WO2022193640A1 - 一种机器人标定方法、装置、机器人及存储介质 - Google Patents

一种机器人标定方法、装置、机器人及存储介质 Download PDF

Info

Publication number
WO2022193640A1
WO2022193640A1 PCT/CN2021/124617 CN2021124617W WO2022193640A1 WO 2022193640 A1 WO2022193640 A1 WO 2022193640A1 CN 2021124617 W CN2021124617 W CN 2021124617W WO 2022193640 A1 WO2022193640 A1 WO 2022193640A1
Authority
WO
WIPO (PCT)
Prior art keywords
operation space
robot
calibration
information
preset
Prior art date
Application number
PCT/CN2021/124617
Other languages
English (en)
French (fr)
Inventor
张硕
谢铮
刘益彰
张志豪
曾英夫
熊友军
Original Assignee
深圳市优必选科技股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳市优必选科技股份有限公司 filed Critical 深圳市优必选科技股份有限公司
Publication of WO2022193640A1 publication Critical patent/WO2022193640A1/zh
Priority to US18/369,858 priority Critical patent/US20240001558A1/en

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J9/00—Programme-controlled manipulators
    • B25J9/16—Programme controls
    • B25J9/1679—Programme controls characterised by the tasks executed
    • B25J9/1692—Calibration of manipulator
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J9/00—Programme-controlled manipulators
    • B25J9/08—Programme-controlled manipulators characterised by modular constructions
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J9/00—Programme-controlled manipulators
    • B25J9/16—Programme controls
    • B25J9/1656—Programme controls characterised by programming, planning systems for manipulators
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J9/00—Programme-controlled manipulators
    • B25J9/16—Programme controls
    • B25J9/1679—Programme controls characterised by the tasks executed
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J9/00—Programme-controlled manipulators
    • B25J9/16—Programme controls
    • B25J9/1694—Programme controls characterised by use of sensors other than normal servo-feedback from position, speed or acceleration sensors, perception control, multi-sensor controlled systems, sensor fusion
    • B25J9/1697—Vision controlled systems
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B2219/00—Program-control systems
    • G05B2219/30—Nc systems
    • G05B2219/39—Robotics, robotics to robotics hand
    • G05B2219/39016—Simultaneous calibration of manipulator and camera

Definitions

  • the present application belongs to the technical field of artificial intelligence, and in particular relates to a robot calibration method, device, robot and storage medium.
  • the embodiments of the present application provide a robot calibration method, device, robot and storage medium, which aim to solve the problems of cumbersome and low efficiency in the current calibration process.
  • an embodiment of the present application provides a method for calibrating a robot, including:
  • the corresponding operation space is gridded to obtain the operation space point after the operation space is gridded;
  • the hand-eye of the robot is calibrated.
  • the corresponding operation space is gridded to obtain the operation space points after the operation space is gridded, including:
  • the operation space information determine the three-dimensional information of the operation space
  • the operation space is divided into grids to obtain a plurality of sub-operation space positions after gridding;
  • the total number of operation space points after gridding of the operation space is obtained.
  • the method before controlling the execution end to move to an operation space point that meets a preset requirement, the method includes:
  • the controlling the execution end to move to an operation space point that meets a preset requirement, and obtaining calibration data includes:
  • the calibration data collected under the corresponding operation space points are obtained.
  • calibrating the hand and eye of the robot according to the obtained calibration data includes:
  • the external parameters of the camera are updated through the LM iterative algorithm to obtain an accurate calibration result.
  • the external parameters of the camera are updated through the LM iterative algorithm to obtain an accurate calibration result, including:
  • the external parameters of the camera are updated through the LM iterative algorithm, and the updated external parameters are used as the preliminary calibration result.
  • the error information includes an error matrix; and the calculating a Jacobian matrix and a residual value according to the error information includes:
  • the error matrix is evaluated to obtain the residual value.
  • an embodiment of the present application provides a robot calibration device, including:
  • an acquisition module used for acquiring the space information of the robot's execution terminal operation
  • a gridding module configured to grid the corresponding operation space according to the operation space information, and obtain the operation space point after the operation space is gridded;
  • control module configured to control the execution end to move to an operation space point that meets preset requirements, and obtain calibration data
  • the calibration module is used for calibrating the hand and eye of the robot according to the obtained calibration data.
  • an embodiment of the present application provides a robot, including a memory, a processor, and a computer program stored in the memory and executable on the processor, which is implemented when the processor executes the computer program The steps of the above robot calibration method.
  • an embodiment of the present application provides a computer-readable storage medium, where a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the robot calibration method are implemented.
  • an embodiment of the present application provides a computer program product, which, when the computer program product runs on an electronic device, causes the electronic device to execute the steps of the above-mentioned robot calibration method.
  • the embodiments of the present application have the following beneficial effects: the embodiments of the present application can obtain the operation space information of the robot performing terminal operation; according to the operation space information, grid the corresponding operation space to obtain the operation space The operation space point after spatial gridding; control the execution end to move to the operation space point that meets the preset requirements, and obtain calibration data; according to the obtained calibration data, the hand-eye of the robot is calibrated. Since the operation space can be gridded according to the operation space information, the operation space points can be determined, and the terminal movement can be automatically controlled to meet the preset requirements. The calibration data can be obtained automatically and accurately, which makes the calibration process simple. , and improve the efficiency.
  • FIG. 1 is a schematic flowchart of a robot calibration method provided by an embodiment of the present application.
  • FIG. 2 is a schematic flowchart of a specific flow of step S102 provided by an embodiment of the present application
  • FIG. 3 is a specific flowchart of step S103 provided by an embodiment of the present application.
  • FIG. 4 is a schematic schematic diagram of a specific flow of step S104 provided by an embodiment of the present application.
  • FIG. 5 is a schematic structural diagram of a robot calibration device provided by an embodiment of the present application.
  • FIG. 6 is a schematic structural diagram of a robot provided by an embodiment of the present application.
  • the term “if” may be contextually interpreted as “when” or “once” or “in response to determining” or “in response to detecting “.
  • the phrases “if it is determined” or “if the [described condition or event] is detected” may be interpreted, depending on the context, to mean “once it is determined” or “in response to the determination” or “once the [described condition or event] is detected. ]” or “in response to detection of the [described condition or event]”.
  • references in this specification to "one embodiment” or “some embodiments” and the like mean that a particular feature, structure or characteristic described in connection with the embodiment is included in one or more embodiments of the present application.
  • appearances of the phrases “in one embodiment,” “in some embodiments,” “in other embodiments,” “in other embodiments,” etc. in various places in this specification are not necessarily All refer to the same embodiment, but mean “one or more but not all embodiments” unless specifically emphasized otherwise.
  • the terms “including”, “including”, “having” and their variants mean “including but not limited to” unless specifically emphasized otherwise.
  • the robot calibration method provided in the embodiment of the present application can be applied to a robot, and the robot may be a robotic arm, a manipulator, a service robot, an entertainment robot, a military robot, an agricultural robot, or the like.
  • the embodiments of the present application do not limit any specific types of robots.
  • a method for calibrating a robot provided by an embodiment of the present application includes:
  • Step S101 obtaining the space information of the robot performing terminal operation.
  • the user can input the operation space information of the robot execution end, and when it is detected that the user inputs the operation space information of the robot execution end, the operation space information is obtained. Or pre-store the operation space information of the robot execution end, and directly obtain the pre-stored operation space information of the robot execution end.
  • Step S102 according to the operation space information, grid the corresponding operation space, and obtain the operation space point after the operation space is gridded.
  • the operation space information includes three-dimensional information of the operation space.
  • the corresponding operation space is divided into grids to obtain a plurality of operation space points.
  • the three-dimensional information of the operation space is the information of the length, width and height of the operation space.
  • the corresponding operation space is gridded to obtain the operation space point after the operation space is gridded, including steps S1021 to S1024:
  • Step S1021 Determine the three-dimensional information of the operation space according to the operation space information.
  • the three-dimensional information included in the operation space information is acquired. If the operation space is a cube, the three-dimensional information of the operation space may include the length, width and height information of the operation space.
  • Step S1022 Perform grid division on the operation space according to a preset distance sampling interval and the three-dimensional information, to obtain a plurality of sub-operation space positions after gridding.
  • the distance sampling interval is preset, and each dimension is divided at the preset distance sampling interval to obtain a plurality of sub-operation space position points.
  • Step S1023 determine the number of gestures of the execution end of each gridded sub-operation space position.
  • each operation position point can have a variety of postures. For example, if any of the three posture angles is different, it can be regarded as a different posture, and each sub-section is determined according to the preset angle sampling interval.
  • the number of gestures of the position points in the operation space can obtain multiple gestures of each sub-operation space position point, and the number of gestures of all the sub-operation space position points is taken as the total number of operation space points that can be operated in the whole operation space.
  • Step S1024 Obtain the total number of operation space points after gridding of the operation space according to the number of gestures at the execution end of each gridded operation space and the positions of a plurality of gridded sub-operation spaces.
  • the total number of operational space points that can be operated in the entire operation space can be determined.
  • the operation space is divided into grids, and a plurality of sub-operation space positions after gridding are obtained.
  • the operation space may be discretized into One by one grid point, make the robot move to these grid points respectively, for example, the operation space is a cube whose length is l, width is w, and height is h.
  • the preset distance sampling interval is ⁇ d
  • the preset angle sampling interval is ⁇ .
  • Step S103 Control the execution end to move to an operation space point that meets a preset requirement, and obtain calibration data.
  • the calibration data includes, but is not limited to, the position information of the preset calibration object in the image coordinate system and the pose information of the execution end in the base coordinate system.
  • the calibration data includes the position information of the preset calibration object in the image coordinate system obtained from each operation space point, and the posture information of the robot execution end in the base coordinate system.
  • Obtaining the position information of the preset calibration object in the image coordinate system may be: when the robot is controlled to perform the terminal movement to the corresponding operation space point, the image detection device detects the position information of the calibration object.
  • the posture information of the robot's execution end in the base coordinate system can be detected by the robot itself.
  • the executing robot can be a robot with eyes outside the hands, that is, the image detection device (such as a camera) is set on a fixed base (such as a fixed work surface), and the image detection device will not follow the execution of the robot. It can also be an eye-on-hand type robot, that is, the image detection device is at the execution end of the robot and will move with the execution end of the robot. If it is a robot with eyes outside the hands, the preset calibration object can be set to the execution end of the robot, and the image detection equipment (such as a camera) can be set under the fixed base, and the execution end can be controlled to move to the operation space point that meets the preset requirements.
  • the image detection device such as a camera
  • Relative motion can be generated between the calibration object and the image detection device, and the calibration data can be obtained by obtaining the position information of the preset calibration object in the image coordinate system at each operation space point, and the preset calibration object on the robot execution end in the base coordinate.
  • the calibration data can be obtained by obtaining the position information of the preset calibration object in the image coordinate system at each operation space point, and according to the robot execution
  • the motion parameter of the terminal acquires the posture information of the execution terminal in a base coordinate system, and the base coordinate system is a coordinate system established on the fixed base of the robot.
  • the method before controlling the execution end to move to an operation space point that meets a preset requirement, includes: determining the accessibility of each operation space point; wherein the accessibility is to determine the execution end Whether it can move to the corresponding operation space point; when the execution terminal can move to the corresponding operation space point, it is determined that the corresponding operation space point meets the preset requirements.
  • the execution end before controlling the execution end to move to an operation space point that meets a preset requirement, first determine whether each operation space point satisfies the preset requirement, and determine whether each operation space point meets the preset requirement through the corresponding operation space point. The accessibility is judged. If the robot execution end can move to the corresponding operation space point, it is determined that the operation space point meets the preset requirements. If the robot execution end cannot move to the corresponding operation space point, the operation space point is determined. Default requirements are not met.
  • the operation space points obtained by the above discretization process may not be reachable. Perform the inverse solution operation on each discrete operation space point to determine this Whether the position is reachable, if the operation space point is unreachable, it will be deleted from the sampling candidate set, that is, the execution end will not be controlled to move to the operation space point.
  • the distance x d of the operation space point is calculated by the interval. If it exists, it is determined to be reachable, and if it does not exist, it is determined to be unreachable.
  • the control of the execution end to move to an operation space point that meets a preset requirement to obtain calibration data includes steps S1031 to 1032:
  • Step S1031 controlling the execution end to move to an operation space point that satisfies a preset requirement, and judging the availability of the operation space point; wherein, the availability indicates whether the calibration data can be collected at the corresponding operation space point, and whether the collected calibration data Whether the data meets preset criteria.
  • the calibration data may not be detectable or available when the robot is at the operation space point. Therefore, the availability of the operation space point should be judged first.
  • the availability indicates whether the corresponding operation space point can be collected or not. to the calibration data, and whether the collected calibration data conforms to the preset standard.
  • the judgment of whether the calibration data can be collected can allow the execution end to move to the operation space point that meets the preset requirements, and check whether the pose of the execution end in the operation space point that meets the preset requirements can be measured. If it is not measurable, the corresponding The operation space point is deleted from the sampling candidate set, that is, the calibration data corresponding to the operation space point is not collected.
  • a standard for usability judgment can be set in advance, and it is determined whether the collected calibration data meets the preset standard.
  • the calibration object is set at the execution end, to judge whether the collected calibration data meets the preset standard, the third component of the axis of the calibration object at the execution end coordinate system can be obtained by calculating the motion parameters, and the calibration object is determined at the execution end.
  • the third component of the axis of the coordinate system should be greater than zero to ensure the stability of the measurement attitude (it is very important in practical applications, because although the camera can detect the calibration object in some positions, the attitude detection of the calibration object is wrong).
  • the image detection device is set at the execution end, and judging whether the collected calibration data meets the preset standard can be calculated by calculating the third component of the axis of the image detection device at the execution end coordinate system, and judging that the calibration object is at the execution end coordinate.
  • the third component of the axis of the system should be greater than zero to ensure the stability of the measurement attitude. It is determined that the third component of the axis of the coordinate system of the image detection device at the execution end should be greater than zero to ensure the stability of the measurement attitude.
  • Step S1032 for the operation space point where the calibration data can be collected and the collected calibration data meets the preset standard, obtain the calibration data collected under the corresponding operation space point.
  • an operation space point that can collect calibration data and the collected calibration data meets the preset standard may be a set of available sampling points, and the calibration data is collected from the set of available sampling points for the operation space point.
  • step S104 the hand-eye of the robot is calibrated according to the obtained calibration data.
  • calibrating the hand-eye of the robot includes solving the external parameters of the camera.
  • the fixed device can be an image detection device when the robot is on the top, and the robot with eyes outside the hand can be a calibration object.
  • the goal of solving the hand-eye calibration problem is to obtain the pose change relationship X between the image detection device and the execution end through the movement of the fixed device. It is assumed that the fixed device has a total of K+1 positions, where K ⁇ 2 and is an integer, Then K times of relative motion will be stored correspondingly.
  • the pose change relationship X is obtained, and the external parameters of the camera can be obtained from the pose change relationship X.
  • the hand-eye calibration of the robot includes steps S1041 to S1046:
  • Step S1041 Perform preliminary calibration on the hand-eye of the robot according to the obtained calibration data, and obtain a preliminary calibration result.
  • the obtained calibration result is taken as the preliminary calibration result.
  • step S1042 the position information of the calibration object in the image coordinate system is acquired, and according to the preliminary calibration result, the position information in the image coordinate system is converted into the first pose in the base coordinate system.
  • the position information under the image coordinate system of the calibration object is obtained through the image detection device, and the preliminary calibration result can be converted into the pose under the base coordinate system, that is, the pose of the calibration object in reality.
  • Step S1043 Determine the second pose of the calibration object in the base coordinate system according to the motion parameters of the execution end of the robot.
  • the robot's own control device determines the second pose of the calibration object in the base coordinate system according to the motion parameters of the robot's execution end, that is, the robot can know the position of the calibration object in the base coordinate system according to the kinematics algorithm. second pose.
  • Step S1044 determining the error information between the first pose and the second pose.
  • Step S1045 Calculate the Jacobian matrix and the residual value according to the error information.
  • the error information includes an error matrix; the calculating a Jacobian matrix and a residual value according to the error information includes: derivation of the error matrix to obtain the Jacobian matrix; The error matrix is evaluated to obtain the residual value.
  • the difference between the parameter matrices corresponding to the first pose and the second pose can be used to obtain an error matrix (which can also be regarded as a polynomial function), and the Jacobian matrix can be obtained by derivation of the error matrix.
  • the error matrix is evaluated to obtain the residual value.
  • Step S1046 according to the Jacobian matrix and the residual value, update the external parameters of the camera through the LM iterative algorithm to obtain an accurate calibration result.
  • the Jacobian matrix, the residual value and the external parameters of the preliminary calibration result are used as the independent variables of the corresponding formula of the LM iteration algorithm, and the external parameters to be updated are used as the dependent variables, and the external parameters of the camera are updated through the LM iterative algorithm to obtain Accurate calibration results.
  • updating the external parameters of the camera through the LM iterative algorithm to obtain an accurate calibration result including: according to the Jacobian matrix and the residual value , update the external parameters of the camera through the LM iterative algorithm, and use the updated external parameters as the preliminary calibration result, and return to execute.
  • the position information in the image coordinate system is converted into the base coordinate system. Steps of the first pose and subsequent steps, until the number of updates reaches a preset threshold or when it is determined that the error information is within a preset error range, the most recently updated external parameters of the camera are used as the precise calibration result.
  • the calibration result obtained is not necessarily the final accurate calibration result, and the steps in step S1042 and subsequent steps are re-executed after each iteration until the number of iteration updates reaches the preset number.
  • the threshold value or when it is determined that the error information is within the preset error range, the current external parameter updated this time is used as the precise calibration result.
  • the operation space information of the robot execution terminal can be obtained; according to the operation space information, the corresponding operation space can be gridded to obtain the operation space point after the operation space is gridded; and the movement of the execution terminal can be controlled.
  • the calibration data is obtained; according to the obtained calibration data, the hand-eye of the robot is calibrated. Since the operation space can be gridded according to the operation space information, the operation space points can be determined, and the terminal movement can be automatically controlled to meet the preset requirements.
  • the calibration data can be obtained automatically and accurately, which makes the calibration process simple. , and improve the efficiency.
  • the embodiments of the present application further provide a robot calibration device, which is used for performing the steps in the above embodiments of the robot calibration method.
  • the robot calibration device can be a virtual appliance in the terminal device, run by the processor of the terminal device, or the terminal device itself.
  • the robot calibration device 500 provided by the embodiment of the present application includes:
  • an acquisition module 501 configured to acquire the space information of the robot performing terminal operation
  • the gridding module 502 is configured to grid the corresponding operation space according to the operation space information, and obtain the operation space point after the operation space is gridded;
  • control module 503 configured to control the execution end to move to an operation space point that meets a preset requirement, and obtain calibration data
  • the calibration module 504 is configured to calibrate the hand-eye of the robot according to the obtained calibration data.
  • the meshing module 502 includes:
  • a first determining unit configured to determine three-dimensional information of the operation space according to the operation space information
  • a dividing unit configured to perform grid division on the operation space according to the preset distance sampling interval and the three-dimensional information, so as to obtain a plurality of sub-operation space positions after gridding
  • a second determining unit configured to determine, according to the preset angle sampling interval, the number of gestures at the execution end of each gridded sub-operation space position
  • the first obtaining unit is configured to obtain the total number of operation space points after gridding of the operation space according to the number of gestures of the execution end of each gridded operation space and the positions of the plurality of gridded sub-operation spaces.
  • the robotic calibration device 500 includes:
  • a third determination unit configured to determine the accessibility of each operation space point; wherein, the accessibility is to determine whether the execution terminal can move to the corresponding operation space point;
  • the movement unit is configured to determine that the corresponding operation space point satisfies the preset requirement when the execution terminal can move to the corresponding operation space point.
  • control module 503 includes:
  • a judgment unit configured to control the execution end to move to an operation space point that meets preset requirements, and determine the availability of the operation space point; wherein, the availability indicates whether the calibration data can be collected at the corresponding operation space point, and the collection Check whether the calibration data meets the preset standard;
  • the second obtaining unit is used for obtaining the calibration data collected under the corresponding operation space point for the operation space point where the calibration data can be collected and the collected calibration data meets the preset standard.
  • the calibration module 504 includes:
  • a preliminary calibration unit configured to perform preliminary calibration on the hand-eye of the robot according to the obtained calibration data, and obtain a preliminary calibration result
  • a conversion unit used for acquiring the position information of the calibration object under the image coordinate system, and converting the position information under the image coordinate system into the first pose under the base coordinate system according to the preliminary calibration result;
  • a fourth determination unit configured to determine the second pose of the calibration object in the base coordinate system according to the motion parameters of the execution end of the robot
  • a fifth determination unit configured to determine error information between the first pose and the second pose
  • a calculation unit configured to calculate the Jacobian matrix and the residual value according to the error information
  • the precise calibration unit is configured to update the external parameters of the camera through the LM iterative algorithm according to the Jacobian matrix and the residual value to obtain an accurate calibration result.
  • the precise calibration unit is specifically configured to: update the extrinsic parameters of the camera through the LM iterative algorithm according to the Jacobian matrix and the residual value, and use the updated extrinsic parameters as the preliminary calibration
  • the steps of converting the position information in the image coordinate system into the first pose in the base coordinate system according to the preliminary calibration result and the subsequent steps are returned to execute until the number of updates reaches a preset threshold or the error information is determined
  • the most recent update of the extrinsic parameters of the camera is used as the precise calibration result.
  • the error information includes an error matrix
  • the calculation unit is specifically configured to: derive the error matrix to obtain the Jacobian matrix; evaluate the error matrix to obtain the residual error value.
  • the operation space information of the robot execution terminal can be obtained; according to the operation space information, the corresponding operation space can be gridded to obtain the operation space point after the operation space is gridded; and the movement of the execution terminal can be controlled.
  • the calibration data is obtained; according to the obtained calibration data, the hand-eye of the robot is calibrated. Since the operation space can be gridded according to the operation space information, the operation space points can be determined, and the terminal movement can be automatically controlled to meet the preset requirements.
  • the calibration data can be obtained automatically and accurately, which makes the calibration process simple. , and improve the efficiency.
  • an embodiment of the present application further provides a robot 600 including: a processor 601, a memory 602, and a computer program 603 stored in the memory 602 and executable on the processor 601, such as Robot calibration procedure.
  • a robot 600 including: a processor 601, a memory 602, and a computer program 603 stored in the memory 602 and executable on the processor 601, such as Robot calibration procedure.
  • the processor 601 executes the computer program 603, the steps in each of the above embodiments of the robot calibration method are implemented.
  • the processor 601 executes the computer program 603 , the functions of the modules in the above-mentioned device embodiments, for example, the functions of the modules 501 to 504 shown in FIG. 5 , are implemented.
  • the computer program 603 may be divided into one or more modules, and the one or more modules are stored in the memory 602 and executed by the processor 601 to complete the present application.
  • the one or more modules may be a series of computer program instruction segments capable of accomplishing specific functions, and the instruction segments are used to describe the execution process of the computer program 603 in the robot 600 .
  • the computer program 603 can be divided into an acquisition module, a gridding module, a control module, and a calibration module. The specific functions of each module have been described in the above embodiments, and are not repeated here.
  • the robot 600 may be a robot with a mobile function, or a computing device such as a desktop computer, a notebook computer, a palmtop computer, and a cloud server.
  • the terminal device may include, but is not limited to, the processor 601 and the memory 602 .
  • FIG. 6 is only an example of the robot 600, and does not constitute a limitation to the robot 600. It may include more or less components than the one shown, or combine some components, or different components, such as
  • the terminal device may also include an input and output device, a network access device, a bus, and the like.
  • the so-called processor 601 may be a central processing unit (Central Processing Unit, CPU), or other general-purpose processors, digital signal processors (Digital Signal Processors, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), Field-Programmable Gate Array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.
  • a general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
  • the memory 602 may be an internal storage unit of the robot 600 , such as a hard disk or a memory of the robot 600 .
  • the memory 602 may also be an external storage device of the robot 600, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card equipped on the robot 600, Flash card (Flash Card) and so on.
  • the memory 602 may also include both an internal storage unit of the robot 600 and an external storage device.
  • the memory 602 is used to store the computer program and other programs and data required by the terminal device.
  • the memory 602 may also be used to temporarily store data that has been output or will be output.
  • the disclosed apparatus/terminal device and method may be implemented in other manners.
  • the apparatus/terminal device embodiments described above are only illustrative.
  • the division of the modules or units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units. Or components may be combined or may be integrated into another system, or some features may be omitted, or not implemented.
  • the shown or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, indirect coupling or communication connection of devices or units, and may be in electrical, mechanical or other forms.
  • the units described as separate components may or may not be physically separated, and components displayed 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 solution in this embodiment.
  • 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.
  • the integrated modules if implemented in the form of software functional units and sold or used as independent products, may be stored in a computer-readable storage medium.
  • the present application can implement all or part of the processes in the methods of the above embodiments, and can also be completed by instructing the relevant hardware through a computer program.
  • the computer program can be stored in a computer-readable storage medium, and the computer When the program is executed by the processor, the steps of the foregoing method embodiments can be implemented.
  • the computer program includes computer program code, and the computer program code may be in the form of source code, object code, executable file or some intermediate form, and the like.
  • the computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM, Read-Only Memory) , Random Access Memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc.
  • ROM Read-Only Memory
  • RAM Random Access Memory
  • electric carrier signal telecommunication signal and software distribution medium, etc.
  • the content contained in the computer-readable media may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction, for example, in some jurisdictions, according to legislation and patent practice, the computer-readable media Electric carrier signals and telecommunication signals are not included.

Abstract

一种机器人标定方法，包括：获取机器人执行末端操作空间信息；根据操作空间信息，将对应的操作空间网格化，获得操作空间网格化后的操作空间点；控制执行末端运动至满足预设要求的操作空间点，获得标定数据；根据获得的标定数据，对所述机器人的手眼进行标定。该方法可根据操作空间信息，对操作空间进行网格化，确定操作空间点，自动控制执行末端运动至满足预设要求的操作空间点，可自动且准确的获取到标定数据，从而使得标定过程简单，且提高了效率。还涉及一种机器人标定装置、机器人及存储介质。

Description

一种机器人标定方法、装置、机器人及存储介质
本申请要求于2021年03月19日在中国专利局提交的、申请号为202110296720.7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
本申请属于人工智能技术领域，尤其涉及一种机器人标定方法、装置、机器人及存储介质。
背景技术
随着人工智能技术的快速发展，各种例如机器人等智能产品顺应而生，机器人在各个领域中发挥着越来越重要的工作，目前很多类型的机器人需要机器视觉配合机器人控制执行末端运动到目的地执行对应的操作等。在进行相应的操作之前要对机器人的手眼进行标定后才能实现准确控制执行末端运动到目的地执行对应的操作等。
然而，在标定过程中需要采集尽可能多位置的标定数据，否则标定不准确，导致不能准确控制执行末端运动到目的地。目前采集标定物尽可能多位置的标定数据的过程中需要人工参与的部分比较复杂，对操作人员的专业素质要求较高，标定过程繁琐，效率低下。
技术问题
本申请实施例提供了一种机器人标定方法、装置、机器人及存储介质，旨在解决现标定过程繁琐，效率低下的问题。
技术解决方案
第一方面，本申请实施例提供了一种机器人标定方法，包括：
获取所述机器人执行末端操作空间信息；
根据所述操作空间信息，将对应的操作空间网格化，获得操作空间网格化后的操作空间点；
控制所述执行末端运动至满足预设要求的操作空间点，获得标定数据；
根据获得的所述标定数据，对所述机器人的手眼进行标定。
在一个实施例中，所述根据所述操作空间信息，将对应的操作空间网格化，获得操作空间网格化后的操作空间点，包括：
根据所述操作空间信息，确定所述操作空间的三维信息；
根据预设距离采样间隔和所述三维信息，对所述操作空间进行网格化划分，得到网格化后的多个子操作空间位置；
根据预设角度采样间隔，确定每个网格化后的子操作空间位置执行末端的姿态数量；
根据所述每个网格化后的操作空间执行末端的姿态数量和多个网格化后的子操作空间位置，获得操作空间网格化后的总操作空间点数。
在一个实施例中，在控制所述执行末端运动至满足预设要求的操作空间点之前，包括：
确定每个操作空间点的可达性；其中，所述可达性为判断所述执行末端能否运动至对应的操作空间点；
在所述执行末端能运动至对应的操作空间点时，判定对应的操作空间点满足预设要求。
在一个实施例中，所述控制所述执行末端运动至满足预设要求的操作空间点，获得标定数据，包括：
控制所述执行末端运动至满足预设要求的操作空间点，判断所述操作空间点的可用性；其中，所述可用性表示在对应操作空间点是否能采集到标定数据，以及采集到标定数据是否符合预设标准；
对能采集到标定数据，且采集到标定数据符合预设标准的操作空间点，获得对应操作 空间点下采集的标定数据。
在一个实施例中，所述根据获得的所述标定数据，对所述机器人的手眼进行标定，包括：
根据获得的所述标定数据，对所述机器人的手眼进行初步标定，得到初步标定结果；
获取标定物在图像坐标系下的位置信息，根据所述初步标定结果，将在图像坐标系下的位置信息转换为基坐标系下的第一位姿；
根据所述机器人执行末端的运动参数，确定所述标定物在基坐标系下的第二位姿；
确定所述第一位姿与所述第二位姿之间的误差信息；
根据所述误差信息计算雅可比矩阵和残差值；
根据所述雅可比矩阵和所述残差值，通过LM迭代算法更新相机的外参数，得到精确标定结果。
在一个实施例中，所述根据所述雅可比矩阵和所述残差值，通过LM迭代算法更新相机的外参数，得到精确标定结果，包括：
根据所述雅可比矩阵和所述残差值，通过LM迭代算法更新相机的外参数，并将更新后的外部参数作为所述初步标定结果，返回执行根据所述初步标定结果，将在图像坐标系下的位置信息转换为基坐标系下的第一位姿的步骤及后续步骤，直至更新次数达到预设阈值或者确定所述误差信息在预设误差范围内时，将最近一次更新相机的外参数作为所述精确标定结果。
在一个实施例中，所述误差信息包括误差矩阵；所述根据所述误差信息计算雅可比矩阵和残差值，包括：
对所述误差矩阵求导，得到所述雅可比矩阵；
对所述误差矩阵求值，得到所述残差值。
第二方面，本申请实施例提供了一种机器人标定装置，包括：
获取模块，用于获取所述机器人执行末端操作空间信息；
网格化模块，用于根据所述操作空间信息，将对应的操作空间网格化，获得操作空间网格化后的操作空间点；
控制模块，用于控制所述执行末端运动至满足预设要求的操作空间点中，获得标定数据；
标定模块，用于根据获得的所述标定数据，对所述机器人的手眼进行标定。
第三方面，本申请实施例提供了一种机器人，包括存储器、处理器以及存储在所述存储器中并可在所述处理器上运行的计算机程序，所述处理器执行所述计算机程序时实现上述机器人标定方法的步骤。
第四方面，本申请实施例提供了一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序，上述计算机程序被处理器执行时实现上述机器人标定方法的步骤。
第五方面，本申请实施例提供了一种计算机程序产品，当计算机程序产品在电子设备上运行时，使得电子设备执行上述现上述机器人标定方法的步骤。
有益效果
本申请实施例与现有技术相比存在的有益效果是：本申请实施例可通过获取所述机器人执行末端操作空间信息；根据所述操作空间信息，将对应的操作空间网格化，获得操作空间网格化后的操作空间点；控制所述执行末端运动至满足预设要求的操作空间点，获得标定数据；根据获得的所述标定数据，对所述机器人的手眼进行标定。由于可根据操作空间信息，对操作空间进行网格化，确定操作空间点，自动控制执行末端运动至满足预设要求的操作空间点，可自动且准确的获取到标定数据，从而使得标定过程简单，且提高了效率。
可以理解的是，上述第二方面至第五方面的有益效果可以参见上述第一方面中的相关 描述，在此不再赘述。
附图说明
为了更清楚地说明本申请实施例中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1是本申请一实施例提供的机器人标定方法的流程示意图；
图2是本申请一实施例提供的步骤S102的具体流程示意图；
图3是本申请一实施例提供的步骤S103的具体流程示意图；
图4是本申请一实施例提供的步骤S104的具体流程示意图；
图5是本申请一实施例提供的机器人标定装置的结构示意图；
图6是本申请一实施例提供的机器人的结构示意图。
本发明的实施方式
以下描述中，为了说明而不是为了限定，提出了诸如特定系统结构、技术之类的具体细节，以便透彻理解本申请实施例。然而，本领域的技术人员应当清楚，在没有这些具体细节的其它实施例中也可以实现本申请。在其它情况中，省略对众所周知的系统、装置、电路以及方法的详细说明，以免不必要的细节妨碍本申请的描述。
应当理解，当在本申请说明书和所附权利要求书中使用时，术语“包括”指示所描述特征、整体、步骤、操作、元素和/或组件的存在，但并不排除一个或多个其它特征、整体、步骤、操作、元素、组件和/或其集合的存在或添加。
还应当理解，在本申请说明书和所附权利要求书中使用的术语“和/或”是指相关联列出的项中的一个或多个的任何组合以及所有可能组合，并且包括这些组合。
如在本申请说明书和所附权利要求书中所使用的那样，术语“如果”可以依据上下文被解释为“当...时”或“一旦”或“响应于确定”或“响应于检测到”。类似地，短语“如果确定”或“如果检测到[所描述条件或事件]”可以依据上下文被解释为意指“一旦确定”或“响应于确定”或“一旦检测到[所描述条件或事件]”或“响应于检测到[所描述条件或事件]”。
另外，在本申请说明书和所附权利要求书的描述中，术语“第一”、“第二”、“第三”等仅用于区分描述，而不能理解为指示或暗示相对重要性。
在本申请说明书中描述的参考“一个实施例”或“一些实施例”等意味着在本申请的一个或多个实施例中包括结合该实施例描述的特定特征、结构或特点。由此，在本说明书中的不同之处出现的语句“在一个实施例中”、“在一些实施例中”、“在其他一些实施例中”、“在另外一些实施例中”等不是必然都参考相同的实施例，而是意味着“一个或多个但不是所有的实施例”，除非是以其他方式另外特别强调。术语“包括”、“包含”、“具有”及它们的变形都意味着“包括但不限于”，除非是以其他方式另外特别强调。
本申请实施例提供的机器人标定方法，可以应用于机器人，所述机器人可以是机械臂、机械手、服务机器人、娱乐机器人、军用机器人、农业机器人等。本申请实施例对机器人的具体类型不作任何限制。
为了说明本申请所述的技术方案，下面通过以下实施例来进行说明。
请参阅图1，本申请实施例提供的一种机器人标定方法，包括：
步骤S101，获取所述机器人执行末端操作空间信息。
具体地，在机器人开始标定时，用户可以输入机器人执行末端的操作空间信息，检测到用户输入机器人执行末端的操作空间信息时，获取该操作空间信息。或者预存储机器人执行末端的操作空间信息，直接获取预存储的机器人执行末端的操作空间信息。
步骤S102，根据所述操作空间信息，将对应的操作空间网格化，获得操作空间网格化 后的操作空间点。
具体地，操作空间信息包括操作空间的三维信息，根据操作空间的三维信息，将对应的操作空间进行网格化划分得到多个操作空间点。操作空间的三维信息如是操作空间的长宽高等信息。
在一个实施例中，如图2所示，所述根据所述操作空间信息，将对应的操作空间网格化，获得操作空间网格化后的操作空间点，包括步骤S1021至步骤S1024：
步骤S1021，根据所述操作空间信息，确定所述操作空间的三维信息。
具体地，获取操作空间信息中包括的三维信息。如操作空间是一个立方体，操作空间的三维信息可包括操作空间的长、宽、高等信息。
步骤S1022，根据预设距离采样间隔和所述三维信息，对所述操作空间进行网格化划分，得到网格化后的多个子操作空间位置。
具体地，预设距离采样间隔，在每个维度间隔预设距离采样间隔处进行划分，得到多个子操作空间位置点。
步骤S1023，根据预设角度采样间隔，确定每个网格化后的子操作空间位置执行末端的姿态数量。
具体地，在得到子操作空间位置点之后，每个操作位置点机器人执行末端可以有多种姿态，如三个姿态角任一个角度不同可认为是姿态不同，根据预设角度采样间隔确定每个子操作空间位置点的姿态数量，可得到每一个子操作空间位置点的多个姿态，将所有子操作空间位置点的姿态数量作为整个操作空间可操作的总操作空间点数。
步骤S1024，根据所述每个网格化后的操作空间执行末端的姿态数量和多个网格化后的子操作空间位置，获得操作空间网格化后的总操作空间点数。
具体地，根据每个子操作空间位置，以及每个子操作位置对应确定的姿态数量，可确定整个操作空间可操作的总操作空间点数。
在一种应用场景中，根据预设距离采样间隔和所述三维信息，对所述操作空间进行网格化划分，得到网格化后的多个子操作空间位置，可以是将操作空间离散化为一个个的网格点，使机器人分别运动到这些网格点，如操作空间是一个长为l，宽为w，高为h的立方体。在进行网格化的过程中，预设距离采样间隔为δd，预设角度采样间隔为δα。此时机器人的操作空间总共可以离散化出的子操作空间位置的个数为n，
Figure PCTCN2021124617-appb-000001
再在每个操作空间位置点上预设角度采样间隔采样，确定每个子操作空间位置执行末端的姿态数量，如预设角度采样间隔为δα，每个子操作空间位置可以离散化出的姿态数量为m，
Figure PCTCN2021124617-appb-000002
获得整个操作空间总的可操作的总操作空间点数为c，c＝m×n，这所有的点可以称为采样位姿的备选集合点。
步骤S103，控制所述执行末端运动至满足预设要求的操作空间点，获得标定数据。
具体地，在得到整个操作空间的总操作空间点数后，判断对应操作空间点是否满足预设要求，如操作空间点数满足预设要求，就控制机器人执行末端运动至满足预设要求的操作空间点，并在操作空间点得到标定数据。所述标定数据包括但不限于预设标定物在图像坐标系下的位置信息和所述执行末端在基坐标系下的位姿信息。如所述标定数据包括从各个操作空间点下获得预设标定物在图像坐标系下的位置信息，以及机器人执行末端在基坐标系下的姿态信息。获得预设标定物在图像坐标系下的位置信息可以是：通过控制机器人执行末端运动至对应操作空间点时，图像检测设备检测标定物的位置信息。机器人执行末 端在基坐标系下的姿态信息可通过机器人自身检测得到。
在具体应用场景中，执行的机器人可以是眼在手外的机器人，即图像检测设备(如相机)设置在固定基座上(如固定的工作台面)，图像检测设备不会随着机器人的执行末端运动而运动，也可以是眼在手上类型的机器人，即将图像检测设备是在机器人的执行末端会随着机器人的执行末端运动而运动。如是眼在手外的机器人，可将预设标定物设置至于机器人的执行末端，图像检测设备(如相机)设置在固定基座下，控制执行末端运动至满足预设要求的操作空间点，预设标定物和图像检测设备之间可产生相对运动，获得标定数据可以是在各个操作空间点获得预设标定物在图像坐标系下的位置信息，以及机器人执行末端上预设标定物在基坐标系下的姿态信息。如是眼在手上的机器人，可将预设标定物设在固定基座上(如固定的工作台面)固定不动，图像检测设备设置在机器人的执行末端，控制执行末端运动至满足预设要求的操作空间点，也可以使预设标定物和图像检测设备之间产生相对运动，获得标定数据可以是在各个操作空间点获得预设标定物在图像坐标系下的位置信息，以及根据机器人执行末端的运动参数获取执行末端在基坐标系下的姿态信息，所述基坐标系为是在所述机器人固定基座上建立的坐标系。
在一个实施例中，在控制所述执行末端运动至满足预设要求的操作空间点之前，包括：确定每个操作空间点的可达性；其中，所述可达性为判断所述执行末端能否运动至对应的操作空间点；在所述执行末端能运动至对应的操作空间点时，判定对应的操作空间点满足预设要求。
具体地，在控制所述执行末端运动至满足预设要求的操作空间点之前先判断每个操作空间点是否满足预设要求，判断每个操作空间点是否满足预设要求通过对应操作空间点的可达性进行判断，如在机器人执行末端能运动至对应的操作空间点，则判定该操作空间点满足预设要求，如机器人执行末端不能运动至对应的操作空间点，则判定该操作空间点不满足预设要求。
在具体应用中，由于执行末端实际的操作空间通常是不规则的形状，因此上述离散化过程得到的操作空间点不一定可达，对每一个离散化的操作空间点进行逆解运算，判断这个位置是否可达，如果该操作空间点不可达则将它从采样备选集合中删除，即不会控制所述执行末端运动至该操作空间点。可达性判据可为
Figure PCTCN2021124617-appb-000003
s.t.FK(q)＝x d，可以理解为是在n个子操作空间位置中是否存在操作空间点q使得根据机器人正运动学函数FK(q)求解出的距离等于通过网格化的预设距离采样间隔计算出该操作空间点的距离x d，存在则判定为可达，不存在则判定不可达。
在一个实施例中，如图3所示，所述控制所述执行末端运动至满足预设要求的操作空间点，获得标定数据，包括步骤S1031至1032：
步骤S1031，控制所述执行末端运动至满足预设要求的操作空间点，判断所述操作空间点的可用性；其中，所述可用性表示在对应操作空间点是否能采集到标定数据，以及采集到标定数据是否符合预设标准。
具体地，某一个操作空间点可达，机器人处于操作空间点时标定数据不一定可检测或者不一定可用，因此要先判断所述操作空间点的可用性，可用性表示在对应操作空间点是否能采集到标定数据，以及采集到标定数据是否符合预设标准。是否能采集到标定数据的判断可以让执行末端分别运动到满足预设要求的操作空间点，检查满足预设要求的操作空间点中执行末端的位姿是否可测量，如不可测量则将对应的操作空间点从采样备选集合中删除，即不采集该操作空间点对应的标定数据。为了确保采样数据的稳定性，采集到标定数据是否符合预设标准，可预先设定可用性判别的标准，判定采集到的标定数据是否符合预设标准。
如眼在手外，标定物设置在执行末端，判断采集到标定数据是否符合预设标准可以是通过运动参数计算得到标定物在执行末端坐标系的轴第三个分量，判定标定物在执行末端坐标系的轴第三个分量要大于零以确保测量姿态的稳定性(在实际应用中很重要，因为有些位置相机虽然可以检测到标定物，但是标定物姿态检测有误)。
如眼在手上，图像检测设备设置在执行末端，判断采集到标定数据是否符合预设标准可以是计算得到图像检测设备在执行末端坐标系的轴第三个分量，判定标定物在执行末端坐标系的轴第三个分量要大于零以确保测量姿态的稳定性，判定图像检测设备在执行末端坐标系的轴第三个分量要大于零以确保测量姿态的稳定。
步骤S1032，对能采集到标定数据，且采集到标定数据符合预设标准的操作空间点，获得对应操作空间点下采集的标定数据。
具体地，对能采集到标定数据，且采集到标定数据符合预设标准的操作空间点可以是一个可用采样点的集合，从该可用采样点的集合对于操作空间点下采集标定数据。
步骤S104，根据获得的所述标定数据，对所述机器人的手眼进行标定。
具体地，对所述机器人的手眼进行标定包括求解相机的外参，手眼标定具体可通过转化为约束关系AiX＝XBi进行求解，如固连装置固连在机器人执行末端上，当是眼在手上的机器人时固连装置可为图像检测设备，当时眼在手外的机器人可为标定物。求解手眼标定问题的目标就是通过固连装置的运动，获得图像检测设备与执行末端之间的位姿变化关系X，假设固连装置共有K+1次位置，其中，K≥2且为整数，则对应会存储K次相对运动，如这K次运动中执行末端转置的相对运动的变换关系为Bi,i＝1,...，K,可根据机器人的运动参数由机器人自身的控制设备得到。通过图像检测设备在K次相对运动过程中观测采集到标定物的位置信息，得到相机的K次相对运动变化关系Ai,i＝1,...，K，进而可通过手眼标定的约束关系计算出位姿变化关系X，从位姿变化关系X可得到相机的外参。
在一个实施例中，如图4所示，所述根据获得的所述标定数据，对所述机器人的手眼进行标定，包括步骤S1041至S1046：
步骤S1041，根据获得的所述标定数据，对所述机器人的手眼进行初步标定，得到初步标定结果。
具体地，根据获得的所述标定数据，对所述机器人的手眼进行标定后，由于该标定可能存在误差，因此将得到标定结果作为初步标定结果。
步骤S1042，获取标定物在图像坐标系下的位置信息，根据所述初步标定结果，将在图像坐标系下的位置信息转换为基坐标系下的第一位姿。
具体地，通过图像检测设备获取标定物下图像坐标系下的位置信息，通过初步标定结果可转化成基坐标系下的位姿，即转化为标定物在现实中的位姿。
步骤S1043，根据所述机器人执行末端的运动参数，确定所述标定物在基坐标系下的第二位姿。
具体地，机器人自身的控制设备根据所述机器人执行末端的运动参数，确定所述标定物在基坐标系下的第二位姿，即机器人根据运动学算法可以知道标定物在基坐标系下的第二位姿。
步骤S1044，确定所述第一位姿与所述第二位姿之间的误差信息。
步骤S1045，根据所述误差信息计算雅可比矩阵和残差值。
在一个实施例中，所述误差信息包括误差矩阵；所述根据所述误差信息计算雅可比矩阵和残差值，包括：对所述误差矩阵求导，得到所述雅可比矩阵；对所述误差矩阵求值，得到所述残差值。
具体地，可以是对第一位姿与所述第二位姿分别对应的参数矩阵做差，得到误差矩阵(也可以视为多项式函数)，对误差矩阵进行求导可以得到雅可比矩阵，对所述误差矩阵求值，得到所述残差值。
步骤S1046，根据所述雅可比矩阵和所述残差值，通过LM迭代算法更新相机的外参数， 得到精确标定结果。
具体地，将雅可比矩阵、所述残差值和初步标定结果的外参数作为LM迭代算法对应公式的自变量，需要更新的外参数作为因变量，通过LM迭代算法更新相机的外参数，得到精确标定结果。
在一个实施例中，所述根据所述雅可比矩阵和所述残差值，通过LM迭代算法更新相机的外参数，得到精确标定结果，包括：根据所述雅可比矩阵和所述残差值，通过LM迭代算法更新相机的外参数，并将更新后的外部参数作为所述初步标定结果，返回执行根据所述初步标定结果，将在图像坐标系下的位置信息转换为基坐标系下的第一位姿的步骤及后续步骤，直至更新次数达到预设阈值或者确定所述误差信息在预设误差范围内时，将最近一次更新相机的外参数作为所述精确标定结果。
具体地，通过LM迭代算法每次更新相机的外参数，得到标定结果不一定是最终的精确标定结果，每次迭代后再重新执行步骤S1042中的步骤及后续步骤，直到迭代更新次数达到预设阈值或者确定所述误差信息在预设误差范围内时，则将当前这一次更新的外参数作为所述精确标定结果。
本申请实施例可通过获取所述机器人执行末端操作空间信息；根据所述操作空间信息，将对应的操作空间网格化，获得操作空间网格化后的操作空间点；控制所述执行末端运动至满足预设要求的操作空间点，获得标定数据；根据获得的所述标定数据，对所述机器人的手眼进行标定。由于可根据操作空间信息，对操作空间进行网格化，确定操作空间点，自动控制执行末端运动至满足预设要求的操作空间点，可自动且准确的获取到标定数据，从而使得标定过程简单，且提高了效率。
本申请实施例还提供一种机器人标定装置，用于执行上述机器人标定方法实施例中的步骤。机器人标定装置可以是终端设备中的虚拟装置(virtual appliance)，由终端设备的处理器运行，也可以是终端设备本身。
如图5所示，本申请实施例提供的机器人标定装置500包括：
获取模块501，用于获取所述机器人执行末端操作空间信息；
网格化模块502，用于根据所述操作空间信息，将对应的操作空间网格化，获得操作空间网格化后的操作空间点；
控制模块503，用于控制所述执行末端运动至满足预设要求的操作空间点中，获得标定数据；
标定模块504，用于根据获得的所述标定数据，对所述机器人的手眼进行标定。
在一个实施例中，所述网格化模块502包括：
第一确定单元，用于根据所述操作空间信息，确定所述操作空间的三维信息；
划分单元，用于根据预设距离采样间隔和所述三维信息，对所述操作空间进行网格化划分，得到网格化后的多个子操作空间位置；
第二确定单元，用于根据预设角度采样间隔，确定每个网格化后的子操作空间位置执行末端的姿态数量；
第一获得单元，用于根据所述每个网格化后的操作空间执行末端的姿态数量和多个网格化后的子操作空间位置，获得操作空间网格化后的总操作空间点数。
在一个实施例中，机器人标定装置500包括：
第三确定单元，用于确定每个操作空间点的可达性；其中，所述可达性为判断所述执行末端能否运动至对应的操作空间点；
运动单元，用于在所述执行末端能运动至对应的操作空间点时，判定对应的操作空间点满足预设要求。
在一个实施例中，所述控制模块503包括：
判断单元，用于控制所述执行末端运动至满足预设要求的操作空间点，判断所述操作空间点的可用性；其中，所述可用性表示在对应操作空间点是否能采集到标定数据，以及 采集到标定数据是否符合预设标准；
第二获得单元，用于对能采集到标定数据，且采集到标定数据符合预设标准的操作空间点，获得对应操作空间点下采集的标定数据。
在一个实施例中，所述标定模块504包括：
初步标定单元，用于根据获得的所述标定数据，对所述机器人的手眼进行初步标定，得到初步标定结果；
转换单元，用于获取标定物在图像坐标系下的位置信息，根据所述初步标定结果，将在图像坐标系下的位置信息转换为基坐标系下的第一位姿；
第四确定单元，用于根据所述机器人执行末端的运动参数，确定所述标定物在基坐标系下的第二位姿；
第五确定单元，用于确定所述第一位姿与所述第二位姿之间的误差信息；
计算单元，用于根据所述误差信息计算雅可比矩阵和残差值；
精确标定单元，用于根据所述雅可比矩阵和所述残差值，通过LM迭代算法更新相机的外参数，得到精确标定结果。
在一个实施例中，所述精确标定单元具体用于：根据所述雅可比矩阵和所述残差值，通过LM迭代算法更新相机的外参数，并将更新后的外部参数作为所述初步标定结果，返回执行根据所述初步标定结果，将在图像坐标系下的位置信息转换为基坐标系下的第一位姿的步骤及后续步骤，直至更新次数达到预设阈值或者确定所述误差信息在预设误差范围内时，将最近一次更新相机的外参数作为所述精确标定结果。
在一个实施例中，所述误差信息包括误差矩阵；所述计算单元具体用于：对所述误差矩阵求导，得到所述雅可比矩阵；对所述误差矩阵求值，得到所述残差值。
本申请实施例可通过获取所述机器人执行末端操作空间信息；根据所述操作空间信息，将对应的操作空间网格化，获得操作空间网格化后的操作空间点；控制所述执行末端运动至满足预设要求的操作空间点，获得标定数据；根据获得的所述标定数据，对所述机器人的手眼进行标定。由于可根据操作空间信息，对操作空间进行网格化，确定操作空间点，自动控制执行末端运动至满足预设要求的操作空间点，可自动且准确的获取到标定数据，从而使得标定过程简单，且提高了效率。
如图6所示，本申请的一个实施例还提供一种机器人600包括：处理器601，存储器602以及存储在所述存储器602中并可在所述处理器601上运行的计算机程序603，例如机器人标定程序。所述处理器601执行所述计算机程序603时实现上述各个机器人标定方法实施例中的步骤。所述处理器601执行所述计算机程序603时实现上述各装置实施例中各模块的功能，例如图5所示模块501至504的功能。
示例性的，所述计算机程序603可以被分割成一个或多个模块，所述一个或者多个模块被存储在所述存储器602中，并由所述处理器601执行，以完成本申请。所述一个或多个模块可以是能够完成特定功能的一系列计算机程序指令段，该指令段用于描述所述计算机程序603在所述机器人600中的执行过程。例如，所述计算机程序603可以被分割成获取模块，网格化模块，控制模块，标定模块，各模块具体功能在上述实施例中已有描述，此处不再赘述。
所述机器人600可以是具有移动功能的机器人，或者桌上型计算机、笔记本、掌上电脑及云端服务器等计算设备。所述终端设备可包括，但不仅限于，处理器601，存储器602。本领域技术人员可以理解，图6仅仅是机器人600的示例，并不构成对机器人600的限定，可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件，例如所述终端设备还可以包括输入输出设备、网络接入设备、总线等。
所称处理器601可以是中央处理单元(Central Processing Unit，CPU)，还可以是其他通用处理器、数字信号处理器(Digital Signal Processor，DSP)、专用集成电路(Application Specific Integrated Circuit，ASIC)、现场可编程门阵列 (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、分立硬件组件等。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。
所述存储器602可以是所述机器人600的内部存储单元，例如机器人600的硬盘或内存。所述存储器602也可以是所述机器人600的外部存储设备，例如所述机器人600上配备的插接式硬盘，智能存储卡(Smart Media Card，SMC)，安全数字(Secure Digital，SD)卡，闪存卡(Flash Card)等。进一步地，所述存储器602还可以既包括所述机器人600的内部存储单元也包括外部存储设备。所述存储器602用于存储所述计算机程序以及所述终端设备所需的其他程序和数据。所述存储器602还可以用于暂时地存储已经输出或者将要输出的数据。
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，仅以上述各功能单元、模块的划分进行举例说明，实际应用中，可以根据需要而将上述功能分配由不同的功能单元、模块完成，即将所述装置的内部结构划分成不同的功能单元或模块，以完成以上描述的全部或者部分功能。实施例中的各功能单元、模块可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中，上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。另外，各功能单元、模块的具体名称也只是为了便于相互区分，并不用于限制本申请的保护范围。上述系统中单元、模块的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在上述实施例中，对各个实施例的描述都各有侧重，某个实施例中没有详述或记载的部分，可以参见其它实施例的相关描述。
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、或者计算机软件和电子硬件的结合来实现。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。
在本申请所提供的实施例中，应该理解到，所揭露的装置/终端设备和方法，可以通过其它的方式实现。例如，以上所描述的装置/终端设备实施例仅仅是示意性的，例如，所述模块或单元的划分，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。另一点，所显示或讨论的相互之间的耦合或直接耦合或通讯连接可以是通过一些接口，装置或单元的间接耦合或通讯连接，可以是电性，机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，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。
所述集成的模块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，本申请实现上述实施例方法中的全部或部分流程，也可以通过计算机程序来指令相关的硬件来完成，所述的计算机程序可存储于一计算机可读存储介质中，该计算机程序在被处理器执行时，可实现上述各个方法实施例的步骤。其中，所述计算机程序包括计算机程序代码，所述计算机程序代码可以为源代码形式、对象代码形式、可执行文件或某些中间形式等。所述计算机可读介质可以包括：能够携带所述计算机程序代码的任何实体或装置、记录介质、U盘、移动硬盘、磁碟、光盘、计算机存储器、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM， Random Access Memory)、电载波信号、电信信号以及软件分发介质等。需要说明的是，所述计算机可读介质包含的内容可以根据司法管辖区内立法和专利实践的要求进行适当的增减，例如在某些司法管辖区，根据立法和专利实践，计算机可读介质不包括电载波信号和电信信号。
以上所述实施例仅用以说明本申请的技术方案，而非对其限制；尽管参照前述实施例对本申请进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本申请各实施例技术方案的精神和范围，均应包含在本申请的保护范围之内。

Claims (10)

  1. 一种机器人标定方法，其特征在于，包括：
    获取所述机器人执行末端操作空间信息；
    根据所述操作空间信息，将对应的操作空间网格化，获得操作空间网格化后的操作空间点；
    控制所述执行末端运动至满足预设要求的操作空间点，获得标定数据；
    根据获得的所述标定数据，对所述机器人的手眼进行标定。
  2. 根据权利要求1所述的机器人标定方法，其特征在于，所述根据所述操作空间信息，将对应的操作空间网格化，获得操作空间网格化后的操作空间点，包括：
    根据所述操作空间信息，确定所述操作空间的三维信息；
    根据预设距离采样间隔和所述三维信息，对所述操作空间进行网格化划分，得到网格化后的多个子操作空间位置；
    根据预设角度采样间隔，确定每个网格化后的子操作空间位置执行末端的姿态数量；
    根据所述每个网格化后的操作空间执行末端的姿态数量和多个网格化后的子操作空间位置，获得操作空间网格化后的总操作空间点数。
  3. 根据权利要求1所述的机器人标定方法，其特征在于，在控制所述执行末端运动至满足预设要求的操作空间点之前，包括：
    确定每个操作空间点的可达性；其中，所述可达性为判断所述执行末端能否运动至对应的操作空间点；
    在所述执行末端能运动至对应的操作空间点时，判定对应的操作空间点满足预设要求。
  4. 根据权利要求1所述的机器人标定方法，其特征在于，所述控制所述执行末端运动至满足预设要求的操作空间点，获得标定数据，包括：
    控制所述执行末端运动至满足预设要求的操作空间点，判断所述操作空间点的可用性；其中，所述可用性表示在对应操作空间点是否能采集到标定数据，以及采集到标定数据是否符合预设标准；
    对能采集到标定数据，且采集到标定数据符合预设标准的操作空间点，获得对应操作空间点下采集的标定数据。
  5. 根据权利要求1所述的机器人标定方法，其特征在于，所述根据获得的所述标定数据，对所述机器人的手眼进行标定，包括：
    根据获得的所述标定数据，对所述机器人的手眼进行初步标定，得到初步标定结果；
    获取标定物在图像坐标系下的位置信息，根据所述初步标定结果，将在图像坐标系下的位置信息转换为基坐标系下的第一位姿；
    根据所述机器人执行末端的运动参数，确定所述标定物在基坐标系下的第二位姿；
    确定所述第一位姿与所述第二位姿之间的误差信息；
    根据所述误差信息计算雅可比矩阵和残差值；
    根据所述雅可比矩阵和所述残差值，通过LM迭代算法更新相机的外参数，得到精确标定结果。
  6. 根据权利要求5所述的机器人标定方法，其特征在于，所述根据所述雅可比矩阵和所述残差值，通过LM迭代算法更新相机的外参数，得到精确标定结果，包括：
    根据所述雅可比矩阵和所述残差值，通过LM迭代算法更新相机的外参数，并将更新后的外部参数作为所述初步标定结果，返回执行根据所述初步标定结果，将在图像坐标系下的位置信息转换为基坐标系下的第一位姿的步骤及后续步骤，直至更新次数达到预设阈值或者确定所述误差信息在预设误差范围内时，将最近一次更新相机的外参数作为所述精确标定结果。
  7. 根据权利要求5所述的机器人标定方法，其特征在于，所述误差信息包括误差矩阵；
    所述根据所述误差信息计算雅可比矩阵和残差值，包括：
    对所述误差矩阵求导，得到所述雅可比矩阵；
    对所述误差矩阵求值，得到所述残差值。
  8. 一种机器人标定装置，其特征在于，包括：
    获取模块，用于获取所述机器人执行末端操作空间信息；
    网格化模块，用于根据所述操作空间信息，将对应的操作空间网格化，获得操作空间网格化后的操作空间点；
    控制模块，用于控制所述执行末端运动至满足预设要求的操作空间点中，获得标定数据；
    标定模块，用于根据获得的所述标定数据，对所述机器人的手眼进行标定。
  9. 一种机器人，包括存储器、处理器以及存储在所述存储器中并可在所述处理器上运行的计算机程序，其特征在于，所述处理器执行所述计算机程序时实现如权利要求1至7任一项所述的方法。
  10. 一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序，其特征在于，所述计算机程序被处理器执行时实现如权利要求1至7任一项所述的方法。
PCT/CN2021/124617 2021-03-19 2021-10-19 一种机器人标定方法、装置、机器人及存储介质 WO2022193640A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US18/369,858 US20240001558A1 (en) 2021-03-19 2023-09-19 Robot calibration method, robot and computer-readable storage medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110296720.7 2021-03-19
CN202110296720.7A CN113119083B (zh) 2021-03-19 2021-03-19 一种机器人标定方法、装置、机器人及存储介质

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US18/369,858 Continuation US20240001558A1 (en) 2021-03-19 2023-09-19 Robot calibration method, robot and computer-readable storage medium

Publications (1)

Publication Number Publication Date
WO2022193640A1 true WO2022193640A1 (zh) 2022-09-22

Family

ID=76773654

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/124617 WO2022193640A1 (zh) 2021-03-19 2021-10-19 一种机器人标定方法、装置、机器人及存储介质

Country Status (3)

Country Link
US (1) US20240001558A1 (zh)
CN (1) CN113119083B (zh)
WO (1) WO2022193640A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113119083B (zh) * 2021-03-19 2022-05-06 深圳市优必选科技股份有限公司 一种机器人标定方法、装置、机器人及存储介质
CN113744341A (zh) * 2021-07-21 2021-12-03 北京旷视科技有限公司 机器人系统的相机位姿标定方法、装置和电子设备

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20140078491A (ko) * 2012-12-17 2014-06-25 현대자동차주식회사 로봇 핸들장치 및 그 제어방법
CN107351089A (zh) * 2017-09-12 2017-11-17 中国科学技术大学 一种机器人运动学参数标定位姿优化选取方法
CN108748146A (zh) * 2018-05-30 2018-11-06 武汉库柏特科技有限公司 一种机器人手眼标定方法及系统
CN109483516A (zh) * 2018-10-16 2019-03-19 浙江大学 一种基于空间距离和极线约束的机械臂手眼标定方法
CN112045682A (zh) * 2020-09-02 2020-12-08 亿嘉和科技股份有限公司 一种固态面阵激光安装的标定方法
CN113119083A (zh) * 2021-03-19 2021-07-16 深圳市优必选科技股份有限公司 一种机器人标定方法、装置、机器人及存储介质

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9616573B2 (en) * 2012-05-25 2017-04-11 The Ritsumeikan Trust Robot control apparatus, robot control method, program, recording medium and robot system
CN107545591B (zh) * 2016-06-29 2021-04-06 沈阳新松机器人自动化股份有限公司 一种基于六点触点法的机器人手眼标定方法
US10076842B2 (en) * 2016-09-28 2018-09-18 Cognex Corporation Simultaneous kinematic and hand-eye calibration
CN107993227B (zh) * 2017-12-15 2020-07-24 深圳先进技术研究院 一种获取3d腹腔镜手眼矩阵的方法和装置
CN109807885B (zh) * 2018-12-29 2021-06-29 深圳市越疆科技有限公司 一种机械手的视觉标定方法、装置及智能终端
CN110390697B (zh) * 2019-07-11 2021-11-05 浙江大学 一种基于lm算法的毫米波雷达与摄像头联合标定方法
CN111047650B (zh) * 2019-12-02 2023-09-01 北京深测科技有限公司 一种用于飞行时间相机的参数标定方法
CN110919658B (zh) * 2019-12-13 2023-03-31 东华大学 一种基于视觉和多坐标系闭环转换的机器人标定方法

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20140078491A (ko) * 2012-12-17 2014-06-25 현대자동차주식회사 로봇 핸들장치 및 그 제어방법
CN107351089A (zh) * 2017-09-12 2017-11-17 中国科学技术大学 一种机器人运动学参数标定位姿优化选取方法
CN108748146A (zh) * 2018-05-30 2018-11-06 武汉库柏特科技有限公司 一种机器人手眼标定方法及系统
CN109483516A (zh) * 2018-10-16 2019-03-19 浙江大学 一种基于空间距离和极线约束的机械臂手眼标定方法
CN112045682A (zh) * 2020-09-02 2020-12-08 亿嘉和科技股份有限公司 一种固态面阵激光安装的标定方法
CN113119083A (zh) * 2021-03-19 2021-07-16 深圳市优必选科技股份有限公司 一种机器人标定方法、装置、机器人及存储介质

Also Published As

Publication number Publication date
CN113119083A (zh) 2021-07-16
CN113119083B (zh) 2022-05-06
US20240001558A1 (en) 2024-01-04

Similar Documents

Publication Publication Date Title
WO2022193640A1 (zh) 一种机器人标定方法、装置、机器人及存储介质
WO2020168770A1 (zh) 物体位姿估计方法及装置
CN110640747B (zh) 机器人的手眼标定方法、系统、电子设备和存储介质
WO2022160787A1 (zh) 一种机器人手眼标定方法, 装置, 可读存储介质及机器人
US20220319050A1 (en) Calibration method and apparatus, processor, electronic device, and storage medium
CN113997295B (zh) 机械臂的手眼标定方法、装置、电子设备及存储介质
JP2022553356A (ja) データ処理方法及び関連装置
WO2022121003A1 (zh) 机器人控制方法、装置、计算机可读存储介质及机器人
WO2022205845A1 (zh) 位姿标定方法、装置、机器人及计算机可读存储介质
CN111652113A (zh) 障碍物检测方法、装置、设备以及存储介质
CN113172636B (zh) 一种自动手眼标定方法、装置及存储介质
CN112902961B (zh) 基于机器视觉定位的标定方法、介质、标定设备及系统
WO2023124233A1 (zh) 一种圆查找方法、装置、电子设备及存储介质
WO2022198992A1 (zh) 一种机械臂运动规划方法、装置、可读存储介质及机械臂
CN113635299A (zh) 一种机械臂的校正方法、终端设备及存储介质
WO2022252635A1 (zh) 多任务融合的人脸定位方法、装置、设备及存储介质
CN114637571B (zh) 电脑终端控制ios终端方法、装置、智能终端及存储介质
WO2022000973A1 (zh) 孔集配准的方法、装置、设备及存储介质
CN116360649A (zh) 移动控制方法、装置、设备及介质
CN106055106B (zh) 一种基于Leap Motion的优势点检测识别方法
CN116681770A (zh) 用于旋转机构上的深度信息采集设备的标定方法及标定装置
CN111583317A (zh) 图像对齐方法、装置及终端设备
CN115934636A (zh) 一种动捕数据结构转换方法、装置、电子设备及介质
CN117422759A (zh) 一种物体的对称轴确定方法、装置、设备及存储介质
CN118003331A (zh) 一种机械臂的标定方法、装置、电子设备及存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21931215

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21931215

Country of ref document: EP

Kind code of ref document: A1