Robot mechanical arm intelligent control method and system

Abstract

The invention provides an intelligent control method and system for a robot mechanical arm, and belongs to the technical field of robot control. The method comprises the steps that a first grabbing strategy of the robot mechanical arm is determined based on a preset task; in response to the received first instruction information, selecting a target grabbing strategy corresponding to the first instruction information from a target strategy library based on the first instruction information, and updating the first grabbing strategy into the target grabbing strategy; a plurality of grabbing strategies are stored in the target strategy library; and the grabbing force of the robot mechanical arm is controlled based on the target grabbing strategy. The working efficiency of the robot mechanical arm can be improved, and the control precision can be improved.

Description

Technical Field

[0001] The present disclosure belongs to the field of robot control technology, and more specifically, to a robot manipulator intelligent control method and system. Background Art

[0002] As a key automation equipment, robotic arms have been widely used in many fields such as industrial production, logistics warehousing, medical surgery, aerospace, etc. However, existing robotic arm control methods still have many limitations. Traditional control methods often rely on pre-set fixed procedures and rules, and it is difficult to make real-time and flexible adjustments according to complex and changing working environments and task requirements. When faced with emergencies in work scenarios, traditional control methods often fail to respond effectively in a timely manner, resulting in reduced work efficiency of robotic arms and even possible safety accidents. Summary of the invention

[0003] The purpose of the present disclosure is to provide a method and system for intelligent control of a robot manipulator to improve the working efficiency and control accuracy of the robot manipulator.

[0004] A first aspect of the embodiments of the present disclosure provides a method for intelligently controlling a robot manipulator arm, comprising: Determining a first grasping strategy of the robot manipulator based on the preset task; In response to receiving the first instruction information, selecting a target grabbing strategy corresponding to the first instruction information from a target strategy library based on the first instruction information, and updating the first grabbing strategy to the target grabbing strategy; the target strategy library stores a plurality of grabbing strategies; The grasping force of the robot arm is controlled based on the target grasping strategy.

[0005] A second aspect of the embodiments of the present disclosure provides a robot manipulator intelligent control system, including: A strategy determination module, used to determine a first grasping strategy of the robot manipulator based on a preset task; An updating module, configured to, in response to receiving the first instruction information, select a target grabbing strategy corresponding to the first instruction information from a target strategy library based on the first instruction information, and update the first grabbing strategy to the target grabbing strategy; the target strategy library stores a plurality of grabbing strategies; A control module is used to control the grasping force of the robot arm based on the target grasping strategy.

[0006] According to a third aspect of an embodiment of the present disclosure, a robot is provided, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of the above-mentioned robot manipulator arm intelligent control method when executing the computer program.

[0007] According to a fourth aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned robot manipulator intelligent control method are implemented.

[0008] The beneficial effects of the robot manipulator intelligent control method and system provided by the embodiments of the present disclosure are: On the one hand, the disclosed embodiments can significantly improve the flexibility and adaptability of the robot arm when performing tasks. The initial grasping strategy is determined by the preset task, and after receiving the instruction information, it can quickly select and update the target grasping strategy that best meets the current task requirements from the target strategy library, which enables the robot to cope with various complex and changeable operation scenarios and ensure the smooth completion of the task.

[0009] On the other hand, the disclosed embodiments can also optimize the gripping force control of the robot's mechanical arm, further improving the accuracy and safety of the operation. By accurately setting the gripping force, the robot can ensure that the object is firmly grasped while avoiding unnecessary damage to the object or the mechanical arm itself. This refined control not only improves work efficiency, but also reduces operational risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0011] Figure 1 A schematic diagram of a flow chart of a robot manipulator intelligent control method provided by an embodiment of the present disclosure; Figure 2 A structural block diagram of a robot manipulator intelligent control system provided by an embodiment of the present disclosure; Figure 3 A schematic block diagram of a robot provided according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0012] In the following description, specific details such as specific system structures and technologies are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present disclosure. However, it should be clear to those skilled in the art that the present disclosure may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obstructing the description of the present disclosure with unnecessary details.

[0013] In order to make the purpose, technical solutions and advantages of the present disclosure more clear, specific embodiments will be described below in conjunction with the accompanying drawings.

[0014] Please refer to Figure 1 , Figure 1 A schematic diagram of a flow chart of a robot manipulator intelligent control method provided by an embodiment of the present disclosure, the method comprising: S101: Determine a first grasping strategy of the robot arm based on a preset task.

[0015] In this embodiment, the preset task is a task set by the robot itself, which specifies the work objectives to be achieved by the robot arm and the operations to be performed. The preset task includes detailed information of the target object, the storage location of the object, the time requirement for task execution, etc.

[0016] Detailed information of the target item, for example, in the scenario of picking up medicine, it can be the type of medicine, the specification of the medicine, the quantity of the medicine, etc.; in the scenario of picking up surgical instruments, it can be the type and model of the surgical instruments, etc. The storage location of the item, for example, in the scenario of picking up medicine, it can be the location of the medicine cabinet or the layer of the cabinet where the medicine is stored, etc.; in the scenario of picking up surgical instruments, it can be the location of the plate where the surgical instruments are placed, etc. The time requirement for task execution is the time at which the corresponding item needs to be picked up.

[0017] In the medical field, such as in scenarios such as taking medicines and surgical instruments, robotic arms can replace manual labor to complete repetitive, high-precision operations, reduce human errors and infection risks, and improve work efficiency.

[0018] The first grasping strategy is the initial grasping plan formulated for the robot's mechanical arm after the robot analyzes and plans the preset task. The plan includes the specific methods and related parameter settings that the mechanical arm should take when grasping the target object. For example, for the drug picking scene, the first grasping strategy can be "using parallel grippers to grasp from the middle of the amoxicillin capsule box, the grasping force is set to 20N, the grasping speed is 8 cm per second, the mechanical arm first moves horizontally to the front of the medicine rack, and then vertically descends to the layer where the medicine is located to grasp"; in the surgical equipment picking scene, the first grasping strategy can be "using a special scalpel clamping head to grasp from the handle of the scalpel, the grasping force is 15N, the grasping speed is 5 cm per second, and the mechanical arm moves to the surgical tray according to the planned collision-free trajectory to accurately grasp the scalpel."

[0019] In this embodiment, the preset task can be a task set in advance by the medical staff before the robot performs the task. When the task starts, the robot analyzes the preset task and obtains the properties of the target object. Different properties correspond to different grasping methods and action paths. The first grasping strategy of the robot arm is determined according to the grasping method and action path.

[0020] S102: In response to receiving the first instruction information, select a target grabbing strategy corresponding to the first instruction information from a target strategy library based on the first instruction information, and update the first grabbing strategy to the target grabbing strategy; the target strategy library stores a plurality of grabbing strategies.

[0021] In this embodiment, the first instruction information is a specific instruction signal received during the operation of the robot arm for changing or adjusting the grasping strategy. The instruction signal has various forms, such as voice instructions, key instructions, etc. These instructions contain new requirements or new situations for the target grasping task. For example, in a hospital medication scene, the original preset task is to take ordinary medicines, and the first instruction information can be a voice message sent by medical staff "Change to taking fragile glass bottle medicines."

[0022] The target strategy library stores a variety of grasping strategies, each of which is pre-set according to different target object attributes, working scenarios, and task requirements. The target strategy library provides a basis for the robot manipulator to select strategies when facing different task situations, so that the manipulator can quickly match the appropriate grasping strategy according to the received instruction information. The target grasping strategy is the grasping strategy that is selected from the target strategy library according to the first instruction information and best meets the current task requirements.

[0023] In this embodiment, after receiving the first instruction information, the robot parses the instruction information to obtain the content such as the change of the target object attribute, the change of the working scene or the adjustment of the task priority, and then searches and matches the target strategy library. By comparing the applicable conditions and key features of the first instruction information with each strategy in the target strategy library, the target grasping strategy that best matches the first instruction information is selected, and the first grasping strategy currently being executed is updated to the target grasping strategy, so as to ensure that the subsequent grasping operation of the robot manipulator can accurately adapt to the new task requirements.

[0024] S103: Controlling the grasping force of the robot arm based on the target grasping strategy.

[0025] In this embodiment, the gripping force is the force applied by the robot arm when grasping the target object. The appropriate gripping force should ensure that the object can be firmly grasped so that it will not fall during the handling process, but it should not be too large to avoid damaging the object or causing damage to the robot arm itself. For example, when grasping a medicine bottle, the gripping force should be controlled to a level that can hold the medicine bottle without crushing it.

[0026] It can be concluded from the above that, on the one hand, this embodiment can significantly improve the flexibility and adaptability of the robot arm when performing tasks. The initial grasping strategy is determined by the preset task, and after receiving the instruction information, it can quickly select and update the target grasping strategy that best meets the current task requirements from the target strategy library, which enables the robot to cope with various complex and changeable operation scenarios and ensure the smooth completion of the task.

[0027] On the other hand, this embodiment can also optimize the gripping force control of the robot's mechanical arm, further improving the accuracy and safety of the operation. By accurately setting the gripping force, the robot can ensure that the object is firmly grasped while avoiding unnecessary damage to the object or the mechanical arm itself. This refined control not only improves work efficiency, but also reduces operational risks.

[0028] In one embodiment of the present disclosure, determining a first grasping strategy of a robot manipulator based on a preset task includes: Split the preset task into multiple subtasks, determine the target object information corresponding to each subtask, and ensure that each subtask is related to another; A first grasping strategy of the robot manipulator is determined based on the target object information corresponding to each subtask.

[0029] In this embodiment, in order to facilitate the robot arm to perform the preset task, the preset task is split into multiple relatively independent and interrelated subtasks according to logic and process. Each subtask has its clear work content and goals. The target object information is various characteristics and state information of the target object related to each subtask.

[0030] The robot arm intelligent control method also includes: Build a task dependency graph based on the execution order and logic of each subtask, and determine the preconditions and postconditions of each subtask.

[0031] The first capture strategy includes: during the execution of each subtask, when the current subtask is completed, other subtasks related to the current subtask are automatically triggered according to the post-conditions of the current subtask in the first time; when the current subtask fails, backtrack to other subtasks related to the current subtask according to the pre-conditions of the current subtask and the task dependency graph.

[0032] In this embodiment, suppose the robot's working scenario is to pick up surgical instruments. The surgical instruments are divided into the first group of instruments, the second group of instruments, the third group of instruments, and the fourth group of instruments. The first group of instruments includes three hemostatic forceps (A, B, C) of different sizes but with the same function, the second group of instruments includes one tweezer, and the third group of instruments includes four needle holders of different specifications (a, b, c, d). Because hemostatic forceps A and needle holder B are used in combination, when the robot chooses to pick up hemostatic forceps A, it must choose needle holder b associated with hemostatic forceps A when picking up the third group of instruments.

[0033] The workflow of this embodiment is as follows: After the robot determines the preset task, it needs to split the preset task more accurately according to its internal logic and process. Just like breaking a complex puzzle into multiple small pieces, each small piece is a subtask. Multiple subtasks are relatively independent but closely related, and each subtask has corresponding target object information and execution specifications. This information includes various characteristics and states of the target object, such as the shape, size, weight, material, position, and whether it is fragile. After the robot determines the target object information corresponding to each subtask, it can comprehensively consider the performance and characteristics of the robot arm to determine the first grasping strategy of the robot arm. The strategy includes the way the robot arm grasps the target object, such as clamping, adsorption, or other methods; the grasping position, whether it is the middle part, edge, or specific handle of the object; the grasping force, which should be able to firmly grasp the object without damaging it; and the grasping speed and other parameters. For example, for fragile glass equipment, the grasping force should be gentle and the speed should be slow and stable.

[0034] It can be concluded from the above that this embodiment can accurately formulate the first grasping strategy of the robot manipulator by subdividing the preset task into multiple related subtasks and determining the specific target object information for each subtask. This method improves the flexibility and accuracy of task execution, ensures the effective operation of the manipulator at different task stages, and thus improves the overall work efficiency and task completion quality.

[0035] In one embodiment of the present disclosure, selecting a target grabbing strategy corresponding to the first instruction information from a target strategy library based on the first instruction information includes: Extracting features from the first instruction information to obtain first key information; Calculate the first similarity between the first key information and the applicable conditions of each crawling strategy in the target strategy library, and calculate the second similarity between the first key information and the key features of each crawling strategy in the target strategy library; Calculating a target similarity based on the first similarity and the second similarity; Based on the target similarity, a target grabbing strategy corresponding to the first instruction information is selected from a target strategy library.

[0036] In this embodiment, feature extraction is performed on the first instruction information to obtain the first key information, including: If the first instruction information is voice information, convert the voice information into text information, and perform feature extraction on the text information to obtain the first key information; If the first instruction information is key information, the code of the key information is identified to obtain a target key code, and the first key information is obtained based on the target key code.

[0037] In this embodiment, if the first instruction information is voice information, the vocabulary, grammar and voice characteristics in the voice information are determined, the voice information is converted into text information based on the vocabulary, grammar and voice characteristics in the voice information, and the text information is feature extracted to obtain the first key information. The specific implementation method is: The first instruction information is filtered using an audio processing algorithm to obtain the first voice information, the endpoints of the first voice information are detected, the starting position and the ending position of the first voice information are determined, and the amount of data to be processed is reduced. The voice signal is analyzed using an acoustic model and a language model. The acoustic model can map voice features to a phoneme sequence, and the language model converts the phoneme sequence into a vocabulary sequence based on the probability distribution and grammatical rules of the vocabulary. For example, a deep neural network acoustic model and a statistically based language model are used to analyze the voice signal frame by frame to identify the vocabulary therein.

[0038] Perform grammatical structure analysis on the identified word sequence to determine the relationship between words and the structure of the sentence. You can use context-free grammar or dependency syntax analysis to analyze the subject, predicate, object and other components of the sentence. Analyze the intonation, speaking rate, stress and other characteristics of the speech. By extracting the fundamental frequency, duration, energy and other features of the speech signal, determine the intonation changes and stress position of the speech. For example, when a certain word in the speech is pronounced with an increased fundamental frequency, longer duration and stronger energy, it means that the word may be the stress location. Assist in understanding the semantic focus of the speech. In some cases, changes in stress and intonation may change the meaning of the sentence.

[0039] According to the results of vocabulary recognition, grammatical analysis and speech characteristic analysis, the speech information is converted into text information that can be recognized by the machine, and then the features of the text information are extracted to obtain the first key information.

[0040] If the first instruction information is key information, the key information code is identified, and different key combinations correspond to different instruction meanings. A mapping table of key codes and key information is pre-established, and the corresponding target object features, task-related information, and working environment information are searched from the mapping table according to the identified key codes.

[0041] In this embodiment, the applicable conditions of the grasping strategy refer to the prerequisites and environmental requirements that need to be met for a grasping strategy to be effectively implemented. These conditions are usually related to factors such as the task scenario, the basic properties of the target object, and the working environment. For example, the applicable conditions can specify the weight range, shape characteristics, spatial position, temperature, humidity, light and other conditions of the surrounding environment of the target object.

[0042] The key features of a grasping strategy refer to the unique characteristic parameters of each grasping strategy that play a key role in the execution of the grasping task. These features directly determine the specific operation mode and behavior of the robot arm when performing the grasping task. Key features may include grasping methods (such as clamping, adsorption, magnetic suction, etc.), grasping force, grasping speed, grasping position, movement trajectory of the robot arm, etc. Different combinations of key features constitute different grasping strategies to adapt to various target objects and task requirements.

[0043] In this embodiment, the first similarity can be calculated using the cosine similarity formula, the second similarity can be calculated using the Euclidean distance, and then the first similarity and the second similarity are weighted and summed to obtain the target similarity. If the weight of the first similarity is the first weight and the weight of the second similarity is the second weight, the values ​​of the first weight and the second weight are dynamically adjusted according to the nature of the task.

[0044] If the nature of the task is an urgent task, the first weight is increased to the first preset weight value, and the second weight is reduced to the second preset weight value; if the nature of the task is a complex task, the first weight is reduced to the second preset weight value, and the second weight is increased to the first preset weight value. The weight adjustment method based on the nature of the task can make the calculated target similarity more accurate.

[0045] In this embodiment, the target grabbing strategy corresponding to the first instruction information is selected from the target strategy library based on the target similarity, including: The grasping strategies in the target strategy library are preliminarily sorted from high to low according to the target similarity to obtain the first sorting list, and an initial dynamic evaluation matrix is ​​established. The rows of the matrix represent the grasping strategies in the strategy library, and the columns represent the strategy evaluation indicators of multiple different dimensions. Each grasping strategy in the first sorting list is evaluated according to the initial dynamic evaluation matrix, and the evaluation results of each dimension are filled into the dynamic evaluation matrix to obtain the target dynamic evaluation matrix. The comprehensive evaluation score of each grasping strategy in the first sorting list is calculated according to the target dynamic evaluation matrix, and the grasping strategy with the highest comprehensive evaluation score is selected as the target grasping strategy corresponding to the first instruction information.

[0046] The comprehensive evaluation score calculation formula is:

[0047] Among them, S represents the crawling strategy, represents the comprehensive evaluation score, i represents the i-th evaluation indicator, n represents the number of evaluation indicators, represents the weight of the i-th evaluation indicator, represents the score of the i-th evaluation indicator.

[0048] It can be concluded from the above that this embodiment achieves the purpose of accurately selecting the corresponding grabbing strategy from the target strategy library by accurately extracting the key features of the first instruction information and comprehensively considering the applicable conditions and similarity of the key features with the target grabbing strategy. At the same time, it supports multiple instruction input methods such as voice and keystrokes, which improves the flexibility and user-friendliness of the system.

[0049] In one embodiment of the present disclosure, the target grasping strategy includes the properties of the target grasping object and the application scenario of the target grasping object; Control the grasping force of the robot arm based on the target grasping strategy, including: The basic grasping force is determined based on the properties of the target grasped object; the basic grasping force is adjusted based on the application scenario of the target grasped object to obtain the grasping force of the robot arm.

[0050] In this embodiment, the properties of the target grasped object refer to the various physical and chemical properties of the target grasped object, which directly affect the force required by the robot arm when grasping. Common properties include but are not limited to: Material: such as glass, plastic, metal, ceramic, etc. Objects of different materials have different mechanical properties such as hardness and toughness, and different requirements for grasping force. For example, glass is fragile and requires a smaller grasping force; while metal is relatively strong and can withstand a larger grasping force.

[0051] Shape: The shape of an object affects the contact area and stability of the grasp, and thus the grasping force. For example, spherical objects are prone to rolling, and require more precise and appropriate grasping force to maintain stability; while rectangular objects are relatively easier to grasp, and the grasping force can be controlled more flexibly.

[0052] Weight: The weight of an object is one of the important factors that determine the gripping force. Heavier objects require more gripping force to overcome gravity and ensure that they will not fall during the gripping and moving process.

[0053] The application scenario of the target grasping object refers to the environment and working conditions of the target grasping object, which will also affect the grasping force of the robot arm. The factors of the application scenario include but are not limited to: space restrictions, ambient temperature, and whether there is vibration, etc.

[0054] The basic grasping force is the grasping force preliminarily determined based on the properties of the target grasped object. It is a basic grasping force value calculated or preset based on the material, shape, weight and other properties of the object without considering the influence of the working scene. The grasping force of the robot arm is the final force used to control the robot arm to actually perform the grasping task. It is obtained after adjusting the basic grasping force and comprehensively considering the working scene factors of the target grasped object, which can ensure that the robot arm can grasp the target object safely and stably in a specific working scene.

[0055] In this embodiment, the basic grasping force is determined by the properties of the target grasped object, and then the basic grasping force is adjusted based on the application scenario of the target grasped object to obtain the grasping force of the robot arm, which can make the grasping force of the robot arm more accurate and reliable.

[0056] In one embodiment of the present disclosure, the robot arm intelligent control method further includes: Determining a first grasping speed of the robot manipulator based on the target grasping strategy; The first grasping speed is corrected based on the grasping force of the robot mechanical arm to obtain the grasping speed of the robot mechanical arm.

[0057] In this embodiment, the first grasping speed of the robot manipulator arm is determined based on the target grasping strategy, including: determining the first grasping speed of the robot manipulator arm by using a rule matching method or a mechanical model calculation method based on the target grasping strategy. The rule matching method, for example, pre-establishes a first corresponding rule table between the weight of the target grasping object and the first grasping speed, or pre-establishes a second corresponding rule table between the material of the target grasping object and the first grasping speed, or pre-establishes a third corresponding rule table between the shape of the target grasping object and the first grasping speed. For example, for fragile materials (such as glass), a low speed rule is established, such as setting the first grasping speed to 150 mm / s; for solid materials (such as metal), the speed can be appropriately increased and set to 400 mm / s. Based on the identified material information, the first grasping speed is determined from the second corresponding rule table. The mechanical model calculation method is to calculate the force and acceleration required in the grasping process according to the Newtonian mechanics principle, combined with the mass, inertia and other parameters of the target grasping object, and then derive the appropriate first grasping speed. For example, for an object with a mass of m, the acceleration is calculated according to F=ma (F is the grasping force and a is the acceleration), and then combined with the kinematic model of the robotic arm to determine the first grasping speed.

[0058] In this embodiment, the first grasping speed is corrected based on the grasping force of the robot mechanical arm to obtain the grasping speed of the robot mechanical arm, including: the first grasping speed is corrected based on the grasping force of the robot mechanical arm and the grasping difficulty coefficient to obtain the grasping speed of the robot mechanical arm. The specific implementation method is: the grasping difficulty coefficient is comprehensively determined based on factors such as the surface roughness, shape complexity, and center of gravity stability of the target grasped object. A relationship model between the grasping difficulty coefficient and the speed correction ratio is established in advance, and the corresponding speed correction ratio is obtained from the model according to the calculated grasping difficulty coefficient. The first grasping speed is multiplied by the correction ratio and then corrected in combination with the grasping force to obtain a more accurate grasping speed of the robot mechanical arm.

[0059] From the above, we can conclude that the grasping force of the robot arm can be controlled by comprehensively considering the properties of the target grasped object and the application scenario. On the one hand, the basic grasping force is determined according to the physical characteristics of the grasped object (such as material, weight, etc.) to ensure stable grasping; on the other hand, the force is flexibly adjusted in combination with the actual application scenario (such as handling, assembly, etc.) to avoid damaging the object or affecting the working efficiency, thus realizing efficient and safe automated grasping operations.

[0060] In one embodiment of the present disclosure, the robot arm intelligent control method further includes: If the grasping force of the robot mechanical arm is greater than a first preset threshold, based on the difference between the grasping force of the robot mechanical arm and the first preset threshold, the first grasping speed is corrected to obtain the grasping speed of the robot mechanical arm; If the grasping force of the robot arm is less than or equal to the first preset threshold, the first grasping speed is corrected based on the first mapping table to obtain the grasping speed of the robot arm; the first mapping table is a mapping table of grasping force and grasping speed.

[0061] In this embodiment, when the grasping force of the robot arm is greater than the first preset threshold, it indicates that the current grasping force is too large, which may cause damage to the target grasped object or increase the burden on the robot arm. At this time, the system will calculate the difference between the grasping force and the first preset threshold, and correct the first grasping speed according to this difference. The larger the difference, the more the grasping force exceeds the normal range, and the correction amplitude will increase accordingly, usually by reducing the grasping speed, thereby reducing the impact force and risk during the grasping process and ensuring the smooth progress of the grasping task.

[0062] When the grasping force of the robot arm is less than or equal to the first preset threshold, the system will use the first mapping table to correct the first grasping speed. The first mapping table constructs the correspondence between grasping force and grasping speed in advance, taking into account the properties of the target grasped object, the working scene and other factors. The system finds the corresponding grasping speed correction value from the first mapping table based on the current grasping force, and then obtains the appropriate grasping speed of the robot arm, ensuring that the arm can complete the grasping task at the optimal speed under different grasping forces.

[0063] From the above, it can be concluded that this embodiment ensures the accuracy and safety of the robot arm operation by dynamically adjusting the grasping speed to adapt to different grasping forces. When the grasping force is too large, the speed is reduced to reduce the impact; when the force is moderate or small, the speed is optimized according to the mapping table, thereby improving the grasping efficiency and stability.

[0064] Corresponding to the robot arm intelligent control method of the above embodiment, Figure 2 This is a block diagram of the structure of a robot arm intelligent control system provided by an embodiment of the present disclosure. For ease of explanation, only the parts related to the embodiment of the present disclosure are shown. Figure 2 The robot manipulator intelligent control system 20 includes: a strategy determination module 21, an update module 22 and a control module 23.

[0065] Wherein, the strategy determination module 21 is used to determine the first grasping strategy of the robot manipulator based on the preset task; The updating module 22 is used for selecting a target grabbing strategy corresponding to the first instruction information from a target strategy library based on the first instruction information in response to receiving the first instruction information, and updating the first grabbing strategy to the target grabbing strategy; the target strategy library stores a plurality of grabbing strategies; The control module 23 is used to control the grasping force of the robot arm based on the target grasping strategy.

[0066] In one embodiment of the present disclosure, the strategy determination module 21 is specifically used to: Split the preset task into multiple subtasks, determine the target object information corresponding to each subtask, and ensure that each subtask is related to another; A first grasping strategy of the robot manipulator is determined based on the target object information corresponding to each subtask.

[0067] In one embodiment of the present disclosure, the update module 22 is specifically used to: Extracting features from the first instruction information to obtain first key information; Calculate the first similarity between the first key information and the applicable conditions of each crawling strategy in the target strategy library, and calculate the second similarity between the first key information and the key features of each crawling strategy in the target strategy library; Calculating a target similarity based on the first similarity and the second similarity; Based on the target similarity, a target grabbing strategy corresponding to the first instruction information is selected from a target strategy library.

[0068] In one embodiment of the present disclosure, the update module 22 is specifically used to: If the first instruction information is voice information, convert the voice information into text information, and perform feature extraction on the text information to obtain the first key information; If the first instruction information is key information, the code of the key information is identified to obtain a target key code, and the first key information is obtained based on the target key code.

[0069] In one embodiment of the present disclosure, the target grasping strategy includes the properties of the target grasping object and the application scenario of the target grasping object; The control module 23 is specifically used for: The basic grasping force is determined based on the properties of the target grasped object; the basic grasping force is adjusted based on the application scenario of the target grasped object to obtain the grasping force of the robot arm.

[0070] In one embodiment of the present disclosure, the control module 23 is further configured to: Determining a first grasping speed of the robot manipulator based on the target grasping strategy; The first grasping speed is corrected based on the grasping force of the robot mechanical arm to obtain the grasping speed of the robot mechanical arm.

[0071] In one embodiment of the present disclosure, the control module 23 is further configured to: If the grasping force of the robot mechanical arm is greater than a first preset threshold, based on the difference between the grasping force of the robot mechanical arm and the first preset threshold, the first grasping speed is corrected to obtain the grasping speed of the robot mechanical arm; If the grasping force of the robot arm is less than or equal to the first preset threshold, the first grasping speed is corrected based on the first mapping table to obtain the grasping speed of the robot arm; the first mapping table is a mapping table of grasping force and grasping speed.

[0072] See also Figure 3 , Figure 3 Schematic diagram of a robot provided by an embodiment of the present disclosure. Figure 3 The robot 300 in the embodiment shown may include: one or more processors 301, one or more input devices 302, one or more output devices 303 and one or more memories 304. The processors 301, input devices 302, output devices 303 and memories 304 communicate with each other via a communication bus 305. The memory 304 is used to store computer programs, which include program instructions. The processor 301 is used to execute the program instructions stored in the memory 304. The processor 301 is configured to call the program instructions to execute the functions of each module / unit in the above-mentioned device embodiments, such as Figure 2 The functions of modules 21 to 23 are shown.

[0073] It should be understood that in the embodiment of the present disclosure, the processor 301 may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0074] The input device 302 may include a touch panel, a fingerprint collection sensor (for collecting the user's fingerprint information and fingerprint direction information), a microphone, etc., and the output device 303 may include a display (LCD, etc.), a speaker, etc.

[0075] The memory 304 may include a read-only memory and a random access memory, and provide instructions and data to the processor 301. A portion of the memory 304 may also include a non-volatile random access memory. For example, the memory 304 may also store information about the device type.

[0076] In a specific implementation, the processor 301, input device 302, and output device 303 described in the embodiments of the present disclosure can execute the implementation methods described in the first and second embodiments of the robot manipulator intelligent control method provided in the embodiments of the present disclosure, and can also execute the implementation methods of the robot described in the embodiments of the present disclosure, which will not be repeated here.

[0077] In another embodiment of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by the processor, all or part of the processes in the above-mentioned embodiment method are implemented, and the computer program can also be completed by instructing the relevant hardware through the computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by the processor, the steps of each of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0078] The computer-readable storage medium may be an internal storage unit of the robot of any of the aforementioned embodiments, such as a hard disk or memory of the robot. The computer-readable storage medium may also be an external storage device of the robot, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the robot. Furthermore, the computer-readable storage medium may also include both an internal storage unit and an external storage device of the robot. The computer-readable storage medium is used to store computer programs and other programs and data required by the robot. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.

[0079] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this disclosure.

[0080] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the robots and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0081] In the several embodiments provided in the present application, it should be understood that the disclosed robots and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces or units, or it can be an electrical, mechanical or other form of connection.

[0082] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of the present disclosure.

[0083] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0084] The above are only specific embodiments of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present disclosure, and these modifications or replacements should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.

Claims

1. A robot arm intelligent control method, characterized in that: include: Determining a first grasping strategy of the robot manipulator based on the preset task; In response to receiving the first instruction information, selecting a target grabbing strategy corresponding to the first instruction information from a target strategy library based on the first instruction information, and updating the first grabbing strategy to the target grabbing strategy; the target strategy library stores a plurality of grabbing strategies; The grasping force of the robot arm is controlled based on the target grasping strategy.

2. The robot arm intelligent control method according to claim 1, characterized in that: The first grasping strategy of the robot manipulator is determined based on the preset task, including: Splitting the preset task into multiple subtasks, determining target object information corresponding to each subtask, and each subtask is correlated; A first grasping strategy of the robot manipulator is determined based on the target object information corresponding to each subtask.

3. The robot arm intelligent control method according to claim 1, characterized in that: The selecting, based on the first instruction information, from a target strategy library a target grabbing strategy corresponding to the first instruction information includes: Extracting features from the first instruction information to obtain first key information; Calculating a first similarity between the first key information and the applicable conditions of each crawling strategy in the target strategy library, and calculating a second similarity between the first key information and the key features of each crawling strategy in the target strategy library; Calculating a target similarity based on the first similarity and the second similarity; A target grabbing strategy corresponding to the first instruction information is selected from a target strategy library based on the target similarity.

4. The robot arm intelligent control method according to claim 3, characterized in that: The step of extracting features from the first instruction information to obtain first key information includes: If the first instruction information is voice information, convert the voice information into text information, and perform feature extraction on the text information to obtain first key information; If the first instruction information is key information, the code of the key information is identified to obtain a target key code, and the first key information is obtained based on the target key code.

5. The robot arm intelligent control method according to claim 1, characterized in that: The target grasping strategy includes the properties of the target grasping object and the working scene of the target grasping object; The control of the grasping force of the robot mechanical arm based on the target grasping strategy includes: A basic grasping force is determined based on the properties of the target grasped object; and the basic grasping force is adjusted based on the working scenario of the target grasped object to obtain the grasping force of the robot mechanical arm.

6. The robot arm intelligent control method according to claim 1, characterized in that: Also includes: Determining a first grasping speed of the robot manipulator based on a target grasping strategy; The first grasping speed is corrected based on the grasping force of the robot mechanical arm to obtain the grasping speed of the robot mechanical arm.

7. The robot arm intelligent control method according to claim 6, characterized in that: Also includes: If the grasping force of the robot mechanical arm is greater than a first preset threshold, based on the difference between the grasping force of the robot mechanical arm and the first preset threshold, the first grasping speed is corrected to obtain the grasping speed of the robot mechanical arm; If the grasping force of the robot arm is less than or equal to a first preset threshold, the first grasping speed is corrected based on a first mapping table to obtain the grasping speed of the robot arm; the first mapping table is a mapping table of grasping force and grasping speed.

8. A robot arm intelligent control system, characterized in that: include: A strategy determination module, used to determine a first grasping strategy of the robot manipulator based on a preset task; An updating module, configured to, in response to receiving the first instruction information, select a target grabbing strategy corresponding to the first instruction information from a target strategy library based on the first instruction information, and update the first grabbing strategy to the target grabbing strategy; the target strategy library stores a plurality of grabbing strategies; A control module is used to control the grasping force of the robot arm based on the target grasping strategy.

9. A robot comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images