Plane grabbing system and grabbing method

Abstract

The invention discloses a plane grabbing system and method, and relates to the technical field of automatic grabbing equipment. The plane grabbing system comprises a part conveying module, an image collecting module, a control unit and a grabbing mechanism. The part conveying module is connected with the material arranging platform, and parts to be grabbed are conveyed to the material arranging platform based on the part conveying module. The image acquisition module is arranged right above the material arrangement platform, and image acquisition of the to-be-grabbed part is realized based on the image acquisition module; the control unit is connected with the image acquisition module to obtain an image of the to-be-grabbed part, image analysis of the to-be-grabbed part is realized based on the control unit, and a control signal is output; the grabbing mechanism is connected with the control unit to receive the control signal, and the grabbing mechanism changes the state of the to-be-grabbed part or conveys the to-be-grabbed part to the material disc based on the control signal; through accurate cooperation of the part conveying module, the image collecting module, the control unit and the grabbing mechanism, efficient, accurate and reliable part grabbing operation is achieved.

Description

Technical Field

[0001] This application relates to the technical field of automated grasping devices, and particularly to a planar grasping system and a grasping method. Background Art

[0002] With the rapid development of industrial automation, part grasping systems play an increasingly important role in the manufacturing industry. Especially in precision manufacturing fields such as automotive and electronics, higher requirements are put forward for the automated grasping, sorting, and assembly of parts; currently, common part grasping systems on the market mainly include technical solutions such as mechanical grasping and vision-guided grasping.

[0003] However, there are still many technical problems in the prior art in dealing with the grasping scenarios of parts with oil stains and high reflectivity. First, in terms of unordered grasping, existing systems are difficult to effectively handle the situation where parts are scattered and have different postures. Especially when there is interference between parts or when grasping in a specified direction is required, the grasping accuracy and efficiency are significantly reduced; second, for parts with oil stains on the surface, existing vision recognition systems are difficult to accurately identify part features, and the presence of oil stains and debris further reduces the recognition accuracy; in addition, the surface of high-reflective parts will cause large changes in the reflective area and degree due to slight changes in the angle, and existing light source designs and image processing algorithms are difficult to cope with this complex situation.

[0004] Therefore, it is urgent to develop a planar grasping system that can effectively solve the above technical problems to improve the accuracy, stability, and efficiency of part grasping and meet the requirements of modern manufacturing for automated production. Summary of the Invention

[0005] In order to solve the technical problems of unordered grasping, dirty part grasping, reflective part recognition, and flexible production line adaptability in the prior art in the grasping scenarios of parts with oil stains and high reflectivity, and to improve the part recognition rate and grasping success rate, the present invention provides a planar grasping system for high-reflective parts with oil stains based on deep learning, and also provides a grasping method applicable to the above planar grasping system.

[0006] The first technical solution adopted in this application is: to provide a planar grasping system, including:

[0007] A part conveying module, which is connected to a sorting platform, and conveys the parts to be grasped to the sorting platform based on the part conveying module;

[0008] An image acquisition module, which is arranged directly above the sorting platform, and realizes image acquisition of the parts to be grasped based on the image acquisition module;

[0009] A control unit, which is connected to the image acquisition module to obtain an image of the part to be grasped, and based on the control unit, image analysis of the part to be grasped is implemented and a control signal is output;

[0010] A grasping mechanism, which is connected to the control unit to receive the control signal, and based on the control signal, changes the state of the part to be grasped or conveys the part to be grasped to a tray.

[0011] Preferably, a vibration mechanism is arranged below the part sorting platform, and based on the vibration mechanism, the distribution of parts on the part sorting platform is changed.

[0012] Preferably, the part conveying module includes a blanking mechanism and a blanking ramp; based on the blanking mechanism, the material box is locked and rotated, and the parts in the material box are poured out onto the blanking ramp; based on the blanking ramp, the impact when the parts are poured out of the material box is buffered and the parts are guided into the part sorting platform.

[0013] Preferably, the image acquisition module includes an industrial camera and a plurality of light sources evenly distributed around the industrial camera; based on the plurality of light sources, uniform illumination is formed to improve the recognition accuracy.

[0014] Preferably, the grasping mechanism includes a SCARA robot and a pneumatic soft gripper, and a friction material is provided on the surface of the pneumatic soft gripper, and based on the friction material, the grasping stability of the pneumatic soft gripper is improved.

[0015] Preferably, the SCARA robot can perform secondary positioning, and based on the secondary positioning, the posture of the part to be grasped is adjusted.

[0016] The second technical solution adopted in this application is: a grasping method is provided, which can be applied to the planar grasping system described in any one of the above, and includes the following steps:

[0017] S1: Based on the blanking mechanism, lock and rotate the material box, and the part to be grasped slides smoothly along the blanking ramp into the part sorting platform;

[0018] S2: The image acquisition module performs image acquisition on the part to be grasped on the part sorting platform;

[0019] S3: The control unit receives the part image data from the image acquisition module, performs image analysis based on a deep learning algorithm and generates a control signal;

[0020] S4: The grasping mechanism performs corresponding operations based on the received control signal to ensure that the part is correctly grasped and placed in the tray.

[0021] Preferably, in the step S2, it further includes detecting the surface condition of the part, and the image detection module dynamically adjusts the light source intensity or angle based on the detection result to optimize the image acquisition quality.

[0022] Preferably, in the step S3, when it is recognized that there is interference between parts, the knocking-down action is accurately executed based on the vibration mechanism or the SCARA robot to change the part distribution.

[0023] Preferably, in the step S4, during the grasping process, the position and force of the gripper are monitored and adjusted in real time to improve the grasping accuracy.

[0024] Due to the adoption of the above technical solutions, compared with the prior art, the present application has at least one of the following beneficial effects:

[0025] 1. Through the precise cooperation of the part conveying module, the image acquisition module, the control unit and the grasping mechanism, an efficient, accurate and reliable part grasping operation is realized.

[0026] 2. Dynamically adjusting the light source intensity or angle according to the specific situation of the part can effectively improve the recognition accuracy.

[0027] 3. The cooperative design of the blanking mechanism and the blanking ramp not only reduces the possible damage to the parts during the transfer process, but also enables the parts to enter the sorting platform in an orderly manner.

[0028] 4. Automatically outputting control signals based on the analysis results to guide the grasping mechanism to execute corresponding actions greatly reduces the need for manual intervention. Description of the Drawings

[0029] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0030] Among them:

[0031] Figure 1 is a framework schematic diagram of an embodiment of the planar grasping system provided by the present application;

[0032] Figure 2 is a structural schematic diagram of an embodiment of the planar grasping system provided by the present application;

[0033] Figure 3 is a flow schematic diagram of an embodiment of the grasping method provided by the present application. Detailed Embodiments

[0034] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. It can be understood that the specific embodiments described herein are only used to explain the present application, rather than limiting the present application. In addition, it should be noted that for the sake of description, only the parts related to the present application rather than all the structures are shown in the accompanying drawings. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts shall fall within the protection scope of the present application.

[0035] The terms "first", "second", etc. in the present application are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products or devices.

[0036] Referring to "embodiments" herein means that specific features, structures or characteristics described in connection with the embodiments can be included in at least one embodiment of the present application. The appearance of this phrase in various positions in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0037] Embodiment 1

[0038] As Figure 1 - Figure 2 shown, Figure 1 is a schematic framework diagram of an embodiment of the planar grasping system provided by the present application; Figure 2 is a schematic structural diagram of an embodiment of the planar grasping system provided by the present application; the planar grasping system includes a part conveying module, an image acquisition module, a control unit and a grasping mechanism.

[0039] The part conveying module is connected to the sorting platform and is used to convey the parts to be grasped to the sorting platform; the sorting platform is a flat workbench surface, the surface of which has been specially treated and has an appropriate friction coefficient, which can not only make the parts placed stably, but also facilitate the movement or adjustment of the parts when needed. The size and height of the sorting platform can be adjusted according to the actual production line; the sorting platform is made of aluminum alloy material and the surface is treated by anodic oxidation to enhance wear resistance and corrosion resistance.

[0040] The image acquisition module is arranged directly above the sorting platform and is used to acquire images of the parts to be grasped. The image acquisition module is installed on a bracket with adjustable height, and the bracket is fixed on the ground or wall around the sorting platform. The installation height of the image acquisition module is adjusted based on the bracket to meet the image acquisition requirements of parts with different sizes; the image acquisition module is connected to the control unit through a data cable to transmit the acquired image data in real time.

[0041] The control unit is connected to the image acquisition module to obtain images of the parts to be grasped, perform image analysis on the parts to be grasped and output control signals; the control unit includes an industrial computer equipped with a high-performance processor and special image processing software; the industrial computer adopts a dust-proof and shock-proof design and is suitable for long-term stable operation in an industrial environment; the control unit has built-in image processing algorithms and can perform preprocessing, feature extraction and target recognition on the received images to determine the position, posture and type of the parts to be grasped; the control unit generates control signals according to the analysis results and transmits them to the grasping mechanism through a communication interface.

[0042] The grasping mechanism is connected to the control unit to receive control signals, and based on the control signals, it changes the state of the parts to be grasped or conveys the parts to be grasped to the tray; the grasping mechanism is installed beside the sorting platform, and its working range covers the entire sorting platform and the tray placement area. The grasping mechanism is connected to the control unit through a cable to receive control signals and perform corresponding actions. The grasping mechanism can accurately locate the position of the parts to be grasped according to the control signals, grasp the parts and place them in the specified tray, or change the state of the parts on the sorting platform as needed.

[0043] In summary, the planar grasping system of this embodiment includes a part conveying module, an image acquisition module, a control unit and a grasping mechanism; the part conveying module is connected to the sorting platform, and based on the part conveying module, the parts to be grasped are conveyed to the sorting platform; the image acquisition module is arranged directly above the sorting platform, and based on the image acquisition module, images of the parts to be grasped are acquired; the control unit is connected to the image acquisition module to obtain images of the parts to be grasped, and based on the control unit, image analysis of the parts to be grasped is performed and control signals are output; the grasping mechanism is connected to the control unit to receive control signals, and based on the control signals, the grasping mechanism changes the state of the parts to be grasped or conveys the parts to be grasped to the tray; through the precise cooperation of the part conveying module, the image acquisition module, the control unit and the grasping mechanism, efficient, accurate and reliable part grasping operations are achieved.

[0044] A vibrating mechanism is provided below the part sorting platform for changing the distribution of parts on the part sorting platform. The vibrating mechanism includes a vibrating motor and a shock-absorbing device; the vibrating mechanism is connected to the part sorting platform through the shock-absorbing device, and the shock-absorbing device adopts a combined design of springs and rubber shock pads, which can not only transmit vibration but also prevent excessive impact; the working mode of the vibrating mechanism can be divided into two types: continuous vibration and intermittent vibration, and the vibration intensity and frequency can be precisely adjusted through the control unit; when parts on the part sorting platform are stacked or interfere with each other, the vibrating mechanism will be activated, and through appropriate vibration, the parts will be dispersed to form a distribution state that is more conducive to grasping; the following details the working process of the vibrating mechanism:

[0045] The parts on the part sorting platform are initially scanned by the image acquisition module to determine the initial position, posture of the parts, and whether there is any interference; when it is found that there is interference between the parts or the posture of some parts is not suitable for direct grasping, it is decided to start vibration.

[0046] After the vibration process ends, the part sorting platform is scanned again using the image acquisition module to evaluate the new position and posture of the parts. If the parts have reached a state suitable for grasping, proceed to the next step; if they still do not meet the requirements, repeat the above vibration steps or adopt robot-assisted knockdown or evacuation.

[0047] Vibration can help separate parts that were originally in contact or even stacked together, thereby reducing the risk of picking up multiple parts simultaneously during the grasping process; for the problem that parts with oil stains are easily adsorbed on the tray, vibration can overcome the adhesion force.

[0048] The part conveying module includes a blanking mechanism and a blanking ramp; based on the blanking mechanism locking the material frame and rotating, the parts in the material frame are poured out onto the blanking ramp; based on the blanking ramp buffering the impact when the parts are poured out of the material frame and guiding the parts into the part sorting platform; the following details the working process of the part conveying module:

[0049] The blanking mechanism first locks the material frame to ensure that the material frame remains stable and immovable during subsequent operations; the material frame is tilted through a rotating mechanism to pour out the parts therein.

[0050] After the parts are poured out of the material frame, they slide down along the blanking ramp with an appropriate inclination angle and a smooth surface; the design purpose of the blanking ramp is to slow down the sliding speed of the parts and avoid collisions and damages between the parts. It should be clear that the specific angle of the blanking ramp is not limited in this application, and the angle of the blanking ramp can be adjusted based on different production lines, and no specific limitation is made on this.

[0051] The end of the blanking ramp is directly connected to the part sorting platform to ensure that the parts can smoothly transition from the ramp to the platform.

[0052] Through the buffering effect of the tipping ramp, the collision probability of parts during transfer can be significantly reduced, thereby reducing the risk of damage; the good connection between the ramp and the sorting platform helps the parts to form a more dispersed layout on the platform, which is beneficial to subsequent image acquisition and recognition work.

[0053] The image acquisition module includes an industrial camera and a plurality of light sources evenly distributed around the industrial camera; in this embodiment, four light sources are evenly distributed around the industrial camera. In other embodiments, the number of light sources can be three or five, and no limitation is made thereto.

[0054] Uniform illumination is formed based on multiple light sources to improve the recognition accuracy; the uniform illumination provided by multiple light sources can effectively eliminate shadows and reflections, making the surface details of the parts more clearly visible, which helps to improve the accuracy of the recognition algorithm.

[0055] The grasping mechanism includes a SCARA robot and a pneumatic soft gripper. The surface of the pneumatic soft gripper is provided with a friction material to improve the grasping stability of the pneumatic soft gripper based on the friction material; the friction material covered on the surface of the pneumatic soft gripper can significantly increase the friction force between the contact surface with the parts, which is particularly important when dealing with parts with oil stains, smooth or irregular shapes. Higher friction force helps to ensure stable grasping even under adverse conditions; for parts with oil stains or other lubricating substances, ordinary grasping tools may cause the parts to fall or shift in position due to slipping. Using materials with a high coefficient of friction can effectively prevent this situation from occurring, ensuring the continuity and reliability during the operation process.

[0056] The SCARA robot can perform secondary positioning to adjust the pose of the part to be grasped. The secondary positioning function is achieved through the precise motion control of the SCARA robot; when the SCARA robot grasps the part, it can move the part to a specified position for pose adjustment according to the instructions of the control unit; during the secondary positioning process, the SCARA robot can rotate the part around the Z axis to adjust the angle of the part, or fine-tune the position of the part in the XY plane to ensure that the part is placed in the tray in the correct pose.

[0057] Embodiment Two

[0058] A grasping method can be applied to the planar grasping system described in Embodiment One, as Figure 3 shown Figure 3 is a schematic flow chart of an embodiment of the grasping method provided by this application, including the following steps:

[0059] S1: Lock and rotate the material box based on the tipping mechanism, and the part to be grasped slides smoothly along the tipping ramp into the sorting platform;

[0060] S2: The image acquisition module acquires images of the parts to be grasped on the feeding platform. The following details the specific process of image acquisition by the image acquisition module:

[0061] The camera takes pictures of the scene containing the standard checkerboard calibration board, and multiple pictures can be taken from multiple angles and positions. All the corner points of the checkerboard in each picture are detected, and the positions of the corner points represent the coordinates in the camera coordinate system.

[0062] If all the necessary corner points are successfully recognized, the robotic arm is made to touch these corner points one by one through the teaching function of the robot, and the robot plane coordinates of each corner point are recorded. If the corner points cannot be successfully recognized, the pictures are acquired again, and the camera angle or lighting conditions are adjusted to obtain clearer images.

[0063] The root mean square error (RMSE) is calculated based on the corner point coordinates in the camera coordinate system and the corresponding robot plane coordinates to evaluate the conversion accuracy. Based on the comparison between the RMSE and the preset threshold, the accuracy of the affine transformation matrix is judged. If the RMSE is less than the preset threshold, the current affine transformation matrix is used to perform the operation of converting the camera coordinate system to the robot coordinate system. If the RMSE is greater than or equal to the preset threshold, the robot performs the touch teaching again, and the robot re-obtains the affine transformation matrix based on increasing the samples or optimizing the touch accuracy.

[0064] It should be clear that in this embodiment, the size of the preset threshold is 0.2; in other embodiments, the size of the preset threshold can be taken as other values, and no limitation is made thereto.

[0065] S3: The control unit receives the part image data from the image acquisition module, performs image analysis based on the deep learning algorithm and generates a control signal. In this embodiment, the deep learning algorithm is constructed based on 1000 part data sets in each of the three states of oil-free, light oil, and heavy oil.

[0066] S4: The grasping mechanism performs corresponding operations based on the received control signal to ensure that the parts are correctly grasped and placed in the tray.

[0067] In step S2, it also includes detecting the surface condition of the parts. The image detection module dynamically adjusts the light source intensity or angle based on the detection results to optimize the image acquisition quality. While the image acquisition module acquires images, it also performs real-time detection of the surface condition of the parts. The detection content includes the reflection situation, shadow distribution, and texture features on the part surface. When a strong reflection area is detected on the part surface, the system will automatically reduce the brightness of the light source in the corresponding direction, and the brightness adjustment range is 50% to 80% of the original brightness. When an obvious shadow is detected on the part surface, the system will increase the brightness of the light source in the corresponding direction of the shadow area, and the brightness adjustment range is 120% to 150% of the original brightness. Through dynamic adjustment, the system can obtain clearer and higher-contrast part images, providing a better data basis for subsequent image analysis.

[0068] In step S3, when interference between parts is identified, the knockdown action is precisely executed based on the vibration mechanism or the SCARA robot to change the part distribution. The control unit analyzes the part images through deep learning algorithms. When interference between parts is identified (such as parts being stacked or stuck to each other), the system will take corresponding measures to change the part distribution. If the interference situation is relatively common, the control unit will activate the vibration mechanism to disperse the parts. If there is only interference in a local area, the control unit will command the SCARA robot to perform a precise knockdown action; the SCARA robot moves above the interference area and gently pushes or separates the interfering parts with pneumatic soft jaws, controlling the force to avoid damaging the parts. After the knockdown action is completed, the system re-performs image acquisition and analysis to check whether the interference is removed. If the interference still exists, the system will adjust the strategy and try different knockdown directions or forces until the part distribution is suitable for grasping.

[0069] In step S4, during the grasping process, the position and force of the gripper are monitored and adjusted in real time to improve the grasping accuracy. When the grasping mechanism performs the grasping operation, it monitors the grasping state in real time through built-in force sensors and position sensors. When a deviation is detected between the actual grasping force and the target grasping force, the system will automatically adjust the air pressure of the pneumatic soft jaws to achieve the optimal grasping force. When it is detected that the part has a displacement during the grasping process, the system will adjust the position of the SCARA robot in real time to ensure that the part is accurately grasped. During the part transportation process, the system continuously monitors the grasping state. If it is detected that the part has a tendency to loosen or slip, the system will immediately increase the grasping force or adjust the grasping position to prevent the part from falling. Through this real-time monitoring and adjustment mechanism, the system can adapt to parts of various shapes and materials, greatly improving the grasping success rate and accuracy.

[0070] In several embodiments provided by the present application, it should be understood that the disclosed methods and devices can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0071] The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0072] In addition, each functional unit in various embodiments of the present application can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0073] The above is only the embodiment of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present application, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present application.

Claims

1. A planar grasping system, characterized in that, Including: A part conveying module, which is connected to the material sorting platform and conveys the parts to be grasped to the material sorting platform based on the part conveying module; An image acquisition module, which is arranged directly above the material sorting platform and realizes image acquisition of the parts to be grasped based on the image acquisition module; A control unit, which is connected to the image acquisition module to obtain the images of the parts to be grasped, realizes image analysis of the parts to be grasped based on the control unit and outputs control signals; A grasping mechanism, which is connected to the control unit to receive the control signals, and the grasping mechanism changes the state of the parts to be grasped or conveys the parts to be grasped to the tray based on the control signals.

2. The planar grasping system according to claim 1, wherein A vibration mechanism is arranged below the material sorting platform, and the distribution of the parts on the material sorting platform is changed based on the vibration mechanism.

3. The planar grasping system according to claim 2, wherein The part conveying module includes a blanking mechanism and a blanking ramp; the blanking mechanism locks and rotates the material box, and the parts in the material box are poured out onto the blanking ramp; the blanking ramp buffers the impact when the parts are poured out of the material box and guides the parts into the material sorting platform.

4. The planar grasping system according to claim 3, wherein, The image acquisition module includes an industrial camera and a plurality of light sources evenly distributed around the industrial camera; uniform illumination is formed based on the plurality of light sources to improve the recognition accuracy.

5. The planar grasping system according to claim 4, wherein The grasping mechanism includes a SCARA robot and a pneumatic soft gripper, and friction materials are provided on the surface of the pneumatic soft gripper, and the grasping stability of the pneumatic soft gripper is improved based on the friction materials.

6. The planar grasping system according to claim 5, wherein, The SCARA robot can perform secondary positioning, and the object pose of the parts to be grasped is adjusted based on the secondary positioning.

7. A grasping method applicable to the planar grasping system according to any one of claims 1-6, characterized in that, Including the following steps: S1: Lock and rotate the material box based on the blanking mechanism, and the parts to be grasped slide smoothly into the material sorting platform along the blanking ramp; S2: The image acquisition module acquires images of the parts to be grasped on the material sorting platform; S3: The control unit receives the part image data from the image acquisition module, performs image analysis based on the deep learning algorithm and generates control signals; S4: The grasping mechanism performs corresponding operations based on the received control signals to ensure that the parts are correctly grasped and placed in the tray.

8. The grasping method according to claim 7, characterized in that In step S2, it also includes detecting the surface condition of the parts, and the image detection module dynamically adjusts the light source intensity or angle based on the detection results to optimize the image acquisition quality.

9. The grasping method according to claim 8, wherein In step S3, when interference is identified between parts, the vibration mechanism or the SCARA robot is precisely used to perform a knocking-down action to change the part distribution.

10. The grasping method according to claim 8, wherein In step S4, the position and force of the gripper are monitored and adjusted in real time during the grasping process to improve the grasping accuracy.

Images