Robotic sorting system, method, terminal and medium with flexible feeding mechanism

Abstract

This invention provides a robot sorting system, method, terminal, and medium with a flexible feeding mechanism. The flexible feeding mechanism reorders the position and orientation of randomly piled parts, transforming them from 3D to a finite number of 2D / 2.5D orientations for easier picking. A vision system can accurately and quickly obtain information such as the position and orientation of the parts. Based on the obtained information, the robot automatically changes to a suitable end gripper, completing the picking efficiently without waiting. A grating system can also be included to detect whether the parts are accurately placed in the receiving box as needed.

Description

Technical Field

[0001] This invention relates to the field of intelligent robot technology, and in particular to a robot sorting system, method, terminal and medium with a flexible feeding mechanism. Background Technology

[0002] In the product kit sorting system, there are many types of products in the kit and the corresponding parts are small and varied. Currently, the picking of parts for different product kits is entirely done manually or semi-automatically, which is cumbersome, simple and repetitive, and consumes a lot of human resources.

[0003] Sorting of packaged products involves grouping identical parts (the same parts from multiple products) into a batch, and then picking and selecting different batches of parts based on the quantity and type of parts required for the packaged product. Characteristics: 1. Different products require different quantities and types of parts. 2. Parts are densely packed and diverse. 3. The operation is complex and has a high degree of difficulty.

[0004] With the increasing maturity of mechanical automation, the sorting of packaged products is gradually moving towards automation, improving sorting efficiency and accuracy while reducing manual labor. Currently, major manufacturers and enterprises are transitioning from traditional manual and semi-automated operations to fully automated operations. However, packaged product sorting has inherent difficulties and limitations: First, packaged products require a wide variety of parts in varying quantities, making picking and processing difficult and labor-intensive. Due to the differences between packaged products, frequent switching between different material racks to complete the task can cause significant operator fatigue, thus making the overall sorting process highly complex. Second, during the transition to full automation, the parts have irregular shapes and are numerous. Batches of parts coming from upstream are often stacked and intertwined, placing extremely demanding and complex requirements on the machinery. This not only requires highly skilled operators but also involves numerous subsequent inspection steps, making picking very difficult. Summary of the Invention

[0005] In view of the shortcomings of the prior art described above, the present invention provides a robotic sorting system, method, terminal and medium with a flexible feeding mechanism to solve the problems in the background art.

[0006] To achieve the above objectives, a first aspect of the present invention provides a robotic sorting system with a flexible feeding mechanism, comprising: a flexible feeding mechanism for rearranging stacked parts materials; a vision system for acquiring images of the parts materials within the flexible feeding mechanism, extracting visual information of the parts materials from the images, and determining whether each part material meets the picking requirements and identifying the type of the end effector of the robotic system based on the visual information; the robotic system including an end effector and a quick-change system; the robotic system establishing a communication connection with the vision system for receiving visual information of the parts materials and type information of the end effector from the vision system, and picking out parts materials that meet the picking requirements after replacing the corresponding end effector using the quick-change system; a receiving mechanism located within the operating range of the robotic system for storing the parts materials picked out by the robotic system; and a conveying system for carrying the receiving mechanism and conveying the receiving mechanism to a designated location.

[0007] In some embodiments of the first aspect of the present invention, the flexible feeding mechanism includes any one or more combinations of a vibration mechanism, a differential speed mechanism, a ramp circulating flow mechanism, and a swaying mechanism.

[0008] In some embodiments of the first aspect of the present invention, the conditions under which each part material meets the picking requirements include: the parts materials are not stacked, the parts materials are separated, and the specific face of the parts material is facing a pre-specified direction.

[0009] In some embodiments of the first aspect of the present invention, the visual information of the part material includes any one or more combinations of the part material's position information, posture information, specification information, and size information.

[0010] In some embodiments of the first aspect of the present invention, the visual information of the part material includes any one or more combinations of the part material's position information, posture information, specification information, and size information.

[0011] In some embodiments of the first aspect of the invention, the robot sorting system further includes a prompting device for issuing a prompt when the grating detection device detects that parts or materials are not placed inaccurately as required in the receiving mechanism.

[0012] In some embodiments of the first aspect of the present invention, the vision system includes: an image acquisition module for acquiring images of parts and materials within the flexible feeding mechanism; an image processing module for extracting visual information of the parts and materials from the images, and determining whether each part and material meets the picking requirements and determining the type of the end effector of the robot system based on the visual information of the parts and materials; and a communication module for transmitting the visual information of the parts and materials and the type information of the end effector to the outside.

[0013] In some embodiments of the first aspect of the invention, the robot picking system further includes: a 3D camera for acquiring the 3D pose and occlusion relationship of the stacked parts for grasping.

[0014] In some embodiments of the first aspect of the present invention, the vision system determines the quantity and graspable posture of the parts and materials based on the images of the parts and materials in the flexible feeding mechanism, and determines whether to continue feeding and whether to rearrange the parts and materials.

[0015] In some embodiments of the first aspect of the present invention, the parts material includes homogeneous materials and / or mixed materials; the homogeneous materials are sorted according to the number of materials, and the mixed materials are selected according to the material category.

[0016] To achieve the above objectives, a second aspect of the present invention provides a robot sorting method, comprising: acquiring an image of parts materials within a flexible feeding mechanism, and extracting visual information of the parts materials from the image; determining whether each part material meets the picking requirements based on the visual information of the parts materials and determining the type of the end effector of the robot system; transmitting the visual information of the parts materials and the type information of the end effector to an external source, so that the robot system can change the corresponding end effector according to the type information of the end effector, and pick out the parts materials that meet the picking requirements based on the visual information of the parts materials.

[0017] To achieve the above objectives, a third aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the robot sorting method.

[0018] To achieve the above objectives, a fourth aspect of the present invention provides an electronic terminal, including a processor and a memory; the memory is used to store a computer program; the processor is used to execute the computer program stored in the memory to cause the terminal to perform the robot sorting method.

[0019] As described above, the robot sorting system, method, terminal, and medium with flexible feeding mechanism of the present invention have the following beneficial effects:

[0020] (1) The present invention utilizes a flexible feeding mechanism to reorder the position, posture, etc. of the disorderly piled parts and materials, thereby transforming them from 3D to a limited number of 2D / 2.5D postures, which facilitates picking.

[0021] (2) The present invention utilizes a vision system to accurately and quickly obtain information such as the position and orientation of parts. Based on the obtained information, the robot automatically changes to a suitable end gripper, without waiting, and completes the picking process with high efficiency.

[0022] (3) The present invention may be equipped with a grating system, which can detect whether the parts are accurately placed in the receiving box as needed. Attached Figure Description

[0023] Figure 1A The image shown is a perspective view of a robot sorting system according to an embodiment of the present invention.

[0024] Figure 1B The image shown is a top view of a robot sorting system according to an embodiment of the present invention.

[0025] Figure 1C The image shown is a side view of a robot sorting system according to an embodiment of the present invention.

[0026] Figure 2A The diagram shown illustrates a scenario where the picking requirements are not met in one embodiment of the present invention.

[0027] Figure 2B The diagram shown illustrates a scenario where the picking requirements are not met in one embodiment of the present invention.

[0028] Figure 2C The diagram shown illustrates a scenario where the picking requirements are not met in one embodiment of the present invention.

[0029] Figure 2D The diagram shown is a schematic representation of a sorting requirement in one embodiment of the present invention.

[0030] Figure 3 The diagram shown is a flowchart of a robot sorting method according to an embodiment of the present invention.

[0031] Figure 4 The diagram shown is a structural schematic of an electronic terminal according to an embodiment of the present invention. Detailed Implementation

[0032] The following specific embodiments illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification.

[0033] It should be understood that the structures, proportions, sizes, etc., illustrated in the accompanying drawings are merely for illustrative purposes to aid those skilled in the art and are not intended to limit the implementation of the invention. Therefore, they have no substantial technical significance. Any modifications to the structure, changes in proportions, or adjustments to size, without affecting the effectiveness and purpose of the invention, should still fall within the scope of the disclosed technical content. The following detailed description should not be considered restrictive, and the scope of the embodiments of this application is limited only by the claims of the published patents. The terminology used herein is for describing specific embodiments only and is not intended to limit the application. Spatial terms such as "upper," "lower," "left," "right," "below," "below," "lower part," "above," "upper part," etc., may be used in the text to illustrate the relationship between one element or feature shown in the figures and another element or feature.

[0034] In this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," "fixing," and "holding" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; 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; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0035] Furthermore, as used herein, the singular forms “a,” “an,” and “the” are intended to include the plural forms as well, unless the context indicates otherwise. It should be further understood that the terms “comprising,” “including,” indicate the presence of the stated feature, operation, element, component, item, kind, and / or group, but do not preclude the presence, occurrence, or addition of one or more other features, operations, elements, components, items, kinds, and / or groups. The terms “or” and “and / or” as used herein are interpreted as inclusive, or mean any one or any combination thereof. Thus, “A, B, or C” or “A, B, and / or C” means “any one of: A; B; C; A and B; A and C; B and C; A, B, and C.” Exceptions to this definition arise only when combinations of elements, functions, or operations are inherently mutually exclusive in some manner.

[0036] Sorting of packaged products has its inherent difficulties and limitations: First, packaged products require a variety of parts in different quantities, making the picking process difficult and labor-intensive. Due to the differences between packaged products, operators need to frequently switch between different material boxes to complete the task, which can be very tiring. Therefore, the overall operation of the sorting process is difficult. Second, during the transition to full automation, the parts have irregular shapes and are numerous. Batches of parts coming from upstream are often stacked and intertwined, which places very demanding and complex requirements on the machinery. This not only requires operators to have a high level of operational skills, but also involves many subsequent inspection steps, making picking very difficult.

[0037] In view of this, the present invention proposes a robotic sorting system with a flexible feeding mechanism, which can realize the automatic outbound and online sorting of parts in the warehouse and the automatic picking of parts into storage containers, replacing manual sorting.

[0038] To make the objectives, technical solutions, and advantages of the present invention clearer, the technical solutions in the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only for explaining the present invention and are not intended to limit the invention.

[0039] Example 1:

[0040] like Figures 1A-1C The diagram shows a schematic representation of a robot sorting system with a flexible feeding mechanism according to an embodiment of the present invention. Figure 1A The image shown is a 3D view of a robotic sorting system; Figure 1B This is a top view of the robotic sorting system; Figure 1C The image shown is a side view of the robotic sorting system. This embodiment of the robotic sorting system includes a robot system 11, a flexible feeding mechanism 12, a receiving mechanism 13, a vision system 14, a conveying system 15, and a gripping and quick-change system (not shown). The various mechanisms and systems within the robotic sorting system will be explained in detail below.

[0041] In some examples, the flexible feeding mechanism 12 is used to rearrange the parts and materials piled up from upstream equipment, transforming them from a 3D orientation to a finite number of 2D or 2.5D orientations. In this embodiment, the flexible feeding mechanism 12 can be a vibration mechanism, a differential mechanism, a ramp circulating flow mechanism, a swaying mechanism, etc.; the vibration mechanism (such as a vibrating table for vibrating materials) drives the piled-up parts and materials to vibrate and change their orientation and layout through its own vibration; the differential mechanism (such as a differential gear) alleviates the pile-up of parts and materials by setting a speed difference between the two sides, thereby changing their orientation and layout; the ramp circulating flow mechanism (such as a circulating ramp conveyor) alleviates the pile-up of parts and materials during the circulating conveying process, thereby changing their orientation and layout; the swaying mechanism (such as a rocking machine or swaying machine, etc.) drives the piled-up parts and materials to sway and change their orientation and layout through its own swaying.

[0042] In some examples, the vision system 14 includes an image acquisition module, an image processing module, and a communication module. The image acquisition module is used to acquire images of parts and materials within the flexible feeding mechanism 12. The image processing module is used to extract visual information of the parts and materials from the images, and to determine whether each part and material meets the picking requirements and to determine the type of the end effector of the robot system based on the visual information. The communication module is used to transmit the visual information of the parts and materials and the type information of the end effector to the outside. The visual information of the parts and materials includes, but is not limited to, the position information, posture information, specification information, and size information of the parts and materials.

[0043] The image acquisition module involved in this embodiment can be a camera, video camera, camera module integrating an optical system or CCD chip, camera module integrating an optical system and CMOS chip, etc.; to increase the size of the visual scanning area, the image acquisition module can also be a wide-angle lens or fisheye lens, etc. The image processing module can be an ARM (Advanced RISC Machines) controller, FPGA (Field Programmable Gate Array) controller, SoC (System on Chip) controller, DSP (Digital Signal Processing) controller, or MCU (Microcontroller Unit) controller, etc. The communication module can be a Wi-Fi module, ZigBee module, Bluetooth module, NB-IoT module, LoRA module, eMTC module, etc., and this embodiment is not limited to any particular type.

[0044] Optionally, the conditions under which parts meet the picking requirements include, but are not limited to, parts not being stacked, parts being separated, and specific faces of parts facing a pre-specified direction. These can be set according to the actual application scenario, and this embodiment does not limit them. For the convenience of those skilled in the art, the following description, in conjunction with... Figures 2A-2DThis is to explain whether the parts and materials meet the picking requirements; Figure 2A The parts and materials in the container were stacked, so they did not meet the picking requirements; Figure 2B Although the parts were not stacked, they were not separated from each other, so they did not meet the picking requirements. Figure 2C Among the parts in the material, part A was not flipped over, that is, the specific face was not facing the pre-specified direction, so it does not meet the picking requirements; Figure 2D The parts in the sample are not stacked; they are separate and all facing the specified direction, thus meeting the picking requirements and allowing the robot system to proceed with the next picking operation. It should be noted that the above example is provided for illustrative purposes and should not be construed as restrictive.

[0045] Specifically, after acquiring images of the parts and materials, a target detection model can be used to detect targets in each part and material in the image and label target boxes. If there are overlapping areas between the labeled target boxes, it can be determined that there are stacked parts and materials in the image. If there are no overlapping areas or gaps between the labeled target boxes, it can be determined that the parts and materials in the image are not separated individually. If the shape and size of the labeled target boxes are inconsistent with the preset shape and size, it can be determined that there are parts and materials in the image whose specific faces are not facing the pre-specified direction. It should be understood that the above judgment method is only one embodiment of the present invention, and the present invention does not limit the specific judgment rules for parts and materials to meet the picking requirements.

[0046] Optionally, the type of end effector in the robot system includes, but is not limited to, suction cups or pneumatic fingers. The type of end effector can be determined based on the size information of the part or material; for example, small-sized parts or materials can use small-sized suction cups / pneumatic fingers, while large-sized parts or materials can use large-sized suction cups / pneumatic fingers, or a combination of multiple suction cups and multiple pneumatic fingers. Alternatively, the type of end effector can be determined based on the orientation information of the part or material; for example, parts or materials with regular and flat orientations can be picked up with suction cups, while parts or materials with irregular and flat orientations can be grasped with pneumatic fingers.

[0047] In some examples, the robot system 11 establishes a communication connection with the vision system 14 to receive attribute information of the parts and materials from the vision system 14. Following the currently determined end effector type of the robot system, the robot system quickly changes the end effector and picks out the parts and materials that meet the picking requirements. After picking, for the remaining parts and materials that are not yet ready for picking, the flexible feeding mechanism 12 will continue to rearrange these parts and materials for the end effector of the robot system 11 to perform a second picking; this process is repeated until all parts and materials have been picked.

[0048] Optionally, the robot system 11 can be a six-axis robot, a four-axis robot, an eight-axis robot, an XYZ three-axis robot, a parallel robot, or other multi-axis robots. Alternatively, it can be a Scara robot with three rotary joints that can be used for assembly operations, or a Delta robot that can achieve high-precision material picking, etc. It is worth noting that in practical application scenarios, any automated device capable of grasping and transporting can be applied to the technical solution of this invention.

[0049] In some examples, the receiving mechanism 13 is used to receive materials. The robot system 11 picks up parts from the flexible feeding mechanism 12 and places them into the receiving mechanism 13. The receiving mechanism 13 involved in this embodiment includes, but is not limited to, storage containers such as material frames, material boxes, and plastic bags.

[0050] Optionally, the receiving mechanism 13 is equipped with a grating detection device (not shown) to detect whether the part material is accurately placed in the receiving mechanism 13 as needed. If a part material is detected that is not accurately placed as needed, it can be removed from the receiving mechanism 13 by the robot system 11 or manually. The grating detection device involved in this embodiment can be a grating sensor, which can perform precise measurement of length and angle, as well as position detection of CNC systems. It has the characteristics of high measurement accuracy, strong anti-interference ability, applicability to dynamic measurement and automatic measurement, and digital display. The grating sensor can be a physical grating, a metering grating, a transmission grating, a reflection grating, etc., and this embodiment is not limited to any particular type.

[0051] Optionally, the robot separation system further includes a prompting device for issuing a prompt when the grating detection device detects that an inaccurately placed part or material has appeared in the receiving mechanism. Optionally, the prompting device may be one or more combinations of indicator lights, speakers, and displays, and the type of indication action may include any one or more combinations of indicator light on / off, sound beeping, and graphic display.

[0052] In some examples, the conveying system 15 is used to transport the receiving mechanism 13 to a downstream or upstream mechanism according to instructions. The conveying system 15 involved in this embodiment includes, but is not limited to, belt conveyors, roller conveyors, chain conveyors, and slide rail conveyors.

[0053] In some examples, the gripping and quick-change system is located on the robot system 11, including the end effector and the quick-change system. The end effector type includes, but is not limited to, suction cups or pneumatic fingers. The quick-change system can use a robotic tool changer to automatically change different end effectors using the robot, making the robot's application more flexible and adaptable. The end effector of the gripping and quick-change system works in conjunction with the quick-change system to quickly and accurately change the end effector and perform gripping and picking based on information such as the size and orientation of the parts and materials detected by the vision system 14.

[0054] In some examples, the robotic sorting system also includes a 3D camera to acquire the 3D pose and occlusion relationships of stacked parts for grasping. It should be noted that the 3D camera provided in this embodiment is designed to determine the 3D pose and occlusion relationships of objects under appropriate stacking conditions for direct grasping, without requiring a flexible feeding mechanism to rearrange the parts, thus improving efficiency. It should be understood that in this embodiment, a state where the 3D pose and occlusion relationships can be acquired by a 3D camera despite a low degree of stacking is defined as appropriate stacking. Since the principle of 3D camera acquisition of 3D pose and occlusion relationships is already known, it will not be elaborated upon further.

[0055] In some examples, the vision system determines the quantity and graspable posture of the parts and materials based on images of the parts and materials within the flexible feeding mechanism, thereby deciding whether to continue feeding and whether to rearrange the parts and materials. Specifically, the vision system can determine the number of materials; if the number is insufficient (e.g., below a preset threshold), it instructs the flexible feeding mechanism to provide more parts and materials; if the grasping posture cannot be determined, the flexible feeding mechanism changes its layout (e.g., through shaking, vibration, differential speed, swaying, etc.).

[0056] In some examples, the parts materials include the same type of material and / or mixed materials; the same type of material is sorted by quantity, and mixed materials are picked by category. Specifically, parts of the same type can be picked by quantity, and mixed materials such as injection molded parts and metal parts can be sorted and distinguished by category.

[0057] Therefore, the robotic sorting system with a flexible feeding mechanism provided in this embodiment can reorder the position and orientation of randomly piled-up parts and materials using the flexible feeding mechanism, thereby transforming 3D into a limited number of 2D / 2.5D orientations for easy picking; it can also use a vision system to accurately and quickly obtain information such as the position and orientation of parts, and based on the obtained information, the robot automatically changes to a suitable end gripper, without waiting, and completes the picking with high efficiency; it can also be equipped with a grating system to detect whether the parts are accurately placed in the receiving box as needed.

[0058] Example 2:

[0059] like Figure 3 The diagram illustrates a flowchart of a robot sorting method according to an embodiment of the present invention. This robot sorting method can be applied to the vision system within the aforementioned robot sorting system, and mainly includes the following steps.

[0060] Step S301: Acquire an image of the part material within the flexible feeding mechanism, and extract visual information of the part material from the image. The visual information of the part material includes, but is not limited to, position information, posture information, specification information, and size information.

[0061] Step S302: Determine whether each part meets the picking requirements based on the visual information of the parts and determine the type of end effector of the robot system.

[0062] In some examples, the conditions under which parts meet the picking requirements include, but are not limited to, parts not stacked, parts separated, and a specific face of a part facing a pre-specified direction. These conditions can be set according to the actual application scenario, and this embodiment does not limit them. Specifically, after obtaining an image of the parts, a target detection model can be used to detect targets in each part in the image and mark target boxes. If there is an overlapping area between the marked target boxes, it can be determined that there are stacked parts in the image. If there is no overlapping area but no gap between the marked target boxes, it can be determined that the parts in the image are not separated. If the shape and size of the marked target boxes are inconsistent with the preset shape and size, it can be determined that there are parts in the image whose specific face does not face the pre-specified direction. It should be understood that the above judgment method is only one embodiment of the present invention, and the present invention does not limit the specific judgment rules for parts meeting the picking requirements.

[0063] In some examples, the types of end effectors in a robot system include, but are not limited to, suction cups, pneumatic fingers, and grippers. The type of end effector can be determined based on the size information of the part or material; for example, small-sized parts or materials can use small-sized suction cups / pneumatic fingers, while large-sized parts or materials can use large-sized suction cups / pneumatic fingers, or a combination of multiple suction cups and multiple pneumatic fingers. Alternatively, the type of end effector can be determined based on the orientation information of the part or material; for example, parts or materials with regular and flat orientations can be picked up with suction cups, while parts or materials with irregular and flat orientations can be gripped with pneumatic fingers.

[0064] Step S303: Transmit the visual information of the parts and materials and the type information of the end effector to the outside, so that the robot system can change the corresponding end effector according to the type information of the end effector, and pick out the parts and materials that meet the picking requirements according to the visual information of the parts and materials.

[0065] It should be noted that the robot sorting method in this embodiment is similar to the implementation method of the robot sorting system with flexible feeding mechanism in Embodiment 1, so it will not be described again.

[0066] Example 3:

[0067] like Figure 4 The diagram illustrates the structure of an electronic terminal according to an embodiment of the present invention. The electronic terminal provided in this example includes: a processor 41, a memory 42, and a communicator 43; the memory 42 is connected to the processor 41 and the communicator 43 via a system bus and communicates with them; the memory 42 is used to store computer programs; the communicator 43 is used to communicate with other devices; and the processor 41 is used to run the computer programs, enabling the electronic terminal to execute the various steps of the robot sorting method described above.

[0068] The system bus mentioned above can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This system bus can be divided into address bus, data bus, control bus, etc. For ease of representation, only one thick line is used in the diagram, but this does not indicate that there is only one bus or one type of bus. The communication interface is used to enable communication between the database access device and other devices (e.g., clients, read-write libraries, and read-only libraries). Memory may include Random Access Memory (RAM) and may also include non-volatile memory, such as at least one disk storage device.

[0069] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0070] Example 4:

[0071] This embodiment provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the robot sorting method.

[0072] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented using computer program-related hardware. The aforementioned computer program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0073] In summary, this invention provides a robotic sorting system, method, terminal, and medium with a flexible feeding mechanism. The flexible feeding mechanism reorders the position and orientation of randomly piled parts, transforming them from 3D to a finite number of 2D / 2.5D orientations for easier picking. The invention utilizes a vision system to accurately and quickly obtain information such as part position and orientation. Based on this information, the robot automatically changes to a suitable end effector, eliminating waiting time and completing the picking process efficiently. This invention can be equipped with a grating system to detect whether parts are accurately placed in the receiving box as needed. Therefore, this invention effectively overcomes the various shortcomings of existing technologies and has high industrial application value.

[0074] The above embodiments are merely illustrative of the principles and effects of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in the present invention should still be covered by the claims of the present invention.

Claims

1. A robotic sorting system with a flexible feeding mechanism, characterized in that, include: Flexible feeding mechanism, used to rearrange stacked parts and materials; The vision system is used to acquire images of parts and materials within the flexible feeding mechanism, extract visual information of the parts and materials from the images, and determine whether each part and material meets the picking requirements and the type of the end effector of the robot system based on the visual information of the parts and materials. The robot system includes an end effector and a quick-change system; The robot system establishes a communication connection with the vision system to receive visual information of parts and materials and type information of the end effector from the vision system. After replacing the corresponding end effector with the quick-change system, the robot system picks out the parts and materials that meet the picking requirements. After picking, the flexible feeding mechanism continues to rearrange the parts and materials that have not reached the picking level, and then feeds them to the end effector of the robot system for a second picking. The above operation is repeated until all parts and materials have been picked. A receiving mechanism, located within the operating range of the robot system, is used to store the parts picked up by the robot system; A conveying system is used to carry the receiving mechanism and transport the receiving mechanism to a designated position; The conditions under which the parts meet the picking requirements include that the parts are not stacked, the parts are separated, and the specific face of the parts is facing a pre-specified direction. After obtaining the image of the parts, each part in the image is detected and a target box is marked. If there is an overlapping area between the marked target boxes, it is determined that there are stacked parts in the image; if there is no overlapping area but no gap between the marked target boxes, it is determined that the parts in the image are not separated individually. If the shape and size of the marked target box are inconsistent with the preset shape and size, it is determined that a part material with a specific face not facing the pre-specified direction has appeared in the image.

2. The robot sorting system according to claim 1, characterized in that, The flexible feeding mechanism includes any one or more combinations of a vibration mechanism, a differential speed mechanism, a ramp circulating flow mechanism, and a swaying mechanism.

3. The robot sorting system according to claim 1, characterized in that, The visual information of the part material includes any one or more combinations of the part material's position information, posture information, specification information, and size information.

4. The robot sorting system according to claim 1, characterized in that, The receiving mechanism is equipped with a grating detection device to detect whether the parts and materials in the receiving mechanism are placed accurately as needed.

5. The robot sorting system according to claim 4, characterized in that, Also includes: A prompting device is provided when the grating detection device detects that a part or material has not been placed accurately as required in the receiving mechanism.

6. The robot sorting system according to claim 1, characterized in that, The vision system includes: The image acquisition module is used to acquire images of the parts and materials within the flexible feeding mechanism; The image processing module extracts visual information of the parts and materials from the image, and determines whether each part and material meets the picking requirements and the type of the end effector of the robot system based on the visual information of the parts and materials. The communication module is used to transmit the visual information of the part material and the type information of the end effector to the outside.

7. The robot sorting system according to claim 1, characterized in that, Also includes: A 3D camera is used to acquire the 3D pose and occlusion relationships of stacked parts and materials for grasping.

8. The robot sorting system according to claim 1, characterized in that, Also includes: The vision system determines the quantity and graspable posture of the parts and materials based on the images of the parts and materials collected in the flexible feeding mechanism, and then decides whether to continue feeding and whether to rearrange the parts and materials.

9. The robot sorting system according to claim 1, characterized in that, The parts materials include the same type of materials and / or mixed materials; the same type of materials are sorted according to the number of materials, and the mixed materials are selected according to the material category.

10. A robot sorting method, characterized in that, include: Acquire images of parts and materials within the flexible feeding mechanism, and extract visual information about the parts and materials from the images; Based on visual information of the parts and materials, determine whether each part and material meets the picking requirements and determine the type of end effector of the robot system; The visual information of the parts and materials and the type information of the end effector are transmitted outward so that the robot system can change the corresponding end effector according to the type information of the end effector and pick out the parts and materials that meet the picking requirements according to the visual information of the parts and materials. After picking, the flexible feeding mechanism continues to rearrange the parts and materials that have not reached the picking level, and then feeds them to the end effector of the robot system for a second picking. The above operation is repeated until all the parts and materials have been picked. The conditions under which the parts meet the picking requirements include that the parts are not stacked, the parts are separated, and the specific face of the parts is facing a pre-specified direction. After acquiring the image of the parts, each part in the image is detected and a target box is marked. If there is an overlapping area between the marked target boxes, it is determined that there are stacked parts in the image; if there is no overlapping area but no gap between the marked target boxes, it is determined that the parts in the image are not separated individually. If the shape and size of the marked target box are inconsistent with the preset shape and size, it is determined that a part material with a specific face not facing the pre-specified direction has appeared in the image.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the robot sorting method of claim 10.

12. An electronic terminal, characterized in that, include: Processor and memory; The memory is used to store computer programs; The processor is used to execute the computer program stored in the memory to cause the terminal to perform the robot sorting method as described in claim 10.

Images