Target tuning method and device for robot

Abstract

A method for target tuning of a robot (2), the method comprising: aligning an orientation of a hand-held tool (41) with an orientation of a robot-held tool (1) of the robot (2); and after alignment, target tuning of the robot (2) for at least one target point to be reached by the robot (2), comprising: for each target point, determining a target point of the robot (2) based on attitude information of the hand-held tool (41) obtained by a tracking device (2) attached to the hand-held tool (41); enabling the robot-held tool (1) to follow the movement of the hand-held tool (41) until the robot-held tool (1) reaches a desired posture; and storing the desired attitude of the robot (2).

Description

Technical Field

[0001] The present invention relates generally to a robot, and more particularly to a method and apparatus for target tuning of a robot. Background Technology

[0002] In industrial robot applications, on-site robot target tuning is a critical process. Typically, users use a TPU (teach pendant unit) to complete the tuning task.

[0003] For example, during robot programming, before the processor associated with the robot runs the code to move the robot's tool, it may be necessary to manually fine-tune some key points of the robot's tool (called the "target pose" or "target"). Typically, the user will operate the TPU to perform the tuning task. Summary of the Invention

[0004] This invention is defined by the claims.

[0005] According to one aspect of this disclosure, a method for target tuning of a robot is provided, the method comprising: aligning the orientation of a handheld tool with the orientation of a robot holding tool; and after said alignment, target tuning of the robot for at least one target point to be reached by the robot, comprising: for each target point, enabling the robot holding tool to follow the movement of the handheld tool based on attitude information of the handheld tool obtained from a tracking device attached to the handheld tool, until the robot holding tool reaches a desired attitude; and saving the desired attitude of the robot.

[0006] Using the methods described above, target tuning for robots can be made more intuitive and easier.

[0007] In some embodiments, aligning the orientation of a handheld tool with the orientation of a robot-held tool includes: calculating the difference between the orientation of the handheld tool and the orientation of the robot-held tool; and outputting orientation adjustment information for the orientation of the handheld tool based on the difference, such that the orientation of the handheld tool can be adjusted to achieve the alignment.

[0008] In some embodiments, aligning the orientation of the handheld tool with the orientation of the robot's robotic tool further includes: after determining that the orientation of the handheld tool is aligned with the orientation of the robot's robotic tool, saving the alignment posture of the handheld tool.

[0009] In some embodiments, outputting orientation adjustment information for the orientation of the handheld tool includes: outputting the orientation adjustment information to guide a user holding the handheld tool to perform orientation adjustment of the handheld tool.

[0010] In some embodiments, orientation adjustment information is output as any one of a visual signal, an auditory signal, or a vibration signal.

[0011] In some embodiments, enabling the robotic tool to follow the movement of the handheld tool until the robotic tool reaches a desired posture includes: obtaining a handheld tool posture change signal of the handheld tool via the tracking device while the handheld tool is moving, the handheld tool posture change signal indicating the amount of posture change of the handheld tool relative to an alignment posture obtained by the handheld tool during the alignment; calculating an updated robotic tool posture of the robotic tool based on the handheld tool posture change signal; and enabling the robotic tool to follow the movement of the handheld tool based on the updated robotic tool posture.

[0012] In some embodiments, enabling the robot tool to follow the movement of the handheld tool based on the updated robot tool posture until the robot tool reaches the desired posture includes: proportionally reducing the translational deviation for the robot tool compared to the translational deviation for the handheld tool, and maintaining the orientational deviation of the robot tool the same as the orientational deviation of the handheld tool.

[0013] In some embodiments, the tool base or tool center point (TCP) of the robot tool holder is used to calculate the updated pose of the robot tool holder.

[0014] In some embodiments, in response to the tracking device entering an orientation alignment mode, a step of aligning the orientation of a handheld tool with that of a robot holding a tool is performed, the orientation alignment mode being activated by user interaction with the tracking device.

[0015] In some embodiments, in response to the tracking device entering a target tuning mode, a step of target tuning of the robot for at least one target point to be reached after the alignment is performed, the target tuning mode being activated by interaction with another user of the tracking device.

[0016] In some embodiments, the method further includes calibrating the attitude of the tracking device relative to the attitude of the handheld tool before enabling the robot to follow the movement of the handheld tool.

[0017] In some embodiments, the method further includes: after target tuning, updating the code to be used by the robot with the at least one target point based on the saved pose.

[0018] In some embodiments, the tracking device is equipped with an image capture device configured to capture at least one image of the robot holding a tool.

[0019] According to another aspect of this disclosure, an apparatus for target tuning of a robot holding a tool is provided, the apparatus comprising: a processor configured to perform the method as described above.

[0020] In some embodiments, the device is a teach pendant device for robotic tool holding, including a tracking device and a handheld tool.

[0021] According to another aspect of this disclosure, a computer-readable medium having a computer program stored thereon is provided, the computer program implementing the method described above when executed by a processor. Attached Figure Description

[0022] In the accompanying drawings, similar / identical reference numerals in different views generally indicate similar / identical parts. The drawings are not necessarily to scale. Rather, the focus is on illustrating the principles of the invention. In these drawings:

[0023] Figure 1 A schematic diagram illustrates a scenario in which a robot uses a tool to handle a workpiece according to an embodiment of the present disclosure;

[0024] Figure 2 A flowchart of a method for robot target tuning according to an embodiment of the present disclosure is shown;

[0025] Figure 3 A schematic diagram showing the alignment of the orientation of a handheld tool with the orientation of a robot holding a tool according to an embodiment of the present disclosure is shown;

[0026] Figure 4 A schematic diagram illustrating target tuning of a robot for at least one target point to be reached after alignment, according to an embodiment of the present disclosure; and

[0027] Figure 5 A schematic diagram of an apparatus for performing a method for target tuning of a robot according to an embodiment of the present disclosure is shown. Detailed Implementation

[0028] Embodiments of this disclosure will be described in more detail with reference to the accompanying drawings. Although the drawings illustrate some embodiments of this disclosure, it should be understood that this disclosure can be implemented in various ways and should not be construed as limited to the embodiments described herein. Rather, embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0029] In the description of embodiments of this disclosure, the term "comprising" and variations thereof shall be interpreted as open-ended terms meaning "including but not limited to". The term "based on" shall be understood as "at least partially based on". The terms "an embodiment" and "the embodiment" shall be understood as "at least one embodiment". The following text may also include other explicit and implicit definitions.

[0030] As mentioned above, TPUs (Teach Pendant Units) are typically used to perform tuning tasks. However, it has been found that performing such tuning tasks with a TPU usually requires the user to select the relevant tool, the relevant work object, the relevant coordinate system, and the relevant motion mode (linear motion or combined motion) through a user interface (UI). In this case, the user needs to know the different relationships between different coordinate systems. Obviously, it is not intuitive and can cause confusion. At the same time, due to the limitations of the TPU, the user must nudge the robot in the position or orientation coordinate system each time, which requires the user to switch back and forth between the position UI and the orientation UI. Misoperations are unavoidable and may sometimes lead to incorrect movement of the robot holding the tool. Therefore, a higher knowledge and skill threshold may be required to complete the target tuning task, and it may require a high degree of patience.

[0031] To reduce the effort required for on-site robot target tuning, lower the user's skill threshold, and reduce the risk of misoperation, an improved method for robot target tuning is proposed, comprising: aligning the orientation of a handheld tool with the orientation of the robot's robotic tool; and after said alignment, target tuning of the robot for at least one target point to be reached, including: for each target point, enabling the handheld tool to follow the movement of the handheld tool based on the posture information of the handheld tool obtained from a tracking device attached to the handheld tool, until the robotic tool reaches the desired posture; and saving the desired posture of the robot. Those skilled in the art will understand that the disclosed method will make robot target tuning more intuitive and easier.

[0032] To better understand the concept of this disclosure, Figure 1 A schematic diagram illustrating an application scenario of using a robot holding a tool to handle a workpiece according to an embodiment of the present disclosure is shown.

[0033] like Figure 1As shown, the robot tool 1 is mounted on the end effector 21 of the robot 2 for processing the surface of the workpiece 3. Typically, the robot 2 can be an industrial robot. For example, the robot can be a multi-arm robot with multiple degrees of freedom, such as a dual-arm robot with six degrees of freedom. In some embodiments, a controller or processor can be associated with or integrated with the robot 2 so that the end effector 21 and the robot tool 1 mounted thereon can be guided to a desired position or moved along a planned path.

[0034] Typically, workpiece 3 can have a surface of any shape to be processed, including, for example, a planar or curved surface. Before processing the workpiece, as described above, it may be necessary to first tune the robot to a desired posture (including orientation and position) for at least one point on workpiece 3 (hereinafter referred to as a target point) (e.g., Target_1) to achieve target tuning. Once the desired posture at the target point is reached, it can be saved and used to update the code run by the robot to process the workpiece in a normal processing mode, in which the robot gripper can be controlled or moved to process the workpiece along, for example, a planned path. It should be noted that although the target point is illustrated above as being workpiece-related, the target point should not be so limited. In this disclosure, the target point can include any point the robot intends to reach, including but not limited to, points on the planned path or points on the workpiece.

[0035] This disclosure aims to provide an improved method for target tuning of a robot to at least one target point it needs to reach. For ease of understanding, Figure 2 A flowchart of a method for target tuning of a robot according to an embodiment of the present disclosure is shown; Figure 3 A schematic diagram illustrating the alignment of the orientation of a handheld tool with the orientation of a robot holding a tool, according to an embodiment of the present disclosure; and Figure 4 A schematic diagram is shown illustrating target tuning of a robot for at least one target point to be reached after alignment, according to an embodiment of the present disclosure.

[0036] like Figure 2 As shown, method 200 can begin at box 210, that is, aligning the orientation of the handheld tool with the orientation of the robot's handheld tool.

[0037] It should be noted that a handheld tool 41 is provided in this disclosure. In some embodiments, the handheld tool 41 may be the same as the robot holding tool 1, and in some other embodiments, a handheld tool 41 similar to the robot holding tool is also possible. As will be explained further below, the handheld tool 41 will facilitate the robot's target tuning.

[0038] In some embodiments, the alignment step can be a completely manual process. For example, a user holding the handheld tool 41 can observe whether the orientation of the handheld tool 41 is aligned with the orientation of the robot holding tool 1. If they are not aligned, the user can adjust the orientation of the handheld tool 41 until it is aligned with the orientation of the robot holding tool 1.

[0039] In some embodiments, this alignment step can be achieved by a tracking device attached to the handheld tool. As an example, the connection between the tracking device 42 and the handheld tool 41 is as follows: Figure 3 As shown. In some cases, the combination of the handheld tool 41 and the tracking device 42 can be referred to as a teach pendant device 4 for the robot holding tool 1. As will be explained further below, the teach pendant device 4 can not only be used to align the orientation of the handheld tool with the orientation of the robot holding tool, but also enable the robot holding tool to follow the movement of the handheld tool after alignment, so as to achieve target tuning.

[0040] Specifically, in some embodiments, the tracking device 42 may be configured to capture at least one image of the robot holding tool 1, which can then be used to determine the orientation of the robot holding tool 1, and / or configured to track the attitude or motion (e.g., orientation and / or position) of the handheld tool 41, which can be used to assist target tuning. Typically, in some embodiments, the tracking device 42 may be equipped with an image capture device (e.g., a camera) for capturing the at least one image and an inertial measurement unit (IMU) for tracking the attitude or motion of the handheld tool 41. The captured images and / or the tracked attitude / motion signals may be recorded and transmitted to a processor or controller for further processing, which may be located within the tracking device or the teach pendant 4 or at a distance from the teach pendant 4.

[0041] It should be noted that in some embodiments, the above-described acquisition steps can be performed in a directional alignment mode, which can be activated by user interaction with the tracking device, for example by pressing a first button set on the tracking device.

[0042] During this orientation alignment mode, the orientation of the robotic tool can be obtained in any possible manner. In a particular embodiment, the orientation of the robotic tool can be determined based on at least one image obtained by a tracking device. Furthermore, the orientation of the handheld tool will be obtained, for example, by the tracking device. Additionally, a comparison will be made between the orientation of the handheld tool and the orientation of the robotic tool. Through this comparison, one or more feedback signals can then be output from the tracking device to guide the user to adjust the orientation of the handheld tool until it aligns with the orientation of the robotic tool. Upon alignment, a confirmation signal can be triggered to notify the user.

[0043] Therefore, in order to align the orientation of the handheld tool with that of the robot holding tool, in some embodiments, block 210 may include: calculating the difference between the orientation of the handheld tool and the orientation of the robot holding tool; and outputting orientation adjustment information for the orientation of the handheld tool based on the difference, so that the orientation of the handheld tool can be adjusted to achieve alignment.

[0044] In particular, in some embodiments, the determination of the orientation of the robot holding the tool can be performed by building a model or algorithm using the at least one image as input. Such models or algorithms are known in the art, and therefore their detailed description is omitted.

[0045] In some embodiments, outputting orientation adjustment information for the orientation of the handheld tool may include: - outputting the orientation adjustment information to guide a user holding the handheld tool to perform orientation adjustments of the handheld tool.

[0046] In particular, in some embodiments, orientation adjustment information can be output as any of a visual signal, an auditory signal, or a vibration signal. Those skilled in the art will understand that such orientation adjustment information can then be used as a feedback signal for a user to hold the handheld tool and manually adjust its orientation. This manual adjustment is intuitive.

[0047] It should be understood that, in box 210, the steps of calculating the difference between the orientation of the handheld tool and the orientation of the robot holding tool, and the steps of outputting the orientation adjustment information of the handheld tool, can be repeated until the orientation of the handheld tool is aligned with the orientation of the robot holding tool.

[0048] In some embodiments, block 210 may further include: after determining that the orientation of the handheld tool is aligned with the orientation of the robot holding tool, saving the alignment posture of the handheld tool. As will be explained further below, the saved alignment posture of the handheld tool can then be used as a reference posture for determining handheld tool posture change signals.

[0049] Once the orientation of the handheld tool is aligned with that of the robot holding the tool, a confirmation signal can be triggered to notify the user, and method 200 can proceed to box 220, that is, after alignment, to target-tun the robot for at least one target point to be reached.

[0050] More specifically, the target tuning step may include: for each target point, enabling the handheld tool to follow the movement of the handheld tool based on the attitude information of the handheld tool obtained by the tracking device attached to the handheld tool, until the robot holding the tool reaches the desired attitude; and saving the desired attitude of the robot.

[0051] Those skilled in the art will understand that this target tuning step after alignment helps the robot achieve the desired pose of at least one target point before normal processing mode. Typically, the target tuning step after alignment is performed in a target tuning mode, which in some embodiments can be activated by interaction with another user of the tracking device, for example, by pressing a second button on the tracking device.

[0052] For example, in practice, after alignment in box 210, the user can activate the target tuning mode by pressing a second button set on the tracking device, whereby the user can then move the handheld tool, and in response, the robot will move its robotic handheld tool to follow the movement of the handheld tool until the robotic handheld tool reaches the desired pose of the target point, such as... Figure 3 As shown. More specifically, during the target tuning mode, the user can observe whether the robot's final pose with the tool reaches the desired pose, and if the desired pose is reached, the user can trigger an acknowledgment signal to record or save the target point (e.g., Figure 1 The desired pose of Target_1 is defined in the code. In some cases, if there are more than one target point to be target tuned, target tuning can be performed on all target points one by one until all of them are target tuned. The desired pose of the robot for each target point can be saved and used to update the code used by the robot to process, for example, a workpiece in normal processing mode.

[0053] In order to enable the robotic tool to follow the movement of the handheld tool until the robotic tool reaches a desired posture, in some embodiments, block 220 may include: - obtaining a handheld tool posture change signal of the handheld tool via the tracking device while the handheld tool is moving, the handheld tool posture change signal indicating the amount of posture change of the handheld tool relative to the alignment posture of the handheld tool obtained during the alignment period; - calculating an updated robotic tool posture of the robotic tool based on the handheld tool posture change signal; and - enabling the robotic tool to follow the movement of the handheld tool based on the updated robotic tool posture.

[0054] To facilitate understanding of the steps involved in calculating the updated pose of the robot tool, the following calculation example is provided.

[0055] First, we assume that the updated robot tool-holding pose can be represented as: That is, the new pose of the tool base of the robot holding the tool relative to the robot's robot base. Furthermore, the updated robot tool-holding pose can be calculated as follows.

[0056] (1)

[0057] in The alignment posture of the tool base of the robot holding the tool relative to the robot base can be obtained after the alignment, and This indicates a new orientation of the tool base of the robot holding the tool relative to the alignment orientation of the tool base of the robot holding the tool, and represents a signal indicating a change in the orientation of the robot holding the tool.

[0058] Since the robot tool holder can follow the movement of the handheld tool, the relationship between the tool base of the robot tool holder and the tool base of the handheld tool is as follows.

[0059] (2)

[0060] in A new orientation indicating the alignment of the tool base of the handheld tool with respect to the tool base of the handheld tool. Those skilled in the art will understand that... A new orientation of the tool base of a handheld tool relative to the alignment of the tool base with the handheld tool, and thus can be used to represent a signal indicating a change in the orientation of the handheld tool.

[0061] Furthermore, the following known relationship H exists between the attitude changes of the tracking device and the attitude changes of the handheld tool.

[0062] (3)

[0063] in The attitude change of the tracking device can be indicated by the new attitude of the tracking device after alignment, relative to the alignment attitude of the tracking device.

[0064] Then, according to the above equations (2) and (3), equation (1) can be transformed into:

[0066] (4)

[0067] Therefore, it is possible to base the handheld tool's attitude change signal (e.g., ) or the attitude change signal of the tracking device (e.g., To calculate the updated robot tool-holding pose (e.g., ).

[0068] Note that before enabling the robot tool holder to follow the movement of the handheld tool until the robot tool holder reaches the desired posture, the posture of the tracking device can be pre-calibrated relative to the posture of the handheld tool. This can help improve the computation of the posture change signal of the tracking device (e.g., ) or handheld tool posture change signals (e.g., (The accuracy of )

[0069] It should also be noted that in the above calculation example, the pose of the tool base of the robot tool holder is used to represent the updated robot tool holder pose. However, this is not a limitation, and in some other embodiments, the poses of other reference points on the robot tool holder can also be used to represent the updated robot tool holder pose. In this case, the reference point can be any point on the robot tool holder other than the tool base.

[0070] For example, in some cases, the tool center point (Too Center Point or TCP) can be chosen as the reference point, and the updated TCP pose of the robot holding the tool can be used to represent the updated robot holding tool pose. In this case, the updated TCP pose will have the following relationship with the updated pose of the tool base of the robot holding tool.

[0071] (5)

[0072] in Indicates the relationship between the TCP and the tool base of the robot holding the tool.

[0073] Using the updated robot tool-holding pose obtained above (e.g., or Therefore, the robot holding the tool can be enabled to follow the movement of the handheld tool.

[0074] For safety purposes, in some embodiments, it may be better to scale down the translational deviation of the robotic tool compared to a handheld tool, while keeping the orientation deviation of the handheld tool the same. However, in some other embodiments, it is also possible to increase the translational deviation of the robotic tool compared to a handheld tool, while keeping the orientation deviation of the robotic tool the same as that of the handheld tool.

[0075] Once the robot has been calibrated to all target points it needs to reach (e.g., on workpiece 3), the saved desired poses can be used to update the code for processing, for example, workpiece 3. The updated code can then be run by the processor or controller associated with the robot to enable it to perform normal processing.

[0076] From the above description, those skilled in the art will understand that, compared to traditional target tuning methods, the target tuning method for robots described above can reduce the workload of target tuning or attitude tuning. Furthermore, it can reduce the risk of target tuning errors. Simultaneously, it can improve the surface accuracy of the machined workpiece 3.

[0077] Those skilled in the art will also understand that the method for target tuning of a robot can be derived from... Figure 5 The illustrated device 500 performs the operation and includes a tracking device 41, a handheld tool 42, and a processor or controller 43. In particular, the processor or controller 43 is configured to perform the calculations as described above.

[0078] Specifically, device 500 can constitute a teach pendant device 4 for robotic tooling. In some embodiments, the processor or controller 43 may be located within the tracking device 41 or the handheld tool 42, and / or the tracking device 41 may be attached to or integrated with the handheld tool 42, which can help realize a compact teach pendant for robotic tooling. However, this is not mandatory; in some other embodiments, the processor 43 may also be positioned at a distance from the tracking device 41 or the handheld tool 42, for example, within a smart device or industrial personal computer (IPC).

[0079] Furthermore, this disclosure may also relate to a computer-readable medium having a computer program stored thereon, which, when executed by a processor, can implement the methods described above.

[0080] By studying the accompanying drawings, the disclosure, and the appended claims, those skilled in the art can understand and implement other variations of the disclosed embodiments in practicing the claimed invention. In the claims, the word "comprising" does not exclude other elements or steps, and the indefinite articles "a" or "an" do not exclude a plurality. The fact that certain measures are recited in mutually different dependent claims does not imply that combinations of these measures cannot be advantageously used. Any reference numerals in the claims should not be construed as limiting the scope.

Claims

1. A method for target tuning of a robot, comprising: Align the orientation of the handheld tool with the orientation of the robot's robotic handheld tool; as well as After the alignment, the robot is target-tuned for at least one target point it is to reach, including: for each target point, Based on the attitude information of the handheld tool obtained by the tracking device attached to the handheld tool, the robot holding the tool can follow the movement of the handheld tool until the robot holding the tool reaches the desired attitude. as well as Save the desired pose of the robot.

2. The method of claim 1, wherein aligning the orientation of the handheld tool with the orientation of the robot's handheld tool comprises: Calculate the difference between the orientation of the handheld tool and the orientation of the robot holding the tool; as well as Based on the difference, orientation adjustment information for the orientation of the handheld tool is output, so that the orientation of the handheld tool can be adjusted to achieve the alignment.

3. The method of claim 2, wherein aligning the orientation of the handheld tool with the orientation of the robot's handheld tool further comprises: After determining that the orientation of the handheld tool is aligned with the orientation of the robot holding tool, the alignment posture of the handheld tool is saved.

4. The method according to claim 2, wherein the output of orientation adjustment information for the orientation of the handheld tool includes: The orientation adjustment information is output to guide the user holding the handheld tool to perform orientation adjustments on the handheld tool.

5. The method of claim 4, wherein the orientation adjustment information is output as any one of a visual signal, an auditory signal, or a vibration signal.

6. The method of claim 1, wherein enabling the robotic tool to follow the movement of the handheld tool until the robotic tool reaches a desired posture comprises: The tracking device obtains a handheld tool attitude change signal as the handheld tool moves, the handheld tool attitude change signal indicating the amount of attitude change of the handheld tool relative to the alignment attitude of the handheld tool obtained during the alignment period. Based on the handheld tool posture change signal, calculate the updated robot tool-holding posture; as well as Based on the updated robot tool-holding posture, the robot tool-holding device can follow the movement of the handheld tool.

7. The method of claim 6, wherein enabling the robot tool holder to follow the movement of the handheld tool until the robot tool holder reaches the desired posture based on the updated robot tool holder posture comprises: Compared to the translational deviation used for the handheld tool, the translational deviation used for the robot-held tool is reduced proportionally, and The orientation deviation of the robot holding the tool is kept the same as that of the handheld tool.

8. The method of claim 6, wherein the tool base or tool center point (TCP) of the robot tool holder is used to calculate the updated robot tool holder pose.

9. The method of claim 1, wherein in response to the tracking device entering an orientation alignment mode, the step of aligning the orientation of the handheld tool with the orientation of the robot holding tool is performed, the orientation alignment mode being activated by user interaction with the tracking device.

10. The method of claim 1, wherein, in response to the tracking device entering a target tuning mode, a step of target tuning the robot for at least one target point to be reached by the robot after alignment is performed, the target tuning mode being activated by interaction with another user of the tracking device.

11. The method according to any one of the preceding claims, further comprising: Before enabling the robot to follow the movement of the handheld tool, the attitude of the tracking device is calibrated relative to the attitude of the handheld tool.

12. The method according to any one of the preceding claims, further comprising: After the target tuning, the code to be used by the robot is updated with the at least one target point based on the saved posture.

13. The method according to any one of the preceding claims, wherein the tracking device is equipped with an image capturing device configured to capture at least one image of the robot holding the tool.

14. An apparatus for target tuning of a robot, comprising: The processor is configured to perform any one of claims 1 to 13.

15. The apparatus of claim 14, wherein the apparatus is a teaching device for the robot to hold the tool, comprising the tracking device and the handheld tool.

16. A computer-readable medium having a computer program stored thereon, the computer program implementing the method according to any one of claims 1 to 13 when executed by a processor.

Images