CN118143947A

CN118143947A - Pose determining method, pose determining device, pose determining equipment and storage medium

Info

Publication number: CN118143947A
Application number: CN202410419862.1A
Authority: CN
Inventors: 王思文; 左方睿
Original assignee: Siasun Co Ltd
Current assignee: Siasun Co Ltd
Priority date: 2024-04-09
Filing date: 2024-04-09
Publication date: 2024-06-07

Abstract

The invention discloses a pose determining method, a pose determining device, pose determining equipment and a storage medium. The method comprises the following steps: acquiring an expected pose corresponding to the mechanical arm, and acquiring a marking plate image under the expected pose; acquiring the current pose of the mechanical arm and acquiring a marking plate image under the current pose; judging whether the deviation between the marking plate image in the current pose and the marking plate image in the expected pose is smaller than a preset threshold value or not; and if the deviation is greater than or equal to the preset threshold, determining a target pose corresponding to the mechanical arm according to the current pose and the expected pose. According to the technical scheme, the robot can perform self-adaptive servo positioning by using the image information only through the 2D camera, so that grabbing work is performed, and the cost is reduced.

Description

Pose determining method, pose determining device, pose determining equipment and storage medium

Technical Field

The embodiment of the invention relates to the technical field of robots, in particular to a pose determining method, a pose determining device, pose determining equipment and a storage medium.

Background

When positioning and grabbing the robot with respect to the eyes on the hands, the pose information of the object to be grabbed in the three-dimensional space is generally required to be known, and the information is required to be obtained according to the 3D information of the object to be grabbed and the hand-eye conversion relation.

However, under many conditions, the parameters of the system calibration may change slowly, for example, under irradiation conditions, the camera parameters may degrade. And the system calibration result is only effective under the calibration condition, and fine structural changes can also need to be recalibrated, such as changes of hand-eye relations which can be caused when the visual positioning system works under the condition of large vibration. In addition, due to factors such as camera distortion, the calibration area of the camera is generally limited to a limited area, and the working range of the robot is limited. Moreover, the calibration of the system is generally complicated, special calibration links and professionals are needed, and the calibration cost is high.

Therefore, under the condition that three-dimensional information of the object to be grabbed cannot be obtained and the hand-eye conversion relation is unknown, how to use the 2D camera to utilize the image information can enable the robot to still perform grabbing work is a direction worthy of thinking and innovation.

Disclosure of Invention

The embodiment of the invention provides a pose determining method, a pose determining device, pose determining equipment and a storage medium, so that a robot can be adaptively servo-positioned by utilizing image information only through a 2D camera, further grabbing work is performed, and cost is reduced.

According to an aspect of the present invention, there is provided a pose determining method, including:

acquiring an expected pose corresponding to the mechanical arm, and acquiring a marking plate image under the expected pose;

Acquiring the current pose of the mechanical arm and acquiring a marking plate image under the current pose;

judging whether the deviation between the marking plate image in the current pose and the marking plate image in the expected pose is smaller than a preset threshold value or not;

and if the deviation is greater than or equal to the preset threshold, determining a target pose corresponding to the mechanical arm according to the current pose and the expected pose.

According to another aspect of the present invention, there is provided a pose determination apparatus including:

The first acquisition module is used for acquiring an expected pose corresponding to the mechanical arm and acquiring a marking plate image under the expected pose;

the second acquisition module is used for acquiring the current pose of the mechanical arm and acquiring a marking plate image under the current pose;

the judging module is used for judging whether the deviation between the marking plate image in the current pose and the marking plate image in the expected pose is smaller than a preset threshold value or not;

and the determining module is used for determining a target pose corresponding to the mechanical arm according to the current pose and the expected pose if the deviation is greater than or equal to the preset threshold.

According to another aspect of the present invention, there is provided an electronic apparatus including:

At least one processor; and

A memory communicatively coupled to the at least one processor; wherein,

The memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the pose determination method according to any of the embodiments of the present invention.

According to another aspect of the present invention, there is provided a computer readable storage medium storing computer instructions for causing a processor to implement the pose determination method according to any embodiment of the present invention when executed.

According to the embodiment of the invention, the expected pose corresponding to the mechanical arm is obtained, the marking plate image under the expected pose is obtained, the current pose of the mechanical arm is obtained, the marking plate image under the current pose is obtained, the two marking plate images are subjected to pixel comparison, whether the deviation between the marking plate image under the current pose and the marking plate image under the expected pose is smaller than the preset threshold value or not is judged, if the deviation is smaller than the preset threshold value, the current pose of the mechanical arm is directly determined as the target pose, and if the deviation is larger than or equal to the preset threshold value, the target pose corresponding to the mechanical arm is determined according to the current pose and the expected pose. According to the technical scheme, the robot can perform self-adaptive servo positioning by using the image information only through the 2D camera, so that grabbing work is performed, and the cost is reduced.

It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a flow chart of a pose determination method in an embodiment of the present invention;

Fig. 2 is a schematic structural view of a pose determining apparatus in an embodiment of the present invention;

fig. 3 is a schematic structural diagram of an electronic device implementing a pose determining method according to an embodiment of the present invention.

Detailed Description

In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.

It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

It will be appreciated that prior to using the technical solutions disclosed in the embodiments of the present disclosure, the user should be informed and authorized of the type, usage range, usage scenario, etc. of the personal information related to the present disclosure in an appropriate manner according to the relevant legal regulations.

Example 1

When the robot with the eyes on the hands is subjected to positioning grabbing operation, the object to be grabbed is often required to be positioned, the process comprises the steps of identifying the object to be grabbed, calculating the space posture and the position of the object to be grabbed, converting the posture information of the object to be grabbed to the tail end of the robot through the hand-eye relation, and converting the posture information to the base coordinate system of the robot, so that the robot can grab the object. While the conditions for achieving this series of operations are often the requirement to obtain a 3D camera and hand-eye relationship. The 3D camera can calculate the pose of the object to be measured by identifying the point cloud information obtained by the object, and the hand-eye relationship can be obtained by calibrating the camera and the robot. In the use process, the connection between the camera and the tail end of the robot is deformed along with the time, and the firmware in the camera is changed, so that the hand-eye relation is influenced, and the grabbing operation is further influenced. And if only the 2D camera is used for utilizing the image information, the self-adaptive servo positioning can be performed, so that the cost is reduced, and the influence caused by the parameter change of the camera is avoided. How to use the 2D camera to use the image information can enable the robot to still perform grabbing work is a main design idea of the embodiment of the invention.

The embodiment of the invention provides a closed-loop visual positioning system, which comprises the following equipment: a robotic arm, a 2D camera, and a marker plate. The mechanical arm may be a mechanical arm of a robot for grabbing an object, the 2D camera may be mounted at the tail end of the mechanical arm, and the marking plate may be placed below or on a side surface of the object to be grabbed (this embodiment is not limited, and may be set according to a relative position and a grabbing manner of the robot and the object to be grabbed), so as to play a role in pose referencing.

The main design gist of the embodiment of the present invention can be described as: when the object (namely the object to be grabbed) is grabbed, when the relation between the object and the marking plate is fixed, only the relation between the camera and the marking plate is required to be kept unchanged when the robot is carrying out grabbing tasks each time, and therefore, the precision can be ensured when the object pose is grabbed, and when the robot is carrying out grabbing tasks, the relation between the camera and the marking plate (the camera is at the tail end of the robot arm, namely the moving mechanical arm) needs to be adjusted.

The main design concept of the embodiment of the invention can be described as follows: and setting the expected pose of the mechanical arm, and recording the characteristic information of the marking plate under the expected pose under the camera coordinate system, wherein the expected relative relation between the lower camera and the marking plate is determined. When the mechanical arm (namely, the camera is arranged at the tail end of the mechanical arm) deviates from the set expected state, the characteristic point information of the marking plate is shot, the pose of the mechanical arm is adjusted, the mechanical arm returns to the expected state, and then the grabbing operation is carried out.

Fig. 1 is a flowchart of a pose determining method according to an embodiment of the present invention, where the present embodiment is applicable to a case where a robot arm performs pose determination when a robot on a hand performs a positioning and grabbing operation, the method may be performed by a pose determining device according to an embodiment of the present invention, and the device may be implemented in a software and/or hardware manner, as shown in fig. 1, and the method specifically includes the following steps:

S101, acquiring a desired pose corresponding to the mechanical arm, and acquiring a marker plate image under the desired pose.

The expected pose can be understood as pose information when the mechanical arm can grasp an object, namely, the pose of the mechanical arm which needs to be corrected.

The image of the marking plate in the desired pose may be an image of the marking plate taken by a camera mounted on the robot arm when the robot arm is in the desired pose state.

Specifically, firstly, setting a desired state corresponding to the robot, namely, setting a desired pose (which can be recorded as Pose a 1) of the mechanical arm, photographing and identifying characteristic point information of the marking plate under the desired pose, recording, and simultaneously storing an image of the marking plate under the desired pose (which can be recorded as GoalImage).

S102, acquiring the current pose of the mechanical arm and acquiring a marking plate image under the current pose.

The current pose can be pose information of the robot in actual operation.

In this embodiment, to simulate the deviation between the current pose and the expected pose of the robot, random winding can be added under the expected pose of the mechanical arm to simulate the actual working state of the mechanical arm. The disturbance range can be random, namely, the expected pose is randomly disturbed in the X, Y and Z directions to obtain the current pose (Pose can be recorded as Pose) so as to ensure that the marking plate can be shot later.

The image of the marking plate under the current pose may be an image of the marking plate taken by a camera mounted on the mechanical arm when the mechanical arm is in the current pose state.

Specifically, the current pose Pose of the mechanical arm is obtained, the characteristic point information of the marking plate is identified by photographing under the current pose, the characteristic point information is recorded, and meanwhile, the marking plate image (which can be recorded as GoalImage') under the current pose is saved.

S103, judging whether the deviation between the marking plate image in the current pose and the marking plate image in the expected pose is smaller than a preset threshold value.

The deviation may refer to a deviation of pixels existing between the marker plate image photographed in the current pose and the marker plate image photographed in the desired pose.

The preset threshold may be a pixel value preset according to an actual situation, which is not limited in this embodiment. The preset threshold may be, for example, 2 pixels.

Specifically, the image of the marking plate shot in the current pose is compared with the image of the marking plate shot in the expected pose in pixels, and whether the deviation between the two images is smaller than a preset threshold value is judged.

If the deviation is smaller than a preset threshold, the current pose of the mechanical arm can be judged to be close to the expected pose, the grabbing operation can be successfully carried out, the current pose of the mechanical arm can be directly determined to be the target pose, and the robot is controlled to grab the target object.

And S104, if the deviation is greater than or equal to a preset threshold, determining a target pose corresponding to the mechanical arm according to the current pose and the expected pose.

The target pose can be pose information when the mechanical arm can grasp an object in actual operation.

Specifically, if the deviation is greater than or equal to a preset threshold, the pose of the mechanical arm is subjected to rotation correction and translation correction according to the current pose and the expected pose, and a target pose corresponding to the mechanical arm is obtained, so that the mechanical arm can successfully grasp a target object.

Optionally, determining the target pose corresponding to the mechanical arm according to the current pose and the expected pose includes:

And carrying out rotation initialization operation on the current pose to obtain rotation deviation.

In the present embodiment, the rotation initialization operation may be understood as an initial rotation operation performed on the robot in the current pose before image correction is performed, the rotation requiring that the camera be able to capture the marking plate after each rotation.

The rotation deviation may be a deviation of a rotation angle existing between a current pose and a desired pose of the mechanical arm.

Specifically, the robot in the current pose is subjected to rotation initialization operation, and rotation deviation is calculated.

And carrying out rotation correction on the mechanical arm according to the rotation deviation to obtain a first pose.

The rotation correction may be performed by rotating the robot arm according to the rotation deviation to a degree as close as possible to the desired pose.

The first pose may be pose information obtained by rotating the mechanical arm according to the rotation deviation.

Specifically, after the rotation deviation is calculated, the current pose of the mechanical arm is subjected to one-time rotation control calculation, and the rotation correction is performed to obtain a first pose (which can be recorded as Pose < 3 >).

And carrying out translation initialization operation on the first pose to obtain translation deviation.

In this embodiment, the translation initializing operation may be understood as an initial translation operation performed on the rotationally corrected robot in the first pose before performing image correction.

The translational deviation may be a deviation of a translational distance existing between the first pose and the desired pose of the mechanical arm.

Specifically, the translation initializing operation is carried out on the robot in the first pose, and the translation deviation is calculated.

And carrying out translation correction on the mechanical arm according to the translation deviation to obtain a second pose.

The translation correction may be to translate the mechanical arm according to the translation deviation, and correct the mechanical arm to a degree as close to the expected pose as possible.

The second pose may be pose information obtained by translating the mechanical arm according to the translation deviation.

Specifically, after the translational deviation is calculated, a translational control calculation is performed on the first pose of the mechanical arm, and a second pose (which can be recorded as Pose 4) is obtained after translational correction is performed.

And determining a rotation control amount and a translation control amount according to the second pose and the expected pose.

In the present embodiment, the rotation control amount and the translational control amount may be obtained by sequentially photographing and calculating the deviation of the marker plate image in the current pose from the marker plate image GoalImage in the desired pose based on the second pose Pose 4.

Specifically, the deviation of the marker plate image in the current pose from the marker plate image GoalImage in the desired pose is calculated by photographing in sequence based on the second pose Pose to obtain the rotation control amount and the translation control amount, so that the mechanical arm performs rotation control and translation control.

And carrying out rotation control and translational control on the mechanical arm according to the rotation control amount and the translational control amount, and taking the rotation control and the translational control as the updated current pose of the mechanical arm.

The rotation control may be to rotate the mechanical arm, and the translation control may be to translate the mechanical arm.

Specifically, the mechanical arm is subjected to rotation control and translation control according to the rotation control amount and the translation control amount, the current pose of the mechanical arm after updating is used as the current pose of the mechanical arm, whether the deviation between the marking plate image under the current pose and the marking plate image under the expected pose at the moment is smaller than a preset threshold value or not is judged, and if the deviation is smaller than the preset threshold value, the current pose of the mechanical arm after updating at the moment is directly determined as the target pose; if the deviation is greater than or equal to a preset threshold, then:

And returning to execute the rotation initialization operation on the current pose to obtain the rotation deviation operation until the target pose is obtained.

Specifically, iteration is sequentially performed, and finally when the deviation between the mark plate image shot under the current pose and the mark plate image GoalImage under the expected pose meets the requirement, namely is smaller than a preset threshold value, iteration is terminated, namely the default camera is adjusted to the shooting position expected to be set, and the grabbing operation can be performed based on the robot state.

Optionally, performing a rotation initialization operation on the current pose to obtain a rotation deviation, including:

And carrying out rotation initialization operation on the current pose, and acquiring a corresponding rotation image set in the rotation initialization operation.

The rotation image set may be a set formed by images of a plurality of marking plates captured by the camera in the process of performing rotation initialization operation on the current pose.

Specifically, before correction based on an image, rotation is initialized, initial rotations (rotation requires that a marking plate can be shot each time) are respectively performed around an X axis, a Y axis and a Z axis under the current pose Pose, and 3 times of rotation are respectively performed to obtain a current shot marking plate image, so that a rotation image set is obtained.

A rotational offset is determined from the set of rotational images and the marker plate image at the desired pose.

Specifically, the rotation deviation is calculated from the marker plate image obtained by 3 rotation photographing and the desired bit image GoalImage.

Optionally, performing a rotation initialization operation on the current pose, and acquiring a corresponding rotation image set in the rotation initialization operation, including:

And rotating the mechanical arm in the current pose around the X axis for a preset degree to obtain a first rotation pose, and acquiring a first rotation image corresponding to the first rotation pose.

The preset degree may be a rotation angle preset according to an actual situation, which is not limited in this embodiment. The preset number of degrees may be, for example, 10 degrees.

The first rotation gesture may be a gesture of rotating the mechanical arm in the current gesture around the X axis by a preset degree. The first rotation image may be an image of the marking plate when the robot arm is in the first rotation posture, which is photographed by a camera mounted on the robot arm.

Specifically, the mechanical arm is rotated around the X axis for a preset degree based on the current pose Pose, and a currently shot marking plate image is obtained through photographing.

And rotating the mechanical arm in the first rotation position around the Y axis for a preset degree to obtain a second rotation position, and acquiring a second rotation image corresponding to the second rotation position.

The second rotation gesture may be a gesture of rotating the mechanical arm in the first rotation gesture around the Y axis by a preset degree. The second rotation image may be an image of the marking plate when the robot arm is in the second rotation posture, which is photographed by a camera mounted on the robot arm.

Specifically, the mechanical arm is rotated around the Y axis for a preset degree based on the first rotation gesture, and the current photographed image of the marking plate is obtained through photographing.

And rotating the mechanical arm in the second rotation position around the Z axis by a preset degree to obtain a third rotation position, and acquiring a third rotation image corresponding to the third rotation position.

The third rotation gesture may be a gesture of rotating the mechanical arm in the second rotation gesture around the Z axis by a preset degree. The third rotation image may be an image of the marking plate when the robot arm is in the third rotation posture, which is photographed by a camera mounted on the robot arm.

Specifically, the mechanical arm is rotated around the Z axis for a preset degree based on the second rotation gesture, and the current photographed image of the marking plate is obtained through photographing.

Optionally, performing a translation initialization operation on the first pose to obtain a translation deviation, including:

and carrying out translation initialization operation on the first pose, and acquiring a corresponding translation image set in the translation initialization operation.

The translation image set may be a set formed by images of a plurality of marking plates captured by the camera in the process of performing translation initialization operation on the first pose.

Specifically, on the basis of the first pose Pose, translation initialization operation is performed, translation is performed along the directions of the X axis, the Y axis and the Z axis respectively, 3 times of translation are obtained through photographing respectively, and a translation image set is obtained.

And determining the translation deviation according to the translation image set and the marker plate image in the expected pose.

Specifically, according to the marker plate image obtained by 3 translation photographing, the marker plate image and the expected bit image GoalImage identify characteristic points, and the translation deviation is calculated.

Optionally, performing a translation initialization operation on the first pose, and acquiring a corresponding translation image set in the translation initialization operation, including:

and translating the mechanical arm in the third rotation gesture along the X-axis direction by a preset distance to obtain a first translation gesture, and acquiring a first translation image corresponding to the first translation gesture.

The preset distance may be a translation distance preset according to an actual situation, which is not limited in this embodiment.

The first translational posture may be a posture state of the mechanical arm after translating the mechanical arm in the first posture along the X-axis direction by a preset distance. The first translational image may be an image of the marking plate when the robot arm is in the first translational posture, which is captured by a camera mounted on the robot arm.

Specifically, the mechanical arm is translated along the X-axis direction by a preset distance under the condition of being based on the first pose Pose, and a currently shot marking plate image is obtained through photographing.

And translating the mechanical arm in the first translational attitude along the Y-axis direction by a preset distance to obtain a second translational attitude, and acquiring a second translational image corresponding to the second translational attitude.

The second translational posture may be a posture state of the mechanical arm after translating the mechanical arm in the first translational posture along the Y-axis direction by a preset distance. The second translational image may be an image of the marking plate when the robot arm is in the second translational pose captured by a camera mounted on the robot arm.

Specifically, the mechanical arm is translated along the Y-axis direction by a preset distance under the condition of being based on the first translation posture, and the current photographed image of the marking plate is obtained through photographing.

And translating the mechanical arm in the second translational attitude along the Z-axis direction by a preset distance to obtain a third translational attitude, and acquiring a third translational image corresponding to the third translational attitude.

The third translational posture may be a posture of the mechanical arm after translating the mechanical arm in the second posture along the Z-axis direction by a preset distance. The third translational image may be an image of the marking plate when the robot arm is in the third translational posture, which is captured by a camera mounted on the robot arm.

Specifically, the mechanical arm is translated along the Z-axis direction by a preset distance under the condition of being based on the second translation gesture, and the current shot marking plate image is obtained through shooting.

Optionally, a deviation exists between the marker plate image in the target pose and the marker plate image in the desired pose that is less than a preset threshold.

As an overall description of an embodiment of the present invention, the detailed flow of the visual positioning method can be described as follows:

1. Firstly, setting an expected state, namely, setting an expected pose of a robot (Pose, recording pose information of the current robot), photographing and identifying characteristic point information of a marker plate under the expected pose, recording, and simultaneously storing a marker plate image GoalImage under the expected pose;

2. Setting deviation between the current state of the simulation robot and the expected pose, adding random winding under the expected pose of the robot, wherein the disturbance range is random, namely adding random disturbance to the expected pose in the X, Y and Z directions to obtain the current pose state Pose2, and ensuring that a marking plate can be shot later;

3. Before correction based on an image, carrying out rotation initialization, respectively carrying out initial rotation around X, Y and Z axes (the rotation requires that a marking plate can be shot each time) based on Pose, wherein the rotation mode is that the marking plate is firstly rotated around the X axis and then photographed to obtain a current photographed marking plate image, then the marking plate is rotated around the Y axis again, and then rotated around the Z axis again by analogy, the marking plate is photographed respectively after rotation, the rotation deviation is calculated according to the marking plate image obtained by 3 times of rotation photographing and the expected image GoalImage, so that one rotation control calculation is carried out, and the current robot is rotated and corrected to obtain Pose3;

4. And initializing translation, namely firstly translating along the X-axis direction under Pose, photographing to obtain a currently photographed image of the marking plate, translating along the Y-axis direction on the basis, analogizing, translating along the Z-axis direction, photographing the marking plate after translation, respectively photographing the marking plate according to the image of the marking plate obtained by 3 times of translation photographing, identifying characteristic points with an expected bitmap image GoalImage, and calculating translation deviation, so that one translation control calculation is performed, and carrying out translation correction on the current robot to obtain Pose.

5. And (3) based on Pose, the deviation between the current marker plate image and the expected image GoalImage is obtained by photographing and calculating sequentially, the rotation control amount and the translation control amount are obtained, the robot is subjected to rotation control and translation control, the iteration is sequentially performed, and finally when the deviation between the current photographed image and the expected image GoalImage meets the requirement, the iteration is terminated, namely the default camera is adjusted to a photographing position which is expected to be set, and the grabbing operation can be performed based on the state of the robot.

And planning the next action of the robot based on the current image characteristics and calculation in the visual servo process of the robot. The visual servo track planning method completes the visual servo task by generating a proper image characteristic point track and then tracking the image characteristic point track by using the controller, so that the image error of each control period is smaller, and the stability of the space track is ensured. Under the condition of no calibration, camera internal parameters, robot kinematic parameters and hand-eye relations are unknown, in which case, a visual servo scheme based on a reference image is utilized to guide the robot to position, and the scheme is not influenced by the change of the camera internal parameters. While the camera may be positioned relative to the non-planar object given a "reference image" taken with a completely different camera.

Example two

Fig. 2 is a schematic structural view of a pose determining apparatus in an embodiment of the present invention. The embodiment can adapt to the situation that the robot arm performs pose determination when the robot on the hand performs positioning grabbing operation, the device can be implemented in a software and/or hardware mode, the device can be integrated in any equipment providing the pose determination function, as shown in fig. 2, and the pose determination device specifically comprises: a first acquisition module 201, a second acquisition module 202, a judgment module 203 and a determination module 204.

The first acquiring module 201 is configured to acquire an expected pose corresponding to the mechanical arm, and acquire a marker plate image under the expected pose;

a second obtaining module 202, configured to obtain a current pose of the mechanical arm, and obtain a marker plate image under the current pose;

a judging module 203, configured to judge whether a deviation between the image of the marking board in the current pose and the image of the marking board in the expected pose is smaller than a preset threshold;

And the determining module 204 is configured to determine, according to the current pose and the desired pose, a target pose corresponding to the mechanical arm if the deviation is greater than or equal to the preset threshold.

Optionally, the determining module 204 includes:

the first operation unit is used for carrying out rotation initialization operation on the current pose to obtain rotation deviation;

the first correcting unit is used for carrying out rotation correction on the mechanical arm according to the rotation deviation to obtain a first pose;

the second operation unit is used for carrying out translation initialization operation on the first pose to obtain translation deviation;

the second correcting unit is used for carrying out translation correction on the mechanical arm according to the translation deviation to obtain a second pose;

A determining unit configured to determine a rotation control amount and a translation control amount according to the second pose and the desired pose;

The control unit is used for carrying out rotation control and translation control on the mechanical arm according to the rotation control quantity and the translation control quantity and taking the rotation control and the translation control as the updated current pose of the mechanical arm;

And the execution unit is used for returning to execute the operation of carrying out rotation initialization on the current pose to obtain rotation deviation until the target pose is obtained.

Optionally, the first operation unit includes:

The first operation subunit is used for carrying out rotation initialization operation on the current pose and acquiring a corresponding rotation image set in the rotation initialization operation;

a first determination subunit for determining a rotation deviation from the set of rotation images and the marker plate image in the desired pose.

Optionally, the first operation subunit is specifically configured to:

rotating the mechanical arm in the current pose around an X axis for a preset degree to obtain a first rotation pose, and acquiring a first rotation image corresponding to the first rotation pose;

rotating the mechanical arm in the first rotation position around the Y axis for the preset degree to obtain a second rotation position, and acquiring a second rotation image corresponding to the second rotation position;

and rotating the mechanical arm in the second rotation position around the Z axis by the preset degree to obtain a third rotation position, and acquiring a third rotation image corresponding to the third rotation position.

The second operation subunit is used for carrying out translation initialization operation on the first pose and acquiring a corresponding translation image set in the translation initialization operation;

And the second determination subunit is used for determining translation deviation according to the translation image set and the marker plate image in the expected pose.

Optionally, the second operation subunit is specifically configured to:

translating the mechanical arm in the third rotation position along the X-axis direction by a preset distance to obtain a first translation position, and acquiring a first translation image corresponding to the first translation position;

Translating the mechanical arm in the first translational attitude by the preset distance along the Y-axis direction to obtain a second translational attitude, and acquiring a second translational image corresponding to the second translational attitude;

And translating the mechanical arm in the second translational attitude along the Z-axis direction by the preset distance to obtain a third translational attitude, and acquiring a third translational image corresponding to the third translational attitude.

Optionally, a deviation between the marker plate image in the target pose and the marker plate image in the expected pose is smaller than the preset threshold.

The product can execute the pose determining method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of executing the pose determining method.

Example III

Fig. 3 shows a schematic diagram of an electronic device 30 that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic equipment may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.

As shown in fig. 3, the electronic device 30 includes at least one processor 31, and a memory, such as a Read Only Memory (ROM) 32, a Random Access Memory (RAM) 33, etc., communicatively connected to the at least one processor 31, wherein the memory stores a computer program executable by the at least one processor, and the processor 31 can perform various suitable actions and processes according to the computer program stored in the Read Only Memory (ROM) 32 or the computer program loaded from the storage unit 38 into the Random Access Memory (RAM) 33. In the RAM 33, various programs and data required for the operation of the electronic device 30 may also be stored. The processor 31, the ROM 32 and the RAM 33 are connected to each other via a bus 34. An input/output (I/O) interface 35 is also connected to bus 34.

Various components in electronic device 30 are connected to I/O interface 35, including: an input unit 36 such as a keyboard, a mouse, etc.; an output unit 37 such as various types of displays, speakers, and the like; a storage unit 38 such as a magnetic disk, an optical disk, or the like; and a communication unit 39 such as a network card, modem, wireless communication transceiver, etc. The communication unit 39 allows the electronic device 30 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.

The processor 31 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 31 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 31 performs the respective methods and processes described above, such as the pose determination method:

In some embodiments, the pose determination method may be implemented as a computer program tangibly embodied on a computer-readable storage medium, such as the storage unit 38. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 30 via the ROM 32 and/or the communication unit 39. When the computer program is loaded into RAM 33 and executed by processor 31, one or more steps of the pose determination method described above may be performed. Alternatively, in other embodiments, the processor 31 may be configured to perform the pose determination method by any other suitable means (e.g., by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.

A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.

The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.

It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.

The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.

Claims

1. The pose determining method is characterized by comprising the following steps of:

2. The method of claim 1, wherein determining a target pose corresponding to a robotic arm from the current pose and the desired pose comprises:

Performing rotation initialization operation on the current pose to obtain rotation deviation;

Carrying out rotation correction on the mechanical arm according to the rotation deviation to obtain a first pose;

carrying out translation initialization operation on the first pose to obtain translation deviation;

carrying out translation correction on the mechanical arm according to the translation deviation to obtain a second pose;

determining a rotation control amount and a translation control amount according to the second pose and the expected pose;

Performing rotation control and translation control on the mechanical arm according to the rotation control amount and the translation control amount to serve as the updated current pose of the mechanical arm;

and returning to execute the operation of rotating and initializing the current pose to obtain the rotation deviation until the target pose is obtained.

3. The method according to claim 2, wherein performing a rotation initialization operation on the current pose to obtain a rotation deviation comprises:

Performing rotation initialization operation on the current pose, and acquiring a corresponding rotation image set in the rotation initialization operation;

and determining a rotation deviation according to the rotation image set and the marker plate image in the expected pose.

4. A method according to claim 3, wherein performing a rotation initialization operation on the current pose and obtaining a corresponding set of rotation images in the rotation initialization operation comprises:

5. The method according to claim 2, wherein performing a translation initialization operation on the first pose to obtain a translation deviation comprises:

performing translation initialization operation on the first pose, and acquiring a corresponding translation image set in the translation initialization operation;

And determining a translation deviation according to the translation image set and the marker plate image in the expected pose.

6. The method of claim 5, wherein performing a translation initialization operation on the first pose and obtaining a corresponding set of translation images in the translation initialization operation comprises:

7. The method of claim 1, wherein a deviation exists between the marker plate image in the target pose and the marker plate image in the desired pose that is less than the preset threshold.

8. A pose determination apparatus, characterized by comprising:

9. An electronic device, the electronic device comprising:

At least one processor; and

A memory communicatively coupled to the at least one processor; wherein,

The memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the pose determination method according to any of claims 1-7.

10. A computer readable storage medium, characterized in that the computer readable storage medium stores computer instructions for causing a processor to implement the pose determination method according to any of claims 1-7 when executed.