WO2018209592A1 - 一种机器人的运动控制方法、机器人及控制器 - Google Patents
一种机器人的运动控制方法、机器人及控制器 Download PDFInfo
- Publication number
- WO2018209592A1 WO2018209592A1 PCT/CN2017/084702 CN2017084702W WO2018209592A1 WO 2018209592 A1 WO2018209592 A1 WO 2018209592A1 CN 2017084702 W CN2017084702 W CN 2017084702W WO 2018209592 A1 WO2018209592 A1 WO 2018209592A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- robot
- compensation value
- marker
- compensation
- motion
- Prior art date
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
Definitions
- the invention relates to the field of motion control of equipment, and in particular to a motion control method for a robot, a robot and a controller.
- Embodiments of the present invention provide a motion control method for a robot and a robot for calibrating a motion trajectory of the robot.
- a first aspect of the embodiments of the present invention provides a motion control method, where the method is applied to a robot, and the camera is mounted on the robot arm, and the method includes:
- a second aspect of the embodiments of the present invention provides a robot, wherein the robot arm of the robot is mounted with a photographing device, and specifically includes:
- An acquiring unit configured to acquire, by the photographing device, a first image including a marker at a target moment of the target period
- a calculating unit configured to calculate a compensation value according to the first image and a pre-stored reference image including the marker
- a determining unit configured to determine whether the compensation value is greater than a preset error value
- a calibration unit configured to perform calibration processing on the motion of the robot according to the compensation value when the compensation value is greater than the preset error value.
- a third aspect of the embodiments of the present invention provides a robot, which specifically includes:
- the controller is used to:
- a fourth aspect of the embodiments of the present invention provides a controller, which is connected to a camera device and a robot arm of the robot.
- the camera device is mounted on a robot arm, and the controller specifically includes:
- the memory is configured to store operation instructions and related data
- the processor is configured to: by calling the operation instruction:
- the robot acquires a first image including a marker by the photographing device at a target moment of a target period; and calculates a compensation value according to the first image and a pre-stored reference image including the marker; Determining whether the compensation value is greater than a preset error value; if the compensation value is greater than the preset error value, performing calibration processing on the motion of the robot according to the compensation value.
- the technical solution of the present invention can calibrate the motion trajectory of the robot during the movement of the robot.
- FIG. 1 is a schematic diagram of a scene structure of a motion control method of a robot according to an embodiment of the present invention
- FIG. 2 is a schematic flow chart of an embodiment of a motion control method of a robot according to an embodiment of the present invention
- FIG. 3 is a schematic diagram of functional modules of a robot according to an embodiment of the present invention.
- FIG. 4 is a schematic diagram of another functional module of a robot according to an embodiment of the present invention.
- FIG. 5 is a schematic structural diagram of a controller of a robot according to an embodiment of the present invention.
- Embodiments of the present invention provide a motion control method for a robot and a robot for calibrating a motion trajectory of the robot.
- Embodiments of the present invention are applicable to an architecture as shown in FIG. 1, in which an industrial robot robot arm is mounted with a photographing device, and one or more markers are placed between the industrial robot moving tracks.
- the photographing device is mounted at an end of a robot arm of the industrial robot.
- the image captured by the imaging device is a depth image, and the depth image includes depth information of any point on the image to the imaging device.
- the photographing device may be a binocular camera, a depth of field camera, or the like.
- the camera device may be other camera devices. The type of the camera device is not limited herein.
- an embodiment of a motion control method for a robot in an embodiment of the present invention includes:
- the first image including the marker is acquired by the photographing device at the target moment of the target period.
- the target time is a time point of capturing a pre-stored reference image at a time point of one cycle, and the time point is located at a time point after a certain period of time begins. For example, in the first cycle, if the robot has a target image for 10 s after the start of the cycle, the 10th s calculated with respect to each cycle is the target time of the cycle. It should be noted that the reference image may be acquired in the first period or may be acquired in other periods. In this embodiment, the reference image is acquired in the first cycle.
- control commands of the robots in each cycle are exactly the same, or the control commands at the start time to the target time in each cycle are exactly the same.
- target period may be set to each motion period of the robot, or one target period may be set at intervals of several cycles, which is not limited herein.
- calculating the compensation value according to the first image and the pre-stored reference image includes: determining, by the robot, the first position information of the marker relative to the photographing device according to the first image acquired by the photographing device and the attribute information of the marker And determining the second position information of the marker relative to the camera according to the pre-stored reference image and the attribute information of the marker, and then the robot determines the compensation value according to the first location information and the second location information.
- the calculating the compensation value by the robot according to the first position information and the second position information includes: the robot calculating the position compensation value in the three-dimensional space according to the first position information and the second position information, and the robot according to the first position information and the The two position information calculates an angle compensation value around the central axis of the camera of the photographing device.
- the method for determining, by the robot, the first position information of the marker relative to the photographing position according to the first image acquired by the photographing device and the attribute information of the marker may be that the robot performs 3D calculation on the marker image information of the first image, wherein The robot performs 3D calculation on the marker image information of the first image, including:
- the attribute information of the object analyzes the marker image in the first image, and extracts the three-dimensional coordinates of the target time marker. It is necessary to specify that when extracting the three-dimensional coordinates of the marker in the image, it is necessary to establish a coordinate axis and a coordinate axis.
- the origin can be located at the center of the camera of the camera.
- the vertical direction is the Z axis, the X axis is from west to east, the Y axis is from south to north, and the Z axis is at the intersection of the X and Y axes.
- the direction can be up.
- the position selection of the coordinate axis may also be other positions, as long as the three-dimensional coordinates of the marker are calculated in the target period and the three-dimensional coordinates of the target object are calculated in the same coordinate system in the first period, so the coordinate axis
- the specific establishment method is not limited here.
- the calculating, by the robot, the position compensation value in the three-dimensional space according to the first position information and the second position information may be, after the robot extracts the three-dimensional coordinates of the marker in the first image and the three-dimensional coordinates of the marker of the reference image stored in advance, The difference between the three-dimensional coordinates of the marker in the first image and the three-dimensional coordinates of the marker in the reference image is obtained, and the position compensation value of the robot in the three-dimensional space is obtained.
- the robot in addition to acquiring the position compensation value in the three-dimensional space according to the first image, it is also necessary to calculate an angle compensation value of the central axis of the camera around the imaging device according to the first position information and the second position information.
- the specific method is that the robot obtains a first angle of a line connecting the center point of the first image and the marker with respect to the X axis (or the Y axis) according to the first position information, and obtains a center of the reference image according to the second position information.
- the second angle of the line connecting the point with the marker relative to the X-axis (or the Y-axis) is made to be different from the first angle and the second angle to obtain an angle compensation value of the robot.
- only the position compensation value or the angle compensation value may be calculated.
- the photographing device can acquire the depth information of the arbitrary point on the captured image to the camera, the positive center of each captured image is directly opposite to the photographing device.
- the three-dimensional coordinates of the marker can be calculated based on the captured image and the depth information from any point on the image to the camera.
- the camera on the robot will also rotate, that is, the captured image will also rotate along the center of the captured image, that is, the marker in the first image and the reference image is relative to the center of the image.
- the amount of rotation of the point is the angle compensation value.
- the robot captures a picture (ie, the first image) by the camera at the target time of the target period, and extracts the coordinates of the marker from the picture, for example, the coordinate is (7, 6, 6).
- the coordinates of the marker extracted by the robot from the pre-stored picture (ie, the reference image) taken at the target time of the first period (which may be other periods) are (7, 7, 8), and then, according to these two Coordinates Calculating the difference, the position compensation value (0, 1, 2) in the three-dimensional space of the robot is obtained, that is, the position of the current shooting device of the robot in the current cycle relative to the position at the first cycle, moving in the negative direction of the Y-axis One unit has moved two units in the negative direction of the Z axis.
- the robot obtains the angle between the line connecting the center point of the image and the marker and the X-axis from the first image (ie, the first angle) is 44.5°, and obtains the connection between the center point of the image and the marker from the reference image.
- the angle of the X-axis (that is, the second angle) is 45°, and the difference between the two angles is calculated, and the angle compensation value of the robot is 0.5°, that is, the position of the robot's camera in the current cycle is relative to The position at one cycle is rotated by 0.5° in the clockwise direction.
- the markers respectively captured by the robot at the time of the translation and the rotation are required, and the two moments are respectively marked as two target moments.
- the images captured by the two target moments are respectively used to detect the position information and the posture information during the movement of the robot, so that the robot can separate the position and posture of the motion of the robot to the maximum extent, and perform accuracy calibration on the position in the moving area.
- Accuracy calibration of the attitude in the rotating area That is, the number of target moments in the cycle and the selection of the number of markers are related to the motion of the robot's motion trajectory.
- the number of internal target moments and the number of markers are more; when the motion trajectory of the robot in one cycle includes actions such as translation and rotation, the robot needs to set one or more target moments during the translation operation, and rotate the robot.
- One or more target moments are set during the action, and one or more target moments are set after the robot completes the rotation motion, and each target moment corresponds to the corresponding marker, so the number of target moments and the number of markers in the cycle may be It is one, it can be multiple, and it is not limited here.
- the image capturing device when the image capturing device captures an image, the image capturing device should face the marker or face the surface where the marker is located as much as possible to make the effect work best.
- step 203 Determine whether the compensation value is greater than a preset error value. If yes, perform step 204. If not, perform step 205.
- the preset error value is input by the programmer in the early stage, and may be different depending on the type of work of the robot, and the specific value is not limited herein.
- the position error value in the preset three-dimensional space is (1, 1, 1), that is, the coordinate error of the X-axis in the compensation value coordinate may not be greater than 1, and the coordinate error of the Y-axis may not be greater than 1, the Z-axis.
- Coordinate error The difference may not be greater than 1, as long as the value of one coordinate axis in the compensation value is greater than or equal to the preset error value, it is judged that the compensation value is greater than the preset error value; if the preset angle error value is 1°, that is, the angle in the compensation value When it is greater than or equal to 1°, it is judged that the compensation value is greater than the preset error value.
- the calibration process includes: performing compensation processing on the coordinate sequence in the robot control command by using the compensation value to obtain a compensation coordinate sequence; and controlling the motion of the robot according to the compensation coordinate sequence.
- the coordinate sequence in the robot control command is compensated according to the position compensation value in the three-dimensional space to obtain a compensated coordinate sequence, and then the motion of the robot is controlled according to the compensated coordinate sequence to correct the motion trajectory of the robot.
- the calibration process further includes: performing compensation processing on the rotation angle in the robot control command by using the compensation value, obtaining a compensation angle, and controlling the motion of the robot according to the compensation angle.
- the coordinates of the robot and the rotation angle are simultaneously compensated, thereby simultaneously calibrating the motion trajectory of the robot and the posture of the robot.
- the coordinates or rotation angle of the robot may be separately compensated separately to separately calibrate the motion trajectory of the robot or the attitude of the robot.
- the coordinates of the marker acquired from the first image are (7, 6, 6), and the coordinates of the marker obtained from the reference image are (7, 7, 8), and then, Based on the difference between the two coordinates, the position compensation value (0, 1, 2) in the three-dimensional space is obtained.
- the position error value in the preset three-dimensional space is (1, 1, 1). Since the coordinate value of the Z-axis in the compensation value and the preset error value is 2>1, it is judged that the compensation value is greater than the preset error value.
- the compensation value (0, 1, 2) compensates the coordinate sequence in the robot control command of the current cycle.
- the compensation coordinate is calculated according to the compensation value (9, 8, 10).
- the corresponding error can be corrected.
- the angle compensation value of the robot is 0.5°
- the corresponding preset angle error value of the robot is 1°. Since 0.5° ⁇ 1°, the angle of the robot does not need to be adjusted. If the posture of the robot needs to be corrected, the rotation angle of the robot control command of the current cycle is compensated by using the compensation value of 0.5°, and the related motion is corrected by controlling the motion of the robot according to the compensated rotation angle.
- the calibration of the movement of the robot is not performed.
- the robot after the robot acquires the compensation value and determines that the compensation value is not greater than the preset error value, the robot still controls the motion of the robot according to the original preset control command, and does not need to perform calibration processing on the motion of the robot.
- the first image including the marker is acquired by the photographing device at the target moment of the target period; the compensation value is calculated according to the first image and the pre-stored reference image including the marker; Whether the compensation value is greater than a preset error value; if the compensation value is greater than the preset error value, performing calibration processing on the motion of the robot according to the compensation value.
- the trajectory of the robot can be calibrated during the operation of the robot.
- the acquiring unit 301 is configured to acquire, by the photographing device, the first image including the marker at the target moment of the target period;
- the calculating unit 302 is configured to calculate a compensation value according to the first image and the pre-stored reference image including the marker;
- the determining unit 303 is configured to determine whether the compensation value is greater than a preset error value
- the calibration unit 304 is configured to perform calibration processing on the motion of the robot according to the compensation value when the compensation value is greater than the preset error value.
- the motion unit 305 is configured to compensate the value less than the preset error value, and does not perform calibration processing on the motion of the robot.
- the acquiring unit 301 acquires the first image including the marker by the photographing device at the target time of the target period; the calculating unit 302 calculates the compensation value according to the first image and the pre-stored reference image including the marker; The unit 303 determines whether the compensation value is greater than the preset error value; if the compensation value is greater than the preset error value, the calibration unit 304 performs a calibration process on the motion of the robot according to the compensation value.
- the technical solution of the present invention can calibrate the motion trajectory of the robot during the movement of the robot.
- another embodiment of the robot in the embodiment of the present invention includes:
- the obtaining unit 401 is configured to acquire, by the photographing device, the first image including the marker at the target moment of the target period;
- a calculating unit 402 configured to use the first image and the pre-stored reference image including the marker To calculate the compensation value
- the computing unit 402 includes:
- a first determining subunit 4021 configured to determine first position information of the marker relative to the photographing device according to the first image and the attribute information of the marker;
- a second determining subunit 4022 configured to determine, according to the pre-stored reference image including the marker and the attribute information of the marker, the second location information of the marker relative to the imaging device;
- the calculating subunit 4023 is configured to calculate a compensation value according to the first location information and the second location information.
- the determining unit 403 is configured to determine whether the compensation value is greater than a preset error value
- the calibration unit 404 is configured to perform calibration processing on the motion of the robot according to the compensation value when the compensation value is greater than the preset error value.
- the calibration unit 404 includes:
- the compensation subunit 4041 is configured to perform compensation processing on the coordinate sequence in the robot control command by using the compensation value to obtain a compensated coordinate sequence;
- the calibration subunit 4042 is configured to control the motion of the robot according to the compensated coordinate sequence.
- the motion unit 405 is configured to compensate the value less than the preset error value, and does not perform calibration processing on the motion track of the robot.
- the acquiring unit 401 acquires the first image including the marker by the photographing device at the target time of the target period; the calculating unit 402 calculates the compensation value according to the first image and the pre-stored reference image including the marker; The unit 403 determines whether the compensation value is greater than the preset error value; if the compensation value is greater than the preset error value, the calibration unit 404 performs a calibration process on the motion of the robot according to the compensation value.
- the technical solution of the present invention can calibrate the motion trajectory of the robot during the movement of the robot.
- the present invention also provides a controller that is coupled to a camera device and a robotic arm of the robot, the camera device being mounted to the robot arm.
- 5 is a device diagram of a controller in an embodiment of the present invention, where the controller 50 includes a memory 510 and a processor 520.
- the memory 510 is configured to store operation instructions and related data.
- the processor 520 is configured to perform the following steps by calling an operation instruction stored in the memory 510:
- a first image including a marker by a photographing device at a target time of the target period; An image and a pre-stored reference image containing the marker to calculate a compensation value; determining whether the compensation value is greater than a preset error value; and if the compensation value is greater than the preset error value, performing calibration processing on the motion of the robot according to the compensation value.
- the reference image and the first image captured by the camera include depth information.
- processor 520 may also be referred to as a central processing unit (English full name: Central Processing Unit, English abbreviation: CPU).
- the memory 510 is configured to store operation instructions and data, so that the processor 520 invokes the above operation instructions to implement corresponding operations, and may include a read only memory and a random access memory. A portion of the memory 510 may also include a non-volatile random access memory (English name: Non-Volatile Random Access Memory, English abbreviation: NVRAM).
- NVRAM Non-Volatile Random Access Memory
- the controller 50 also includes a bus system 530 that couples various components of the controller 50, each of which includes a memory 510, a processor 520, wherein the bus system 530 can include a power bus in addition to the data bus. , control bus and status signal bus. However, for clarity of description, various buses are labeled as bus system 530 in the figure.
- processor 520 may be an integrated circuit chip with signal processing capabilities.
- each step of the foregoing method may be completed by an integrated logic circuit of hardware in the processor 520 or an instruction in a form of software.
- the processor 520 may be a general-purpose processor, a digital signal processor (English name: Digital Signal Processing, English abbreviation: DSP), an application specific integrated circuit (English name: Application Specific Integrated Circuit, English abbreviation: ASIC), ready-made programmable Gate array (English name: Field-Programmable Gate Array, English abbreviation: FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.
- DSP Digital Signal Processing
- ASIC Application Specific Integrated Circuit
- FPGA ready-made programmable Gate array
- the methods, steps, and logical block diagrams disclosed in the embodiments of the present invention may be implemented or carried out.
- the general purpose processor may be a microprocessor or the processor or any conventional processor or the like.
- the steps of the method disclosed in the embodiments of the present invention may be directly implemented by the hardware decoding processor, or may be performed by a combination of hardware and software modules in the decoding processor.
- the software module can be located in a conventional storage medium such as random access memory, flash memory, read only memory, programmable read only memory or electrically erasable programmable memory, registers, and the like.
- the storage medium is located in the memory 510, and the processor 520 reads the information in the memory 510 and performs the steps of the above method in combination with its hardware.
- processor 520 may also invoke an operation instruction in the memory 510 to perform the following steps:
- the compensation value is calculated based on the first position information and the second position information.
- the compensation value includes a position compensation value and/or an angle compensation value.
- the specific implementation of the calibration process performed by the processor 520 on the motion of the robot according to the compensation value may be:
- the compensation sequence is used to compensate the coordinate sequence in the robot control command to obtain a compensated coordinate sequence; and the motion of the robot is controlled according to the compensated coordinate sequence.
- the specific implementation of the processor 520 performing calibration processing on the motion of the robot according to the compensation value may be:
- the compensation angle is used to compensate the rotation angle in the robot control command to obtain the compensation angle; and the movement of the robot is controlled according to the compensation angle.
- the controller acquires the first image including the marker by the photographing device at the target moment of the target period; calculates the compensation value according to the first image and the pre-stored reference image including the marker; and determines whether the compensation value is greater than The error value is set; if the compensation value is greater than the preset error value, the motion of the robot is calibrated according to the compensation value.
- the trajectory of the robot can be calibrated during the movement of the robot.
- An embodiment of the present invention further provides a robot including a robot arm, a photographing device mounted on the robot arm, and a controller, and the robot executes the above-described motion control method of the robot through the controller to make the robot move In the process, if the movement track of the robot deviates from the preset motion track, it can calibrate its own motion track during the motion.
- the disclosed system, apparatus, and method may be implemented in other manners.
- the device embodiments described above are merely illustrative
- the division of the unit is only a logical function division, and the actual implementation may have another division manner, for example, multiple units or components may be combined or may be integrated into another system, or some features may be ignored. Or not.
- the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, and may be in an electrical, mechanical or other form.
- the units described as separate components may or may not be physically separated, and the 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 of the embodiment.
- each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
- the above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.
- the integrated unit if implemented in the form of a software functional unit and sold or used as a standalone product, may be stored in a computer readable storage medium.
- the technical solution of the present invention which is essential or contributes to the prior art, or all or part of the technical solution, may be embodied in the form of a software product stored in a storage medium.
- a number of instructions are included to cause a computer device (which may be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention.
- the foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and the like. .
Landscapes
- Engineering & Computer Science (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Manipulator (AREA)
Abstract
公开了一种机器人的运动控制方法、机器人及控制器,用于在机器人运动的过程中校准机器人的运动轨迹。该控制方法包括:在目标周期的目标时刻通过所述拍摄装置获取包含标记物的第一图像(201);根据所述第一图像以及预先存储的包含标记物的参考图像来计算补偿值(202);判断所述补偿值是否大于预置误差值(203);若所述补偿值大于所述预置误差值,则根据所述补偿值对所述机器人的运动进行校准处理(204)。该方法可以在机器人运动过程中校准机器人的运动轨迹。
Description
本发明涉及设备的运动控制领域,特别涉及一种机器人的运动控制方法、机器人及控制器。
随着科技的不断发展,很多工业生产都应用了工业机器人。工业机器人一般都是按照预设的控制程序周期性地完成动作,而工业机器人会因长时间运动或其它因素而导致精度有一定下降。当该工业机器人的精度出现下降时,工业机器人就无法准确的完成预设的动作。例如,在对工业产品进行抓取时,抓取位置会不准确,导致不能对工业产品进行精确的抓取。现有技术为了解决精度下降问题,一般都是由技术人员通过调整工业机器人的控制程序来实现,该方法需要技术人员的操作,且需要暂停该工业机器人的工作。
发明内容
本发明实施例提供了一种机器人的运动控制方法及机器人,用于校准机器人的运动轨迹。
本发明实施例第一方面提供了一种运动控制方法,所述方法应用于机器人,所述机器人的机械臂上安装有拍摄装置,具体包括:
在目标周期的目标时刻通过所述拍摄装置获取包含标记物的第一图像;
根据所述第一图像以及预先存储的包含标记物的参考图像来计算补偿值;
判断所述补偿值是否大于预置误差值;
若所述补偿值大于所述预置误差值,则根据所述补偿值对所述机器人的运动进行校准处理。
本发明实施例第二方面提供了一种机器人,所述机器人的机械臂上安装有拍摄装置,具体包括:
获取单元,用于在目标周期的目标时刻通过所述拍摄装置获取包含标记物的第一图像;
计算单元,用于根据所述第一图像以及预先存储的包含标记物的参考图像来计算补偿值;
判断单元,用于判断所述补偿值是否大于预置误差值;
校准单元,用于在所述补偿值大于所述预置误差值时,根据所述补偿值对所述机器人的运动进行校准处理。
本发明实施例第三方面提供了一种机器人,具体包括:
机械臂、安装在所述机械臂上的拍摄装置及控制器;
所述控制器用于:
在目标周期的目标时刻通过所述拍摄装置获取包含标记物的第一图像;
根据所述第一图像以及预先存储的包含标记物的参考图像来计算补偿值;
判断所述补偿值是否大于预置误差值;
若所述补偿值大于所述预置误差值,则根据所述补偿值对所述机器人的运动进行校准处理。
本发明实施例第四方面提供了一种控制器,所述控制器与拍摄装置以及机器人的机械臂相连,所述拍摄装置安装于机械臂上,所述控制器具体包括:
存储器及处理器;
所述存储器,用于存储操作指令以及相关数据;
所述处理器通过调用所述操作指令,用于:
在目标周期的目标时刻通过所述拍摄装置获取包含标记物的第一图像;
根据所述第一图像以及预先存储的包含标记物的参考图像来计算补偿值;
判断所述补偿值是否大于预置误差值;
若所述补偿值大于所述预置误差值,则根据所述补偿值对所述机器人的运动进行校准处理。
从以上技术方案可以看出,本发明实施例具有以下优点:
本发明实施例中,所述机器人在目标周期的目标时刻通过所述拍摄装置获取包含标记物的第一图像;根据所述第一图像以及预先存储的包含标记物的参考图像来计算补偿值;判断所述补偿值是否大于预置误差值;若所述补偿值大于所述预置误差值,则根据所述补偿值对所述机器人的运动进行校准处理。本发明的技术方案可以在机器人运动的过程中校准机器人的运动轨迹。
图1为本发明实施例中机器人的运动控制方法一个场景架构示意图;
图2为本发明实施例中机器人的运动控制方法一个实施例流程示意图;
图3为本发明实施例中机器人的功能模块示意图;
图4为本发明实施例中机器人的另一个功能模块示意图;
图5为本发明实施例中一种机器人的控制器的结构示意图。
本发明实施例提供了一种机器人的运动控制方法及机器人,用于校准机器人的运动轨迹。
为了使本技术领域的人员更好地理解本发明方案,下面将结合本发明实施例中的附图,对本发明实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例仅仅是本发明一部分的实施例,而不是全部的实施例。
本发明的说明书和权利要求书及上述附图中的术语“第一”、“第二”、“第三”、“第四”等(如果存在)是用于区别类似的对象,而不必用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换,以便这里描述的实施例能够以除了在这里图示或描述的内容以外的顺序实施。此外,术语“包括”或“具有”及其任何变形,意图在于覆盖不排他的包含,例如,包含了一系列步骤或单元的过程、方法、系统、产品或设备不必限于清楚地列出的那些步骤或单元,而是可包括没有清楚地列出的或对于这些过程、方法、产品或设备固有的其它步骤或单元。
本发明实施例可应用于如图1所示的架构,该架构中,工业机器人机械臂上安装有拍摄装置,并在该工业机器人移动轨迹间放置有一个或多个标记物。具体的,所述拍摄装置安装在所述工业机器人的机械臂的末端。
需要说明的是,该拍摄装置拍摄的图像为深度图像,该深度图像包含该图像上任意点到拍摄装置的深度信息。在本实施例中,所述拍摄装置可以为双目摄像机、景深摄像机等。在其他实施例中,所述拍摄装置还可以是其他的拍摄装置,具体的拍摄装置的类型在此不做限定。
请参阅图2,本发明实施例中机器人的运动控制方法一个实施例包括:
201、在目标周期的目标时刻通过拍摄装置获取包含标记物的第一图像。
本实施例中,当机器人运动到需要拍摄标记物的目标周期时,会在目标周期的目标时刻利用拍摄装置获取包含标记物的第一图像。
其中,目标时刻为拍摄预先存储的参考图像的时间在一个周期的时刻点,该时刻点位于一个周期开始一定时长后的一个时间点。例如在第一周期时,假如一个周期有60s,机器人在周期开始后的第10s拍摄目标图像,则相对于每个周期开始计算的第10s为该周期的目标时刻。需要说明的是,该参考图像可以是在第一周期获取,也可以是在其他周期获取。本实施例中,该参考图像是在第一周期获取。
需要说明的是,每个周期中机器人的控制命令完全相同,或是在每个周期中的起始时刻到目标时刻的控制命令完全相同。
需要说明的是,目标周期可以设置为机器人的每一个运动周期,也可以间隔几个周期设置一个目标周期,具体此处不做限定。
202、根据所述第一图像以及预先存储的包含标记物的参考图像来计算补偿值。
本实施例中,根据第一图像以及预先存储的参考图像来计算补偿值包括,该机器人根据拍摄装置获取到的第一图像以及标记物的属性信息确定标记物相对于拍摄装置的第一位置信息,并根据预先存储的参考图像以及标记物的属性信息确定标记物相对于拍摄装置的第二位置信息,然后机器人再根据第一位置信息以及第二位置信息确定补偿值。其中,机器人根据第一位置信息以及第二位置信息计算出补偿值包括,机器人根据第一位置信息以及第二位置信息计算出在三维空间中的位置补偿值,以及机器人根据第一位置信息以及第二位置信息计算出绕拍摄装置的摄像头的中心轴的角度补偿值。
其中,机器人根据拍摄装置获取到的第一图像以及标记物的属性信息确定标记物相对于拍摄位置的第一位置信息的方法可以为,机器人对第一图像的标记物图像信息进行3D计算,其中,机器人对第一图像的标记物图像信息进行3D计算包括:
机器人在目标周期的目标时刻通过拍摄装置获取第一图像之后,会根据标
记物的属性信息对第一图像中的标记物图像进行分析,提取目标时刻标记物的三维坐标,需要说明的是:提取图像中的标记物的三维坐标时,需要建立坐标轴,坐标轴的原点可以位于拍摄装置的摄像头的中心位置,垂直向上的方向为Z轴,X轴的方向为从西到东,Y轴的方向为从南到北,Z轴交于X和Y轴的交点,方向可以向上。需要说明的是,坐标轴的位置选取还可以是其他位置,只要保证在目标周期计算标记物的三维坐标和在第一周期时计算目标物的三维坐标在同一坐标系下即可,所以坐标轴的具体建立方式在此不做限定。
机器人根据第一位置信息以及第二位置信息计算出在三维空间中的位置补偿值可以为,机器人提取第一图像中的标记物的三维坐标和预先存储的参考图像的标记物的三维坐标之后,将第一图像中的标记物三维坐标和参考图像中的标记物三维坐标作差,得到机器人在三维空间中的位置补偿值。
在本实施例中,在根据第一图像获取到在三维空间中的位置补偿值之外,还需要根据第一位置信息和第二位置信息计算出绕拍摄装置的摄像头的中心轴的角度补偿值,具体方法为,机器人根据第一位置信息得出第一图像的中心点与标记物的连线相对于X轴(或者Y轴)第一角度,且根据第二位置信息得出参考图像的中心点与标记物的连线相对于X轴(或者Y轴)的第二角度,将第一角度和第二角度做差,得到机器人的角度补偿值。在其他实施例中,也可只计算所述位置补偿值或所述角度补偿值。
需要说明的是,由于所述拍摄装置可以获取其拍摄的图像上任意点到摄像头的深度信息,且每次拍摄的图像的正中心都正对着拍摄装置。根据拍摄的图像以及图像上任意点到摄像头的深度信息即可计算出标记物的三维坐标。同时,如果机器人有旋转,那么机器人上的拍摄装置也会进行旋转,也即拍摄的图像也会沿着拍摄的图像的中心进行旋转,也即第一图像与参考图像中标记物相对于图像中心点的旋转量即是角度补偿值。
下面结合具体实施例来说明本实施例:
例如,机器人在目标周期的目标时刻通过拍摄装置拍摄到一张图片(也即第一图像),并从该图片中提取标记物的坐标,例如该坐标为(7,6,6),此时机器人从预先存储的在第一周期(也可以是其他周期)的目标时刻所拍摄的图片(也即参考图像)中提取的标记物的坐标为(7,7,8),然后,根据这两个坐标
作差值计算,得到机器人三维空间中的位置补偿值(0,1,2),也即机器人的拍摄装置在当前周期的位置相对于在第一周期时的位置,向Y轴的负方向移动了1个单位,向Z轴的负方向移动了2个单位。同时,机器人从第一图像中获取图像中心点与标记物的连线与X轴的夹角(也即第一角度)为44.5°,从参考图像中获取图像中心点与标记物的连线与X轴的夹角(也即第二角度)为45°,根据该两个角度作差值计算,得到机器人的角度补偿值0.5°,也即机器人的拍摄装置在当前周期的位置相对于在第一周期时的位置,沿顺时针方向转动了0.5°。
需要说明的是,采集参考第一周期的目标时刻的标记物位置信息时,需要在机器人在做平移和旋转动作的时刻时分别拍摄的标记物,并分别将两个时刻标记为两个目标时刻,也即两个目标时刻所分别拍摄的图像分别用于检测机器人运动过程中的位置信息以及姿态信息,使得机器人能够最大限度分离检测机器人运动的位置跟姿态,在移动区域对位置进行精度校准,在旋转区域对姿态进行精度校准。即周期内目标时刻的个数与标记物个数的选取与机器人运动轨迹的距离与动作相关,运动轨迹越长,周期内目标时刻的个数与标记物个数越多,动作越复杂,周期内目标时刻的个数与标记物个数越多;当机器人在一个周期内的运动轨迹包括平移跟旋转等动作,那么机器人需要在做平移操作时设置一个或多个目标时刻,在机器人做旋转动作时设置一个或多个目标时刻,在机器人做完旋转动作之后再设置一个或多个目标时刻,每个目标时刻对应相应的标记物,所以周期内目标时刻的个数与标记物个数可以是一个,也可以是多个,具体此处不做限定。
需要说明的是,拍摄装置在拍摄图像时,拍摄装置应尽量正对着标记物或者正对着标记物所处的平面,以使得效果最好。
203、判断补偿值是否大于预置误差值,若大于,则执行步骤204,若不大于,则执行步骤205。
本实施例中,该预置误差值为程序员前期输入的,会因机器人的工作类型的不同有所区别,具体数值此处不做限定。
例如,假如预置的三维空间中的位置误差值为(1,1,1),即补偿值坐标中的X轴的坐标误差不可以大于1,Y轴的坐标误差不可以大于1,Z轴的坐标误
差不可以大于1,只要补偿值中存在一个坐标轴的值大于等于预置误差值,则判断补偿值大于预置误差值;假如预置的角度误差值为1°,即补偿值中的角度大于等于1°时,则判断补偿值大于预置误差值。
204、根据所述补偿值对所述机器人的运动进行校准处理。
本实施例中,该校准处理包括:利用所述补偿值对机器人控制命令中的坐标序列进行补偿处理,得到补偿坐标序列;及按照所述补偿坐标序列控制所述机器人的运动。具体的,根据三维空间中的位置补偿值对机器人控制命令中的坐标序列进行补偿处理,得到补偿坐标序列,然后根据该补偿坐标序列控制所述机器人的运动,以校正所述机器人的运动轨迹。
在本实施例中,该校准处理还包括:利用所述补偿值对机器人控制命令中的旋转角度进行补偿处理,得到补偿角度,及按照所述补偿角度控制所述机器人的运动。
需要说明的是,本实施例中同时对所述机器人的坐标以及旋转角度进行补偿处理,从而同时校准机器人的运动轨迹和机器人的姿态。在其他实施例中,也可单独对所述机器人的坐标或者旋转角度进行单独补偿,以单独校准机器人的运动轨迹或者机器人的姿态。
如步骤202中所举的例子,从第一图像中获取的标记物的坐标为(7,6,6),从参考图像中获取的标记物的坐标为(7,7,8),然后,根据这两个坐标作差值计算,得到三维空间中的位置补偿值(0,1,2)。而预置的三维空间中的位置误差值为(1,1,1),由于补偿值和预置误差值中Z轴的坐标2>1,故判断补偿值大于预置误差值,此时利用补偿值(0,1,2)对当前周期的机器人控制命令中的坐标序列进行补偿处理。例如,当前周期的机器人控制命令中的一个坐标值为(9,7,8),则根据补偿值计算得出的是补偿坐标为(9,8,10)。当按照补偿坐标控制机器人运行时,即可校正相应的误差。同理,机器人的角度补偿值为0.5°,该机器人相对应的预置角度误差值为1°,由于0.5°<1°,所以机器人的角度不需要作调整。若机器人的姿态需要校正,则利用该补偿值0.5°对当前周期的机器人控制命令中的旋转角度进行补偿处理,并按照补偿后的旋转角度控制所述机器人运动即可校正相关的误差。
205、不对所述机器人的运动作校准处理。
本实施例中,当机器人获取补偿值,且判断该补偿值不大于预置误差值之后,机器人依然按照原预置的控制命令控制所述机器人运动,不需要对该机器人的运动进行校准处理。
本发明实施例中,在目标周期的目标时刻通过所述拍摄装置获取包含标记物的第一图像;根据所述第一图像以及预先存储的包含标记物的参考图像来计算补偿值;判断所述补偿值是否大于预置误差值;若所述补偿值大于所述预置误差值,则根据所述补偿值对所述机器人的运动进行校准处理。通过本发明,可以在机器人运行的过程中校准所述机器人的运动轨迹。
上面对本发明实施例中的机器人的运动控制方法进行了描述,下面对本发明实施例中的机器人进行描述,请参阅图3。
获取单元301,用于在目标周期的目标时刻通过拍摄装置获取包含标记物的第一图像;
计算单元302,用于根据第一图像以及预先存储的包含标记物的参考图像来计算补偿值;
判断单元303,用于判断补偿值是否大于预置误差值;
校准单元304,用于在补偿值大于预置误差值时,根据补偿值对机器人的运动进行校准处理。
运动单元305,用于补偿值小于预置误差值,不对所述机器人的运动作校准处理。
本发明实施例中,获取单元301在目标周期的目标时刻通过拍摄装置获取包含标记物的第一图像;计算单元302根据第一图像以及预先存储的包含标记物的参考图像来计算补偿值;判断单元303判断补偿值是否大于预置误差值;若补偿值大于预置误差值,则校准单元304根据补偿值对机器人的运动进行校准处理。本发明的技术方案可以在机器人运动的过程中校准机器人的运动轨迹。
请参阅图4,本发明实施例中机器人另一个实施例包括:
获取单元401,用于在目标周期的目标时刻通过拍摄装置获取包含标记物的第一图像;
计算单元402,用于根据第一图像以及预先存储的包含标记物的参考图像
来计算补偿值;
其中,计算单元402包括:
第一确定子单元4021,用于根据第一图像以及标记物的属性信息确定标记物相对于拍摄装置的第一位置信息;
第二确定子单元4022,用于根据预先存储的包含标记物的参考图像以及标记物的属性信息确定标记物相对于拍摄装置的第二位置信息;及
计算子单元4023,用于根据第一位置信息以及第二位置信息计算出补偿值。
判断单元403,用于判断补偿值是否大于预置误差值;
校准单元404,用于在补偿值大于预置误差值时,根据补偿值对机器人的运动进行校准处理。
其中,校准单元404包括:
补偿子单元4041,用于利用补偿值对机器人控制命令中的坐标序列进行补偿处理,得到补偿坐标序列;
校准子单元4042,用于按照所述补偿坐标序列控制所述机器人的运动。
运动单元405,用于补偿值小于预置误差值,不对所述机器人的运动轨迹作校准处理。
本发明实施例中,获取单元401在目标周期的目标时刻通过拍摄装置获取包含标记物的第一图像;计算单元402根据第一图像以及预先存储的包含标记物的参考图像来计算补偿值;判断单元403判断补偿值是否大于预置误差值;若补偿值大于预置误差值,则校准单元404根据补偿值对机器人的运动进行校准处理。本发明的技术方案可以在机器人运动的过程中校准机器人的运动轨迹。
本发明还提供了一种控制器,该控制器与拍摄装置以及机器人的机械臂相连,该拍摄装置安装于机械臂上。请参阅图5,为本发明实施例中控制器的装置图,其中控制器50包括:存储器510、处理器520。
其中,存储器510,用于存储操作指令以及相关数据;
处理器520通过调用存储器510存储的操作指令,用于执行如下步骤:
在目标周期的目标时刻通过拍摄装置获取包含标记物的第一图像;根据第
一图像以及预先存储的包含标记物的参考图像来计算补偿值;判断补偿值是否大于预置误差值;若补偿值大于预置误差值,则根据补偿值对机器人的运动进行校准处理。
所述参考图像和所述拍摄装置拍摄的第一图像包含深度信息。
需要说明的是,本实施例中,处理器520还可以称为中央处理单元(英文全称:Central Processing Unit,英文缩写:CPU)。
存储器510,用于存储操作指令和数据,以便处理器520调用上述操作指令实现相应操作,可以包括只读存储器和随机存取存储器。存储器510的一部分还可以包括非易失性随机存取存储器(英文全称:Non-Volatile Random Access Memory,英文缩写:NVRAM)。
控制器50还包括总线系统530,总线系统530将控制器50的各个组件耦合在一起,上述各个组件包括存储器510、处理器520,其中总线系统530除包括数据总线之外,还可以包括电源总线、控制总线和状态信号总线等。但是为了清楚说明起见,在图中将各种总线都标为总线系统530。
本实施例中,还需要说明的是,上述本发明实施例揭示的方法可以应用于处理器520中,或者由处理器520实现。处理器520可能是一种集成电路芯片,具有信号的处理能力。在实现过程中,上述方法的各步骤可以通过处理器520中的硬件的集成逻辑电路或者软件形式的指令完成。上述的处理器520可以是通用处理器、数字信号处理器(英文全称:Digital Signal Processing,英文缩写:DSP)、专用集成电路(英文全称:Application Specific Integrated Circuit,英文缩写:ASIC)、现成可编程门阵列(英文全称:Field-Programmable Gate Array,英文缩写: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发明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。结合本发明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510,处理器520读取存储器510中的信息,结合其硬件完成上述方法的步骤。
在另一个可能的实施例中,处理器520还可以调用存储器510中的操作指令,执行如下步骤:
根据第一图像以及标记物的属性信息确定标记物相对于拍摄装置的第一位置信息;
根据预先存储的包含标记物的参考图像以及标记物的属性信息确定标记物相对于拍摄装置的第二位置信息;及
根据第一位置信息以及第二位置信息计算出补偿值。
所述补偿值包括位置补偿值和/或角度补偿值。
在上述实施例中处理器520根据补偿值对机器人的运动进行校准处理的具体实现可为:
利用补偿值对机器人控制命令中的坐标序列进行补偿处理,得到补偿坐标序列;及按照补偿坐标序列控制机器人的运动。
处理器520根据补偿值对机器人的运动进行校准处理的具体实现可为:
利用补偿值对机器人控制命令中的旋转角度进行补偿处理,得到补偿角度;及按照补偿角度控制机器人的运动。
以上实施例中,控制器在目标周期的目标时刻通过拍摄装置获取包含标记物的第一图像;根据第一图像以及预先存储的包含标记物的参考图像来计算补偿值;判断补偿值是否大于预置误差值;若补偿值大于预置误差值,则根据补偿值对机器人的运动进行校准处理。可以在机器人运动的过程中校准机器人的运动轨迹。
本发明实施例还提供了一种机器人,该机器人包括机械臂、安装在机械臂上的拍摄装置及控制器,上述机器人通过上述控制器执行上述的机器人的运动控制方法,以使得在机器人的运动过程中,如果机器人的运动轨迹与预置的运动轨迹发生一定偏差时,能够在运动过程中校准自身的运动轨迹。
所属领域的技术人员可以清楚地了解到,为描述的方便和简洁,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,所揭露的系统,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,所述单元的划分,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,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,在本发明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,本发明的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或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)执行本发明各个实施例所述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(ROM,Read‐Only Memory)、随机存取存储器(RAM,Random Access Memory)、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述,以上实施例仅用以说明本发明的技术方案,而非对其限制;尽管参照前述实施例对本发明进行了详细的说明,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发明各实施例技术方案的精神和范围。
Claims (24)
- 一种机器人的运动控制方法,其特征在于,所述方法应用于机器人,所述机器人的机械臂上安装有拍摄装置,所述方法包括:在目标周期的目标时刻通过所述拍摄装置获取包含标记物的第一图像;根据所述第一图像以及预先存储的包含标记物的参考图像来计算补偿值;判断所述补偿值是否大于预置误差值;若所述补偿值大于所述预置误差值,则根据所述补偿值对所述机器人的运动进行校准处理。
- 根据权利要求1所述的方法,其特征在于,所述根据所述第一图像以及预先存储的包含标记物的参考图像来计算补偿值包括:根据所述第一图像以及标记物的属性信息确定所述标记物相对于拍摄装置的第一位置信息;根据所述预先存储的包含标记物的参考图像以及所述标记物的属性信息确定所述标记物相对于拍摄装置的第二位置信息;及根据所述第一位置信息以及所述第二位置信息计算出所述补偿值。
- 根据权利要求2所述的方法,其特征在于,所述补偿值包括位置补偿值和/或角度补偿值。
- 根据权利要求2所述的方法,其特征在于,所述参考图像和所述拍摄装置拍摄的第一图像包含深度信息。
- 根据权利要求1至4中任一项所述的方法,其特征在于,所述根据所述补偿值对所述机器人的运动进行校准处理包括:利用所述补偿值对机器人控制命令中的坐标序列进行补偿处理,得到补偿坐标序列;及按照所述补偿坐标序列控制所述机器人的运动。
- 根据权利要求1至4中任一项所述的方法,其特征在于,所述根据所述补偿值对所述机器人的运动进行校准处理包括:利用所述补偿值对机器人控制命令中的旋转角度进行补偿处理,得到补偿角度;及按照所述补偿角度控制所述机器人的运动。
- 一种机器人,其特征在于,所述机器人的机械臂上安装有拍摄装置,所述机器人包括:获取单元,用于在目标周期的目标时刻通过所述拍摄装置获取包含标记物的第一图像;计算单元,用于根据所述第一图像以及预先存储的包含标记物的参考图像来计算补偿值;判断单元,用于判断所述补偿值是否大于预置误差值;校准单元,用于在所述补偿值大于所述预置误差值时,根据所述补偿值对所述机器人的运动进行校准处理。
- 根据权利要求7所述的机器人,其特征在于,所述计算单元包括:第一确定子单元,用于根据所述第一图像以及标记物的属性信息确定所述标记物相对于拍摄装置的第一位置信息;第二确定子单元,用于根据所述预先存储的包含标记物的参考图像以及所述标记物的属性信息确定所述标记物相对于拍摄装置的第二位置信息;及计算子单元,用于根据所述第一位置信息以及所述第二位置信息计算出所述补偿值。
- 根据权利要求8所述的机器人,其特征在于,所述补偿值包括位置补偿值和/或角度补偿值。
- 根据权利要求8所述的机器人,其特征在于,所述参考图像和所述拍摄装置拍摄的第一图像包含深度信息。
- 根据权利要求7至9中任一项所述的机器人,其特征在于,所述校准单元包括:补偿子单元,用于利用所述补偿值对机器人控制命令中的坐标序列进行补偿处理,得到补偿坐标序列;校准子单元,用于按照所述补偿坐标序列控制所述机器人的运动。
- 根据权利要求11所述的机器人,其特征在于,所述补偿子单位还用于利用所述补偿值对机器人控制命令中的旋转角度进行补偿处理,得到补偿角度;及所述校准子单元还用于按照所述补偿角度控制所述机器人的运动。
- 一种机器人,其特征在于,所述机器人包括:机械臂、安装在所述机械臂上的拍摄装置及控制器;所述控制器用于:在目标周期的目标时刻通过所述拍摄装置获取包含标记物的第一图像;根据所述第一图像以及预先存储的包含标记物的参考图像来计算补偿值;判断所述补偿值是否大于预置误差值;若所述补偿值大于所述预置误差值,则根据所述补偿值对所述机器人的运动进行校准处理。
- 根据权利要求13所述的机器人,其特征在于,所述控制器根据所述第一图像以及预先存储的包含标记物的参考图像来计算补偿值,包括:根据所述第一图像以及标记物的属性信息确定所述标记物相对于拍摄装置的第一位置信息;根据所述预先存储的包含标记物的参考图像以及所述标记物的属性信息确定所述标记物相对于拍摄装置的第二位置信息;及根据所述第一位置信息以及所述第二位置信息计算出所述补偿值。
- 根据权利要求14所述的机器人,其特征在于,所述补偿值包括位置补偿值和/或角度补偿值。
- 根据权利要求14所述的机器人,其特征在于,所述参考图像和所述拍摄装置拍摄的第一图像包含深度信息。
- 根据权利要求13至16中任一项所述的机器人,其特征在于,所述控制器根据所述补偿值对所述机器人的运动进行校准处理,包括:利用所述补偿值对机器人控制命令中的坐标序列进行补偿处理,得到补偿坐标序列;及按照所述补偿坐标序列控制所述机器人的运动。
- 根据权利要求13至16中任一项所述的机器人,其特征在于,所述控制器根据所述补偿值对所述机器人的运动进行校准处理,包括:利用所述补偿值对机器人控制命令中的旋转角度进行补偿处理,得到补偿角度;及按照所述补偿角度控制所述机器人的运动。
- 一种控制器,其特征在于,所述控制器与拍摄装置以及机器人的机械臂相连,所述拍摄装置安装于机械臂上,所述控制器包括:存储器及处理器;所述存储器,用于存储操作指令以及相关数据;所述处理器通过调用所述操作指令,用于:在目标周期的目标时刻通过所述拍摄装置获取包含标记物的第一图像;根据所述第一图像以及预先存储的包含标记物的参考图像来计算补偿值;判断所述补偿值是否大于预置误差值;若所述补偿值大于所述预置误差值,则根据所述补偿值对所述机器人的运动进行校准处理。
- 根据权利要求19所述的控制器,其特征在于,所述处理器根据所述第一图像以及预先存储的包含标记物的参考图像来计算补偿值,包括:根据所述第一图像以及标记物的属性信息确定所述标记物相对于拍摄装置的第一位置信息;根据所述预先存储的包含标记物的参考图像以及所述标记物的属性信息确定所述标记物相对于拍摄装置的第二位置信息;及根据所述第一位置信息以及所述第二位置信息计算出所述补偿值。
- 根据权利要求20所述的控制器,其特征在于,所述补偿值包括位置补偿值和/或角度补偿值。
- 根据权利要求20所述的控制器,其特征在于,所述参考图像和所述拍摄装置拍摄的第一图像包含深度信息。
- 根据权利要求19至22中任一项所述的控制器,其特征在于,所述处理器根据所述补偿值对所述机器人的运动进行校准处理,包括:利用所述补偿值对机器人控制命令中的坐标序列进行补偿处理,得到补偿坐标序列;及按照所述补偿坐标序列控制所述机器人的运动。
- 根据权利要求19至22中任一项所述的控制器,其特征在于,所述处理器根据所述补偿值对所述机器人的运动进行校准处理,包括:利用所述补偿值对机器人控制命令中的旋转角度进行补偿处理,得到补偿 角度;及按照所述补偿角度控制所述机器人的运动。
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201780090902.0A CN110636923B (zh) | 2017-05-17 | 2017-05-17 | 一种机器人的运动控制方法、机器人及控制器 |
PCT/CN2017/084702 WO2018209592A1 (zh) | 2017-05-17 | 2017-05-17 | 一种机器人的运动控制方法、机器人及控制器 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/CN2017/084702 WO2018209592A1 (zh) | 2017-05-17 | 2017-05-17 | 一种机器人的运动控制方法、机器人及控制器 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2018209592A1 true WO2018209592A1 (zh) | 2018-11-22 |
Family
ID=64273115
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2017/084702 WO2018209592A1 (zh) | 2017-05-17 | 2017-05-17 | 一种机器人的运动控制方法、机器人及控制器 |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN110636923B (zh) |
WO (1) | WO2018209592A1 (zh) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113514050A (zh) * | 2021-04-01 | 2021-10-19 | 中车青岛四方机车车辆股份有限公司 | 定位方法、系统、介质、设备、移动平台以及检修生产线 |
CN116423505A (zh) * | 2023-03-30 | 2023-07-14 | 杭州邦杰星医疗科技有限公司 | 一种机械臂导航手术中机械臂配准模块误差校准方法 |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111739092A (zh) * | 2020-06-12 | 2020-10-02 | 广东博智林机器人有限公司 | 一种吊篮、检测机器人、检测控制系统及检测方法 |
CN112168352B (zh) * | 2020-09-25 | 2021-08-17 | 武汉联影智融医疗科技有限公司 | 手术机器人控制方法、计算机设备及手术机器人系统 |
CN115331174B (zh) * | 2022-08-19 | 2023-06-13 | 中国安全生产科学研究院 | 一种企业安全生产标准化智能监管系统及方法 |
CN115519544B (zh) * | 2022-10-10 | 2023-12-15 | 深圳进化动力数码科技有限公司 | 一种生鲜分拣机器人抓取方法、装置、设备及存储介质 |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050107920A1 (en) * | 2003-11-18 | 2005-05-19 | Fanuc Ltd | Teaching position correcting device |
CN102922521A (zh) * | 2012-08-07 | 2013-02-13 | 中国科学技术大学 | 一种基于立体视觉伺服的机械臂系统及其实时校准方法 |
CN105643369A (zh) * | 2014-11-28 | 2016-06-08 | 发那科株式会社 | 机床以及具备机器人的协作系统 |
CN106003018A (zh) * | 2015-03-30 | 2016-10-12 | 精工爱普生株式会社 | 机器人、机器人控制装置以及机器人系统 |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH08272414A (ja) * | 1995-03-29 | 1996-10-18 | Fanuc Ltd | ロボットとハンドカメラを用いた視覚センサのキャリブレーション方法 |
JP4967858B2 (ja) * | 2007-06-29 | 2012-07-04 | 日産自動車株式会社 | カメラとロボット間のキャリブレーション方法及びその装置 |
CN101637908B (zh) * | 2008-07-29 | 2010-11-03 | 上海发那科机器人有限公司 | 一种用于机器人搬运作业的视觉定位方法 |
EP2255930A1 (de) * | 2009-05-27 | 2010-12-01 | Leica Geosystems AG | Verfahren und System zum hochpräzisen Positionieren mindestens eines Objekts in eine Endlage im Raum |
US10099365B2 (en) * | 2012-08-02 | 2018-10-16 | Fuji Corporation | Work machine provided with articulated robot and electric component mounting machine |
JP2016221645A (ja) * | 2015-06-02 | 2016-12-28 | セイコーエプソン株式会社 | ロボット、ロボット制御装置およびロボットシステム |
-
2017
- 2017-05-17 CN CN201780090902.0A patent/CN110636923B/zh active Active
- 2017-05-17 WO PCT/CN2017/084702 patent/WO2018209592A1/zh active Application Filing
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050107920A1 (en) * | 2003-11-18 | 2005-05-19 | Fanuc Ltd | Teaching position correcting device |
CN102922521A (zh) * | 2012-08-07 | 2013-02-13 | 中国科学技术大学 | 一种基于立体视觉伺服的机械臂系统及其实时校准方法 |
CN105643369A (zh) * | 2014-11-28 | 2016-06-08 | 发那科株式会社 | 机床以及具备机器人的协作系统 |
CN106003018A (zh) * | 2015-03-30 | 2016-10-12 | 精工爱普生株式会社 | 机器人、机器人控制装置以及机器人系统 |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113514050A (zh) * | 2021-04-01 | 2021-10-19 | 中车青岛四方机车车辆股份有限公司 | 定位方法、系统、介质、设备、移动平台以及检修生产线 |
CN113514050B (zh) * | 2021-04-01 | 2024-05-28 | 佛山中车四方轨道车辆有限公司 | 定位方法、系统、介质、设备、移动平台以及检修生产线 |
CN116423505A (zh) * | 2023-03-30 | 2023-07-14 | 杭州邦杰星医疗科技有限公司 | 一种机械臂导航手术中机械臂配准模块误差校准方法 |
CN116423505B (zh) * | 2023-03-30 | 2024-04-23 | 杭州邦杰星医疗科技有限公司 | 一种机械臂导航手术中机械臂配准模块误差校准方法 |
Also Published As
Publication number | Publication date |
---|---|
CN110636923B (zh) | 2023-03-21 |
CN110636923A (zh) | 2019-12-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2018209592A1 (zh) | 一种机器人的运动控制方法、机器人及控制器 | |
CN106426172B (zh) | 一种工业机器人工具坐标系的标定方法与系统 | |
JP6966582B2 (ja) | ロボットモーション用のビジョンシステムの自動ハンドアイ校正のためのシステム及び方法 | |
CN111331592B (zh) | 机械手臂工具中心点校正装置及其方法以及机械手臂系统 | |
JP5949242B2 (ja) | ロボットシステム、ロボット、ロボット制御装置、ロボット制御方法、およびロボット制御プログラム | |
JP5850962B2 (ja) | ビジュアルフィードバックを利用したロボットシステム | |
US10173324B2 (en) | Facilitating robot positioning | |
CN112223302B (zh) | 基于多传感器的带电作业机器人的快速标定方法及装置 | |
JP7326911B2 (ja) | 制御システムおよび制御方法 | |
WO2019114339A1 (zh) | 机械臂运动的校正方法和装置 | |
EP3421930B1 (en) | Three-dimensional shape data and texture information generation system, photographing control program, and three-dimensional shape data and texture information generation method | |
CN111801198A (zh) | 一种手眼标定方法、系统及计算机存储介质 | |
TWI677413B (zh) | 用於機械手臂系統之校正方法及裝置 | |
JP2019115974A (ja) | ビジョンベース操作システムのキャリブレーション及びオペレーション | |
JPWO2018043525A1 (ja) | ロボットシステム、ロボットシステム制御装置、およびロボットシステム制御方法 | |
JP2015136770A (ja) | 視覚センサのデータ作成システム及び検出シミュレーションシステム | |
JP7185860B2 (ja) | 多軸可動視覚システムのキャリブレーション方法 | |
CN111152243B (zh) | 控制系统 | |
JP2019098409A (ja) | ロボットシステムおよびキャリブレーション方法 | |
JP2019077026A (ja) | 制御装置、ロボットシステム、制御装置の動作方法及びプログラム | |
US20210178601A1 (en) | Device to monitor state of balance of robot, method of operation for such device, and computer readable medium | |
WO2019100216A1 (zh) | 3d建模方法、电子设备、存储介质及程序产品 | |
CN108616744B (zh) | 一种仿生双眼视觉校准系统及校准方法 | |
CN109389645B (zh) | 相机自校准方法、系统、相机、机器人及云端服务器 | |
Niu et al. | Eye-in-hand manipulation for remote handling: Experimental setup |
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: 17909782 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: 17909782 Country of ref document: EP Kind code of ref document: A1 |