵确定模块，被配置为将所述第一点云数据与所述第二点云数据进行匹配，确定所述第一点云数据与所述第二点云数据之间的变换矩阵；
坐标确定模块，被配置为根据所述预设出发点的坐标信息和所述变换矩阵，确定所述当前位置点的坐标信息。
根据本公开的又一些实施例，提供一种确定车辆位置的装置，包括：存储器；以及耦接至所述存储器的处理器，所述处理器被配置为基于存储在所述存储器中的指令，执行任一实施例所述的确定车辆位置的方法。
根据本公开的再一些实施例，提供一种非瞬时性计算机可读存储介质，其上存储 有计算机程序，该程序被处理器执行时实现任一实施例所述的确定车辆位置的方法。
附图说明
下面将对实施例或相关技术描述中所需要使用的附图作简单的介绍。根据下面参照附图的详细描述，可以更加清楚地理解本公开。
显而易见地，下面描述中的附图仅仅是本公开的一些实施例，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示出根据本公开的一些实施例的确定车辆位置的方法的流程示意图。
图2示出根据本公开的一些实施例的确定当前位置点的方法的流程示意图。
图3示出根据本公开的一些实施例的确定车辆位置的装置的示意图。
图4示出根据本公开的另一些实施例的确定车辆位置的装置的示意图。
具体实施方式
发明人发现，在相关技术中，确定的车辆的实时位置的准确性严重依赖GPS的信号好坏，在任意位置出发的场景中，例如车辆处在两栋高楼之间或者处在隧道中等情况时，GPS的信号较差甚至无信号时，根据GPS确定的位置将存在较大误差或无法给出位置信息，会导致车辆无法正常行驶，甚至后续的自动驾驶会带来安全问题。
为此，本公开提供一种能够提高确定的车辆位置的准确性的方法。
在本公开的实施例中，根据车辆的全球定位系统GPS的定位状态，确定车辆的当前位置点；获取车辆在当前位置点测得的激光点云数据，作为第一点云数据；获取车辆的预设出发点在点云地图中对应的点云数据，作为第二点云数据；将第一点云数据与第二点云数据进行匹配，确定第一点云数据与第二点云数据之间的变换矩阵；根据预设出发点的坐标信息和变换矩阵，确定当前位置点的坐标信息。车辆在任意位置点，通过点云配准的方法确定变换矩阵，进而确定当前位置点的坐标信息，使得车辆在各种复杂环境下都可以快速的获得精确的当前位置，不依赖GPS设备，避免GPS信号较差甚至无信号导致无法确定车辆的位置的问题，并且，提高了确定车辆位置的准确性。下面将结合本公开实施例中的附图，对本公开实施例中的技术方案进行清楚、完整地描述。
图1示出根据本公开的一些实施例的确定车辆位置的方法的流程示意图。该方法例如可以由确定车辆位置的装置执行。
如图1所示，该实施例的方法包括步骤101-105。
在步骤101，根据车辆的全球定位系统GPS的定位状态，确定车辆的当前位置点。
在一些实施例中，在车辆的GPS的定位状态优于预设条件的情况下，将GPS当前测量的第一位置点作为当前位置点。其中，GPS的定位状态例如可以通过GPS板卡上给出的定位精度来确定，在GPS板卡的定位精度大于预设精度阈值的情况下，即，确定GPS的定位状态优于预设条件。
在一些实施例中，在车辆的GPS的定位状态不优于预设条件的情况下，根据传感器测量的上一时刻的位置点的信息，计算当前时刻的位置点的预测值；获取当前时刻的位置点的测量值；利用当前时刻的位置点的测量值对预测值进行修正，确定第二位置点，将第二位置点作为车辆的当前位置点。
其中，传感器包括IMU(Inertial Measurement Unit，惯性测量单元)和轮速计。在当前时刻的上一时刻，首先，轮速计和IMU中的加速度计测量车辆的各轴的速度及其加速度和各轴的旋转速度及其加速度，IMU中的陀螺仪、加速度计和算法处理单元通过对加速度和旋转角度的测量得出车辆的运动轨迹以及姿态角。然后，IMU通过原点的位置信息以及累积车辆的上一时刻的位置点的信息来计算当前时刻的位置点的位置信息和姿态信息，例如可以利用推位算法(Dead Reckoning)计算得到当前时刻的位置点的位姿信息。其中，累积车辆的上一时刻的位置点的信息例如包括车辆各轴的累积的速度及其加速度的变化量、旋转速度及其加速度的变化量、姿态角的变化量等。
获取当前时刻的位置点的测量值包括：将激光雷达在当前时刻测量的激光点云数据在点云地图中的位置点的信息作为当前时刻的位置点的测量值；或者，将GPS在当前时刻测量的位置点的信息作为当前时刻的位置点的测量值。最后，利用当前时刻的位置点的测量值对预测值进行修正，例如可以使用扩展卡尔曼EKF(Extended Kalman Filter)算法进行修正，得到第二位置点，将第二位置点作为车辆的当前位置点。
在一些实施例中，在车辆的GPS的定位状态不优于预设条件的情况下，将在点云地图中人工设置的第三位置点作为车辆的当前位置点。通过人工设置的方式确定车辆的当前位置点，可以快速地为后续的点云配准以及确定位置做好准备。
如图2所示，图2示出了根据本公开的一些实施例的确定当前位置点的方法的流程示意图。
首先，在步骤201，判断GPS的定位状态是否优于预设条件。
如果车辆的GPS的定位状态优于预设条件，在步骤202，将GPS当前测量的第一位置点作为当前位置点。
如果车辆的GPS的定位状态不优于预设条件，在步骤203，判断是否可以获得第二位置点。第二位置点的信息例如可以存储在记忆位置文件中。车辆处于正常行驶状态时，例如可以以10Hz频率向记忆位置文件写入车辆的实时位姿数据，当前位姿数据覆盖上一帧位姿数据。其中，将车辆的实时位姿写入记忆位置文件的频率可根据车辆的速度设置，例如可以设置为保证两次采样(即写入记忆位置文件)的时间间隔内车辆的位移量不大于车辆的定位初始化模块对输入的当前位置的误差要求。从而可以通过读取记忆位置文件获得车辆断电前的位置，用于确定当前位置点。
在一些实施例中，记忆位置文件中写入的第二位置点的计算方法例如可以包括：首先根据传感器测量的上一时刻的位置点的信息，计算当前时刻的位置点的预测值；获取当前时刻的位置点的测量值；利用当前时刻的位置点的测量值对预测值进行修正，确定第二位置点，将第二位置点作为车辆的当前位置点。
如果获得了第二位置信点，那么，在步骤204，将第二位置点作为车辆的当前位置点。
如果记忆位置文件被损坏，或者，车辆第一次上电导致初始化记忆位置文件无效，会导致不可以获得记忆位置文件中存储的第二位置信点的信息。
如果没有获得第二位置信点，那么，在步骤205，将在点云地图中人工设置的第三位置点作为车辆的当前位置点。
上述实施例可以在车辆的GPS的信号太差或者无信号时，根据GPS的定位状态的不同提供了多种方法确定大致的当前位置点，使得不依赖GPS的信号就可以确定车辆所在的当前位置点，为后续准确地确定车辆的位置奠定了基础。
在步骤102，获取车辆在当前位置点测得的激光点云数据，作为第一点云数据。
在获取到车辆的当前位置点的位置信息后，例如可以利用激光雷达扫描周围环境测得的激光点云数据，作为第一点云数据。如果车辆在当前位置点测得的激光点云数据的坐标系与点云地图坐标系不同，例如为激光雷达坐标系，则可以将激光点云数据由激光雷达坐标系转换到点云地图坐标系作为第一点云数据。
在步骤103，获取车辆的预设出发点在点云地图中对应的点云数据，作为第二点云数据。
根据预设出发点的位置信息获取高精度点云地图，获取预设出发点在点云地图中 对应的点云数据，作为第二点云数据。如果预设出发点的位置信息与点云地图的坐标系不同，可以首先将预设出发点的位置信息转换到点云地图坐标系。
预设出发点的位置信息例如可以预先测量，只需要测量一次，可永久使用。预设出发点的位置信息根据车辆所使用的坐标系不同而采用不同的表示方式。例如，如果车辆使用WGS84(World Geodetic System 1984)坐标系，预设出发点的位置信息可以用经纬度的形式表示，如果车辆使用SLAM(Simultaneous Localization And Mapping，即时定位与地图构建)地图，预设出发点的位置信息可以用车辆相对于地图原点的相对位置表示。
在步骤104，将第一点云数据与第二点云数据进行匹配，确定第一点云数据与第二点云数据之间的变换矩阵。
可以采用点云配准算法将第一点云数据与第二点云数据进行匹配，点云配准算法例如可以包括ICP(Iterative Closest Point，最近迭代)算法、GICP(Generalized Iterative Closest Point，广义最近迭代)算法、NDT(Normal Distribution Transform，正态分布转换)算法或基于多分辨率高斯混合映射的定位算法等，不限于所举示例。将第一点云数据与第二点云数据进行匹配后，可以得到由第二点云数据到第一点云数据的变换矩阵。变换矩阵可以为4×4的旋转平移矩阵，第二点云数据根据变换矩阵进行旋转平移变换后与第一点云数据的误差满足预设条件。
在一些实施例中，将第二点云数据划分为地面第二点云数据和非地面第二点云数据，将第一点云数据划分为地面第一点云数据和非地面第一点云数据；根据地面第二点云数据和地面第一点云数据，确定第一变换矩阵；根据第一变换矩阵，非地面第二点云数据和非地面第一点云数据，确定第二变换矩阵。
其中，确定第一变换矩阵包括：首先对地面第一点云数据进行降采样处理；将地面第二点云数据和降采样后的地面第一点云数据进行匹配，得到由地面第二点云数据到降采样后的地面第一点云数据的旋转平移矩阵，作为第一变换矩阵。通过降采样处理可以减少数据处理量，提高匹配效率。降采样后的地面第一点云数据可以与地面第二点云数据的密度，点之间的距离等相匹配。可以采用ICP算法将地面第二点云数据和降采样后的地面第一点云数据进行匹配，得到第一变换矩阵M 1。
其中，确定第二变换矩阵包括：首先将非地面第二点云数据根据第一变换矩阵进行变换，得到变换后的非地面第二点云数据；将非地面第一点云数据进行降采样处理；将变换后的非地面第二点云数据和降采样后的非地面第一点云数据进行匹配，得到由 变换后的非地面第二点云数据到降采样后的非地面第一点云数据的旋转平移矩阵，作为第二变换矩阵。利用第一变换矩阵对非地面第二点云数据进行变换后，与非地面第一点云数据更加接近。进一步将变换后的非地面第二点云数据和降采样后的非地面第一点云数据进行匹配，准确度更高。通过降采样处理可以减少数据处理量，提高匹配效率。可以采用基于多分辨率高斯混合映射(Multiresolution Gaussian Mixture Maps)的定位算法等算法将变换后的非地面第二点云数据和降采样后的非地面第一点云数据进行匹配，得到第二变换矩阵M 2。
在步骤105，根据预设出发点的坐标信息和变换矩阵，确定当前位置点的坐标信息。
将预设出发点的坐标信息根据第一变换矩阵进行变换，得到第一坐标信息，将第一坐标信息中z轴坐标值，作为当前位置点的z轴坐标值；将第一坐标信息根据第二变换矩阵进行变换，得到第二坐标信息，将第二坐标信息中的x轴坐标值和y轴坐标值，作为当前位置点的x轴坐标值和y轴坐标值。
例如，预设出发点的坐标信息表示为(x,y,z)，变换矩阵表示为
Figure PCTCN2021100288-appb-000001
则当前位置点的坐标信息(x’,y’,z’)可以根据
Figure PCTCN2021100288-appb-000002
确定。
其中，地图坐标系中x，y，z轴的坐标值(x,y,z)和(x’,y’,z’)例如可以分别表示经度，纬度和高度。
在一些实施例中，还包括确定车辆的当前位置点的姿态信息。例如，首先，将预设出发点对应的姿态信息根据第一变换矩阵进行变换，得到第一姿态信息，将第一姿态信息中的横滚角值和俯仰角值，作为车辆当前的横滚角值和俯仰角值；然后，将第一姿态信息第二变换矩阵进行变换，得到第二姿态信息，将第二姿态信息中的航向角值，作为车辆当前的航向角值。
其中，根据地面第二点云数据和地面第一点云数据的匹配，能够更加准确的确定高度、横滚角和俯仰角的变换情况，因此，采用第一变换矩阵M 1确定当前位置点的z轴坐标值和车辆当前的横滚角值和俯仰角值更加准确。
预设出发点对应的预设姿态信息可以为点云地图中预设出发点对应的点云数据 生成时的姿态信息。预设姿态信息包括预设横滚角值、预设俯仰角值和预设航向角值，一般情况下可以默认均为0。假设预设出发点的坐标信息表示为P 0＝(x,y,z)，根据预设出发点对应的预设姿态信息得到姿态矩阵R(为3×3矩阵)，则可以得到预设出发点的位姿矩阵
Figure PCTCN2021100288-appb-000003
位姿矩阵为4×4矩阵，与第一变换矩阵M 1相乘可以得到当前位置点的第一位姿矩阵，根据第一位姿矩阵可以得到第一坐标信息和第一姿态信息，从而得到当前位置点的z轴坐标值，和车辆当前的横滚角值和俯仰角值。
将第一姿态信息第二变换矩阵进行变换，得到第二姿态信息，将第二姿态信息中的航向角值，作为车辆当前的航向角值。例如可以将第一位姿矩阵与第二变换矩阵M 2相乘得到第二位姿矩阵，根据第二位姿矩阵得到第二坐标信息和第二姿态信息，从而得到当前位置点的x轴坐标值，y轴坐标值和车辆当前的航向角值。根据非地面第二点云数据和非地面第一点云数据的匹配，能够更加准确的确定经度、纬度和航向角的变换情况，因此，根据第二变换矩阵M 2，确定当前位置点的x轴坐标值，y轴坐标值和车辆当前的航向角值更加准确。
上述实施例中，车辆处于任意位置点，可以通过点云配准的方法确定变换矩阵，进而确定当前位置点的坐标信息，使得车辆在各种复杂环境下都可以快速的获得精确的当前位置，不依赖GPS设备，避免GPS信号较差甚至无信号导致无法确定车辆的位置的问题，并且，提高了确定车辆位置的准确性。此外，通过地面第一点云数据和地面第二点云数据的匹配，能够更加准确的确定预设出发点和当前位置点的高度、俯仰角和横滚角的变化，通过非地面第一点云数据和非地面第二点云数据的匹配，能够更加准确的确定预设出发点和当前位置点的经纬度和航向的变化。因此，根据上述实施例的方法能够更加准确地确定车辆在当前位置点的坐标信息和姿态信息。
图3示出根据本公开的一些实施例的确定车辆位置的装置的示意图。
如图3所示，该实施例的确定车辆位置的装置300包括：当前位置点确定模块301，第一点云数据确定模块302，第二点云数据确定模块303，变换矩阵确定模块304，以及坐标确定模块305。
当前位置点确定模块301，被配置为根据车辆的全球定位系统GPS的定位状态，确定车辆的当前位置点。
在一些实施例中，当前位置点确定模块301被配置为在车辆的GPS的定位状态优于预设条件的情况下，将GPS当前测量的第一位置点作为当前位置点。
在另一些实施例中，当前位置点确定模块301被配置为在车辆的GPS的定位状态不优于预设条件的情况下，根据传感器测量的上一时刻的位置点的信息，计算当前时刻的位置点的预测值；获取当前时刻的位置点的测量值；利用当前时刻的位置点的测量值对预测值进行修正，确定第二位置点，将第二位置点作为车辆的当前位置点。其中，获取当前时刻的位置点的测量值包括：将激光雷达在当前时刻测量的激光点云数据在点云地图中的位置点的信息作为当前时刻的位置点的测量值；或者，将GPS在当前时刻测量的位置点的信息作为当前时刻的位置点的测量值。
在又一些实施例中，当前位置点确定模块301被配置为在车辆的GPS的定位状态不优于预设条件的情况下，将在点云地图中人工设置的第三位置点作为车辆的当前位置点。
在车辆的GPS的信号太差或者无信号时，根据GPS的定位状态的不同提供了多种方法确定当前位置点，使得不依赖GPS的信号就可以确定车辆所在的当前位置点，为后续准确地确定车辆的位置奠定了基础。
第一点云数据确定模块302，被配置为获取车辆在当前位置点测得的激光点云数据，作为第一点云数据。
第二点云数据确定模块303，被配置为获取车辆的预设出发点在点云地图中对应的点云数据，作为第二点云数据。
变换矩阵确定模块304，被配置为将第一点云数据与第二点云数据进行匹配，确定第一点云数据与第二点云数据之间的变换矩阵。
在一些实施例中，变换矩阵确定模块304，被配置为将第二点云数据划分为地面第二点云数据和非地面第二点云数据，将第一点云数据划分为地面第一点云数据和非地面第一点云数据；根据地面第二点云数据和地面第一点云数据，确定第一变换矩阵；根据第一变换矩阵，非地面第二点云数据和非地面第一点云数据，确定第二变换矩阵。其中，确定第一变换矩阵包括：对地面第一点云数据进行降采样处理；将地面第二点云数据和降采样后的地面第一点云数据进行匹配，得到由地面第二点云数据到降采样后的地面第一点云数据的旋转平移矩阵，作为第一变换矩阵。其中，确定第二变换矩阵包括：将非地面第二点云数据根据第一变换矩阵进行变换，得到变换后的非地面第二点云数据；将非地面第一点云数据进行降采样处理；将变换后的非地面第二点云数据和降采样后的非地面第一点云数据进行匹配，得到由变换后的非地面第二点云数据到降采样后的非地面第一点云数据的旋转平移矩阵，作为第二变换矩阵。
坐标确定模块305，被配置为根据预设出发点的坐标信息和变换矩阵，确定当前位置点的坐标信息。
坐标确定模块305，被配置为将预设出发点的坐标信息根据第一变换矩阵进行变换，得到第一坐标信息，将第一坐标信息中z轴坐标值，作为当前位置点的z轴坐标值；将第一坐标信息根据第二变换矩阵进行变换，得到第二坐标信息，将第二坐标信息中的x轴坐标值和y轴坐标值，作为当前位置点的x轴坐标值和y轴坐标值。
在一些实施例中，坐标确定模块305，还被配置为确定车辆的当前位置点的姿态信息。例如，首先，将预设出发点对应的姿态信息根据第一变换矩阵进行变换，得到第一姿态信息，将第一姿态信息中的横滚角值和俯仰角值，作为车辆当前的横滚角值和俯仰角值；然后，将第一姿态信息第二变换矩阵进行变换，得到第二姿态信息，将第二姿态信息中的航向角值，作为车辆当前的航向角值。
上述实施例，可以使得车辆在各种复杂环境下都可以快速地确定精确的当前位置，不依赖GPS设备，避免GPS信号较差甚至无信号导致无法确定车辆的位置的问题，并且，提高了确定车辆位置的准确性。此外，通过区分地面点和非地面点，分别进行匹配，能够更加准确的确定预设出发点和当前位置点的高度、俯仰角和横滚角的变化，以及预设出发点和当前位置点的经纬度和航向的变化，从而实现了准确地确定车辆在当前位置点的坐标信息和姿态信息这一效果。
图4示出根据本公开的另一些实施例的确定车辆位置的装置的示意图。
如图4所示，该实施例的确定车辆位置的装置400包括：存储器401以及耦接至该存储器401的处理器402，处理器402被配置为基于存储在存储器401中的指令，执行本公开任意一些实施例中的确定车辆位置的方法。
例如，首先，根据车辆的全球定位系统GPS的定位状态，确定车辆的当前位置点；获取车辆在当前位置点测得的激光点云数据，作为第一点云数据；获取车辆的预设出发点在点云地图中对应的点云数据，作为第二点云数据；然后，将第一点云数据与第二点云数据进行匹配，确定第一点云数据与第二点云数据之间的变换矩阵；最后，根据预设出发点的坐标信息和变换矩阵，确定当前位置点的坐标信息。
其中，存储器401例如可以包括系统存储器、固定非易失性存储介质等。系统存储器例如存储有操作系统、应用程序、引导装载程序(Boot Loader)以及其他程序等。
确定车辆位置的装置400还可以包括输入输出接口403、网络接口404、存储接口405等。这些接口403，404，405以及存储器401和处理器402之间例如可以通过 总线406连接。其中，输入输出接口403为显示器、鼠标、键盘、触摸屏等输入输出设备提供连接接口。网络接口404为各种联网设备提供连接接口。存储接口405为SD卡、U盘等外置存储设备提供连接接口。
本领域内的技术人员应当明白，本公开的实施例可提供为方法、系统、或计算机程序产品。因此，本公开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，本公开可采用在一个或多个其中包含有计算机程序代码的计算机非瞬时性可读存储介质(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。
本公开是参照根据本公开实施例的方法、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。应理解为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设备上，使得在计算机或其他可编程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。
以上所述仅为本公开的较佳实施例，并不用以限制本公开，凡在本公开的精神和原则之内，所作的任何修改、等同替换、改进等，均应包含在本公开的保护范围之内。

Claims (13)

  1. 一种确定车辆位置的方法，包括：
    根据车辆的全球定位系统GPS的定位状态，确定所述车辆的当前位置点；
    获取所述车辆在当前位置点测得的激光点云数据，作为第一点云数据；
    获取所述车辆的预设出发点在点云地图中对应的点云数据，作为第二点云数据；
    将所述第一点云数据与所述第二点云数据进行匹配，确定所述第一点云数据与所述第二点云数据之间的变换矩阵；
    根据所述预设出发点的坐标信息和所述变换矩阵，确定所述当前位置点的坐标信息。
  2. 根据权利要求1所述的确定车辆位置的方法，其中，确定所述车辆的当前位置点包括：
    在车辆的GPS的定位状态优于预设条件的情况下，将GPS当前测量的第一位置点作为当前位置点。
  3. 根据权利要求1所述的确定车辆位置的方法，其中，确定所述车辆的当前位置点包括：
    在车辆的GPS的定位状态不优于预设条件的情况下，根据传感器测量的上一时刻的位置点的信息，计算当前时刻的位置点的预测值；
    获取当前时刻的位置点的测量值；
    利用当前时刻的位置点的所述测量值对所述预测值进行修正，确定第二位置点，将所述第二位置点作为所述车辆的当前位置点。
  4. 根据权利要求3所述的确定车辆位置的方法，其中，所述获取当前时刻的位置点的测量值包括：
    将激光雷达在当前时刻测量的激光点云数据在点云地图中的位置点的信息作为当前时刻的位置点的测量值；
    或者，将GPS在当前时刻测量的位置点的信息作为当前时刻的位置点的测量值。
  5. 根据权利要求1所述的确定车辆位置的方法，其中，确定所述车辆的当前位置 点包括：
    在车辆的GPS的定位状态不优于预设条件的情况下，将在点云地图中人工设置的第三位置点作为所述车辆的当前位置点。
  6. 根据权利要求1所述的确定车辆位置的方法，其中，所述将所述第一点云数据与所述第二点云数据进行匹配，确定所述第一点云数据与所述第二点云数据之间的变换矩阵包括：
    将所述第二点云数据划分为地面第二点云数据和非地面第二点云数据，将所述第一点云数据划分为地面第一点云数据和非地面第一点云数据；
    根据所述地面第二点云数据和地面第一点云数据，确定第一变换矩阵；
    根据所述第一变换矩阵，所述非地面第二点云数据和所述非地面第一点云数据，确定第二变换矩阵。
  7. 根据权利要求6所述的确定车辆位置的方法，其中，所述根据所述地面第二点云数据和地面第一点云数据，确定第一变换矩阵包括：
    对所述地面第一点云数据进行降采样处理；
    将所述地面第二点云数据和降采样后的地面第一点云数据进行匹配，得到由所述地面第二点云数据到降采样后的地面第一点云数据的旋转平移矩阵，作为所述第一变换矩阵。
  8. 根据权利要求6所述的确定车辆位置的方法，其中，所述根据所述第一变换矩阵，所述非地面第二点云数据和所述非地面第一点云数据，确定第二变换矩阵包括：
    将所述非地面第二点云数据根据所述第一变换矩阵进行变换，得到变换后的非地面第二点云数据；
    将所述非地面第一点云数据进行降采样处理；
    将变换后的非地面第二点云数据和降采样后的非地面第一点云数据进行匹配，得到由所述变换后的非地面第二点云数据到降采样后的非地面第一点云数据的旋转平移矩阵，作为所述第二变换矩阵。
  9. 根据权利要求1所述的确定车辆位置的方法，其中，所述根据所述预设出发点 的坐标信息和所述变换矩阵，确定所述当前位置点的坐标信息包括：
    将所述预设出发点的坐标信息根据所述第一变换矩阵进行变换，得到第一坐标信息，将所述第一坐标信息中z轴坐标值，作为所述当前位置点的z轴坐标值；
    将所述第一坐标信息根据所述第二变换矩阵进行变换，得到第二坐标信息，将所述第二坐标信息中的x轴坐标值和y轴坐标值，作为所述当前位置点的x轴坐标值和y轴坐标值。
  10. 根据权利要求1所述的确定车辆位置的方法，还包括：
    将所述预设出发点对应的姿态信息根据所述第一变换矩阵进行变换，得到第一姿态信息，将所述第一姿态信息中的横滚角值和俯仰角值，作为所述车辆当前的横滚角值和俯仰角值；
    将所述第一姿态信息所述第二变换矩阵进行变换，得到第二姿态信息，将所述第二姿态信息中的航向角值，作为所述车辆当前的航向角值。
  11. 一种确定车辆位置的装置，包括：
    当前位置点确定模块，被配置为根据车辆的GPS的定位状态，确定所述车辆的当前位置点；
    第一点云数据确定模块，被配置为获取所述车辆在当前位置点测得的激光点云数据，作为第一点云数据；
    第二点云数据确定模块，被配置为获取所述车辆的预设出发点在点云地图中对应的点云数据，作为第二点云数据；
    变换矩阵确定模块，被配置为将所述第一点云数据与所述第二点云数据进行匹配，确定所述第一点云数据与所述第二点云数据之间的变换矩阵；
    坐标确定模块，被配置为根据所述预设出发点的坐标信息和所述变换矩阵，确定所述当前位置点的坐标信息。
  12. 一种确定车辆位置的装置，包括：
    存储器；以及
    耦接至所述存储器的处理器，所述处理器被配置为基于存储在所述存储器中的指令，执行权利要求1-10中任一项所述的确定车辆位置的方法。
  13. 一种非瞬时性计算机可读存储介质，其上存储有计算机程序，该程序被处理器执行时实现权利要求1-10中任一项所述的确定车辆位置的方法。
PCT/CN2021/100288 2020-07-09 2021-06-16 确定车辆位置的方法和装置 WO2022007602A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP21837352.0A EP4130800A4 (en) 2020-07-09 2021-06-16 METHOD AND DEVICE FOR DETERMINING THE POSITION OF A VEHICLE
US18/000,050 US20230204384A1 (en) 2020-07-09 2021-06-16 Method and apparatus for determining location of vehicle

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010657188.2A CN112835085B (zh) 2020-07-09 2020-07-09 确定车辆位置的方法和装置
CN202010657188.2 2020-07-09

Publications (1)

Publication Number Publication Date
WO2022007602A1 true WO2022007602A1 (zh) 2022-01-13

Family

ID=75923201

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/100288 WO2022007602A1 (zh) 2020-07-09 2021-06-16 确定车辆位置的方法和装置

Country Status (4)

Country Link
US (1) US20230204384A1 (zh)
EP (1) EP4130800A4 (zh)
CN (1) CN112835085B (zh)
WO (1) WO2022007602A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114353807A (zh) * 2022-03-21 2022-04-15 沈阳吕尚科技有限公司 一种机器人的定位方法及定位装置
CN115236645A (zh) * 2022-09-23 2022-10-25 北京小马易行科技有限公司 激光雷达的姿态确定方法以及姿态确定装置
CN115437385A (zh) * 2022-10-21 2022-12-06 上海木蚁机器人科技有限公司 移动机器人的激光定位方法、装置、设备和介质

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112835085B (zh) * 2020-07-09 2022-04-12 北京京东乾石科技有限公司 确定车辆位置的方法和装置
CN113900517B (zh) * 2021-09-30 2022-12-20 北京百度网讯科技有限公司 线路导航方法和装置、电子设备、计算机可读介质
CN118046890A (zh) * 2022-11-09 2024-05-17 北汽福田汽车股份有限公司 车辆定位方法、装置及车辆

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2019070824A1 (en) * 2017-10-03 2019-04-11 Uber Technologies, Inc. METHODS FOR LOCATING AUTONOMOUS VEHICLES
CN109887028A (zh) * 2019-01-09 2019-06-14 天津大学 一种基于点云数据配准的无人车辅助定位方法
CN110609290A (zh) * 2019-09-19 2019-12-24 北京智行者科技有限公司 激光雷达匹配定位方法及装置
CN110988894A (zh) * 2019-12-25 2020-04-10 畅加风行(苏州)智能科技有限公司 一种面向港口环境的多源数据融合的无人驾驶汽车实时定位方法
CN111168669A (zh) * 2019-12-26 2020-05-19 上海高仙自动化科技发展有限公司 机器人控制方法、机器人和可读存储介质
CN111812658A (zh) * 2020-07-09 2020-10-23 北京京东乾石科技有限公司 位置确定方法、装置、系统和计算机可读存储介质
US20200393566A1 (en) * 2019-06-14 2020-12-17 DeepMap Inc. Segmenting ground points from non-ground points to assist with localization of autonomous vehicles
CN112835085A (zh) * 2020-07-09 2021-05-25 北京京东乾石科技有限公司 确定车辆位置的方法和装置
CN112835086A (zh) * 2020-07-09 2021-05-25 北京京东乾石科技有限公司 确定车辆位置的方法和装置

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9383753B1 (en) * 2012-09-26 2016-07-05 Google Inc. Wide-view LIDAR with areas of special attention
CN104764457B (zh) * 2015-04-21 2017-11-17 北京理工大学 一种用于无人车的城市环境构图方法
CN106530297B (zh) * 2016-11-11 2019-06-07 北京睿思奥图智能科技有限公司 基于点云配准的物体抓取区域定位方法
CN108228798B (zh) * 2017-12-29 2021-09-17 百度在线网络技术（北京）有限公司 确定点云数据之间的匹配关系的方法和装置
CN109297510B (zh) * 2018-09-27 2021-01-01 百度在线网络技术（北京）有限公司 相对位姿标定方法、装置、设备及介质

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2019070824A1 (en) * 2017-10-03 2019-04-11 Uber Technologies, Inc. METHODS FOR LOCATING AUTONOMOUS VEHICLES
CN109887028A (zh) * 2019-01-09 2019-06-14 天津大学 一种基于点云数据配准的无人车辅助定位方法
US20200393566A1 (en) * 2019-06-14 2020-12-17 DeepMap Inc. Segmenting ground points from non-ground points to assist with localization of autonomous vehicles
CN110609290A (zh) * 2019-09-19 2019-12-24 北京智行者科技有限公司 激光雷达匹配定位方法及装置
CN110988894A (zh) * 2019-12-25 2020-04-10 畅加风行(苏州)智能科技有限公司 一种面向港口环境的多源数据融合的无人驾驶汽车实时定位方法
CN111168669A (zh) * 2019-12-26 2020-05-19 上海高仙自动化科技发展有限公司 机器人控制方法、机器人和可读存储介质
CN111812658A (zh) * 2020-07-09 2020-10-23 北京京东乾石科技有限公司 位置确定方法、装置、系统和计算机可读存储介质
CN112835085A (zh) * 2020-07-09 2021-05-25 北京京东乾石科技有限公司 确定车辆位置的方法和装置
CN112835086A (zh) * 2020-07-09 2021-05-25 北京京东乾石科技有限公司 确定车辆位置的方法和装置

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4130800A4 *

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114353807A (zh) * 2022-03-21 2022-04-15 沈阳吕尚科技有限公司 一种机器人的定位方法及定位装置
CN114353807B (zh) * 2022-03-21 2022-08-12 沈阳吕尚科技有限公司 一种机器人的定位方法及定位装置
CN115236645A (zh) * 2022-09-23 2022-10-25 北京小马易行科技有限公司 激光雷达的姿态确定方法以及姿态确定装置
CN115236645B (zh) * 2022-09-23 2023-01-24 北京小马易行科技有限公司 激光雷达的姿态确定方法以及姿态确定装置
CN115437385A (zh) * 2022-10-21 2022-12-06 上海木蚁机器人科技有限公司 移动机器人的激光定位方法、装置、设备和介质

Also Published As

Publication number Publication date
CN112835085B (zh) 2022-04-12
EP4130800A1 (en) 2023-02-08
US20230204384A1 (en) 2023-06-29
EP4130800A4 (en) 2024-05-08
CN112835085A (zh) 2021-05-25

Similar Documents

Publication Publication Date Title
WO2022007602A1 (zh) 确定车辆位置的方法和装置
CN111812658B (zh) 位置确定方法、装置、系统和计算机可读存储介质
US10788830B2 (en) Systems and methods for determining a vehicle position
CN107727079B (zh) 一种微小型无人机全捷联下视相机的目标定位方法
CN110927708B (zh) 智能路侧单元的标定方法、装置及设备
WO2020038285A1 (zh) 车道线的定位方法和装置、存储介质、电子装置
CN108932737B (zh) 车载相机俯仰角标定方法和装置、电子设备以及车辆
CN207360243U (zh) 车载导航定位全景云台
WO2021164341A1 (zh) 航向安装误差确定
CN110221328A (zh) 一种组合导航方法和装置
CN113933818A (zh) 激光雷达外参的标定的方法、设备、存储介质及程序产品
CN111427061A (zh) 一种机器人建图方法、装置，机器人及存储介质
JP2020064056A (ja) 位置推定装置及び方法
CN112835086B (zh) 确定车辆位置的方法和装置
CN110715659A (zh) 零速检测方法、行人惯性导航方法、装置及存储介质
CN109781117B (zh) 一种组合定位方法和系统
CN109141411B (zh) 定位方法、定位装置、移动机器人及存储介质
CN112116651B (zh) 一种基于无人机单目视觉的地面目标定位方法和系统
WO2022063120A1 (zh) 组合导航系统初始化方法、装置、介质及电子设备
CN114136315B (zh) 一种基于单目视觉辅助惯性组合导航方法及系统
JP4986883B2 (ja) 標定装置、標定方法および標定プログラム
JP6610466B2 (ja) 車両制御システム
CN116952229A (zh) 无人机定位方法、装置、系统和存储介质
JP3005682B1 (ja) 滑走路画像を用いた位置・姿勢の割出し方法およびその装置
CN114413898B (zh) 多传感器数据融合方法、装置、计算机设备及存储介质

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: 21837352

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2021837352

Country of ref document: EP

Effective date: 20221024

NENP Non-entry into the national phase

Ref country code: DE