WO2020168667A1 - 基于共享slam地图的高精度定位方法及*** - Google Patents

基于共享slam地图的高精度定位方法及*** Download PDF

Info

Publication number
WO2020168667A1
WO2020168667A1 PCT/CN2019/093533 CN2019093533W WO2020168667A1 WO 2020168667 A1 WO2020168667 A1 WO 2020168667A1 CN 2019093533 W CN2019093533 W CN 2019093533W WO 2020168667 A1 WO2020168667 A1 WO 2020168667A1
Authority
WO
WIPO (PCT)
Prior art keywords
sensor
vehicle
map
shared
slam map
Prior art date
Application number
PCT/CN2019/093533
Other languages
English (en)
French (fr)
Inventor
周建
肖志光
李良
Original Assignee
广州小鹏汽车科技有限公司
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 广州小鹏汽车科技有限公司 filed Critical 广州小鹏汽车科技有限公司
Priority to EP19916277.7A priority Critical patent/EP3885866A4/en
Publication of WO2020168667A1 publication Critical patent/WO2020168667A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
    • G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
    • 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
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/28—Navigation; 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
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0268—Control of position or course in two dimensions specially adapted to land vehicles using internal positioning means
    • G05D1/0274—Control of position or course in two dimensions specially adapted to land vehicles using internal positioning means using mapping information stored in a memory device

Definitions

  • the present invention relates to the technical field of vehicles, and in particular to a high-precision positioning method and system based on shared SLAM maps (Simultaneous Localization And Mapping, real-time positioning and map construction).
  • GPS Global Positioning System
  • the embodiment of the invention discloses a high-precision positioning method and system based on a shared SLAM map, which can improve the accuracy of the vehicle positioning function.
  • the first aspect of the embodiments of the present invention discloses a high-precision positioning method based on a shared SLAM map, which is characterized in that the method includes:
  • the vehicle body positioning information of the current vehicle is determined according to the sensor positioning information, the external parameters of the first sensor, and the external parameters of the second sensor.
  • the first sensor's pose is acquired by the first sensor of the current vehicle, and it is determined in the shared SLAM map with the The positioning information of the sensor matching the pose of the first sensor includes:
  • the external parameters of the first sensor are acquired, and the external parameters of the second sensor of the shared vehicle are read from the shared SLAM map.
  • Parameters including:
  • the external parameters of the second sensor of the map sharing vehicle are read from the map sharing vehicle information.
  • the current vehicle is determined based on the sensor location information, the external parameters of the first sensor, and the external parameters of the second sensor.
  • Body positioning information including:
  • the current positioning information is determined as the body positioning information of the current vehicle.
  • the method further includes:
  • the second aspect of the embodiments of the present invention discloses a high-precision positioning system based on shared SLAM maps, which is characterized in that it includes:
  • An acquiring unit configured to acquire the shared SLAM map of the current geographic location of the vehicle through the network
  • the first acquisition unit is configured to acquire the first sensor pose through the first sensor of the current vehicle, and determine the sensor positioning information matching the first sensor pose in the shared SLAM map;
  • a reading unit for acquiring the external parameters of the first sensor, and reading the external parameters of the second sensor of the map-sharing vehicle from the shared SLAM map, the shared SLAM map being constructed by the map-sharing vehicle;
  • the first determining unit is configured to determine the current vehicle body positioning information according to the sensor positioning information, the external parameters of the first sensor, and the external parameters of the second sensor.
  • the first collection unit includes:
  • a collection subunit configured to collect the first sensor pose based on the external parameters of the first sensor through the first sensor of the current vehicle
  • a first determining subunit configured to determine a target pose corresponding to the first sensor pose in the shared SLAM map
  • a generating subunit is used to generate sensor positioning information including the target pose, where the sensor positioning information matches the first sensor.
  • the reading unit includes:
  • the first acquisition subunit is configured to acquire current vehicle information of the current vehicle, and read the external parameters of the first sensor in the current vehicle information;
  • the second acquiring subunit is configured to acquire map shared vehicle information of the map shared vehicle that constructs the shared SLAM map included in the shared SLAM map;
  • the reading subunit is used to read the external parameters of the second sensor of the map sharing vehicle from the map sharing vehicle information.
  • the first determining unit includes:
  • a calculation subunit for calculating and generating a transformation matrix between the external parameters of the first sensor and the external parameters of the second sensor
  • a transformation subunit configured to transform the target pose in the sensor positioning information into a second sensor pose through the transformation matrix
  • the second determining subunit is configured to determine the current positioning information matching the pose of the second sensor in the shared SLAM map
  • the third determining subunit is configured to determine the current positioning information as the body positioning information of the current vehicle.
  • system further includes:
  • the second collection unit is configured to collect the geographic location of the current vehicle through the positioning module of the current vehicle;
  • the second determining unit is configured to determine area information corresponding to the geographic location, where the area information includes the geographic location;
  • a detection unit configured to detect whether the current vehicle stores a target SLAM map matching the area information
  • the acquiring unit is specifically configured to acquire the shared SLAM map of the geographic location of the current vehicle through the network when the detection result of the detecting unit is negative.
  • a vehicle-mounted electronic device including:
  • a memory storing executable program codes
  • a processor coupled with the memory
  • the processor invokes the executable program code stored in the memory to execute part or all of the steps of any method of the first aspect.
  • a computer-readable storage medium stores program code, where the program code includes part or all of the method for executing any one of the methods of the first aspect. Step instructions.
  • a fifth aspect of the embodiments of the present invention discloses a computer program product, which when the computer program product runs on a computer, causes the computer to execute part or all of the steps of any method in the first aspect.
  • an application publishing platform is disclosed.
  • the application publishing platform is used to publish a computer program product, wherein when the computer program product runs on a computer, the computer executes any of the first aspect Part or all of the steps of a method.
  • the shared SLAM map of the geographic location of the current vehicle is acquired through the network; the first sensor pose is acquired through the first sensor of the current vehicle, and the pose matching the first sensor is determined in the shared SLAM map Sensor positioning information; obtain the external parameters of the first sensor, and read the external parameters of the second sensor of the map-sharing vehicle from the shared SLAM map.
  • the shared SLAM map is constructed by the map-sharing vehicle; according to the sensor positioning information, the external parameters of the first sensor The parameters and the external parameters of the second sensor determine the current vehicle body positioning information.
  • a shared SLAM map of any geographic location uploaded by other vehicles to the network can be obtained through the network, and the sensor pose of the current vehicle can also be obtained through the sensor, so that the current vehicle can be in the shared SLAM map Determine the unique positioning information corresponding to the sensor's pose, thereby improving the accuracy of the vehicle positioning function.
  • FIG. 1 is a schematic flowchart of a high-precision positioning method based on shared SLAM map disclosed in an embodiment of the present invention
  • FIG. 2 is a schematic flowchart of another high-precision positioning method based on shared SLAM map disclosed in an embodiment of the present invention
  • FIG. 3 is a schematic flowchart of another high-precision positioning method based on shared SLAM map disclosed in an embodiment of the present invention
  • FIG. 4 is a schematic structural diagram of a high-precision positioning system based on shared SLAM maps disclosed in an embodiment of the present invention
  • FIG. 5 is a schematic structural diagram of another high-precision positioning system based on shared SLAM maps disclosed in an embodiment of the present invention.
  • FIG. 6 is a schematic structural diagram of another high-precision positioning system based on shared SLAM maps disclosed in an embodiment of the present invention.
  • Fig. 7 is a schematic structural diagram of a vehicle-mounted electronic device disclosed in an embodiment of the present invention.
  • the embodiment of the invention discloses a high-precision positioning method and system based on a shared SLAM map, which can obtain the shared SLAM map through the network, so that the current vehicle can determine the unique positioning information corresponding to the sensor pose in the shared SLAM map , Thereby improving the accuracy of the vehicle positioning function. Detailed descriptions are given below.
  • FIG. 1 is a schematic flowchart of a high-precision positioning method based on shared SLAM map disclosed in an embodiment of the present invention. As shown in Figure 1, the high-precision positioning method based on shared SLAM maps may include the following steps:
  • the vehicle-mounted electronic device obtains a shared SLAM map of the geographic location of the current vehicle through the network.
  • the current vehicle can use GPS to collect the geographic location of the current vehicle. Because the GPS positioning accuracy is low, and the cross-layer positioning in multi-storey buildings cannot be achieved through GPS, the current vehicle needs to obtain The SLAM map of the geographic location.
  • the SLAM map can be a visual SLAM map or a laser SLAM map. As a high-precision map, the SLAM map can achieve high-precision positioning.
  • the SLAM map can contain information obtained by each sensor The environmental information of different locations, therefore, the SLAM map can contain the spatial information of each geographic location, and the unique positioning information can be determined in the SLAM map based on the spatial information of the current vehicle’s environment collected by the current vehicle’s sensors, so as to achieve The vehicles on the SLAM map are accurately positioned across floors in multi-story buildings.
  • the in-vehicle electronic device may be a control terminal set in the current vehicle, and the owner of the current vehicle can control the current vehicle through the in-vehicle electronic device.
  • the current vehicle may store SLAM maps in advance, and there is no limit to the number of SLAM maps stored in the current vehicle. If the current vehicle stores the target SLAM map corresponding to the geographic location of the current vehicle, the current vehicle The vehicle can directly use the target SLAM map to locate the current vehicle; if the current vehicle does not store the target SLAM map corresponding to the geographic location of the current vehicle, the current vehicle can obtain the geographic location through the network (such as the Internet, local area network, etc.) The matched shared SLAM map is then positioned according to the acquired shared SLAM map.
  • the network such as the Internet, local area network, etc.
  • the method of the pre-stored SLAM map of the current vehicle may be: if the geographic location where the current vehicle travels is the location that the current vehicle travels to for the first time, and the current vehicle fails to obtain the corresponding SLAM map through the network, then
  • the vehicle can collect the current environmental information around the vehicle through the sensors on the vehicle (such as vision sensors or laser sensors, etc.), and then can construct a SLAM map based on the environmental information collected by the sensors, and the size of the area covered by the SLAM can be preset
  • the size of the area the current vehicle can associate the constructed SLAM map with the current geographic location and store it in the current vehicle, so that when the vehicle passes the geographic location again, it can directly obtain the SLAM map for positioning, which improves the vehicle positioning Accuracy can also speed up vehicle positioning.
  • the current shared SLAM map obtained by the vehicle through the network can construct a SLAM map for the map-sharing vehicle, and then associate the SLAM map with the geographic location of the map-sharing vehicle and store it on a server (such as a cloud server).
  • a server such as a cloud server.
  • the external parameters of the sensors on the map-sharing vehicle may also be different from the external parameters of the sensors of the current vehicle, in order to ensure that any vehicle can be used.
  • the shared SLAM map can store the vehicle information of the map shared vehicle that constructs the shared SLAM map.
  • the vehicle information can include the model of the map shared vehicle, the external parameters of the sensor, and inertial measurement Information such as parameters of a unit (Inertial Measurement Unit, IMU), which is not limited in this embodiment of the present invention.
  • IMU Inertial Measurement Unit
  • the vehicle-mounted electronic device obtains the first sensor pose through the first sensor of the current vehicle, and determines the sensor positioning information matching the first sensor pose in the shared SLAM map.
  • the first sensor may be a vision sensor or a laser sensor installed on the current vehicle, and the vision sensor may be a sensor such as a camera or a camera installed on the current vehicle.
  • the first sensor may be arranged in front of the current vehicle or on the top of the current vehicle. When the current vehicle is driving, the position of the sensor can be collected at all times through the first sensor, that is, the position of the first sensor.
  • the first sensor pose acquired by the current vehicle can find the same pose in the shared SLAM map, so the on-board electronic device can determine the target pose matching the first sensor pose from the shared SLAM map, and further from the shared SLAM map
  • the position information corresponding to the target pose is determined, so that the position information corresponding to the target pose is determined as the sensor positioning information.
  • the vehicle-mounted electronic device obtains the external parameters of the first sensor, and reads the external parameters of the second sensor of the map-sharing vehicle from the shared SLAM map, and the shared SLAM map is constructed by the map-sharing vehicle.
  • the first sensor of the current vehicle may determine that the first sensor is based on the external parameters of the first sensor of the current vehicle relative to the vehicle body before the initial driving.
  • the in-vehicle electronic device can obtain the vehicle information of the map-sharing vehicle that constructs the shared SLAM map from the shared SLAM map, and can determine the shared external parameters of the sensors of the map-sharing vehicle from the vehicle information.
  • the vehicle-mounted electronic device determines the current vehicle body positioning information according to the sensor positioning information, the external parameters of the first sensor, and the external parameters of the second sensor.
  • the on-vehicle electronic device can calculate the current transformation matrix from the external parameter of the first sensor to the shared external parameter of the shared sensor based on the external parameters of the first sensor and the external parameters of the shared sensor, so that the on-board electronic device The target pose in the sensor positioning information that is the same as the first sensor pose is transformed to the second sensor pose through the current transformation matrix.
  • the second sensor pose is also the pose in the shared SLAM map.
  • the on-board electronic device can The position information corresponding to the pose of the second sensor is determined in the shared SLAM map, and the position information corresponding to the pose of the second sensor can be considered as the body positioning information of the current vehicle body.
  • the shared SLAM map can be obtained through the network, so that the current vehicle can determine the unique positioning information corresponding to the sensor pose in the shared SLAM map, thereby improving the accuracy of the vehicle positioning function .
  • implementing the method described in FIG. 1 not only improves the accuracy of vehicle positioning, but also speeds up vehicle positioning.
  • FIG. 2 is a schematic flowchart of another high-precision positioning method based on shared SLAM map disclosed in an embodiment of the present invention.
  • the embodiment of the present invention adds a method for determining the sensor positioning information corresponding to the first sensor's pose in the shared SLAM map, and explains in more detail the construction of the second sensor of the shared vehicle of the shared SLAM map.
  • the acquisition method of external parameters not only improves the accuracy of positioning based on the shared SLAM map, but also accurately acquires the external parameters of the second sensor in the shared SLAM map.
  • the high-precision positioning method based on shared SLAM maps may include the following steps:
  • the vehicle-mounted electronic device obtains a shared SLAM map of the geographic location of the current vehicle through the network.
  • the vehicle-mounted electronic device acquires the first sensor pose based on the external parameter of the first sensor through the first sensor of the current vehicle.
  • the first sensor of the current vehicle may be a vision sensor or a laser sensor.
  • the first sensor of the current vehicle can record the pose of the first sensor. Since the shared SLAM map is constructed by the sensor pose collected by the second sensor and the body pose collected by the body odometer, it is necessary to obtain the current vehicle's pose
  • the first sensor is relative to the external parameters of the body of the current vehicle, so that the external parameters of the first sensor can determine the relationship between the pose of the first sensor collected by the first sensor and the body of the current vehicle.
  • the external parameters of the first sensor may include six degrees of freedom. The six degrees of freedom may be obtained based on the first sensor coordinate system of the first sensor.
  • the first sensor coordinate system may take the first sensor as the coordinate origin.
  • the forward direction of the vehicle is the x-axis of the first sensor coordinate system
  • the left side of the current forward direction of the vehicle is the y-axis of the first sensor coordinate system
  • the direction perpendicular to the ground plane is the z direction.
  • the first sensor coordinate system may also include The current vehicle heading angle ⁇ , roll angle ⁇ , and pitch angle ⁇ , therefore, x, y, z, ⁇ , ⁇ , and ⁇ are the external parameters of the first sensor and include six degrees of freedom.
  • the vehicle-mounted electronic device determines the target pose corresponding to the first sensor pose in the shared SLAM map.
  • the in-vehicle electronic device can determine the position of the first sensor in the shared SLAM map.
  • the target pose corresponding to the pose.
  • the vehicle-mounted electronic device generates sensor positioning information including the target pose, and the sensor positioning information matches the first sensor.
  • the target pose in the shared SLAM map can correspond to the target location information of the map-sharing vehicle, and the on-board electronic device can generate sensor location information containing the target location information.
  • the target pose corresponding to the first sensor pose can be determined from the shared SLAM map, and the geographic location corresponding to the target pose can be determined from the shared SLAM map.
  • the geographic location can be determined as the pose of the first sensor's pose in the shared SLAM map, so that the pose currently collected by the first sensor can be linked with the shared SLAM map, so that the in-vehicle electronic device can read from the shared SLAM map. Determine the position of the first sensor pose.
  • the on-vehicle electronic device acquires current vehicle information of the current vehicle, and reads the external parameters of the first sensor in the current vehicle information.
  • the current vehicle information of the current vehicle may include various parameter information of the vehicle, such as the model of the vehicle, the information of the equipment installed on the vehicle, etc. Therefore, the current vehicle information may include the first sensor installed on the current vehicle External parameters.
  • the in-vehicle electronic device acquires map shared vehicle information of the map shared vehicle that constructs the shared SLAM map included in the shared SLAM map.
  • a map-sharing vehicle constructs a shared SLAM map
  • the second sensor is constructed and can collect images in the second coordinate system established by the external parameters of the second sensor. Therefore, it can be considered that the image for constructing the shared SLAM map is obtained based on the second coordinate system of the second sensor.
  • the on-board electronic device reads the external parameters of the second sensor of the map-sharing vehicle from the map-sharing vehicle information.
  • the above steps 205 to 207 are implemented. Since the shared SLAM map is constructed by map-sharing vehicles, and the external parameters of the visual sensors may be different between different vehicles, the map-sharing vehicles can When constructing the shared SLAM map, add the external parameters of the second sensor of the map-sharing vehicle to the map-sharing vehicle information of the shared SLAM map, so that the vehicle using the shared SLAM map can obtain the map-sharing vehicle information from the map-sharing vehicle information According to the external parameters of the second sensor, the sensor pose of the first sensor acquired by the current vehicle is accurately converted to the shared SLAM map according to the external parameters of the second sensor, so as to improve the accuracy of positioning based on the shared SLAM map.
  • the vehicle-mounted electronic device determines the current vehicle body positioning information according to the sensor positioning information, the external parameters of the first sensor, and the external parameters of the second sensor.
  • the shared SLAM map can be obtained through the network, so that the current vehicle can determine the unique positioning information corresponding to the sensor pose in the shared SLAM map, thereby improving the accuracy of the vehicle positioning function .
  • implementing the method described in FIG. 2 can determine the position of the first sensor's pose from the shared SLAM map.
  • implementing the method described in Figure 2 can improve the accuracy of positioning based on shared SLAM maps.
  • FIG. 3 is a schematic flowchart of another high-precision positioning method based on shared SLAM map disclosed in an embodiment of the present invention.
  • the embodiment of the present invention further illustrates the method of positioning the first sensor pose based on the transformation matrix in the shared SLAM map, and also enriches the way to obtain the shared SLAM map, which can improve vehicle positioning. It can also accurately obtain the shared SLAM map currently needed by the vehicle.
  • the high-precision positioning method based on shared SLAM map may include the following steps:
  • the vehicle-mounted electronic device collects the geographic location of the current vehicle through the positioning module of the current vehicle.
  • the positioning module of the current vehicle may include a GPS positioning device, so that the on-board electronic equipment can locate the current vehicle according to the GPS positioning device when the SLAM map is not obtained, and obtain the geographic location of the current vehicle.
  • the geographic location can be represented by GPS information, so that the current vehicle can be positioned without obtaining the SLAM map, which ensures the comprehensiveness of vehicle positioning.
  • the in-vehicle electronic device determines area information corresponding to the geographic location, and the area information includes the geographic location.
  • the on-vehicle electronic device can be divided into several areas in advance, and the coverage of each area can be determined in advance.
  • the on-vehicle electronic device can set the geographic location contained in each area, so that the coverage of each area is based on the regional information. , So that the in-vehicle electronic equipment can determine the area information that matches any geographic location.
  • the SLAM map can be constructed based on the coverage of each area, so that the on-board electronic equipment can obtain the SLAM map within a certain range near the current geographic location, ensuring the comprehensive positioning based on the SLAM map.
  • the in-vehicle electronic device detects whether the current vehicle stores a target SLAM map matching the area information, and if so, ends this process; if not, executes step 304 to step 314.
  • the following steps can also be performed:
  • the vehicle-mounted electronic equipment obtains the pre-stored target SLAM map
  • the vehicle-mounted electronic device acquires the current sensor pose through the first sensor of the current vehicle
  • the vehicle-mounted electronic device determines the current positioning information matching the current sensor pose in the target SLAM map.
  • the target SLAM map stored in advance by the on-board electronic device can be directly obtained, so that the on-board electronic device can determine the vehicle's positioning information in the target SLAM map according to the current sensor pose acquired by the first sensor, thereby The process of acquiring the SLAM map is simplified, and the positioning speed of the vehicle in the SLAM map is improved.
  • the above steps 301 to 303 are implemented. Since the SLAM map can include roads, buildings, etc. in an area, the vehicle can be determined according to the current rough geographic location (such as GPS positioning information) obtained The area where the vehicle is located, and the SLAM map of the area is obtained, so that the vehicle can perform accurate positioning according to the SLAM map of the area.
  • the current rough geographic location such as GPS positioning information
  • the vehicle-mounted electronic device obtains a shared SLAM map of the geographic location of the current vehicle through the network.
  • the vehicle-mounted electronic device acquires the first sensor pose based on the external parameter of the first sensor through the first sensor of the current vehicle.
  • the vehicle-mounted electronic device determines the target pose corresponding to the first sensor pose in the shared SLAM map.
  • the vehicle-mounted electronic device generates sensor positioning information including the target pose, and the sensor positioning information matches the first sensor.
  • the on-board electronic device acquires current vehicle information of the current vehicle, and reads the external parameters of the first sensor in the current vehicle information.
  • the on-board electronic device acquires map shared vehicle information of the map shared vehicle that constructs the shared SLAM map included in the shared SLAM map.
  • the on-board electronic device reads the external parameters of the second sensor of the map-sharing vehicle from the map-sharing vehicle information.
  • the in-vehicle electronic device calculates and generates a transformation matrix between the external parameter of the first sensor and the external parameter of the second sensor.
  • the manner in which the vehicle-mounted electronic device calculates and generates a transformation matrix between the external parameters of the first sensor and the external parameters of the second sensor may include the following steps:
  • the in-vehicle electronic device generates a first conversion matrix between the first sensor of the current vehicle and the body of the current vehicle according to the external parameters of the first sensor, and the first conversion matrix is used to convert the data collected by the first sensor in the first sensor coordinate system The pose of the first sensor below is converted to the first body coordinate system of the current vehicle body;
  • the in-vehicle electronic device generates a second conversion matrix between the second sensor of the map-sharing vehicle and the body of the map-sharing vehicle according to the external parameters of the second sensor, and the second conversion matrix is used to transfer the data collected by the second sensor to the second sensor
  • the pose of the second sensor in the coordinate system is converted to the second body coordinate system of the body of the map-sharing vehicle;
  • the in-vehicle electronic device multiplies the inverse matrix of the first transformation matrix by the second transformation matrix to obtain a transformation matrix between the external parameters of the first sensor and the external parameters of the second sensor.
  • the first conversion matrix and the second conversion matrix can be generated respectively according to the external parameters of the first sensor and the external parameters of the second sensor, and the inverse matrix of the first conversion matrix and the second conversion matrix Multiply to obtain the transformation matrix between the external parameters of the first sensor and the external parameters of the second sensor, so that the pose of the first sensor collected by the first sensor of the current vehicle is transformed to the shared vehicle constructed by the map sharing vehicle through the transformation matrix In the SLAM map, the accuracy of the pose transformation of the first sensor is improved.
  • the vehicle-mounted electronic device transforms the target pose in the sensor positioning information into the second sensor pose through the transformation matrix.
  • the target pose can be considered to be the pose based on the external parameters of the first sensor of the current vehicle in the shared SLAM map, and the second sensor pose obtained by the conversion matrix of the target pose can be considered to be shared
  • the SLAM map is based on the pose of the external parameters of the second sensor of the map-sharing vehicle, that is, the external parameters of the first sensor of the current vehicle are transformed into the external parameters of the second sensor of the map-sharing vehicle that shares the SLAM map.
  • the positioning in the shared SLAM map corresponding to the sensor pose can be understood as the positioning information of the current body of the current vehicle.
  • the vehicle-mounted electronic device determines the current positioning information matching the pose of the second sensor in the shared SLAM map.
  • the vehicle-mounted electronic device determines the current positioning information as the current vehicle body positioning information.
  • the steps 311 to 314 described above can be used to transform the pose of the first vision sensor based on the external parameters of the first sensor into the second vision based on the external parameters of the second sensor based on the transformation matrix.
  • the sensor pose so that the second vision sensor pose based on the external parameters of the second sensor can be accurately positioned in the shared SLAM map to improve the accuracy of positioning.
  • the shared SLAM map can be obtained through the network, so that the current vehicle can determine the unique positioning information corresponding to the sensor pose in the shared SLAM map, thereby improving the accuracy of the vehicle positioning function .
  • implementing the method described in FIG. 3 simplifies the acquisition process of the SLAM map and improves the positioning speed of the vehicle in the SLAM map.
  • the implementation of the method described in Figure 3 enables the vehicle to perform accurate positioning based on the SLAM map of the area.
  • implementing the method described in FIG. 3 improves the accuracy of the pose transformation of the first sensor.
  • the method described in Figure 3 is implemented to improve the accuracy of positioning.
  • FIG. 4 is a schematic structural diagram of a high-precision positioning system based on shared SLAM map disclosed in an embodiment of the present invention.
  • the high-precision positioning system based on shared SLAM maps may include:
  • the acquiring unit 401 is configured to acquire a shared SLAM map of the geographic location of the current vehicle through the network.
  • the first acquisition unit 402 is configured to acquire the first sensor pose through the first sensor of the current vehicle, and determine the sensor positioning information matching the first sensor pose in the shared SLAM map.
  • the reading unit 403 is configured to obtain the external parameters of the first sensor, and read the external parameters of the second sensor of the map-sharing vehicle from the shared SLAM map obtained by the obtaining unit 401.
  • the shared SLAM map is constructed by the map-sharing vehicle.
  • the first determining unit 404 is configured to determine the current vehicle body positioning information according to the sensor positioning information collected by the first collecting unit 402, the external parameters of the first sensor obtained by the reading unit 403, and the external parameters of the second sensor.
  • the shared SLAM map can be obtained through the network, so that the current vehicle can determine the unique positioning information corresponding to the sensor pose in the shared SLAM map, thereby improving the vehicle positioning function. Accuracy.
  • the accuracy of vehicle positioning is improved, and the speed of vehicle positioning can also be accelerated.
  • FIG. 5 is a schematic structural diagram of another high-precision positioning system based on shared SLAM map disclosed in an embodiment of the present invention.
  • the high-precision positioning system based on the shared SLAM map shown in FIG. 5 is optimized by the high-precision positioning system based on the shared SLAM map shown in FIG. 4.
  • the high-precision positioning system based on the shared SLAM map shown in Figure 5 determines the sensor positioning information corresponding to the first sensor's pose in the shared SLAM map , And a more detailed description of the method of acquiring the external parameters of the second sensor of the shared vehicle for constructing a shared SLAM map, which not only improves the accuracy of positioning based on the shared SLAM map, but also accurately obtains the second sensor in the shared SLAM map
  • the first collection unit 402 in the high-precision positioning system based on shared SLAM map shown in FIG. 5 may include:
  • the collection subunit 4021 is configured to collect the first sensor pose based on the external parameters of the first sensor through the first sensor of the current vehicle.
  • the first determining subunit 4022 is configured to determine the target pose corresponding to the first sensor pose collected by the collecting subunit 4021 in the shared SLAM map.
  • the generating subunit 4023 is configured to generate sensor positioning information including the target pose determined by the first determining subunit 4022, and the sensor positioning information matches the first sensor.
  • the target pose corresponding to the first sensor pose may be determined from the shared SLAM map, and the geographic location corresponding to the target pose may be determined from the shared SLAM map, and the geographic location may be determined as the first sensor
  • the pose is the pose in the shared SLAM map, so that the pose currently collected by the first sensor can be linked with the shared SLAM map, so that the vehicle-mounted electronic device can determine the position of the first sensor's pose from the shared SLAM map.
  • the reading unit 403 of the high-precision positioning system based on the shared SLAM map shown in FIG. 5 may include:
  • the first acquiring subunit 4031 is used to acquire current vehicle information of the current vehicle, and read the external parameters of the first sensor in the current vehicle information;
  • the second acquiring subunit 4032 is configured to acquire map shared vehicle information of the map shared vehicle used to construct the shared SLAM map included in the shared SLAM map;
  • the second acquiring subunit 4032 is triggered to start.
  • the reading subunit 4033 is configured to read the external parameters of the second sensor of the map shared vehicle from the map shared vehicle information acquired by the second acquisition subunit 4032.
  • the map-sharing vehicle can use the map when constructing the shared SLAM map.
  • the external parameters of the second sensor of the shared vehicle are added to the map shared vehicle information of the shared SLAM map, so that the vehicle using the shared SLAM map can obtain the external parameters of the second sensor of the map shared vehicle from the map shared vehicle information, Furthermore, according to the external parameters of the second sensor, the sensor pose of the first sensor acquired by the current vehicle is accurately converted to the shared SLAM map, so as to improve the accuracy of positioning based on the shared SLAM map.
  • the shared SLAM map can be obtained through the network, so that the current vehicle can determine the unique positioning information corresponding to the sensor pose in the shared SLAM map, thereby improving the vehicle positioning function. Accuracy.
  • the position of the first sensor's pose can be determined from the shared SLAM map.
  • the accuracy of positioning based on shared SLAM maps can be improved.
  • FIG. 6 is a schematic structural diagram of another high-precision positioning system based on shared SLAM map disclosed in an embodiment of the present invention.
  • the high-precision positioning system based on the shared SLAM map shown in FIG. 6 is optimized by the high-precision positioning system based on the shared SLAM map shown in FIG. 5.
  • the high-precision positioning system based on the shared SLAM map shown in Figure 6 further illustrates the positioning of the first sensor based on the transformation matrix in the shared SLAM map.
  • a determining unit 404 may include:
  • the calculation subunit 4041 is used to calculate and generate a transformation matrix between the external parameters of the first sensor and the external parameters of the second sensor.
  • the transformation subunit 4042 is used to transform the target pose in the sensor positioning information into the second sensor pose through the transformation matrix obtained by the calculation subunit 4041.
  • the second determining subunit 4043 is configured to determine the current positioning information matching the pose of the second sensor determined by the transforming subunit 4042 in the shared SLAM map.
  • the third determining subunit 4044 is configured to determine the current positioning information determined by the second determining subunit 4043 as the current vehicle body positioning information.
  • the implementation of this embodiment can be based on the transformation matrix to transform the pose of the first vision sensor based on the external parameters of the first sensor into the pose of the second vision sensor based on the external parameters of the second sensor, so that The second visual sensor's pose, which is the external parameter of the second sensor, can accurately locate in the shared SLAM map, improving the accuracy of positioning.
  • the calculation subunit 4041 calculates and generates a transformation matrix between the external parameters of the first sensor and the external parameters of the second sensor, specifically, as follows:
  • the first conversion matrix between the first sensor of the current vehicle and the body of the current vehicle is generated according to the external parameters of the first sensor, and the first conversion matrix is used to convert the first sensor collected by the first sensor in the first sensor coordinate system.
  • a sensor pose is converted to the first body coordinate system of the current vehicle body;
  • the second conversion matrix is used to convert the data collected by the second sensor in the second sensor coordinate system.
  • the pose of the second sensor is converted to the second body coordinate system of the body of the map-sharing vehicle;
  • the inverse matrix of the first conversion matrix is multiplied by the second conversion matrix to obtain a conversion matrix between the external parameters of the first sensor and the external parameters of the second sensor.
  • the first conversion matrix and the second conversion matrix can be generated respectively according to the external parameters of the first sensor and the external parameters of the second sensor, and the inverse matrix of the first conversion matrix and the second conversion matrix Multiply to obtain the transformation matrix between the external parameters of the first sensor and the external parameters of the second sensor, so that the pose of the first sensor collected by the first sensor of the current vehicle is transformed to the shared vehicle constructed by the map sharing vehicle through the transformation matrix In the SLAM map, the accuracy of the pose transformation of the first sensor is improved.
  • the high-precision positioning system based on the shared SLAM map shown in FIG. 5 may further include:
  • the second collecting unit 405 is configured to collect the geographic position of the current vehicle through the positioning module of the current vehicle;
  • the second determining unit 406 is configured to determine the area information corresponding to the geographic location collected by the second collecting unit 405, and the area information includes the geographic location;
  • the detecting unit 407 is configured to detect whether the current vehicle stores a target SLAM map that matches the area information determined by the second determining unit 406;
  • the obtaining unit 401 is configured to obtain a shared SLAM map of the geographic location of the current vehicle through the network when the detection result of the detecting unit 407 is negative.
  • the vehicle can determine the area where the vehicle is located according to the current rough geographic location (such as GPS positioning information) obtained, and obtain the The SLAM map of the area, so that the vehicle can perform accurate positioning according to the SLAM map of the area.
  • the current rough geographic location such as GPS positioning information
  • the detection unit 407 may also be used for:
  • the target SLAM map stored in advance by the on-board electronic device can be directly obtained, so that the on-board electronic device can determine the vehicle's positioning information in the target SLAM map according to the current sensor pose acquired by the first sensor, thereby The process of acquiring the SLAM map is simplified, and the positioning speed of the vehicle in the SLAM map is improved.
  • the shared SLAM map can be obtained through the network, so that the current vehicle can determine the unique positioning information corresponding to the sensor pose in the shared SLAM map, thereby improving the vehicle positioning function. Accuracy.
  • the acquisition process of the SLAM map is simplified, and the positioning speed of the vehicle in the SLAM map is improved.
  • the vehicle can be accurately positioned according to the SLAM map of the area.
  • the accuracy of the pose transformation of the first sensor is improved.
  • the accuracy of positioning can be improved.
  • FIG. 7 is a schematic structural diagram of a vehicle-mounted electronic device disclosed in an embodiment of the present invention.
  • the vehicle-mounted electronic equipment may include:
  • a memory 701 storing executable program codes
  • a processor 702 coupled with the memory 701;
  • the processor 702 calls the executable program code stored in the memory 701 to execute part or all of the steps of the method in the above method embodiments.
  • the embodiment of the present invention also discloses a computer-readable storage medium, where the computer-readable storage medium stores program code, where the program code includes instructions for executing part or all of the steps in the above method embodiments.
  • the embodiment of the present invention also discloses a computer program product, wherein when the computer program product runs on a computer, the computer is caused to execute part or all of the steps of the method in the above method embodiments.
  • the embodiment of the present invention also discloses an application publishing platform, wherein the application publishing platform is used to publish a computer program product, wherein, when the computer program product runs on a computer, the computer is caused to execute parts of the method in the above method embodiments Or all steps.
  • system and “network” in this article are often used interchangeably in this article.
  • and/or in this text is only an association relationship that describes associated objects, indicating that there can be three relationships, such as A and/or B, which can mean that A alone exists, and A and B exist at the same time. There are three cases of B alone.
  • character “/” in this text generally indicates that the associated objects before and after are in an "or” relationship.
  • B corresponding to A means that B is associated with A, and B can be determined according to A.
  • determining B according to A does not mean that B is determined only according to A, and B can also be determined according to A and/or other information.
  • the program can be stored in a computer-readable storage medium.
  • the storage medium includes read-only Memory (Read-Only Memory, ROM), Random Access Memory (RAM), Programmable Read-only Memory (PROM), Erasable Programmable Read Only Memory, EPROM), One-time Programmable Read-Only Memory (OTPROM), Electronically-Erasable Programmable Read-Only Memory (EEPROM), CD-ROM (Compact Disc) Read-Only Memory, CD-ROM) or other optical disk storage, magnetic disk storage, tape storage, or any other computer-readable medium that can be used to carry or store data.
  • Read-Only Memory ROM
  • RAM Random Access Memory
  • PROM Programmable Read-only Memory
  • EPROM Erasable Programmable Read Only Memory
  • OTPROM One-time Programmable Read-Only Memory
  • EEPROM Electronically-Erasable Programmable Read-Only Memory
  • CD-ROM Compact Disc
  • the units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • the functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit.
  • the above-mentioned integrated unit can be implemented in the form of hardware or software functional unit.
  • the aforementioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-accessible memory.
  • the essence of the technical solution of the present invention or the part that contributes to the existing technology or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory.
  • a computer device which may be a personal computer, a server, or a network device, etc., specifically a processor in a computer device

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • General Physics & Mathematics (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Multimedia (AREA)
  • Electromagnetism (AREA)
  • Navigation (AREA)
  • Instructional Devices (AREA)

Abstract

一种基于共享SLAM地图的高精度定位方法及***，包括：通过网络获取当前车辆所处地理位置的共享SLAM地图（101）；在共享SLAM地图中确定第一传感器的定位信息（102），并结合当前车辆的第一传感器的外部参数以及地图共享车辆的第二传感器的外部参数，确定当前车辆的车身在共享地图中的相对定位信息（104）；能够通过网络发布自身车辆或者获取到其他车辆的任意地理位置的共享SLAM地图，共享SLAM地图为相对坐标地图，可以为视觉或者激光SLAM地图；通过附加传感器与车身的外部参数信息，提高了相对坐标地图制图和定位的灵活性，还提高了车辆定位功能的准确率。

Description

基于共享SLAM地图的高精度定位方法及*** 技术领域
本发明涉及车辆技术领域，具体涉及一种基于共享SLAM地图(Simultaneous Localization And Mapping，即时定位与构建地图)的高精度定位方法及***。
背景技术
随着自动驾驶汽车的快速发展，定位功能几乎成为了自动驾驶汽车的必备功能。当前，自动驾驶汽车通常会使用全球定位***(Global Positioning System，GPS)对自动驾驶汽车进行定位。然而，在实践中发现，当自动驾驶汽车处于地下停车场或者多层停车场时，通过GPS确定的自动驾驶车辆的当前位置可能对应当前停车场的多个位置，因此自动驾驶车辆无法根据GPS定位到自动驾驶车辆在当前停车场中的具***置，从而导致自动驾驶汽车的定位功能的准确率较低。
发明内容
本发明实施例公开一种基于共享SLAM地图的高精度定位方法及***，能够提高车辆定位功能的准确率。
本发明实施例第一方面公开一种基于共享SLAM地图的高精度定位方法，其特征在于，所述方法包括：
通过网络获取当前车辆所处地理位置的所述共享SLAM地图；
通过所述当前车辆的第一传感器采集得到第一传感器位姿，并在所述共享SLAM地图中确定与所述第一传感器位姿匹配的传感器定位信息；
获取所述第一传感器的外部参数，并从所述共享SLAM地图中读取地图共享车辆的第二传感器的外部参数，所述共享SLAM地图由所述地图共享车辆构建；
根据所述传感器定位信息、所述第一传感器的外部参数以及所述第二传感器的外部参数确定所述当前车辆的车身定位信息。
作为一种可选的实施方式，在本发明实施例第一方面中，所述通过所述当前车辆的第一传感器采集得到第一传感器位姿，并在所述共享SLAM地图中确定与所述第一传感器位姿匹配的传感器定位信息，包括：
通过所述当前车辆的第一传感器采集得到基于所述第一传感器的外部参数的第一传感器位姿；
在所述共享SLAM地图中确定与所述第一传感器位姿对应的目标位姿；
生成包含所述目标位姿的传感器定位信息，所述传感器定位信息与所述第一传感器匹配。
作为一种可选的实施方式，在本发明实施例第一方面中，所述获取所述第一传感器的外部参数，并从所述共享SLAM地图中读取地图共享车辆的第二传感器的外部参数，包括：
获取所述当前车辆的当前车辆信息，并读取所述当前车辆信息中的所述第一传感器的外部参数；
获取所述共享SLAM地图中包含的构建所述共享SLAM地图的地图共享车辆的地图共享车辆信息；
从所述地图共享车辆信息中读取所述地图共享车辆的第二传感器的外部参数。
作为一种可选的实施方式，在本发明实施例第一方面中，所述根据所述传感器定位信息、所述第一传感器的外部参数以及所述第二传感器的外部参数确定所述当前车辆的车身定位信息，包括：
计算生成所述第一传感器的外部参数与所述第二传感器的外部参数之间的变换矩阵；
通过所述变换矩阵将所述传感器定位信息中的所述目标位姿变换为第二传感器位姿；
在所述共享SLAM地图中确定与所述第二传感器位姿匹配的当前定位信息；
将所述当前定位信息确定为所述当前车辆的车身定位信息。
作为一种可选的实施方式，在本发明实施例第一方面中，所述方法还包括：
通过当前车辆的定位模块采集所述当前车辆所处的地理位置；
确定所述地理位置对应的区域信息，所述区域信息中包含所述地理位置；
检测所述当前车辆是否存储有与所述区域信息匹配的目标SLAM地图；
如果否，执行所述的通过网络获取当前车辆所处地理位置的所述共享SLAM地图。
本发明实施例第二方面公开一种基于共享SLAM地图的高精度定位***，其特征在于，包括：
获取单元，用于通过网络获取当前车辆所处地理位置的所述共享SLAM地图；
第一采集单元，用于通过所述当前车辆的第一传感器采集得到第一传感器位姿，并在所述共享SLAM地图中确定与所述第一传感器位姿匹配的传感器定位信息；
读取单元，用于获取所述第一传感器的外部参数，并从所述共享SLAM地图中读取地图共享车辆的第二传感器的外部参数，所述共享SLAM地图由所述地图共享车辆构建；
第一确定单元，用于根据所述传感器定位信息、所述第一传感器的外部参数以及所述第二传感器的外部参数确定所述当前车辆的车身定位信息。
作为一种可选的实施方式，在本发明实施例第二方面中，所述第一采集单元包括：
采集子单元，用于通过所述当前车辆的第一传感器采集得到基于所述第一传感器的外部参数的第一传感器位姿；
第一确定子单元，用于在所述共享SLAM地图中确定与所述第一传感器位姿对应的目标位姿；
生成子单元，用于生成包含所述目标位姿的传感器定位信息，所述传感器定位信息与所述第一传感器匹配。
作为一种可选的实施方式，在本发明实施例第二方面中，所述读取单元包括：
第一获取子单元，用于获取所述当前车辆的当前车辆信息，并读取所述当前车辆信息中的所述第一传感器的外部参数；
第二获取子单元，用于获取所述共享SLAM地图中包含的构建所述共享SLAM地图的地图共享车辆的地图共享车辆信息；
读取子单元，用于从所述地图共享车辆信息中读取所述地图共享车辆的第二传感器的外部参数。
作为一种可选的实施方式，在本发明实施例第二方面中，所述第一确定单元包括：
计算子单元，用于计算生成所述第一传感器的外部参数与所述第二传感器的外部参数之间的变换矩阵；
变换子单元，用于通过所述变换矩阵将所述传感器定位信息中的所述目标位姿变换为第二传感器位姿；
第二确定子单元，用于在所述共享SLAM地图中确定与所述第二传感器位姿匹配的当前定位信息；
第三确定子单元，用于将所述当前定位信息确定为所述当前车辆的车身定位信息。
作为一种可选的实施方式，在本发明实施例第二方面中，所述***还包括：
第二采集单元，用于通过当前车辆的定位模块采集所述当前车辆所处的地理位置；
第二确定单元，用于确定所述地理位置对应的区域信息，所述区域信息中包含所述地理位置；
检测单元，用于检测所述当前车辆是否存储有与所述区域信息匹配的目标SLAM地图；
所述获取单元，具体用于在所述检测单元的检测结果为否时，通过网络获取当前车辆所处地理位置的所述共享SLAM地图。
本发明实施例第三方面公开一种车载电子设备，包括：
存储有可执行程序代码的存储器；
与所述存储器耦合的处理器；
所述处理器调用所述存储器中存储的所述可执行程序代码，执行第一方面的任意一种方法的部分或全部步骤。
本发明实施例第四方面公开一种计算机可读存储介质，所述计算机可读存储介质存储了程序代码，其中，所述程序代码包括用于执行第一方面的任意一种方法的部分或全部步骤的指令。
本发明实施例第五方面公开一种计算机程序产品，当所述计算机程序产品在计算机上运行时，使得所述计算机执行第一方面的任意一种方法的部分或全部步骤。
本发明实施例第六方面公开一种应用发布平台，所述应用发布平台用于发布计算机程序产品，其中，当所述计算机程序产品在计算机上运行时，使得所述计算机执行第一方面的任意一种方法的部分或全部步骤。
与现有技术相比，本发明实施例具有以下有益效果：
本发明实施例中，通过网络获取当前车辆所处地理位置的共享SLAM地图；通过当前车辆的第一传感器采集得到第一传感器位姿，并在共享SLAM地图中确定与第一传感器位姿匹配的传感器定位信息；获取第一传感器的外部参数，并从共享SLAM地图中读取地图共享车辆的第二传感器的外部参数，共享SLAM地图由地图共享车辆构建；根据传感器定位信息、第一传感器的外部参数以及第二传感器的外部参数确定当前车辆的车身定位信息。可见，实施本发明实施例，能够通过网络获取到其他车辆上传至网络的任意地理位置的共享SLAM地图，并且还可以通过传感器获取当前车辆的传感器位姿，以使当前车辆可以在共享SLAM地图中确定与该传感器位姿对应的唯一的定位信息，从而提高了车辆定位功能的准确率。
附图说明
为了更清楚地说明本发明实施例中的技术方案，下面将对实施例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是本发明实施例公开的一种基于共享SLAM地图的高精度定位方法的流程示意图；
图2是本发明实施例公开的另一种基于共享SLAM地图的高精度定位方法的流程示意图；
图3是本发明实施例公开的另一种基于共享SLAM地图的高精度定位方法的流程示意图；
图4是本发明实施例公开的一种基于共享SLAM地图的高精度定位***的结构示意图；
图5是本发明实施例公开的另一种基于共享SLAM地图的高精度定位***的结构示意图；
图6是本发明实施例公开的另一种基于共享SLAM地图的高精度定位***的结构示意图；
图7是本发明实施例公开的一种车载电子设备的结构示意图。
具体实施方式
下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅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做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。
需要说明的是，本发明实施例及附图中的术语“包括”和“具有”以及它们任何变形，意图在于覆盖不排他的包含。例如包含了一系列步骤或单元的过程、方法、***、产品或设备没有限定于已列出 的步骤或单元，而是可选地还包括没有列出的步骤或单元，或可选地还包括对于这些过程、方法、产品或设备固有的其它步骤或单元。
本发明实施例公开一种基于共享SLAM地图的高精度定位方法及***，能够通过网络获取到共享SLAM地图，以使当前车辆可以在共享SLAM地图中确定与该传感器位姿对应的唯一的定位信息，从而提高了车辆定位功能的准确率。以下分别进行详细说明。
实施例一
请参阅图1，图1是本发明实施例公开的一种基于共享SLAM地图的高精度定位方法的流程示意图。如图1所示，该基于共享SLAM地图的高精度定位方法可以包括以下步骤：
101、车载电子设备通过网络获取当前车辆所处地理位置的共享SLAM地图。
本发明实施例中，当前车辆可以通过GPS采集当前车辆所处的地理位置，由于GPS定位的精确度较低，以及通过GPS无法实现在多层建筑中的跨层定位，因此，当前车辆需要获取该地理位置的SLAM地图，SLAM地图可以为视觉SLAM地图，也可以为激光SLAM地图，SLAM地图作为一种高精度地图可以实现精确度较高的定位，此外，SLAM地图中可以包含各个传感器获取的不同地点的环境信息，因此，SLAM地图中可以包含各个地理位置的空间信息，可以根据当前车辆的传感器采集到的当前车辆所处环境的空间信息在SLAM地图中确定唯一的定位信息，从而实现基于SLAM地图的车辆在多层建筑中精确的跨层定位。此外，车载电子设备可以是设置于当前车辆中的控制终端，当前车辆的车主可以通过车载电子设备实现对当前车辆的控制。
本发明实施例中，当前车辆中可以预先存储有SLAM地图，且对于当前车辆存储的SLAM地图的数量不做限定，如果当前车辆中存储有当前车辆所处地理位置对应的目标SLAM地图，则当前车辆可以直接使用该目标SLAM地图进行当前车辆的定位；如果当前车辆中未存储有当前车辆所处地理位置对应的目标SLAM地图，当前车辆可以通过网络(如互联网、局域网等)获取与该地理位置匹配的共享SLAM地图，进而根据获取到的共享SLAM地图进行定位。
本发明实施例中，当前车辆预先存储的SLAM地图的方式可以为：如果当前车辆行驶到的地理位置为初次行驶到的位置，且当前车辆也未能通过网络获取到对应的SLAM地图，则当前车辆可以通过车辆上的传感器(如视觉传感器或激光传感器等)采集到当前车辆周围的环境信息，进而可以根据传感器采集的环境信息构建SLAM地图，且该SLAM覆盖的区域面积大小可以是预设的面积大小，当前车辆可以将构建的SLAM地图与当前的地理位置进行关联，并存储至当前车辆中，以便于车辆再次经过该地理位置时可以直接获取到SLAM地图进行定位，即提高了车辆定位的准确性，还可以加快车辆定位的速度。
本发明实施例中，当前车辆通过网络获取到的共享SLAM地图可以为地图共享车辆构建SLAM地图之后，将该SLAM地图与地图共享车辆所在地理位置关联，并存储至服务器(如云服务器)上，以使其他车辆在行驶至该地理位置时可以通过网络从服务器上获取到与该地理位置匹配的共享SLAM地图，以避免当前车辆中未存储有该地理位置的SLAM地图而导致的定位不准确的情况。
本发明实施例中，由于地图共享车辆与当前车辆的车辆型号可能存在不同，因此，地图共享车辆上的传感器的外部参数与当前车辆的传感器的外部参数也可能存在不同，为了保证任意车辆都可以使用地图共享车辆共享的共享SLAM地图，在共享SLAM地图中可以存储有构建共享SLAM地图的地图共享车辆的车辆信息，该车辆信息中可以包含该地图共享车辆的型号、传感器的外部参数以及惯性测量单元(Inertial Measurement Unit，IMU)的参数等信息，对此，本发明实施例不做限定。
102、车载电子设备通过当前车辆的第一传感器采集得到第一传感器位姿，并在共享SLAM地图中确定与第一传感器位姿匹配的传感器定位信息。
本发明实施例中，第一传感器可以为设置在当前车辆上的视觉传感器或者激光传感器，视觉传感 器可以为设置在当前车辆上的摄像头或相机等传感器。第一传感器可以设置在当前车辆的前方或当前车辆的顶部。当前车辆在行驶的过程中可以通过第一传感器时刻采集传感器的位姿，即第一传感器位姿。当前车辆获取的第一传感器位姿可以在共享SLAM地图中找到相同的位姿，因此车载电子设备可以从共享SLAM地图中确定与第一传感器位姿匹配的目标位姿，进一步从共享SLAM地图中确定该目标位姿对应的位置信息，从而将该目标位姿对应的位置信息确定为传感器定位信息。
103、车载电子设备获取第一传感器的外部参数，并从共享SLAM地图中读取地图共享车辆的第二传感器的外部参数，共享SLAM地图由地图共享车辆构建。
本发明实施例中，当前车辆的第一传感器在最初行驶之前可以确定该第一传感器基于当前车辆的第一传感器相对于车辆车身的外部参数。车载电子设备可以从共享SLAM地图中获取构建该共享SLAM地图的地图共享车辆的车辆信息，可以从车辆信息中确定地图共享车辆的传感器的共享外部参数。
104、车载电子设备根据传感器定位信息、第一传感器的外部参数以及第二传感器的外部参数确定当前车辆的车身定位信息。
本发明实施例中，车载电子设备可以根据第一传感器的外部参数和共享传感器的外部参数计算得到从第一传感器的外部参数转换至共享传感器的共享外部参数的当前变换矩阵，进而使车载电子设备将传感器定位信息中的与第一传感器位姿相同的目标位姿通过当前变换矩阵变换至第二传感器位姿，该第二传感器位姿也为在共享SLAM地图中的位姿，车载电子设备可以共享SLAM地图中确定第二传感器位姿对应的位置信息，该第二传感器位姿对应的位置信息可以认为是当前车辆车身的车身定位信息。
在图1所描述的方法中，能够通过网络获取到共享SLAM地图，以使当前车辆可以在共享SLAM地图中确定与该传感器位姿对应的唯一的定位信息，从而提高了车辆定位功能的准确率。此外，实施图1所描述的方法，既提高了车辆定位的准确性，还可以加快车辆定位的速度。
实施例二
请参阅图2，图2是本发明实施例公开的另一种基于共享SLAM地图的高精度定位方法的流程示意图。与实施例一相比，本发明实施例增加了在共享SLAM地图中确定第一传感器位姿对应的传感器定位信息的方法，以及更加详细的说明了构建共享SLAM地图的地图共享车辆的第二传感器的外部参数的获取方式，既提高了基于共享SLAM地图定位的准确性，又准确的获取共享SLAM地图中的第二传感器的外部参数。如图2所示，该基于共享SLAM地图的高精度定位方法可以包括以下步骤：
201、车载电子设备通过网络获取当前车辆所处地理位置的共享SLAM地图。
202、车载电子设备通过当前车辆的第一传感器采集得到基于第一传感器的外部参数的第一传感器位姿。
本发明实施例中，当前车辆的第一传感器可以是视觉传感器或激光传感器。当前车辆的第一传感器可以记录第一传感器位姿，由于共享SLAM地图是通过第二传感器采集到的传感器位姿和车身里程计采集到的车身位姿共同构建的，因此，需要得到当前车辆的第一传感器相对于当前车辆的车身的外部参数，以使通过该第一传感器的外部参数可以确定第一传感器采集到的第一传感器位姿与当前车辆的车身的关系。该第一传感器的外部参数可以包含六个自由度，这六个自由度可以是基于第一传感器的第一传感器坐标系得到的，该第一传感器坐标系可以以第一传感器为坐标原点，当前车辆的前进方向为第一传感器坐标系的x轴，当前车辆的前进方向的左侧为第一传感器坐标系的y轴，与地平面垂直的方向为z方向，第一传感器坐标系还可以包括当前车辆的航向角α、翻滚角β和俯仰角γ，因此，x、y、z、α、β以及γ就为第一传感器的外部参数包含六个自由度。
203、车载电子设备在共享SLAM地图中确定与第一传感器位姿对应的目标位姿。
本发明实施例中，由于第一传感器位姿是由第一传感器采集得到的，且共享SLAM地图也是通过共 享车辆的传感器构建的，因此车载电子设备可以在共享SLAM地图中确定与第一传感器位姿对应的目标位姿。
204、车载电子设备生成包含目标位姿的传感器定位信息，该传感器定位信息与第一传感器匹配。
本发明实施例中，共享SLAM地图中的目标位姿可以对应地图共享车辆的目标定位信息，车载电子设备可以生成包含该目标定位信息的传感器定位信息。
本发明实施例中，实施上述的步骤202～步骤204，可以从共享SLAM地图中确定与第一传感器位姿对应的目标位姿，并从共享SLAM地图中确定该目标位姿对应的地理位置，该地理位置可以确定为第一传感器位姿在共享SLAM地图中的位姿，从而可以将第一传感器当前采集到的位姿与共享SLAM地图进行联系，以使车载电子设备可以从共享SLAM地图中确定第一传感器位姿的位置。
205、车载电子设备获取当前车辆的当前车辆信息，并读取当前车辆信息中的第一传感器的外部参数。
本发明实施例中，当前车辆的当前车辆信息可以包含车辆的各种参数信息，如车辆的型号、车辆上设置的设备的信息等，因此当前车辆信息中可以包含当前车辆上设置的第一传感器的外部参数。
206、车载电子设备获取共享SLAM地图中包含的构建共享SLAM地图的地图共享车辆的地图共享车辆信息。
本发明实施例中，地图共享车辆在构建共享SLAM地图时，通常需要根据地图共享车辆的第二传感器设置用于构建共享SLAM地图的坐标系，由于共享SLAM地图是根据第二传感器采集到的图像构建的，且第二传感器可以在第二传感器的外部参数建立的第二坐标系下采集图像，因此可以认为构建共享SLAM地图的图像是基于第二传感器的第二坐标系得到的。
207、车载电子设备从地图共享车辆信息中读取地图共享车辆的第二传感器的外部参数。
本发明实施例中，实施上述的步骤205～步骤207，由于共享SLAM地图是由地图共享车辆构建的，且不同的车辆之间的视觉传感器的外部参数可能不同，因此，地图共享车辆在可以在构建共享SLAM地图时将地图共享车辆的第二传感器的外部参数添加至共享SLAM地图的地图共享车辆信息中，以使使用该共享SLAM地图的车辆可以从地图共享车辆信息中获取到地图共享车辆的第二传感器的外部参数，进而根据第二传感器的外部参数将当前车辆获取的第一传感器的传感器位姿准确的转换至共享SLAM地图中，以提高基于共享SLAM地图定位的准确性。
208、车载电子设备根据传感器定位信息、第一传感器的外部参数以及第二传感器的外部参数确定当前车辆的车身定位信息。
在图2所描述的方法中，能够通过网络获取到共享SLAM地图，以使当前车辆可以在共享SLAM地图中确定与该传感器位姿对应的唯一的定位信息，从而提高了车辆定位功能的准确率。此外，实施图2所描述的方法，可以从共享SLAM地图中确定第一传感器位姿的位置。此外，实施图2所描述的方法，可以提高基于共享SLAM地图定位的准确性。
实施例三
请参阅图3，图3是本发明实施例公开的另一种基于共享SLAM地图的高精度定位方法的流程示意图。与实施例一和实施例二相比，本发明实施例进一步说明了第一传感器位姿基于变换矩阵在共享SLAM地图中定位的方法，还丰富了获取共享SLAM地图的方式，既可以提高车辆定位的准确性，还可以准确的获取车辆当前需要的共享SLAM地图。如图3所示，该基于共享SLAM地图的高精度定位方法可以包括以下步骤：
301、车载电子设备通过当前车辆的定位模块采集当前车辆所处的地理位置。
本发明实施例中，当前车辆的定位模块中可以包含GPS定位装置，以使车载电子设备在未获取到 SLAM地图时可以根据GPS定位装置对当前车辆进行定位，获得当前车辆所处地理位置，该地理位置可以用GPS信息表示，从而使当前车辆在未获取到SLAM地图的情况下也能进行定位，保证了车辆定位的全面性。
302、车载电子设备确定地理位置对应的区域信息，该区域信息中包含地理位置。
本发明实施例中，车载电子设备可以预先划分若干个区域，并且可以预先确定各个区域的覆盖范围，其中车载电子设备可以设置各个区域包含的地理位置，从而根据各个区域的覆盖范围是从区域信息，以使车载电子设备可以确定与任意一个地理位置匹配的区域信息。此外，SLAM地图可以基于各个区域的覆盖范围来构建，以使车载电子设备可以获取到当前地理位置附近一定范围内的SLAM地图，保证了基于SLAM地图定位的全面。
303、车载电子设备检测当前车辆是否存储有与区域信息匹配的目标SLAM地图，如果是，结束本流程；如果否，执行步骤304～步骤314。
作为一种可选的实施方式，如果当前车辆存储有与区域信息匹配的目标SLAM地图，还可以执行以下步骤：
车载电子设备获取预先存储的目标SLAM地图；
车载电子设备通过当前车辆的第一传感器采集得到当前传感器位姿；
车载电子设备在目标SLAM地图中确定与当前传感器位姿匹配的当前定位信息。
其中，实施这种实施方式，可以直接获取车载电子设备预先存储的目标SLAM地图，以使车载电子设备可以根据第一传感器获取到的当前传感器位姿确定车辆在目标SLAM地图中的定位信息，从而简化了SLAM地图的获取过程，提高了车辆在SLAM地图中的定位速度。
本发明实施例中，实施上述的步骤301～步骤303，由于SLAM地图中可以包含一个区域内的道路、建筑物等内容，因此车辆可以根据获取的当前粗略的地理位置(如GPS定位信息)确定车辆所在区域，并获取该区域的SLAM地图，以使车辆可以根据该区域的SLAM地图进行精确的定位。
304、车载电子设备通过网络获取当前车辆所处地理位置的共享SLAM地图。
305、车载电子设备通过当前车辆的第一传感器采集得到基于第一传感器的外部参数的第一传感器位姿。
306、车载电子设备在共享SLAM地图中确定与第一传感器位姿对应的目标位姿。
307、车载电子设备生成包含目标位姿的传感器定位信息，传感器定位信息与第一传感器匹配。
308、车载电子设备获取当前车辆的当前车辆信息，并读取当前车辆信息中的第一传感器的外部参数。
309、车载电子设备获取共享SLAM地图中包含的构建共享SLAM地图的地图共享车辆的地图共享车辆信息。
310、车载电子设备从地图共享车辆信息中读取地图共享车辆的第二传感器的外部参数。
311、车载电子设备计算生成第一传感器的外部参数与第二传感器的外部参数之间的变换矩阵。
作为一种可选的实施方式，车载电子设备计算生成第一传感器的外部参数与第二传感器的外部参数之间的变换矩阵的方式可以包括以下步骤：
车载电子设备根据第一传感器的外部参数生成当前车辆的第一传感器与当前车辆的车身之间的第一转换矩阵，该第一转换矩阵用于将第一传感器采集到的在第一传感器坐标系下的第一传感器位姿转换至当前车辆的车身的第一车身坐标系下；
车载电子设备根据第二传感器的外部参数生成地图共享车辆的第二传感器与地图共享车辆的车身之间的第二转换矩阵，该第二转换矩阵用于将第二传感器采集到的在第二传感器坐标系下的第二传感 器位姿转换至地图共享车辆的车身的第二车身坐标系下；
车载电子设备将第一转换矩阵的逆矩阵与第二转换矩阵相乘，得到第一传感器的外部参数与第二传感器的外部参数之间的变换矩阵。
其中，实施这种实施方式，可以根据第一传感器的外部参数和第二传感器的外部参数分别生成第一转换矩阵和第二转换矩阵，并且通过将第一转换矩阵的逆矩阵与第二转换矩阵相乘，得到第一传感器的外部参数与第二传感器的外部参数之间的变换矩阵，以使当前车辆的第一传感器采集到的第一传感器位姿通过变换矩阵变换至地图共享车辆构建的共享SLAM地图中，提高了第一传感器位姿变换的准确性。
312、车载电子设备通过变换矩阵将传感器定位信息中的目标位姿变换为第二传感器位姿。
本发明实施例中，目标位姿可以认为是在共享SLAM地图中基于当前车辆的第一传感器的外部参数的位姿，目标位姿通过变换矩阵转换得到的第二传感器位姿可以认为是在共享SLAM地图中基于地图共享车辆的第二传感器的外部参数的位姿，即将当前车辆的第一传感器的外部参数转变成了构建共享SLAM地图的地图共享车辆的第二传感器的外部参数，因此第二传感器位姿对应的共享SLAM地图中的定位可以理解为是当前车辆的当前车身的定位信息。
313、车载电子设备在共享SLAM地图中确定与第二传感器位姿匹配的当前定位信息。
314、车载电子设备将当前定位信息确定为当前车辆的车身定位信息。
本发明实施例中，实施上述的步骤311～步骤314，可以以变换矩阵为依据，将基于第一传感器的外部参数的第一视觉传感器位姿变换为基于第二传感器的外部参数的第二视觉传感器位姿，以使基于第二传感器的外部参数的第二视觉传感器位姿可以准确的在共享SLAM地图中进行定位，提高定位的准确性。
在图3所描述的方法中，能够通过网络获取到共享SLAM地图，以使当前车辆可以在共享SLAM地图中确定与该传感器位姿对应的唯一的定位信息，从而提高了车辆定位功能的准确率。此外，实施图3所描述的方法，简化了SLAM地图的获取过程，提高了车辆在SLAM地图中的定位速度。此外，实施图3所描述的方法，使车辆可以根据该区域的SLAM地图进行精确的定位。此外，实施图3所描述的方法，提高了第一传感器位姿变换的准确性。此外，实施图3所描述的方法，提高定位的准确性。
实施例四
请参阅图4，图4是本发明实施例公开的一种基于共享SLAM地图的高精度定位***的结构示意图。如图4所示，该基于共享SLAM地图的高精度定位***可以包括：
获取单元401，用于通过网络获取当前车辆所处地理位置的共享SLAM地图。
第一采集单元402，用于通过当前车辆的第一传感器采集得到第一传感器位姿，并在共享SLAM地图中确定与第一传感器位姿匹配的传感器定位信息。
读取单元403，用于获取第一传感器的外部参数，并从获取单元401获取的共享SLAM地图中读取地图共享车辆的第二传感器的外部参数，共享SLAM地图由地图共享车辆构建。
第一确定单元404，用于根据第一采集单元402采集的传感器定位信息、读取单元403获取的第一传感器的外部参数以及第二传感器的外部参数确定当前车辆的车身定位信息。
可见，在图4所描述的***中，能够通过网络获取到共享SLAM地图，以使当前车辆可以在共享SLAM地图中确定与该传感器位姿对应的唯一的定位信息，从而提高了车辆定位功能的准确率。此外，在图4所描述的***中，即提高了车辆定位的准确性，还可以加快车辆定位的速度。
实施例五
请参阅图5，图5是本发明实施例公开的另一种基于共享SLAM地图的高精度定位***的结构示意 图。其中，图5所示的基于共享SLAM地图的高精度定位***是由图4所示的基于共享SLAM地图的高精度定位***进行优化得到的。与图4所示的基于共享SLAM地图的高精度定位***相比，图5所示的基于共享SLAM地图的高精度定位***在共享SLAM地图中确定第一传感器位姿对应的传感器定位信息的方法，以及更加详细的说明了构建共享SLAM地图的地图共享车辆的第二传感器的外部参数的获取方式，既提高了基于共享SLAM地图定位的准确性，又准确的获取共享SLAM地图中的第二传感器的外部参数，图5所示的基于共享SLAM地图的高精度定位***中第一采集单元402可以包括：
采集子单元4021，用于通过当前车辆的第一传感器采集得到基于第一传感器的外部参数的第一传感器位姿。
第一确定子单元4022，用于在共享SLAM地图中确定与采集子单元4021采集的第一传感器位姿对应的目标位姿。
生成子单元4023，用于生成包含第一确定子单元4022确定的目标位姿的传感器定位信息，该传感器定位信息与第一传感器匹配。
本发明实施例中，可以从共享SLAM地图中确定与第一传感器位姿对应的目标位姿，并从共享SLAM地图中确定该目标位姿对应的地理位置，该地理位置可以确定为第一传感器位姿在共享SLAM地图中的位姿，从而可以将第一传感器当前采集到的位姿与共享SLAM地图进行联系，以使车载电子设备可以从共享SLAM地图中确定第一传感器位姿的位置。
作为一种可选的实施方式，图5所示的基于共享SLAM地图的高精度定位***的读取单元403可以包括：
第一获取子单元4031，用于获取当前车辆的当前车辆信息，并读取当前车辆信息中的第一传感器的外部参数；
第二获取子单元4032，用于获取共享SLAM地图中包含的构建共享SLAM地图的地图共享车辆的地图共享车辆信息；
本发明实施例中，具体的，在第一获取子单元4031读取当前车辆信息中的第一传感器的外部参数之后，触发第二获取子单元4032启动。
读取子单元4033，用于从第二获取子单元4032获取的地图共享车辆信息中读取地图共享车辆的第二传感器的外部参数。
其中，实施这种实施方式，由于共享SLAM地图是由地图共享车辆构建的，且不同的车辆之间的视觉传感器的外部参数可能不同，因此，地图共享车辆在可以在构建共享SLAM地图时将地图共享车辆的第二传感器的外部参数添加至共享SLAM地图的地图共享车辆信息中，以使使用该共享SLAM地图的车辆可以从地图共享车辆信息中获取到地图共享车辆的第二传感器的外部参数，进而根据第二传感器的外部参数将当前车辆获取的第一传感器的传感器位姿准确的转换至共享SLAM地图中，以提高基于共享SLAM地图定位的准确性。
可见，在图5所描述的***中，能够通过网络获取到共享SLAM地图，以使当前车辆可以在共享SLAM地图中确定与该传感器位姿对应的唯一的定位信息，从而提高了车辆定位功能的准确率。此外，在图5所描述的***中，可以从共享SLAM地图中确定第一传感器位姿的位置。此外，在图5所描述的***中，可以提高基于共享SLAM地图定位的准确性。
实施例六
请参阅图6，图6是本发明实施例公开的另一种基于共享SLAM地图的高精度定位***的结构示意图。其中，图6所示的基于共享SLAM地图的高精度定位***是由图5所示的基于共享SLAM地图的高精度定位***进行优化得到的。与图5所示的基于共享SLAM地图的高精度定位***相比，图6所示的 基于共享SLAM地图的高精度定位***进一步说明了第一传感器位姿基于变换矩阵在共享SLAM地图中定位的方法，还丰富了获取共享SLAM地图的方式，既可以提高车辆定位的准确性，还可以准确的获取车辆当前需要的共享SLAM地图，图6所示的基于共享SLAM地图的高精度定位***的第一确定单元404可以包括：
计算子单元4041，用于计算生成第一传感器的外部参数与第二传感器的外部参数之间的变换矩阵。
变换子单元4042，用于通过计算子单元4041得到的变换矩阵将传感器定位信息中的目标位姿变换为第二传感器位姿。
第二确定子单元4043，用于在共享SLAM地图中确定与变换子单元4042确定的第二传感器位姿匹配的当前定位信息。
第三确定子单元4044，用于将第二确定子单元4043确定的当前定位信息确定为当前车辆的车身定位信息。
其中，实施这种实施方式，可以以变换矩阵为依据，将基于第一传感器的外部参数的第一视觉传感器位姿变换为基于第二传感器的外部参数的第二视觉传感器位姿，以使基于第二传感器的外部参数的第二视觉传感器位姿可以准确的在共享SLAM地图中进行定位，提高定位的准确性。
作为一种可选的实施方式，计算子单元4041计算生成第一传感器的外部参数与第二传感器的外部参数之间的变换矩阵的方式具体可以为：
根据第一传感器的外部参数生成当前车辆的第一传感器与当前车辆的车身之间的第一转换矩阵，该第一转换矩阵用于将第一传感器采集到的在第一传感器坐标系下的第一传感器位姿转换至当前车辆的车身的第一车身坐标系下；
根据第二传感器的外部参数生成地图共享车辆的第二传感器与地图共享车辆的车身之间的第二转换矩阵，该第二转换矩阵用于将第二传感器采集到的在第二传感器坐标系下的第二传感器位姿转换至地图共享车辆的车身的第二车身坐标系下；
将第一转换矩阵的逆矩阵与第二转换矩阵相乘，得到第一传感器的外部参数与第二传感器的外部参数之间的变换矩阵。
其中，实施这种实施方式，可以根据第一传感器的外部参数和第二传感器的外部参数分别生成第一转换矩阵和第二转换矩阵，并且通过将第一转换矩阵的逆矩阵与第二转换矩阵相乘，得到第一传感器的外部参数与第二传感器的外部参数之间的变换矩阵，以使当前车辆的第一传感器采集到的第一传感器位姿通过变换矩阵变换至地图共享车辆构建的共享SLAM地图中，提高了第一传感器位姿变换的准确性。
作为一种可选的实施方式，图5所示的基于共享SLAM地图的高精度定位***还可以包括：
第二采集单元405，用于通过当前车辆的定位模块采集当前车辆所处的地理位置；
第二确定单元406，用于确定第二采集单元405采集的地理位置对应的区域信息，该区域信息中包含地理位置；
检测单元407，用于检测当前车辆是否存储有与第二确定单元406确定的区域信息匹配的目标SLAM地图；
获取单元401，用于在检测单元407的检测结果为否时，通过网络获取当前车辆所处地理位置的共享SLAM地图。
其中，实施这种实施方式，由于SLAM地图中可以包含一个区域内的道路、建筑物等内容，因此车辆可以根据获取的当前粗略的地理位置(如GPS定位信息)确定车辆所在区域，并获取该区域的SLAM地图，以使车辆可以根据该区域的SLAM地图进行精确的定位。
作为一种可选的实施方式，检测单元407还可以用于：
当检测出当前车辆存储有与区域信息匹配的目标SLAM地图时，获取预先存储的目标SLAM地图；
通过当前车辆的第一传感器采集得到当前传感器位姿；
在目标SLAM地图中确定与当前传感器位姿匹配的当前定位信息。
其中，实施这种实施方式，可以直接获取车载电子设备预先存储的目标SLAM地图，以使车载电子设备可以根据第一传感器获取到的当前传感器位姿确定车辆在目标SLAM地图中的定位信息，从而简化了SLAM地图的获取过程，提高了车辆在SLAM地图中的定位速度。
可见，在图6所描述的***中，能够通过网络获取到共享SLAM地图，以使当前车辆可以在共享SLAM地图中确定与该传感器位姿对应的唯一的定位信息，从而提高了车辆定位功能的准确率。此外，在图6所描述的***中，简化了SLAM地图的获取过程，提高了车辆在SLAM地图中的定位速度。此外，在图6所描述的***中，使车辆可以根据该区域的SLAM地图进行精确的定位。此外，在图6所描述的***中，提高了第一传感器位姿变换的准确性。此外，在图6所描述的***中，可以提高定位的准确性。
实施例七
请参阅图7，图7是本发明实施例公开的一种车载电子设备的结构示意图。如图7所示，该车载电子设备可以包括：
存储有可执行程序代码的存储器701；
与存储器701耦合的处理器702；
其中，处理器702调用存储器701中存储的可执行程序代码，执行以上各方法实施例中的方法的部分或全部步骤。
本发明实施例还公开一种计算机可读存储介质，其中，计算机可读存储介质存储了程序代码，其中，程序代码包括用于执行以上各方法实施例中的方法的部分或全部步骤的指令。
本发明实施例还公开一种计算机程序产品，其中，当计算机程序产品在计算机上运行时，使得计算机执行如以上各方法实施例中的方法的部分或全部步骤。
本发明实施例还公开一种应用发布平台，其中，应用发布平台用于发布计算机程序产品，其中，当计算机程序产品在计算机上运行时，使得计算机执行如以上各方法实施例中的方法的部分或全部步骤。
应理解，说明书通篇中提到的“本发明实施例”意味着与实施例有关的特定特征、结构或特性包括在本发明的至少一个实施例中。因此，在整个说明书各处出现的“在本发明实施例中”未必一定指相同的实施例。此外，这些特定特征、结构或特性可以以任意适合的方式结合在一个或多个实施例中。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可选实施例，所涉及的动作和模块并不一定是本发明所必须的。
在本发明的各种实施例中，应理解，上述各过程的序号的大小并不意味着执行顺序的必然先后，各过程的执行顺序应以其功能和内在逻辑确定，而不应对本发明实施例的实施过程构成任何限定。
另外，本文中术语“***”和“网络”在本文中常可互换使用。应理解，本文中术语“和/或”，仅仅是一种描述关联对象的关联关系，表示可以存在三种关系，例如A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B这三种情况。另外，本文中字符“/”，一般表示前后关联对象是一种“或”的关系。
在本发明所提供的实施例中，应理解，“与A对应的B”表示B与A相关联，根据A可以确定B。但还应理解，根据A确定B并不意味着仅仅根据A确定B，还可以根据A和/或其他信息确定B。
本领域普通技术人员可以理解上述实施例的各种方法中的全部或部分步骤是可以通过程序来指令相关的硬件来完成，该程序可以存储于一计算机可读存储介质中，存储介质包括只读存储器(Read-Only Memory，ROM)、随机存储器(Random Access Memory，RAM)、可编程只读存储器(Programmable Read-only Memory，PROM)、可擦除可编程只读存储器(Erasable Programmable Read Only Memory，EPROM)、一次可编程只读存储器(One-time Programmable Read-Only Memory，OTPROM)、电子抹除式可复写只读存储器(Electrically-Erasable Programmable Read-Only Memory，EEPROM)、只读光盘(Compact Disc Read-Only Memory，CD-ROM)或其他光盘存储器、磁盘存储器、磁带存储器、或者能够用于携带或存储数据的计算机可读的任何其他介质。
上述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可位于一个地方，或者也可以分布到多个网络单元上。可根据实际的需要选择其中的部分或全部单元来实现本实施例方案的目的。
另外，在本发明各实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。
上述集成的单元若以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可获取的存储器中。基于这样的理解，本发明的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或者部分，可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储器中，包括若干请求用以使得一台计算机设备(可以为个人计算机、服务器或者网络设备等，具体可以是计算机设备中的处理器)执行本发明的各个实施例上述方法的部分或全部步骤。
以上对本发明实施例公开的一种基于共享SLAM地图的高精度定位方法及***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. 一种基于共享SLAM地图的高精度定位方法，其特征在于，所述方法包括：
    通过网络获取当前车辆所处地理位置的所述共享SLAM地图；
    通过所述当前车辆的第一传感器采集得到第一传感器位姿，并在所述共享SLAM地图中确定与所述第一传感器位姿匹配的传感器定位信息；
    获取所述第一传感器的外部参数，并从所述共享SLAM地图中读取地图共享车辆的第二传感器的外部参数，所述共享SLAM地图由所述地图共享车辆构建；
    根据所述传感器定位信息、所述第一传感器的外部参数以及所述第二传感器的外部参数确定所述当前车辆的车身定位信息。
  2. 根据权利要求1所述的方法，其特征在于，所述通过所述当前车辆的第一传感器采集得到第一传感器位姿，并在所述共享SLAM地图中确定与所述第一传感器位姿匹配的传感器定位信息，包括：
    通过所述当前车辆的第一传感器采集得到基于所述第一传感器的外部参数的第一传感器位姿；
    在所述共享SLAM地图中确定与所述第一传感器位姿对应的目标位姿；
    生成包含所述目标位姿的传感器定位信息，所述传感器定位信息与所述第一传感器匹配。
  3. 根据权利要求2所述的方法，其特征在于，所述获取所述第一传感器的外部参数，并从所述共享SLAM地图中读取地图共享车辆的第二传感器的外部参数，包括：
    获取所述当前车辆的当前车辆信息，并读取所述当前车辆信息中的所述第一传感器的外部参数；
    获取所述共享SLAM地图中包含的构建所述共享SLAM地图的地图共享车辆的地图共享车辆信息；
    从所述地图共享车辆信息中读取所述地图共享车辆的第二传感器的外部参数。
  4. 根据权利要求3所述的方法，其特征在于，所述根据所述传感器定位信息、所述第一传感器的外部参数以及所述第二传感器的外部参数确定所述当前车辆的车身定位信息，包括：
    计算生成所述第一传感器的外部参数与所述第二传感器的外部参数之间的变换矩阵；
    通过所述变换矩阵将所述传感器定位信息中的所述目标位姿变换为第二传感器位姿；
    在所述共享SLAM地图中确定与所述第二传感器位姿匹配的当前定位信息；
    将所述当前定位信息确定为所述当前车辆的车身定位信息。
  5. 根据权利要求1～4任一项所述的方法，其特征在于，所述方法还包括：
    通过当前车辆的定位模块采集所述当前车辆所处的地理位置；
    确定所述地理位置对应的区域信息，所述区域信息中包含所述地理位置；
    检测所述当前车辆是否存储有与所述区域信息匹配的目标SLAM地图；
    如果否，执行所述的通过网络获取当前车辆所处地理位置的所述共享SLAM地图。
  6. 一种基于共享SLAM地图的高精度定位***，其特征在于，包括：
    获取单元，用于通过网络获取当前车辆所处地理位置的所述共享SLAM地图；
    第一采集单元，用于通过所述当前车辆的第一传感器采集得到第一传感器位姿，并在所述共享SLAM地图中确定与所述第一传感器位姿匹配的传感器定位信息；
    读取单元，用于获取所述第一传感器的外部参数，并从所述共享SLAM地图中读取地图共享车辆的第二传感器的外部参数，所述共享SLAM地图由所述地图共享车辆构建；
    第一确定单元，用于根据所述传感器定位信息、所述第一传感器的外部参数以及所述第二传感器的外部参数确定所述当前车辆的车身定位信息。
  7. 根据权利要求6所述的***，其特征在于，所述第一采集单元包括：
    采集子单元，用于通过所述当前车辆的第一传感器采集得到基于所述第一传感器的外部参数的第一传感器位姿；
    第一确定子单元，用于在所述共享SLAM地图中确定与所述第一传感器位姿对应的目标位姿；
    生成子单元，用于生成包含所述目标位姿的传感器定位信息，所述传感器定位信息与所述第一传感器匹配。
  8. 根据权利要求7所述的***，其特征在于，所述读取单元包括：
    第一获取子单元，用于获取所述当前车辆的当前车辆信息，并读取所述当前车辆信息中的所述第一传感器的外部参数；
    第二获取子单元，用于获取所述共享SLAM地图中包含的构建所述共享SLAM地图的地图共享车辆的地图共享车辆信息；
    读取子单元，用于从所述地图共享车辆信息中读取所述地图共享车辆的第二传感器的外部参数。
  9. 根据权利要求7或8所述的***，其特征在于，所述第一确定单元包括：
    计算子单元，用于计算生成所述第一传感器的外部参数与所述第二传感器的外部参数之间的变换矩阵；
    变换子单元，用于通过所述变换矩阵将所述传感器定位信息中的所述目标位姿变换为第二传感器位姿；
    第二确定子单元，用于在所述共享SLAM地图中确定与所述第二传感器位姿匹配的当前定位信息；
    第三确定子单元，用于将所述当前定位信息确定为所述当前车辆的车身定位信息。
  10. 根据权利要求9所述的***，其特征在于，所述***还包括：
    第二采集单元，用于通过当前车辆的定位模块采集所述当前车辆所处的地理位置；
    第二确定单元，用于确定所述地理位置对应的区域信息，所述区域信息中包含所述地理位置；
    检测单元，用于检测所述当前车辆是否存储有与所述区域信息匹配的目标SLAM地图；
    所述获取单元，具体用于在所述检测单元的检测结果为否时，通过网络获取当前车辆所处地理位置的所述共享SLAM地图。
PCT/CN2019/093533 2019-02-18 2019-06-28 基于共享slam地图的高精度定位方法及*** WO2020168667A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
EP19916277.7A EP3885866A4 (en) 2019-02-18 2019-06-28 HIGH ACCURACY LOCALIZATION METHOD AND SYSTEM BASED ON COMMON SLAM MAP

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910119444.X 2019-02-18
CN201910119444.XA CN109857111B (zh) 2019-02-18 2019-02-18 基于共享slam地图的高精度定位方法及***

Publications (1)

Publication Number Publication Date
WO2020168667A1 true WO2020168667A1 (zh) 2020-08-27

Family

ID=66898080

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/093533 WO2020168667A1 (zh) 2019-02-18 2019-06-28 基于共享slam地图的高精度定位方法及***

Country Status (3)

Country Link
EP (1) EP3885866A4 (zh)
CN (1) CN109857111B (zh)
WO (1) WO2020168667A1 (zh)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113218385A (zh) * 2021-05-24 2021-08-06 周口师范学院 基于slam的高精度车辆定位方法
CN113256731A (zh) * 2021-04-01 2021-08-13 深圳市宁创云软件技术有限公司 基于单目视觉的目标检测方法及装置
CN114360093A (zh) * 2021-12-31 2022-04-15 江苏鸣实纯钧科技有限公司 基于北斗rtk、slam定位和图像分析的路侧停车位巡检方法
US11568649B2 (en) 2021-01-15 2023-01-31 Continental Automotive Systems, Inc. Landmark-less simultaneous localization and mapping

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109857111B (zh) * 2019-02-18 2020-11-13 广州小鹏汽车科技有限公司 基于共享slam地图的高精度定位方法及***
CN110262516A (zh) * 2019-07-17 2019-09-20 深圳市英博超算科技有限公司 具有自动驾驶功能的车辆、方法以及装置
CN110446164B (zh) * 2019-07-23 2021-05-04 达闼机器人有限公司 移动终端定位方法、装置、移动终端和服务器
CN110517531B (zh) * 2019-09-05 2021-08-17 武汉中海庭数据技术有限公司 一种基于高精度地图数据的多层停车场定位方法
CN111738281B (zh) * 2020-08-05 2020-12-22 鹏城实验室 同时定位与建图***及其地图软切换方法、存储介质
CN115587151A (zh) * 2021-07-05 2023-01-10 灵动科技（北京）有限公司 用于车辆的使用共享slam地图的方法和装置

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103674011A (zh) * 2012-09-19 2014-03-26 联想(北京)有限公司 即时定位与地图构建设备、***与方法
US20150312774A1 (en) * 2014-04-25 2015-10-29 The Hong Kong University Of Science And Technology Autonomous robot-assisted indoor wireless coverage characterization platform
CN106931963A (zh) * 2017-04-13 2017-07-07 高域（北京）智能科技研究院有限公司 环境数据共享平台、无人飞行器、定位方法和定位***
CN107223269A (zh) * 2016-12-29 2017-09-29 深圳前海达闼云端智能科技有限公司 三维场景定位方法和装置
CN107818592A (zh) * 2017-11-24 2018-03-20 北京华捷艾米科技有限公司 协作式同步定位与地图构建的方法、***及交互***
CN109857111A (zh) * 2019-02-18 2019-06-07 广州小鹏汽车科技有限公司 基于共享slam地图的高精度定位方法及***

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101639360B (zh) * 2009-08-21 2012-03-07 肖湘萍 导航平台和导航***
US9478029B2 (en) * 2014-10-23 2016-10-25 Qualcomm Incorporated Selection strategy for exchanging map information in collaborative multi-user SLAM systems
KR101965296B1 (ko) * 2016-11-30 2019-04-19 연세대학교 산학협력단 파티클 간에 지도를 공유하는 이동체의 위치 추정 및 지도 작성 방법 및 장치
US10816346B2 (en) * 2016-12-30 2020-10-27 DeepMap Inc. Occupancy map updates based on sensor data collected by autonomous vehicles
CN107246868B (zh) * 2017-07-26 2021-11-02 上海舵敏智能科技有限公司 一种协同导航定位***及导航定位方法
CN108759844B (zh) * 2018-06-07 2021-11-16 科沃斯商用机器人有限公司 机器人重定位与环境地图构建方法、机器人及存储介质
CN109059941B (zh) * 2018-07-06 2019-11-29 禾多科技（北京）有限公司 特征地图构建方法、视觉定位方法及对应装置

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103674011A (zh) * 2012-09-19 2014-03-26 联想(北京)有限公司 即时定位与地图构建设备、***与方法
US20150312774A1 (en) * 2014-04-25 2015-10-29 The Hong Kong University Of Science And Technology Autonomous robot-assisted indoor wireless coverage characterization platform
CN107223269A (zh) * 2016-12-29 2017-09-29 深圳前海达闼云端智能科技有限公司 三维场景定位方法和装置
CN106931963A (zh) * 2017-04-13 2017-07-07 高域（北京）智能科技研究院有限公司 环境数据共享平台、无人飞行器、定位方法和定位***
CN107818592A (zh) * 2017-11-24 2018-03-20 北京华捷艾米科技有限公司 协作式同步定位与地图构建的方法、***及交互***
CN109857111A (zh) * 2019-02-18 2019-06-07 广州小鹏汽车科技有限公司 基于共享slam地图的高精度定位方法及***

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3885866A4 *

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11568649B2 (en) 2021-01-15 2023-01-31 Continental Automotive Systems, Inc. Landmark-less simultaneous localization and mapping
CN113256731A (zh) * 2021-04-01 2021-08-13 深圳市宁创云软件技术有限公司 基于单目视觉的目标检测方法及装置
CN113218385A (zh) * 2021-05-24 2021-08-06 周口师范学院 基于slam的高精度车辆定位方法
CN114360093A (zh) * 2021-12-31 2022-04-15 江苏鸣实纯钧科技有限公司 基于北斗rtk、slam定位和图像分析的路侧停车位巡检方法
CN114360093B (zh) * 2021-12-31 2024-03-08 江苏鸣实纯钧科技有限公司 基于北斗rtk、slam定位和图像分析的路侧停车位巡检方法

Also Published As

Publication number Publication date
EP3885866A4 (en) 2022-01-26
EP3885866A1 (en) 2021-09-29
CN109857111B (zh) 2020-11-13
CN109857111A (zh) 2019-06-07

Similar Documents

Publication Publication Date Title
WO2020168667A1 (zh) 基于共享slam地图的高精度定位方法及***
CN109540148B (zh) 基于slam地图的定位方法及***
CN109931944B (zh) 一种ar导航方法、装置、车端设备、服务端及介质
JP6656886B2 (ja) 情報処理装置、制御方法、プログラム及び記憶媒体
CN105676251A (zh) 车辆乘客识别
CN109425343A (zh) 本车位置推断装置
JP6950832B2 (ja) 位置座標推定装置、位置座標推定方法およびプログラム
JP6033689B2 (ja) クルーズコントロール装置及びその方法、並びに車両特定装置
WO2020082777A1 (zh) 车位检测方法及装置
CN110388925A (zh) 用于与自动导航有关的车辆定位的***和方法
JP2021524026A (ja) 姿勢判断システムおよび方法
CN110531771B (zh) 一种速度规划方法及装置、车辆
CN110119138A (zh) 用于自动驾驶车辆的自定位方法、***和机器可读介质
CN109213144A (zh) 人机接口（hmi）架构
CN110579211A (zh) 一种步行定位方法及***
KR102217422B1 (ko) 운전면허시험 처리 장치
CN111982133B (zh) 基于高精地图对车辆进行定位的方法、装置及电子设备
JP6610466B2 (ja) 車両制御システム
JP7044537B2 (ja) 自動走行制御システム、合成データ生成方法、プログラム
WO2020042347A1 (zh) 一种应用于自动驾驶的实时定位方法及装置
CN111351497B (zh) 一种车辆的定位方法、装置、地图的构建方法和装置
CN109115233B (zh) 无目的地导航方法、装置、***和计算机可读介质
US11846523B2 (en) Method and system for creating a localization map for a vehicle
WO2021024665A1 (ja) 情報処理システム、情報処理装置及び情報処理方法
JP2020073931A (ja) 情報処理装置、制御方法、プログラム及び記憶媒体

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: 19916277

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 19916277.7

Country of ref document: EP

ENP Entry into the national phase

Ref document number: 2019916277

Country of ref document: EP

Effective date: 20210625

NENP Non-entry into the national phase

Ref country code: DE