WO2020216342A1 - 一种位姿数据处理方法和系统 - Google Patents

一种位姿数据处理方法和系统 Download PDF

Info

Publication number
WO2020216342A1
WO2020216342A1 PCT/CN2020/086784 CN2020086784W WO2020216342A1 WO 2020216342 A1 WO2020216342 A1 WO 2020216342A1 CN 2020086784 W CN2020086784 W CN 2020086784W WO 2020216342 A1 WO2020216342 A1 WO 2020216342A1
Authority
WO
WIPO (PCT)
Prior art keywords
pose
data
positioning
matrix
edge
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2020/086784
Other languages
English (en)
French (fr)
Inventor
杨晟
马腾
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Didi Infinity Technology and Development Co Ltd
Original Assignee
Beijing Didi Infinity Technology and Development Co Ltd
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 Beijing Didi Infinity Technology and Development Co Ltd filed Critical Beijing Didi Infinity Technology and Development Co Ltd
Publication of WO2020216342A1 publication Critical patent/WO2020216342A1/zh
Priority to US17/451,838 priority Critical patent/US20220044436A1/en
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—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
    • G01C21/30—Map- or contour-matching
    • G01C21/32—Structuring or formatting of map data
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/29—Geographical information databases
    • 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
    • G01C21/10—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration
    • G01C21/12—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning
    • G01C21/16—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation
    • 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
    • G01C21/10—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration
    • G01C21/12—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning
    • G01C21/16—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation
    • G01C21/165—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation combined with non-inertial navigation instruments
    • 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
    • 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
    • G01S19/45—Determining position by combining measurements of signals from the satellite radio beacon positioning system with a supplementary measurement
    • 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
    • G01S19/45—Determining position by combining measurements of signals from the satellite radio beacon positioning system with a supplementary measurement
    • G01S19/47—Determining position by combining measurements of signals from the satellite radio beacon positioning system with a supplementary measurement the supplementary measurement being an inertial measurement, e.g. tightly coupled inertial
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/901—Indexing; Data structures therefor; Storage structures
    • G06F16/9024—Graphs; Linked lists
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2200/00—Indexing scheme for image data processing or generation, in general
    • G06T2200/04—Indexing scheme for image data processing or generation, in general involving 3D image data

Definitions

  • This application relates to the field of positioning technology, and in particular to a method and system for processing pose data.
  • the map generation equipment In the process of high-precision map collection, in addition to GPS (Global Position System), the map generation equipment is also equipped with visual sensors, laser sensors, and inertial sensors to receive the communication quality of GPS signals in the global positioning system When it is poor, repair and optimize to a certain extent.
  • the above-mentioned map generation device can maintain a certain period of positioning when the GPS signal quality is degraded or even lost through the extended Kalman filter algorithm.
  • the accumulation of uncertainty will result in a gradual positioning accuracy. Decline until it is lost, and the decline in positioning accuracy will significantly affect the quality of the high-precision map, and the point cloud will be globally inconsistent with accumulation.
  • the optimization method in the prior art does not distinguish the weight of each side in the pose graph, which will have a poor effect on eliminating accumulated errors. Therefore, it is necessary to provide a more accurate method and system for processing pose data to be able to optimize different ranges for each region.
  • One of the embodiments of the present application provides a method for processing pose data.
  • the method is applicable to a map generating device that is coupled with a global positioning system and a pose sensor system, the global positioning system is used to output positioning data, and the pose sensor system is used to output motion pose data.
  • the positioning data and the motion posture data are used to combine to generate pose estimation data, wherein the pose data processing method includes: in response to the generated positioning data, determining the positioning accuracy information corresponding to the positioning data; The positioning accuracy information determines the confidence of the pose estimation data; and according to the confidence of the pose estimation data, processing the pose estimation data to obtain optimized pose data.
  • the system is suitable for a map generating device, the map generating device is coupled with a global positioning system and a pose sensor system, the global positioning system is used to output positioning data, and the pose sensor system is used to output motion pose data, so
  • the positioning data and the motion posture data are used to combine to generate pose estimation data
  • the pose data processing system includes: at least one memory for storing computer instructions; at least one processor in communication with the memory, When the at least one processor executes the computer instruction, the at least one processor causes the system to execute: in response to the generated positioning data, determine the positioning accuracy information corresponding to the positioning data; and according to the positioning accuracy Information, determining the confidence of the pose estimation data; and according to the confidence of the pose estimation data, processing the pose estimation data to obtain optimized pose data.
  • the system is suitable for a map generating device, the map generating device is coupled with a global positioning system and a pose sensor system, the global positioning system is used to output positioning data, and the pose sensor system is used to output motion pose data, so
  • the positioning data and the motion posture data are used to combine to generate pose estimation data
  • the pose data processing system includes: a first determining module, which is configured to determine the position corresponding to the positioning data in response to the generated positioning data Positioning accuracy information; a second determining module for determining the confidence level of the pose estimation data according to the positioning accuracy information; and an optimization module for determining the position and attitude estimation data confidence level according to the
  • the pose estimation data is processed to obtain the optimized pose data.
  • One of the embodiments of the present application provides a method for processing pose data.
  • the method is applicable to a map generating device that is coupled with a global positioning system and a pose sensor system, the global positioning system is used to output positioning data, and the pose sensor system is used to output motion pose data.
  • the positioning data and the motion posture data are used to combine to generate pose estimation data, and the pose data processing method includes: in response to the generated positioning data, determining the positioning accuracy information corresponding to the positioning data; and according to the positioning accuracy The information determines the confidence level of the pose estimation data.
  • the determining the confidence of the pose estimation data according to the positioning accuracy information specifically includes: inputting the positioning accuracy information, the positioning data, and the motion posture data into a lossless Kalman filter To obtain the front-end mileage estimation data corresponding to the pose estimation data; divide the front-end mileage estimation data into temporal and spatial consistency to determine each group of point clouds, and construct the corresponding pose according to the respective groups of point clouds Figure, wherein the output result of the lossless Kalman filter includes the confidence level.
  • the dividing the front-end mileage estimation data into temporal and spatial consistency to obtain each group of point clouds, and constructing a corresponding pose map according to the respective groups of point clouds specifically includes: The mileage estimation data is divided according to preset time intervals to determine the first type of edge in the pose map; and the front-end mileage estimation data is divided according to the preset position interval to determine the second type of edge in the pose map Analyze the motion trajectory contained in the motion posture data, generate the groups of point clouds according to the continuity of the motion trajectories, and determine the first frame point cloud in the groups of point clouds as the position The vertex of the pose graph.
  • the method further includes: determining the inverse matrix of the covariance matrix of the output of the lossless Kalman filter, and recording it as the information matrix of the first type of edge; Perform registration processing on any two groups of point clouds in, to determine the inverse matrix of the covariance matrix generated during the registration processing, and record it as the information matrix of the second type of edge.
  • the method further includes: determining the information matrix of the first type edge according to preset hardware parameters of the map generating device and/or signal strength of the positioning data.
  • the method further includes: correcting the three-dimensional position of each group of point clouds in the pose image according to the information matrix of the first type of edge and the information matrix of the second type of edge .
  • the determining the information matrix of the first type edge according to the preset hardware parameters of the map generation device and/or the signal strength of the positioning data specifically includes: according to the map generation device The parameter dimension of the pose estimation data is determined by the preset hardware parameters and/or the signal strength of the positioning data; the preset weight corresponding to the parameter dimension is set to the value of the diagonal matrix, according to the diagonal The matrix determines the information matrix of the edge of the first type.
  • the parameter dimension includes at least one of the following: absolute position in the north direction, absolute position in the east direction, absolute position in the ground direction, roll angle, pitch angle, and yaw angle.
  • the pose sensor system includes at least one of the following: a vision sensor, a laser sensor, and an inertial sensor.
  • the global positioning system includes a positioning board and a satellite communication antenna.
  • One of the embodiments of the present application provides a pose data processing system.
  • the system is suitable for a map generating device, the map generating device is coupled with a global positioning system and a pose sensor system, the global positioning system is used to output positioning data, and the pose sensor system is used to output motion pose data, so
  • the positioning data and the motion posture data are used to combine to generate pose estimation data
  • the pose data processing system includes a processor, and the processor performs the following steps: in response to the generated positioning data, determining that the positioning data corresponds to The positioning accuracy information; the confidence of the pose estimation data is determined according to the positioning accuracy information.
  • the map generating device includes a memory, a controller, and a computer program stored on the memory and running on the controller, and the controller executes the The computer program implements the pose data processing method described in any one of the embodiments of the present application.
  • One of the embodiments of the present application provides a computer-readable storage medium that stores computer instructions. After the computer reads the computer instructions in the storage medium, the computer executes any one of the embodiments of the present application. The method described in the item.
  • Fig. 1 is a schematic diagram of an application scenario of a pose data processing system according to some embodiments of the present application
  • Figure 2 is a block diagram of a pose data processing system according to some embodiments of the present application.
  • Fig. 3 is an exemplary flowchart of a pose data processing method according to some embodiments of the present application.
  • FIG. 4 is an exemplary flowchart of a method for determining the confidence of pose estimation data according to some embodiments of the present application
  • Fig. 5 is a schematic block diagram of a map generating device according to some embodiments of the present application.
  • Fig. 6 is a schematic block diagram of a map generating device according to other embodiments of the present application.
  • FIG. 7 is a schematic diagram of the effect of optimization of pose estimation data according to other embodiments of the present application.
  • system is a method for distinguishing different components, elements, parts, parts, or assemblies of different levels.
  • the words can be replaced by other expressions.
  • a flowchart is used in this application to illustrate the operations performed by the system according to the embodiments of the application. It should be understood that the preceding or following operations are not necessarily performed exactly in order. Instead, the steps can be processed in reverse order or simultaneously. At the same time, other operations can be added to these processes, or a certain step or several operations can be removed from these processes.
  • the embodiments of the present application can be applied to different transportation systems, for example, taxis, special cars, ride-hailing cars, buses, agent driving, etc.
  • the "passenger”, “passenger terminal”, “passenger terminal”, “customer”, “demand”, “service demander”, “service requester”, “consumer”, “consumer”, “customer”, “customer”, “customer”, “Users who use demand” etc. are interchangeable and refer to the party who needs or subscribes to the service. It can be an individual or a tool.
  • the "driver”, “driver terminal”, “driver terminal”, “provider”, “supplier”, “service provider”, “server”, “service provider”, etc. described in this application can also be mutually exchanged. Exchange refers to individuals, tools or other entities that provide services or assist in providing services.
  • the "user” described in this application may be a party that needs or subscribes to services, or a party that provides services or assists in providing services.
  • Fig. 1 is an application scenario diagram of a pose data processing system 100 according to some embodiments of the present application.
  • the pose data processing system 100 may be an online platform for high-precision map collection.
  • the pose data processing system 100 may include a server 110, a network 120, a collection terminal 130, and a storage device 140.
  • the server 110 can be used to process information and/or data related to high-precision map collection.
  • the server 110 can process the data collected by the collection terminal 130, and optimize the pose map to improve the performance of the poor GPS signal area. positioning accuracy.
  • the server 110 may be a single server or a group of servers. The server group may be centralized or distributed (for example, the server 110 may be a distributed system).
  • the server 110 may be local or remote.
  • the server 110 may access the information and/or data stored in the collection terminal 130 and the storage device 140 through the network 120.
  • the server 110 may be directly connected to the collection terminal 130 and the storage device 140 to access the stored information and/or data.
  • the server 110 may be implemented on a cloud platform.
  • the cloud platform may include private cloud, public cloud, hybrid cloud, community cloud, distributed cloud, inter-cloud, multiple clouds, etc., or any combination of the foregoing examples.
  • the network 120 may facilitate the exchange of information and/or data.
  • one or more components in the pose data processing system 100 can be sent to/from other components in the pose data processing system 100 via the network 120 /Receive information and/or data.
  • the server 110 may receive collected data (such as positioning data or motion posture data) from the collection terminal 130 via the network 120.
  • the network 120 may be any form of wired or wireless network or any combination thereof.
  • the network 120 may include a cable network, a wired network, an optical fiber network, a telecommunication network, an internal network, the Internet, a local area network (LAN), a wide area network (WAN), a wireless local area network (WLAN), a metropolitan area network (MAN), Wide Area Network (WAN), Public Switched Telephone Network (PSTN), Bluetooth Network, Zigbee Network, Near Field Communication (NFC) Network, Global System for Mobile Communications (GSM) Network, Code Division Multiple Access (CDMA) Network, Time Division Multiple Access ( TDMA) network, general packet radio service (GPRS) network, enhanced data rate GSM evolution (EDGE) network, wideband code division multiple access (WCDMA) network, high-speed downlink packet access (HSDPA) network, long-term evolution (LTE) Network, user datagram protocol (UDP) network, transmission control protocol/Internet protocol (TCP/IP) network, short message service (SMS) network, wireless application protocol (WAP) network, ultra-wideband (UWB) network, infrared
  • the pose data processing system 100 may include one or more network access points.
  • the pose data processing system 100 may include wired or wireless network access points, such as base stations and/or wireless access points 120-1, 120-2, ..., one or more components of the pose data processing system 100 may pass It is connected to the network 120 to exchange data and/or information.
  • the collection terminal 130 may be a device for collecting data. In some embodiments, the collection terminal 130 may be used in a system for analyzing and processing collected data to generate analysis results. In some embodiments, the collection terminal 130 may include an autonomous driving vehicle 130-1, a robot 130-2, an autonomous driving wheelchair 130-3, etc. or any combination thereof. In some embodiments, the collection terminal 130 may be a device that has positioning technology and can perceive the surrounding environment, and is used to locate the location of the collection terminal 130 and detect surrounding obstacles. For example, the collection terminal 130 may include a GPS receiver, a lidar, an inertial sensor, a camera (for example, a monocular, binocular, or panoramic camera), etc. In some embodiments, the collection terminal 130 may send positioning information and surrounding environment information to the server 110.
  • the storage device 140 may store data and/or instructions related to high-precision map collection. In some embodiments, the storage device 140 may store data obtained/acquired from the collection terminal 130. In some embodiments, the storage device 140 may store data and/or instructions used by the server 110 to execute or use to complete the exemplary methods described in this application. In some embodiments, the storage device 140 may include mass memory, removable memory, volatile read-write memory, read-only memory (ROM), etc., or any combination thereof. Exemplary mass storage devices may include magnetic disks, optical disks, solid state disks, and the like. Exemplary removable storage may include flash drives, floppy disks, optical disks, memory cards, compact disks, magnetic tapes, and the like. An exemplary volatile read-only memory may include random access memory (RAM).
  • RAM random access memory
  • Exemplary RAMs may include dynamic RAM (DRAM), double rate synchronous dynamic RAM (DDR SDRAM), static RAM (SRAM), thyristor RAM (T-RAM), zero capacitance RAM (Z-RAM), and the like.
  • Exemplary ROMs may include mask ROM (MROM), programmable ROM (PROM), erasable programmable ROM (EPROM), electronically erasable programmable ROM (EEPROM), compact disk ROM (CD-ROM), and digital General disk ROM, etc.
  • the storage device 140 may be implemented on a cloud platform.
  • the cloud platform may include private cloud, public cloud, hybrid cloud, community cloud, distributed cloud, internal cloud, multi-layer cloud, etc., or any combination thereof.
  • the storage device 140 may be connected to the network 120 to communicate with one or more components in the pose data processing system 100 (for example, the server 110, the collection terminal 130).
  • One or more components in the pose data processing system 100 can access data or instructions stored in the storage device 140 through the network 120.
  • the storage device 140 may directly connect or communicate with one or more components (for example, the server 110, the collection terminal 130, etc.) in the pose data processing system 100.
  • the storage device 140 may be part of the server 110.
  • Fig. 2 is a block diagram of a pose data processing system according to some embodiments of the present application.
  • the pose data processing system 200 is suitable for map generation equipment.
  • the map generation device is coupled with a global positioning system and a pose sensor system.
  • the global positioning system is used to output positioning data
  • the pose sensor system is used to output motion pose data, positioning data and
  • the motion pose data is used in conjunction to generate pose estimation data.
  • FIG. 4 and FIG. 5 For more information about the map generating device, please refer to the description of FIG. 4 and FIG. 5, which will not be repeated here.
  • the system 200 may include a first determination module 210, a second determination module 220, and an optimization module 230.
  • the first determining module 210 may be configured to determine the positioning accuracy information corresponding to the positioning data in response to the generated positioning data. For more information about determining the positioning accuracy information corresponding to the positioning data, refer to the description of step 310, which is not repeated here.
  • the second determining module 220 may be used to determine the confidence of the pose estimation data according to the positioning accuracy information. For more details about determining the confidence level of the pose estimation data, refer to the description of step 320, which is not repeated here.
  • the optimization module 230 may be used to process the pose estimation data according to the confidence of the pose estimation data to obtain optimized pose data. For more details about the optimized pose data obtained by processing the pose estimation data, please refer to the description of step 330, which will not be repeated here.
  • system and its modules shown in FIG. 2 can be implemented in various ways.
  • the system and its modules may be implemented by hardware, software, or a combination of software and hardware.
  • the hardware part can be implemented using dedicated logic;
  • the software part can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or dedicated design hardware.
  • processor control codes for example on a carrier medium such as a disk, CD or DVD-ROM, such as a read-only memory (firmware Such codes are provided on a programmable memory or a data carrier such as an optical or electronic signal carrier.
  • the system and its modules of this application can not only be implemented by hardware circuits such as very large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, etc., or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc. It can also be implemented by software executed by various types of processors, or can be implemented by a combination of the aforementioned hardware circuit and software (for example, firmware).
  • the above description of the pose data processing system and its modules is only for convenience of description, and does not limit the present application within the scope of the embodiments mentioned. It can be understood that for those skilled in the art, after understanding the principle of the system, it is possible to arbitrarily combine various modules, or form a subsystem to connect with other modules without departing from this principle.
  • the first determining module 210, the second determining module 220, and the optimization module 230 disclosed in FIG. 2 may be different modules in one system, or one module may implement the above two or Functions of more than two modules.
  • the first determining module 210 and the second determining module 220 may be two modules, or one module may simultaneously have the functions of determining the positioning accuracy information corresponding to the positioning data and determining the confidence of the pose estimation data.
  • each module may share a storage module, and each module may also have its own storage module. Such deformations are all within the protection scope of this application.
  • Fig. 3 is an exemplary flowchart of a method for processing pose data according to some embodiments of the present application.
  • the pose data processing method can be applied to a map generating device.
  • the map generating device is provided with a global positioning system and a pose sensor system.
  • the global positioning system is used to output positioning data
  • the pose sensor system is used to output motion pose data.
  • the map generating device please refer to the description of FIG. 4 and FIG. 5, which will not be repeated here.
  • the positioning data and the motion posture data please refer to the description of step 310, which is not repeated here.
  • the pose data processing method may include:
  • Step 310 In response to the generated positioning data, determine positioning accuracy information corresponding to the positioning data. Specifically, step 310 may be performed by the first determining module 210.
  • the positioning data can include all data that can be used to locate the subject (such as the three-dimensional coordinate position generated by the global positioning system based on the communication signal of the positioning satellite, etc.), and the motion posture data can include all data related to motion or posture (such as motion trajectory, Speed, acceleration, etc.).
  • the pose estimation data may be determined by combining positioning data and motion pose data.
  • the pose estimation data may include six-dimensional parameters including absolute position in the north direction, absolute position in the east direction, absolute position in the ground direction, roll angle, pitch angle, and yaw angle.
  • the roll angle is the angle that the body of the map generating device rolls over to the horizontal line on the left and right sides.
  • the angle range of the roll angle is (-180°, 180°).
  • the pitch angle is based on the direction of the body of the map generating device and the horizontal direction.
  • the angle formed by the pitch angle is [-90°, 90°].
  • the yaw angle is the angle formed by the nose direction of the map generating device and the preset heading.
  • the angle range of the yaw angle is (- 180°, 180°].
  • the positioning accuracy information may include: PDOP (Positional Dilution of Precision, strength of position accuracy, that is, three-dimensional/spatial position accuracy information, such as factors such as longitude, latitude, and elevation), and HDOP (Horizontal Positional Dilution of Precision, level /The degree of accuracy of the plane position, such as factors such as longitude and latitude), VDOP (Vertical Positional Dilution of Precision, the degree of vertical position accuracy, such as the elevation factor).
  • PDOP Positional Dilution of Precision
  • strength of position accuracy that is, three-dimensional/spatial position accuracy information, such as factors such as longitude, latitude, and elevation
  • HDOP Horizontal Positional Dilution of Precision, level /The degree of accuracy of the plane position, such as factors such as longitude and latitude
  • VDOP Vertical Positional Dilution of Precision, the degree of vertical position accuracy, such as the elevation factor
  • the value of the above-mentioned accuracy strength (or known as the precision factor) is usually proportional to the positioning accuracy information, that is, the smaller the value of the accuracy strength, the smaller the error of the positioning data corresponding to the positioning accuracy information, indicating that the positioning is accurate The higher the degree.
  • the first determining module 210 may determine the positioning accuracy information corresponding to the positioning data in response to the generated positioning data.
  • Step 320 Determine the confidence level of the pose estimation data according to the positioning accuracy information. Specifically, step 320 may be performed by the second determining module 220.
  • the confidence of the pose estimation data can be used to characterize the reliability of the pose estimation data. The higher the confidence, the more reliable the pose estimation data, that is, the smaller the error of the pose estimation data.
  • the second determining module 220 may determine the confidence level of the pose estimation data according to the positioning accuracy information. Specifically, the second determining module 220 may input the positioning accuracy information, the positioning data, and the motion attitude data into the lossless Kalman filter, and may determine the front-end mileage estimation data and the covariance matrix corresponding to the pose estimation data.
  • the lossless Kalman filter is a combination of lossless transformation and the standard Kalman filter system. Through lossless transformation, the nonlinear system equation is suitable for the standard Kalman filter system under the linear assumption.
  • the front-end mileage estimation data may be the next segment of driving trajectory data estimated through a lossless Kalman filter, and the front-end mileage estimation data may be different from the actual driving trajectory.
  • the second determining module 220 may also divide the front-end mileage estimation data to determine each group of point clouds, and construct a corresponding pose map according to the respective groups of point clouds.
  • the pose graph is composed of nodes (or vertices) and edges.
  • the node corresponds to the pose data of a certain position
  • the edge corresponds to the pose change data between two nodes.
  • the front-end mileage estimation data can be divided based on the real-time movement trajectory collected by the laser sensor (belonging to the pose sensor system) to generate each group of point clouds (blocks), but it is not limited to the above division method. During the division process, the length of each segment of the motion trajectory can be determined adaptively according to the positioning accuracy information.
  • the division granularity of the corresponding motion trajectory section (Road length/path time) is larger.
  • the second determining module 220 may perform temporal and spatial consistency division on the front-end mileage estimation data to determine each group of point clouds, and construct a corresponding pose map according to the respective groups of point clouds. Specifically, the second determining module 220 may divide the front-end mileage estimation data according to a preset time interval (for example, 1 second, 2 seconds, or 3 seconds) to obtain multiple groups of point clouds divided at the preset time interval.
  • the pose change data between the point clouds is the first type of edge in the pose graph, that is, the first type of edge is generated to reflect the time correlation of each group of point clouds.
  • the second determining module 220 can divide the front-end mileage estimation data according to preset position distances (for example, 3 meters, 5 meters, or 7 meters) to obtain multiple groups of point clouds divided according to the preset position distances.
  • the relative pose change data between the point clouds is the second type of edge in the pose graph. Calculate the relative pose transformation information between the two sets of point clouds (usually a transformation matrix) through the shape of the two sets of point clouds, so that the two sets of point clouds can be aligned after the transformation. Therefore, the second type of edge is generated to reflect each group The correlation of the point cloud in the spatial position.
  • the second determination module 220 may also analyze the motion trajectory contained in the motion posture data, splice and generate each group of point clouds according to the continuity of the motion trajectory, and determine the first frame of point cloud in each group of point clouds as The vertex of the pose graph.
  • the motion trajectory may be a motion trajectory collected in real time based on a laser sensor (or called a lidar, belonging to a pose sensor system).
  • the pose graph divided along the motion trajectory has the first type of edge and the second type of edge, but for each group of point clouds that are not adjacent in the time domain, In other words, the pose graph divided along the motion trajectory only has the second type of edge.
  • the second determining module 220 may also determine the confidence level of the pose estimation data based on the covariance matrix output by the lossless Kalman filter and the pose map.
  • the confidence of the pose estimation data may include the confidence corresponding to the first type of edge and the confidence of the second type of edge, that is, the information matrix of the first type of edge and the information matrix of the second type of edge.
  • Step 330 Process the pose estimation data according to the confidence of the pose estimation data to obtain optimized pose data. Specifically, step 330 may be performed by the optimization module 230.
  • the optimization module 230 can correct the three-dimensional position of each group of point clouds in the pose graph according to the information matrix of the first type of edge and the information matrix of the second type of edge, that is, the The pose estimation data is optimized. If the covariance in the information matrix of the first type of edge or the second type of edge is larger, the weight of the first type of edge or the second type of edge is also higher, then the correction range is reduced, otherwise, the correction range is increased. Specifically, the optimization module 230 may comprehensively consider the covariance in the information matrix of the edge of the first type or the edge of the second type, so as to optimize the pose estimation data in the pose graph.
  • processing the pose estimation data to obtain the optimized pose data can be used for non-linear optimization of the pose graph, that is, by adjusting the positions of all vertices in the pose graph, to try to meet the constraints of all edges, and then obtain the The optimal vertex position under edge constraints.
  • the data collection mode of the navigation device can also be adjusted according to the confidence, for example, data collection Dimensions, data collection period, data collection interval, data collection accuracy and data noise reduction parameters, etc.
  • the foregoing description of the process 300 is only for example and description, and does not limit the scope of application of this application.
  • various modifications and changes can be made to the process 300 under the guidance of this application.
  • these amendments and changes are still within the scope of this application.
  • the preset time interval and/or the preset position distance are not limited to the values listed in step 320, and may also be other values.
  • Fig. 4 is an exemplary flowchart of a method for determining the confidence of pose estimation data according to some embodiments of the present application.
  • the method for determining the confidence of the pose estimation data may be executed by the second determining module 220.
  • the method for determining the confidence of the pose estimation data may include:
  • Step 410 Determine the inverse matrix of the covariance matrix of the output of the lossless Kalman filter, and record it as the information matrix of the first type of edge.
  • the second determining module 220 may perform matrix inversion on the covariance matrix of the output of the lossless Kalman filter to obtain the inverse matrix of the covariance matrix, and record it as the information matrix of the first type of edge . It can be understood that the pose covariance result output by the lossless Kalman filter implies the confidence of the pose estimation data.
  • the covariance matrix of the output of the lossless Kalman filter also implies the confidence level
  • the above-mentioned confidence level essentially depends on the positioning data, the motion posture data and the positioning accuracy information.
  • Confidence is essentially determined by the GPS signal strength and measurement error. Therefore, by generating the information matrix of the first type of edge and the information matrix of the second type of edge, it is to adjust each of the pose maps according to the GPS signal strength and measurement error.
  • the weight of the class edge further improves the reliability and positioning accuracy of the position of each vertex in the pose graph, and reduces the layering phenomenon in the optimization process of the pose graph.
  • the information matrix of the first type of edge can be determined according to the preset hardware parameters of the map generating device and/or the signal strength of the positioning data.
  • the parameter dimension of the pose estimation data can be determined according to the preset hardware parameters of the map generating device and/or the signal strength of the positioning data, and then the preset weight corresponding to the parameter dimension can be set to the diagonal matrix. Value, according to the diagonal matrix to determine the information matrix of the first type of edge.
  • the parameter dimension may include at least one of the absolute position in the north direction, the absolute position in the east direction, the absolute position in the ground direction, the roll angle, the pitch angle, and the yaw angle.
  • the information matrix of the first type of edge can adopt the following sixth-order diagonal matrix:
  • ⁇ 2 north , ⁇ 2 east , ⁇ 2 grouding , ⁇ 2 roll , ⁇ 2 pitch and ⁇ 2 heading are the absolute position in the north direction, the absolute position in the east direction, the absolute position toward the ground, the roll angle, the pitch angle and the heading , respectively.
  • the covariance corresponding to the deflection angle is the absolute position in the north direction, the absolute position in the east direction, the absolute position toward the ground, the roll angle, the pitch angle and the heading , respectively.
  • the information matrix of the first type of edge is determined according to the preset hardware parameters and/or the signal strength of the positioning data of the map generating device, due to the preset hardware parameters and/or positioning data of the map generating device
  • the signal strength of is related to the GPS signal strength and measurement error. Therefore, the weight of various edges of the pose graph is adjusted indirectly according to the GPS signal strength and measurement error, thereby improving the reliability and positioning of the position of each vertex in the pose graph Accuracy reduces the layering phenomenon in the optimization process of the pose map.
  • Step 420 Perform registration processing on any two groups of point clouds in each group of point clouds to determine the inverse matrix of the covariance matrix generated during the registration processing, and record it as the information matrix of the second type of edge.
  • the second determining module 220 may perform registration processing on any two groups of point clouds in each group of point clouds, and perform matrix inversion on the covariance matrix generated during the registration processing to obtain the covariance matrix.
  • the point cloud registration process may be a transformation process that aligns two sets of point clouds, and the transformation process corresponds to a transformation matrix, that is, a covariance matrix.
  • the information matrix of the second type of edge can adopt the following sixth-order diagonal matrix:
  • the first column vector, the second column vector and the third column vector They are the covariances corresponding to the relative position in the north direction, the relative position in the east direction, and the relative position in the ground direction.
  • the fourth column vector, the fifth column vector and the sixth column vector They are the corresponding covariances of the relative roll angle, relative pitch angle, and relative yaw angle.
  • the information matrix of the first type of edge and/or the information matrix of the second type of edge is not limited to the sixth-order diagonal matrix, and may also be the diagonal matrix of other orders, or may also be the sixth-order non-diagonal matrix.
  • Fig. 5 is a schematic block diagram of a map generating device according to some embodiments of the present application.
  • the map generating device 500 may include a memory 502, a controller 504, and a computer program stored on the memory 502 and running on the server.
  • the controller 504 executes the computer program.
  • the map generating device 500 may include a navigation device 506, and the navigation device 506 may include a global positioning system 5061 and a pose sensor system 5062.
  • the global positioning system 5061 may include a positioning board and a satellite communication antenna. The positioning board and the satellite communication antenna may be used to collect the three-dimensional position and heading angle information of the map generating device 500 in the earth coordinate system.
  • the heading angle information may include the aforementioned roll angle, pitch angle, and yaw angle.
  • the pose sensor system 5062 may include at least one or more of a vision sensor, a laser sensor, and an inertial sensor, and the vision sensor, laser sensor, and inertial sensor may be combined to collect speed, motion trajectory, and acceleration information.
  • Fig. 6 is a schematic block diagram of a map generating device according to other embodiments of the present application.
  • This application also proposes a computer-readable storage medium 800 on which a computer program is stored.
  • the computer program When the computer program is read by the map generating device 500, it can implement the steps defined in any pose data processing method in this application.
  • the map generating device 500 may be a whole device integrating various parts, that is, the various parts are integrated into one body. For example, each part of the map generating device 500 is located on the collecting device 130. In some embodiments, the map generating device 500 may also be a device including various scattered parts, that is, each part or some parts are independent systems, and the map generating device 500 is just a collective name for each system, for example, a pose information processing system In 100, the server 110 is located at a certain location (that is, the location where the server is centrally managed) and the navigation device 506 is located on the collection device 130.
  • FIG. 7 is a schematic diagram of the effect of optimization of pose estimation data according to other embodiments of the present application.
  • the unit length of the t1 axis and the t2 axis adopt the same dimension and scale accuracy (f1, f2, f3, f4, f5 and f6), and the unit height of the total deviation axis of the displacement also adopts the same dimension and Scale accuracy (d1, d2 and d3), the various edges in the pose graph corresponding to the top of the t1 axis have not introduced confidence (weights), and the various edges in the pose graph corresponding to the top of the t2 axis have introduced confidence (weights) ).
  • the GPS signal strength and measurement error corresponding to the f1 scale baseline and f4 scale baseline belong to the normal range.
  • the correction amplitude of the point cloud corresponding to the point p1 (area) and the point cloud corresponding to the point k1 (area) are almost unchanged. Therefore, the correction range of the point cloud corresponding to the p4 point (region) and the point cloud corresponding to the k4 point (region) are almost unchanged.
  • the GPS signal strength corresponding to the f2 scale baseline and the f5 scale baseline is relatively poor and the measurement error is large.
  • the GPS signal strength corresponding to the f3 scale baseline and the f6 scale baseline is relatively strong and the measurement error is small.
  • the possible beneficial effects brought by the embodiments of the present application include, but are not limited to: determining the confidence of the pose estimation data, and then setting different weights for each edge of the pose graph according to the confidence, so that the back-end loopback process can target Each group of point clouds is optimized accordingly, which improves the optimization efficiency and reliability of the pose map, reduces the layering phenomenon of point cloud data in the pose map, and improves the accuracy and reliability of generating high-precision maps based on pose estimation data Sex.
  • different embodiments may produce different beneficial effects.
  • the possible beneficial effects may be any one or a combination of the above, or any other beneficial effects that may be obtained.
  • this application uses specific words to describe the embodiments of the application.
  • “one embodiment”, “an embodiment”, and/or “some embodiments” mean a certain feature, structure, or characteristic related to at least one embodiment of the present application. Therefore, it should be emphasized and noted that “one embodiment” or “one embodiment” or “an alternative embodiment” mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. .
  • some features, structures, or characteristics in one or more embodiments of the present application can be appropriately combined.
  • the computer storage medium may contain a propagated data signal containing a computer program code, for example on a baseband or as part of a carrier wave.
  • the propagated signal may have multiple manifestations, including electromagnetic forms, optical forms, etc., or suitable combinations.
  • the computer storage medium may be any computer readable medium other than the computer readable storage medium, and the medium may be connected to an instruction execution system, device, or device to realize communication, propagation, or transmission of the program for use.
  • the program code located on the computer storage medium can be transmitted through any suitable medium, including radio, cable, fiber optic cable, RF, or similar medium, or any combination of the above medium.
  • the computer program codes required for the operation of each part of this application can be written in any one or more programming languages, including object-oriented programming languages such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C++, C#, VB.NET, Python Etc., conventional programming languages such as C language, Visual Basic, Fortran 2003, Perl, COBOL 2002, PHP, ABAP, dynamic programming languages such as Python, Ruby and Groovy, or other programming languages.
  • the program code can run entirely on the user's computer, or run as an independent software package on the user's computer, or partly run on the user's computer and partly run on a remote computer, or run entirely on the remote computer or server.
  • the remote computer can be connected to the user's computer through any form of network, such as a local area network (LAN) or a wide area network (WAN), or to an external computer (for example, via the Internet), or in a cloud computing environment, or as a service Use software as a service (SaaS).
  • LAN local area network
  • WAN wide area network
  • SaaS service Use software as a service

Landscapes

  • Engineering & Computer Science (AREA)
  • Remote Sensing (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Automation & Control Theory (AREA)
  • Mathematical Physics (AREA)
  • General Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Optimization (AREA)
  • Mathematical Analysis (AREA)
  • Pure & Applied Mathematics (AREA)
  • Software Systems (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Algebra (AREA)
  • Computing Systems (AREA)
  • Multimedia (AREA)
  • Navigation (AREA)
  • Position Fixing By Use Of Radio Waves (AREA)

Abstract

提供了一种位姿数据处理方法和系统，适用于地图生成设备。该地图生成设备与全球定位系统和位姿传感器系统耦合，该全球定位系统用于输出定位数据，该位姿传感器系统用于输出运动姿态数据，该定位数据和该运动姿态数据用于结合生成位姿估计数据。该位姿数据处理方法包括：响应于生成的定位数据，确定该定位数据对应的定位精度信息（310）；根据定位精度信息，确定该位姿估计数据的置信度（320）；根据该位姿估计数据的置信度，对该位姿估计数据进行处理得到优化后的位姿数据（330）。

Description

一种位姿数据处理方法和系统
优先权声明
本申请要求2019年4月25日提交的中国申请号201910339237.5的优先权，全部内容通过引用并入本文。
技术领域
本申请涉及定位技术领域，特别涉及一种位姿数据处理方法和系统。
背景技术
在高精度地图采集过程中，地图生成设备中除设置GPS(Global Position System，全球定位系统)外，还设置有视觉传感器、激光传感器和惯性传感器等，以在全球定位系统接收GPS信号的通信质量较差时，进行一定程度的修复和优化。相关技术中，上述地图生成设备通过扩展卡尔曼滤波算法，能在GPS信号质量下降甚至丢失的情况下维持一定时长的定位，但随着时间的推移，不确定性的累积会导致定位精度的逐渐下滑直至丢失，而定位精度的下降又会显著影响高精度地图的质量，并随着累积而产生点云全局不一致的现象。
现有技术中的优化手段对位姿图中各边的权重不做区分，这样会消除积累误差的效果较差。因此，有必要提供一种更为精准的位姿数据处理方法和系统，以能针对各区域进行不同幅度的优化。
发明内容
本申请实施例之一提供一种位姿数据处理方法。所述方法适用于地图生成设备，所述地图生成设备与全球定位系统和位姿传感器系统耦合，所述全球定位系统用于输出定位数据，所述位姿传感器系统用于输出运动姿态数据，所述定位数据和所述运动姿态数据用于结合生成位姿估计数据，其中，所述位姿数据处理方法包括：响应于生成的定位数据，确定所述定位数据对应的定位精度信息； 根据所述定位精度信息，确定所述位姿估计数据的置信度；以及根据所述位姿估计数据的置信度，对所述位姿估计数据进行处理得到优化后的位姿数据。
本申请实施例之一提供一种位姿数据处理系统。所述系统适用于地图生成设备，所述地图生成设备与全球定位系统和位姿传感器系统耦合，所述全球定位系统用于输出定位数据，所述位姿传感器系统用于输出运动姿态数据，所述定位数据和所述运动姿态数据用于结合生成位姿估计数据，其中，所述位姿数据处理系统包括：用于存储计算机指令的至少一个存储器；与所述存储器通讯的至少一个处理器，其中当所述至少一个处理器执行所述计算机指令时，所述至少一个处理器使所述系统执行：响应于生成的定位数据，确定所述定位数据对应的定位精度信息；根据所述定位精度信息，确定所述位姿估计数据的置信度；以及根据所述位姿估计数据的置信度，对所述位姿估计数据进行处理得到优化后的位姿数据。
本申请实施例之一提供一种位姿数据处理系统。所述系统适用于地图生成设备，所述地图生成设备与全球定位系统和位姿传感器系统耦合，所述全球定位系统用于输出定位数据，所述位姿传感器系统用于输出运动姿态数据，所述定位数据和所述运动姿态数据用于结合生成位姿估计数据，其中，所述位姿数据处理系统包括：第一确定模块，用于响应于生成的定位数据，确定所述定位数据对应的定位精度信息；第二确定模块，用于根据所述定位精度信息，确定所述位姿估计数据的置信度；以及优化模块，用于根据所述位姿估计数据的置信度，对所述位姿估计数据进行处理得到优化后的位姿数据。
本申请实施例之一提供一种位姿数据处理方法。所述方法适用于地图生成设备，所述地图生成设备与全球定位系统和位姿传感器系统耦合，所述全球定位系统用于输出定位数据，所述位姿传感器系统用于输出运动姿态数据，所述定位数据和所述运动姿态数据用于结合生成位姿估计数据，所述位姿数据处理方法包括：响应于生成的定位数据，确定所述定位数据对应的定位精度信息；根据所述定位精度信息确定所述位姿估计数据的置信度。
在一些实施例中，所述根据所述定位精度信息确定所述位姿估计数据的置信度，具体包括：将所述定位精度信息、所述定位数据和所述运动姿态数据输入无损卡尔曼滤波器，以获取所述位姿估计数据对应的前端里程估计数据；对所述前端里程估计数据进行时空一致性划分，以确定各组点云，并根据所述各组点云构建对应的位姿图，其中，所述无损卡尔曼滤波器的输出结果包含所述置信度。
在一些实施例中，所述对所述前端里程估计数据进行时空一致性划分，以获取各组点云，并根据所述各组点云构建对应的位姿图，具体包括：将所述前端里程估计数据按照预设时间间隔进行划分，以确定位姿图中的第一类边；以及将所述前端里程估计数据按照预设位置间距进行划分，以确定位姿图中的第二类边；解析所述运动姿态数据中包含的运动轨迹，根据所述运动轨迹的连续性拼接生成所述各组点云，并将所述各组点云中的第一帧点云确定为所述位姿图的顶点。
在一些实施例中，所述方法还包括：确定所述无损卡尔曼滤波器的输出的协方差矩阵的逆矩阵，并记作所述第一类边的信息矩阵；对所述各组点云中的任两组点云进行配准处理，以确定所述配准处理时生成的协方差矩阵的逆矩阵，并记作所述第二类边的信息矩阵。
在一些实施例中，所述方法还包括：根据所述地图生成设备的预设硬件参数和/或所述定位数据的信号强度，确定所述第一类边的信息矩阵。
在一些实施例中，所述方法还包括：根据所述第一类边的信息矩阵和所述第二类边的信息矩阵，对所述位姿图中的各组点云的三维位置进行修正。
在一些实施例中，所述根据所述地图生成设备的预设硬件参数和/或所述定位数据的信号强度，确定所述第一类边的信息矩阵，具体包括：根据所述地图生成设备的预设硬件参数和/或所述定位数据的信号强度，确定所述位姿估计数据的参数维度；将所述参数维度对应的预设权重设置为对角矩阵的值，根据所述对角矩阵确定所述第一类边的信息矩阵。
在一些实施例中，所述参数维度包括以下至少一种：北方向绝对位置、东 方向绝对位置、朝地方向绝对位置、翻滚角、俯仰角和航偏角。
在一些实施例中，所述位姿传感器系统包含以下至少一种：视觉传感器、激光传感器和惯性传感器。
在一些实施例中，所述全球定位系统包含定位板卡和卫星通讯天线。
本申请实施例之一提供一种位姿数据处理系统。所述系统适用于地图生成设备，所述地图生成设备与全球定位系统和位姿传感器系统耦合，所述全球定位系统用于输出定位数据，所述位姿传感器系统用于输出运动姿态数据，所述定位数据和所述运动姿态数据用于结合生成位姿估计数据，所述位姿数据处理系统包括处理器，所述处理器执行以下步骤：响应于生成的定位数据，确定所述定位数据对应的定位精度信息；根据所述定位精度信息确定所述位姿估计数据的置信度。
本申请实施例之一提供一种地图生成设备，所述地图生成设备包括存储器、控制器及存储在所述存储器上并可在所述控制器上运行的计算机程序，所述控制器执行所述计算机程序时实现如本申请实施例中任一项所述的位姿数据处理方法。
本申请实施例之一提供一种计算机可读存储介质，所述存储介质存储计算机指令，当计算机读取所述存储介质中的所述计算机指令后，所述计算机执行本申请实施例中任一项所述的方法。
附图说明
本申请将以示例性实施例的方式进一步说明，这些示例性实施例将通过附图进行详细描述。这些实施例并非限制性的，在这些实施例中，相同的编号表示相同的结构，其中：
图1是根据本申请的一些实施例所示的位姿数据处理系统的应用场景示意图；
图2是根据本申请的一些实施例所示的位姿数据处理系统的模块图；
图3是根据本申请的一些实施例所示的位姿数据处理方法的示例性流程图；
图4是根据本申请一些实施例所示的位姿估计数据的置信度的确定方法的示例性流程图；
图5是根据本申请的一些实施例所示的地图生成设备的示意框图；
图6是根据本申请的另一些实施例所示的地图生成设备的示意框图；以及
图7是根据本申请另一些实施例所示的位姿估计数据优化的效果示意图。
具体实施方式
为了更清楚地说明本申请实施例的技术方案，下面将对实施例描述中所需要使用的附图作简单的介绍。显而易见地，下面描述中的附图仅仅是本申请的一些示例或实施例，对于本领域的普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图将本申请应用于其它类似情景。除非从语言环境中显而易见或另做说明，图中相同标号代表相同结构或操作。
应当理解，本文使用的“系统”、“装置”、“单元”和/或“模组”是用于区分不同级别的不同组件、元件、部件、部分或装配的一种方法。然而，如果其他词语可实现相同的目的，则可通过其他表达来替换所述词语。
如本申请和权利要求书中所示，除非上下文明确提示例外情形，“一”、“一个”、“一种”和/或“该”等词并非特指单数，也可包括复数。一般说来，术语“包括”与“包含”仅提示包括已明确标识的步骤和元素，而这些步骤和元素不构成一个排它性的罗列，方法或者设备也可能包含其它的步骤或元素。
本申请中使用了流程图用来说明根据本申请的实施例的系统所执行的操作。应当理解的是，前面或后面操作不一定按照顺序来精确地执行。相反，可以按照倒序或同时处理各个步骤。同时，也可以将其他操作添加到这些过程中，或 从这些过程移除某一步或数步操作。
本申请的实施例可以应用于不同的运输系统，例如，出租车、专车、顺风车、巴士、代驾等。本申请描述的“乘客”、“乘客端”、“乘客终端”、“顾客”、“需求者”、“服务需求者”、“服务请求者”、“消费者”、“消费方”、“使用需求者”等是可以互换的，是指需要或者订购服务的一方，可以是个人，也可以是工具。同样地，本申请描述的“司机”、“司机端”、“司机终端”、“提供者”、“供应者”、“服务提供者”、“服务者”、“服务方”等也是可以互换的，是指提供服务或者协助提供服务的个人、工具或者其他实体等。另外，本申请描述的“用户”可以是需要或者订购服务的一方，也可以是提供服务或者协助提供服务的一方。
图1是根据本申请一些实施例所示的位姿数据处理系统100的应用场景图。
位姿数据处理系统100可以是用于高精度地图采集的在线平台。位姿数据处理系统100可以包括服务器110、网络120、采集终端130和存储设备140。
在一些实施例中，服务器110可以用于处理与高精度地图采集有关的信息和/或数据，例如，服务器110可以处理采集终端130采集的数据，优化位姿图以提高GPS信号较差区域的定位精度。在一些实施例中，服务器110可以是单个的服务器或者服务器群组。所述服务器群可以是集中式的或分布式的(例如，服务器110可以是分布式的系统)。在一些实施例中，服务器110可以是本地的或远程的。例如，服务器110可以通过网络120访问存储在采集终端130、存储设备140中的信息和/或数据。再例如，服务器110可以直接连接到采集终端130、存储设备140以访问存储的信息和/或数据。在一些实施例中，服务器110可以在一个云平台上实现。仅作为示例，所述云平台可以包括私有云、公共云、混合云、社区云、分布云、云之间、多重云等或上述举例的任意组合。
网络120可以促进信息和/或数据的交换。在一些实施例中，位姿数据处理系统100中的一个或以上组件(例如，服务器110、采集终端130和存储设备 140)可以通过网络120向/从位姿数据处理系统100中的其他组件发送/接收信息和/或数据。例如，服务器110可以通过网络120从采集终端130接收采集数据(如，定位数据或运动姿态数据)。在一些实施例中，网络120可以为任意形式的有线或无线网络或其任意组合。仅作为示例，网络120可以包括缆线网络、有线网络、光纤网络、远程通信网络、内部网络、互联网、局域网(LAN)、广域网(WAN)、无线局域网(WLAN)、城域网(MAN)、广域网(WAN)、公共交换电话网络(PSTN)、蓝牙网络、紫蜂网络、近场通讯(NFC)网络、全球移动通讯系统(GSM)网络、码分多址(CDMA)网络、时分多址(TDMA)网络、通用分组无线服务(GPRS)网络、增强数据速率GSM演进(EDGE)网络、宽带码分多址接入(WCDMA)网络、高速下行分组接入(HSDPA)网络、长期演进(LTE)网络、用户数据报协议(UDP)网络、传输控制协议/互联网协议(TCP/IP)网络、短讯息服务(SMS)网络、无线应用协议(WAP)网络、超宽带(UWB)网络、红外线等或其任意组合。在一些实施例中，位姿数据处理系统100可以包括一个或以上网络接入点。例如，位姿数据处理系统100可以包括有线或无线网络接入点，例如基站和/或无线接入点120-1、120-2、…，位姿数据处理系统100的一个或以上组件可以通过其连接到网络120以交换数据和/或信息。
在一些实施例中，采集终端130可以采集数据的设备。在一些实施例中，采集终端130可以用于对采集的数据进行分析加工以生成分析结果的系统。在一些实施例中，采集终端130可以包括自动驾驶车辆130-1、机器人130-2以及自动驾驶轮椅130-3等或其任意组合。在一些实施例中，采集终端130可以是具有定位技术和能够感知周围环境的设备，用于定位采集终端130的位置和探测周围障碍物。例如，采集终端130上可以包括GPS接收器、激光雷达、惯性传感器、相机(如，单目、双目或全景相机)等。在一些实施例中，采集终端130可以将定位信息和周围环境信息发送到服务器110。
存储设备140可以存储与高精度地图采集相关的数据和/或指令。在一些 实施例中，存储设备140可以存储从采集终端130获得/获取的数据。在一些实施例中，存储设备140可以存储服务器110用于执行或使用来完成本申请中描述的示例性方法的数据和/或指令。在一些实施例中，存储设备140可以包括大容量存储器、可移动存储器、易失性读写存储器、只读存储器(ROM)等或其任意组合。示例性的大容量储存器可以包括磁盘、光盘、固态磁盘等。示例性可移动存储器可以包括闪存驱动器、软盘、光盘、存储卡、压缩盘、磁带等。示例性的挥发性只读存储器可以包括随机存取内存(RAM)。示例性的RAM可包括动态RAM(DRAM)、双倍速率同步动态RAM(DDR SDRAM)、静态RAM(SRAM)、闸流体RAM(T-RAM)和零电容RAM(Z-RAM)等。示例性的ROM可以包括掩模ROM(MROM)、可编程ROM(PROM)、可擦除可编程ROM(EPROM)、电子可擦除可编程ROM(EEPROM)、光盘ROM(CD-ROM)和数字通用磁盘ROM等。在一些实施例中，所述存储设备140可以在云平台上实现。仅作为示例，所述云平台可以包括私有云、公共云、混合云、社区云、分布云、内部云、多层云等或其任意组合。
在一些实施例中，存储设备140可以连接到网络120以与位姿数据处理系统100中的一个或以上组件(例如，服务器110、采集终端130)通信。位姿数据处理系统100中的一个或以上组件可以通过网络120访问存储设备140中存储的数据或指令。在一些实施例中，存储设备140可以与位姿数据处理系统100中的一个或以上组件(例如，服务器110、采集终端130等)直接连接或通信。在一些实施例中，存储设备140可以是服务器110的一部分。
图2是根据本申请一些实施例所示的位姿数据处理系统的模块图。
该位姿数据处理系统200适用于地图生成设备，地图生成设备与全球定位系统和位姿传感器系统耦合，全球定位系统用于输出定位数据，位姿传感器系统用于输出运动姿态数据，定位数据和运动姿态数据用于结合生成位姿估计数据。关于地图生成设备的更多内容可以参见图4和图5的描述，在此不作赘述。
如图2所示，系统200可以包括第一确定模块210、第二确定模块220以 及优化模块230。
第一确定模块210可以用于响应于生成的定位数据，确定定位数据对应的定位精度信息。关于确定定位数据对应的定位精度信息的更多内容可以参见步骤310的描述，在此不作赘述。
第二确定模块220可以用于根据定位精度信息，确定位姿估计数据的置信度。关于确定位姿估计数据的置信度的更多内容可以参见步骤320的描述，在此不作赘述。
优化模块230可以用于根据位姿估计数据的置信度，对位姿估计数据进行处理得到优化后的位姿数据。关于对位姿估计数据进行处理得到优化后的位姿数据的更多内容可以参见步骤330的描述，在此不作赘述。
应当理解，图2所示的系统及其模块可以利用各种方式来实现。例如，在一些实施例中，系统及其模块可以通过硬件、软件或者软件和硬件的结合来实现。其中，硬件部分可以利用专用逻辑来实现；软件部分则可以存储在存储器中，由适当的指令执行系统，例如微处理器或者专用设计硬件来执行。本领域技术人员可以理解上述的方法和系统可以使用计算机可执行指令和/或包含在处理器控制代码中来实现，例如在诸如磁盘、CD或DVD-ROM的载体介质、诸如只读存储器(固件)的可编程的存储器或者诸如光学或电子信号载体的数据载体上提供了这样的代码。本申请的系统及其模块不仅可以有诸如超大规模集成电路或门阵列、诸如逻辑芯片、晶体管等的半导体、或者诸如现场可编程门阵列、可编程逻辑设备等的可编程硬件设备的硬件电路实现，也可以用例如由各种类型的处理器所执行的软件实现，还可以由上述硬件电路和软件的结合(例如，固件)来实现。
需要注意的是，以上对于位姿数据处理系统及其模块的描述，仅为描述方便，并不能把本申请限制在所举实施例范围之内。可以理解，对于本领域的技术人员来说，在了解该系统的原理后，可能在不背离这一原理的情况下，对各个模块进行任意组合，或者构成子系统与其他模块连接。例如，在一些实施例中，例 如，图2中披露的第一确定模块210、第二确定模块220以及优化模块230可以是一个系统中的不同模块，也可以是一个模块实现上述的两个或两个以上模块的功能。例如，第一确定模块210和第二确定模块220可以是两个模块，也可以是一个模块同时具有确定定位数据对应的定位精度信息和确定位姿估计数据的置信度的功能。例如，各个模块可以共用一个存储模块，各个模块也可以分别具有各自的存储模块。诸如此类的变形，均在本申请的保护范围之内。
图3是根据本申请一些实施例所示的位姿数据处理方法的示例性流程图。
该位姿数据处理方法可以适用于地图生成设备，地图生成设备中设有全球定位系统和位姿传感器系统，全球定位系统用于输出定位数据，位姿传感器系统用于输出运动姿态数据。关于地图生成设备的更多内容可以参见图4和图5的描述，在此不作赘述。关于定位数据和运动姿态数据的更多内容可以参见步骤310的描述，在此不作赘述。
如图3所示，该位姿数据处理方法可以包括：
步骤310，响应于生成的定位数据，确定所述定位数据对应的定位精度信息。具体的，步骤310可以由第一确定模块210执行。
定位数据可以包括所有可用于对主体进行定位的数据(如全球定位系统基于定位卫星的通讯信号生成的三维坐标位置等)，运动姿态数据可以包括所有和运动或姿态相关的数据(如运动轨迹、速度、加速度等)。在一些实施例中，可以结合定位数据和运动姿态数据确定位姿估计数据。位姿估计数据可以包括北方向绝对位置、东方向绝对位置、朝地方向绝对位置、翻滚角、俯仰角和航偏角在内的六个维度的参数。翻滚角为根据地图生成设备的机身向左右两侧水平线侧翻的夹角，翻滚角的角度范围为(-180°，180°]。俯仰角为根据地图生成设备的机身方向与水平方向形成的夹角，俯仰角的角度范围为[-90°，90°]。偏航角为根据地图生成设备的机头方向与预设航向形成的夹角，偏航角的角度范围为(-180°，180°]。
在生成定位数据的同时，可以确定相应的定位精度信息。可选地，定位精 度信息可以包括：PDOP(Positional Dilution of Precision，位置精度强弱度，即三维/空间位置精度信息，譬如经度、纬度、高程等因子)、HDOP(Horizontal Positional Dilution of Precision，水平/平面位置精度强弱度，譬如经度、纬度等因子)、VDOP(Vertical Positional Dilution of Precision，垂直位置精度强弱度，譬如高程因子)。上述精度强弱度(或称为精度因子)的值与定位精度信息通常是成正比关系，即精度强弱度的值越小，则定位精度信息对应的定位数据的误差越小，表示定位准确度越高。
在一些实施例中，第一确定模块210可以响应于生成的定位数据，确定定位数据对应的定位精度信息。
步骤320，根据定位精度信息，确定位姿估计数据的置信度。具体的，步骤320可以由第二确定模块220执行。
在一些实施例中，位姿估计数据的置信度可以用于表征位姿估计数据的可靠度，置信度越高，表示位姿估计数据越可靠，即位姿估计数据的误差越小。在一些实施例中，第二确定模块220可以根据定位精度信息，确定位姿估计数据的置信度。具体的，第二确定模块220可以将定位精度信息、定位数据和运动姿态数据输入无损卡尔曼滤波器，可以确定位姿估计数据对应的前端里程估计数据和协方差矩阵。无损卡尔曼滤波器是无损变换和标准Kalman滤波体系的结合，通过无损变换使非线性系统方程适用于线性假设下的标准Kalman滤波体系。前端里程估计数据可以为通过无损卡尔曼滤波器估计出的下一段行驶轨迹数据，该前端里程估计数据可能与实际行驶轨迹不同。
在一些实施例中，第二确定模块220还可以对该前端里程估计数据进行划分，以确定各组点云，并根据该各组点云构建对应的位姿图。位姿图由节点(或称为顶点)和边构成，节点对应某个位置的位姿数据，边对应两个节点之间的位姿变化数据。通常可以基于激光传感器(属于位姿传感器系统)实时采集的运动轨迹，并进一步基于运动轨迹划分前端里程估计数据，以生成各组点云(块)，但不限于上述划分方法。在划分过程时，可以按照定位精度信息自适应地确定各 段运动轨迹的长度，例如，精度因子的值越小(即，定位数据的误差越小)，则其对应的运动轨迹路段的划分粒度(路段长度/途径时间)越大。完成上述划分过程后，每一小段连续的运动轨迹将作为位姿图的一个节点，并进行优化。
优选地，第二确定模块220可以对该前端里程估计数据进行时空一致性划分，以确定各组点云，并根据该各组点云构建对应的位姿图。具体的，第二确定模块220可以将前端里程估计数据按照预设时间间隔(如，1秒、2秒或3秒)进行划分，得到按预设时间间隔划分的多组点云，该多组点云之间的位姿变化数据即为位姿图中的第一类边，即通过生成第一类边来反映各组点云在时间上的相关性。相应的，第二确定模块220可以将前端里程估计数据按照预设位置间距(如，3米、5米或7米)进行划分，得到按预设位置间距划分的多组点云，该多组点云之间的相对位姿变化数据即为位姿图中的第二类边。通过两组点云的形状计算它们之间的相对位姿变换信息(通常是一个变换矩阵)，使得经过该变换后能够将两组点云对齐，因此，通过生成第二类边来反映各组点云在空间位置上的相关性。通过按时空一致性对前端里程估计数据进行划分，可以将多个点云划分为同一组，通过处理各组点云代替处理单帧点云，减少了位姿数据处理系统100的计算量。可选地，第二确定模块220还可以解析运动姿态数据中包含的运动轨迹，根据该运动轨迹的连续性拼接生成各组点云，并将各组点云中的第一帧点云确定为位姿图的顶点。运动轨迹可以是基于激光传感器(或称为激光雷达，属于位姿传感器系统)实时采集的运动轨迹。综上可知，对于时域相邻的各组点云来说，沿运动轨迹划分后的位姿图具备第一类边和第二类边，但对于时域不相邻的各组点云来说，沿运动轨迹划分后的位姿图仅具备第二类边。
在一些实施例中，第二确定模块220还可以基于无损卡尔曼滤波器输出的协方差矩阵和该位姿图，确定位姿估计数据的置信度。位姿估计数据的置信度可以包括对应于第一类边的置信度和第二类边的置信度，即第一类边的信息矩阵和第二类边的信息矩阵。关于确定位姿估计数据的置信度的更多内容可以参见图4及其描述，本申请对此不作赘述。
步骤330，根据位姿估计数据的置信度，对位姿估计数据进行处理得到优化后的位姿数据。具体的，步骤330可以由优化模块230执行。
在一些实施例中，优化模块230可以根据第一类边的信息矩阵和第二类边的信息矩阵，对位姿图中的各组点云的三维位置进行修正，即对位姿图中的位姿估计数据进行优化。如果第一类边或第二类边的信息矩阵中协方差较大，则第一类边或第二类边的权重也较高，那么修正幅度则降低，反之，则提高修正幅度。具体的，优化模块230可以综合考虑第一类边或第二类边的信息矩阵中的协方差，从而对位姿图中的位姿估计数据进行优化。例如，可以设置第一类边的权重占比为70％、第二类边的权重占比为30％，然后确定综合后的修正幅度，以对位姿图中的位姿估计数据进行优化。对位姿估计数据进行处理得到优化后的位姿数据可以为对位姿图进行非线性优化，即通过调整位姿图中所有顶点的位置，来尽量满足所有边的约束，进而求得在所有边约束下的最优顶点位置。
进一步地，除了根据位姿估计数据的置信度，在位姿图优化的过程中自适应调整各组点云的优化幅度以外，还可以根据置信度调整导航设备的数据采集模式，譬如，数据采集维度、数据采集周期、数据采集间隔、数据采集精度和数据降噪参数等。
在进行位姿估计数据的优化过程中，还可以着重调整GPS信号较弱区域的位姿估计数据，以提高各组点云的三维位置的准确性和可靠性，降低了位姿图优化过程中的分层现象。
应当注意的是，上述有关流程300的描述仅仅是为了示例和说明，而不限定本申请的适用范围。对于本领域技术人员来说，在本申请的指导下可以对流程300进行各种修正和改变。然而，这些修正和改变仍在本申请的范围之内。例如，预设时间间隔和/或预设位置间距不限于步骤320中列举的数值，还可以为其他数值。
图4是根据本申请一些实施例所示的位姿估计数据的置信度的确定方法的示例性流程图。在一些实施例中，该位姿估计数据的置信度的确定方法可以由 第二确定模块220执行。
如图4所示，该位姿估计数据的置信度的确定方法可以包括：
步骤410，确定无损卡尔曼滤波器的输出的协方差矩阵的逆矩阵，并记作第一类边的信息矩阵。
在一些实施例中，第二确定模块220可以对无损卡尔曼滤波器的输出的协方差矩阵进行矩阵求逆，以得到协方差矩阵的逆矩阵，并将其记作第一类边的信息矩阵。可以理解，无损卡尔曼滤波器输出的位姿协方差结果中，隐含了位姿估计数据的置信度。
确定第一类边的信息矩阵，旨在生成第一类边后，对第一类边赋予对应的权重，以在对位姿图进行优化时确定相应的修正幅度，具体地，如果第一类边的信息矩阵中协方差较大，则第一类边的权重也较高，那么修正幅度则降低，反之，则提高修正幅度。
进一步地，由于无损卡尔曼滤波器的输出的协方差矩阵也隐含了置信度，结合前文所述，上述置信度其实质是取决于定位数据、运动姿态数据和定位精度信息，更进一步地，置信度其实质是取决于GPS信号强度和测量误差，因此，通过生成第一类边的信息矩阵和第二类边的信息矩阵，即是根据GPS信号强度和测量误差来调整位姿图的各类边的权重，进而提高位姿图中各顶点位置的可靠性和定位精度，降低了位姿图优化过程中的分层现象。
优先地，可以根据地图生成设备的预设硬件参数和/或定位数据的信号强度，确定第一类边的信息矩阵。具体的，可以根据地图生成设备的预设硬件参数和/或所述定位数据的信号强度，确定位姿估计数据的参数维度，然后可以将该参数维度对应的预设权重设置为对角矩阵的值，根据对角矩阵确定第一类边的信息矩阵。优选地，参数维度可以包括北方向绝对位置、东方向绝对位置、朝地方向绝对位置、翻滚角、俯仰角和航偏角中的至少一种。例如，第一类边的信息矩阵可以采用如下的六阶对角矩阵：
Figure PCTCN2020086784-appb-000001
其中，σ 2 north、σ 2 east、σ 2 grouding、σ 2 roll、σ 2 pitch和σ 2 heading分别为北方向绝对位置、东方向绝对位置、朝地方向绝对位置、翻滚角、俯仰角和航偏角对应的协方差。
在上述技术方案中，通过根据地图生成设备的预设硬件参数和/或定位数据的信号强度，确定所述第一类边的信息矩阵，由于地图生成设备的预设硬件参数和/或定位数据的信号强度关联于GPS信号强度和测量误差，因此，也是间接地根据GPS信号强度和测量误差来调整位姿图的各类边的权重，进而提高位姿图中各顶点位置的可靠性和定位精度，降低了位姿图优化过程中的分层现象。
步骤420，对各组点云中的任两组点云进行配准处理，以确定配准处理时生成的协方差矩阵的逆矩阵，并记作第二类边的信息矩阵。
在一些实施例中，第二确定模块220可以通过对各组点云中的任两组点云进行配准处理，对配准处理时生成的协方差矩阵进行矩阵求逆，以得到协方差矩阵的逆矩阵，并将其记作第二类边的信息矩阵。点云配准处理可以为将两组点云进行对齐的变换处理，该变换处理对应一个变换矩阵，即协方差矩阵。例如，第二类边的信息矩阵可以采用如下的六阶对角矩阵：
Figure PCTCN2020086784-appb-000002
其中，第一列向量、第二列向量和第三列向量中的
Figure PCTCN2020086784-appb-000003
分别为北方向相对位置、东方向相对位置、朝地方向相对位置对应的协方差，第四列向量、第五列向量和第六列向量中的
Figure PCTCN2020086784-appb-000004
分别为相对翻滚角、相对俯仰角和相对航偏角对应的协方差。
与第一类边的位姿优化逻辑相似，如果第二类边的信息矩阵中协方差较大，则第二类边的权重也较高，那么修正幅度则降低，反之，则提高修正幅度。
应当注意的是，上述有关流程400的描述仅仅是为了示例和说明，而不限定本申请的适用范围。对于本领域技术人员来说，在本申请的指导下可以对流程400进行各种修正和改变。然而，这些修正和改变仍在本申请的范围之内。例如，第一类边的信息矩阵和/或第二类边的信息矩阵不限于六阶对角矩阵，还可以为其他阶数的对角矩阵，或者还可以为六阶非对角矩阵。
图5是根据本申请一些实施例所示的地图生成设备的示意框图。
如图5所示，地图生成设备500可以包括存储器502、控制器504及存储在所述存储器502上并可在所述服务器上运行的计算机程序，所述控制器504执行所述计算机程序时实现本申请中任一项位姿数据处理方法限定的步骤，和/或包括如图1所示的位姿数据处理系统100。地图生成设备500可以包括导航设备506，导航设备506可以包括全球定位系统5061和位姿传感器系统5062。在一些实施例中，全球定位系统5061可以包括定位板卡和卫星通讯天线，定位板卡和卫星通讯天线可以用于采集地图生成设备500在地球坐标系中的三维位置和航向角信息，其中，航向角信息可以包括上述翻滚角、俯仰角和航偏角。在一些实施例中，位姿传感器系统5062可以包含视觉传感器、激光传感器和惯性传感器中至少一种或几种，视觉传感器、激光传感器和惯性传感器可以结合用于采集速度、运动轨迹和加速度信息。
图6是根据本申请另一些实施例所示的地图生成设备的示意框图。
本申请还提出了一种计算机可读存储介质800，其上存储有计算机程序，上述计算机程序被地图生成设备500读取时，能够实现本申请中任一项位姿数 据处理方法限定的步骤。
在一些实施例中，地图生成设备500可以是整合各个部分的一个整体设备，即各个部分集成为一体，例如，地图生成设备500中各部分都位于采集设备130上。在一些实施例中，地图生成设备500也可以是包括各个分散部分的设备，即各个部分或某些部分是独立的系统，地图生成设备500只是各个系统的合称，例如，位姿信息处理系统100中服务器110位于某位置(即，服务器集中管理的地点)和导航设备506位于采集设备130上。
图7是根据本申请另一些实施例所示的位姿估计数据优化的效果示意图。
如图7所示，t1轴和t2轴的单位长度采用相同的量纲和刻度精度(f1、f2、f3、f4、f5和f6)，位移总偏差轴的单位高度也采用相同的量纲和刻度精度(d1、d2和d3)，t1轴上方对应的位姿图中的各类边未引入置信度(权重)，t2轴上方对应的位姿图中的各类边已引入置信度(权重)。
f1刻度基线和f4刻度基线对应的GPS信号强度和测量误差均属于正常范围，此时，p1点(区域)对应的点云与k1点(区域)对应的点云的修正幅度几乎不变，同理，p4点(区域)对应的点云与k4点(区域)对应的点云的修正幅度几乎不变。
f2刻度基线和f5刻度基线对应的GPS信号强度较差和测量误差较大，此时，对比p2点(区域)对应的点云的修正幅度，通过引入置信度提高k2点(区域)对应的点云的修正幅度，同理，对比p5点(区域)对应的点云的修正幅度，通过引入置信度提高k5点(区域)对应的点云的修正幅度。
f3刻度基线和f6刻度基线对应的GPS信号强度较强和测量误差较小，此时，对比p3点(区域)对应的点云的修正幅度，通过引入置信度降低k3点(区域)对应的点云的修正幅度，同理，对比p6点(区域)对应的点云的修正幅度，通过引入置信度降低k6点(区域)对应的点云的修正幅度。
本申请实施例可能带来的有益效果包括但不限于：通过确定位姿估计数 据的置信度，进而根据置信度对位姿图的各个边进行不同权重设置，使得后端回环处理过程中能够针对各组点云进行相应的优化，提高了位姿图优化效率和可靠性，减少了位姿图中点云数据的分层现象，提升了基于位姿估计数据生成高精度地图的精确度和可靠性。需要说明的是，不同实施例可能产生的有益效果不同，在不同的实施例里，可能产生的有益效果可以是以上任意一种或几种的组合，也可以是其他任何可能获得的有益效果。
上文已对基本概念做了描述，显然，对于本领域技术人员来说，上述详细披露仅仅作为示例，而并不构成对本申请的限定。虽然此处并没有明确说明，本领域技术人员可能会对本申请进行各种修改、改进和修正。该类修改、改进和修正在本申请中被建议，所以该类修改、改进、修正仍属于本申请示范实施例的精神和范围。
同时，本申请使用了特定词语来描述本申请的实施例。如“一个实施例”、“一实施例”、和/或“一些实施例”意指与本申请至少一个实施例相关的某一特征、结构或特点。因此，应强调并注意的是，本说明书中在不同位置两次或多次提及的“一实施例”或“一个实施例”或“一个替代性实施例”并不一定是指同一实施例。此外，本申请的一个或多个实施例中的某些特征、结构或特点可以进行适当的组合。
此外，本领域技术人员可以理解，本申请的各方面可以通过若干具有可专利性的种类或情况进行说明和描述，包括任何新的和有用的工序、机器、产品或物质的组合，或对他们的任何新的和有用的改进。相应地，本申请的各个方面可以完全由硬件执行、可以完全由软件(包括固件、常驻软件、微码等)执行、也可以由硬件和软件组合执行。以上硬件或软件均可被称为“数据块”、“模块”、“引擎”、“单元”、“组件”或“系统”。此外，本申请的各方面可能表现为位于一个或多个计算机可读介质中的计算机产品，该产品包括计算机可读程序编码。
计算机存储介质可能包含一个内含有计算机程序编码的传播数据信号，例如在基带上或作为载波的一部分。该传播信号可能有多种表现形式，包括电磁 形式、光形式等，或合适的组合形式。计算机存储介质可以是除计算机可读存储介质之外的任何计算机可读介质，该介质可以通过连接至一个指令执行系统、装置或设备以实现通讯、传播或传输供使用的程序。位于计算机存储介质上的程序编码可以通过任何合适的介质进行传播，包括无线电、电缆、光纤电缆、RF、或类似介质，或任何上述介质的组合。
本申请各部分操作所需的计算机程序编码可以用任意一种或多种程序语言编写，包括面向对象编程语言如Java、Scala、Smalltalk、Eiffel、JADE、Emerald、C++、C#、VB.NET、Python等，常规程序化编程语言如C语言、Visual Basic、Fortran 2003、Perl、COBOL 2002、PHP、ABAP，动态编程语言如Python、Ruby和Groovy，或其他编程语言等。该程序编码可以完全在用户计算机上运行、或作为独立的软件包在用户计算机上运行、或部分在用户计算机上运行部分在远程计算机运行、或完全在远程计算机或服务器上运行。在后种情况下，远程计算机可以通过任何网络形式与用户计算机连接，比如局域网(LAN)或广域网(WAN)，或连接至外部计算机(例如通过因特网)，或在云计算环境中，或作为服务使用如软件即服务(SaaS)。
此外，除非权利要求中明确说明，本申请所述处理元素和序列的顺序、数字字母的使用、或其他名称的使用，并非用于限定本申请流程和方法的顺序。尽管上述披露中通过各种示例讨论了一些目前认为有用的发明实施例，但应当理解的是，该类细节仅起到说明的目的，附加的权利要求并不仅限于披露的实施例，相反，权利要求旨在覆盖所有符合本申请实施例实质和范围的修正和等价组合。例如，虽然以上所描述的系统组件可以通过硬件设备实现，但是也可以只通过软件的解决方案得以实现，如在现有的服务器或移动设备上安装所描述的系统。
同理，应当注意的是，为了简化本申请披露的表述，从而帮助对一个或多个发明实施例的理解，前文对本申请实施例的描述中，有时会将多种特征归并至一个实施例、附图或对其的描述中。但是，这种披露方法并不意味着本申请对象所需要的特征比权利要求中提及的特征多。实际上，实施例的特征要少于上述披 露的单个实施例的全部特征。
一些实施例中使用了描述成分、属性数量的数字，应当理解的是，此类用于实施例描述的数字，在一些示例中使用了修饰词“大约”、“近似”或“大体上”来修饰。除非另外说明，“大约”、“近似”或“大体上”表明所述数字允许有±20％的变化。相应地，在一些实施例中，说明书和权利要求中使用的数值参数均为近似值，该近似值根据个别实施例所需特点可以发生改变。在一些实施例中，数值参数应考虑规定的有效数位并采用一般位数保留的方法。尽管本申请一些实施例中用于确认其范围广度的数值域和参数为近似值，在具体实施例中，此类数值的设定在可行范围内尽可能精确。
针对本申请引用的每个专利、专利申请、专利申请公开物和其他材料，如文章、书籍、说明书、出版物、文档等，特此将其全部内容并入本申请作为参考。与本申请内容不一致或产生冲突的申请历史文件除外，对本申请权利要求最广范围有限制的文件(当前或之后附加于本申请中的)也除外。需要说明的是，如果本申请附属材料中的描述、定义、和/或术语的使用与本申请所述内容有不一致或冲突的地方，以本申请的描述、定义和/或术语的使用为准。
最后，应当理解的是，本申请中所述实施例仅用以说明本申请实施例的原则。其他的变形也可能属于本申请的范围。因此，作为示例而非限制，本申请实施例的替代配置可视为与本申请的教导一致。相应地，本申请的实施例不仅限于本申请明确介绍和描述的实施例。

Claims (21)

  1. 一种位姿数据处理方法，适用于地图生成设备，所述地图生成设备与全球定位系统和位姿传感器系统耦合，所述全球定位系统用于输出定位数据，所述位姿传感器系统用于输出运动姿态数据，所述定位数据和所述运动姿态数据用于结合生成位姿估计数据，其中，所述位姿数据处理方法包括：
    响应于生成的定位数据，确定所述定位数据对应的定位精度信息；
    根据所述定位精度信息，确定所述位姿估计数据的置信度；以及
    根据所述位姿估计数据的置信度，对所述位姿估计数据进行处理得到优化后的位姿数据。
  2. 如权利要求1所述的位姿数据处理方法，其中，所述根据所述定位精度信息，确定所述位姿估计数据的置信度包括：
    将所述定位精度信息、所述定位数据和所述运动姿态数据输入无损卡尔曼滤波器，以获取所述位姿估计数据对应的前端里程估计数据和协方差矩阵；
    对所述前端里程估计数据进行时空一致性划分，以确定各组点云，并根据所述各组点云构建对应的位姿图；以及
    基于所述协方差矩阵和所述位姿图，确定所述位姿估计数据的置信度。
  3. 如权利要求2所述的位姿数据处理方法，其中，所述对所述前端里程估计数据进行时空一致性划分，以确定各组点云，并根据所述各组点云构建对应的位姿图包括：
    将所述前端里程估计数据按照预设时间间隔进行划分，以确定位姿图中的第一类边；
    以及将所述前端里程估计数据按照预设位置间距进行划分，以确定位姿图中的第二类边；以及
    解析所述运动姿态数据中包含的运动轨迹，根据所述运动轨迹的连续性拼接生成所述各组点云，并将所述各组点云中的第一帧点云确定为所述位姿图的 顶点。
  4. 如权利要求3所述的位姿数据处理方法，其中，所述基于所述协方差矩阵和所述位姿图，确定所述位姿估计数据的置信度包括：
    确定所述无损卡尔曼滤波器的输出的协方差矩阵的逆矩阵，并记作所述第一类边的信息矩阵；以及
    对所述各组点云中的任两组点云进行配准处理，以确定所述配准处理时生成的协方差矩阵的逆矩阵，并记作所述第二类边的信息矩阵。
  5. 如权利要求4所述的位姿数据处理方法，其中，所述确定所述无损卡尔曼滤波器的输出的协方差矩阵的逆矩阵，并记作所述第一类边的信息矩阵包括：
    根据所述地图生成设备的预设硬件参数和/或所述定位数据的信号强度，确定所述第一类边的信息矩阵。
  6. 如权利要求4或5所述的位姿数据处理方法，其中，所述根据所述位姿估计数据的置信度，对所述位姿估计数据进行处理得到优化后的位姿数据包括：
    根据所述第一类边的信息矩阵和所述第二类边的信息矩阵，对所述位姿图中的各组点云的三维位置进行修正。
  7. 如权利要求5所述的位姿数据处理方法，其中，所述根据所述地图生成设备的预设硬件参数和/或所述定位数据的信号强度，确定所述第一类边的信息矩阵包括：
    根据所述地图生成设备的预设硬件参数和/或所述定位数据的信号强度，确定所述位姿估计数据的参数维度；以及
    将所述参数维度对应的预设权重设置为对角矩阵的值，根据所述对角矩阵确定所述第一类边的信息矩阵。
  8. 如权利要求7所述的位姿数据处理方法，其中，
    所述参数维度包括以下至少一种：北方向绝对位置、东方向绝对位置、朝地方向绝对位置、翻滚角、俯仰角和航偏角。
  9. 如权利要求1至8中任一项所述的位姿数据处理方法，其中，
    所述位姿传感器系统包含以下至少一种：视觉传感器、激光传感器和惯性传感器。
  10. 一种位姿数据处理系统，适用于地图生成设备，所述地图生成设备与全球定位系统和位姿传感器系统耦合，所述全球定位系统用于输出定位数据，所述位姿传感器系统用于输出运动姿态数据，所述定位数据和所述运动姿态数据用于结合生成位姿估计数据，其中，所述位姿数据处理系统包括：
    用于存储计算机指令的至少一个存储器；
    与所述存储器通讯的至少一个处理器，其中当所述至少一个处理器执行所述计算机指令时，所述至少一个处理器使所述系统执行：
    响应于生成的定位数据，确定所述定位数据对应的定位精度信息；
    根据所述定位精度信息，确定所述位姿估计数据的置信度；以及
    根据所述位姿估计数据的置信度，对所述位姿估计数据进行处理得到优化后的位姿数据。
  11. 如权利要求10所述的位姿数据处理系统，其中，为确定所述位姿估计数据的置信度，所述至少一个处理器使所述系统进一步执行：
    将所述定位精度信息、所述定位数据和所述运动姿态数据输入无损卡尔曼滤波器，以获取所述位姿估计数据对应的前端里程估计数据和协方差矩阵；
    对所述前端里程估计数据进行时空一致性划分，以确定各组点云，并根据所 述各组点云构建对应的位姿图；以及
    基于所述协方差矩阵和所述位姿图，确定所述位姿估计数据的置信度。
  12. 如权利要求11所述的位姿数据处理系统，其中，为根据所述各组点云构建对应的位姿图，所述至少一个处理器使所述系统进一步执行：
    将所述前端里程估计数据按照预设时间间隔进行划分，以确定位姿图中的第一类边；
    以及将所述前端里程估计数据按照预设位置间距进行划分，以确定位姿图中的第二类边；以及
    解析所述运动姿态数据中包含的运动轨迹，根据所述运动轨迹的连续性拼接生成所述各组点云，并将所述各组点云中的第一帧点云确定为所述位姿图的顶点。
  13. 如权利要求12所述的位姿数据处理系统，其中，为基于所述协方差矩阵和所述位姿图，确定所述位姿估计数据的置信度，所述至少一个处理器使所述系统进一步执行：
    确定所述无损卡尔曼滤波器的输出的协方差矩阵的逆矩阵，并记作所述第一类边的信息矩阵；以及
    对所述各组点云中的任两组点云进行配准处理，以确定所述配准处理时生成的协方差矩阵的逆矩阵，并记作所述第二类边的信息矩阵。
  14. 如权利要求13所述的位姿数据处理系统，其中，为确定所述无损卡尔曼滤波器的输出的协方差矩阵的逆矩阵，并记作所述第一类边的信息矩阵，所述至少一个处理器使所述系统进一步执行：
    根据所述地图生成设备的预设硬件参数和/或所述定位数据的信号强度，确定所述第一类边的信息矩阵。
  15. 如权利要求13或14所述的位姿数据处理系统，其中，为根据所述位姿估计数据的置信度，对所述位姿估计数据进行处理得到优化后的位姿数据，所述至少一个处理器使所述系统进一步执行：
    根据所述第一类边的信息矩阵和所述第二类边的信息矩阵，对所述位姿图中的各组点云的三维位置进行修正。
  16. 如权利要求14所述的位姿数据处理系统，其中，为根据所述地图生成设备的预设硬件参数和/或所述定位数据的信号强度，确定所述第一类边的信息矩阵，所述至少一个处理器使所述系统进一步执行：
    根据所述地图生成设备的预设硬件参数和/或所述定位数据的信号强度，确定所述位姿估计数据的参数维度；
    将所述参数维度对应的预设权重设置为对角矩阵的值，根据所述对角矩阵确定所述第一类边的信息矩阵。
  17. 如权利要求16所述的位姿数据处理系统，其中，
    所述参数维度包括以下至少一种：北方向绝对位置、东方向绝对位置、朝地方向绝对位置、翻滚角、俯仰角和航偏角。
  18. 如权利要求10至17中任一项所述的位姿数据处理系统，其中，
    所述位姿传感器系统包含以下至少一种：视觉传感器、激光传感器和惯性传感器。
  19. 一种位姿数据处理系统，适用于地图生成设备，所述地图生成设备与全球定位系统和位姿传感器系统耦合，所述全球定位系统用于输出定位数据，所述位姿传感器系统用于输出运动姿态数据，所述定位数据和所述运动姿态数据用 于结合生成位姿估计数据，其中，所述位姿数据处理系统包括：
    第一确定模块，用于响应于生成的定位数据，确定所述定位数据对应的定位精度信息；
    第二确定模块，用于根据所述定位精度信息，确定所述位姿估计数据的置信度；以及
    优化模块，用于根据所述位姿估计数据的置信度，对所述位姿估计数据进行处理得到优化后的位姿数据。
  20. 一种地图生成设备，所述地图生成设备包括存储器、控制器及存储在所述存储器上并可在所述控制器上运行的计算机程序，其中，
    所述控制器执行所述计算机程序时实现如权利要求1至9中任一项所述的位姿数据处理方法。
  21. 一种计算机可读存储介质，其中，所述存储介质存储计算机指令，当所述计算机指令被处理器执行时实现如权利要求1至9中任一项所述的方法。
PCT/CN2020/086784 2019-04-25 2020-04-24 一种位姿数据处理方法和系统 Ceased WO2020216342A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US17/451,838 US20220044436A1 (en) 2019-04-25 2021-10-22 Pose data processing method and system

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910339237.5A CN111854769B (zh) 2019-04-25 2019-04-25 位姿数据处理方法、装置、地图生成设备和存储介质
CN201910339237.5 2019-04-25

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US17/451,838 Continuation US20220044436A1 (en) 2019-04-25 2021-10-22 Pose data processing method and system

Publications (1)

Publication Number Publication Date
WO2020216342A1 true WO2020216342A1 (zh) 2020-10-29

Family

ID=72941489

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/086784 Ceased WO2020216342A1 (zh) 2019-04-25 2020-04-24 一种位姿数据处理方法和系统

Country Status (3)

Country Link
US (1) US20220044436A1 (zh)
CN (1) CN111854769B (zh)
WO (1) WO2020216342A1 (zh)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114140526A (zh) * 2021-11-19 2022-03-04 浙江大学 一种基于深度学习的无序工件三维视觉位姿估计方法
CN114494020A (zh) * 2022-02-15 2022-05-13 国网江苏省电力工程咨询有限公司 一种电缆沟道点云数据的数据拼接方法
CN114972493A (zh) * 2021-02-26 2022-08-30 阿里巴巴集团控股有限公司 预测视觉定位置信度的方法、装置、云服务及存储介质
CN115540875A (zh) * 2022-11-24 2022-12-30 成都运达科技股份有限公司 一种用于股道内列车车辆高精度检测定位的方法及系统

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR102383567B1 (ko) * 2019-12-16 2022-04-06 네이버랩스 주식회사 시각 정보 처리 기반의 위치 인식 방법 및 시스템
US11989343B2 (en) * 2022-01-05 2024-05-21 Nokia Technologies Oy Pose validity for XR based services
CN115170617B (zh) * 2022-06-06 2026-03-24 亿咖通(湖北)技术有限公司 一种轨迹优化方法和电子设备
CN116091564B (zh) * 2022-11-16 2026-01-30 北京百度网讯科技有限公司 基于局部地图的置信度确定方法、装置、设备及存储介质
CN116229506B (zh) * 2023-02-09 2026-04-21 上海交通大学 一种三维人体姿态估计方法、系统、应用、介质及终端

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104850615A (zh) * 2015-05-14 2015-08-19 西安电子科技大学 一种基于g2o的SLAM后端优化算法方法
CN108873001A (zh) * 2018-09-17 2018-11-23 江苏金智科技股份有限公司 一种精准评判机器人定位精度的方法
CN109116397A (zh) * 2018-07-25 2019-01-01 吉林大学 一种车载多相机视觉定位方法、装置、设备及存储介质
CN109186601A (zh) * 2018-07-05 2019-01-11 南京理工大学 一种基于自适应无迹卡尔曼滤波的激光slam算法
WO2019025788A1 (en) * 2017-07-31 2019-02-07 Oxford University Innovation Limited METHOD FOR CONSTRUCTING A MOVEMENT MODEL OF A MOBILE DEVICE AND ASSOCIATED SYSTEMS
CN109443351A (zh) * 2019-01-02 2019-03-08 亿嘉和科技股份有限公司 一种稀疏环境下的机器人三维激光定位方法

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5050904B2 (ja) * 2007-04-09 2012-10-17 セイコーエプソン株式会社 現在位置測位方法及び測位装置
CN101141820B (zh) * 2007-10-22 2010-11-10 中兴通讯股份有限公司 一种3g网卡定位实现方法、装置及系统
US20170164315A1 (en) * 2011-08-18 2017-06-08 Rivada Research, Llc Method and System for Performing Trilateration for Fixed Infrastructure Nodes (FIN) Based On Enhanced Location Based Information
GB201301281D0 (en) * 2013-01-24 2013-03-06 Isis Innovation A Method of detecting structural parts of a scene
US10416679B2 (en) * 2017-06-27 2019-09-17 GM Global Technology Operations LLC Method and apparatus for object surface estimation using reflections delay spread
CN108064019B (zh) * 2017-12-29 2021-02-05 北京奇宝科技有限公司 一种智能定位方法、装置、服务器和计算机可读存储介质
CN108317949B (zh) * 2018-02-07 2020-05-15 桂林电子科技大学 一种rtk高精度差分定位形变监测系统及方法
CN108519090B (zh) * 2018-03-27 2021-08-20 东南大学—无锡集成电路技术研究所 一种基于优化的ukf算法的双通道组合定姿算法的实现方法
CN108375370B (zh) * 2018-07-02 2019-03-01 江苏中科院智能科学技术应用研究院 一种面向智能巡防无人机的复合导航系统
CN109358638B (zh) * 2018-09-10 2021-07-27 南京航空航天大学 基于分布式地图的无人机视觉避障方法
US11521329B2 (en) * 2019-11-22 2022-12-06 Baidu Usa Llc Updated point cloud registration pipeline based on ADMM algorithm for autonomous vehicles
CN117367419A (zh) * 2022-06-29 2024-01-09 深圳市海柔创新科技有限公司 机器人定位方法、装置和计算可读存储介质

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104850615A (zh) * 2015-05-14 2015-08-19 西安电子科技大学 一种基于g2o的SLAM后端优化算法方法
WO2019025788A1 (en) * 2017-07-31 2019-02-07 Oxford University Innovation Limited METHOD FOR CONSTRUCTING A MOVEMENT MODEL OF A MOBILE DEVICE AND ASSOCIATED SYSTEMS
CN109186601A (zh) * 2018-07-05 2019-01-11 南京理工大学 一种基于自适应无迹卡尔曼滤波的激光slam算法
CN109116397A (zh) * 2018-07-25 2019-01-01 吉林大学 一种车载多相机视觉定位方法、装置、设备及存储介质
CN108873001A (zh) * 2018-09-17 2018-11-23 江苏金智科技股份有限公司 一种精准评判机器人定位精度的方法
CN109443351A (zh) * 2019-01-02 2019-03-08 亿嘉和科技股份有限公司 一种稀疏环境下的机器人三维激光定位方法

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
TAO WANG: "Research on Localization Method for Autonomous Driving Vehicle", CHINESE MASTER’S THESES FULL-TEXT DATABASE, 1 April 2017 (2017-04-01), pages 1 - 94, XP055745908 *
ZI-RUI WU: "Analysis and Research on Blind Guiding Robot Localization and Orientation Based on Multi-Sensor Fusion", CHINESE MASTER’S THESES FULL-TEXT DATABASE, 1 May 2015 (2015-05-01), pages 1 - 74, XP055745889 *

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114972493A (zh) * 2021-02-26 2022-08-30 阿里巴巴集团控股有限公司 预测视觉定位置信度的方法、装置、云服务及存储介质
CN114140526A (zh) * 2021-11-19 2022-03-04 浙江大学 一种基于深度学习的无序工件三维视觉位姿估计方法
CN114494020A (zh) * 2022-02-15 2022-05-13 国网江苏省电力工程咨询有限公司 一种电缆沟道点云数据的数据拼接方法
CN115540875A (zh) * 2022-11-24 2022-12-30 成都运达科技股份有限公司 一种用于股道内列车车辆高精度检测定位的方法及系统
CN115540875B (zh) * 2022-11-24 2023-03-07 成都运达科技股份有限公司 一种用于股道内列车车辆高精度检测定位的方法及系统

Also Published As

Publication number Publication date
CN111854769A (zh) 2020-10-30
CN111854769B (zh) 2022-07-22
US20220044436A1 (en) 2022-02-10

Similar Documents

Publication Publication Date Title
WO2020216342A1 (zh) 一种位姿数据处理方法和系统
Wen et al. Factor graph optimization for GNSS/INS integration: A comparison with the extended Kalman filter
US10659925B2 (en) Positioning method, terminal and server
US10878243B2 (en) Method, device and apparatus for generating electronic map, storage medium, and acquisition entity
WO2022127532A1 (zh) 一种激光雷达与imu的外参标定方法、装置及设备
US12412286B2 (en) Point cloud registration method, apparatus, device and storage medium
CN109410735B (zh) 反射值地图构建方法和装置
US10086955B2 (en) Pattern-based camera pose estimation system
CN109407073B (zh) 反射值地图构建方法和装置
CN110989619B (zh) 用于定位对象的方法、装置、设备和存储介质
CN110764111A (zh) 雷达坐标与大地坐标的转换方法、装置、系统及介质
US10451403B2 (en) Structure-based camera pose estimation system
CN110609290A (zh) 激光雷达匹配定位方法及装置
Mu et al. A GNSS/INS-integrated system for an arbitrarily mounted land vehicle navigation device
US9858669B2 (en) Optimized camera pose estimation system
CN115326084A (zh) 车辆定位方法、装置、计算机设备、存储介质
CN112362054A (zh) 一种标定方法、装置、电子设备及存储介质
US20170350708A1 (en) Using of a novel map to improve performance of indoor positioning system
CN115032672A (zh) 一种基于定位子系统的融合定位方法及系统
US20210048512A1 (en) Apparatus and method for efficient scanner trajectory reconstruction from mobile lidar point cloud
Chiang et al. Multifusion schemes of INS/GNSS/GCPs/V-SLAM applied using data from smartphone sensors for land vehicular navigation applications
Yang et al. Robust navigation system for UGV based on the IMU/vision/geomagnetic fusion: C. Yang et al.
CN115327476B (zh) 远场时差定位条件下布站方法及系统
WO2024139465A1 (zh) 定位信息处理方法、装置、设备和介质
O’Connor et al. Low-latency GNSS multipath simulation and building wall detection in urban environments

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: 20794536

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20794536

Country of ref document: EP

Kind code of ref document: A1