Main and auxiliary double-camera visual guiding structure for robot machining

Abstract

The utility model discloses a main-auxiliary double-camera visual guidance structure for robot machining, and relates to the technical field of robot visual guidance machining. An end effector is mounted at the tail end of a mechanical arm of a robot; comprising a camera support, an eye outside-hand depth camera, an eye on-hand depth camera, a control cabinet electrically connected with the robot and an industrial personal computer electrically connected with the eye outside-hand depth camera, the eye on-hand depth camera and the control cabinet. The eye outside-hand depth camera obtains coordinate information of a to-be-machined position of the roughly-positioned to-be-machined workpiece and sends the coordinate information to the industrial personal computer; the industrial personal computer controls the eye depth camera to move on the hand through the control cabinet so that the second view area can correspond to the to-be-machined position. The eye-on-hand depth camera obtains coordinate information of a to-be-machined position of the precisely-positioned to-be-machined workpiece and sends the coordinate information to the industrial personal computer; and the industrial personal computer drives and guides the end effector through the control cabinet to perform finish machining on the to-be-machined position of the to-be-machined workpiece. According to the utility model, robot visual guidance processing with coarse positioning and fine positioning can be realized.

Description

TECHNICAL FIELD

[0001] The utility model relates to robot vision guiding processing technical field, in particular to a kind of main auxiliary dual-camera vision guiding structure for robot processing. BACKGROUND

[0002] In the field of robot vision guiding technology, eye-in-hand and eye-to-hand systems are usually divided into two categories. In the eye-in-hand system, the camera is installed at the end of the robot arm and moves with the robot. In the eye-to-hand system, the camera is installed in a fixed position and does not move with the robot. The eye-in-hand robot vision guiding method has the advantages of flexible shooting angle and high imaging accuracy, but the field of view is relatively limited. The eye-to-hand robot vision guiding method has the advantage of large field of view, but the shooting angle is fixed and the imaging accuracy is relatively low. The combination of eye-in-hand and eye-to-hand robot vision guiding methods can complement each other and improve the robot's vision guiding ability.

[0003] Therefore, the utility model innovatively provides a kind of main auxiliary dual-camera vision guiding structure for robot processing, can use the large field of view depth camera of eye-to-hand to collect the scene point cloud of processing site, complete robot large-scale rough positioning vision guiding, use the small field of view depth camera of eye-in-hand to collect the process feature point cloud of workpiece, to complete the vision guiding processing of small range of robot, by free and reasonable switching between large and small field of view cameras, the robot vision guiding processing of rough positioning and fine positioning can be realized, to overcome the limitations of prior art. UTILITY MODEL CONTENT

[0004] Therefore, the utility model provides a kind of main auxiliary dual-camera vision guiding structure for robot processing, to solve the technical problems of low positioning efficiency and poor vision guiding ability caused by the eye-in-hand or eye-to-hand system of traditional robot single vision guiding processing.

[0005] To achieve the above purpose, the utility model adopts the following technical scheme:

[0006] The utility model provides a kind of main auxiliary dual-camera vision guiding structure for robot processing, and the workpiece to be processed is arranged on one side of robot, and the end effector for processing workpiece to be processed is installed at the end of the mechanical arm of robot;It includes:

[0007] Camera support, the camera support is arranged in the side of the workpiece to be processed;

[0008] Eye-to-hand depth camera, the eye-to-hand depth camera is installed on the camera support and forms a field of view area one on the side corresponding to the workpiece to be processed;

[0009] an eye-in-hand depth camera mounted on the peripheral wall of the robot arm and close to the end effector to form a field of view area two corresponding to one side of the end effector;

[0010] a control cabinet electrically connected to the robot to control the movement of the end effector driven by the robot arm;

[0011] an industrial computer electrically connected to the eye-in-hand depth camera, the eye-in-hand depth camera and the control cabinet, the eye-in-hand depth camera acquires coordinate information of the rough positioning of the processing position of the workpiece to be processed and sends it to the industrial computer; the industrial computer outputs the coordinate information of the rough positioning of the processing position of the workpiece to be processed to the control cabinet, the control cabinet controls the movement of the eye-in-hand depth camera to make the field of view area two corresponding to the processing position; the eye-in-hand depth camera acquires coordinate information of the fine positioning of the processing position of the workpiece to be processed and sends it to the industrial computer; the industrial computer outputs the coordinate information of the fine positioning of the processing position of the workpiece to be processed to the control cabinet, the control cabinet drives the end effector to fine process the processing position of the workpiece to be processed.

[0012] When the main and auxiliary dual-camera visual guidance structure for robot processing of the utility model works, after the workpiece to be processed reaches the designated processing station, the industrial computer captures the overall scene point cloud of the processing station by starting the eye-in-hand depth camera fixed on the camera support, and then the workpiece can be moved to the field of view center of the field of view area one of the eye-in-hand depth camera by robot or manually; the industrial computer starts the eye-in-hand depth camera again to acquire the scene point cloud, and the processing position (i.e. the processing feature) of the workpiece to be processed is roughly positioned according to the acquired scene point cloud data, and then the robot is guided to move and gradually approach the processing feature by the eye-in-hand depth camera until the processing feature is in the field of view center of the field of view area two of the eye-in-hand depth camera. The industrial computer triggers the eye-in-hand depth camera again to acquire the processing feature point cloud data, and the visual guidance algorithm built-in the industrial computer accurately identifies and positions the processing feature according to the obtained processing feature point cloud data, and then the industrial computer guides the robot action through the control cabinet to complete the processing of the workpiece to be processed by the end effector. The eye-in-hand depth camera of the utility model realizes the rough positioning of the workpiece to be processed, overcoming the small field of view limitation of single use of the eye-in-hand depth camera; the eye-in-hand depth camera realizes the fine positioning of the processing feature guided by the robot, overcoming the low positioning accuracy of single use of the eye-in-hand depth camera. The utility model realizes high-precision processing of robot visual guidance by freely and reasonably switching between large and small field of view cameras.

[0013] As a further improvement of the above technical solution, it further comprises a workpiece positioning robot for moving the workpiece to be processed to a central position of the field of view area of the eye-in-hand external depth camera; the workpiece to be processed is installed on the workpiece positioning robot; and the industrial computer is electrically connected to the workpiece positioning robot.

[0014] The above technical solution has the beneficial effect that when the industrial computer starts the eye-in-hand external depth camera to perform rough positioning of the workpiece to be processed, the workpiece positioning robot can be controlled by the industrial computer to move the workpiece to be processed to the central position of the field of view area, thereby reducing the labor intensity and improving the processing efficiency.

[0015] As a further improvement of the above technical solution, the camera support comprises a base, a vertical rod and a mounting seat.

[0016] The lower end of the vertical rod is fixed to the base, the eye-in-hand external depth camera is fixedly installed on the mounting seat, and the mounting seat is slidably installed on the vertical rod to adjust the position height of the eye-in-hand external depth camera and further adjust the position height of the field of view area.

[0017] The above technical solution has the beneficial effect that by fixing the mounting seat at different heights of the vertical rod, the position height of the eye-in-hand external depth camera can be flexibly adjusted, and further the position height of the field of view area can be flexibly adjusted as needed.

[0018] As a further improvement of the above technical solution, the mounting seat is arranged perpendicularly to the vertical rod, one end of the mounting seat is slidably sleeved on the vertical rod and can be fastened to the vertical rod by a fastener, the other end of the mounting seat is fixed with a camera mounting platform, and the eye-in-hand external depth camera is installed on the upper end of the camera mounting platform.

[0019] As a further improvement of the above technical solution, it further comprises a heightening support fixedly installed on the outer peripheral wall of the mechanical arm, and the eye-in-hand external depth camera is fixedly installed on the top end of the heightening support.

[0020] The above technical solution has the beneficial effect that the heightening support can make the field of view area two of the eye-in-hand external depth camera avoid the end effector at the front end, thereby preventing the end effector from interfering with the collection of scene point cloud data of the eye-in-hand external depth camera in space.

[0021] Via the above technical solution, compared with the prior art, the utility model discloses a kind of main auxiliary dual-camera visual guidance structures for robot processing, with the following advantages and beneficial effects:

[0022] 1. The eye-in-hand depth camera of the utility model realizes the rough positioning of workpieces, and overcomes the small field of view limitation of single use of the eye-in-hand depth camera. The eye-in-hand depth camera realizes the fine positioning of the machining features guided by the robot, and overcomes the low positioning accuracy of single use of the eye-in-hand depth camera.

[0023] 2. The utility model discloses a main and auxiliary dual-camera visual guidance positioning, can carry out the free and reasonable switching between the large and small field of view cameras, thereby realizing the robot visual guidance machining of rough positioning plus fine positioning. DRAWINGS

[0024] In order to more clearly illustrate the technical scheme in the embodiments of the utility model or the prior art, the following will briefly introduce the drawings needed to be used in the embodiment or the prior art description, and obviously, the drawings in the following description are only the embodiments of the utility model, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative labor.

[0025] Fig. 1 The utility model discloses a main and auxiliary dual-camera visual guidance structure for robot machining whole structure three-dimensional schematic view;

[0026] Fig. 2 The utility model discloses a main and auxiliary dual-camera visual guidance structure for robot machining another visual angle three-dimensional schematic view;

[0027] Fig. 3 The utility model discloses a camera support structure schematic view of main and auxiliary dual-camera visual guidance structure for robot machining;

[0028] Fig. 4 The utility model discloses a main and auxiliary dual-camera visual guidance structure for robot machining eye-in-hand depth camera installation state schematic view;

[0029] In the drawing: 1, robot;11, mechanical arm;12, end effector;2, workpiece to be processed;3, camera support;31, base;32, vertical rod;33, mounting seat;331, fastener;332, mounting platform;4, eye-in-hand depth camera;41, field of view area one;5, eye-in-hand depth camera;51, field of view area two;6, control cabinet;7, industrial computer;8, cushioning support;9, workpiece clamping tooling. DETAILED DESCRIPTION

[0030] The embodiments of the utility model will be described in detail below, and the examples of the embodiments are shown in the drawings, wherein the same or similar reference signs represent the same or similar elements or elements with the same or similar functions throughout. The embodiments described below by referring to the drawings are exemplary and are intended to explain the utility model, and cannot be understood as the limitation of the utility model.

[0031] In the description of the utility model, it is understood that the terms "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer" and the like indicate the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the utility model and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as limiting the utility model.

[0032] In addition, the terms "first", "second" are only for the purpose of description, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the technical features indicated. Therefore, the features defined with "first", "second" can explicitly or implicitly include one or more of the features. In the description of the utility model, the meaning of "multiple" is two or more than two, unless otherwise specifically limited.

[0033] In the utility model, unless otherwise specifically defined and limited, the terms "mounting", "connection", "connection", "fixing" and the like should be understood broadly, for example, it can be fixedly connected, or it can be detachably connected, or it can be integrated; it can be mechanically connected, or it can be electrically connected; it can be directly connected, or it can be indirectly connected through an intermediate medium; it can be the communication or interaction relationship between two elements. For ordinary skilled in the art, the specific meaning of the above terms in the utility model can be understood according to the specific circumstances.

[0034] According to the utility model embodiment, as shown in Figs. 1 to 4 A main and auxiliary dual-camera visual guidance structure for robot machining, as shown in the figure, comprising: a robot 1, a camera support 3, an eye-in-hand depth camera 4, an eye-on-hand depth camera 5, a control cabinet 6 and an industrial computer 7.

[0035] The workpiece 2 to be processed is arranged on one side of the robot 1, and the end effector 12 for processing the workpiece 2 to be processed is mounted at the end of the mechanical arm 11 of the robot 1; the camera support 3 is arranged on the side of the workpiece 2 to be processed; the eye-in-hand external depth camera 4 is mounted on the camera support 3 and forms a field of view area one 41 on the side corresponding to the workpiece 2 to be processed; the eye-in-hand external depth camera 5 is mounted on the outer peripheral wall of the mechanical arm 11 and is close to the end effector 12 to form a field of view area two 51 on the side corresponding to the end effector 12; the control cabinet 6 is electrically connected to the robot 1 to control the mechanical arm 11 of the robot 1 to drive the end effector 12 to move for processing; the industrial computer 7 is electrically connected to the eye-in-hand external depth camera 4, the eye-in-hand external depth camera 5 and the control cabinet 6, so as to coarsely position the coordinate information of the workpiece 2 to be processed by acquiring the scene point cloud data shot by the eye-in-hand external depth camera 4, and then drive the eye-in-hand external depth camera 5 to move by the control cabinet 6 to make the field of view area two 51 correspond to the workpiece 2 to be processed, and then finely position the coordinate information of the workpiece 2 to be processed by acquiring the scene point cloud data shot by the eye-in-hand external depth camera 5, and then drive the end effector 12 to finely process the workpiece 2 to be processed by the control cabinet 6.

[0036] When the workpiece 2 to be processed reaches the specified processing station, the industrial computer 7 starts the eye-in-hand external depth camera 4 fixed on the camera support 3 to capture the overall scene point cloud of the processing station, and then the workpiece can be moved to the central field of view of the field of view area one 41 of the eye-in-hand external depth camera 4 by the robot or manually; the industrial computer 7 starts the eye-in-hand external depth camera 4 again to acquire the scene point cloud, coarsely positions the workpiece 2 to be processed according to the acquired scene point cloud data, and then guides the robot 1 to drive the eye-in-hand external depth camera 5 to move and gradually approach the workpiece 2 to be processed until the workpiece 2 to be processed is in the central field of view of the field of view area two 51 of the eye-in-hand external depth camera 5. The industrial computer 7 triggers the eye-in-hand external depth camera 5 again to acquire the workpiece 2 to be processed point cloud data, and the visual guidance algorithm built in the industrial computer 7 accurately identifies and positions the workpiece 2 to be processed according to the obtained workpiece 2 to be processed point cloud data, and then the industrial computer 7 guides the robot 1 to move by the control cabinet 6 to complete the processing of the workpiece 2 to be processed by the end effector 12. The eye-in-hand external depth camera 4 of the utility model realizes coarse positioning of the workpiece 2 to be processed, and overcomes the small field of view limitation of single use of the eye-in-hand external depth camera 5; the eye-in-hand external depth camera 5 realizes fine positioning of the workpiece 2 to be processed by the robot, and overcomes the low positioning accuracy of single use of the eye-in-hand external depth camera 4. The utility model realizes high-precision processing of robot visual guidance by freely and reasonably switching between the large and small field of view cameras.

[0037] In some embodiments, a workpiece positioning robot is further included for moving the workpiece 2 to be processed to a central position of the field of view area one 41 of the hand-eye depth camera 4; the workpiece 2 to be processed is mounted on the workpiece positioning robot; and the industrial computer 7 is electrically connected to the workpiece positioning robot.

[0038] When the industrial computer 7 starts the hand-eye depth camera 4 to perform rough positioning of the workpiece 2 to be processed, the workpiece positioning robot can be controlled by the industrial computer 7 to move the workpiece 2 to be processed to the central position of the field of view area one 41, thereby reducing the labor intensity and improving the processing efficiency.

[0039] Specifically, the workpiece positioning robot can be arranged at the side of the robot 1, and the workpiece positioning robot is mounted with a workpiece clamping tool 9, and the workpiece 2 to be processed is mounted on the workpiece positioning robot through the workpiece clamping tool 9.

[0040] In some embodiments, the camera support 3 includes a base 31, a vertical rod 32, and a mounting seat 33.

[0041] The lower end of the vertical rod 32 is fixed on the base 31, and the hand-eye depth camera 4 is fixedly installed on the mounting seat 33; the mounting seat 33 is slidably installed on the vertical rod 32 to adjust the position height of the hand-eye depth camera 4, and further adjust the position height of the field of view area one 41.

[0042] By fixing the mounting seat 33 at different heights on the vertical rod 32, the position height of the hand-eye depth camera 4 can be flexibly adjusted, and further the position height of the field of view area one 41 can be flexibly adjusted as needed.

[0043] In some embodiments, the mounting seat 33 is arranged vertically to the vertical rod 32, one end of the mounting seat 33 is slidably sleeved on the vertical rod 32 and can be fastened on the vertical rod 32 by fasteners 331; the other end of the mounting seat 33 is welded with a camera mounting platform 332; and the hand-eye depth camera 4 is bolted on the upper end of the camera mounting platform 332. The fasteners 331 can be selected from screws or bolts.

[0044] In some embodiments, a heightening support 8 is further included, which is fixedly installed on the outer peripheral wall of the mechanical arm 11 by bolts or U-shaped tube clamps, and the hand-eye depth camera 5 is fixedly installed on the top end of the heightening support 8 by bolts.

[0045] The heightening support 8 can make the field of view area two 51 of the hand-eye depth camera 5 avoid the end effector 12 at the front end, so as to prevent the end effector 12 from interfering with the collection of scene point cloud data of the hand-eye depth camera 5 in space.

[0046] It should be noted that the eye-in-hand depth camera is fixed in the robot coordinate system, and the large field of view eye-in-hand depth camera and the small field of view eye-in-hand depth camera are calibrated in advance. The coordinates of the point cloud captured by the eye-in-hand depth camera and the eye-in-hand depth camera can be converted into the coordinates of the corresponding points in the robot coordinate system; the point cloud captured by the large field of view eye-in-hand depth camera is processed, and the to-be-processed feature of the to-be-processed workpiece can be determined through a visual recognition algorithm. The specific depth camera calibration method and the visual recognition algorithm belong to the prior art, and will not be described here.

[0047] It should be noted that the robot 1 is a six-degree-of-freedom articulated industrial robot for workpiece machining, and an ABB robot can be selected; the control cabinet 6 is an ABB robot control cabinet compatible with the ABB robot. The end effector 12 is installed at the flange end of the robot arm 11 of the robot 1, serving as a tool for machining workpieces. The eye-in-hand depth camera is a small field of view depth camera installed at the end of the robot arm; the eye-in-hand depth camera is a large field of view camera fixed on the camera support. The industrial computer 7 is used to complete the visual guidance of the robot 1 for workpiece machining. The industrial computer 7 is connected to the ABB robot control cabinet and the two eye-in-hand depth cameras (the eye-in-hand depth camera 4 and the eye-in-hand depth camera 5), analyzes and processes the point cloud model captured by the depth camera through a specific visual algorithm, extracts the coordinate information of the to-be-processed feature in the point cloud model, and feeds back the coordinate information to the ABB robot control cabinet. The ABB robot control cabinet includes an integrated unit of a robot motion controller and a PLC controller. The ABB robot control cabinet and the industrial computer are connected through Ethernet to realize Socket communication, which is mainly used to accept the industrial computer signal and control the ABB robot motion.

[0048] In some embodiments, a specific example of cutting the sprue and the riser of the ball valve blank is given. After the ball valve blank reaches the designated machining station, the industrial computer 7 captures the overall scene point cloud of the machining station by starting the eye-in-hand depth camera 4 fixed on the camera support 3, and then moves the ball valve blank to the center of the field of view of the eye-in-hand depth camera 4. The industrial computer 7 starts the eye-in-hand depth camera 4 again to obtain the scene point cloud, roughly positions the sprue or the riser of the ball valve blank according to the obtained scene point cloud data, and then guides the robot 7 to gradually approach the ball valve blank to be cut, until the ball valve blank to be cut is in the center of the field of view of the eye-in-hand depth camera 5. The industrial computer 7 triggers the eye-in-hand depth camera again to obtain the feature point cloud of the ball valve blank to be cut, and the visual guidance algorithm accurately identifies and positions the ball valve blank to be cut according to the obtained feature point cloud, and then the industrial computer 7 guides the robot 1 through the control cabinet 6 to complete the cutting of the sprue or the riser of the ball valve blank by means of the end effector 12. The end effector 12 can be an electric cutting saw.

[0049] In the description of the present specification, the description referring to the terms "one embodiment", "some embodiments", "an example", "a specific example", or "some examples" and the like means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the present specification, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Also, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and integrate different embodiments or examples described in the present specification.

[0050] Although the embodiments of the present application have been shown and described above, it is understood that the above-described embodiments are exemplary and are not to be construed as limiting the present application, and those skilled in the art can make changes, modifications, replacements and variations to the above-described embodiments within the scope of the present application.

Claims

1. A dual-camera vision guidance structure for robot processing, wherein a workpiece (2) to be processed is arranged on one side of a robot (1), and an end effector (12) for processing the workpiece (2) is installed at the end of the robotic arm (11) of the robot (1); characterized in that, include: A camera bracket (3) is arranged on the side of the workpiece (2) to be processed; An eye-to-hand depth camera (4) is mounted on the camera bracket (3) and forms a field of view (41) on the side corresponding to the workpiece (2) to be processed; An eye-on-hand depth camera (5) is mounted on the outer peripheral wall of the robotic arm (11) and close to the end effector (12) to form a second field of view (51) on the side corresponding to the end effector (12); Control cabinet (6), which is electrically connected to the robot (1) to control the robotic arm (11) of the robot (1) to drive the end effector (12) to perform processing movements; An industrial control computer (7) is electrically connected to the eye-in-the-hand external depth camera (4), the eye-in-the-hand depth camera (5), and the control cabinet (6). The eye-in-the-hand external depth camera (4) acquires the coordinate information of the workpiece (2) to be processed and sends it to the industrial control computer (7). The industrial control computer (7) outputs the coordinate information of the workpiece (2) to be processed and sends it to the control cabinet (6). The control cabinet (6) controls the eye-in-the-hand depth camera (5) to move so that the second field of view (51) corresponds to the workpiece. The eye-in-the-hand depth camera (5) acquires the coordinate information of the workpiece (2) to be processed and sends it to the industrial control computer (7). The industrial control computer (7) outputs the coordinate information of the workpiece (2) to be processed and sends it to the control cabinet (6). The control cabinet (6) drives and guides the end effector (12) to perform fine processing on the workpiece (2).

2. The dual-camera vision guidance structure for robot processing according to claim 1, characterized in that, It also includes a workpiece positioning robot for moving the workpiece (2) to the center of the field of view (41) of the eye-to-hand depth camera (4); the workpiece (2) is mounted on the workpiece positioning robot.

3. The dual-camera vision guidance structure for robot processing according to claim 1, characterized in that, The camera bracket (3) includes a base (31), a pole (32), and a mounting base (33); The lower end of the pole (32) is fixed on the base (31); the eye-in-the-hand depth camera (4) is fixedly mounted on the mounting base (33); the mounting base (33) is slidably mounted on the pole (32) to adjust the position height of the eye-in-the-hand depth camera (4), thereby adjusting the position height of the field of view (41).

4. The dual-camera vision guidance structure for robot processing according to claim 3, characterized in that, The mounting base (33) is arranged perpendicular to the upright (32). One end of the mounting base (33) is slidably sleeved on the upright (32) and can be fastened to the upright (32) by fasteners (331). The other end of the mounting base (33) is fixed with a camera mounting platform (332). The eye-to-hand depth camera (4) is mounted on the upper end of the camera mounting platform (332).

5. The dual-camera vision guidance structure for robot processing according to claim 1, characterized in that, It also includes a raised support (8), which is fixedly installed on the outer peripheral wall of the robotic arm (11), and the eye-on-hand depth camera (5) is fixedly installed on the top of the raised support (8).

Images