Industrial robot visual control method, device, storage medium and system

Abstract

The invention is suitable for the technical field of industrial automation control, and provides an industrial robot visual control method and device, a storage medium and a system.The method comprises the steps that multiple pieces of image information of a to-be-carried object is obtained, and the optimal grabbing point of the surface of the to-be-carried object is obtained; an estimated motion path of the optimal grabbing point is obtained; an estimated grabbing position coordinate is obtained; acquiring a pressurization value of the pressure applied by the elastic mechanical arm; and the mechanical arm is controlled to transfer the to-be-carried object, and the pressurization value continues to be increased. Compared with the prior art, the method has the advantages that the multi-mode fusion control method formed by matching the visual sensor and the pressure sensor is combined with the tactile feedback containing force control, the visual response delay is compensated, and the response speed of the system is increased, so that the method is suitable for a high-speed production line, particularly suitable for high-speed handling and carrying tasks of a high-speed conveying belt, and the generation efficiency is higher.

Description

Technical Field

[0001] The present invention belongs to the field of industrial automation control technology, and in particular relates to an industrial robot vision control method, device, storage medium and system. Background Art

[0002] Industrial robots are programmable, multi-jointed automated mechanical devices that integrate mechanical engineering, electronics, computer control, and artificial intelligence technologies. They are used to replace humans in performing repetitive or high-precision tasks. Industrial robots using vision control enhance their environmental perception capabilities through cameras, image processing algorithms, and feedback mechanisms.

[0003] Existing industrial robot control methods are quite diverse. For example, geometric parameters are calibrated through the hand-eye matrix to obtain the relative position between the camera coordinate system and the robot coordinate system. Fixed-size images of the robot end area and the corresponding time are collected during the working state, and then the position changes of the robot end in the body coordinate system at different times are known. Finally, the coordinate relationship between the robot and the object is used to grasp the object.

[0004] However, the image processing technologies used in existing single visual control methods all have delays. For example, feature extraction and 3D reconstruction cause control system lags. The time period after visual recognition and grasping is long, which is difficult to meet the needs of high-speed production lines. The grasping efficiency of high-speed and dynamic targets is low. Summary of the Invention

[0005] The purpose of the embodiments of the present application is to provide a method for visual control of industrial robots, aiming to solve the problem that the image processing technologies used in existing single visual control methods all have delays, such as feature extraction and 3D reconstruction, which cause control system lags, and the time period after visual recognition and grasping is long, which is difficult to match the requirements of high-speed production lines and has low efficiency in grasping high-speed and dynamic targets.

[0006] The embodiment of the present application is implemented by providing a method for visual control of an industrial robot, the method comprising:

[0007] Acquire several images of the object to be transported, and obtain its morphological feature information and motion state information;

[0008] Based on the morphological feature information, an optimal grasping point on the surface of the object to be transported is obtained;

[0009] Based on the motion state information, an estimated motion path of the optimal grasping point is obtained;

[0010] Obtaining a motion range equation of the robotic arm, obtaining a coordinate intersection point between the motion range equation and the estimated path, and obtaining an estimated grasping position coordinate;

[0011] Obtain a preset lead time, control the flexible robotic arm to reach the estimated grasping position coordinates before the lead time and start applying pressure to the object to be transported, and obtain the pressurization value of the pressure applied by the flexible robotic arm;

[0012] Control the pressurization value so that when the optimal grasping point of the object to be transported reaches the estimated grasping position coordinates, the pressurization value just reaches the critical pressure, and the critical pressure is the minimum pressure at which the flexible robotic arm can stably pick up the object to be transported;

[0013] Control the robotic arm to transport the object to be transported and continue to increase the pressurization value until the pressurization value reaches the second threshold.

[0014] Another object of the embodiments of the present application is to provide an industrial robot vision control device, and the device includes:

[0015] A basic information acquisition module, configured to acquire a plurality of image information of the object to be transported to obtain its morphological feature information and motion state information;

[0016] An optimal grasping point acquisition module, configured to obtain the optimal grasping point on the surface of the object to be transported based on the morphological feature information;

[0017] An estimated motion path acquisition module, configured to obtain the estimated motion path of the optimal grasping point based on the motion state information;

[0018] An estimated grasping position coordinate acquisition module, configured to obtain the motion range equation of the robotic arm, obtain the coordinate intersection point of the motion range equation and the estimated path, and obtain the estimated grasping position coordinates;

[0019] A pressure value acquisition module, configured to obtain a preset lead time, control the flexible robotic arm to reach the estimated grasping position coordinates before the lead time and start applying pressure to the object to be transported, and obtain the pressurization value of the pressure applied by the flexible robotic arm;

[0020] A pressurization control module, configured to control the pressurization value so that when the optimal grasping point of the object to be transported reaches the estimated grasping position coordinates, the pressurization value just reaches the critical pressure, and the critical pressure is the minimum pressure at which the flexible robotic arm can stably pick up the object to be transported;

[0021] A transfer control module, configured to control the robotic arm to transport the object to be transported and continue to increase the pressurization value until the pressurization value reaches the second threshold.

[0022] Another object of the embodiments of the present application is to provide a computer-readable storage medium storing a computer program which, when executed by a processor, causes the processor to execute the steps of the industrial robot vision control method as described above.

[0023] Another object of the embodiments of the present application is to provide an industrial robot vision control system, which comprises a memory, an image acquisition device, a pressure sensing device and a processor.

[0024] The memory stores a computer program which, when executed by the processor, causes the processor to execute the steps of the industrial robot vision control method as described above.

[0025] The image acquisition device is used to acquire the image information of the object to be carried.

[0026] The pressure sensing device is used to collect the pressurization value of the elastic robotic arm applying pressure to the object to be carried.

[0027] The prominent advantage of the industrial robot vision control method provided by the embodiments of the present application is that, compared with the traditional pure vision control handling scheme, the present application uses a multi-modal fusion control method formed by the cooperation of a vision sensor and a pressure sensor, combined with tactile feedback containing force control, to compensate for the visual reaction delay and improve the response speed of the system. Thus, it is applicable to high-speed production lines, especially suitable for high-speed handling tasks on high-speed conveyor belts, and the production efficiency is higher. Description of the Drawings

[0028] Figure 1 It is an application environment diagram of an industrial robot vision control method provided by the embodiments of the present application.

[0029] Figure 2 It is a flowchart of an industrial robot vision control method provided by the embodiments of the present application.

[0030] Figure 3 It is a structural block diagram of an industrial robot vision control device provided by the embodiments of the present application.

[0031] Figure 4 It is an internal structural block diagram of a computer device in one embodiment. Detailed Embodiments

[0032] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0033] It can be understood that the terms "first", "second", etc. used in this application may be used herein to describe various elements, but unless otherwise specified, these elements are not limited by these terms. These terms are only used to distinguish a first unit or module from another unit or module. For example, without departing from the scope of this application, the first script may be referred to as the second script, and similarly, the second script may be referred to as the first script.

[0034] Figure 1 The following is an application environment diagram of the industrial robot vision control method provided by the embodiments of this application. As Figure 1 shown, in this application environment, it includes an image acquisition device 110 and a computer device 120.

[0035] The computer device 120 can be an independent physical server or terminal, or a server cluster composed of multiple physical servers. It can be a cloud server that provides basic cloud computing services such as cloud servers, cloud databases, cloud storage, and CDN. It can be a tablet computer, a laptop computer, a desktop computer, etc., but is not limited thereto.

[0036] The video acquisition device 110 and the computer device 120 can be connected through a network, and this application does not limit this.

[0037] As Figure 2 shown, in one embodiment, an industrial robot vision control method is proposed. In this embodiment, this method is mainly exemplified by being applied to the computer device 120 in the above Figure 1 . An industrial robot vision control method may specifically include the following steps:

[0038] Step S10, obtain a plurality of image information of the object to be carried, and obtain its morphological feature information and motion state information.

[0039] In this embodiment, the system first obtains images of the object on the transportation conveyor belt. These images can refer to consecutive video frames and the timestamps corresponding to the video frames. Through these images, information such as the shape, size, and posture of the object that can identify the object to be carried can be analyzed. For example, the length, width, and height of a cuboid box and the motion state information. The motion state information can include information such as the specific position of the item on the bar conveyor belt, the posture of movement, the speed of movement, etc., and obtain the equation of the motion state of the object over time.

[0040] Step S20, based on the morphological feature information, obtain the best grasping point on the surface of the object to be carried.

[0041] In this embodiment, the shape of the object to be transported is analyzed. For example, if the object to be transported is a rectangular parallelepiped, the optimal grasping points may be two points symmetrically located near the center of gravity of two symmetrical faces of the rectangular parallelepiped. It is understood that four or more symmetrical points may also be used to ensure that the object can be grasped stably and does not tip over. These points are set as the optimal grasping points.

[0042] Step S30: obtaining an estimated motion path of the optimal grasping point based on the motion state information.

[0043] In this embodiment, the specific motion trajectory equation of the item on the conveyor belt compared to a certain positioning point, that is, the motion state information is obtained and then combined with the relative position coordinates of the optimal grasping point on the object, the equation of the motion path of the optimal grasping point itself over time can be obtained, that is, the estimated motion path.

[0044] Step S40 , obtaining a motion range equation of the robotic arm, obtaining a coordinate intersection point between the motion range equation and the estimated path, and obtaining the estimated grasping position coordinates.

[0045] In this embodiment, the robotic arm is equipped with several swingable gripping arms. These arms can rotate in a fan-shaped pattern around a central axis, with a gripping contact at the distal end. Therefore, the gripping contact has a trajectory equation for its range of motion. To ensure that the gripping contact grasps an object at the optimal gripping point, removing it from the conveyor belt, the intersection of the range of motion equation and the estimated path equation must be solved, resulting in the estimated gripping position coordinates. At this point, the robotic arm can stably grasp the object and perform other tasks such as transport, delivery, and assembly.

[0046] Step S50 , obtaining a preset lead time, controlling the elastic manipulator to reach the estimated grasping position coordinates before the lead time and start applying pressure to the object to be transported, and obtaining a pressure value of the pressure applied by the elastic manipulator.

[0047] In this embodiment, it is understood that the gripping end of the robotic arm is typically equipped with an elastic clip, etc., to prevent damage to the object caused by rigid gripping. Because the gripping force of the elastic clamp can vary, and the object's box generally has a certain length, a threshold time is set for the lead time. For example, the threshold time t is 0.5 seconds. During this time, the clamp pre-contacts the object and begins pressurization to prevent damage to the object's surface caused by sudden pressure increase. The pressure starts at 0 and gradually increases.

[0048] Step S60, controlling the pressurization value so that when the optimal gripping point of the object to be transported reaches the estimated gripping position coordinates, the pressurization value just reaches the critical pressure, which is the minimum pressure at which the elastic robotic arm can stably grip the object to be transported.

[0049] In this embodiment, the fixture applies force to the surface of the box gradually. Since the box is in a moving state on the conveyor belt, the pressure for clamping is controlled to increase gradually until it just reaches the critical pressure, that is, the moment when the robotic arm can lift the object to be transported off the surface of the moving conveyor belt. At this time, the clamping point of the fixture for the object to be transported just happens to be at the optimal grasping point.

[0050] With such a setting, the advantages of vision and pressure touch are comprehensively utilized, which can effectively reduce the long time waste caused by the separation of the identification, transportation, and clamping steps in the traditional handling method, and thus effectively improve the overall operation quality.

[0051] Step S70: Control the robotic arm to transport the object to be transported and continue to increase the pressurization value until the pressurization value reaches the second threshold.

[0052] In the embodiment of the present application, the critical pressure can just stably lift the object. However, in order to maintain the stability of subsequent transportation and assembly processes, it is necessary to continue to increase the clamping pressure until it reaches the second threshold to improve safety and stability.

[0053] In the embodiment of the present application, compared with the traditional pure vision control handling scheme, the present application uses a multi-modal fusion control method formed by the cooperation of a vision sensor and a pressure sensor, combined with tactile feedback containing force control, to compensate for the visual reaction delay and improve the response speed of the system. Thus, it is applicable to high-speed production lines, especially suitable for high-speed handling tasks on high-speed conveyor belts, and has higher production efficiency.

[0054] In a preferred embodiment, the method for obtaining several image information of the object to be transported and obtaining its morphological feature information is as follows:

[0055] Based on a binocular camera, model the object to be transported to obtain its estimated parallax model;

[0056] Compare and match the estimated parallax model with the standard part models in the model library, and set the standard part models with a similarity exceeding the threshold as the matching models;

[0057] Set the morphological feature information of the matching model as the morphological feature information of the object to be transported.

[0058] In the embodiment of the present application, by comparing with the standard part models in the model library, the standard part models similar to the object to be transported are determined. The model library contains several cuboid models, cylinder models, etc. of the same or different types, which are used to provide templates for automatic matching of the system. It can be understood that each standard part model is preset with several optimal grasping points. The models can be matched by calculating the cosine similarity. If the matching degree exceeds the threshold, it can be considered that the standard part model is similar to the object to be transported, and its preset optimal grasping points are selected.

[0059] In a preferred embodiment, the method for obtaining the optimal gripping point on the surface of the object to be transported based on the morphological feature information is:

[0060] Each standard part model in the model library is preset with several optimal gripping positions;

[0061] Acquiring a mapping correspondence between the matching model and the estimated disparity model;

[0062] An optimal grasping position preset by the matching model is obtained, and based on the mapping correspondence, a position mapping of the optimal grasping position on the estimated disparity model is obtained, and the position is set as the optimal grasping point.

[0063] In the embodiments of the present application, the mapping correspondence may refer to proportional scaling, elongation, and expansion. The goal is to find the optimal gripping point of an object by matching the standard parts model. By matching with the standard parts model library, the optimal gripping point can be accurately identified and selected, and the versatility is improved to adapt to different types of objects and gripping requirements. It is understandable that the optimal gripping position preset by the matching model can also refer to an algorithm for calculating the position, which is obtained by the system automatically calculating the surface curvature of the object, and does not necessarily refer to specific coordinates.

[0064] In a preferred embodiment, the estimated motion path of the optimal grasping point is obtained based on the motion state information:

[0065] Obtain the coordinates of the center of mass of the object to be transported, and obtain the estimated center of mass path based on the motion state information;

[0066] Obtain the relative position relationship of each optimal grasping point compared to the center of mass;

[0067] Based on the relative position relationship and the estimated centroid path, an estimated motion path of each optimal grasping point is obtained.

[0068] In an embodiment of the present application, a rigid body motion model is established. The standard part model in the model library is preset with the position coordinates of the center of mass. In this case, the movement of the center of mass point can represent the overall motion state of the object. Based on the motion state of the object, the motion trajectory of the center of mass over a period of time in the future is predicted. The relative position of the grasping point on the object is obtained so that the position of the grasping point relative to the center of mass can be accurately calculated. Therefore, the trajectory of the grasping point is calculated by the motion of the center of mass of the object, which requires less calculation than directly tracking the motion of each grasping point.

[0069] In a preferred embodiment, a method for obtaining the range of motion equation of the manipulator, obtaining the intersection of the range of motion equation and the coordinates of the estimated path, and obtaining the estimated grasping position coordinates is as follows:

[0070] Get the range of motion of the robot arm , obtain the trajectory curve of the estimated path P over time t ;

[0071] Solve the following equation to get the estimated grasping position coordinates :

[0072]

[0073] In the embodiment of the present application, the range of motion equation of the robotic arm is obtained based on the kinematic model of the robotic arm. This equation can be used to calculate the working area that the robotic arm can reach, and then perform an intersection operation with the estimated path to obtain the optimal grasping position coordinates.

[0074] In a preferred embodiment, the pressurization value is controlled in the following manner so that when the optimal grasping point of the object to be transported reaches the estimated grasping position coordinates, the pressurization value just reaches the critical pressure:

[0075]

[0076] in, is the critical pressure, is the pressure at time t; is a positive parameter that controls the pressure change rate, and t is a time variable that represents the time of the extrusion process.

[0077] In the embodiments of this application, this process ensures that the pressure gradually increases during the control process, but the rate of increase gradually slows down as the pressure increases until the elastic robotic arm reaches the minimum critical pressure for stable grasping. The advantage of this approach is that the pressure control does not fluctuate suddenly, avoiding excessive or insufficient pressure, ensuring the safety of the object during handling and the stability of the robotic arm.

[0078] like Figure 3 As shown, in one embodiment, an industrial robot vision control device is provided. The industrial robot vision control device can be integrated into the above-mentioned computer device 120, and specifically may include:

[0079] The basic information acquisition module 510 is used to acquire a number of image information of the object to be transported, and obtain its morphological feature information and motion state information;

[0080] An optimal grasping point acquisition module 520 is used to obtain an optimal grasping point on the surface of the object to be transported based on the morphological feature information;

[0081] An estimated motion path acquisition module 530 is configured to obtain an estimated motion path of an optimal grasping point based on the motion state information;

[0082] The estimated grasping position coordinate acquisition module 540 is configured to obtain the motion range equation of the robotic arm, obtain the coordinate intersection point of the motion range equation and the estimated path, and obtain the estimated grasping position coordinate;

[0083] The pressure value acquisition module 550 is configured to obtain a preset lead time, control the elastic robotic arm to reach the estimated grasping position coordinate before the lead time and start applying pressure to the object to be transported, and obtain the pressurization value of the pressure applied by the elastic robotic arm;

[0084] The pressurization control module 560 is configured to control the pressurization value so that when the optimal grasping point of the object to be transported reaches the estimated grasping position coordinate, the pressurization value exactly reaches the critical pressure, and the critical pressure is the minimum pressure at which the elastic robotic arm can stably pick up the object to be transported;

[0085] The transfer control module 570 is configured to control the robotic arm to perform transfer on the object to be transported and continue to increase the pressurization value until the pressurization value reaches the second threshold.

[0086] In the embodiment of the present application, the explanation and description of the above industrial robot vision control device can refer to the explanation of the corresponding method above. For the description of the industrial robot vision control method, please refer to the above, and details will not be repeated here.

[0087] In the embodiment of the present application, the present application uses a multi-modal fusion control method formed by the cooperation of a vision sensor and a pressure sensor, combined with tactile feedback containing force control, to compensate for visual reaction delay and improve the response speed of the system, so as to be applicable to high-speed production lines, especially applicable to high-speed handling tasks on high-speed conveyor belts, and the production efficiency is higher.

[0088] In one embodiment, the basic information acquisition module 510 specifically includes:

[0089] The estimated parallax model acquisition module is configured to model the object to be transported based on a binocular camera and obtain its estimated parallax model;

[0090] The matching model acquisition module is configured to compare and match the estimated parallax model with the standard part model in the model library, and set the standard part model with a similarity exceeding the threshold as the matching model;

[0091] The morphological feature information acquisition module is configured to set the morphological feature information of the matching model as the morphological feature information of the object to be transported.

[0092] In the embodiment of the present application, the explanation of the above modules refers to the explanation of the corresponding method, and details will not be repeated here.

[0093] Figure 4The internal structure diagram of a computer device in an embodiment is shown. The computer device may specifically be Figure 1 the computer device 120 in Figure 4 . As shown, the computer device includes a processor, a memory, a network interface, an input device, and a display screen connected via a system bus. Among them, the memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system and may also store a computer program. When the computer program is executed by the processor, the processor can implement the industrial robot vision control method. The internal memory may also store a computer program. When the computer program is executed by the processor, the processor can execute the industrial robot vision control method. The display screen of the computer device may be a liquid crystal display screen, etc. The input device of the computer device may be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the computer device housing, or an external keyboard, touchpad, or mouse, etc.

[0094] Those skilled in the art can understand that Figure 4 the structure shown in

[0095] is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements. Figure 4 In an embodiment, the industrial robot vision control device provided by this application can be implemented in the form of a computer program, and the computer program can run on a device such as Figure 3 . The memory of the device may store each program module that makes up the industrial robot vision control device. For example,

[0096] the basic information acquisition module 510, the best grasping point acquisition module 520, etc. shown in Figure 4 . The computer program composed of each program module enables the processor to execute the steps in the industrial robot vision control method of each embodiment of this application described in this specification. Figure 3 For example, the computer device shown in <(

[0097] can execute step S10 through the basic information acquisition module 510 in the industrial robot vision control device shown in

[0098] In the embodiments of the present application, for the description of the above industrial robot vision control method, please refer to the above text and will not be elaborated here.

[0099] In the embodiments of the present application, for the program running based on the method stored in the storage medium of the embodiments of the present application, the advantage is that the present application uses a multi-modal fusion control method formed by the cooperation of a vision sensor and a pressure sensor, combined with tactile feedback containing force control, to compensate for visual reaction delay and improve the response speed of the system, so as to be applicable to high-speed production lines, especially applicable to high-speed processing and handling tasks on high-speed conveyor belts, and the production efficiency is higher.

[0100] In one embodiment, an industrial robot vision control system is provided, including a memory, an image acquisition device, a pressure sensing device, and a processor;

[0101] A computer program is stored in the memory, and when the computer program is executed by the processor, the processor executes the steps of the industrial robot vision control method as described above;

[0102] The image acquisition device is used to acquire image information of the object to be handled;

[0103] The pressure sensing device is used to collect the pressurization value of the pressure exerted by the elastic robotic arm on the object to be handled.

[0104] In the embodiments of the present application, the system can be a computer hardware system. When the above system is running, it executes its corresponding method. For the description of the above industrial robot vision control method, please refer to the above text and will not be elaborated here.

[0105] In the embodiments of the present application, the advantage of the present system is that the present application uses a multi-modal fusion control method formed by the cooperation of a vision sensor and a pressure sensor, combined with tactile feedback containing force control, to compensate for visual reaction delay and improve the response speed of the system, so as to be applicable to high-speed production lines, especially applicable to high-speed processing and handling tasks on high-speed conveyor belts, and the production efficiency is higher.

[0106] It should be understood that although the steps in the flowcharts of the embodiments of the present application are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in each embodiment may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least a part of other steps or sub-steps or stages of other steps.

[0107] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided in the present application can include non-volatile and / or volatile memories. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or an external cache. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0108] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0109] The above embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.

Claims

1. An industrial robot vision control method, characterized in that, The method includes: Obtaining a plurality of image information of the object to be carried, and obtaining its morphological feature information and motion state information; Based on the morphological feature information, obtaining the optimal grasping point on the surface of the object to be carried; Based on the motion state information, obtaining the estimated motion path of the optimal grasping point; Obtaining the motion range equation of the robotic arm, obtaining the coordinate intersection point of the motion range equation and the estimated path, and obtaining the estimated grasping position coordinates; Obtaining a preset lead time, controlling the flexible robotic arm to reach the estimated grasping position coordinates before the lead time and start applying pressure to the object to be carried, and obtaining the pressurization value of the pressure applied by the flexible robotic arm; Controlling the pressurization value so that when the optimal grasping point of the object to be carried reaches the estimated grasping position coordinates, the pressurization value just reaches the critical pressure, and the critical pressure is the minimum pressure at which the flexible robotic arm can stably pick up the object to be carried; Controlling the robotic arm to carry out the transfer of the object to be carried and continuously increasing the pressurization value until the pressurization value reaches the second threshold.

2. The vision control method of an industrial robot according to claim 1, wherein, The method for obtaining a plurality of image information of the object to be carried and obtaining its morphological feature information is: Based on a binocular camera, modeling the object to be carried and obtaining its estimated parallax model; Comparing and matching the estimated parallax model with the standard part models in the model library, and setting the standard part model with a similarity exceeding the threshold as the matching model; Setting the morphological feature information of the matching model as the morphological feature information of the object to be carried.

3. The industrial robot vision control method according to claim 2, characterized in that, The method for obtaining the optimal grasping point on the surface of the object to be carried based on the morphological feature information is: Each standard part model in the model library is preset with a plurality of optimal grasping positions; Obtaining the mapping correspondence between the matching model and the estimated parallax model; Obtaining the preset optimal grasping position of the matching model, and based on the mapping correspondence, obtaining the position mapping of the optimal grasping position on the estimated parallax model, and setting this position as the optimal grasping point.

4. A visual control method for an industrial robot according to claim 1, characterized in that, The estimated motion path of the optimal grasping point based on the motion state information: Obtaining the centroid point coordinates of the object to be carried, and based on the motion state information, obtaining the estimated centroid path of the centroid; Obtaining the relative position relationship of each optimal grasping point with respect to the centroid; Based on the relative position relationship and the estimated centroid path, obtaining the estimated motion path of each optimal grasping point.

5. A visual control method for an industrial robot according to claim 1, characterized in that The method for obtaining the motion range equation of the robotic arm, obtaining the coordinate intersection point of the motion range equation and the estimated path, and obtaining the estimated grasping position coordinates is: Obtain that the motion range of the robotic arm is , and obtain the trajectory curve of the estimated path P with respect to time t ; Solve the following equation to obtain the estimated grasping position coordinates : 。 6. The industrial robot vision control method according to claim 1, wherein Controlling the pressurization value in the following manner so that when the optimal grasping point of the object to be carried reaches the estimated grasping position coordinates, the pressurization value just reaches the critical pressure: Among them, is the critical pressure, is the pressure at time t; is a positive parameter for controlling the pressure change rate, and t is the time variable representing the time of the extrusion process.

7. An industrial robot vision control device, characterized in that, The device includes: A basic information acquisition module for obtaining a plurality of image information of the object to be carried and obtaining its morphological feature information and motion state information; An optimal grasping point acquisition module for obtaining the optimal grasping point on the surface of the object to be carried based on the morphological feature information; An estimated motion path acquisition module for obtaining the estimated motion path of the optimal grasping point based on the motion state information; The estimated grasping position coordinate acquisition module is used to obtain the motion range equation of the robotic arm, obtain the coordinate intersection point of the motion range equation and the estimated path, and obtain the estimated grasping position coordinates; The pressure value acquisition module is used to obtain the preset lead time, control the elastic robotic arm to reach the estimated grasping position coordinates before the lead time and start applying pressure to the object to be transported, and obtain the pressurization value of the pressure applied by the elastic robotic arm; The pressurization control module is used to control the pressurization value so that when the optimal grasping point of the object to be transported reaches the estimated grasping position coordinates, the pressurization value just reaches the critical pressure, and the critical pressure is the minimum pressure at which the elastic robotic arm can stably pick up the object to be transported; The transfer control module is used to control the robotic arm to transport the object to be transported and continue to increase the pressurization value until the pressurization value reaches the second threshold.

8. An industrial robot vision control device according to claim 7, wherein, The basic information acquisition module includes: The estimated parallax model acquisition module is used to model the object to be transported based on a binocular camera and obtain its estimated parallax model; The matching model acquisition module is used to compare and match the estimated parallax model with the standard part models in the model library, and set the standard part models with a similarity exceeding the threshold as the matching models; The morphological feature information acquisition module is used to set the morphological feature information of the matching model as the morphological feature information of the object to be transported.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor executes the steps of the industrial robot vision control method according to any one of claims 1 to 6.

10. An industrial robot vision control system, characterized in that, It includes a memory, an image acquisition device, a pressure sensing device, and a processor; The memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the industrial robot vision control method according to any one of claims 1 to 6; The image acquisition device is used to acquire the image information of the object to be transported; The pressure sensing device is used to collect the pressurization value of the pressure applied by the elastic robotic arm to the object to be transported.

Images