Intelligent Control Method and System for Robot Manipulator

Abstract

The present disclosure provides a method and system for intelligent control of a robotic manipulator, belonging to the technical field of robot control. The method includes: determining a first grasping strategy for the robotic manipulator based on a preset task; in response to receiving first instruction information, selecting a target grasping strategy corresponding to the first instruction information from a target strategy library, and updating the first grasping strategy to the target grasping strategy; a plurality of grasping strategies are stored in the target strategy library; controlling the grasping force of the robotic manipulator based on the target grasping strategy. The present disclosure can improve the working efficiency of the robotic manipulator and improve the control accuracy.

Description

Technical Field

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

[0002] As a key automation device, robot manipulators have been extremely widely used in many fields such as industrial production, logistics warehousing, medical surgery, and aerospace. However, there are still many limitations in the existing control methods for robot manipulators. Traditional control methods often rely on pre-set fixed programs and rules, and it is difficult to make real-time and flexible adjustments according to complex and changeable working environments and task requirements. When faced with unexpected situations in the working scenario, traditional control methods often cannot respond effectively in time, resulting in a decrease in the working efficiency of the robot manipulator and even possibly causing 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] In the first aspect of the embodiments of the present disclosure, a method for intelligent control of a robot manipulator is provided, including:

[0005] Determining a first grasping strategy for the robot manipulator based on a preset task;

[0006] In response to receiving first instruction information, selecting a target grasping strategy corresponding to the first instruction information from a target strategy library based on the first instruction information, and updating the first grasping strategy to the target grasping strategy; a variety of grasping strategies are stored in the target strategy library;

[0007] Controlling the grasping force of the robot manipulator based on the target grasping strategy.

[0008] In the second aspect of the embodiments of the present disclosure, an intelligent control system for a robot manipulator is provided, including:

[0009] A strategy determination module for determining a first grasping strategy for the robot manipulator based on a preset task;

[0010] An update module for, in response to receiving first instruction information, selecting a target grasping strategy corresponding to the first instruction information from a target strategy library based on the first instruction information, and updating the first grasping strategy to the target grasping strategy; a variety of grasping strategies are stored in the target strategy library;

[0011] A control module for controlling the grasping force of the robot manipulator based on the target grasping strategy.

[0012] In a third aspect of the embodiments of the present disclosure, a robot is provided, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of the above-mentioned intelligent control method for a robot manipulator are implemented.

[0013] In a fourth aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided. 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 intelligent control method for a robot manipulator are implemented.

[0014] The beneficial effects of the intelligent control method and system for a robot manipulator provided by the embodiments of the present disclosure are as follows:

[0015] On the one hand, the embodiments of the present disclosure can significantly improve the flexibility and adaptability of a robot manipulator when performing tasks. By presetting a task to determine an initial grasping strategy, and being able to quickly select and update to the target grasping strategy that best meets the current task requirements from the target strategy library after receiving instruction information, this enables the robot to cope with various complex and changeable operation scenarios and ensures the smooth completion of tasks.

[0016] On the other hand, the embodiments of the present disclosure can also optimize the grasping force control of the robot manipulator, further improving the accuracy and safety of operations. By precisely setting the grasping force, the robot can ensure firm grasping of an object while avoiding unnecessary damage to the object or the manipulator itself. This refined control not only improves work efficiency but also reduces operation risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the following drawings are only some embodiments of the present disclosure. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0018] Figure 1 It is a schematic flowchart of the intelligent control method for a robot manipulator provided by an embodiment of the present disclosure;

[0019] Figure 2 It is a structural block diagram of the intelligent control system for a robot manipulator provided by an embodiment of the present disclosure;

[0020] Figure 3 It is a schematic block diagram of a robot provided by an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0021] In the following description, specific details such as specific system architectures and technologies are presented for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present disclosure. However, those skilled in the art should clearly understand that the present disclosure can also 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 unnecessary details from interfering with the description of the present disclosure.

[0022] To make the objectives, technical solutions, and advantages of the present disclosure clearer, the following will be described through specific embodiments in conjunction with the accompanying drawings.

[0023] Please refer to Figure 1 , Figure 1 which is a schematic flowchart of an intelligent control method for a robotic manipulator provided by an embodiment of the present disclosure. The method includes:

[0024] S101: Determine a first grasping strategy for the robotic manipulator based on a preset task.

[0025] In this embodiment, the preset task is a task set by the robot itself, which stipulates the working objectives to be achieved by the manipulator and the operation content to be executed. The preset task includes detailed information about the target item, the storage location of the item, the time requirement for task execution, etc.

[0026] The detailed information about the target item, for example, in the scenario of fetching medicine, can be the type of medicine, the specification of the medicine, the quantity of the medicine, etc.; in the scenario of fetching surgical instruments, it can be the type and model of the surgical instruments. The storage location of the item, for example, in the scenario of fetching medicine, can be the cabinet location and shelf location where the medicine is stored; in the scenario of fetching surgical instruments, it can be the plate location where the surgical instruments are placed. The time requirement for task execution is the moment when the corresponding item needs to be fetched.

[0027] In the medical field, in scenarios such as fetching medicine and fetching surgical instruments, the robotic manipulator can replace humans to complete repetitive and high-precision operations, reducing human errors and the risk of infection and improving work efficiency.

[0028] The first grasping strategy is the initial grasping plan formulated for the robotic arm after the robot analyzes and plans a preset task. This plan includes the specific methods to be adopted when the robotic arm grasps the target item and relevant parameter settings, etc. For example, for the scenario of fetching medicine, the first grasping strategy can be "using parallel grippers to grasp from the middle of the amoxicillin capsule box, setting the grasping force to 20N, the grasping speed to 8 centimeters per second, the robotic arm first moves horizontally to the front of the medicine rack, and then vertically descends to the layer where the medicine is located for grasping"; in the scenario of fetching surgical instruments, the first grasping strategy can be "using a special scalpel gripper head to grasp from the handle part of the scalpel, the grasping force is 15N, the grasping speed is 5 centimeters per second, and the robotic arm moves to the surgical tray along the planned collision-free trajectory to precisely grasp the scalpel".

[0029] In this embodiment, the preset task can be a task set in advance by medical staff before the robot executes the task. When the task starts, the robot analyzes the preset task to obtain the attributes of the target object. Different attributes correspond to different grasping methods and action paths, and the first grasping strategy of the robotic arm of the robot is determined according to the grasping method and the action path.

[0030] S102: In response to receiving the first instruction information, select the target grasping strategy corresponding to the first instruction information from the target strategy library, and update the first grasping strategy to the target grasping strategy; there are multiple grasping strategies stored in the target strategy library.

[0031] In this embodiment, the first instruction information is a specific instruction signal received during the operation of the robotic arm of the robot for changing or adjusting the grasping strategy. This instruction signal has various forms, such as voice instructions, button instructions, etc. These instructions contain new requirements or new situations regarding the target grasping task. For example, in the scenario of fetching medicine in a hospital, if the original preset task is to fetch ordinary medicine, the first instruction information can be the voice message "change to fetching fragile glass bottled medicine" sent by the medical staff.

[0032] There are multiple grasping strategies stored in the target strategy library, and each grasping strategy is preset according to different target object attributes, working scenarios, and task requirements. The target strategy library provides a basis for the robotic arm of the robot to select strategies in the face of different task situations, enabling the robotic arm to quickly match the appropriate grasping strategy according to the received instruction information. The target grasping strategy is the grasping strategy that is screened out from the target strategy library according to the first instruction information and best meets the current task requirements.

[0033] In this embodiment, when the robot receives the first instruction information, it parses the instruction information to obtain content such as changes in the target object attributes, changes in the working scenario, or adjustments to the task priority, and then retrieves and matches the target policy library. By comparing the first instruction information with the applicable conditions and key features of each policy in the target policy library, the target grasping policy that best matches the first instruction information is selected, and the currently executing first grasping policy is updated to this target grasping policy, so as to ensure that the subsequent grasping operations of the robot manipulator can accurately adapt to the new task requirements.

[0034] S103: Control the grasping force of the robot manipulator based on the target grasping policy.

[0035] In this embodiment, the grasping force is the magnitude of the force exerted by the robot manipulator when grasping the target object. The appropriate grasping force should not only ensure that the object can be firmly grasped so that it will not fall during handling, but also not be too large to damage the object or cause damage to the manipulator itself. For example, when grasping a medicine bottle, the grasping force needs to be controlled to the extent that it can hold the medicine bottle without crushing it.

[0036] It can be concluded from the above that, on the one hand, this embodiment can significantly improve the flexibility and adaptability of the robot manipulator when performing tasks. By presetting the task to determine the initial grasping policy and being able to quickly select and update to the target grasping policy that best meets the current task requirements from the target policy library after receiving the instruction information, the robot can cope with various complex and changeable operation scenarios and ensure the smooth completion of the task.

[0037] On the other hand, this embodiment can also optimize the grasping force control of the robot manipulator and further improve the accuracy and safety of the operation. By precisely setting the grasping force, the robot can avoid causing unnecessary damage to the object or the manipulator itself while ensuring a firm grasp of the object. This refined control not only improves work efficiency but also reduces operation risks.

[0038] In an embodiment of the present disclosure, determining the first grasping policy of the robot manipulator based on a preset task includes:

[0039] Split the preset task into multiple subtasks, and determine the target object information corresponding to each subtask. Each subtask is relevant to each other;

[0040] Determine the first grasping policy of the robot manipulator based on the target object information corresponding to each subtask.

[0041] In this embodiment, to facilitate the robot manipulator in executing a preset task, the preset task is split into multiple relatively independent yet interrelated subtasks according to logic and process. Each subtask has its clear work content and goal. The target object information is various characteristic and status information of the target object related to each subtask.

[0042] The intelligent control method for the robot manipulator further includes:

[0043] Construct a task dependency graph according to the execution sequence and logic of each subtask, and determine the preconditions and postconditions of each subtask.

[0044] The first grasping strategy includes: during the execution of each subtask, when the current subtask is completed, automatically trigger other subtasks related to the current subtask according to the postconditions of the current subtask within the first time; when the current subtask fails, trace back to other subtasks related to the current subtask according to the preconditions of the current subtask and the task dependency graph.

[0045] In this embodiment, suppose the working scenario of the robot 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 3 hemostats (A, B, C) with different sizes but the same function, the second group of instruments includes 1 pair of forceps, and the third group of instruments includes 4 needle holders (a, b, c, d) with different specifications. Since hemostat A is used in combination with needle holder b, when the robot selects to pick up hemostat A, then when picking up the third group of instruments, it must select needle holder b related to hemostat A.

[0046] The working process of this embodiment is as follows:

[0047] After the robot determines the preset task, it needs to split the preset task more precisely according to its internal logic and process. Just like disassembling a complex jigsaw puzzle into multiple small pieces, each small piece is a subtask. Multiple subtasks are relatively independent but closely related. Each subtask has corresponding target object information and execution specifications. This information includes various characteristics and statuses of the target object, such as the shape, size, weight, material, position, and whether it is fragile of the object. After the robot determines the target object information corresponding to each subtask, it can comprehensively consider the performance and characteristics of the manipulator to determine the first grasping strategy of the robot manipulator. This strategy includes the way the manipulator grasps the target object, such as using clamping, adsorption, or other methods; the grasping position, whether it is to grasp the middle part, edge, or a specific handle of the object; the grasping force, which should be able to firmly grasp the object without damaging it; and parameters such as the grasping speed. For example, for fragile glass instruments, the grasping force should be gentle, and the speed should be slow and stable.

[0048] It can be concluded from the above that in this embodiment, by subdividing the preset task into multiple related subtasks and determining the specific target object information for each subtask, the first grasping strategy of the robotic arm can be accurately formulated. This method improves the flexibility and accuracy of task execution, ensures the effective operation of the robotic arm in different task stages, and thus enhances the overall work efficiency and task completion quality.

[0049] In an embodiment of the present disclosure, selecting the target grasping strategy corresponding to the first instruction information from the target strategy library includes:

[0050] Performing feature extraction on the first instruction information to obtain first key information;

[0051] Calculating the first similarity between the first key information and the applicable conditions of each grasping strategy in the target strategy library, and calculating the second similarity between the first key information and the key features of each grasping strategy in the target strategy library;

[0052] Calculating the target similarity based on the first similarity and the second similarity;

[0053] Selecting the target grasping strategy corresponding to the first instruction information from the target strategy library based on the target similarity.

[0054] In this embodiment, performing feature extraction on the first instruction information to obtain first key information includes:

[0055] If the first instruction information is voice information, converting the voice information into text information and performing feature extraction on the text information to obtain first key information;

[0056] If the first instruction information is key information, identifying the encoding of the key information to obtain the target key encoding, and obtaining the first key information based on the target key encoding.

[0057] In this embodiment, if the first instruction information is voice information, determining the vocabulary, grammar, and voice characteristics in the voice information, converting the voice information into text information based on the vocabulary, grammar, and voice characteristics in the voice information, and performing feature extraction on the text information to obtain first key information. The specific implementation method is as follows:

[0058] Using an audio processing algorithm to filter the first instruction information to obtain first voice information, detecting the endpoints of the first voice information, and determining the start position and end position of the first voice information to reduce the amount of data to be processed. Analyzing the voice signal using an acoustic model and a language model. The acoustic model can map voice features to a phoneme sequence, and the language model can convert the phoneme sequence into a vocabulary sequence according to the probability distribution of vocabulary and grammar rules. For example, using a deep neural network acoustic model and a statistical-based language model to analyze the voice signal frame by frame to identify the vocabulary therein.

[0059] Perform syntactic structure analysis on the recognized lexical sequence to determine the relationships between words and the structure of the sentence. Methods such as context-free grammar or dependency syntactic analysis can be used to analyze components such as the subject, predicate, and object of the sentence. Analyze features such as the intonation, speech rate, and stress of the speech. By extracting features such as the fundamental frequency, duration, and energy of the speech signal, judge the intonation changes and stress positions in the speech. For example, when a certain word in the speech has an increased fundamental frequency, an extended duration, and enhanced energy during pronunciation, it indicates that this word may be the location of the stress. Assist in understanding the semantic focus of the speech. In some cases, changes in stress and intonation may change the meaning of the sentence.

[0060] According to the results of lexical recognition, syntactic analysis, and speech feature analysis, convert the speech information into text information that can be recognized by a machine, and then extract features from this text information to obtain the first key information.

[0061] If the first instruction information is key information, identify the encoding of the key information. Different key combinations correspond to different instruction meanings. Establish a mapping table between key encodings and key information in advance. According to the recognized key encoding, look up the corresponding target object features, task-related information, and working environment information in the mapping table.

[0062] In this embodiment, the applicable conditions of the grasping strategy refer to the prerequisite conditions and environmental requirements that need to be met for a certain grasping strategy to be effectively implemented. These conditions are usually related to factors such as the task scenario, the basic attributes 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, etc. of the target object.

[0063] The key features of the grasping strategy refer to the unique feature parameters of each grasping strategy that play a key role in the execution of the grasping task. These features directly determine the specific operation methods and behavioral performances of the robotic arm when performing the grasping task. The key features can include grasping methods (such as clamping, adsorption, magnetic adsorption, etc.), grasping force, grasping speed, grasping position, the motion trajectory of the robotic arm, etc. Different combinations of key features constitute different grasping strategies to adapt to various different target objects and task requirements.

[0064] In this embodiment, the cosine similarity formula can be used to calculate the first similarity, the Euclidean distance can be used to calculate the second similarity, 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, then the values of the first weight and the second weight are dynamically adjusted according to the nature of the task.

[0065] 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 decreased to the second preset weight value; if the nature of the task is a complex task, the first weight is decreased 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.

[0066] In this embodiment, selecting the target grasping strategy corresponding to the first instruction information from the target policy library based on the target similarity includes:

[0067] The grasping strategies in the target policy library are initially sorted from high to low according to the target similarity to obtain the first sorted list, and an initial dynamic evaluation matrix is established. The rows of the matrix represent the grasping strategies in the policy library, and the columns represent multiple different dimensions of policy evaluation indicators. Each grasping strategy in the first sorted 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 scores of each grasping strategy in the first sorted list are 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.

[0068] The formula for calculating the comprehensive evaluation score is:

[0069]

[0070] where S represents the grasping strategy, represents the comprehensive evaluation score, i represents the i-th evaluation index, n represents the number of evaluation indexes, represents the weight of the i-th evaluation index, represents the score of the i-th evaluation index.

[0071] It can be concluded from the above that in this embodiment, by accurately extracting the key features of the first instruction information and comprehensively considering the applicability conditions and the similarity of the key features of the target grasping strategy, the purpose of accurately selecting the corresponding grasping strategy from the target policy library is achieved. At the same time, it supports multiple instruction input methods such as voice and keys, improving the flexibility and user-friendliness of the system.

[0072] In an embodiment of the present disclosure, the target grasping strategy includes the attributes of the target grasping object and the application scenario of the target grasping object;

[0073] Controlling the grasping force of the robot manipulator based on the target grasping strategy includes:

[0074] Determining the basic grasping force based on the attributes of the target grasping object; adjusting the basic grasping force according to the application scenario of the target grasping object to obtain the grasping force of the robot manipulator.

[0075] In this embodiment, the attributes of the target object to be grasped refer to various physical and chemical characteristics of the target object to be grasped, which will directly affect the force required for the robotic arm to grasp. Common attributes include, but are not limited to:

[0076] Material: Such as glass, plastic, metal, ceramic, etc. The mechanical properties such as hardness and toughness of objects with different materials are different, and the requirements for grasping force are also different. For example, glass materials are fragile and require a smaller grasping force; while metal materials are relatively strong and can withstand a larger grasping force.

[0077] Shape: The shape of the object will affect the contact area and stability of grasping, and thus affect the grasping force. For example, spherical objects are easy to roll and require more precise and appropriate grasping force to maintain stability; while cuboid-shaped objects are relatively easier to grasp, and the control of the grasping force can be relatively broad.

[0078] Weight: The weight of the object is one of the important factors determining the grasping force. Heavier objects require a greater grasping force to overcome gravity and ensure that they do not fall during the grasping and moving process.

[0079] The application scenario of the target object to be grasped refers to the environment and working conditions where the target object to be grasped is located, and these factors will also affect the grasping force of the robotic arm. The factors of the application scenario include, but are not limited to: space limitation, environmental temperature, and whether there is vibration, etc.

[0080] The basic grasping force is the grasping force initially determined based on the attributes of the target object to be grasped, and it is a basic grasping force value calculated or preset according to the attributes of the object such as material, shape, and weight without considering the influence of the working scenario. The grasping force of the robotic arm is the finally determined force used to control the robotic arm to actually perform the grasping task. It is obtained by comprehensively considering the working scenario factors of the target object to be grasped on the basis of the basic grasping force, and can ensure that the robotic arm safely and stably grasps the target object in a specific working scenario.

[0081] In this embodiment, by determining the basic grasping force through the attributes of the target object to be grasped and then adjusting the basic grasping force based on the application scenario of the target object to be grasped to obtain the grasping force of the robotic arm, the grasping force of the robotic arm can be made more accurate and reliable.

[0082] In an embodiment of the present disclosure, the intelligent control method of the robotic arm further includes:

[0083] Determining the first grasping speed of the robotic arm based on the target grasping strategy;

[0084] Correcting the first grasping speed based on the grasping force of the robotic arm to obtain the grasping speed of the robotic arm.

[0085] In this embodiment, determining the first grasping speed of the robotic arm based on the target grasping strategy includes: determining the first grasping speed of the robotic arm by using the rule matching method or the mechanical model calculation method based on the target grasping strategy. For the rule matching method, for example, a first corresponding rule table between the weight of the target grasping object and the first grasping speed is established in advance, or a second corresponding rule table between the material of the target grasping object and the first grasping speed is established in advance, or a third corresponding rule table between the shape of the target grasping object and the first grasping speed is established in advance. For example, for a fragile material (such as glass), a low-speed rule is established, such as setting the first grasping speed to 150 mm / s; for a solid material (such as metal), the speed can be appropriately increased to 400 mm / s. According to the recognized material information, the first grasping speed is determined from the second corresponding rule table. The mechanical model calculation method is to calculate the required force and acceleration during the grasping process according to Newton's mechanical principle, combined with parameters such as the mass and inertia of the target grasping object, and then deduce 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, a is the acceleration), and then the first grasping speed is determined in combination with the kinematic model of the robotic arm.

[0086] In this embodiment, correcting the first grasping speed based on the grasping force of the robotic arm to obtain the grasping speed of the robotic arm includes: correcting the first grasping speed based on the grasping force of the robotic arm and the grasping difficulty coefficient to obtain the grasping speed of the robotic arm. The specific implementation method is as follows: The grasping difficulty coefficient is comprehensively determined according to factors such as the surface roughness, shape complexity, and center of gravity stability of the target grasping object. A relationship model between the grasping difficulty coefficient and the speed correction ratio is established in advance. According to the calculated grasping difficulty coefficient, the corresponding speed correction ratio is obtained from this model. The first grasping speed is multiplied by this correction ratio and then corrected in combination with the grasping force to obtain a more accurate grasping speed of the robotic arm.

[0087] It can be concluded from the above that the grasping force of the robotic arm is controlled by comprehensively considering the attributes of the target grasping object and the application scenario. On the one hand, the basic grasping force is determined according to the physical characteristics of the grasping 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 item or affecting the operation efficiency, thereby realizing efficient and safe automated grasping operations.

[0088] In an embodiment of the present disclosure, the intelligent control method of the robotic arm further includes:

[0089] If the grasping force of the robot manipulator is greater than the first preset threshold, the grasping speed of the robot manipulator is obtained by correcting the first grasping speed based on the difference between the grasping force of the robot manipulator and the first preset threshold;

[0090] If the grasping force of the robot manipulator 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 manipulator; the first mapping table is a mapping table of grasping force and grasping speed.

[0091] In this embodiment, when the grasping force of the robot manipulator is greater than the first preset threshold, it indicates that the current grasping force is too large, which may damage the target object to be grasped or increase the burden on the manipulator. At this time, the system calculates the difference between the grasping force and the first preset threshold, and corrects the first grasping speed according to this difference. The larger the difference, the more the grasping force exceeds the normal range, and the greater the correction amplitude. Usually, the grasping speed is reduced to reduce the impact force and risk during the grasping process, and ensure the smooth progress of the grasping task.

[0092] When the grasping force of the robot manipulator is less than or equal to the first preset threshold, the system uses the first mapping table to correct the first grasping speed. The first mapping table pre - constructs the corresponding relationship between the grasping force and the grasping speed, taking into account factors such as the attributes of the target object to be grasped and the working scenario. The system finds the corresponding grasping speed correction value from the first mapping table according to the current grasping force, and then obtains the appropriate grasping speed of the robot manipulator, ensuring that the manipulator can complete the grasping task at the optimal speed under different grasping forces.

[0093] It can be concluded from the above that this embodiment ensures the accuracy and safety of the robot manipulator 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, improving the grasping efficiency and stability.

[0094] Corresponding to the robot manipulator intelligent control method in the above - mentioned embodiment, Figure 2 This is a structural block diagram of a robot manipulator intelligent control system provided by an embodiment of the present disclosure. For the sake of illustration, only the parts related to the embodiments of the present disclosure are shown. Refer to Figure 2 and the robot manipulator intelligent control system 20 includes: a strategy determination module 21, an update module 22, and a control module 23.

[0095] Among them, the strategy determination module 21 is used to determine the first grasping strategy of the robot manipulator based on a preset task;

[0096] An update module 22, configured to, in response to receiving first instruction information, select, from a target policy library, a target grasping policy corresponding to the first instruction information, and update the first grasping policy to the target grasping policy; the target policy library stores multiple grasping policies;

[0097] A control module 23, configured to control the grasping force of the robotic arm based on the target grasping policy.

[0098] In an embodiment of the present disclosure, the policy determination module 21 is specifically configured to:

[0099] Split a preset task into multiple subtasks, determine the target object information corresponding to each subtask, and there is a correlation between each subtask;

[0100] Determine a first grasping policy of the robotic arm based on the target object information corresponding to each subtask.

[0101] In an embodiment of the present disclosure, the update module 22 is specifically configured to:

[0102] Extract features from the first instruction information to obtain first key information;

[0103] Calculate a first similarity between the first key information and the applicable conditions of each grasping policy in the target policy library, and calculate a second similarity between the first key information and the key features of each grasping policy in the target policy library;

[0104] Calculate a target similarity based on the first similarity and the second similarity;

[0105] Select, from the target policy library, a target grasping policy corresponding to the first instruction information based on the target similarity.

[0106] In an embodiment of the present disclosure, the update module 22 is specifically configured to:

[0107] If the first instruction information is voice information, convert the voice information into text information, and extract features from the text information to obtain first key information;

[0108] If the first instruction information is key information, identify the encoding of the key information to obtain a target key encoding, and obtain first key information based on the target key encoding.

[0109] In an embodiment of the present disclosure, the target grasping policy includes the attributes of the target grasping object and the application scenario of the target grasping object;

[0110] The control module 23 is specifically configured to:

[0111] Determine a basic grasping force based on the attributes of the target grasping object; adjust the basic grasping force according to the application scenario of the target grasping object to obtain the grasping force of the robotic arm.

[0112] In one embodiment of the present disclosure, the control module 23 is further specifically configured to:

[0113] Determine a first grasping speed of the robotic arm based on the target grasping strategy;

[0114] Correct the first grasping speed based on the grasping force of the robotic arm to obtain the grasping speed of the robotic arm.

[0115] In one embodiment of the present disclosure, the control module 23 is further specifically configured to:

[0116] If the grasping force of the robotic arm is greater than a first preset threshold, correct the first grasping speed based on the difference between the grasping force of the robotic arm and the first preset threshold to obtain the grasping speed of the robotic arm;

[0117] If the grasping force of the robotic arm is less than or equal to the first preset threshold, correct the first grasping speed based on the first mapping table to obtain the grasping speed of the robotic arm; the first mapping table is a mapping table of grasping force and grasping speed.

[0118] See Figure 3 , Figure 3 which is a schematic block diagram of a robot provided in an embodiment of the present disclosure. As Figure 3 shown, the robot 300 in this embodiment 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 above-mentioned processors 301, input devices 302, output devices 303, and memories 304 communicate with each other through a communication bus 305. The memory 304 is used to store a computer program, and the computer program includes program instructions. The processor 301 is configured to execute the program instructions stored in the memory 304. Among them, 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 the modules 21 to 23 shown.

[0119] It should be understood that in the embodiments of the present disclosure, the so-called processor 301 may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0120] The input device 302 may include a touchpad, a fingerprint acquisition sensor (for acquiring the fingerprint information and the direction information of the fingerprint of the user), a microphone, etc., and the output device 303 may include a display (such as an LCD), a speaker, etc.

[0121] The memory 304 may include a read-only memory and a random access memory, and provide instructions and data to the processor 301. A part 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.

[0122] In specific implementation, the processor 301, the input device 302, and the output device 303 described in the embodiments of the present disclosure may execute the implementation manners described in the first embodiment and the second embodiment of the intelligent control method for the robotic manipulator provided by the embodiments of the present disclosure, and may also execute the implementation manner of the robot described in the embodiments of the present disclosure, which will not be elaborated herein.

[0123] In another embodiment of the present disclosure, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program, and the computer program includes program instructions. When the program instructions are executed by a processor, all or part of the processes in the methods of the above embodiments are implemented. It can also be completed by instructing related hardware through the computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0124] The computer-readable storage medium can be the internal storage unit of the robot in any of the foregoing embodiments, such as the hard disk or memory of the robot. The computer-readable storage medium can also be an external storage device of the robot, such as a plug-in hard disk equipped on the robot, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Further, the computer-readable storage medium can also include both the internal storage unit and the external storage device of the robot. The computer-readable storage medium is used to store the computer program and other programs and data required by the robot. The computer-readable storage medium can also be used to temporarily store the data that has been output or will be output.

[0125] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the components and steps of the examples have been generally described according to their functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present disclosure.

[0126] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described robot and units can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0127] In several embodiments provided by the present application, it should be understood that the disclosed robot and method can be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed coupling or direct coupling or communication connection to each other can be an indirect coupling or communication connection through some interfaces or units, and can also be an electrical, mechanical or other form of connection.

[0128] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiments of the present disclosure.

[0129] In addition, each functional unit in various embodiments of the present disclosure can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0130] The above is only the specific implementation manner of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present disclosure can easily think of various equivalent modifications or substitutions, and these modifications or substitutions should be covered within the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be subject to the protection scope of the claims.

Claims

1. An intelligent control method for a robotic manipulator, characterized in that, Including: Determine a first grasping strategy for the robotic arm of the robot based on a preset task; In response to receiving the first instruction information, select a target grasping strategy corresponding to the first instruction information from the target strategy library, and update the first grasping strategy to the target grasping strategy; A variety of grasping strategies are stored in the target strategy library; Control the grasping force of the robotic arm of the robot based on the target grasping strategy; The method further includes: determining a first grasping speed of the robotic arm of the robot based on the target grasping strategy; Modify the first grasping speed based on the grasping force of the robotic arm of the robot to obtain the grasping speed of the robotic arm of the robot; If the grasping force of the robotic arm of the robot is greater than a first preset threshold, modify the first grasping speed based on the difference between the grasping force of the robotic arm of the robot and the first preset threshold to obtain the grasping speed of the robotic arm of the robot; If the grasping force of the robotic arm of the robot is less than or equal to the first preset threshold, modify the first grasping speed based on the first mapping table to obtain the grasping speed of the robotic arm of the robot; the first mapping table is a mapping table of grasping force and grasping speed.

2. The intelligent control method for a robotic manipulator according to claim 1, characterized in that, The determining a first grasping strategy for the robotic arm of the robot based on a preset task includes: Split the preset task into multiple subtasks, determine the target object information corresponding to each subtask, and there is a correlation between each subtask; Determine a first grasping strategy for the robotic arm of the robot based on the target object information corresponding to each subtask.

3. The intelligent control method for a robotic manipulator according to claim 1, characterized in that, The selecting a target grasping strategy corresponding to the first instruction information from the target strategy library based on the first instruction information includes: Extract features from the first instruction information to obtain first key information; Calculate a first similarity between the first key information and the applicable conditions of each grasping strategy in the target strategy library, and calculate a second similarity between the first key information and the key features of each grasping strategy in the target strategy library; Calculate a target similarity based on the first similarity and the second similarity; Select a target grasping strategy corresponding to the first instruction information from the target strategy library based on the target similarity.

4. The intelligent control method of the robotic manipulator according to claim 3, characterized in that, The 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 extract features from the text information to obtain first key information; If the first instruction information is key information, identify the encoding of the key information to obtain a target key encoding, and obtain first key information based on the target key encoding.

5. The intelligent control method of the robot manipulator according to claim 1, characterized in that The target grasping strategy includes the attributes of the target grasping object and the working scenario of the target grasping object; The controlling the grasping force of the robotic arm of the robot based on the target grasping strategy includes: Determine a basic grasping force based on the attributes of the target grasping object; adjust the basic grasping force based on the working scenario of the target grasping object to obtain the grasping force of the robotic arm of the robot.

6. An intelligent control system for a robotic manipulator, characterized in that, Including: A strategy determination module, configured to determine a first grasping strategy for the robotic arm of the robot based on a preset task; An update module, configured to, in response to receiving first instruction information, select a target grasping strategy corresponding to the first instruction information from a target policy library, and update the first grasping strategy to the target grasping strategy; a plurality of grasping strategies are stored in the target policy library; A control module, configured to control the grasping force of the robot manipulator based on the target grasping strategy; The control module is specifically further configured to determine a first grasping speed of the robot manipulator based on the target grasping strategy; The grasping speed of the robot manipulator is obtained by correcting the first grasping speed based on the grasping force of the robot manipulator; If the grasping force of the robot manipulator is greater than a first preset threshold, the grasping speed of the robot manipulator is obtained by correcting the first grasping speed based on the difference between the grasping force of the robot manipulator and the first preset threshold; If the grasping force of the robot manipulator is less than or equal to the first preset threshold, the grasping speed of the robot manipulator is obtained by correcting the first grasping speed based on a first mapping table; the first mapping table is a mapping table of grasping force and grasping speed.

7. 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 5 are implemented.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images