A rapid grasping method for intelligent sensing robotic arms based on pre-defined object visual judgment.

Abstract

This invention discloses a rapid grasping method for an intelligent sensing robotic arm based on visual judgment of a preset object. The method includes: capturing image information of a preset object; performing target recognition on the preset object based on the image information to determine the object parameter information; and controlling the intelligent sensing robotic arm to grasp the preset object according to the object parameter information and a preset weight gradient value set. By performing target recognition on the preset object through visual perception and making precise adjustments based on the preset weight gradient set, the intelligent sensing robotic arm is controlled to grasp the preset object. This achieves adaptive adjustment of the grasping parameters, ensuring the accuracy of the grasping parameters, and enabling rapid grasping of target objects even without setting grasping parameters, thus improving the intelligence and efficiency of the grasping process.

Description

Technical Field

[0001] This invention relates to the field of automatic control technology, and in particular to a rapid grasping method for an intelligent sensing robotic arm based on preset visual judgment of objects. Background Technology

[0002] Robotic grippers that rely on visual judgment of pre-defined objects are a common gripping method in practical applications. This method reduces labor costs and avoids potential dangers caused by direct contact between people and objects.

[0003] Currently, vision-based robotic gripping methods on the market fall into two categories: one is direct gripping based on traditional computer vision; the other is direct gripping based on deep learning.

[0004] However, both of these methods are often based on a pre-set grasping force. After identifying the position and category of the object, they directly grasp it according to the set grasping force. When the object has not been grasped with a set grasping force, there is a lack of data feedback on the grasping force during the grasping process, making it impossible to quickly judge the grasping force. This will undoubtedly increase the adaptive judgment time of the robotic arm and fail to achieve the goal of fast grasping. Summary of the Invention

[0005] This invention provides a rapid grasping method for an intelligent sensing robotic arm based on visual judgment of preset objects, so as to achieve adaptive grasping of different preset objects.

[0006] According to a first aspect of the present invention, a method for rapid grasping by an intelligent sensing robotic arm based on preset visual judgment of an object is provided, the method comprising:

[0007] Capture image information of preset items;

[0008] Based on the image information, target recognition is performed on the preset item to determine the object parameter information of the preset item;

[0009] Based on the object's parameter information and a preset weight gradient value set, the intelligent sensing robotic arm is controlled to grasp the preset item.

[0010] According to a second aspect of the present invention, a rapid grasping device for an intelligent sensing robotic arm based on preset object visual judgment is provided, comprising:

[0011] The information capture module is used to capture image information of preset items;

[0012] The information determination module is used to perform target recognition on a preset item based on the image information and determine the object parameter information of the preset item;

[0013] The grasping module is used to control the intelligent sensing robot to grasp the preset item based on the object parameter information and the preset weight gradient value group.

[0014] According to a third aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0015] At least one processor; and

[0016] A memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to execute the rapid grasping method of the intelligent sensing robotic arm based on preset object visual judgment as described in any embodiment of the present invention.

[0018] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions, the computer instructions being configured to cause a processor to execute and implement the rapid grasping method of the intelligent sensing robotic arm based on preset object visual judgment as described in any embodiment of the present invention.

[0019] The technical solution of this invention involves capturing image information of a preset object; performing target recognition on the preset object based on the image information to determine the object parameter information; and controlling an intelligent sensing robotic arm to grasp the preset object according to the object parameter information and a preset weight gradient value set. By performing target recognition on the preset object through visual perception and making precise adjustments based on the preset weight gradient set, the intelligent sensing robotic arm is controlled to grasp the preset object. This achieves adaptive adjustment of the grasping parameters, ensuring the accuracy of the grasping parameters, and enabling rapid grasping of the target object even without setting grasping parameters, thus improving the intelligence and efficiency of the grasping process.

[0020] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1This is a flowchart of a rapid grasping method for an intelligent sensing robotic arm based on preset object visual judgment, according to Embodiment 1 of the present invention.

[0023] Figure 2 This is a flowchart of a rapid grasping method for an intelligent sensing robotic arm based on preset object visual judgment, according to Embodiment 2 of the present invention.

[0024] Figure 3 This is an example flowchart of a rapid grasping method for an intelligent sensing robotic arm based on preset object visual judgment, according to Embodiment 2 of the present invention.

[0025] Figure 4 This is a structural schematic diagram of a rapid grasping device for an intelligent sensing robotic arm based on preset object visual judgment, according to Embodiment 3 of the present invention.

[0026] Figure 5 This is a schematic diagram of the structure of an electronic device that implements an embodiment of the present invention. Detailed Implementation

[0027] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0029] Example 1

[0030] Figure 1This is a flowchart illustrating a rapid grasping method for an intelligent sensing robotic arm based on preset object visual judgment, as provided in Embodiment 1 of the present invention. This embodiment is applicable to the grasping situation of an intelligent sensing robotic arm. The method can be executed by a rapid grasping device of the intelligent sensing robotic arm based on preset object visual judgment. This rapid grasping device can be implemented in hardware and / or software, and can be configured within the intelligent sensing robotic arm. Figure 1 As shown, the method includes:

[0031] S110, Capture image information of preset items.

[0032] In this embodiment, the preset item can be understood as the object to be grasped. The image information can be understood as an image of the preset item captured by the acquisition device, such as an RGB image.

[0033] Specifically, the processor can capture preset items in the application scenario through a data acquisition device (such as a binocular camera).

[0034] S120. Based on image information, perform target recognition on the preset items and determine the object parameter information of the preset items.

[0035] In this embodiment, object parameter information can be understood as parameters used to characterize a preset item.

[0036] Specifically, the processor can take image information as input and use deep learning or other methods to perform target recognition on preset objects. In this embodiment, deep learning is used as an example only, and the method of target recognition is not limited. The preset object category, attributes, density and volume information are obtained as object parameter information.

[0037] S130. Based on the object parameter information and the preset weight gradient value group, control the intelligent sensing robot arm to grasp the preset item.

[0038] In this embodiment, the weight gradient value group can be understood as N weight gradient values ​​set from low to high.

[0039] Specifically, the processor can roughly estimate the gripping force and optimal gripping angle for a preset item based on the object's parameter information. It then controls the intelligent sensing robotic arm to grasp the preset item according to this gripping force and angle. By analyzing the actual gripping process and combining it with a weight gradient value set, the processor gradually adjusts the gripping force. For example, the processor can increase the gripping force sequentially from low to high according to the weight gradient value set until the intelligent sensing robotic arm can grasp the preset item, thus obtaining the optimal gripping force for that item. Once the optimal gripping force for grasping the preset item is determined, the intelligent sensing robotic arm is controlled to grasp the preset item using this optimal gripping force.

[0040] The technical solution of this invention involves capturing image information of a preset object; performing target recognition on the preset object based on the image information to determine the object parameter information; and controlling an intelligent sensing robotic arm to grasp the preset object according to the object parameter information and a preset weight gradient value set. By performing target recognition on the preset object through visual perception and making precise adjustments based on the preset weight gradient set, the intelligent sensing robotic arm is controlled to grasp the preset object. This achieves adaptive adjustment of the grasping parameters, ensuring the accuracy of the grasping parameters, and enabling rapid grasping of the target object even without setting grasping parameters, thus improving the intelligence and efficiency of the grasping process.

[0041] Example 2

[0042] Figure 2 This is a flowchart of a rapid grasping method for an intelligent sensing robotic arm based on preset object visual judgment, provided in Embodiment 2 of the present invention. This embodiment is a further refinement of the above embodiment. Figure 2 As shown, the method includes:

[0043] S210, Capture image information of preset items.

[0044] S220. Based on image information, perform target recognition on the preset items and determine the object parameter information of the preset items.

[0045] S230. Based on the object parameter information, compare it with the preset object database to determine whether there is a reference object that matches the preset item.

[0046] In this embodiment, the object database can be understood as a database used to store the grasping parameters of each object.

[0047] Specifically, the processor can compare the object parameters of each object in the preset object database based on the object parameter information to determine whether there is a reference object that matches the preset item, that is, whether there are similar or identical objects in the object database.

[0048] Furthermore, the step of comparing the object's parameter information with a pre-defined object database to determine whether a reference object matching the pre-defined item exists may include:

[0049] a1. Obtain the candidate object parameter set for each object in the object database.

[0050] In this embodiment, the candidate object parameter set can be understood as a collection of parameter information corresponding to each object stored in the object database.

[0051] Specifically, the processor can obtain a set of candidate object parameters from the object database.

[0052] b1. Compare the object parameter information with the parameters of each candidate object included in the candidate object parameter set.

[0053] Specifically, the processor can compare the parameters included in the object parameter information of the preset item with the corresponding parameters of the candidate object, such as volume parameters, density parameters, and object parameters.

[0054] c1. If the preset item parameters in the candidate object parameter set meet the comparison conditions, then there is a reference object, and the candidate object corresponding to the preset item parameters is used as the reference object.

[0055] In this embodiment, the comparison conditions can be understood as conditions used to determine whether two objects are similar or identical. The preset item parameters can be understood as object parameters that are similar to or identical to the object parameter information. The reference object can be understood as an object similar to or close to the preset item.

[0056] Specifically, the processor can compare the object parameters of each candidate object in the candidate object parameter set with the object parameter information of the preset item. If the object parameter information in the candidate object parameter set meets the comparison conditions, it is used as the preset item parameter. If the preset item parameter and the object parameter information have the same parameters or the error is within a certain range, the corresponding candidate object is used as the reference object.

[0057] For example, the preset item is a glass water cup, and its corresponding object parameter information can be: object type is water cup, volume is A1, density is B1. There is a candidate object C in the object database, and its corresponding candidate parameter information is: object type is water cup, volume is A2, density is B1. Then, candidate object C is used as the reference object.

[0058] d1. Otherwise, determine that no reference object exists in the object database.

[0059] Specifically, the processor can compare the object parameters of each candidate object in the candidate object parameter set with the object parameter information of the preset item. If the object parameter information of all candidate objects does not meet the comparison conditions, such as the difference between the parameters of the preset item and the object parameter information being too large, then there is no reference object in the object database.

[0060] S240. If so, read the grasping parameters of the reference object from the object database, use the grasping parameters as control parameters, and control the intelligent sensing robot arm to grasp the preset item based on the control parameters.

[0061] In this embodiment, the grasping parameters can be understood as the optimal parameters when grasping a reference object. The control parameters can be understood as the parameters that control the intelligent sensing robotic arm to grasp objects.

[0062] Specifically, after comparison by the processor, when a reference object matching the preset item exists in the object database, the corresponding grasping parameters of the reference object can be read. The grasping parameters are used as control parameters to control the intelligent sensing robot's movements, and the intelligent sensing robot is controlled to grasp the preset item based on the control parameters.

[0063] S250. If not, then determine the control parameters based on the object parameter information and weight gradient value group, and control the intelligent sensing robot arm to grasp the preset item based on the control parameters.

[0064] Specifically, after comparison by the processor, when no reference object matching the preset item exists in the object database, the processor can roughly estimate the gripping force and optimal gripping angle based on the object parameter information. The processor then controls the intelligent sensing robotic arm to grasp the preset item according to this gripping force and angle. The gripping force is gradually adjusted based on the actual gripping process and a weight gradient value set. For example, the processor can increase the gripping force sequentially from low to high according to the weight gradient value set until the intelligent sensing robotic arm can grasp the preset item, thus obtaining the optimal gripping force for that preset item. The optimal gripping force for grasping the preset item is determined, and the intelligent sensing robotic arm is controlled to grasp the preset item using this optimal gripping force.

[0065] Furthermore, the steps for determining control parameters based on object parameter information and weight gradient value sets may include:

[0066] a2. Based on the object parameter information, determine the grasping angle value and the initial calibrator value for grasping the preset object, and use the initial calibrator value as the grasping force value of the intelligent sensing robot arm.

[0067] In this embodiment, the grasping angle value can be understood as the grasping angle of the intelligent sensing robotic arm relative to the preset object. The initial calibration base can be understood as a roughly estimated grasping force. The grasping force value can be understood as the force with which the intelligent sensing robotic arm grasps the preset object.

[0068] Specifically, the processor can estimate the grasping angle and grasping force of the intelligent sensing robot arm to grasp a preset item based on the object parameter information, determine the grasping angle value and the initial calibrator, and use the initial calibrator as the grasping force value of the intelligent sensing robot arm.

[0069] b2. Grasp the preset item based on the grasping angle value and grasping force value, and determine the displacement change of the preset item.

[0070] In this embodiment, the displacement change can be understood as the amount of movement of the preset item.

[0071] Specifically, before grasping, the processor can determine the initial position of the preset item using a binocular camera, and control the intelligent sensing robotic arm to grasp the preset item in a set direction based on the grasping angle and grasping force values. Based on the initial position, the amount of displacement change of the preset item can be determined.

[0072] For example, when the grab is successful, the preset item will move upward, resulting in an upward displacement change; when the grab fails, the preset item will not move upward, and may remain in place or experience a small displacement change.

[0073] c2. Based on the displacement change, gripping force value, and weight gradient value group, adjust the gripping force value to determine the final force value.

[0074] Specifically, the processor can determine whether the grasp is successful based on the amount of displacement change. If the grasp fails, the processor can gradually adjust the grasping force value based on the weight gradient values ​​included in the weight gradient value group until a displacement change occurs, and determine the grasping force value at the time when the displacement change occurs as the final force value.

[0075] Furthermore, the step of adjusting the force value based on the displacement change, gripping force value, and weight gradient value set to determine the final force value may include:

[0076] c21. When the displacement change is less than the preset displacement threshold, the target gradient value is selected from the weight gradient value group in a preset order.

[0077] In this embodiment, the displacement threshold can be understood as a threshold used to determine whether the grasping was successful. The preset order can be understood as the order in which the grasping force values ​​are adjusted, which can be in order of increasing or decreasing grasping weight gradient values. The target gradient value can be understood as the value used to adjust the grasping force values.

[0078] Specifically, when the displacement change is less than the preset displacement threshold, it can be understood that the target has not been displaced, that is, the intelligent sensing robot arm has not successfully grasped it, and the target gradient value can be selected from the weight gradient value group in a preset order.

[0079] For example, the weight gradient value group includes four weight gradient values ​​W1, W2, W3 and W4 in ascending order. When the displacement change is less than the preset displacement threshold, the target gradient value can be determined as W1 first. If the displacement change is less than the preset displacement threshold in the next judgment, the target gradient value can be determined as W2, and so on.

[0080] c22. Adjust the gripping force value according to the target gradient value and the initial reference value to obtain a new gripping force value, and return to the gripping operation of the preset item.

[0081] Specifically, the processor can adjust the gripping force value based on the target gradient value and the initial reference value. For example, by adding the target gradient value to the initial reference value, a new gripping force value is obtained, and combined with the gripping angle value, the processor returns to continue executing the gripping operation in step b2.

[0082] c23. When the displacement change is greater than or equal to the displacement threshold, the gripping force value will be used as the final force value.

[0083] Specifically, when the displacement change is greater than or equal to the displacement threshold, it can be understood that the target has undergone a large displacement, that is, the intelligent sensing robotic arm has successfully grasped it, and the processor can use the grasping force value at this time as the final force value corresponding to the preset item.

[0084] d2. Determine the control parameters based on the final force value and gripping angle value.

[0085] Specifically, the processor can determine the control parameters based on the final force value and the gripping angle value.

[0086] The technical solution of this invention makes an initial judgment on object parameters such as volume and shape through visual perception, which can provide a reasonable initial reference value for the preset object. It realizes adaptive adjustment of grasping parameters, and performs comprehensive evaluation calculation by combining force feedback and displacement change after force application. It quickly calibrates the initial reference value through weight gradient value group to determine the final force value. It also has a data storage and data comparison mechanism for the object database. When there is a matching reference object, it grasps the preset object based on the grasping parameters of the reference object, which improves the grasping efficiency of the object and ensures the accuracy of the grasping parameters. It achieves rapid grasping of the target object without setting grasping parameters, thus improving the intelligence of grasping.

[0087] As a first optional embodiment of this second embodiment, after controlling the intelligent sensing robotic arm to grasp the preset item based on the object parameter information and the preset weight gradient value set, further optimization can be achieved, including:

[0088] If there is no reference object matching the preset item in the object database, the parameter information to be stored in the object database is determined based on the object parameter information and control parameters.

[0089] In this embodiment, the parameter information can be understood as the grasping parameters and object parameter information corresponding to the preset item.

[0090] Specifically, if there is no reference object matching the preset item in the object database, that is, if there are no grasping parameters for the preset item in the object database, the processor can associate and record the object parameter information and control parameters after successful grasping to determine the parameter information to be stored in the object database.

[0091] Furthermore, based on the above embodiments, the step of determining the parameter information to be stored in the object database according to the object parameter information and control parameters may include:

[0092] a3. Establish the relationship between object parameter information and control parameters.

[0093] In this embodiment, the association relationship can be understood as the relationship between object parameter information and control parameters.

[0094] Specifically, to facilitate subsequent searches, the processor can establish a correlation between object parameter information and control parameters, so that the corresponding control parameters can be found based on the object parameter information.

[0095] b3. Use the association relationship, object parameter information and control parameters as parameter information.

[0096] Specifically, the processor can use the relationships, object parameter information, and control parameters as parameter information and store the parameter information in the object database.

[0097] In the first optional embodiment of this second embodiment, when there is no reference object matching the preset item in the object database, the grasping parameters are stored so that grasping parameters can be used when grasping similar or identical objects in the future, thereby improving grasping efficiency.

[0098] For example, to facilitate understanding of the technical solution of the present invention, an example is used to illustrate a rapid grasping method of an intelligent sensing robotic arm based on preset object visual judgment proposed in the present invention. Figure 3 This is an example flowchart of a rapid grasping method for an intelligent sensing robotic arm based on preset object visual judgment, provided in Embodiment 2 of the present invention. Figure 3 As shown, it includes the following steps:

[0099] S301, Capture image information of preset items;

[0100] S302. Based on image information, perform target recognition on the preset items and determine the object parameter information of the preset items;

[0101] S303. Based on the object parameter information, compare it with the preset object database to determine whether there is a reference object that matches the preset item. If yes, proceed to step S304; otherwise, proceed to step S305.

[0102] S304. Read the grasping parameters of the reference object from the object database, use the grasping parameters as control parameters, and control the intelligent sensing robot arm to grasp the preset items based on the control parameters.

[0103] S305. Based on the object parameter information, determine the grasping angle value and the initial calibrator value for grasping the preset item, use the initial calibrator value as the grasping force value of the intelligent sensing robot arm, and grasp the preset item based on the grasping angle value and the grasping force value.

[0104] S306. Determine whether the displacement change is less than a preset displacement threshold. If yes, proceed to step S307; otherwise, proceed to step S309.

[0105] S307. Select the target gradient value from the weight gradient value group in a preset order;

[0106] S308. Adjust the gripping force value according to the target gradient value and the initial reference value to obtain a new gripping force value, and grip the preset item based on the new gripping force value and gripping angle value.

[0107] S309. Use the gripping force value as the final force value, and use the final force value and gripping angle value as control parameters;

[0108] S310. Store the object parameter information and control parameters in the object database.

[0109] Example 3

[0110] Figure 4 This is a structural schematic diagram of a rapid grasping device for an intelligent sensing robotic arm based on preset object visual judgment, provided in Embodiment 3 of the present invention. Figure 4 As shown, the device includes: an information capture module 41, an information determination module 42, and a grasping module 43. Among them,

[0111] Information capture module 41 is used to capture image information of preset items;

[0112] Information determination module 42 is used to perform target recognition on a preset item based on the image information and determine the object parameter information of the preset item;

[0113] The grasping module 43 is used to control the intelligent sensing robot to grasp the preset item based on the object parameter information and the preset weight gradient value group.

[0114] The technical solution of this invention involves capturing image information of a preset object; performing target recognition on the preset object based on the image information to determine the object parameter information; and controlling an intelligent sensing robotic arm to grasp the preset object according to the object parameter information and a preset weight gradient value set. By performing target recognition on the preset object through visual perception and making precise adjustments based on the preset weight gradient set, the intelligent sensing robotic arm is controlled to grasp the preset object. This achieves adaptive adjustment of the grasping parameters, ensuring the accuracy of the grasping parameters, and enabling rapid grasping of the target object even without setting grasping parameters, thus improving the intelligence and efficiency of the grasping process.

[0115] Optionally, the capture module 43 includes:

[0116] The first determining module is used to compare the object parameter information with a preset object database to determine whether there is a reference object that matches the preset item.

[0117] The second determining module is used to read the grasping parameters of the reference object from the object database if the condition is met, use the grasping parameters as control parameters, and control the intelligent sensing robot arm to grasp the preset item based on the control parameters.

[0118] The third determining module is used to determine the control parameters based on the object parameter information and the weight gradient value group if no, and to control the intelligent sensing robot arm to grasp the preset item based on the control parameters.

[0119] Furthermore, the first determining module is specifically used for:

[0120] Obtain the candidate object parameter set for each object in the object database;

[0121] The object parameter information is compared with the parameters of each candidate object included in the candidate object parameter set;

[0122] If the preset item parameters in the candidate object parameter set meet the comparison conditions, then the reference object exists, and the candidate object corresponding to the preset item parameters is used as the reference object.

[0123] Otherwise, it is determined that the reference object does not exist in the object database.

[0124] Furthermore, the third determining module includes:

[0125] The first determining unit is used to determine the grasping angle value and the initial calibrator value for grasping the preset item based on the object parameter information, and to use the initial calibrator value as the grasping force value of the intelligent sensing robot arm.

[0126] The second determining unit is used to grasp the preset item based on the grasping angle value and the grasping force value, and determine the displacement change of the preset item;

[0127] The third determining unit is used to adjust the gripping force value based on the displacement change, the gripping force value, and the weight gradient value group to determine the final force value.

[0128] The fourth determining unit is used to determine the control parameters based on the final force value and the grasping angle value.

[0129] The third determining unit is specifically used for:

[0130] When the displacement change is less than a preset displacement threshold, a target gradient value is selected from the weight gradient value group in a preset order;

[0131] The grasping force value is adjusted according to the target gradient value and the initial benchmark value to obtain a new grasping force value, and the grasping operation on the preset item is returned.

[0132] When the displacement change is greater than or equal to the displacement threshold, the gripping force value is taken as the final force value.

[0133] Optionally, the device may also include:

[0134] The storage module is used to determine the parameter information to be stored in the object database based on the object parameter information and the control parameters if no reference object matching the preset item exists in the object database.

[0135] Furthermore, the storage module is specifically used for:

[0136] Establish the association between the object parameter information and the control parameters;

[0137] The association relationship, the object parameter information, and the control parameters are used as the parameter information.

[0138] The rapid grasping device of the intelligent sensing robot based on preset object visual judgment provided in the embodiments of the present invention can execute the rapid grasping method of the intelligent sensing robot based on preset object visual judgment provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0139] Example 4

[0140] Figure 5 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0141] like Figure 5 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0142] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0143] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the rapid grasping method of an intelligent sensing robotic arm based on preset object visual judgment.

[0144] In some embodiments, the rapid grasping method of the intelligent sensing robot based on preset object visual judgment can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the rapid grasping method of the intelligent sensing robot based on preset object visual judgment described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the rapid grasping method of the intelligent sensing robot based on preset object visual judgment by any other suitable means (e.g., by means of firmware).

[0145] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0146] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0147] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0148] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0149] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0150] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0151] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0152] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A quick grasping method of an intelligent perception robot based on preset object visual judgment, characterized in that, include: Capture image information of preset items; Based on the image information, target recognition is performed on the preset item to determine the object parameter information of the preset item; Based on the object parameter information and the preset weight gradient value set, the intelligent sensing robotic arm is controlled to grasp the preset item; The step of controlling the intelligent sensing robotic arm to grasp the preset item based on the object parameter information and a preset weight gradient value set includes: Based on the object parameter information, a comparison is performed in a preset object database to determine whether there is a reference object that matches the preset item. If so, the grasping parameters of the reference object are read from the object database, and the grasping parameters are used as control parameters. Based on the control parameters, the intelligent sensing robot arm is controlled to grasp the preset item. If not, then the control parameters are determined based on the object parameter information and the weight gradient value group, and the intelligent sensing robot arm is controlled to grasp the preset item based on the control parameters; The step of determining the control parameters based on the object parameter information and the weight gradient value set includes: Based on the object parameter information, the grasping angle value and the initial calibrator value for grasping the preset item are determined, and the initial calibrator value is used as the grasping force value of the intelligent sensing robot arm. The preset item is grasped based on the grasping angle value and the grasping force value, and the displacement change of the preset item is determined. The gripping force value is adjusted based on the displacement change, the gripping force value, and the weight gradient value group to determine the final force value; The control parameters are determined based on the final force value and the gripping angle value. The step of adjusting the gripping force value based on the displacement change, the initial reference value, and the weight gradient value set to determine the final force value includes: When the displacement change is less than a preset displacement threshold, a target gradient value is selected from the weight gradient value group in a preset order; The grasping force value is adjusted according to the target gradient value and the initial benchmark value to obtain a new grasping force value, and the grasping operation on the preset item is returned. When the displacement change is greater than or equal to the displacement threshold, the gripping force value is taken as the final force value.

2. The method of claim 1, wherein, The step of comparing the object parameter information with a preset object database to determine whether a reference object matching the preset item exists includes: Obtain the candidate object parameter set for each object in the object database; The object parameter information is compared with the parameters of each candidate object included in the candidate object parameter set; If the preset item parameters in the candidate object parameter set meet the comparison conditions, then the reference object exists, and the candidate object corresponding to the preset item parameters is used as the reference object. Otherwise, it is determined that the reference object does not exist in the object database.

3. The method according to claim 1, characterized in that, After controlling the intelligent sensing robotic arm to grasp the preset item based on the object parameter information and a preset weight gradient value set, the method further includes: If no reference object matching the preset item exists in the object database, the parameter information to be stored in the object database is determined based on the object parameter information and the control parameters.

4. The method according to claim 3, characterized in that, The step of determining the parameter information to be stored in the object database based on the object parameter information and the control parameters includes: Establish the association between the object parameter information and the control parameters; The association relationship, the object parameter information, and the control parameters are used as the parameter information.

5. A rapid grasping device for an intelligent sensing robotic arm based on preset object visual judgment, characterized in that, include: The information capture module is used to capture image information of preset items; The information determination module is used to perform target recognition on a preset item based on the image information and determine the object parameter information of the preset item; The grasping module is used to control the intelligent sensing robot arm to grasp the preset item based on the object parameter information and the preset weight gradient value group. The crawling module includes: The first determining module is used to compare the object parameter information with a preset object database to determine whether there is a reference object that matches the preset item. The second determining module is used to read the grasping parameters of the reference object from the object database if the condition is met, use the grasping parameters as control parameters, and control the intelligent sensing robot arm to grasp the preset item based on the control parameters. The third determining module is used to determine the control parameters based on the object parameter information and the weight gradient value group if no, and to control the intelligent sensing robot arm to grasp the preset item based on the control parameters; The third determining module includes: The first determining unit is used to determine the grasping angle value and the initial calibrator value for grasping the preset item based on the object parameter information, and to use the initial calibrator value as the grasping force value of the intelligent sensing robot arm. The second determining unit is used to grasp the preset item based on the grasping angle value and the grasping force value, and determine the displacement change of the preset item. The third determining unit is used to adjust the grasping force value based on the displacement change, the grasping force value, and the weight gradient value group to determine the final force value. The fourth determining unit is used to determine the control parameters based on the final force value and the grasping angle value; Specifically, the third determining unit is used for: When the displacement change is less than a preset displacement threshold, a target gradient value is selected from the weight gradient value group in a preset order; The grasping force value is adjusted according to the target gradient value and the initial benchmark value to obtain a new grasping force value, and the grasping operation on the preset item is returned. When the displacement change is greater than or equal to the displacement threshold, the gripping force value is taken as the final force value.

6. An intelligent sensing robotic arm, characterized in that, The intelligent sensing robotic arm includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the rapid grasping method of the intelligent sensing robotic arm based on preset object visual judgment as described in any one of claims 1-4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the rapid grasping method of the intelligent sensing robotic arm based on preset object visual judgment as described in any one of claims 1-4.

Images