Body-equipped robot end gripping adjustment method, device and medium

Abstract

This invention provides a method, apparatus, and medium for adjusting the end-effector gripping mechanism of an embodied robot, comprising: in response to a start signal of the end-effector gripping device of the embodied robot, acquiring force data and gripping mechanism parameters of the end-effector gripping mechanism, and inputting the force data and gripping mechanism parameters into a pre-trained gripping stress state recognition model to obtain gripping stress state information, wherein the gripping mechanism parameters include at least: the elastic modulus, compressive strength, contact area, and gripping stroke of the gripping mechanism, and the gripping stress state information includes: risk state and safe state; based on the gripping stress state information, determining an adjustment mode, the adjustment mode being used to adjust the force data to target gripping stress data, wherein the adjustment mode includes: adjustment mode and fixed mode; in response to the adjustment mode, generating a control instruction set, the control instruction set being used to control the gripping component of the end-effector gripping mechanism to move to a target position adapted to the target gripping stress data.

Description

Technical Field

[0001] This invention relates to the field of end-effector gripping technology for automata, and more specifically, to an end-effector gripping adjustment method, device, and medium for automata. Background Technology

[0002] As a key component of industrial robots that directly contact workpieces and perform tasks such as clamping, handling, and assembly, the end effector of omnidirectional robots directly affects the quality of operation and the safety of the workpiece. Currently, most existing end effector devices for omnidirectional robots employ fixed, preset clamping forces or manual adjustments, lacking intelligent stress monitoring and adaptive control. Traditional clamping devices cannot detect the contact stress state between the end effector and the workpiece in real time, and cannot effectively distinguish between risky and safe states during clamping. They can only rely on preset clamping forces or positions to achieve clamping fixation, and cannot adjust stress parameters in real time based on differences in workpiece material, surface conditions, and dynamic disturbances during operation. In scenarios where omnidirectional robots perform high-speed handling, complex trajectory movements, or workpieces with large dimensional tolerance fluctuations, the clamping mechanism is prone to stress imbalance: on the one hand, excessive clamping stress may lead to surface indentations, deformation, or even internal structural damage to the workpiece; on the other hand, insufficient clamping stress may cause the workpiece to loosen, shift, or even fall off, seriously affecting operational safety and reliability. Meanwhile, the undifferentiated adjustment mode of traditional equipment cannot achieve targeted stress calibration and stable locking, resulting in poor adaptability. It is difficult to meet the high precision and high stability control requirements of the end effector of the robot in the precision manufacturing field, and the workpiece clamping damage rate and drop rate remain high.

[0003] There is currently no effective solution to the above problems. Summary of the Invention

[0004] The main objective of this invention is to provide a method, device, and medium for adjusting the end-effector gripping of a robot, in order to solve the technical problem that existing end-effector gripping devices for robots cannot identify gripping stress risks and safety conditions, and cannot adaptively switch adjustment modes.

[0005] According to one aspect of the present invention, in order to achieve the above-mentioned objective, a method for adjusting the end-effector gripping mechanism of an embodied robot is provided, comprising: in response to a start signal of the end-effector gripping device of the embodied robot, acquiring force data and gripping mechanism parameters of the end-effector gripping mechanism, and inputting the force data and gripping mechanism parameters into a pre-trained gripping stress state recognition model to obtain gripping stress state information, wherein the gripping mechanism parameters include at least: the elastic modulus, compressive strength, contact area, and gripping stroke of the gripping mechanism, and the gripping stress state information includes: a risk state and a safe state; based on the gripping stress state information, determining an adjustment mode, the adjustment mode being used to adjust the force data to target gripping stress data, wherein the adjustment mode includes: an adjustment mode and a fixed mode; in response to the adjustment mode, generating a control instruction set, the control instruction set being used to control the gripping member of the end-effector gripping mechanism to move to a target position adapted to the target gripping stress data.

[0006] Furthermore, before inputting the force data and clamping mechanism parameters into the pre-trained clamping stress state recognition model, the process includes: obtaining a sample dataset, wherein the sample dataset includes multiple sets of sample data, each set of sample data including historical force data, historical clamping mechanism parameters and corresponding clamping stress state labels; constructing an initial neural network model; and training the initial neural network model using the sample dataset to obtain the clamping stress state recognition model.

[0007] Furthermore, the initial neural network model is trained using a sample dataset to obtain a clamping stress state recognition model, including: dividing the sample dataset into a training set and a validation set; iteratively training the initial neural network model using the training set and validating the trained initial neural network model using the validation set; and determining the trained initial neural network model as the clamping stress state recognition model in response to successful validation.

[0008] Furthermore, based on the clamping stress state information, the adjustment mode is determined, including: when the clamping stress state information is in a risk state, the adjustment mode is determined to be an adjustment mode; when the clamping stress state information is in a safe state, the adjustment mode is determined to be a fixed mode.

[0009] Furthermore, the adjustment mode includes: determining the adjustment direction of the clamping component based on the deviation between the force data and the target clamping stress data, and generating an adjustment instruction set step by step according to a preset step size. The adjustment instruction set is used to match the force data with the target clamping stress data until the force data matches the target clamping stress data.

[0010] Furthermore, an adjustment instruction set is generated sequentially according to a preset step size, including: obtaining the current deviation value between the current force data and the target clamping stress data; determining the current adjustment step size based on the current deviation value, wherein the current adjustment step size is positively correlated with the current deviation value; and generating an adjustment instruction set in response to the current adjustment step size.

[0011] Furthermore, the fixed mode includes: keeping the current position of the clamping component unchanged and continuously monitoring the force data; when the deviation of the force data from the target clamping stress data exceeds a preset deviation threshold, the adjustment mode is re-triggered.

[0012] Furthermore, in the process of generating adjustment instruction sets step by step according to preset step size, the process also includes: after each generation of adjustment instruction sets, reacquiring the force data and recalculating the current deviation value between the force data and the target clamping stress data; when the current deviation value is less than the preset deviation threshold, stopping the generation of adjustment instruction sets and switching the current adjustment mode to fixed mode.

[0013] According to one embodiment of the present invention, an end-effector gripping adjustment device for a unibody robot is also provided, comprising: an acquisition module, configured to acquire force data and gripping mechanism parameters of the end-effector gripping mechanism in response to a working start signal of the end-effector gripping device, and input the force data and gripping mechanism parameters into a pre-trained gripping stress state recognition model to obtain gripping stress state information, wherein the gripping mechanism parameters include at least: the elastic modulus, compressive strength, contact area, and gripping stroke of the gripping mechanism, and the gripping stress state information includes: a risk state and a safe state; a determination module, configured to determine an adjustment mode based on the gripping stress state information, the adjustment mode being used to adjust the force data to target gripping stress data, wherein the adjustment mode includes: an adjustment mode and a fixed mode; and a generation module, configured to generate a control instruction set in response to the adjustment mode, the control instruction set being used to control the gripping member of the end-effector gripping mechanism to move to a target position adapted to the target gripping stress data.

[0014] According to another aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored executable program, wherein, when the executable program is executed, it controls the device where the computer-readable storage medium is located to perform the methods of various embodiments of the present invention.

[0015] By applying the technical solution of this invention, in response to the start signal of the end-effector gripping device of the embodied robot, force data and gripping mechanism parameters are acquired and input into a pre-trained neural network model. This model accurately identifies the gripping stress risk and safety status of the end-effector gripping mechanism. Based on real-time gripping stress data, it can adaptively match adjustment or fixed modes and generate a dedicated control instruction set to drive the gripper to move precisely to a position suitable for the target stress, achieving intelligent, dynamic, and precise control of gripping stress. This adjustment method completely overcomes the shortcomings of traditional equipment's lagging gripping stress control and singular adjustment. It avoids workpiece crushing damage caused by stress overload and eliminates loosening and detachment problems caused by insufficient stress. It can perfectly adapt to the gripping needs of workpieces of different materials and different working conditions, solving the technical problem that existing end-effector gripping devices of embodied robots cannot identify gripping stress risk and safety status and cannot adaptively switch adjustment modes. Attached Figure Description

[0016] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0017] Figure 1 This is a flowchart of a method for adjusting the end effector of a robot according to one embodiment of the present invention;

[0018] Figure 2 This is a structural block diagram of an end-effector gripping and adjusting device for a robot according to one embodiment of the present invention. Detailed Implementation

[0019] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0020] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0021] According to an embodiment of the present invention, an embodiment of a method for adjusting the end effector gripper of a robot is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0022] This method embodiment can be executed in an electronic device or similar computing device that includes a memory and a processor. Taking operation on a vehicle terminal as an example, the vehicle terminal may include one or more processors (processors may include, but are not limited to, central processing units (CPUs), graphics processing units (GPUs), digital signal processing (DSP) chips, microcontroller units (MCUs), field-programmable gate arrays (FPGAs), neural network processors (NPUs), tensor processors (TPUs), artificial intelligence (AI) type processors, etc.) and a memory for storing data. Optionally, the vehicle terminal may also include transmission devices, input / output devices, and display devices for communication functions. Those skilled in the art will understand that the above structural description is merely illustrative and does not limit the structure of the vehicle terminal. For example, the vehicle terminal may include more or fewer components than described above, or have a different configuration than described above.

[0023] The memory can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the automaton gripping and adjustment method for the automaton in this embodiment of the invention. The processor executes various functional applications and data processing by running the computer program stored in the memory, thereby realizing the aforementioned automaton gripping and adjustment method for the automaton. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to the mobile terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0024] The transmission device is used to receive or send data via a network. Specific examples of the network mentioned above may include a wireless network provided by the mobile terminal's communication provider. In one example, the transmission device includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device may be a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0025] Display devices can be, for example, touchscreen liquid crystal displays (LCDs) and touch displays (also referred to as "touchscreens" or "touch displays"). The LCD allows users to interact with the user interface of the mobile terminal. In some embodiments, the mobile terminal has a graphical user interface (GUI), which allows users to interact with the GUI through finger contact and / or gestures on a touch-sensitive surface. Optional human-computer interaction functions include: creating web pages, drawing, word processing, creating electronic documents, playing games, video conferencing, instant messaging, sending and receiving emails, call interfaces, playing digital video, playing digital music, and / or web browsing, etc. Executable instructions for performing the above human-computer interaction functions are configured / stored in one or more processor-executable computer program products or readable storage media.

[0026] Figure 1 This is a flowchart of a method for adjusting the end effector of a robot according to one embodiment of the present invention, such as... Figure 1 As shown, the method includes the following steps:

[0027] Step S110: In response to the start signal of the end-effector gripping device of the robot, acquire the force data and gripping mechanism parameters of the end-effector gripping mechanism, and input the force data and gripping mechanism parameters into the pre-trained gripping stress state recognition model to obtain gripping stress state information;

[0028] In step S110, before the embodied robot's end effector gripper officially begins gripping operations, the entire equipment is in a standby state. All mechanical structures, data acquisition modules, and control modules complete preliminary self-checks and parameter initializations to ensure stable operation of subsequent actions and data processing flows. When the embodied robot moves the end effector gripper to the vicinity of the target workpiece and completes the initial closure of the gripper, making contact between the gripper and the workpiece surface, the on-site personnel or the automatic control system will trigger the corresponding start signal for the embodied robot's end effector gripper. This start signal will be immediately transmitted to the equipment's built-in control system, serving as the trigger condition for the formal start of the entire adjustment process.

[0029] Upon receiving the start signal from the end-effector, the equipment control system immediately initiates a status monitoring process for the end-effector. The core task is to acquire the force data and corresponding parameters of the end-effector during its operation. The end-effector is the core component that directly contacts the workpiece, enabling clamping, fixing, and handling. The magnitude and trend of stress generated within it and at its contact points directly affect the safety of the workpiece during clamping and handling, and also determine the subsequent adjustment actions that the robot needs to perform.

[0030] In acquiring the force data and parameters of the end effector, it is first necessary to comprehensively collect various basic data during equipment operation. Force data directly reflects the magnitude and distribution of the force exerted by the end effector at the contact point with the workpiece, serving as the fundamental basis for judging the mechanism's working state. Specifically, the force data of the end effector is collected by multi-dimensional force sensors located at the connection point between the gripper and the robot, or directly on the inner contact surface of the gripper. These sensors simultaneously acquire force components in three orthogonal directions and torque components around these three orthogonal directions, thus comprehensively reflecting the complete mechanical information of the contact force between the gripper and the workpiece. The analog signals acquired by the multi-dimensional force sensors are amplified and filtered by a signal conditioning circuit, then converted into digital signals by an analog-to-digital converter and transmitted to the control system processor as the raw force data for subsequent processing.

[0031] The clamping mechanism parameters are inherent attribute parameters pre-entered and stored in the control system's storage unit before the equipment leaves the factory and is used. These parameters include several core components, at least covering the clamping mechanism's elastic modulus, compressive strength, contact area, and clamping stroke. The elastic modulus reflects the ease with which the material undergoes elastic deformation; the compressive strength represents the maximum compressive load the mechanism can withstand; the contact area is the area where the clamping structure and the workpiece are in contact; and the clamping stroke is the effective range of adjustable distance for the clamping mechanism. These parameters collectively form the foundation for subsequent stress state identification and judgment by the neural network model. Optionally, the clamping mechanism parameters may also include parameters such as the material density of the clamping mechanism, Poisson's ratio, and the coefficient of friction between the clamping element and the workpiece contact surface to further improve the accuracy of model recognition.

[0032] After real-time acquisition of force data and reading of clamping mechanism parameters, the equipment control system inputs the force data and clamping mechanism parameters into a pre-trained clamping stress state recognition model. This clamping stress state recognition model is an artificial intelligence model based on neural networks. It has been trained and validated offline before the equipment was put into use and can automatically identify and output the current clamping stress state of the end clamping mechanism based on the input force data and clamping mechanism parameters. The model's input layer receives pre-processed force data (including multi-dimensional force and torque information) and various clamping mechanism parameters. After feature extraction and nonlinear mapping in at least one hidden layer, the output layer outputs the corresponding clamping stress state classification result.

[0033] Based on the clamping stress state recognition model, the final output clamping stress state information is divided into two categories: risk state and safe state. When the model identifies a risk state, it indicates that the current stress change rate or absolute stress value of the clamping mechanism exceeds the safe range, and the stress state of the mechanism is abnormal, requiring immediate stress adjustment. When the model identifies a safe state, it means that the stress change of the current clamping mechanism is stable, and all indicators are within a reasonable range, requiring no additional stress adjustment. This neural network-based recognition logic can accurately distinguish the operating state of the mechanism, providing reliable support for subsequent mode adjustments.

[0034] Based on the above step S110, in this embodiment of the invention, after the end-effector gripping device of the embodied robot is activated, force data and gripping mechanism parameters are acquired and input into a pre-trained neural network model, thereby achieving accurate identification of gripping stress risk state and safety state, providing a reliable data basis and judgment basis for determining the subsequent adaptive adjustment mode.

[0035] Step S120: Based on the clamping stress state information, determine the adjustment mode. The adjustment mode is used to adjust the force data to the target clamping stress data.

[0036] In step S120, after determining the clamping stress state information of the end-clamping mechanism, the equipment will proceed with the next step based on the acquired clamping stress state information to determine the corresponding adjustment mode. Different clamping stress states correspond to different operating logics, and the selected adjustment mode will serve as the core basis for the subsequent mechanism actions, ensuring that the clamping operation always conforms to the safety specifications for workpiece handling and processing.

[0037] After receiving the clamping stress state information output by the clamping stress state recognition model, the equipment control system first identifies and judges this information to determine the specific stress state of the current clamping mechanism. In this embodiment, the clamping stress state information is clearly divided into two categories with different risk levels: a risky state and a safe state. The control system automatically adapts the corresponding adjustment mode based on the recognition results to ensure that the control of clamping stress is more targeted and reasonable.

[0038] The core function of all the adjustment modes set up in this system is to correct and control the current force data of the end-effector clamping mechanism, ultimately matching the force data with the preset target clamping stress data. The target clamping stress data is a pre-set standard value that combines the workpiece material protection requirements, the clamping mechanism's load-bearing capacity, and the need to prevent slippage during handling operations; it represents the ideal working state that the clamping mechanism needs to maintain. The target clamping stress data can be differentiated according to parameters such as the weight, shape, material hardness, and surface roughness of different workpieces, and is entered into the control system's storage unit before the equipment operates.

[0039] Specifically, when the clamping stress state information is in a risky state, it indicates that the stress change rate or absolute value of the current end-effector clamping mechanism exceeds the safe range, and there is an abnormal contact stress between the mechanism and the workpiece. This may cause indentation, deformation, or even internal structural damage to the workpiece surface, or displacement of the workpiece during clamping due to uneven stress distribution. In this case, the control system determines the adjustment mode to be the regulating mode. When the clamping stress state information is in a safe state, it means that the stress change of the current end-effector clamping mechanism is stable, and all indicators are within a reasonable range. The contact stress neither exceeds the upper limit of the compressive strength of the workpiece material nor falls below the minimum stress threshold required to reliably fix the workpiece. In this case, the control system determines the adjustment mode to be the fixed mode. By distinguishing and judging the stress state information and accurately selecting the corresponding adjustment mode, the stress of the clamping mechanism can be effectively kept within a reasonable range, providing reliable protection for workpiece clamping and handling.

[0040] Furthermore, when the control system determines the adjustment mode to be adjustment mode, the equipment enters the active stress calibration process. In this process, the control system first calculates the deviation between the current force data and the target clamping stress data. The deviation is calculated by comparing the actual force data collected by the multi-dimensional force sensor with the pre-stored target clamping stress data item by item, and obtaining the difference between the two as the deviation value. This deviation value can be positive or negative; a positive value indicates that the current clamping stress is greater than the target value, and a negative value indicates that the current clamping stress is less than the target value.

[0041] After calculating the deviation value, the control system determines the adjustment direction of the clamping component based on the sign of the deviation value. Specifically, a positive deviation value indicates that the current clamping stress is too high, requiring the clamping component to move in the releasing direction to reduce the clamping stress; a negative deviation value indicates that the current clamping stress is insufficient, requiring the clamping component to move in the clamping direction to increase the clamping stress. After determining the adjustment direction, the control system generates adjustment commands sequentially according to a preset step size. The preset step size can be a fixed step size value pre-set at the factory based on the mechanical characteristics and control accuracy requirements of the clamping mechanism, or a variable step size value dynamically determined based on the current deviation value.

[0042] As a preferred implementation, during the process of generating adjustment commands sequentially according to a preset step size, the control system does not use a fixed step size value. Instead, it dynamically determines the current adjustment step size for each adjustment based on the current deviation value. Specifically, the control system acquires the current deviation value between the current force data and the target clamping stress data, and then determines the current adjustment step size based on this deviation value. The current adjustment step size is positively correlated with the current deviation value; that is, the larger the deviation value, the larger the adjustment step size, and the smaller the deviation value, the smaller the adjustment step size. This achieves a step-by-step approximation strategy combining coarse and fine adjustment. When the deviation is large, a large step size is used to quickly reduce the deviation; when the deviation is small, a small step size is used to accurately approximate the target value, thereby improving adjustment accuracy while ensuring adjustment efficiency. After determining the current adjustment step size, the control system generates the corresponding adjustment command according to the current adjustment step size, driving the clamping component to move according to that step size.

[0043] After each adjustment command is generated and the clamping component is moved, the control system reacquires the force data and recalculates the current deviation between the force data and the target clamping stress data. This determines the adjustment effect and whether further adjustment is needed. When the calculated current deviation value is less than a preset deviation threshold, it indicates that the current force data is sufficiently close to the target clamping stress data, and the clamping stress meets the accuracy requirements. At this point, the control system stops generating adjustment commands and switches the current adjustment mode from adjustment mode to fixed mode, ensuring the clamping mechanism remains stably in the current clamping position.

[0044] Furthermore, when the control system determines the adjustment mode to be fixed, the equipment enters the stress stabilization and holding process. In fixed mode, the core task of the control system is no longer to actively adjust the position of the clamping component, but to maintain the current position of the clamping component, so that the clamping mechanism continues to clamp the workpiece under the current stress state. However, in scenarios where the embodied robot performs high-speed handling, complex trajectory movements, or encounters external disturbances, the contact stress between the clamping mechanism and the workpiece may fluctuate due to inertial forces, centrifugal forces, or external impacts.

[0045] Therefore, even in fixed mode, the control system still needs to continuously monitor the force data using multi-dimensional force sensors to ensure that the stress fluctuation amplitude remains within an acceptable range. The control system compares the monitored force data with the target clamping stress data in real time and calculates the deviation between the two. When the deviation value does not exceed a preset deviation threshold, it indicates that the stress fluctuation is within a reasonable range and will not affect the stability and safety of clamping; the control system continues to maintain the fixed mode. When the deviation value exceeds the preset deviation threshold, it indicates that the stress fluctuation has exceeded the safe range, and there is a risk of clamping failure. At this time, the control system automatically re-triggers the adjustment mode and executes the above active calibration process again to readjust the force data back to near the target clamping stress data.

[0046] Based on the above step S120, in this embodiment of the invention, after obtaining the clamping stress state information, the adjustment mode or the fixed mode is automatically determined according to the distinction between the risk state and the safe state. In the adjustment mode, the adjustment direction and adjustment step size are determined according to the deviation value to gradually approach the target value. In the fixed mode, continuous monitoring is performed and the adjustment is re-triggered when the deviation threshold is exceeded. This realizes intelligent, dynamic and precise control of clamping stress, which not only avoids workpiece damage caused by stress overload, but also eliminates the problem of workpiece loosening and falling off caused by insufficient stress.

[0047] Step S140: In response to the adjustment mode, a control instruction set is generated. The control instruction set is used to control the clamping member of the end clamping mechanism to move to a target position that matches the target clamping stress data.

[0048] In step S140, after determining the corresponding adjustment mode, the device generates a matching control instruction set based on the currently selected adjustment mode. This control instruction set serves as the direct basis for action execution, primarily driving the clamping component of the end-effector to move according to a predetermined strategy, ultimately stopping the clamping component at a target position that matches the target clamping stress data. This maintains the clamping stress of the end-effector within the standard range, achieving reliable clamping and fixation of the workpiece. The control instruction set specifically includes parameters such as the target position coordinates of the clamping component, moving speed, acceleration, adjustment direction, and adjustment step size. These parameters vary depending on the current adjustment mode.

[0049] Specifically, when the control system determines that the current adjustment mode is adjustment mode, the equipment enters the active stress calibration command generation process. The control system first determines the adjustment direction of the clamping component based on the deviation between the current force data and the target clamping stress data. The deviation is calculated by comparing the actual force data collected by the multi-dimensional force sensor with the pre-stored target clamping stress data item by item, and obtaining the difference between the two as the deviation value. When the deviation value is positive, it indicates that the current clamping stress is greater than the target value, and the clamping component needs to be controlled to move in the releasing direction to reduce the clamping stress; when the deviation value is negative, it indicates that the current clamping stress is less than the target value, and the clamping component needs to be controlled to move in the clamping direction to increase the clamping stress.

[0050] After determining the adjustment direction, the control system generates an adjustment command according to a preset step size. The preset step size can be a fixed value pre-set at the factory based on the mechanical characteristics and control accuracy requirements of the clamping mechanism. As a preferred implementation, the control system can also dynamically determine the current adjustment step size based on the magnitude of the current deviation value. The current adjustment step size is positively correlated with the current deviation value; that is, the larger the deviation value, the larger the adjustment step size, and vice versa. The control system generates a corresponding adjustment command based on the adjustment direction and the current adjustment step size. This adjustment command is a core component of the control command set. The adjustment command is transmitted to the actuator that drives the clamping component. The actuator can include drive elements such as servo motors, stepper motors, cylinders, or hydraulic cylinders, and their associated transmission mechanisms. Upon receiving the adjustment command, the actuator drives the clamping component to perform the corresponding movement according to the adjustment direction and adjustment step size specified in the command.

[0051] The aforementioned adjustment process is not completed in one step, but rather is a cyclical process of successive approximations. Each time the control system generates an adjustment command and drives the clamping component to move, it reacquires the force data and recalculates the current deviation between the force data and the target clamping stress data. If the current deviation is still large, the control system continues to generate the next adjustment command and drives the clamping component to move again, until the force data matches the target clamping stress data. During this cycle, the control command set is dynamically updated based on the recalculated deviation value, ensuring that each round of adjustment generates corresponding control parameters based on the latest force state. When the calculated current deviation value is less than a preset deviation threshold, it indicates that the force data is sufficiently close to the target clamping stress data, and the clamping stress meets the accuracy requirements. At this point, the control system stops generating adjustment commands and switches the current adjustment mode from adjustment mode to fixed mode.

[0052] When the control system determines that the current adjustment mode is fixed, the equipment enters the stress stabilization and holding command generation process. In fixed mode, the control system generates a set of holding commands, which are used to control the clamping component to remain in its current position without actively adjusting its position, so that the clamping mechanism continues to clamp the workpiece under the current stress state. The holding command includes current position locking parameters and a zero displacement command. After receiving the holding command, the actuator maintains the current output torque or output force unchanged, so that the clamping component remains stably in its current position.

[0053] However, in scenarios where embodied robots perform high-speed handling, complex trajectory movements, or encounter external disturbances, the contact stress between the clamping mechanism and the workpiece may fluctuate due to inertial forces, centrifugal forces, or external impacts. Even in fixed mode, the control system still needs to continuously monitor the force data through multi-dimensional force sensors and compare the monitored force data with the target clamping stress data in real time to calculate the deviation value between the two. When the deviation value does not exceed the preset deviation threshold, the control system continues to maintain the fixed mode and continuously generates holding commands. When the deviation value exceeds the preset deviation threshold, it indicates that the stress fluctuation has exceeded the safe range, and there is a risk of clamping failure. At this time, the control system automatically triggers the current adjustment mode from fixed mode back to adjustment mode, and generates a control command set in adjustment mode again, re-executes the active calibration process, and readjusts the force data back to near the target clamping stress data.

[0054] It is worth noting that throughout the adjustment process, the control system reacquires the force data and recalculates the deviation value after each adjustment command is generated, realizing a closed-loop control of "acquisition—judgment—adjustment—reacquisition—rejudgment—readjustment". This closed-loop control method ensures the effectiveness of each adjustment and prevents stress deviation caused by insufficient or excessive adjustment in a single instance. Each newly generated adjustment command is an update and optimization of the previous adjustment command. The entire control command set is continuously iterated and updated as the adjustment process progresses until the deviation between the force data and the target clamping stress data converges to within the preset deviation threshold. At this point, the control command set is finalized, and the clamping component stably remains at the target position that matches the target clamping stress data.

[0055] After the clamping component reaches the target position, the control system will continue to monitor the matching degree between the force data and the target clamping stress data. If the deviation value exceeds the preset deviation threshold again due to external disturbances during subsequent operations, the control system will trigger the adjustment mode again, generate a new set of control commands to drive the clamping component to move to the new target position, thereby ensuring that the clamping stress is always maintained within a safe and reasonable range throughout the entire clamping and handling operation cycle.

[0056] Based on the above step S140, in this embodiment of the invention, after determining the adjustment mode, a corresponding control instruction set is generated. In the adjustment mode, adjustment instructions are generated sequentially according to the deviation value until the force data matches the target value. In the fixed mode, a holding instruction is generated and the deviation value is continuously monitored. When the threshold is exceeded, the adjustment is re-triggered and the instruction set is updated. This achieves precise closed-loop control of the clamping position, ensuring that the clamping part always stays at the target position that matches the target clamping stress data, which greatly improves the stability and safety of clamping.

[0057] Based on steps S110 to S140 above, in this embodiment of the invention, by responding to the start signal of the end-effector gripping device of the embodied robot, force data and gripping mechanism parameters are acquired and input into a pre-trained neural network model. This accurately identifies the gripping stress risk and safety status of the end-effector gripping mechanism. It can adaptively match the adjustment mode or the fixed mode based on real-time gripping stress data and generate a dedicated control instruction set to drive the gripper to move precisely to the position suitable for the target stress, thus achieving intelligent, dynamic, and precise control of the gripping stress. This adjustment method completely overcomes the shortcomings of traditional equipment's lagging gripping stress control and singular adjustment. It can avoid workpiece crushing damage caused by stress overload and eliminate loosening and detachment problems caused by insufficient stress. It can perfectly adapt to the gripping needs of workpieces of different materials and different working conditions, solving the technical problem that existing end-effector gripping devices of embodied robots cannot identify gripping stress risk and safety status and cannot adaptively switch adjustment modes.

[0058] The end-effector gripping adjustment method of the embodied robot embodiment of the present invention further includes, before inputting the force data and gripping mechanism parameters into the pre-trained gripping stress state recognition model: acquiring a sample dataset, wherein the sample dataset includes multiple sets of sample data, each set of sample data including historical force data, historical gripping mechanism parameters and corresponding gripping stress state labels; constructing an initial neural network model; and training the initial neural network model using the sample dataset to obtain the gripping stress state recognition model.

[0059] This embodiment employs a clamping stress state recognition model trained on a neural network. It is trained offline with a large amount of labeled sample data, enabling the model to learn and memorize the complex nonlinear mapping relationship between historical force data, historical clamping mechanism parameters and stress state. This allows for rapid and accurate identification of newly acquired data in practical applications, effectively improving the adaptive, generalization and accuracy of stress state discrimination.

[0060] Furthermore, the initial neural network model is trained using a sample dataset to obtain a clamping stress state recognition model, including: dividing the sample dataset into a training set and a validation set; iteratively training the initial neural network model using the training set and validating the trained initial neural network model using the validation set; and determining the trained initial neural network model as the clamping stress state recognition model in response to successful validation.

[0061] This embodiment divides the sample dataset into a training set and a validation set. The initial neural network model is iteratively trained using the training set, and the trained model is validated using an independent validation set. Only after the validation is passed is the model determined as the clamping stress state recognition model, thereby effectively avoiding the risk of model overfitting and ensuring that the model has good generalization ability and stable recognition accuracy.

[0062] Furthermore, based on the clamping stress state information, the adjustment mode is determined, including: when the clamping stress state information is in a risk state, the adjustment mode is determined to be an adjustment mode; when the clamping stress state information is in a safe state, the adjustment mode is determined to be a fixed mode.

[0063] This embodiment achieves differentiated and targeted adaptive control by accurately matching the adjustment mode or the fixed mode according to the clamping stress state information. It can actively calibrate the stress to eliminate safety hazards under risk conditions, and maintain stable clamping to avoid unnecessary adjustment disturbances under safe conditions, effectively improving the adaptability and rationality of clamping stress adjustment.

[0064] Furthermore, the adjustment mode includes: determining the adjustment direction of the clamping component based on the deviation between the force data and the target clamping stress data, and generating an adjustment instruction set step by step according to a preset step size. The adjustment instruction set is used to match the force data with the target clamping stress data until the force data matches the target clamping stress data.

[0065] This embodiment determines the adjustment direction based on the deviation between the force data and the target clamping stress data, and generates adjustment instruction sets step by step according to a preset step size to achieve gradual matching between the force data and the target clamping stress data. It adopts a closed-loop feedback and step-by-step approximation adjustment strategy, which effectively avoids stress overshoot or oscillation caused by a single large adjustment. This ensures both the stability and safety of the adjustment process, as well as the accuracy and reliability of the final stress matching.

[0066] Furthermore, an adjustment instruction set is generated sequentially according to a preset step size, including: obtaining the current deviation value between the current force data and the target clamping stress data; determining the current adjustment step size based on the current deviation value, wherein the current adjustment step size is positively correlated with the current deviation value; and generating an adjustment instruction set in response to the current adjustment step size.

[0067] This embodiment obtains the current deviation value between the current force data and the target clamping stress data, and determines the current adjustment step size that is positively correlated with the current deviation value. It realizes a dynamic step-like adjustment strategy that allows for rapid approach with large step sizes when the deviation is large and precise approximation with small step sizes when the deviation is small. This not only effectively shortens the adjustment time and improves the adjustment efficiency, but also avoids the problems of overshooting with large step sizes or slow adjustment with small step sizes that may be caused by single step sizes. It significantly improves the accuracy and stability of stress adjustment.

[0068] Furthermore, the fixed mode includes: keeping the current position of the clamping component unchanged and continuously monitoring the force data; when the deviation of the force data from the target clamping stress data exceeds a preset deviation threshold, the adjustment mode is re-triggered.

[0069] This embodiment maintains a stable clamping state by keeping the current position of the clamping component unchanged in a fixed mode, while continuously monitoring the force data and automatically re-triggering the adjustment mode when the deviation from the target value exceeds a preset deviation threshold. This avoids the disturbance to clamping stability caused by unnecessary frequent adjustments, and ensures timely intervention and calibration when the stress changes significantly, thus achieving an organic unity of stable maintenance and dynamic response.

[0070] Furthermore, in the process of generating adjustment instruction sets step by step according to preset step size, the process also includes: after each generation of adjustment instruction sets, reacquiring the force data and recalculating the current deviation value between the force data and the target clamping stress data; when the current deviation value is less than the preset deviation threshold, stopping the generation of adjustment instruction sets and switching the current adjustment mode to fixed mode.

[0071] This embodiment reacquires the force data and recalculates the current deviation value after each generation of adjustment command set. When the deviation value is less than the preset deviation threshold, the adjustment is stopped in time and switched to the fixed mode. This forms a closed-loop control mechanism of "adjustment-monitoring-judgment-switching". It avoids stress oscillation and energy waste caused by over-adjustment, and ensures that the system quickly enters a stable holding state after the adjustment accuracy meets the requirements. This significantly improves the efficiency of the adjustment process and the overall stability of the system.

[0072] This invention also provides an end-effector gripping and adjustment device for a robot, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0073] Figure 2 According to one embodiment of the present invention, a robotic end-effector gripping and adjusting device includes:

[0074] The acquisition module 201 is used to acquire the force data and clamping mechanism parameters of the end-effector in response to the working start signal of the end-effector gripping device of the robot, and input the force data and clamping mechanism parameters into the pre-trained clamping stress state recognition model to obtain clamping stress state information. The clamping mechanism parameters include at least the elastic modulus, compressive strength, contact area and clamping stroke of the clamping mechanism, and the clamping stress state information includes risk state and safe state.

[0075] The determining module 202 is used to determine the adjustment mode based on the clamping stress state information. The adjustment mode is used to adjust the force data to the target clamping stress data. The adjustment mode includes: adjustment mode and fixing mode.

[0076] The generation module 203 is used to generate a control instruction set in response to the adjustment mode. The control instruction set is used to control the clamping member of the end clamping mechanism to move to a target position that is adapted to the target clamping stress data.

[0077] It should be noted that the above modules can be implemented by software or hardware. For the latter, they can be implemented in the following ways, but are not limited to: all the above modules are located in the same processor; or, the above modules are located in different processors in any combination.

[0078] According to one embodiment of the present invention, an electronic device is also provided, comprising: a memory storing an executable program; and a processor for running the program, wherein the program executes the above-described end-effector gripping and adjustment method for a holographic robot during runtime.

[0079] Optionally, in this embodiment, the processor can be configured to perform the following steps via a computer program:

[0080] Step S1: In response to the start signal of the end-effector gripping device of the embodied robot, acquire the force data and gripping mechanism parameters of the end-effector gripping mechanism, and input the force data and gripping mechanism parameters into the pre-trained gripping stress state recognition model to obtain gripping stress state information. The gripping mechanism parameters include at least: the elastic modulus, compressive strength, contact area and gripping stroke of the gripping mechanism, and the gripping stress state information includes: risk state and safe state.

[0081] Step S2: Based on the clamping stress state information, determine the adjustment mode. The adjustment mode is used to adjust the force data to the target clamping stress data. The adjustment mode includes: adjustment mode and fixing mode.

[0082] Step S3: In response to the adjustment mode, a control instruction set is generated. The control instruction set is used to control the clamping member of the end clamping mechanism to move to the target position that matches the target clamping stress data.

[0083] According to one embodiment of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored executable program, wherein, when the executable program is running, it controls the device where the storage medium is located to perform the above-described embodied robot end effector gripping and adjustment method.

[0084] Optionally, in this embodiment, the storage medium may be configured to store a computer program for performing the following steps:

[0085] Step S1: In response to the start signal of the end-effector gripping device of the embodied robot, acquire the force data and gripping mechanism parameters of the end-effector gripping mechanism, and input the force data and gripping mechanism parameters into the pre-trained gripping stress state recognition model to obtain gripping stress state information. The gripping mechanism parameters include at least: the elastic modulus, compressive strength, contact area and gripping stroke of the gripping mechanism, and the gripping stress state information includes: risk state and safe state.

[0086] Step S2: Based on the clamping stress state information, determine the adjustment mode. The adjustment mode is used to adjust the force data to the target clamping stress data. The adjustment mode includes: adjustment mode and fixing mode.

[0087] Step S3: In response to the adjustment mode, a control instruction set is generated. The control instruction set is used to control the clamping member of the end clamping mechanism to move to the target position that matches the target clamping stress data.

[0088] Optionally, in this embodiment, the storage medium may include, but is not limited to, various media capable of storing computer programs, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0089] According to one embodiment of the present invention, a computer program product is also provided, including a computer program that, when executed by a processor, implements the above-described end-effector gripping and adjustment method for a holographic robot.

[0090] Optionally, in this embodiment, the above-mentioned computer program product can be configured as a computer program that performs the following steps:

[0091] Step S1: In response to the start signal of the end-effector gripping device of the embodied robot, acquire the force data and gripping mechanism parameters of the end-effector gripping mechanism, and input the force data and gripping mechanism parameters into the pre-trained gripping stress state recognition model to obtain gripping stress state information. The gripping mechanism parameters include at least: the elastic modulus, compressive strength, contact area and gripping stroke of the gripping mechanism, and the gripping stress state information includes: risk state and safe state.

[0092] Step S2: Based on the clamping stress state information, determine the adjustment mode. The adjustment mode is used to adjust the force data to the target clamping stress data. The adjustment mode includes: adjustment mode and fixing mode.

[0093] Step S3: In response to the adjustment mode, a control instruction set is generated. The control instruction set is used to control the clamping member of the end clamping mechanism to move to the target position that matches the target clamping stress data.

[0094] Optionally, specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementations, and will not be repeated here.

[0095] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0096] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between units or modules may be electrical or other forms.

[0097] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0098] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0099] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0100] The above are merely preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for adjusting the end effector gripper of a robot, characterized in that, include: In response to the start signal of the end-effector gripping device of the embodied robot, the force data and gripping mechanism parameters of the end-effector gripping mechanism are acquired, and the force data and gripping mechanism parameters are input into a pre-trained gripping stress state recognition model to obtain gripping stress state information. The gripping mechanism parameters include at least the elastic modulus, compressive strength, contact area and gripping stroke of the gripping mechanism, and the gripping stress state information includes risk state and safe state. Based on the clamping stress state information, an adjustment mode is determined. The adjustment mode is used to adjust the force data to the target clamping stress data. The adjustment mode includes: an adjustment mode and a fixing mode. In response to the adjustment mode, a set of control instructions is generated to control the clamping member of the end clamping mechanism to move to a target position that matches the target clamping stress data.

2. The end-effector gripping and adjustment method for a robot according to claim 1, characterized in that, Before inputting the force data and the clamping mechanism parameters into the pre-trained clamping stress state recognition model, the method further includes: Obtain a sample dataset, wherein the sample dataset includes multiple sets of sample data, and each set of sample data includes historical force data, historical clamping mechanism parameters, and corresponding clamping stress state labels; Construct the initial neural network model; The initial neural network model is trained using the sample dataset to obtain the clamping stress state recognition model.

3. The end-effector gripping and adjustment method for a unibody robot according to claim 2, characterized in that, The initial neural network model is trained using the sample dataset to obtain the clamping stress state recognition model, including: The sample dataset is divided into a training set and a validation set; The initial neural network model is iteratively trained using the training set, and the trained initial neural network model is validated using the validation set. Upon successful verification, the trained initial neural network model is determined as the clamping stress state recognition model.

4. The end-effector gripping and adjustment method for a robot according to claim 1, characterized in that, Based on the clamping stress state information, the adjustment mode is determined, including: When the clamping stress state information is in a risk state, the adjustment mode is determined to be the regulation mode; When the clamping stress state information is in a safe state, the adjustment mode is determined to be the fixed mode.

5. The end-effector gripping and adjustment method for a unibody robot according to claim 4, characterized in that, The adjustment modes include: Based on the deviation between the force data and the target clamping stress data, the adjustment direction of the clamping component is determined, and an adjustment instruction set is generated sequentially according to a preset step size. The adjustment instruction set is used to match the force data with the target clamping stress data until the force data matches the target clamping stress data.

6. The end-effector gripping and adjustment method for a unibody robot according to claim 5, characterized in that, An adjustment instruction set is generated sequentially according to a preset step size, including: Obtain the current deviation value between the current force data and the target clamping stress data; Based on the current deviation value, the current adjustment step size is determined, wherein the current adjustment step size is positively correlated with the current deviation value; In response to the current adjustment step size, the adjustment instruction set is generated.

7. The end-effector gripping and adjustment method for a unibody robot according to claim 4, characterized in that, The fixed mode includes: Maintain the current position of the clamping member unchanged and continuously monitor the force data; When the deviation of the force data from the target clamping stress data exceeds a preset deviation threshold, the adjustment mode is retried.

8. The end-effector gripping and adjustment method for a unibody robot according to claim 5, characterized in that, The process of generating adjustment instruction sets sequentially according to preset step sizes also includes: After each generation of the adjustment instruction set, the force data is reacquired, and the current deviation between the force data and the target clamping stress data is recalculated. When the current deviation value is less than the preset deviation threshold, the generation of the adjustment instruction set is stopped, and the current adjustment mode is switched to the fixed mode.

9. A gripping and adjusting device for the end effector of a robot, characterized in that, include: The acquisition module is used to acquire the force data and clamping mechanism parameters of the end-effector in response to the working start signal of the end-effector gripping device of the robot, and input the force data and clamping mechanism parameters into a pre-trained clamping stress state recognition model to obtain clamping stress state information. The clamping mechanism parameters include at least the elastic modulus, compressive strength, contact area and clamping stroke of the clamping mechanism, and the clamping stress state information includes risk state and safe state. The determining module is used to determine an adjustment mode based on the clamping stress state information. The adjustment mode is used to adjust the force data to the target clamping stress data. The adjustment mode includes an adjustment mode and a fixing mode. A generation module is used to generate a set of control instructions in response to the adjustment mode. The set of control instructions is used to control the clamping member of the end clamping mechanism to move to a target position that matches the target clamping stress data.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored executable program, wherein, when the executable program is executed, it controls the device on which the storage medium is located to perform the end-effector gripping and adjustment method of any one of claims 1 to 8.

Images