Grasping methods, actuators and robots

Abstract

This application relates to the field of intelligent grasping equipment technology, and in particular to a grasping method, an execution device, and a robot. The execution device has an execution mechanism for grasping a workpiece; a vision unit is located on the execution mechanism, and the field of view of the vision unit covers the gripping area of ​​the execution mechanism and the workpiece; the grasping method includes: acquiring a target image of the workpiece acquired in real time by the vision unit; calculating the target distance from the execution mechanism to the workpiece based on the target image; and controlling the execution mechanism to move the target distance to grasp the workpiece. The relative positions of the vision unit and the execution mechanism are fixed, and the field of view of the vision unit moves synchronously with the execution mechanism, improving the real-time performance of information acquisition. The vision unit can obtain the distance the execution mechanism needs to move to grip the workpiece the instant it acquires the target image of the workpiece, directly calculate the target distance, and complete autonomous grasping, achieving immediate use and rapid deployment.

Description

Technical Field

[0001] This application relates to the field of intelligent grasping equipment technology, and in particular to a grasping method, an execution device, and a robot. Background Technology

[0002] Currently, vision devices are installed externally to the actuators to collect positional information of the actuators and the workpieces, enabling positioning and operational control. However, external vision devices require extensive calibration of the vision and robotic arm coordinates. Furthermore, the layout of the work platform must be planned, and the camera installation position repeatedly debugged and corrected. When the production line changes or the camera position is moved, the vision units need to be recalibrated, and the grasping logic altered, making coordinate calibration cumbersome.

[0003] The information disclosed in this background section is intended only to enhance the understanding of the overall background of this application and should not be construed as an admission or in any way implying that the information constitutes prior art known to those skilled in the art. Summary of the Invention

[0004] Therefore, it is necessary to provide a grasping method, execution device, and robot to address the problem that external vision devices require extensive calibration of vision and robotic arm coordinates, which leads to cumbersome coordinate calibration.

[0005] In a first aspect, embodiments of this application provide a gripping method using an execution device, the execution device comprising: an execution mechanism for gripping a workpiece; and at least one vision unit disposed on the execution mechanism, the vision unit having a field of view covering the gripping area of ​​the execution mechanism and the workpiece; the method comprising:

[0006] Acquire the target image of the executed component in real time by the vision unit;

[0007] Calculate the target distance from the actuator to the executed part based on the target image;

[0008] Control the actuator to move the target distance to grab the object to be executed.

[0009] Secondly, embodiments of this application provide an execution device, comprising:

[0010] An actuator includes a connector, a drive assembly, and an actuator. The drive assembly is located on the connector and drives the actuator to grip or release the executed component.

[0011] At least one vision unit is provided on the connector, and the field of view of the vision unit is used to cover the actuator and the executed component.

[0012] Thirdly, embodiments of this application provide a robot, which includes a robotic arm and an execution device. The execution device is the same as the one described in the second aspect, and the connection seat of the execution device is connected to the robotic arm.

[0013] The vision unit of the aforementioned actuator is integrated into the actuator, allowing the vision unit's field of view to directly cover the mating area of ​​the actuator and the executed part, with the mating areas of the actuator and the executed part coinciding within the field of view. The relative positions of the vision unit and the actuator are fixed, and the vision unit's field of view 31 moves synchronously with the actuator, continuously acquiring information about the actuator and the executed part. This reduces blind spots present in external vision devices and improves the real-time performance of information acquisition. Furthermore, the change in the relative position of the actuator and the vision unit reduces the workload of additional calibration of their relative positions, significantly saving on multiple calibration, debugging, and logic development tasks, eliminating accumulated errors caused by multi-layer coordinate transformations, and improving grasping accuracy and operational stability. This application ensures that the vision unit's field of view coincides with the clamping area of ​​the actuator, enabling execution throughout the clamping process under the vision's field of view, providing a real-time view of the executed part. The grasping method provided in this application enables the vision unit to acquire the target image of the executable in real time and calculate the target distance from the actuator to the executable, thus achieving real-time positioning and immediate grasping of the executable. In other words, the vision unit can determine the distance the actuator needs to move to grip the executable the instant it acquires the target image of the executable. After recognizing the position of the executable, the vision unit can directly calculate the target distance and complete autonomous grasping, achieving plug-and-play functionality and rapid deployment. Attached Figure Description

[0014] Figure 1 This is a flowchart of a crawling method provided in an embodiment of this application.

[0015] Figure 2 A side view of a robot provided in an embodiment of this application.

[0016] Figure 3 This is a perspective view of an execution device provided in an embodiment of this application.

[0017] Figure 4 This is a cross-sectional view of a portion of the structure of an execution device provided in an embodiment of this application.

[0018] Figure 5 An exploded view of an actuator provided in an embodiment of this application.

[0019] Figure 6 This is an assembly diagram of a slider and a rack provided in an embodiment of this application.

[0020] Explanation of reference numerals in the attached drawings: 100, robot; 10, actuator; 1, connecting seat; 11, connecting shell; 111, first receiving cavity; 112, mounting hole; 12, connecting cover; 121, second receiving cavity; 122, mounting groove; 123, opening; 13, receiving cavity; 2, actuator; 21, drive assembly; 211, driver; 212, transmission assembly; 2121, gear; 2122, rack; 21221, third side; 21222, fourth side; 22, actuator; 23, sliding assembly; 231, slide; 2311, support; 2312, slide rod; 232, sliding element; 2321, first side; 2322, second side; 2323, sliding hole; 3, vision unit; 31, acquisition field of view; 20, robotic arm. Detailed Implementation

[0021] To make the above-mentioned objectives, features, and advantages of this application more apparent and understandable, the specific embodiments of this application are described in detail below with reference to the accompanying drawings. Many specific details are set forth in the following description to provide a thorough understanding of this application. However, this application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar modifications without departing from the spirit of this application. Therefore, this application is not limited to the specific embodiments disclosed below.

[0022] This application provides a gripping method for guiding an execution device 10 to clamp a workpiece. The execution device 10 includes an execution mechanism 2 and at least one vision unit 3. The execution mechanism 2 is used to grip the workpiece, and the vision unit 3 is disposed on the execution mechanism 2. The field of view of the vision unit 3 covers the gripping area of ​​the execution mechanism 2 and the workpiece. Please refer to [link to relevant documentation]. Figure 1The method includes: acquiring a target image of the workpiece captured in real time by the vision unit 3; calculating the target distance from the execution mechanism 2 to the workpiece based on the target image; and controlling the execution mechanism 2 to move the target distance to grasp the workpiece. Thus, the execution device 10 of this application integrates the execution mechanism 2 and the vision unit 3. The relative positional relationship between the vision unit 3 and the execution mechanism 2 is fixed. Compared to an external vision system, the execution device 10 of this application will not change the relative position of the execution mechanism 2 and the vision unit 3 due to the installation or debugging of the execution mechanism 2. This reduces the workload of additional calibration of the relative position of the execution mechanism 2 and the vision unit 3, significantly saving the workload of multiple calibrations, debugging, and logic development, eliminating the cumulative error caused by multi-layer coordinate transformations, and improving grasping accuracy and operational stability. Furthermore, this application ensures that the visual field of the vision unit 3 and the clamping area of ​​the execution mechanism 2 coincide, allowing the entire clamping process to be performed under the visual field, providing a real-time view of the workpiece. The grasping method provided in this application enables the vision unit 3 to acquire the target image of the object to be grasped in real time and calculate the target distance from the actuator 2 to the object, thus achieving real-time positioning and immediate grasping of the object. In other words, the vision unit 3 can obtain the distance that the actuator 2 needs to move to grasp the object the instant it acquires the target image of the object. After recognizing the position of the object, the vision unit 3 can directly calculate the target distance and complete autonomous grasping, achieving plug-and-play functionality and rapid deployment.

[0023] In some embodiments, the target distance from the actuator 2 to the executed component is calculated based on the target image, including:

[0024] Based on the target image, calculate the theoretical movement distance from actuator 2 to the executed part;

[0025] Calculate the deviation of the actual movement of actuator 2;

[0026] Calculate the target distance from actuator 2 to the executed part based on the deviation and the theoretical movement distance.

[0027] Due to errors caused by the installation and movement of actuator 2, the theoretical movement distance of actuator 2 and the target distance may differ. Therefore, it is necessary to calculate the deviation of the actual movement of actuator 2 in advance to obtain the target distance of actuator 2.

[0028] In some embodiments, the number of vision units 3 is two, and the theoretical movement distance from the actuator 2 to the executed part is calculated based on the target image, including:

[0029] Calculate the theoretical movement distance from actuator 2 to the executed part according to the preset movement distance formula;

[0030] The preset movement distance formula is as follows:

[0031] Z = (f × B) / d, where Z is the theoretical moving distance, f is the focal length of visual unit 3, B is the straight-line distance between the optical centers of two visual units 3, and d is the parallax between the two visual units 3.

[0032] Spatial dimension positioning is achieved using two vision units 3 based on the principle of binocular triangulation. The straight-line distance and focal length between the optical centers of the two vision units 3 are fixed structural parameters. Only the parallax of the two vision units 3 needs to be calculated to determine the theoretical movement distance of the actuator 2, reducing computational processing logic and lowering hardware costs. The complementary imaging perspectives of the two vision units 3 form a cross-field of view that covers the clamping operation area of ​​the actuator 2, ensuring stable acquisition of workpiece position information, reducing occlusion, and achieving higher positioning accuracy. The theoretical movement distance is calculated using the above method, and the results can be output in real time with fast response speed, adapting to dynamic grasping.

[0033] It is understandable that the disparity between the two visual units 3 refers to the pixel difference between the two visual units 3 when capturing the same feature point on the same image line. Both visual units 3 can be 2D cameras. The optical axes of the two visual units 3 are parallel, and their imaging planes are coplanar. When the actuator 2 moves to any point P in space, the projection points PL and PR on the imaging planes of the left and right visual units 3 will be on the same horizontal line. At this time, the disparity d is defined as the difference in the horizontal coordinates of the point in the left and right images: d = xL − xR. Where xL refers to the horizontal coordinate of the point in the left image, which is the coordinate read by the left visual unit 3. xR refers to the horizontal coordinate of the point in the right image, which is the coordinate read by the right visual unit 3.

[0034] In some embodiments, calculating the deviation of the actual movement of the actuator 2 includes:

[0035] The control actuator 2 is positioned at the first acquisition position, enabling the vision unit 3 to acquire a standard image of the standard gauge block;

[0036] Analyze the physical length of standard blocks in a standard image;

[0037] The control actuator 2 moves the physical length along the length direction of the standard gauge block to the second acquisition position, so that the vision unit 3 can acquire the comparison image of the standard gauge block;

[0038] Match the same feature point in the standard image and the comparison image, and calculate the deviation of the feature point along the length direction of the standard block.

[0039] By using standard gauge blocks to calculate in advance the deviation between the actual and theoretical distances of the actuator 2, the theoretical distance can be corrected to the actual distance, thereby reducing the clamping error of the actuator 2.

[0040] Understandably, vision unit 3 identifies the standard gauge block as ABCD at the first acquisition position. After identification, vision unit 3 resolves the physical length of the standard gauge block as |AB|=|CD|=a. The control actuator 2 moves the physical gauge block 'a' to the second acquisition position. After stabilization, vision unit 3 identifies the standard gauge block as A'B'C'D' at the second acquisition position. The deviation Δ=|BA'|. The target distance of the moving mechanism 2 can be calculated from the deviation and the theoretical moving distance using the encoder.

[0041] Thus, the method of this application obtains the theoretical movement distance of the actuator 2 through two vision units 3, calculates the deviation of the actual movement of the actuator 2 through standard gauge blocks, and then directly obtains the actual movement distance of the actuator 2 from the deviation and the theoretical movement distance. In this way, the actuator 2 can accurately grasp the executed part based on the actual movement distance when moving.

[0042] Please see Figure 2 This application provides a robot 100, which includes a robotic arm 20 and an execution device 10. The connection seat 1 of the execution device 10 is connected to the robotic arm 20. The robotic arm 20 can drive the execution device 10 to move in multiple directions and over a wider range, expanding the workspace and operating range of the execution device 10, allowing the execution device 10 to flexibly reach different workstations or target locations, and meeting the robot 100's grasping and handling needs in multiple scenarios and locations.

[0043] Please see Figure 3 The execution device 10 includes an execution mechanism 2 and at least one vision unit 3. The execution mechanism 2 includes a connecting base 1, a drive assembly 21, and an execution element 22. The drive assembly 21 is disposed on the connecting base 1 and drives the execution element 22 to grasp or release the executed element. The vision unit 3 is disposed on the connecting base 1. (See [link to relevant documentation]). Figure 2 The field of view 31 of the vision unit 3 covers both the actuator 22 and the executed component. The vision unit 3 is integrated into the actuator 2, allowing its field of view 31 to directly cover the mating area of ​​the actuator 22 and the executed component, with the mating areas overlapping within the field of view 31. The relative positions of the vision unit 3 and the actuator 2 are fixed, and the field of view 31 of the vision unit 3 moves synchronously with the actuator 2, continuously acquiring information about the actuator 22 and the executed component. This reduces blind spots associated with external vision devices and improves the real-time performance of information acquisition.

[0044] The embodiments of this application do not limit the specific type and gripping method of the actuator 22. The actuator 22 may be an adsorption component, a clamping component, a magnetic component, or an adhesive attachment, etc.

[0045] The embodiments of this application do not limit the specific type of the executable component. The executable component may be a consumer electronics structural component, such as a mobile phone screen, display panel, camera module, etc., or a semiconductor structural component, such as a circuit board, chip carrier, etc., or an automotive part, such as a connector, precision gear, etc.

[0046] Please see Figure 4 and Figure 5 The drive assembly 21 includes a driver 211 and a transmission assembly 212. The driver 211 is mounted on the connecting base 1 and is driven by the transmission assembly 212. The transmission assembly 212 is movably mounted on the connecting base 1. There are two actuators 22, and the transmission assembly 212 is driven by the two actuators 22 to clamp or release the executed part. The two actuators 22 clamp the executed part using an opening and closing clamping method, which is applicable to various types of actuators 22 and offers better versatility. Furthermore, clamping the executed part increases the contact area between the actuators 22 and the executed part, improving gripping stability and reliability, and reducing the risk of the executed part falling. The addition of the transmission assembly 212 to the drive assembly 21 converts the output motion of the driver 211 into the opening and closing motion of the two actuators 22.

[0047] Please see Figure 4 The connecting seat 1 is provided with a receiving cavity 13 and an opening 123 communicating with the receiving cavity 13 (see [reference]). Figure 5 The connector 1 is also provided with a mounting slot 122 (see [link]). Figure 5 Please see Figure 4 The mounting slot 122 is positioned opposite to the receiving cavity 13. Please refer to [link / reference]. Figure 2 The mounting slot 122 and the opening 123 are located on the same side of the connector 1. Please refer to [link / reference]. Figure 4 Both the drive 211 and the transmission assembly 212 are located within the receiving cavity 13. Please refer to [link / reference]. Figure 2 and Figure 4 Two actuators 22 pass through openings 123 and are located outside the receiving cavity 13. The vision unit 3 is located within the mounting groove 122 and is tilted relative to the connecting seat 1 towards the actuators 22. In this way, the driver 211 and the transmission assembly 212 are both hidden within the receiving cavity 13 of the connecting seat 1, improving the space utilization and integration of the connecting seat 1. The mounting groove 122 and the opening 123 are located on the same side of the connecting seat 1, meaning the vision unit 3 and the actuators 22 are also located on the same side of the connecting seat 1. The vision unit 3 is close to the actuators 22, allowing its field of view 31 to directly cover both the actuators 22 and the executed component, reducing blind spots. The tilt of the vision unit 3 towards the actuators 22 allows it to simultaneously acquire positional information of both the actuators 22 and the executed component from different angles, further reducing blind spots. When multiple vision units 3 are included, their fields of view 31 intersect and face the working area of ​​the actuators 22, expanding the range of the field of view 31.

[0048] The embodiments of this application do not limit the installation method of the driver 211 and the transmission assembly 212 in the receiving cavity 13 of the connector 1.

[0049] Please see Figure 4 and Figure 5 The connecting base 1 includes a connecting shell 11 and a connecting cover 12. The receiving cavity 13 includes a first receiving cavity 111 and a second receiving cavity 121. The connecting shell 11 is provided with a first receiving cavity 111 and a mounting hole 112 communicating with the first receiving cavity 111 (see [reference]). Figure 4 The connecting cover 12 is disposed on the connecting shell 11, and the connecting cover 12 is provided with a second receiving cavity 121 (see [link]). Figure 4 ), opening 123 and mounting slot 122 (see Figure 5 The second receiving cavity 121 and the first receiving cavity 111 are respectively located on both sides of the mounting hole 112. The mounting groove 122 and the second receiving cavity 121 are arranged opposite to each other. The mounting groove 122 and the opening 123 are located on the same side of the connecting cover 12. The main body of the driver 211 is connected to the connecting shell 11 and is located in the first receiving cavity 111. The output end of the driver 211 passes through the mounting hole 112 and is located in the second receiving cavity 121. The transmission component 212 is located in the second receiving cavity 121. The two actuators 22 pass through the opening 123 and are located outside the second receiving cavity 121. The vision unit 3 is connected to the connecting cover 12 and is located in the mounting groove 122.

[0050] By setting up the connecting shell 11, connecting cover 12, and first receiving cavity 111 and second receiving cavity 121, the driver 211 and transmission assembly 212 are partitioned, reducing mutual interference, improving the structural stability of the actuator 10, improving the internal regularity of the connecting seat 1, and increasing space utilization. The partitioned assembly of the driver 211, transmission assembly 212, and vision unit 3 facilitates assembly.

[0051] The embodiments of this application do not limit the specific number of visual units 3. The number of visual units 3 can be one, two, three, four, etc., and can be set according to the information collection requirements of the executor 22 and the executed component.

[0052] The field of view 31 of the visual unit 3 refers to the maximum field of view that the visual unit 3 can capture. The ability of the field of view 31 to cover both the executing element 22 and the executed element means that it can completely capture both the currently operating executing element 22 and the executed element being operated by the executing element into the field of view of the visual unit 3. In other words, the visual unit 3 can simultaneously observe both the executing element 22 and the executed element.

[0053] Please see Figure 3 The number of vision units 3 is two, and the two vision units 3 are spaced apart along the direction intersecting the opening and closing of the two actuators 22. Please refer to Figure 2The acquisition fields 31 of the two vision units 3 intersect and face the working area of ​​the actuator 22, which can expand the range of the acquisition field 31. The two vision units 3 can simultaneously acquire the position information of the actuator 22 and the executed part from different angles, reducing blind spots. When the two actuators 22 perform the unfolding action, the acquisition fields 31 of the two vision units 3 can cover the clamping area. When the two actuators 22 perform the clamping action to clamp the executed part, the acquisition fields 31 can cover the two actuators 22 and the executed part.

[0054] The detection principle of the two vision units 3 and the actuator 2 is as follows: The two vision units 3 adopt the binocular vision triangulation principle and the standard gauge block closed-loop calibration method. Each vision unit 3 is equipped with a camera. The two cameras acquire target images of the actuator 22 and the executed part from different perspectives. The spatial position of the target is calculated based on the imaging parallax. Then, using the known size characteristics of the standard gauge block, the theoretical displacement of the actuator 2 is compared with the actual displacement detected by the two cameras to obtain the motion deviation and perform compensation and correction. In this way, the vision coordinate system and the actuator 2 coordinate system can be unified, thereby realizing the positioning and execution control of the actuator 22 and the executed part.

[0055] The embodiments of this application do not limit the specific type of the driver 211. The driver 211 may be a rotary motor or a rotary cylinder, etc.

[0056] The embodiments of this application do not limit the specific type of the transmission component 212. The transmission component 212 may be a gear and rack transmission component, a lead screw and nut transmission component, a synchronous belt and synchronous pulley transmission component, etc., all of which can convert the rotational motion of the driver 211 into the opening and closing motion of the actuator 22.

[0057] Please see Figure 5 The transmission component 212 includes a gear 2121 and two racks 2122. The two racks 2122 are meshed with the gear 2121. The output end of the driver 211 is driven and connected to the gear 2121. The two racks 2122 are movably connected to the connecting seat 1 along the clamping direction. Each rack 2122 is connected to an actuator 22.

[0058] The driver 211 drives the gear 2121 to rotate, which in turn drives two racks 2122 to move in opposite directions. Each rack 2122 drives a corresponding actuator 22 to move. The two actuators 22 can move closer together to perform a clamping action, or they can move further apart to perform a releasing action. The gear 2121 simultaneously drives the two racks 2122 to move in both directions, improving the consistency and synchronization of the opening and closing of the two actuators 22, reducing the number of parts in the transmission assembly 212, simplifying the structure and size, and reducing assembly difficulty.

[0059] The embodiments of this application do not limit the connection method of the rack 2122 being movably connected to the connecting seat 1. The rack 2122 may be rolledly connected to the connecting seat 1 or slidably connected to the connecting seat 1.

[0060] Please see Figure 5 The actuator 2 also includes two sliding components 23. Each sliding component 23 includes a slide base 231 and a sliding member 232. The slide base 231 is located on the connecting seat 1. The sliding member 232 is slidably connected to the slide base 231 along the clamping direction. The sliding member 232 is correspondingly connected to a rack 2122.

[0061] The drive component drives the gear 2121, which in turn drives the rack 2122. The rack 2122 then moves the slider 232 relative to the slide block 231. This sliding connection between the slide block 231 and the slider 232 facilitates installation, reduces costs, and decreases the complexity of the drive assembly 21.

[0062] Please see Figure 6 The slider 232 has a first side 2321 and a second side 2322 that are bent and connected. The surface of the rack 2122 facing away from the tooth includes a third side 21221 and a fourth side 21222 that are bent and connected. The third side 21221 is disposed opposite to the tooth. The third side 21221 is connected to the first side 2321, and the fourth side 21222 is connected to the second side 2322.

[0063] The first side 2321 is in contact with the third side 21221, and the second side 2322 is in contact with the fourth side 21222. This increases the connection area between the sliding member 232 and the rack 2122, improves the support effect on the rack 2122, and makes the transmission between the rack 2122 and the gear 2121 more stable.

[0064] The embodiments of this application do not limit the specific types of the slide block 231 and the sliding member 232. The slide block 231 can be a slide rail, a slide groove, a guide post, etc., and correspondingly, the sliding member 232 can be a slider, a sliding protrusion, a guide sleeve, etc.

[0065] Please see Figure 5 and Figure 6 The slide block 231 includes a support member 2311 and a slide rod 2312. The support member 2311 is provided on the connecting seat 1. The slide rod 2312 is connected to the support member 2311 along the clamping direction. The sliding member 232 is provided with a sliding hole 2323 and is sleeved on the slide rod 2312.

[0066] Sliding is achieved through the cooperation between the sliding rod 2312 and the sliding hole 2323, which can reduce frictional resistance. The sliding hole 2323 is provided on the sliding part 232 to facilitate processing.

[0067] Please see Figure 5 and Figure 6There are two slide rods 2312, which are spaced apart on the support member 2311; there are two sliding holes 2323, and the two slide rods 2312 are respectively inserted into the sliding holes 2323.

[0068] Multiple sliding rods 2312 are set up to guide the sliding member 232 together, constrain the sliding member 232, improve the movement accuracy of the sliding member 232 along the clamping direction, and can disperse the force between the sliding member 232 and the actuator 22, reduce local load and wear, improve the overall load-bearing capacity of the drive assembly 21, and extend its service life.

[0069] Please see Figure 6 One of the sliding holes 2323 is provided on the side of the slider 232 near the first side 2321, and the other sliding hole is provided on the side of the slider 232 near the second side 2322. Thus, one sliding rod 2312 can be inserted through the side of the slider 232 near the first side 2321, and the other slider 232 can be inserted through the side of the slider 232 near the second side 2322.

[0070] In summary, please refer to Figure 2 The execution device 10 provided in this application embodiment directly mounts two vision units 3 onto the execution device 10, and the two vision units 3 form an intersecting acquisition field of view 31. The acquisition field of view 31 coincides with the clamping area of ​​the two actuators 22, reducing blind spots. The vision units 3 move synchronously with the execution device 10, providing real-time visual flow data, improving the action accuracy of the execution device 10, and providing correction and guidance for the execution device 10's clamping operation. Please refer to... Figure 6 By adding a slide rod 2312 and a sliding member 232 with a sliding hole 2323, friction is reduced and the structure is simplified. Each sliding component 23 is provided with two slide rods 2312, which can improve the load-bearing effect. The first side 2321 and the second side 2322 of the sliding member 232 are connected to the third side 21221 and the fourth side 21222 of the rack 2122, which improves the transmission stability.

[0071] In the description of this application, it should be understood that if terms such as "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "radial", "circumferential" appear, these terms indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, and are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this application.

[0072] Furthermore, where the terms "first" and "second" appear, these terms are for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined with "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, where the term "multiple" appears, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0073] In this application, unless otherwise expressly specified and limited, the terms "installation," "connection," "joining," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components, unless otherwise expressly limited. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances.

[0074] In this application, unless otherwise expressly specified and limited, the use of descriptions such as "above" or "below" the second feature indicates that the first and second features are in direct contact or indirect contact via an intermediate medium. Furthermore, "above," "on top of," and "over" the second feature can mean that the first feature is directly above or diagonally above the second feature, or simply that the first feature is at a higher horizontal level than the second feature. Similarly, "below," "below," and "under" the second feature can mean that the first feature is directly below or diagonally below the second feature, or simply that the first feature is at a lower horizontal level than the second feature.

[0075] It should be noted that if an element is referred to as being "fixed to" or "set on" another element, it can be directly on the other element or there may be an intervening element. If an element is considered to be "connected to" another element, it can be directly connected to the other element or there may be an intervening element. If so, the terms "vertical," "horizontal," "upper," "lower," "left," "right," and similar expressions used in this application are for illustrative purposes only and do not represent the only possible implementation.

[0076] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0077] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A grasping method of an actuator, characterized in that, The execution device includes: an execution mechanism for gripping a workpiece; and at least one vision unit disposed on the execution mechanism, the vision unit having a field of view covering the gripping area of ​​the execution mechanism and the workpiece; the method includes: The target image of the executed component is acquired in real time by the vision unit; Based on the target image, calculate the target distance from the actuator to the executed component; The actuator is controlled to move the target distance to grasp the executed item.

2. The grasping method according to claim 1, characterized in that, The step of calculating the target distance from the actuator to the executed component based on the target image includes: Based on the target image, calculate the theoretical movement distance from the actuator to the executed component; Calculate the deviation of the actual movement of the actuator; The target distance from the actuator to the executed component is calculated based on the deviation and the theoretical movement distance.

3. The grasping method according to claim 2, characterized in that, The number of vision units is two, and the step of calculating the theoretical movement distance from the actuator to the executed part based on the target image includes: The theoretical movement distance from the actuator to the executed component is calculated according to a preset movement distance formula. The formula for the preset movement distance is as follows: Z = (f × B) / d, where Z is the theoretical moving distance, f is the focal length of the visual unit, B is the straight-line distance between the optical centers of the two visual units, and d is the parallax between the two visual units.

4. The grasping method according to claim 2, characterized in that, The calculation of the deviation of the actual movement of the actuator includes: The actuator is controlled to be in the first acquisition position, so that the vision unit acquires a standard image of the standard block; Analyze the physical length of the standard block in the standard image; The actuator is controlled to move the physical length of the standard gauge block to the second acquisition position along the length direction of the standard gauge block, so that the vision unit can acquire the comparison image of the standard gauge block; Match the same feature point in the standard image and the comparison image, and calculate the deviation of the feature point along the length direction of the standard block.

5. An actuator, characterized in that, include: An actuator includes a connecting base, a drive assembly, and an actuator, wherein the drive assembly is disposed on the connecting base and is driven to be connected to the actuator to grip or release the executed element; as well as At least one vision unit is provided on the connector, and the field of view of the vision unit is used to cover the actuator and the executed component.

6. The actuator according to claim 5, characterized in that, The drive assembly includes a driver and a transmission assembly. The driver is disposed on the connector and is driven to the transmission assembly. The transmission assembly is movably disposed on the connector. There are two actuators. The transmission assembly is driven to the two actuators so that they clamp or release the actuator.

7. The actuator according to claim 6, characterized in that, The transmission assembly includes a gear and two racks. The two racks are meshed with the gear. The output end of the driver is driven and connected to the gear. The two racks are movably connected to the connecting seat along the clamping direction. Each rack is connected to one of the actuators.

8. The actuator according to claim 7, characterized in that, The actuator further includes two sliding components, each of which includes a slide base and a sliding member. The slide base is disposed on the connecting seat, and the sliding member is slidably connected to the slide base along the clamping direction. The sliding member is correspondingly connected to one of the racks.

9. The actuator according to claim 8, characterized in that, The slider has a first side and a second side that are bent and connected. The surface of the rack facing away from the teeth includes a third side and a fourth side that are bent and connected. The third side is disposed opposite to the teeth. The third side is connected to the first side, and the fourth side is connected to the second side.

10. The actuator according to claim 8, characterized in that, The slide includes a support member and a slide rod. The support member is disposed on the connecting seat, and the slide rod is connected to the support member along the clamping direction. The slide member has a through-hole and is sleeved on the slide rod.

11. The actuator according to claim 10, characterized in that, The number of sliding rods is two, and the two sliding rods are spaced apart on the support member; the number of sliding holes is two, and the two sliding rods are correspondingly inserted into the sliding holes.

12. The actuator according to claim 6, characterized in that, The connector has a receiving cavity and an opening communicating with the receiving cavity. The connector also has a mounting groove, which is disposed opposite to the receiving cavity. The mounting groove and the opening are located on the same side of the connector. The driver and the transmission assembly are both located inside the receiving cavity. The two actuators pass through the opening and are located outside the receiving cavity. The vision unit is disposed inside the mounting groove and is tilted relative to the connector towards the actuator.

13. The actuator according to claim 12, characterized in that, The connector includes a connector shell and a connector cover. The receiving cavity includes a first receiving cavity and a second receiving cavity. The connector shell has the first receiving cavity and a mounting hole communicating with the first receiving cavity. The connector cover is disposed on the connector shell. The connector cover has the second receiving cavity, the opening, and the mounting groove. The second receiving cavity and the first receiving cavity are disposed on opposite sides of the mounting hole. The mounting groove and the second receiving cavity are disposed opposite to each other. The mounting groove and the opening are located on the same side of the connector cover. The main body of the driver is connected to the connector shell and is located in the first receiving cavity. The output end of the driver passes through the mounting hole and is located in the second receiving cavity. The transmission assembly is disposed in the second receiving cavity. The two actuators pass through the opening and are located outside the second receiving cavity. The vision unit is connected to the connector cover and is located in the mounting groove.

14. A robot, characterized in that, The robot includes a robotic arm and an actuator, wherein the actuator is the actuator as described in any one of claims 5 to 13, and the connector of the actuator is connected to the robotic arm.

Images