WO2022160790A1 - 一种三维地图的构建方法及装置 - Google Patents

一种三维地图的构建方法及装置 Download PDF

Info

Publication number
WO2022160790A1
WO2022160790A1 PCT/CN2021/124676 CN2021124676W WO2022160790A1 WO 2022160790 A1 WO2022160790 A1 WO 2022160790A1 CN 2021124676 W CN2021124676 W CN 2021124676W WO 2022160790 A1 WO2022160790 A1 WO 2022160790A1
Authority
WO
WIPO (PCT)
Prior art keywords
coordinate system
real
local
sta
dimensional map
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/CN2021/124676
Other languages
English (en)
French (fr)
Inventor
郑月
王伟杰
杨师华
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.)
Huawei Technologies Co Ltd
Original Assignee
Huawei Technologies 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 Huawei Technologies Co Ltd filed Critical Huawei Technologies Co Ltd
Priority to KR1020237028996A priority Critical patent/KR20230137395A/ko
Priority to EP21922381.5A priority patent/EP4283567A4/en
Priority to JP2023546328A priority patent/JP2024509690A/ja
Publication of WO2022160790A1 publication Critical patent/WO2022160790A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T17/00—Three-dimensional [3D] modelling for computer graphics
    • G06T17/05—Geographic models
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/86—Combinations of lidar systems with systems other than lidar, radar or sonar, e.g. with direction finders
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/88—Lidar systems specially adapted for specific applications
    • G01S17/89—Lidar systems specially adapted for specific applications for mapping or imaging
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/50—Depth or shape recovery
    • G06T7/55—Depth or shape recovery from multiple images
    • G06T7/579—Depth or shape recovery from multiple images from motion
    • 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
    • G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10016—Video; Image sequence
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10024—Color image
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10028—Range image; Depth image; 3D point clouds
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30244—Camera pose

Definitions

  • the embodiments of the present application relate to the field of communication technologies, and in particular, to a method and apparatus for constructing a three-dimensional map.
  • SLAM simultaneous localization and mapping
  • SLAM mainly includes visual SLAM and laser SLAM.
  • visual SLAM is affected by factors such as light intensity and background texture, which may lead to low map accuracy.
  • laser SLAM can obtain relatively accurate positioning information of the detection target, it cannot obtain the texture and color of the detection target. and other scene information, which will lead to the problem of poor visualization of the map.
  • Embodiments of the present application provide a method and device for constructing a three-dimensional map, which are used to construct a more accurate and complete three-dimensional map and improve the accuracy of real-time positioning and navigation.
  • an embodiment of the present application provides a method for constructing a three-dimensional map, the method comprising: acquiring a current global point cloud map by a three-dimensional map constructing device; During the process, a plurality of pieces of image data are collected by the local collection device arranged on the movable device; and the three-dimensional map construction device determines the collection time corresponding to each piece of image data collected by the local collection device , the real-time pose information of the local collection device; the three-dimensional map construction device performs a three-dimensional map based on the current global point cloud map, the multiple image data and the real-time pose information of the local collection device Construct.
  • the current global point cloud map is obtained by using the top-down angle, which can complement each other with the local image data collected by the local collection device, thereby improving the integrity of the constructed three-dimensional map and improving the construction time of the three-dimensional map. robustness. Therefore, compared with the existing implementation of SLAM based only on collected sensor data, it may result in fewer collected features, resulting in inaccurate technical problems in the constructed three-dimensional map. method, which can improve the accuracy of 3D map construction.
  • the three-dimensional map is constructed under a specified coordinate system, and the specified coordinate system is any one of the following coordinate systems: the first coordinate determined by the pose of the global acquisition device at the initial moment system, a second coordinate system determined by the pose of the local acquisition device at the initial moment, a world coordinate system, and a third coordinate system determined by the pose of any fixed point in space.
  • the three-dimensional map construction device constructs a three-dimensional map based on the current global point cloud map, the multiple pieces of image data and the real-time pose information of the local acquisition device, which may be implemented to determine the current global point.
  • the transformation relationship is determined according to the pose relationship between the original coordinate system and the coordinate origin of the specified coordinate system.
  • the map under the original coordinate system is determined.
  • the data includes one or more of the current global point cloud map, the multiple pieces of image data and the real-time pose information of the local acquisition device; based on the current global point in the specified coordinate system
  • the cloud map, the multiple pieces of image data and the real-time pose information of the local collecting device construct a three-dimensional map, and obtain a three-dimensional map in the specified coordinate system.
  • the device for constructing a three-dimensional map can construct the three-dimensional map in any coordinate system, which facilitates real-time positioning and navigation based on the constructed three-dimensional map.
  • the coordinate conversion of any spatial point in the map data between different coordinate systems it can be determined according to the pose of the coordinate origin of the coordinate system, so as to obtain the conversion relationship between the different coordinate systems. Therefore, when the present application is implemented, the global point cloud map collected by the global collection device and the image data collected by the local collection device can be realized, thereby improving the integrity and accuracy of the constructed three-dimensional map.
  • the relative pose of the global collection device and the AP is fixed, the relative pose of the local collection device to the STA is fixed, and the AP communicates with the STA.
  • the original coordinate system different from the designated coordinate system is the first coordinate system
  • the designated coordinate system is the second coordinate system
  • the conversion relationship is the first conversion relationship
  • the The apparatus for constructing the three-dimensional map determines the first conversion relationship according to the following methods: determining the first conversion matrix according to the relative pose between the global acquisition apparatus and the AP, and determining the first conversion matrix according to the positioning result of the AP on the STA.
  • Two transformation matrices, a third transformation matrix is determined according to the relative pose of the STA and the local acquisition device; based on the product of the first transformation matrix, the second transformation matrix and the third transformation matrix, the obtained Describe the first conversion relationship.
  • the transformation relationship between the coordinate system of the global acquisition device and the initial local acquisition device coordinate system can be obtained, so that the coordinate transformation of the global point cloud map or local image data can be realized.
  • a more accurate and complete three-dimensional map can be obtained compared with the prior art.
  • the present application can reduce the amount of calculation, and the accuracy of the positioning result based on the AP to the STA can be guaranteed. .
  • the device for constructing the three-dimensional map determines the acquisition time corresponding to the acquisition of each piece of image data by the local acquisition device, and the real-time pose information of the local acquisition device may be obtained by acquiring At each acquisition time corresponding to each piece of the image data is collected, the real-time positioning result of the AP on the STA; based on the initial positioning result of the AP on the STA at the initial time, the The initial pose information of the STA under the fourth coordinate system and the real-time positioning result, and the real-time pose information of the STA under the fourth coordinate system at each collection moment is obtained, wherein the fourth coordinate system The origin of the coordinates is determined by the pose of the STA at the initial moment; according to the real-time pose information of the STA in the fourth coordinate system and the third transformation matrix, it is determined that the local acquisition device is in the fourth coordinate system Real-time pose information under the four-coordinate system; coordinate transformation of the real-time pose information of the local collection device under the fourth coordinate system to obtain the real-time pose of
  • the real-time pose information of the local collection device at each collection moment is obtained after coordinate transformation of the real-time positioning result of the STA based on the AP, so there is no need to rely on other image data collected in adjacent times.
  • the method of estimating the real-time pose of the robot by performing feature matching on image data in adjacent time may have the disadvantage of time accumulation error, so that the accuracy of the constructed three-dimensional map can be improved.
  • the apparatus for constructing the three-dimensional map detects a loopback abnormality existing in the moving process of the movable device based on the real-time positioning result of the STA by the AP.
  • the AP performs loopback detection on the positioning result of the STA through the AP, which can improve the construction efficiency of the 3D map, and improve the efficiency of the construction of the 3D map. Robustness of loop closure detection in textured environments (such as white walls).
  • the device for constructing a three-dimensional map before the device for constructing a three-dimensional map acquires a plurality of pieces of image data collected by the local acquisition device during the movement of the movable device, the device for constructing a three-dimensional map is based on the current The global point cloud map plans a moving path for the movable device; the three-dimensional map construction device generates a movement instruction according to the real-time pose information of the local acquisition device and the moving path; the three-dimensional map construction device provides the The controller of the movable device sends the movement instruction, so that the controller controls the movable device to move according to the movement instruction.
  • the moving path is planned for the movable device based on the current global point cloud map obtained through the acquisition, and then based on the real-time pose information of the local acquisition device, the movable device can be moved within the movable moving path.
  • the movement instruction can avoid the blind movement of the movable device, so it can improve the efficiency and accuracy of the three-dimensional map construction.
  • an embodiment of the present application provides an apparatus for constructing a three-dimensional map, where the apparatus includes a transceiver unit and a processing unit.
  • the functions performed by the transceiver unit and the processing unit may correspond to the steps performed by the apparatus for constructing a three-dimensional map involved in any possible design or implementation of the first aspect.
  • an embodiment of the present application further provides a computing device, the computing device includes one or more processors and a memory, the memory is coupled to the processor, the memory stores computer program code, the memory Computer program code includes computer instructions.
  • the processor executes computer instructions in the memory to perform the method provided in any possible design of the first aspect above.
  • the computing device may also include a display screen. The display screen is used to display information to the user under the trigger of the processor, such as the global point cloud map collected by the global collection device, or the image data collected by the local collection device, and the like.
  • the computing device further includes a communication interface to which the processor is coupled.
  • the communication interface may be a transceiver or an input/output interface; when the computing device is a chip included in a network device, the communication interface may be an input/output interface of the chip.
  • the transceiver may be a transceiver circuit, and the input/output interface may be an input/output circuit.
  • an embodiment of the present application further provides a computing device cluster, including at least one computing device as provided in the third aspect.
  • embodiments of the present application further provide a computer storage medium, where a computer program is stored in the computer storage medium, and when the computer program is executed by a computer, the method provided in any possible design of the first aspect is enabled. is realized.
  • an embodiment of the present application further provides a computer program product, the computer program product comprising: computer program code, when the computer program code is executed by the processor of the communication device, the communication device is made to execute any one of the above-mentioned first aspects. method in a possible design.
  • an embodiment of the present application further provides a chip for reading and executing a software program stored in a memory, so as to implement the method in any possible design of the foregoing first aspect.
  • the memory may be connected to the chip, or the memory may also be built in the chip.
  • FIG. 1 is a schematic flowchart of a SLAM system
  • FIG. 2 is an application scenario diagram of a method for constructing a three-dimensional map in an embodiment of the present application
  • FIG. 3 is an interactive schematic diagram of a method for constructing a three-dimensional map in an embodiment of the present application
  • FIG. 4 is a schematic flowchart of a method for constructing a three-dimensional map in an embodiment of the present application
  • FIG. 5 is a schematic structural diagram of an apparatus for constructing a three-dimensional map in an embodiment of the present application.
  • FIG. 6 is a schematic structural diagram of another apparatus for constructing a three-dimensional map in an embodiment of the present application.
  • FIG. 7 is a schematic structural diagram of a chip provided in an embodiment of the present application.
  • the embodiments of the present application can be applied to scenarios such as real-time positioning and navigation of a movable device during autonomous movement.
  • movable devices such as sweeping robots, food delivery robots, delivery robots, mobile trolleys, logistics trolleys, etc.
  • This application does not make any limitation on the specific type of applicable removable device.
  • SLAM technology is mainly used to construct 3D maps in the existing technology.
  • 3D maps may have problems such as low accuracy due to time accumulation errors, and incomplete 3D maps due to blind spots of sight.
  • the embodiments of the present application provide a method for constructing a three-dimensional map, which can construct a three-dimensional map by combining a global point cloud map, multiple local image data, and real-time pose information of a local acquisition device, thereby realizing Complementary blindness of global point cloud map and local image data to build a more accurate and complete 3D map.
  • FIG. 1 is a schematic flowchart of a SLAM system.
  • SLAM technology can be understood as: the mobile robot starts from an unknown location in an unknown environment, and during the moving process, performs its own positioning according to the position estimation and map, and at the same time builds an incremental map on the basis of its own positioning to realize the autonomous positioning and navigation.
  • the SLAM system mainly includes several functions of sensor data acquisition 101 , odometer 102 , loopback detection 103 , nonlinear optimization 104 and map building 105 . Among them, the main realization of each function is as follows:
  • the sensor data collection 101 is used to collect sensor data required in the process of constructing a map.
  • the sensor data includes, but is not limited to, image data, laser point cloud information, inertial sensor data, and the like.
  • sensor data can be image data collected by visual sensors such as cameras and cameras;
  • laser SLAM sensor data can be laser point clouds obtained by lidar, or images based on laser point clouds Wait.
  • the odometer 102 is used for estimating the pose change of the robot and establishing a local three-dimensional map.
  • the pose change includes translation information and rotation information.
  • laser SLAM and visual SLAM are mainly matched and compared according to the sensor data in adjacent time, and then the pose of the robot can be estimated.
  • the process of calculating the odometer since the estimated robot pose is obtained based on the change of the robot's pose in adjacent time, there may be a large time accumulation error, which will lead to the construction of the three-dimensional map. Accuracy is reduced.
  • the loopback detection 103 is used for judging whether the current position of the robot is a position that has been reached before, and if it is judged that there is a loopback, the loopback information is used for nonlinear optimization 104 to correct the drift of the odometer.
  • the nonlinear optimization 104 is used to optimize the robot pose obtained by the odometer 102 and the loopback information of the loopback detection 103 in different time periods, mainly by optimizing the robot pose and map to obtain a global consistency robot movement trajectory.
  • the map building 105 is used to build a complete global three-dimensional map according to the movement trajectory of the robot and a plurality of local three-dimensional maps established by the odometer 102 .
  • the constructed global three-dimensional map includes, but is not limited to, a sparse map, a dense map, a semantic map, etc., which is not limited in this application.
  • the way of constructing a map through visual SLAM is greatly affected by the accuracy of image feature matching. There are few features extracted from the data, which may lead to inaccurate pose tracking and unmatched maps.
  • the method of constructing a map through laser SLAM has the disadvantage of poor visualization.
  • the height of the robot is limited, there is also the problem of incomplete map construction because the information of the occluded objects at high places cannot be obtained.
  • the embodiments of the present application provide a method for constructing a three-dimensional map.
  • the embodiments of the present application may be applicable to a three-dimensional map construction scene.
  • the three-dimensional map construction scene may be the first construction of the three-dimensional map, or the reconstruction of the three-dimensional map; and may be the construction of an indoor three-dimensional map, or the construction of an outdoor three-dimensional map.
  • the construction of the indoor 3D map can be, for example, the construction of the indoor 3D map by the sweeping robot, the construction of the warehouse 3D map by the mobile car, etc.
  • the construction of the outdoor 3D map can be, for example, the construction of the 3D map of the park by the logistics trolley of the park, etc. This application This is not limited.
  • FIG. 2 is an application scenario diagram of a method for constructing a three-dimensional map provided by an embodiment of the present application.
  • the application scenario may include: a global collection device 201 , an access point (AP) 202 , a workstation (station, STA) 203 , and a local collection device 204 .
  • AP access point
  • STA workstation
  • local collection device 204 a local collection device
  • the global collection device 201 may be set at the same height as the roof to collect the global point cloud map under the target scene; or, if the present application is applied to the construction of an outdoor three-dimensional map In a scenario, the global collection device 201 may be installed at a height such as a wall, a utility pole, etc. The present application does not limit the installation manner of the global collection device 201 .
  • the global acquisition device 201 may be a depth sensor, and the depth sensor includes, but is not limited to, a laser radar based on ranging laser, a depth camera, a depth camera, and the like.
  • the AP 202 is used to locate the workstation STA 203 to obtain the positioning result of the STA, so that the real-time pose information of the STA can be determined.
  • the AP 202 can receive the access of one or more STAs 203 based on the optical communication technology, and can also receive the access of one or more STAs 203 through the wireless technology.
  • the optical communication technology for communication between the AP 202 and the STA 203 includes but is not limited to light fidelity technology (light fidelity, Li-Fi), visible light communication technology (visible light communication, VLC), free space optical communication (free-space optical communication technology) space optical communication, FSO) and so on.
  • the AP 202 and the global acquisition device 201 may be two independent devices, for example, an AP device and a depth sensor; or, the AP 202 and the global acquisition device 201 may also be included in an integrated device, for example , there is an integrated device, including a unit that can realize the function of the global collection device 201, and a unit that can realize the function of the AP 202 at the same time; or, the global collection device 201 can also be integrated in the AP 202, which is not limited in this application.
  • the local collection device 204 can be provided on the movable device, or integrated in the movable device.
  • the local acquisition device 204 is used to acquire a plurality of different image data during the movement of the movable device.
  • the local collection device 204 may be a monocular camera, a binocular camera, a red-green-blue depth (RGBD) camera, etc., which is not limited in this application.
  • RGBD red-green-blue depth
  • the application scenario also includes: the upper computer 205 (which may include 205a or 205b in FIG. 2 ) and the cloud server 206 .
  • the host computer 205a is used to obtain the data of the global acquisition device 201 and the AP 202, and processes and calculates the received data, so as to realize the display of the global point cloud map and the issuance of control instructions.
  • the global point cloud map collected by the global collection device 201 is subjected to coordinate transformation processing, and based on the global point cloud map, the moving path planning of the movable device is realized, and the like.
  • the host computer 205b is used to obtain the data of the local acquisition device 204 and the STA 203, and the received data is processed and calculated to realize the display of local image data and the issuance of control instructions, etc.
  • the host computer 205b can be set in the movable device, can realize autonomous movement control of the movable device, and act as the controller of the movable device.
  • the division of modules in the embodiments of the present application is schematic, and is only a logical function division. In actual implementation, there may be other division methods.
  • each functional unit in each embodiment of the present application It can be integrated in one processing unit, or it can exist physically alone, or two or more units can be integrated in one unit.
  • the upper computer 205b can be integrated inside the movable device, or it can be a separate physical exist.
  • the above-mentioned integrated units may be implemented in the form of hardware, or may be implemented in the form of software functional units.
  • the methods provided in the embodiments of the present application may be implemented by the host computer 205a connected to the global collection device 201, or by the host computer 205b connected by the local acquisition device 204, or by the cloud server 206, or even by the host computer and the host computer 205b.
  • the coordination and division of labor of the cloud server is realized, that is, one or a combination of the upper computer 205a, the upper computer 205b or the cloud server can be used as a construction device for a three-dimensional map that implements the method provided by the present application.
  • the implementation can be determined according to the computing capability of each device and/or the actual scene. For example, if the computing capability of the host computer 205a can support the implementation of the method provided by the present application, the method provided by the present application can be implemented by the host computer 205a. This is not limited.
  • each device included in the application scenario may be different.
  • FIG. 3 is an interactive schematic diagram of a method for constructing a three-dimensional map according to an embodiment of the present application.
  • the interaction flow includes the following steps:
  • the apparatus for constructing a three-dimensional map acquires a current global point cloud map.
  • the global point cloud map can be acquired by the global acquisition device 201 .
  • the global point cloud map represents a large viewing angle range in the target scene that needs to build a 3D map.
  • the global point cloud map can be from taken from a camera in a room.
  • the current global point cloud map can be acquired in real time or periodically, so that the changes in the target scene can be known in time, so that a structure that can better reflect this can be constructed. time-accurate 3D maps.
  • composition of the device for constructing the three-dimensional map can be determined according to the actual situation, and can be implemented by one or a combination of the host computer 205a, the host computer 205b or the cloud server 206 in FIG. 2 . This is not limited.
  • the global point cloud map can be applied to the moving path planning of the movable device.
  • the area of the walkable road surface in the target scene is determined, and then a moving path can be planned for the movable device in the area of the walkable road surface.
  • the device for constructing the three-dimensional map can also determine the real-time pose of the local acquisition device, thereby determining the orientation of the local acquisition device, that is, the movement direction of the mobile device. Then, the apparatus for constructing the three-dimensional map may generate a movement instruction according to the movement direction of the movable device in the determined area of the traversable road surface.
  • the three-dimensional map construction apparatus can send the movement instruction to the controller of the movable device, for example, the movable device can be the cart in FIG. 2, and the controller can be, for example, the upper computer 205b on the cart in FIG.
  • the upper computer 205b controls the movable device to move according to the movement instruction.
  • the three-dimensional map constructing apparatus acquires multiple pieces of image data collected by the local collecting apparatus disposed on the movable equipment during the movement of the movable equipment.
  • the local capture device can be set on the movable device, the local capture device can move with the movement of the movable device, so that the local capture device can capture multiple different images during the movement of the movable device.
  • the local collecting device can periodically collect image data, for example, one image data is collected every 10S; or, the local collecting device can also collect one image data after the movable device moves a specified distance each time. Not limited.
  • the three-dimensional map construction device determines the real-time pose information of the local acquisition device at the acquisition time corresponding to the acquisition of each piece of the image data by the local acquisition device.
  • the odometer 102 is used to perform feature matching on the adjacent image data collected by the local collection device to estimate the pose change of the local collection device.
  • the odometer 102 is used to perform feature matching on the adjacent image data collected by the local collection device to estimate the pose change of the local collection device.
  • the positioning information of the STA can be obtained in real time based on the AP.
  • the relative pose of the AP and the global collection device is set to be fixed, and the relative pose of the STA and the local collection device is set to be fixed. Therefore, The real-time pose information of the STA can be determined through the real-time positioning result of the STA by the AP. Then, since the relative pose between the STA and the local collection device is fixed, the real-time pose information of the local collection device can be further determined based on the real-time pose information of the STA. It should be noted that, in general scenarios, the poses of the global collection device and AP are set to be fixed at different times, while the local collection device and STA are set on movable devices, so the pose information of the local collection device and AP changes. .
  • the three-dimensional map construction device constructs a three-dimensional map based on the current global point cloud map, the multiple pieces of image data, and the determined multiple real-time pose information.
  • the three-dimensional map can be constructed under the specified coordinate system.
  • the specified coordinate system may be any of the following coordinate systems: a first coordinate system (also referred to as a global acquisition device coordinate system) determined by the pose of the global acquisition device at the initial moment, a The second coordinate system determined by the pose of the local acquisition device at the initial moment (also referred to as the initial local acquisition device coordinate system), the world coordinate system, and the third coordinate system determined by the pose of any fixed point in space (for example, The AP coordinate system determined by the pose of the AP introduced in the foregoing content, etc.).
  • the pose includes position and attitude, that is, three-dimensional coordinates and orientation.
  • the initial moment can be expressed as any moment when the movable device is in a stationary state in the target scene, or it can also be any moment when the three-dimensional map construction device selects from the movable device during the moving process.
  • the selection of is not limited, mainly to select a relative pose device of the global acquisition device and the local acquisition device at the same time as the basic conversion relationship.
  • the steps are as follows:
  • Step A1 The three-dimensional map construction device determines the original coordinate system where the current global point cloud map, the multiple pieces of image data and the real-time pose information of the local acquisition device are located respectively.
  • the global point cloud map collected by the global collecting device 201 is in the coordinate system of the global collecting device.
  • the image data collected by the local collection device 204 is in the real-time local collection device coordinate system determined by the real-time pose of the local collection device.
  • the real-time pose information of the local collection device can be determined by the real-time pose information of the STA, so the real-time pose information of the local collection device is in the real-time STA coordinate system determined by the real-time pose of the STA.
  • Step A2 For an original coordinate system different from the designated coordinate system, coordinate transformation is performed on the map data in the original coordinate system based on the conversion relationship, to obtain map data in the designated coordinate system.
  • the conversion relationship is determined according to the pose relationship between the original coordinate system and the coordinate origin of the designated coordinate system, and the map data in the original coordinate system includes the current global point cloud map, the multiple One or more of image data and real-time pose information of the local acquisition device.
  • the specified coordinate system is the initial local acquisition device coordinate system
  • the original coordinate system of the global point cloud map is the global acquisition device coordinate system
  • the first conversion relationship from the global acquisition device coordinate system to the initial local acquisition device coordinate system is obtained, based on this
  • the first transformation relationship performs coordinate transformation on the global point cloud map in the coordinate system of the global acquisition device
  • the global point cloud map in the coordinate system of the initial local acquisition device is obtained.
  • the first conversion relationship for converting the global point cloud map of the global acquisition device coordinate system to the initial local acquisition device coordinate system can be obtained through the content described below.
  • the homogeneous coordinates of any point in the space in the global acquisition device coordinate system can be expressed as [X L , Y L , Z L , 1] T
  • the homogeneous coordinates of the point in the initial local acquisition device coordinate system can be expressed as [X C , Y C , Z C , 1] T
  • the coordinate transformation relationship of this point between the global acquisition device coordinate system and the initial local acquisition device coordinate system can be expressed by the following formula 1:
  • the matrix R 3*3 is a rotation matrix, which is used to represent the transformation of the orientation angle between the global acquisition device coordinate system and the initial local acquisition device coordinate system
  • the matrix T 3*1 is a translation vector, which is used to represent the transformation of three-dimensional coordinates between the global acquisition device coordinate system and the initial local acquisition device coordinate system.
  • the matrix R 3*3 ′ is the inverse matrix of the matrix R 3*3 in formula 1
  • the matrix T 3*1 ′ is the inverse of the product of the inverse matrix of the matrix R 3*3 and the translation vector T 3*1 in formula 1
  • the specific expression can refer to the following formula 3. It can be understood that the above formula 2 is the inverse process of formula 1.
  • the first transformation relationship for converting any spatial point from the global acquisition device coordinate system to the initial local acquisition device coordinate system, and the conversion of any spatial point from the initial local acquisition device coordinate system to the global acquisition device coordinate system can be obtained.
  • Collect the second transformation relationship in the coordinate system of the device thus, convenient coordinate conversion between different coordinate systems can be realized.
  • the coordinate transformation relationship from the global acquisition device coordinate system to the initial local acquisition device coordinate system can be determined based on the initial positioning result of the AP on the STA at the initial moment, and the specific implementation can be determined by three transformation matrices, as follows:
  • the first transformation matrix is determined according to the relative pose between the global acquisition device and the AP. Wherein, based on the fixed relative pose between the global acquisition device and the AP, it can be obtained that the first transformation matrix is a fixed matrix. It should be noted that no matter which way the global collection device and the AP are implemented, for example, the independent way described in the foregoing content, being included in the integrated device, or the global collection device being included in the AP; since the global collection device and the AP are included in the The origin of the coordinates of the light-emitting device (that is, the module used for optical communication) is different. In order to obtain a more accurate conversion relationship, the global acquisition device and the AP are represented based on the coordinate origin of the global acquisition device and the coordinate origin of the light-emitting device of the AP. relative pose between.
  • the first transformation matrix can be determined by the matrix To represent.
  • the second transformation matrix is determined according to the relative pose between the AP and the STA, and can be determined by the matrix To represent.
  • the apparatus for constructing the three-dimensional map may determine the relative pose between the AP and the STA based on the positioning result of the AP on the STA, and then determine the second transformation matrix.
  • the positioning result of the STA by the AP can be determined by the matrix
  • the determination of the second transformation matrix based on the positioning result of the AP on the STA can be expressed by the following formula 3:
  • the third transformation matrix is determined according to the relative pose between the STA and the local acquisition device. Wherein, the relative pose between the STA and the local acquisition device is fixed, so that it can be obtained that the third transformation matrix is also a fixed matrix.
  • the third transformation matrix can be obtained by using the matrix To represent.
  • the conversion relationship between the global acquisition device and the local acquisition device can be obtained.
  • the conversion relationship can be determined, for example, by the following formula 4:
  • the manner in which the apparatus for constructing the three-dimensional map determines the conversion relationship may also be implemented based on the aid of the calibration object.
  • calibration objects such as checkerboards and targets can be placed in the target scene.
  • the acquisition areas of the global acquisition device and the local acquisition device include a common field of view, which can also be understood as two. Both can collect calibration information.
  • the following describes how to determine the real-time pose information of the local acquisition device in the specified coordinate system based on the real-time positioning result of the STA by the AP.
  • a fourth coordinate system (also referred to as an initial STA coordinate system) is established with the initial pose of the STA at the initial moment, then the STA is at the coordinate origin of the initial STA coordinate system at this time, and the initial pose information of the STA may be Expressed as
  • the matrix I 3*3 is represented as a matrix whose coordinate system is consistent with the orientation of the STA.
  • the third conversion matrix from the STA to the local acquisition device is: Then the initial pose of the local acquisition device in the initial STA coordinate system can be expressed as And, the device for constructing the three-dimensional map can also determine that the pose of the STA in the AP coordinate system (that is, the coordinate system established with the pose of the AP at the initial moment as the coordinate origin) is the initial positioning result of the STA by the AP. To represent.
  • the three-dimensional map construction device determines the real-time pose information of the local acquisition device in the initial local acquisition device coordinate system through the following steps:
  • Step B1 the three-dimensional map construction device determines the real-time positioning result of the AP to the STA at time t1, assuming that the To represent.
  • step B2 the three-dimensional map construction device performs coordinate transformation on the STA in the AP coordinate system to obtain the real-time pose information of the STA in the initial STA coordinate system. To represent.
  • Step B3 the three-dimensional map construction device determines the real-time pose of the local acquisition device under the initial STA coordinate system according to the real-time pose information of the STA under the initial STA coordinate system and the third transformation matrix information.
  • the relative pose of the local acquisition device compared to the STA at time t1 can be determined by the initial pose of the local acquisition device in the initial STA coordinate system at the initial time. Then at time t1, the real-time pose of the local acquisition device in the initial STA coordinate system is updated as
  • Step B4 Perform coordinate transformation on the real-time pose information of the local acquisition device in the initial STA coordinate system to obtain real-time pose information of the local acquisition device in the initial local acquisition device coordinate system.
  • the real-time pose information of the local collection device in the initial local collection device coordinate system can be determined by the product of the third transformation matrix and the real-time pose information of the local collection device in the initial STA coordinate system, which can be expressed as the following example :
  • the conversion relationship is acquired in a calibrator-assisted manner, it can be based on the positioning result of the AP on the STA, the acquired conversion relationship, the first conversion matrix between the global acquisition device and the AP, and the STA and the local
  • the second transformation matrix between the collection devices determines the real-time pose information of the local collection devices.
  • the real-time pose information of the local collection device at each collection moment is obtained after coordinate transformation of the real-time positioning result of the STA based on the AP, so there is no need to rely on other image data collected in adjacent times.
  • time accumulation error There is a disadvantage of time accumulation error that may exist in the technology.
  • Step A3 The three-dimensional map construction device constructs the three-dimensional map based on the current global point cloud map, the multiple pieces of image data and the real-time pose information of the local acquisition device under the specified coordinate system, and obtains the Describe the 3D map in the specified coordinate system.
  • the apparatus for constructing the three-dimensional map realizes the loopback detection, it can directly determine whether there is a loopback abnormality in the moving process of the movable device through the positioning result of the STA by the AP, and, In a specific implementation, the apparatus for constructing a three-dimensional map can also perform loop closure anomaly detection in combination with feature matching of image data at the same time.
  • the similarity between different image data can only be compared by extracting a series of features from sensor data, and then combining the bag of words method.
  • the three-dimensional map construction device performs loopback detection on the positioning result of the STA through the AP, which can improve the construction efficiency of the three-dimensional map.
  • the apparatus for constructing a three-dimensional map constructs a three-dimensional map by using the method provided by the embodiment of the present application
  • the embodiment of the present application needs to use the STA and the AP for processing, it needs to determine whether the STA included in the movable device is online. If the STA is not online, traditional SLAM can be performed directly using image data collected by the local collection device. For example, if the local collection device is an RGBD camera, visual SLAM can be performed based on the image data collected by the RGBD camera.
  • the map construction device can obtain the global point cloud map, after optimizing the obtained real-time pose information and loopback anomalies of the local acquisition device based on the nonlinear optimization 104, the map construction 105 can be used. Build a 3D map.
  • the processing of the nonlinear optimization 104 function in this embodiment of the present application may refer to the optimization method in the SLAM system, which will not be repeated in this application.
  • FIG. 4 is a schematic flowchart of a method for constructing a three-dimensional map provided by the embodiment of the present application.
  • the method provided by the present application further includes several functions of global point cloud map acquisition 401 , coordinate transformation 402 , moving path planning 403 , movement instruction generation 404 and positioning information acquisition 405 .
  • the main realization of each function newly added in this application is as follows:
  • the global point cloud map acquisition 401 indicates that the global acquisition device acquires the current global point cloud map.
  • the coordinate transformation 402 represents the coordinate transformation of the current global point cloud map, the multiple pieces of image data, and the map data that does not belong to the specified coordinate system in the real-time pose information of the local acquisition device to obtain the specified coordinate system. map data below.
  • the transformation of the global point cloud map from the global acquisition device coordinate system to the initial local acquisition device coordinate system is used as an example for description. If the implementation is to convert the local image data from the local acquisition coordinate system to the global acquisition device coordinate system, the coordinate conversion 402 can perform coordinate conversion processing based on the local image data obtained by the sensor data acquisition 101 .
  • the moving path planning 403 indicates that a moving path can be planned for the movable device based on the global point cloud map, so as to avoid blind movement of the movable device.
  • the movement instruction generation 404 is used to represent a movement instruction generated for the movable device based on the movement path and the pose of the local acquisition device, thereby controlling the movement of the movable device.
  • the positioning information acquisition 405 represents the acquisition of the positioning result of the STA by the AP, which can be used to perform the loopback detection 103 to improve the construction efficiency of the three-dimensional map.
  • the obtained positioning information can also be used as input information of the odometer 102 together with the collected sensor data and the global point cloud map, so as to improve the accuracy of the estimation of the real-time pose information of the local collecting device.
  • the host computer 205 cannot support the processing requirements of the calculation amount of the odometer 102, the nonlinear optimization 104, etc. in combination with the global point cloud map, then the obtained The global point cloud map can also be directly used for map building 105. In this way, the global point cloud map and the local three-dimensional map can be fused together, and mutual blindness can also be complemented to obtain a more complete global three-dimensional map.
  • the specific fusion method of map and traditional SLAM is not limited.
  • the present application jointly constructs a three-dimensional map by combining the global point cloud map collected from a top-down perspective, and by combining the optical communication between the AP and the STA, a relatively accurate conversion relationship can be obtained, It provides a guarantee for constructing a three-dimensional map, and can reduce the probability that the constructed three-dimensional map is incomplete due to the existence of a collection blind area in a local acquisition device.
  • the global point cloud map can also plan the movement path of the movable device, thereby avoiding the blind movement of the movable device in the target scene, thereby improving the construction efficiency of the 3D map.
  • an embodiment of the present application further provides a three-dimensional map construction device 500 , as shown in FIG.
  • the apparatus 500 for constructing a three-dimensional map includes: a transceiver unit 501 and a processing unit 502, and the apparatus 500 can be used to implement the methods described in the above method embodiments.
  • the optional transceiver unit 501 and the processing unit 502 can be connected to each other through a communication line 503; the communication line 503 can be a peripheral component interconnect (PCI for short) bus or an extended industry standard architecture (extended industry standard architecture). , referred to as EISA) bus and so on.
  • the communication line 503 can be divided into an address bus, a data bus, a control bus, and the like. For ease of presentation, only one thick line is used in FIG. 5, but it does not mean that there is only one bus or one type of bus.
  • the transceiver unit 501 is used to obtain the current global point cloud map; and the transceiver unit 501 is also used to obtain the data collected by the local collection device installed on the movable device during the movement of the movable device. multiple pieces of image data; and, the processing unit 502 is configured to determine the real-time pose information of the local collection device at the acquisition moment corresponding to each piece of the image data collected by the local collection device; the processing unit Step 502 is further configured to construct a three-dimensional map based on the current global point cloud map, the multiple pieces of image data, and the real-time pose information of the local acquisition device.
  • the three-dimensional map is constructed under a specified coordinate system
  • the specified coordinate system is any one of the following coordinate systems: a first coordinate system determined by the pose of the global acquisition device at an initial moment, a coordinate system determined by the initial The second coordinate system determined by the pose of the local acquisition device, the world coordinate system, and the third coordinate system determined by the pose of any fixed point in space;
  • the processing unit 502 is configured to, based on the current global
  • it is specifically used to: determine the current global point cloud map, the multiple pieces of image data and all the The original coordinate system where the real-time pose information of the local acquisition device is located respectively; for the original coordinate system different from the designated coordinate system, the map data under the original coordinate system is coordinate-transformed based on the conversion relationship, and the designated coordinate is obtained.
  • the map data under the original coordinate system the conversion relationship is determined according to the pose relationship between the original coordinate system and the coordinate origin of the specified coordinate system, and the map data under the original coordinate system includes the current global point cloud map, One or more of the multiple pieces of image data and the real-time pose information of the local acquisition device; based on the current global point cloud map under the specified coordinate system, the multiple pieces of image data and all
  • the three-dimensional map is constructed according to the real-time pose information of the local collecting device, and the three-dimensional map under the specified coordinate system is obtained.
  • the relative pose of the global collection device and the access point AP is fixed, the relative pose of the local collection device to the workstation STA is fixed, and the AP communicates with the STA;
  • the original coordinate system of the coordinate system is the first coordinate system, the specified coordinate system is the second coordinate system, and the conversion relationship is the first conversion relationship.
  • the processing unit 502 is configured to determine the The first transformation relationship: determine a first transformation matrix according to the relative pose of the global acquisition device and the AP, determine a second transformation matrix according to the positioning result of the AP on the STA, determine the second transformation matrix according to the STA and the AP
  • the relative pose of the local acquisition device determines a third transformation matrix; and based on the product of the first transformation matrix, the second transformation matrix and the third transformation matrix, the first transformation relationship is obtained.
  • the processing unit 502 is configured to determine the real-time pose information of the local acquisition device at the acquisition time corresponding to each piece of image data acquired by the local acquisition device, specifically It is used for: acquiring the real-time positioning result of the STA by the AP at each acquisition moment corresponding to each piece of the image data is collected; based on the initial positioning result of the AP on the STA at the initial moment, the The initial pose information of the STA in the fourth coordinate system at the initial moment and the real-time positioning result, to obtain the real-time pose information of the STA under the fourth coordinate system at each collection moment, wherein the The coordinate origin of the fourth coordinate system is determined by the pose of the STA at the initial moment; the local acquisition device is determined according to the real-time pose information of the STA in the fourth coordinate system and the third transformation matrix Real-time pose information under the fourth coordinate system; coordinate transformation of the real-time pose information of the local collection device under the fourth coordinate system to obtain the local collection device under the specified coordinate system real-time pose information.
  • processing unit 502 is further configured to detect, based on the real-time positioning result of the AP on the STA, a loopback abnormality existing in the moving process of the movable device.
  • the processing unit 502 is further configured to, before acquiring a plurality of pieces of image data collected by the local collecting device during the movement of the movable device, based on the current global point cloud map Plan a movement path for the movable device; generate a movement instruction according to the real-time pose information of the local acquisition device and the movement path; the transceiver unit 501 is further configured to send the information to the controller of the movable device. and the moving instruction, so that the controller controls the movable device to move according to the moving instruction.
  • each functional unit in each embodiment of the present application It can be integrated in one processing unit, or it can exist physically alone, or two or more units can be integrated in one unit.
  • the above-mentioned integrated units may be implemented in the form of hardware, or may be implemented in the form of software functional units.
  • the integrated unit if implemented as a software functional unit and sold or used as a stand-alone product, may be stored in a computer-readable storage medium.
  • the technical solutions of the present application can be embodied in the form of software products in essence, or the parts that contribute to the prior art, or all or part of the technical solutions, and the computer software products are stored in a storage medium , including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor (processor) to execute all or part of the steps of the methods in the various embodiments of the present application.
  • the aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk and other media that can store program codes .
  • an embodiment of the present application further provides a schematic structural diagram of an apparatus 600 for constructing a three-dimensional map.
  • the apparatus 600 may be used to implement the methods described in the foregoing method embodiments, and reference may be made to the descriptions in the foregoing method embodiments.
  • Apparatus 600 may include one or more processors 601 .
  • the processor 601 may be a general-purpose processor or a special-purpose processor, or the like. For example, it may be a baseband processor, or a central processing unit.
  • the baseband processor can be used to process communication protocols and communication data
  • the central processing unit can be used to control the three-dimensional map construction device (such as a base station, terminal, or chip, etc.), execute software programs, and process data of software programs.
  • the apparatus for constructing a three-dimensional map may include a transceiving unit to realize signal input (reception) and output (transmission).
  • the transceiver unit may be a transceiver, a radio frequency chip, or the like.
  • the apparatus 600 includes one or more processors 601, and the one or more processors 601 may implement the methods shown in the embodiments shown above.
  • processor 601 may also implement other functions in addition to implementing the methods in the above-described embodiments.
  • the processor 601 may execute an instruction, so that the apparatus 600 executes the method described in the foregoing method embodiment.
  • the instructions can be stored in the processor in whole or in part, such as the instruction 603, or in the memory 602 coupled with the processor, such as the instruction 604, or the apparatus 600 can be implemented by the instructions 603 and 604 together to execute the above method. method described in the example.
  • the apparatus 600 may include one or more memories 602 having stored thereon instructions 604 that may be executed on a processor to cause the apparatus 600 to perform the methods described in the above method embodiments.
  • data may also be stored in the memory.
  • Instructions and/or data may also be stored in the optional processor.
  • one or more memories 602 may store the corresponding relationships described in the above embodiments, or related parameters or tables involved in the above embodiments, and the like.
  • the processor and memory can be provided separately or integrated.
  • the apparatus 600 may further include a transceiver 605 and an antenna 606 .
  • the processor 601 may be referred to as a processing unit, and controls the apparatus (terminal or base station).
  • the transceiver 605 may be referred to as a transceiver, a transceiver circuit, or a transceiver unit, etc., and is used to implement the transceiver function of the device through the antenna 606 .
  • the processor in this embodiment of the present application may be an integrated circuit chip, which has a signal processing capability.
  • the steps of the above method embodiments may be completed by the hardware integrated logic circuit 702 in the processor or the instructions in the form of software.
  • the above-mentioned processor may be a general-purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), an off-the-shelf programmable gate array (field programmable gate array, FPGA), or other possible solutions.
  • DSP digital signal processor
  • ASIC application specific integrated circuit
  • FPGA field programmable gate array
  • Programming logic devices discrete gate or transistor logic devices, discrete hardware components.
  • the methods, steps, and logic block diagrams disclosed in the embodiments of this application can be implemented or executed.
  • a general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
  • the steps of the method disclosed in conjunction with the embodiments of the present application may be directly embodied as executed by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor.
  • the software modules may be located in random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, registers and other storage media mature in the art.
  • the storage medium is located in the memory, and the processor reads the information in the memory, and completes the steps of the above method in combination with its hardware.
  • the memory in this embodiment of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memory.
  • the non-volatile memory can be read only memory (ROM), programmable read only memory (programmable ROM, PROM), erasable programmable read only memory (erasable PROM, EPROM), electrically erasable programmable read only memory Read memory (electrically EPROM, EEPROM) or flash memory.
  • Volatile memory may be random access memory (RAM), which acts as an external cache.
  • RAM random access memory
  • DRAM dynamic random access memory
  • SDRAM synchronous DRAM
  • SDRAM double data rate synchronous dynamic random access memory
  • ESDRAM enhanced synchronous dynamic random access memory
  • SLDRAM synchronous link dynamic random access memory
  • direct rambus RAM direct rambus RAM
  • Embodiments of the present application further provide a computer storage medium on which a computer program is stored, and when the computer program is executed by a computer, implements the method for constructing a three-dimensional map in any of the above-described method embodiments.
  • Embodiments of the present application further provide a computer program product, which implements the method for constructing a three-dimensional map according to any of the above-described method embodiments when the computer program product is executed by a computer.
  • the computer program product includes one or more computer instructions.
  • the computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable device.
  • Computer instructions may be stored in or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from a website site, computer, server, or data center over a wire (e.g.
  • coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (eg infrared, wireless, microwave, etc.) means to transmit to another website site, computer, server or data center.
  • a computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, or the like that contains one or more of the available mediums integrated.
  • Useful media may be magnetic media (eg, floppy disk, hard disk, magnetic tape), optical media (eg, high-density digital video disc (DVD)), or semiconductor media (eg, solid state disk (SSD)) )Wait.
  • An embodiment of the present application further provides a processing apparatus, including a processor and an interface; the processor is configured to execute the method for constructing a three-dimensional map according to any of the above-mentioned method embodiments.
  • the above-mentioned processing device may be a chip, and the processor may be implemented by hardware or software.
  • the processor may be a logic circuit 702, an integrated circuit, etc.; when implemented by software , the processor can be a general-purpose processor, and is implemented by reading software codes stored in a memory, which can be integrated in the processor or located outside the processor and exist independently.
  • an embodiment of the present application further provides a chip 700, including an input and output interface 701 and a logic circuit 702.
  • the input and output interface 701 is used for receiving/outputting code instructions or information
  • the logic circuit 702 is used for executing code instructions Or according to the information, the method for constructing a three-dimensional map of any one of the above-mentioned method embodiments is performed.
  • the chip 700 can implement the functions shown in the processing unit and/or the transceiver unit in the above embodiments.
  • the input and output interface 701 is used to obtain the current global point cloud map.
  • the input and output interface 701 is used to acquire multiple pieces of image data collected by a local acquisition device disposed on the movable device during the movement of the movable device.
  • the disclosed apparatus and method may be implemented in other manners.
  • the apparatus embodiments described above are only illustrative.
  • the division of units is only a logical function division.
  • there may be other division methods for example, multiple units or components may be combined or integrated. to another system, or some features can be ignored, or not implemented.
  • the shown or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, and may also be electrical, mechanical or other forms of connection.
  • Units described as separate components may or may not be physically separated, and components shown as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solutions of the embodiments of the present application.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit.
  • the above-mentioned integrated units may be implemented in the form of hardware, or may be implemented in the form of software functional units.
  • Computer storage media includes both computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another.
  • a storage medium can be any available medium that a computer can access.
  • computer storage media may include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage media, or other magnetic storage devices, or that can be used to carry or store data in the form of instructions or data structures. desired program code and any other medium that can be accessed by a computer. also.
  • any connection can be a suitable computer storage medium.
  • the software is transmitted from a website, server, or other remote source using coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwave
  • coaxial cable , fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, wireless, and microwave
  • Disk and disc includes compact disc (CD), laser disc, optical disc, digital versatile disc (DVD), floppy disk, and blu-ray disc, where disks generally reproduce data magnetically, and discs Lasers are used to optically copy data. Combinations of the above should also be included within the scope of protection of computer storage media.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Remote Sensing (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Theoretical Computer Science (AREA)
  • Software Systems (AREA)
  • Geometry (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Electromagnetism (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Computer Graphics (AREA)
  • Processing Or Creating Images (AREA)
  • Navigation (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
  • Image Analysis (AREA)

Abstract

一种三维地图的构建方法及装置，用以构建更为准确和完整的三维地图。该方法为：三维地图的构建装置获取当前的全局点云地图（S301）；以及，在可移动设备移动过程中，设置于所述可移动设备上的局部采集装置采集的多张图像数据（S302）；并，确定在所述局部采集装置采集每张所述图像数据所对应的采集时刻，所述局部采集装置的实时位姿信息（S303）；最后，基于所述当前的全局点云地图、所述多张图像数据和所述局部采集装置的实时位姿信息进行三维地图的构建（S304）。

Description

一种三维地图的构建方法及装置
本申请要求于2021年2月1日提交中国国家知识产权局、申请号为202110136015.0、申请名称为“一种三维地图的构建方法及装置”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请实施例涉及通信技术领域，尤其涉及一种三维地图的构建方法及装置。
背景技术
在实时定位、导航等技术领域，重要的先决条件便是构建三维地图，例如，移动机器人完成智能行为，需要获取准确的位置信息。因此，构建三维地图的完整性和准确性会直接影响定位、导航功能的实现。
目前，现有技术中主要采用同步定位与建图(simultaneous localization and mapping，SLAM)技术实现三维地图的构建。其中，SLAM主要包括视觉SLAM和激光SLAM。然而，视觉SLAM会受到光线强弱、背景纹理等因素的影响，因此可能会导致地图准确度低的问题；激光SLAM虽然可获取检测目标较为准确的定位信息，但无法获取检测目标的纹理、颜色等场景信息，从而会导致地图的可视化较差的问题。
因此，如何构建更为准确、完整的三维地图是值得研究的技术问题。
发明内容
本申请实施例提供一种三维地图的构建方法及装置，用以构建更为准确、完整的三维地图，提高实时定位、导航的准确性。
本申请实施例提供的具体技术方案如下：
第一方面，本申请实施例提供了一种三维地图的构建方法，该方法包括：三维地图的构建装置获取当前的全局点云地图；以及，所述三维地图的构建装置获取在可移动设备移动过程中，设置于所述可移动设备上的局部采集装置采集的多张图像数据；并，所述三维地图的构建装置确定在所述局部采集装置采集每张所述图像数据所对应的采集时刻，所述局部采集装置的实时位姿信息；所述三维地图的构建装置基于所述当前的全局点云地图、所述多张图像数据和所述局部采集装置的实时位姿信息进行三维地图的构建。
该方法中，通过利用俯视角度获取当前的全局点云地图，可以和局部采集装置采集的局部的图像数据进行互相补盲，从而可以提升构建的三维地图的完整性，以及可以提高三维地图构建时的鲁棒性。由此，相比于现有技术中存在的仅基于采集的传感器数据进行SLAM的实施方式，可能会导致采集的特征较少，从而导致构建的三维地图不准确的技术问题，通过本申请提供的方法，可以提高三维地图构建的准确性。
在一种可能的设计中，所述三维地图构建于指定坐标系下，所述指定坐标系为以下坐标系中任一坐标系：由初始时刻所述全局采集装置的位姿确定的第一坐标系、由所述初始时刻所述局部采集装置的位姿确定的第二坐标系、世界坐标系、以任一固定空间点的位姿 确定的第三坐标系。所述三维地图的构建装置基于所述当前的全局点云地图、所述多张图像数据和所述局部采集装置的实时位姿信息进行三维地图的构建，可实施为确定所述当前的全局点云地图、所述多张图像数据和所述局部采集装置的实时位姿信息分别所在的原始坐标系；对于不同于所述指定坐标系的原始坐标系，将该原始坐标系下的地图数据基于转换关系进行坐标转换，得到所述指定坐标系下的地图数据，所述转换关系根据该原始坐标系和所述指定坐标系的坐标原点之间的位姿关系确定，该原始坐标系下的地图数据包括所述当前的全局点云地图、所述多张图像数据和所述局部采集装置的实时位姿信息中的一种或多种；基于所述指定坐标系下的所述当前的全局点云地图、所述多张图像数据和所述局部采集装置的实时位姿信息进行三维地图的构建，得到所述指定坐标系下的三维地图。
基于该设计，三维地图的构建装置可以将三维地图构建于任一坐标系下，便于基于构建的三维地图进行实时定位、导航等。其中，针对地图数据中的任一空间点在不同坐标系之间的坐标转换，可以根据坐标系的坐标原点的位姿确定，以得到不同坐标系之间的转换关系。因此，本申请实施时，可以实现结合全局采集装置采集的全局点云地图和局部采集装置采集的图像数据，进而可以提高构建的三维地图的完整性和准确性。
在一种可能的设计中，所述全局采集装置与AP相对位姿固定，所述局部采集装置与STA相对位姿固定，所述AP和所述STA进行通信。示例性的，若所述不同于所述指定坐标系的原始坐标系为所述第一坐标系，所述指定坐标系为所述第二坐标系，所述转换关系为第一转换关系，所述三维地图的构建装置根据以下方式确定所述第一转换关系：根据所述全局采集装置与所述AP的相对位姿确定第一转换矩阵、根据所述AP对所述STA的定位结果确定第二转换矩阵、根据所述STA与所述局部采集装置的相对位姿确定第三转换矩阵；基于所述第一转换矩阵、所述第二转换矩阵和所述第三转换矩阵的乘积，得到所述第一转换关系。
在该设计中，通过采用AP对STA的定位结果，可以得到全局采集装置坐标系和初始局部采集装置坐标系之间的转换关系，从而可以实现对全局点云地图或局部图像数据的坐标转换，以实现在同一坐标系下基于全局点云地图和局部图像数据进行三维地图的构建，进而实现相比于现有技术可以得到更具准确性、完整性的三维地图。相比于现有技术中基于SLAM技术需要采用相邻的不同时间内的传感器数据进行特征匹配之后才能确定的实施方式，本申请可以减少计算量，并且基于AP对STA的定位结果可以保障准确性。
在一种可能的设计中，所述三维地图的构建装置确定在所述局部采集装置采集每张所述图像数据所对应的采集时刻，所述局部采集装置的实时位姿信息，可实施为获取在采集每张所述图像数据所对应的每个采集时刻，所述AP对所述STA的实时定位结果；基于所述初始时刻所述AP对所述STA的初始定位结果、所述初始时刻所述STA在第四坐标系下的初始位姿信息以及所述实时定位结果，得到每个采集时刻所述STA在所述第四坐标系下的实时位姿信息，其中，所述第四坐标系的坐标原点由所述初始时刻所述STA的位姿确定；根据所述STA在所述第四坐标系下的实时位姿信息、所述第三转换矩阵确定所述局部采集装置在所述第四坐标系下的实时位姿信息；将所述局部采集装置在所述第四坐标系下的实时位姿信息进行坐标转换，得到所述局部采集装置在所述指定坐标系下的实时位姿信息。在该设计中，局部采集装置在每个采集时刻的实时位姿信息是基于AP对STA的实时定位结果进行坐标转换之后得到，因此无需依托相邻时间内采集的其他图像数据，这样，可以避免现有技术中通过相邻时间内的图像数据进行特征匹配来估算机器人实时位姿的方式 可能存在的时间累积误差的缺点，从而可以提高构建的三维地图的准确性。
在一种可能的设计中，所述三维地图的构建装置基于所述AP对所述STA的实时定位结果，检测所述可移动设备在移动过程中存在的回环异常。
在该设计中，相比于现有技术中进行回环检测的实施方式只能通过从传感器数据中提取一系列特征，然后结合词袋(bag of words)的方法，比较不同的图像数据之间的相似度，才能确定可移动设备当前移动到的位置是否为曾经到达过的位姿，本申请实施时，通过AP对STA的定位结果进行回环检测，可以提升三维地图的构建效率，并提升在弱纹理环境下(比如白墙)回环检测的鲁棒性。
在一种可能的设计中，所述三维地图的构建装置获取在所述可移动设备移动过程中所述局部采集装置采集的多张图像数据之前，所述三维地图的构建装置基于所述当前的全局点云地图为所述可移动设备规划移动路径；所述三维地图的构建装置根据所述局部采集装置的实时位姿信息和所述移动路径生成移动指令；所述三维地图的构建装置向所述可移动设备的控制器发送所述移动指令，以使所述控制器控制所述可移动设备根据所述移动指令进行移动。
在该设计中，基于通过获取的当前的全局点云地图为可移动设备规划移动路径，然后基于局部采集装置的实时位姿信息，为可移动设备生成可以在可移动的移动路径范围内移动的移动指令，可以避免可移动设备的盲目移动，因此可以提升三维地图构建的效率和准确性。
第二方面，本申请实施例提供一种三维地图的构建装置，所述装置包括收发单元和处理单元。其中，所述收发单元、所述处理单元执行的功能可以和上述第一方面中任一可能的设计或实现方式中涉及的三维地图的构建装置执行的步骤相对应。
第三方面，本申请实施例还提供了一种计算设备，所述计算设备包括一个或多个处理器和存储器，所述存储器与所述处理器耦合，所述存储器存储计算机程序代码，所述计算机程序代码包括计算机指令。所述处理器执行所述存储器中的计算机指令，以执行上述第一方面任一可能的设计中提供的方法。可选的所述计算设备还可以包括显示屏。所述显示屏用于在所述处理器的触发下向用户显示信息，例如全局采集装置采集的全局点云地图，或局部采集装置采集的图像数据等等。可选地，该计算设备还包括通信接口，处理器与通信接口耦合。该通信接口可以是收发器或输入/输出接口；当该计算设备为网络设备中包含的芯片时，该通信接口可以是芯片的输入/输出接口。可选地，收发器可以为收发电路，输入/输出接口可以是输入/输出电路。
第四方面，本申请实施例还提供了一种计算设备集群，包括至少一个如上述第三方面所提供的计算设备。
第五方面，本申请实施例还提供一种计算机存储介质，所述计算机存储介质存储有计算机程序，当所述计算机程序被计算机执行时，使第一方面任一种可能的设计中提供的方法被实现。
第六方面，本申请实施例还提供了一种计算机程序产品，该计算机程序产品包括：计算机程序代码，当计算机程序代码被通信装置的处理器运行时，使得通信装置执行上述第一方面任一种可能的设计中的方法。
第七方面，本申请实施例还提供一种芯片，用于读取并执行存储器中存储的软件程序，以实现上述第一方面任一种可能的设计中的方法。其中，所述存储器可以与所述芯片相连， 或所述存储器也可以内置于所述芯片中。
上述第二方面至第七方面中任一方面的有益效果请具体参阅上述第一方面中各种可能的设计的有益效果，在此不再赘述。
附图说明
图1为一种SLAM系统的流程示意图；
图2为本申请实施例中一种三维地图的构建方法的应用场景图；
图3为本申请实施例中一种三维地图的构建方法的交互示意图；
图4为本申请实施例中一种三维地图的构建方法的流程示意图；
图5为本申请实施例中一种三维地图的构建装置的结构示意图；
图6为本申请实施例中另一种三维地图的构建装置的结构示意图；
图7为本申请实施例中提供的一种芯片的结构示意图。
具体实施方式
下面将结合附图，对本申请实施例进行详细描述。
本申请实施例可以应用于可移动设备在自主移动过程中的实时定位及导航等场景中。其中，可移动设备诸如扫地机器人、送餐机器人、配送机器人、移动小车、物流小车等。本申请对适用的可移动设备的具体类型不做任何限制。
为了满足可移动设备较为准确的智能行走行为，通常需要构建完整、准确的三维地图。目前，现有技术中主要采用SLAM技术实现三维地图的构建，然而采用SLAM技术构建三维地图可能存在由于时间累积误差导致的精度低，由于视线盲区导致的三维地图不完整等问题。
有鉴于此，本申请实施例提供了一种三维地图的构建方法，通过结合全局点云地图、多张局部的图像数据以及局部采集装置的实时位姿信息来进行三维地图的构建，从而可以实现全局点云地图和局部的图像数据的互相补盲，以构建更准确、完整的三维地图。
首先介绍下本申请实施例可以应用到的系统架构。图1为一种SLAM系统的流程示意图。SLAM技术可以理解为：移动机器人从未知环境的未知地点出发，在移动过程中，根据位置估计和地图进行自身定位，同时在自身定位的基础上建造增量式地图，实现移动机器人的自主定位和导航。SLAM系统主要包括传感器数据采集101、里程计102、回环检测103、非线性优化104以及建图105几个功能。其中，各功能的主要实现如下：
所述传感器数据采集101，用于采集进行构建地图过程中需要的传感器数据。其中，传感器数据包括但不限于图像数据、激光点云信息、惯性传感器数据等。例如，在视觉SLAM中，传感器数据可以为利用相机、摄像头等视觉传感器采集的图像数据；在激光SLAM中，传感器数据可以为通过激光雷达获取到的激光点云，或基于激光点云得到的图像等。
所述里程计102，用于估算机器人的位姿变化，建立局部三维地图。其中，位姿变化包括平移信息和旋转信息。现有技术中，激光SLAM和视觉SLAM主要是根据相邻时间内的传感器数据进行匹配和比较，进而可以估算机器人的位姿。然而，在进行里程计的计算过程中，由于估算机器人的位姿是基于相邻时间内机器人的位姿变化得到的，因此可能会存在较大的时间累积误差，从而会导致构建的三维地图的准确性降低。
所述回环检测103，用于判断机器人当前位置是否为曾经到达过的位置，若判断存在回环，则将回环信息用于非线性优化104，以校正里程计的漂移。
所述非线性优化104，用于根据不同时间段内所述里程计102得到的机器人位姿、所述回环检测103的回环信息进行优化，主要通过对机器人位姿、地图的优化，得到全局一致的机器人移动轨迹。
所述建图105，用于根据机器人的移动轨迹、所述里程计102建立的多幅局部的三维地图构建完整的全局三维地图。其中，构建的全局三维地图包括但不限于稀疏地图、稠密地图、语义地图等，本申请对此不进行限定。
基于背景技术中介绍的内容和上述介绍到的内容，通过视觉SLAM进行构建地图的方式，由于受到图像特征匹配准确性的影响较大，在光线不理想、背景弱纹理的条件下，因为从传感器数据中提取到的特征较少，因此可能会导致位姿跟踪不准确、地图无匹配等问题。通过激光SLAM进行构建地图的方式，存在可视化差的缺点，并且，在机器人高度受限的情况下，还存在因为无法获取高处被遮挡物体的信息，进而会导致地图构建不完整的问题。以及，通过现有技术中的SLAM技术，在估算机器人位姿时，可能存在较大的时间累积误差的缺点。因此，本申请实施例提供一种三维地图的构建方法。
本申请实施例可以适用于三维地图构建场景。具体的，三维地图构建场景可以是对三维地图的首次构建，也可以是对三维地图的重建；并且可以是进行室内三维地图的构建，也可以是进行室外三维地图的构建。其中，室内三维地图的构建例如可以是扫地机器人对室内三维地图的构建，移动小车对仓库三维地图的构建等；室外三维地图的构建例如可以是园区物流小车对园区三维地图的构建等，本申请对此不进行限定。
需要说明的是，本申请中涉及的多个，是指两个或两个以上。“和/或”，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。字符“/”一般表示前后关联对象是一种“或”的关系。另外，应当理解，尽管在本申请实施例中可能采用术语第一、第二等来描述各数据、但这些数据不应限于这些术语。这些术语仅用来将各数据彼此区分开。
图2为本申请实施例提供的一种三维地图的构建方法的应用场景图。该应用场景可以包括：全局采集装置201、接入点(access point，AP)202、工作站(station，STA)203、局部采集装置204。
其中，若本申请应用于室内三维地图的构建场景，全局采集装置201可以设置于屋顶等高处，用于采集目标场景下的全局点云地图；或者，若本申请应用于室外三维地图的构建场景，全局采集装置201可以设置于墙体、电线杆子等高处，本申请对全局采集装置201的设置方式不进行限定。全局采集装置201可以是深度传感器，深度传感器包括但不限于基于测距激光器的激光雷达、深度摄像头、深度相机等。
AP 202用于对工作站STA 203进行定位得到STA的定位结果，由此可以确定STA的实时位姿信息。其中，AP 202可以基于光通信技术接收一个或多个STA 203的接入，也可以通过无线技术接收一个或多个STA 203的接入等。其中，AP 202与STA 203之间进行通信的光通信技术包括但不限于光保真技术(light fidelity，Li-Fi)、可见光通信技术(visible light communication，VLC)、自由空间光通信(free-space optical communication，FSO)等。需要说明的是，AP 202和全局采集装置201可以是两个独立的设备，例如可以是一个AP设备和一个深度传感器；或者，AP 202和全局采集装置201也可以都包含在集成设备中，例如， 存在一个集成设备，包含可以实现全局采集装置201功能的单元，同时包含可以实现AP 202功能的单元；又或者，全局采集装置201还可以集成在AP 202中，本申请对此不进行限定。
局部采集装置204可以设置于可移动设备上，或集成在可移动设备中。局部采集装置204用于在可移动设备的移动过程中采集多张不同的图像数据。其中，局部采集装置204可以是单目摄像头、双目摄像头、红绿蓝深度(RGBD)摄像头等，本申请对此不做限定。与全局采集装置201和AP 202之间的相对位姿关系同理，本申请实施时，对局部采集装置204和STA 203之间的相对位姿关系也不进行限定。
此外，该应用场景中还包括：上位机205(可以包括图2中的205a或205b)以及云服务器206。其中，所述上位机205a用于获取全局采集装置201和AP 202的数据，并对接收的数据进行处理和计算，实现全局点云地图的显示以及控制指令的下发等，例如上位机205a对全局采集装置201采集到的全局点云地图进行坐标转换处理，基于全局点云地图实现对可移动设备的移动路径规划等。同理，所述上位机205b用于获取局部采集装置204和STA 203的数据，并对接收的数据进行处理和计算，实现局部的图像数据的显示以及控制指令的下发等，例如，上位机205b可以设置于可移动设备中，可以实现对可移动设备的自主移动控制，作为可移动设备的控制器。需要说明的是，本申请实施例中对模块的划分是示意性的，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，另外，在本申请各个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，例如上位机205b可以是集成在可移动设备内部，或者也可以是单独的物理存在。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。
本申请实施例提供的方法可以通过全局采集装置201连接的上位机205a实现，还可以通过局部采集装置204连接的上位机205b实现，或者还可以通过云服务器206实现，甚至还可以通过上位机与云服务器的协调分工实现，即上位机205a、上位机205b或云服务器中的一种或组合可以作为实现本申请提供的方法的三维地图的构建装置。实施时可以根据各设备的计算能力和/或实际场景确定，例如，若上位机205a的计算能力可以支持实施本申请提供的方法，则可以通过上位机205a实现本申请提供的方法，本申请对此不做限定。
需要说明的是，根据具体的实际需要，应用场景中包含的每个设备的类型和数量可能不相同。例如，设置在屋顶上的全局采集装置201可以有多个，每个全局采集装置201负责采集一个区域内的全局点云地图；或者，设置在屋顶上的AP 202也可以有多个。
基于图2所示的场景，图3为本申请实施例提供的一种三维地图的构建方法的交互示意图。该交互流程包括以下步骤：
S301、三维地图的构建装置获取当前的全局点云地图。
示例性的，全局点云地图可以通过全局采集装置201获取。实施时，全局点云地图表示包含需要构建三维地图的目标场景内较大的视角范围，例如若需要构建房间内的三维地图，以便于扫地机器人进行智能移动行为，则全局点云地图可以为从一个房间内的摄像头中获取的。并且，由于目标场景内的物体的位置可能经常变化，当前的全局点云地图可以是实时获取的，或者周期性获取的，以便于可以及时获知目标场景内的变化，从而可以构建更能反映此时准确的三维地图。
需要说明的是，三维地图的构建装置的组成可以根据实际场景的情况确定，实施时可以由图2中的上位机205a、上位机205b或云服务器206中的一种或组合构成，本申请对 此不进行限定。
在一种可能的实施方式中，全局点云地图可以应用于对可移动设备的移动路径规划。示例性的，通过对全局点云地图的特征提取，确定目标场景中的可行走路面的区域，进而可以在可行走路面的区域内为可移动设备规划移动路径。并且，三维地图的构建装置还可以确定局部采集装置的实时位姿，由此可以确定局部采集装置的朝向，也即可移动设备的移动方向。然后，三维地图的构建装置可以在确定的可行走路面的区域中根据可移动设备的移动方向生成移动指令。三维地图的构建装置可以将移动指令发送给可移动设备的控制器，所述可移动设备例如可以是图2中的小车，控制器例如可以是图2中小车上的上位机205b，由此可以通过上位机205b控制可移动设备根据移动指令进行移动。通过该设计，基于获取的全局点云地图，可以为可移动设备规划移动路径，可以避免可移动设备的盲目移动，因此可以提升三维地图构建的效率和准确性。
S302、所述三维地图的构建装置获取在可移动设备移动过程中，设置于所述可移动设备上的局部采集装置采集的多张图像数据。
示例性的，由于局部采集装置可以设置在可移动设备上，因此局部采集装置可以随着可移动设备的移动而移动，这样局部采集装置可以在可移动设备的移动过程中采集多张不同的图像数据。具体实施为，局部采集装置可以周期性采集图像数据，例如每10S采集一张图像数据；或者，局部采集装置还可以在可移动设备每次移动指定距离之后采集一张图像数据，本申请对此不进行限定。
S303、所述三维地图的构建装置确定在所述局部采集装置采集每张所述图像数据所对应的采集时刻，所述局部采集装置的实时位姿信息。
现有技术中，在SLAM系统中，通过里程计102对局部采集装置采集的相邻图像数据进行特征匹配，来估算局部采集装置的位姿变化，然而，可能会存在较大的时间累积误差的缺点。
为了构建更准确的三维地图，基于AP可以实时获取STA的定位信息，本申请实施时，通过设置AP与全局采集装置的相对位姿固定，并且设置STA与局部采集装置的相对位姿固定，因此可以通过AP对STA的实时定位结果可以确定STA的实时位姿信息。然后，由于STA和局部采集装置之间的相对位姿固定，因此可以基于STA的实时位姿信息进一步确定局部采集装置的实时位姿信息。需要说明的是，一般场景下，设置全局采集装置和AP在不同时刻的位姿固定，而局部采集装置和STA由于设置于可移动设备上，因此局部采集装置和AP的位姿信息是变化的。
S304、所述三维地图的构建装置基于所述当前的全局点云地图、所述多张图像数据和确定的多个所述实时位姿信息进行三维地图的构建。
示例性的，根据实际场景的需要，可以将三维地图构建于指定坐标系下。其中，所述指定坐标系可以为以下坐标系中任一坐标系：由初始时刻所述全局采集装置的位姿确定的第一坐标系(也可称为全局采集装置坐标系)、由所述初始时刻所述局部采集装置的位姿确定的第二坐标系(也可称为初始局部采集装置坐标系)、世界坐标系、以任一固定空间点的位姿确定的第三坐标系(例如以前述内容中介绍到的AP的位姿确定的AP坐标系等)。其中，位姿包括位置和姿态，即三维坐标和朝向。其中，初始时刻可以表示为可移动设备在目标场景中处于静止状态的任一时刻，或者也可以是三维地图的构建装置从可移动设备在移动过程中选取的任一时刻，本申请对初始时刻的选取不进行限定，主要是为了选择一 个相同时刻的全局采集装置和局部采集装置的相对位姿装置作为基础的转换关系。
在构建三维地图的实施过程中，三维地图的构建装置获取到的当前的全局点云地图、所述多张图像数据和确定的多个所述实时位姿信息可能处于不同的坐标系下，为了实现融合式地进行三维地图的构建，将这些信息转换到相同的坐标系下，步骤如下：
步骤A1：三维地图的构建装置确定所述当前的全局点云地图、所述多张图像数据和所述局部采集装置的实时位姿信息分别所在的原始坐标系。
示例性，全局采集装置201采集的全局点云地图处于全局采集装置坐标系下。局部采集装置204采集的图像数据处于由所述局部采集装置的实时位姿确定的实时局部采集装置坐标系下。所述局部采集装置的实时位姿信息可以通过STA的实时位姿信息确定，因此局部采集装置的实时位姿信息处于由所述STA的实时位姿确定的实时STA坐标系下。
步骤A2：对于不同于所述指定坐标系的原始坐标系，将该原始坐标系下的地图数据基于转换关系进行坐标转换，得到所述指定坐标系下的地图数据。
其中，所述转换关系根据该原始坐标系和所述指定坐标系的坐标原点之间的位姿关系确定，该原始坐标系下的地图数据包括所述当前的全局点云地图、所述多张图像数据和所述局部采集装置的实时位姿信息中的一种或多种。例如，若指定坐标系为初始局部采集装置坐标系，全局点云地图的原始坐标系为全局采集装置坐标系，获取全局采集装置坐标系到初始局部采集装置坐标系的第一转换关系，基于该第一转换关系对全局采集装置坐标系的全局点云地图进行坐标转换之后，得到初始局部采集装置坐标系下的全局点云地图。
示例性的，若指定坐标系为初始局部采集装置坐标系，则将全局采集装置坐标系的全局点云地图转换到初始局部采集装置坐标系下的第一转换关系可以通过以下介绍的内容得到。
假设空间中存在任一点在全局采集装置坐标系下的齐次坐标可以表示为[X L，Y L，Z L，1] T，该点在初始局部采集装置坐标系下的齐次坐标表示为[X C，Y C，Z C，1] T，则该点在全局采集装置坐标系和初始局部采集装置坐标系之间的坐标转换关系可以通过以下公式1表示：
Figure PCTCN2021124676-appb-000001
其中，所述
Figure PCTCN2021124676-appb-000002
表示全局采集装置坐标系到初始局部采集装置坐标系的转换矩阵，所述矩阵R 3*3为旋转矩阵，用来表示全局采集装置坐标系和初始局部采集装置坐标系之间的朝向角度的转换。所述矩阵T 3*1为平移向量，用来表示全局采集装置坐标系和初始局部采集装置坐标系之间的三维坐标的转换。
需要说明的是，若将在初始局部采集装置坐标系下的空间点转换到全局采集装置坐标系下可以通过以下公式2表示：
Figure PCTCN2021124676-appb-000003
其中，矩阵R 3*3′为公式1中矩阵R 3*3的逆矩阵，矩阵T 3*1′为矩阵R 3*3的逆矩阵与公式1中平移向量T 3*1的乘积的相反数，具体表达方式可以参照以下公式3。可以理解，以上公式2为公式1的逆过程。
根据以上公式1和公式2可以得到将任一空间点从全局采集装置坐标系转换到初始局部采集装置坐标系下的第一转换关系，以及任一空间点从初始局部采集装置坐标系转换到 全局采集装置坐标系下的第二转换关系。从而可以实现不同坐标系之间方便的坐标转换。
一种可能的实施方式中，全局采集装置坐标系到初始局部采集装置坐标系的坐标转换关系可以基于初始时刻AP对STA的初始定位结果确定，具体实施为可以由三个转换矩阵确定，如下：
第一转换矩阵为根据全局采集装置与AP之间的相对位姿确定的。其中，基于全局采集装置和AP之间的相对位姿固定，由此可以得到第一转换矩阵为固定矩阵。需要说明的是，无论全局采集装置和AP是通过哪种方式实现，例如前述内容中介绍到的独立方式、包含在集成设备中或全局采集装置包含在AP中；由于全局采集装置和AP中包含的发光装置(即用于进行光通信的模块)的坐标原点不同，为了得到更加准确的转换关系，因此基于全局采集装置的坐标原点和AP的发光装置的坐标原点坐标来体现全局采集装置与AP之间的相对位姿。
示例性的，第一转换矩阵可以通过矩阵
Figure PCTCN2021124676-appb-000004
来表示。
第二转换矩阵为根据AP与STA之间的相对位姿确定的，可以通过矩阵
Figure PCTCN2021124676-appb-000005
来表示。
由于STA设置于可移动设备上，因此在可移动设备移动过程中，AP与STA之间的相对位姿是实时变化的，所以第二转换矩阵不属于固定矩阵。具体实施时，三维地图的构建装置可以基于AP对STA的定位结果确定AP与STA之间的相对位姿，进而确定第二转换矩阵。
示例性的，AP对STA的定位结果可以通过矩阵
Figure PCTCN2021124676-appb-000006
基于AP对STA的定位结果确定第二转换矩阵可以通过以下公式3表示：
Figure PCTCN2021124676-appb-000007
第三转换矩阵为根据STA与局部采集装置之间的相对位姿确定的。其中，STA与局部采集装置之间的相对位姿固定，由此可以得到第三转换矩阵同样为固定矩阵。
示例性的，与第一转换矩阵相同的获取原理，第三转换矩阵可以通过矩阵
Figure PCTCN2021124676-appb-000008
来表示。
因此，结合以上第一转换矩阵、第二转换矩阵和第三转换矩阵的乘积，可以得到全局采集装置与局部采集装置的转换关系。其中，转换关系例如可以通过以下公式4确定：
Figure PCTCN2021124676-appb-000009
另一种可能的实施方式中，本申请实施时，三维地图的构建装置确定转换关系的方式还可以是基于标定物辅助的方式实现的。示例性的，在目标场景中可以放置棋盘格、靶标等标定物，在可移动设备移动过程中的任一时刻，全局采集装置和局部采集装置的采集区域内包含共同视野，也可以理解为两者均可以采集到标定物信息。这种场景下，基于计算机视觉技术领域中的特征提取与匹配的算法，确定任一时刻t标定物在局部采集装置坐标系下的坐标集合{[X C i，Y C i，Z C i|i∈标定物]} t，以及标定物在全局采集装置坐标系下的坐标集合{[X L i，Y L i，Z L i|i∈标定物]} t，然后利用迭代最近点(iterative closest point，ICP)、点对应(perspective-n-point，PnP)等配准算法，计算将全局点云地图从全局采集装置坐标 系转换到局部采集装置坐标系的转换关系，然后基于转换关系对全局点云地图进行坐标转换，得到局部采集装置坐标系下的全局点云地图。
以下介绍如何基于AP对STA的实时定位结果，确定指定坐标系下的局部采集装置的实时位姿信息。
示例性的，在初始时刻以STA的初始位姿建立第四坐标系(也可称为初始STA坐标系)，则此时STA处于初始STA坐标系的坐标原点，则STA的初始位姿信息可以表示为
Figure PCTCN2021124676-appb-000010
其中，矩阵I 3*3表示为坐标系与STA朝向一致的矩阵。根据前述介绍到的内容可以得到STA到局部采集装置的第三转换矩阵为
Figure PCTCN2021124676-appb-000011
则局部采集装置在初始STA坐标系下的初始位姿可以表示为
Figure PCTCN2021124676-appb-000012
以及，三维地图的构建装置还可以确定STA在AP坐标系(即以初始时刻AP的位姿为坐标原点建立的坐标系)下的位姿为AP对STA的初始定位结果，假设以
Figure PCTCN2021124676-appb-000013
来表示。
在移动过程中，以任一时刻t1作为示例。三维地图的构建装置确定局部采集装置在初始局部采集装置坐标系下的实时位姿信息可以通过以下步骤确定：
步骤B1，三维地图的构建装置确定t1时刻AP对STA的实时定位结果，假设以
Figure PCTCN2021124676-appb-000014
来表示。
步骤B2，三维地图的构建装置将AP坐标系下的STA进行坐标转换，得到STA在初始STA坐标系下的实时位姿信息，假设以
Figure PCTCN2021124676-appb-000015
来表示。
步骤B3，三维地图的构建装置根据所述STA在所述初始STA坐标系下的实时位姿信息、所述第三转换矩阵确定所述局部采集装置在所述初始STA坐标系下的实时位姿信息。
示例性的，因为第三转换矩阵为固定矩阵，则t1时刻局部采集装置相比于STA的相对位姿可以通过初始时刻局部采集装置在初始STA坐标系下的初始位姿确定。则t1时刻，局部采集装置在初始STA坐标系下的实时位姿更新为
Figure PCTCN2021124676-appb-000016
步骤B4，将所述局部采集装置在所述初始STA坐标系下的实时位姿信息进行坐标转换，得到所述局部采集装置在初始局部采集装置坐标系下的实时位姿信息。其中，所述局部采集装置在初始局部采集装置坐标系下的实时位姿信息可以由第三转换矩阵与局部采集装置在初始STA坐标系下的实时位姿信息的乘积确定，可以表示为如下示例：
Figure PCTCN2021124676-appb-000017
另一种可能的示例中，若采用标定物辅助的方式获取转换关系，则可以基于AP对STA的定位结果、获取的转换关系、全局采集装置与AP之间的第一转换矩阵以及STA与局部采集装置之间的第二转换矩阵，确定局部采集装置的实时位姿信息。
通过以上示例，局部采集装置在每个采集时刻的实时位姿信息是基于AP对STA的实时定位结果进行坐标转换之后得到，因此无需依托相邻时间内采集的其他图像数据，这样， 可以避免现有技术中可能存在的时间累积误差的缺点。
步骤A3：三维地图的构建装置基于所述指定坐标系下的所述当前的全局点云地图、所述多张图像数据和所述局部采集装置的实时位姿信息进行三维地图的构建，得到所述指定坐标系下的三维地图。
此外，基于AP对STA的定位结果，本申请实施时，三维地图的构建装置在实现回环检测时，可以通过AP对STA的定位结果直接确定可移动设备在移动过程中是否存在回环异常，并且，具体实施时三维地图的构建装置还可以同时结合对图像数据的特征匹配进行回环异常的检测。通过该设计，相比于现有技术中进行回环检测的实施方式只能通过从传感器数据中提取一系列特征，然后结合词袋(bag of words)的方法，比较不同的图像数据之间的相似度，进而确定可移动设备当前移动到的位置是否为曾经到达过的位姿，本申请实施时，三维地图的构建装置通过AP对STA的定位结果进行回环检测，可以提升三维地图的构建效率。
需要说明的是，三维地图的构建装置在通过本申请实施例提供的方法进行三维地图的构建之前，由于本申请实施例需要借助STA和AP进行处理，需要判断可移动设备上包含的STA是否在线，若STA不在线，则可以直接采用局部采集装置采集的图像数据进行传统的SLAM，例如，若局部采集装置为RGBD相机，则可以基于RGBD相机采集的图像数据进行视觉SLAM。
示例性的，在三维地图的构建装置可以获取到全局点云地图的基础上，在基于非线性优化104对得到的局部采集装置的实时位姿信息和回环异常进行优化之后，可以基于建图105进行三维地图的构建。其中，本申请实施例进行非线性优化104功能的处理可以参照SLAM系统中的优化方式，本申请对此不再赘述。
为了更清楚的理解本申请实施例提供的方法，图4为本申请实施例提供的一种三维地图的构建方法的流程示意图。与现有技术中的SLAM系统相比，实现本申请提供的方法还包括全局点云地图获取401、坐标转换402、移动路径规划403、移动指令生成404及定位信息获取405几个功能。其中，本申请中新增的各功能的主要实现如下：
其中，所述全局点云地图获取401表示全局采集装置获取当前的全局点云地图。
所述坐标转换402表示将所述当前的全局点云地图、所述多张图像数据和所述局部采集装置的实时位姿信息中不属于指定坐标系的地图数据进行坐标转换，得到指定坐标系下的地图数据。本申请实施例中，以将全局点云地图从全局采集装置坐标系转换到初始局部采集装置坐标系下作为示例进行说明。若实施时采用将局部的图像数据由局部采集坐标系转换到全局采集装置坐标系下的实施方式，则坐标转换402可以基于传感器数据采集101得到的局部的图像数据进行坐标转换处理。
所述移动路径规划403表示可以基于全局点云地图为可移动设备规划移动路径，从而避免可移动设备的盲目移动。所述移动指令生成404用于表示基于移动路径和局部采集装置的位姿，为可移动设备生成的移动指令，由此控制可移动设备的移动。
所述定位信息获取405表示AP对STA的定位结果的获取，可以用于进行回环检测103，提升三维地图的构建效率。并且，获取到的定位信息还可以和采集的传感器数据、全局点云地图一起作为里程计102的输入信息，提升对于局部采集装置的实时位姿信息的估算的准确性。
其中，根据具体的实际场景需要，或者根据计算能力的限制，例如，上位机205无法 支持结合全局点云地图实现里程计102、非线性优化104等方面的计算量的处理要求，则将获取的全局点云地图也可以直接用于建图105，这样结合全局点云地图和局部的三维地图进行融合，也可以进行相互补盲，得到更完整的全局三维地图，本申请对获取的全局点云地图和传统的SLAM的具体融合方式不做限定。
通过以上方法实施例介绍的内容，本申请通过结合俯视角度下采集的全局点云地图来共同进行三维地图的构建，并且通过结合AP和STA之间的光通信，可以得到较为准确的转换关系，为构建三维地图提供了保障，以及可以降低由于局部采集装置存在采集盲区而导致构建的三维地图不完整的概率。并且，通过全局点云地图还可以规划可移动设备的移动路径，进而可以避免可以移动设备在目标场景中的盲目移动，由此可以提升三维地图的构建效率。
基于与上述三维地图的构建方法的同一技术构思，本申请实施例还提供一种三维地图的构建装置500，如图5所示，该装置可以上位机205上，还可以设置在云服务器206上，所述三维地图的构建装置500包括：收发单元501以及处理单元502，装置500可用于实现上述方法实施例中描述的方法。其中，可选的收发单元501以及处理单元502可以通过通信线路503相互连接；通信线路503可以是外设部件互连标准(peripheral component interconnect，简称PCI)总线或扩展工业标准结构(extended industry standard architecture，简称EISA)总线等。所述通信线路503可以分为地址总线、数据总线、控制总线等。为便于表示，图5中仅用一条粗线表示，但并不表示仅有一根总线或一种类型的总线。
所述收发单元501，用于获取当前的全局点云地图；以及，所述收发单元501，还用于获取在可移动设备移动过程中，设置于所述可移动设备上的局部采集装置采集的多张图像数据；并，所述处理单元502，用于确定在所述局部采集装置采集每张所述图像数据所对应的采集时刻，所述局部采集装置的实时位姿信息；所述处理单元502，还用于基于所述当前的全局点云地图、所述多张图像数据和所述局部采集装置的实时位姿信息进行三维地图的构建。
其中，所述三维地图构建于指定坐标系下，所述指定坐标系为以下坐标系中任一坐标系：由初始时刻所述全局采集装置的位姿确定的第一坐标系、由所述初始时刻所述局部采集装置的位姿确定的第二坐标系、世界坐标系、以任一固定空间点的位姿确定的第三坐标系；所述处理单元502，用于基于所述当前的全局点云地图、所述多张图像数据和所述局部采集装置的实时位姿信息进行三维地图的构建时，具体用于：确定所述当前的全局点云地图、所述多张图像数据和所述局部采集装置的实时位姿信息分别所在的原始坐标系；对于不同于所述指定坐标系的原始坐标系，将该原始坐标系下的地图数据基于转换关系进行坐标转换，得到所述指定坐标系下的地图数据，所述转换关系根据该原始坐标系和所述指定坐标系的坐标原点之间的位姿关系确定，该原始坐标系下的地图数据包括所述当前的全局点云地图、所述多张图像数据和所述局部采集装置的实时位姿信息中的一种或多种；基于所述指定坐标系下的所述当前的全局点云地图、所述多张图像数据和所述局部采集装置的实时位姿信息进行三维地图的构建，得到所述指定坐标系下的三维地图。
示例性的，所述全局采集装置与接入点AP相对位姿固定，所述局部采集装置与工作站STA相对位姿固定，所述AP和所述STA进行通信；若所述不同于所述指定坐标系的原始坐标系为所述第一坐标系，所述指定坐标系为所述第二坐标系，所述转换关系为第一转换关系，所述处理单元502，用于根据以下方式确定所述第一转换关系：根据所述全局采 集装置与所述AP的相对位姿确定第一转换矩阵、根据所述AP对所述STA的定位结果确定第二转换矩阵、根据所述STA与所述局部采集装置的相对位姿确定第三转换矩阵；基于所述第一转换矩阵、所述第二转换矩阵和所述第三转换矩阵的乘积，得到所述第一转换关系。
在一种可能的实施方式中，所述处理单元502，用于确定在所述局部采集装置采集每张所述图像数据所对应的采集时刻，所述局部采集装置的实时位姿信息时，具体用于：获取在采集每张所述图像数据所对应的每个采集时刻，所述AP对所述STA的实时定位结果；基于所述初始时刻所述AP对所述STA的初始定位结果、所述初始时刻所述STA在第四坐标系下的初始位姿信息以及所述实时定位结果，得到每个采集时刻所述STA在所述第四坐标系下的实时位姿信息，其中，所述第四坐标系的坐标原点由所述初始时刻所述STA的位姿确定；根据所述STA在所述第四坐标系下的实时位姿信息、所述第三转换矩阵确定所述局部采集装置在所述第四坐标系下的实时位姿信息；将所述局部采集装置在所述第四坐标系下的实时位姿信息进行坐标转换，得到所述局部采集装置在所述指定坐标系下的实时位姿信息。
此外，所述处理单元502，还用于基于所述AP对所述STA的实时定位结果，检测所述可移动设备在移动过程中存在的回环异常。
在一种可能的设计中，所述处理单元502，还用于在获取在所述可移动设备移动过程中所述局部采集装置采集的多张图像数据之前，基于所述当前的全局点云地图为所述可移动设备规划移动路径；根据所述局部采集装置的实时位姿信息和所述移动路径生成移动指令；所述收发单元501，还用于向所述可移动设备的控制器发送所述移动指令，以使所述控制器控制所述可移动设备根据所述移动指令进行移动。
需要说明的是，本申请实施例中对模块的划分是示意性的，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，另外，在本申请各个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。
集成的单元如果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读取存储介质中。基于这样的理解，本申请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介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)或处理器(processor)执行本申请各个实施例方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(read-only memory，ROM)、随机存取存储器(random access memory，RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
基于与上述三维地图的构建方法相同的构思，如图6所示，本申请实施例还提供了一种三维地图的构建装置600的结构示意图。装置600可用于实现上述方法实施例中描述的方法，可以参见上述方法实施例中的说明。装置600可以包括一个或多个处理器601。处理器601可以是通用处理器或者专用处理器等。例如可以是基带处理器、或中央处理器。基带处理器可以用于对通信协议以及通信数据进行处理，中央处理器可以用于对三维地图的构建装置(如，基站、终端、或芯片等)进行控制，执行软件程序，处理软件程序的数据。三维地图的构建装置可以包括收发单元，用以实现信号的输入(接收)和输出(发送)。 例如，收发单元可以为收发器，射频芯片等。
装置600包括一个或多个处理器601，一个或多个处理器601可实现上述所示的实施例中所示的方法。
可选的，处理器601除了实现上述所示的实施例的方法，还可以实现其他功能。
可选的，一种设计中，处理器601可以执行指令，使得装置600执行上述方法实施例中描述的方法。指令可以全部或部分存储在处理器内，如指令603，也可以全部或部分存储在与处理器耦合的存储器602中，如指令604，也可以通过指令603和604共同使得装置600执行上述方法实施例中描述的方法。
在又一种可能的设计中装置600中可以包括一个或多个存储器602，其上存有指令604，指令可在处理器上被运行，使得装置600执行上述方法实施例中描述的方法。可选的，存储器中还可以存储有数据。可选的处理器中也可以存储指令和/或数据。例如，一个或多个存储器602可以存储上述实施例中所描述的对应关系，或者上述实施例中所涉及的相关的参数或表格等。处理器和存储器可以单独设置，也可以集成在一起。
在又一种可能的设计中，装置600还可以包括收发器605以及天线606。处理器601可以称为处理单元，对装置(终端或者基站)进行控制。收发器605可以称为收发机、收发电路、或者收发单元等，用于通过天线606实现装置的收发功能。
应注意，本申请实施例中的处理器可以是一种集成电路芯片，具有信号的处理能力。在实现过程中，上述方法实施例的各步骤可以通过处理器中的硬件的集成逻辑电路702或者软件形式的指令完成。上述的处理器可以是通用处理器、数字信号处理器(digital signal processor，DSP)、专用集成电路(application specific integrated circuit，ASIC)、现成可编程门阵列(field programmable gate array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件。可以实现或者执行本申请实施例中的公开的各方法、步骤及逻辑框图。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。结合本申请实施例所公开的方法的步骤可以直接体现为硬件译码处理器执行完成，或者用译码处理器中的硬件及软件模块组合执行完成。软件模块可以位于随机存储器，闪存、只读存储器，可编程只读存储器或者电可擦写可编程存储器、寄存器等本领域成熟的存储介质中。该存储介质位于存储器，处理器读取存储器中的信息，结合其硬件完成上述方法的步骤。
可以理解，本申请实施例中的存储器可以是易失性存储器或非易失性存储器，或可包括易失性和非易失性存储器两者。其中，非易失性存储器可以是只读存储器(ROM)、可编程只读存储器(programmable ROM，PROM)、可擦除可编程只读存储器(erasable PROM，EPROM)、电可擦除可编程只读存储器(electrically EPROM，EEPROM)或闪存。易失性存储器可以是随机存取存储器(RAM)，其用作外部高速缓存。通过示例性但不是限制性说明，许多形式的RAM可用，例如静态随机存取存储器(static RAM，SRAM)、动态随机存取存储器(dynamic RAM，DRAM)、同步动态随机存取存储器(synchronous DRAM，SDRAM)、双倍数据速率同步动态随机存取存储器(double data rate SDRAM，DDR SDRAM)、增强型同步动态随机存取存储器(enhanced SDRAM，ESDRAM)、同步连接动态随机存取存储器(synchlink DRAM，SLDRAM)和直接内存总线随机存取存储器(direct rambus RAM，DR RAM)。应注意，本文描述的系统和方法的存储器旨在包括但不限于这些和任意其它适合类型的存储器。
本申请实施例还提供了一种计算机存储介质，其上存储有计算机程序，该计算机程序被计算机执行时实现上述所示的任一方法实施例的三维地图的构建方法。
本申请实施例还提供了一种计算机程序产品，该计算机程序产品被计算机执行时实现上述所示的任一方法实施例的三维地图的构建方法。
在上述实施例中，可以全部或部分地通过软件、硬件、固件或者其任意组合来实现。当使用软件实现时，可以全部或部分地以计算机程序产品的形式实现。计算机程序产品包括一个或多个计算机指令。在计算机上加载和执行计算机指令时，全部或部分地产生按照本申请实施例的流程或功能。计算机可以是通用计算机、专用计算机、计算机网络、或者其他可编程装置。计算机指令可以存储在计算机可读存储介质中，或者从一个计算机可读存储介质向另一个计算机可读存储介质传输，例如，计算机指令可以从一个网站站点、计算机、服务器或数据中心通过有线(例如同轴电缆、光纤、数字用户线(digital subscriber line，DSL))或无线(例如红外、无线、微波等)方式向另一个网站站点、计算机、服务器或数据中心进行传输。计算机可读存储介质可以是计算机能够存取的任何可用介质或者是包含一个或多个可用介质集成的服务器、数据中心等数据存储设备。可用介质可以是磁性介质(例如，软盘、硬盘、磁带)、光介质(例如，高密度数字视频光盘(digital video disc，DVD))、或者半导体介质(例如，固态硬盘(solid state disk，SSD))等。
本申请实施例还提供了一种处理装置，包括处理器和接口；处理器，用于执行上述所示的任一方法实施例的三维地图的构建方法。
应理解，上述处理装置可以是一个芯片，处理器可以通过硬件来实现也可以通过软件来实现，当通过硬件实现时，该处理器可以是逻辑电路702、集成电路等；当通过软件来实现时，该处理器可以是一个通用处理器，通过读取存储器中存储的软件代码来实现，该存储器可以集成在处理器中，可以位于处理器之外，独立存在。
如图7所示，本申请实施例还提供了一种芯片700，包括输入输出接口701和逻辑电路702，输入输出接口701用于接收/输出代码指令或信息，逻辑电路702用于执行代码指令或根据信息，以执行上述所示的任一方法实施例的三维地图的构建方法。
芯片700可以实现上述实施例中处理单元和/或收发单元所示的功能。
例如，输入输出接口701用于获当前的全局点云地图。
又如，输入输出接口701用于获取在可移动设备移动过程中，设置于所述可移动设备上的局部采集装置采集的多张图像数据。
本领域普通技术人员可以意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，能够以电子硬件、计算机软件或者二者的结合来实现，为了清楚地说明硬件和软件的可互换性，在上述说明中已经按照功能一般性地描述了各示例的组成及步骤。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的范围。
所属领域的技术人员可以清楚地了解到，为了描述的方便和简洁，上述描述的系统、装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在本申请所提供的几个实施例中，应该理解到，所揭露的装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合 或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另外，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口、装置或单元的间接耦合或通信连接，也可以是电的，机械的或其它的形式连接。
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，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本申请实施例方案的目的。
另外，在本申请各个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，也可以是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。
通过以上的实施方式的描述，所属领域的技术人员可以清楚地了解到本申请可以用硬件实现，或固件实现，或它们的组合方式来实现。当使用软件实现时，可以将上述功能存储在计算机存储介质中或作为计算机存储介质上的一个或多个指令或代码进行传输。计算机存储介质包括计算机存储介质和通信介质，其中通信介质包括便于从一个地方向另一个地方传送计算机程序的任何介质。存储介质可以是计算机能够存取的任何可用介质。以此为例但不限于：计算机存储介质可以包括RAM、ROM、EEPROM、CD-ROM或其他光盘存储、磁盘存储介质或者其他磁存储设备、或者能够用于携带或存储具有指令或数据结构形式的期望的程序代码并能够由计算机存取的任何其他介质。此外。任何连接可以适当的成为计算机存储介质。例如，如果软件是使用同轴电缆、光纤光缆、双绞线、数字用户线(DSL)或者诸如红外线、无线电和微波之类的无线技术从网站、服务器或者其他远程源传输的，那么同轴电缆、光纤光缆、双绞线、DSL或者诸如红外线、无线和微波之类的无线技术包括在所属介质的定影中。如本申请所使用的，盘(Disk)和碟(disc)包括压缩光碟(CD)、激光碟、光碟、数字通用光碟(DVD)、软盘和蓝光光碟，其中盘通常磁性的复制数据，而碟则用激光来光学的复制数据。上面的组合也应当包括在计算机存储介质的保护范围之内。

Claims (15)

  1. 一种三维地图的构建方法，其特征在于，包括：
    三维地图的构建装置获取当前的全局点云地图；以及，
    所述三维地图的构建装置获取在可移动设备移动过程中，设置于所述可移动设备上的局部采集装置采集的多张图像数据；并，
    所述三维地图的构建装置确定在所述局部采集装置采集每张所述图像数据所对应的采集时刻，所述局部采集装置的实时位姿信息；
    所述三维地图的构建装置基于所述当前的全局点云地图、所述多张图像数据和所述局部采集装置的实时位姿信息进行三维地图的构建。
  2. 根据权利要求1所述的方法，其特征在于，所述三维地图构建于指定坐标系下，所述指定坐标系为以下坐标系中任一坐标系：由初始时刻所述全局采集装置的位姿确定的第一坐标系、由所述初始时刻所述局部采集装置的位姿确定的第二坐标系、世界坐标系、以任一固定空间点的位姿确定的第三坐标系；
    所述三维地图的构建装置基于所述当前的全局点云地图、所述多张图像数据和所述局部采集装置的实时位姿信息进行三维地图的构建，包括：
    确定所述当前的全局点云地图、所述多张图像数据和所述局部采集装置的实时位姿信息分别所在的原始坐标系；
    对于不同于所述指定坐标系的原始坐标系，将该原始坐标系下的地图数据基于转换关系进行坐标转换，得到所述指定坐标系下的地图数据，所述转换关系根据该原始坐标系和所述指定坐标系的坐标原点之间的位姿关系确定，该原始坐标系下的地图数据包括所述当前的全局点云地图、所述多张图像数据和所述局部采集装置的实时位姿信息中的一种或多种；
    基于所述指定坐标系下的所述当前的全局点云地图、所述多张图像数据和所述局部采集装置的实时位姿信息进行三维地图的构建，得到所述指定坐标系下的三维地图。
  3. 根据权利要求2所述的方法，其特征在于，所述全局采集装置与接入点AP相对位姿固定，所述局部采集装置与工作站STA相对位姿固定，所述AP和所述STA进行通信；
    若所述不同于所述指定坐标系的原始坐标系为所述第一坐标系，所述指定坐标系为所述第二坐标系，所述转换关系为第一转换关系，所述三维地图的构建装置根据以下方式确定所述第一转换关系：
    根据所述全局采集装置与所述AP的相对位姿确定第一转换矩阵、根据所述AP对所述STA的定位结果确定第二转换矩阵、根据所述STA与所述局部采集装置的相对位姿确定第三转换矩阵；
    基于所述第一转换矩阵、所述第二转换矩阵和所述第三转换矩阵的乘积，得到所述第一转换关系。
  4. 根据权利要求3所述的方法，其特征在于，所述三维地图的构建装置确定在所述局部采集装置采集每张所述图像数据所对应的采集时刻，所述局部采集装置的实时位姿信息，包括：
    获取在采集每张所述图像数据所对应的每个采集时刻，所述AP对所述STA的实时定位结果；
    基于所述初始时刻所述AP对所述STA的初始定位结果、所述初始时刻所述STA在第四坐标系下的初始位姿信息以及所述实时定位结果，得到每个采集时刻所述STA在所述第四坐标系下的实时位姿信息，其中，所述第四坐标系的坐标原点由所述初始时刻所述STA的位姿确定；
    根据所述STA在所述第四坐标系下的实时位姿信息、所述第三转换矩阵确定所述局部采集装置在所述第四坐标系下的实时位姿信息；
    将所述局部采集装置在所述第四坐标系下的实时位姿信息进行坐标转换，得到所述局部采集装置在所述指定坐标系下的实时位姿信息。
  5. 根据权利要求3或4所述的方法，其特征在于，所述方法还包括：
    所述三维地图的构建装置基于所述AP对所述STA的实时定位结果，检测所述可移动设备在移动过程中存在的回环异常。
  6. 根据权利要求1～5任一项所述的方法，其特征在于，所述三维地图的构建装置获取在所述可移动设备移动过程中所述局部采集装置采集的多张图像数据之前，所述方法还包括：
    所述三维地图的构建装置基于所述当前的全局点云地图为所述可移动设备规划移动路径；
    所述三维地图的构建装置根据所述局部采集装置的实时位姿信息和所述移动路径生成移动指令；
    所述三维地图的构建装置向所述可移动设备的控制器发送所述移动指令，以使所述控制器控制所述可移动设备根据所述移动指令进行移动。
  7. 一种三维地图的构建装置，其特征在于，包括收发单元和处理单元；
    所述收发单元，用于获取当前的全局点云地图；以及，
    所述收发单元，还用于获取在可移动设备移动过程中，设置于所述可移动设备上的局部采集装置采集的多张图像数据；并，
    所述处理单元，用于确定在所述局部采集装置采集每张所述图像数据所对应的采集时刻，所述局部采集装置的实时位姿信息；
    所述处理单元，还用于基于所述当前的全局点云地图、所述多张图像数据和所述局部采集装置的实时位姿信息进行三维地图的构建。
  8. 根据权利要求7所述的装置，其特征在于，所述三维地图构建于指定坐标系下，所述指定坐标系为以下坐标系中任一坐标系：由初始时刻所述全局采集装置的位姿确定的第一坐标系、由所述初始时刻所述局部采集装置的位姿确定的第二坐标系、世界坐标系、以任一固定空间点的位姿确定的第三坐标系；
    所述处理单元，用于基于所述当前的全局点云地图、所述多张图像数据和所述局部采集装置的实时位姿信息进行三维地图的构建时，具体用于：
    确定所述当前的全局点云地图、所述多张图像数据和所述局部采集装置的实时位姿信息分别所在的原始坐标系；
    对于不同于所述指定坐标系的原始坐标系，将该原始坐标系下的地图数据基于转换关系进行坐标转换，得到所述指定坐标系下的地图数据，所述转换关系根据该原始坐标系和所述指定坐标系的坐标原点之间的位姿关系确定，该原始坐标系下的地图数据包括所述当前的全局点云地图、所述多张图像数据和所述局部采集装置的实时位姿信息中的一种或多 种；
    基于所述指定坐标系下的所述当前的全局点云地图、所述多张图像数据和所述局部采集装置的实时位姿信息进行三维地图的构建，得到所述指定坐标系下的三维地图。
  9. 根据权利要求8所述的装置，其特征在于，所述全局采集装置与接入点AP相对位姿固定，所述局部采集装置与工作站STA相对位姿固定，所述AP和所述STA进行通信；
    若所述不同于所述指定坐标系的原始坐标系为所述第一坐标系，所述指定坐标系为所述第二坐标系，所述转换关系为第一转换关系，所述处理单元，用于根据以下方式确定所述第一转换关系：
    根据所述全局采集装置与所述AP的相对位姿确定第一转换矩阵、根据所述AP对所述STA的定位结果确定第二转换矩阵、根据所述STA与所述局部采集装置的相对位姿确定第三转换矩阵；
    基于所述第一转换矩阵、所述第二转换矩阵和所述第三转换矩阵的乘积，得到所述第一转换关系。
  10. 根据权利要求9所述的装置，其特征在于，所述处理单元，用于确定在所述局部采集装置采集每张所述图像数据所对应的采集时刻，所述局部采集装置的实时位姿信息时，具体用于：
    获取在采集每张所述图像数据所对应的每个采集时刻，所述AP对所述STA的实时定位结果；
    基于所述初始时刻所述AP对所述STA的初始定位结果、所述初始时刻所述STA在第四坐标系下的初始位姿信息以及所述实时定位结果，得到每个采集时刻所述STA在所述第四坐标系下的实时位姿信息，其中，所述第四坐标系的坐标原点由所述初始时刻所述STA的位姿确定；
    根据所述STA在所述第四坐标系下的实时位姿信息、所述第三转换矩阵确定所述局部采集装置在所述第四坐标系下的实时位姿信息；
    将所述局部采集装置在所述第四坐标系下的实时位姿信息进行坐标转换，得到所述局部采集装置在所述指定坐标系下的实时位姿信息。
  11. 根据权利要求9或10所述的装置，其特征在于，所述处理单元，还用于基于所述AP对所述STA的实时定位结果，检测所述可移动设备在移动过程中存在的回环异常。
  12. 根据权利要求7～11任一项所述的装置，其特征在于，所述处理单元，还用于在获取在所述可移动设备移动过程中所述局部采集装置采集的多张图像数据之前，基于所述当前的全局点云地图为所述可移动设备规划移动路径；
    根据所述局部采集装置的实时位姿信息和所述移动路径生成移动指令；
    所述收发单元，还用于向所述可移动设备的控制器发送所述移动指令，以使所述控制器控制所述可移动设备根据所述移动指令进行移动。
  13. 一种计算设备，其特征在于，所述计算设备包括存储器和一个或多个处理器；其中，所述存储器存储计算机程序代码，所述计算机程序代码包括计算机指令；当所述计算机指令被所述处理器执行时，使得如权利要求1至6中任一项所述的方法被执行。
  14. 一种计算机设备集群，其特征在于，所述计算机设备集群包括至少一个如权利要求13所述的计算设备。
  15. 一种计算机存储介质，其特征在于，所述计算机存储介质中存储有计算机程序，当 所述计算机程序被计算机执行时，使得如权利要求1至6任一项所述的方法被执行。
PCT/CN2021/124676 2021-02-01 2021-10-19 一种三维地图的构建方法及装置 Ceased WO2022160790A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
KR1020237028996A KR20230137395A (ko) 2021-02-01 2021-10-19 3차원 지도 구축 방법 및 장치
EP21922381.5A EP4283567A4 (en) 2021-02-01 2021-10-19 METHOD AND APPARATUS FOR CONSTRUCTING THREE-DIMENSIONAL CARDS
JP2023546328A JP2024509690A (ja) 2021-02-01 2021-10-19 三次元地図を構築する方法および装置

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110136015.0 2021-02-01
CN202110136015.0A CN114842156B (zh) 2021-02-01 2021-02-01 一种三维地图的构建方法及装置

Publications (1)

Publication Number Publication Date
WO2022160790A1 true WO2022160790A1 (zh) 2022-08-04

Family

ID=82560751

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/124676 Ceased WO2022160790A1 (zh) 2021-02-01 2021-10-19 一种三维地图的构建方法及装置

Country Status (5)

Country Link
EP (1) EP4283567A4 (zh)
JP (1) JP2024509690A (zh)
KR (1) KR20230137395A (zh)
CN (1) CN114842156B (zh)
WO (1) WO2022160790A1 (zh)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115143941A (zh) * 2022-09-01 2022-10-04 山东省青东智能科技有限公司 一种基于云平台的智能测绘3d工业相机
CN115576955A (zh) * 2022-12-07 2023-01-06 成都智元汇信息技术股份有限公司 一种基于数据库的感知设备自建坐标信息存储方法及系统
CN115830263A (zh) * 2023-02-16 2023-03-21 四川省地质调查研究院 一种水文地质动态三维模型构建方法及系统
CN116563394A (zh) * 2023-07-10 2023-08-08 国科天成科技股份有限公司 一种异面点空间坐标标定系统和方法
CN116797744A (zh) * 2023-08-29 2023-09-22 武汉大势智慧科技有限公司 多时相实景三维模型的构建方法、系统及终端设备
CN117761717A (zh) * 2024-02-21 2024-03-26 天津大学四川创新研究院 一种自动回环三维重建系统及运行方法
CN118372258A (zh) * 2024-06-21 2024-07-23 西湖大学 分布式视觉集群机器人系统

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115524684B (zh) * 2022-09-13 2026-03-27 深圳市欢创科技股份有限公司 一种激光雷达畸变点云角度识别方法、装置及机器人
CN115657069B (zh) * 2022-10-19 2026-01-30 南方科技大学 三维地图创建方法、装置及测绘设备
CN118075686A (zh) * 2024-04-22 2024-05-24 南方电网调峰调频发电有限公司 抽水蓄能基建工程目标智能感知方法、装置和计算机设备

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108226938A (zh) * 2017-12-08 2018-06-29 华南理工大学 一种agv小车的定位系统和方法
CN108320329A (zh) * 2018-02-02 2018-07-24 维坤智能科技（上海）有限公司 一种基于3d激光的3d地图创建方法
CN109087393A (zh) * 2018-07-23 2018-12-25 汕头大学 一种构建三维地图的方法
KR20190064311A (ko) * 2017-11-30 2019-06-10 주식회사 모빌테크 라이다를 이용한 지도 생성 방법 및 장치
CN110047142A (zh) * 2019-03-19 2019-07-23 中国科学院深圳先进技术研究院 无人机三维地图构建方法、装置、计算机设备及存储介质
CN110084853A (zh) * 2019-04-22 2019-08-02 北京易达图灵科技有限公司 一种视觉定位方法及系统
CN112105890A (zh) * 2019-01-30 2020-12-18 百度时代网络技术（北京）有限公司 用于自动驾驶车辆的基于rgb点云的地图生成系统

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5719277B2 (ja) * 2011-11-09 2015-05-13 日本電信電話株式会社 物体座標系変換行列推定成否判定装置および物体座標系変換行列推定成否判定方法ならびにそのプログラム
FR3044574B1 (fr) * 2015-12-03 2019-06-14 Institut Maupertuis Robot de soudage par friction malaxage
CN107462226A (zh) * 2017-02-28 2017-12-12 苏州迪美格智能科技有限公司 一种三维地图测绘系统
US11537140B2 (en) * 2017-09-04 2022-12-27 Nidec-Shimpo Corporation Mobile body, location estimation device, and computer program
CN109341707B (zh) * 2018-12-03 2022-04-08 南开大学 未知环境下移动机器人三维地图构建方法
CN111337947B (zh) * 2020-05-18 2020-09-22 深圳市智绘科技有限公司 即时建图与定位方法、装置、系统及存储介质
CN112162561A (zh) * 2020-10-13 2021-01-01 上海美迪索科电子科技有限公司 一种地图构建优化方法、装置、介质及设备
CN112197764B (zh) * 2020-12-07 2021-04-06 广州极飞科技有限公司 实时位姿确定方法、装置及电子设备
CN112223302B (zh) * 2020-12-17 2021-02-26 国网瑞嘉(天津)智能机器人有限公司 基于多传感器的带电作业机器人的快速标定方法及装置

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20190064311A (ko) * 2017-11-30 2019-06-10 주식회사 모빌테크 라이다를 이용한 지도 생성 방법 및 장치
CN108226938A (zh) * 2017-12-08 2018-06-29 华南理工大学 一种agv小车的定位系统和方法
CN108320329A (zh) * 2018-02-02 2018-07-24 维坤智能科技（上海）有限公司 一种基于3d激光的3d地图创建方法
CN109087393A (zh) * 2018-07-23 2018-12-25 汕头大学 一种构建三维地图的方法
CN112105890A (zh) * 2019-01-30 2020-12-18 百度时代网络技术（北京）有限公司 用于自动驾驶车辆的基于rgb点云的地图生成系统
CN110047142A (zh) * 2019-03-19 2019-07-23 中国科学院深圳先进技术研究院 无人机三维地图构建方法、装置、计算机设备及存储介质
CN110084853A (zh) * 2019-04-22 2019-08-02 北京易达图灵科技有限公司 一种视觉定位方法及系统

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4283567A4

Cited By (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115143941A (zh) * 2022-09-01 2022-10-04 山东省青东智能科技有限公司 一种基于云平台的智能测绘3d工业相机
CN115576955A (zh) * 2022-12-07 2023-01-06 成都智元汇信息技术股份有限公司 一种基于数据库的感知设备自建坐标信息存储方法及系统
CN115576955B (zh) * 2022-12-07 2023-02-14 成都智元汇信息技术股份有限公司 一种基于数据库的感知设备自建坐标信息存储方法及系统
CN115830263A (zh) * 2023-02-16 2023-03-21 四川省地质调查研究院 一种水文地质动态三维模型构建方法及系统
CN115830263B (zh) * 2023-02-16 2023-04-18 四川省地质调查研究院 一种水文地质动态三维模型构建方法及系统
CN116563394A (zh) * 2023-07-10 2023-08-08 国科天成科技股份有限公司 一种异面点空间坐标标定系统和方法
CN116563394B (zh) * 2023-07-10 2023-09-22 国科天成科技股份有限公司 一种异面点空间坐标标定系统和方法
CN116797744A (zh) * 2023-08-29 2023-09-22 武汉大势智慧科技有限公司 多时相实景三维模型的构建方法、系统及终端设备
CN116797744B (zh) * 2023-08-29 2023-11-07 武汉大势智慧科技有限公司 多时相实景三维模型的构建方法、系统及终端设备
CN117761717A (zh) * 2024-02-21 2024-03-26 天津大学四川创新研究院 一种自动回环三维重建系统及运行方法
CN117761717B (zh) * 2024-02-21 2024-05-07 天津大学四川创新研究院 一种自动回环三维重建系统及运行方法
CN118372258A (zh) * 2024-06-21 2024-07-23 西湖大学 分布式视觉集群机器人系统

Also Published As

Publication number Publication date
JP2024509690A (ja) 2024-03-05
KR20230137395A (ko) 2023-10-04
CN114842156A (zh) 2022-08-02
EP4283567A4 (en) 2024-07-31
CN114842156B (zh) 2025-08-12
EP4283567A1 (en) 2023-11-29

Similar Documents

Publication Publication Date Title
WO2022160790A1 (zh) 一种三维地图的构建方法及装置
Sarlin et al. Lamar: Benchmarking localization and mapping for augmented reality
US11276191B2 (en) Estimating dimensions for an enclosed space using a multi-directional camera
CN108369743B (zh) 使用多方向相机地图构建空间
WO2021233029A1 (en) Simultaneous localization and mapping method, device, system and storage medium
CN106940186B (zh) 一种机器人自主定位与导航方法及系统
CN113869422B (zh) 多相机目标匹配方法、系统、电子设备及可读存储介质
WO2021195939A1 (zh) 一种双目拍摄装置的外参的标定方法、可移动平台及系统
WO2022027611A1 (zh) 移动机器人的定位方法、构建地图的方法及移动机器人
Cheng et al. 3D radar and camera co-calibration: A flexible and accurate method for target-based extrinsic calibration
WO2024021340A1 (zh) 机器人跟随方法、装置、机器人及计算机可读存储介质
TW202538452A (zh) 自移動設備的控制方法及裝置、設備、媒體與程式產品
CN116704038A (zh) 铺贴机器人的控制方法及相关设备
JP2023159484A (ja) 情報処理装置、情報処理システム、情報処理装置の制御方法およびプログラム
CN113570663B (zh) 基于单线激光雷达和顶视摄像头融合的室内定位方法
KR102852930B1 (ko) 거리 및 각도기반 라이다 포인트의 투영법을 달리하는 카메라 및 라이다의 캘리브레이션 방법 및 서버
TW202539260A (zh) 自移動設備的環境感知方法、自移動設備、電腦儲存媒體及電子設備
JP2023503750A (ja) ロボットの位置決め方法及び装置、機器、記憶媒体
CN115019167B (zh) 基于移动终端的融合定位方法、系统、设备及存储介质
CN118409589A (zh) 限制区域设置方法、自移动设备、终端设备及存储介质
CN118565457A (zh) 一种基于观测方向的栅格地图构建方法、装置及智能移动设备
WO2023088127A1 (zh) 室内导航方法、服务器、装置和终端
KR20240013706A (ko) 자기 위치 측정이 가능한 로봇 및 위치 측정 방법
US11662740B2 (en) Position estimating apparatus, method for determining position of movable apparatus, and non-transitory computer readable medium
Chu et al. Image to Lidar Registration using image feature matching

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: 21922381

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 2023546328

Country of ref document: JP

ENP Entry into the national phase

Ref document number: 20237028996

Country of ref document: KR

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2021922381

Country of ref document: EP

Effective date: 20230824

WWR Wipo information: refused in national office

Ref document number: 1020237028996

Country of ref document: KR