Modularized kitchen knife rapid assembly robot and method

Abstract

The invention provides a modular kitchen knife rapid assembly robot and method, and the method comprises the steps: extracting the parameter drift characteristics of an assembly robot during the switching assembly of different kitchen knife modules from historical assembly data, and determining the structural error of the assembly robot during the switching assembly of different kitchen knife modules through the parameter drift characteristics; based on the collected dynamic alignment image, extracting an alignment deviation sequence of a blade and a knife handle in the rapid assembly process of the modular kitchen knife, and determining dynamic interference deviation in the rapid assembly process of the modular kitchen knife through fluctuation characteristics of the alignment deviation sequence; according to the structural error and the dynamic interference deviation, the assembly alignment compensation amount of a blade and a knife handle when the assembly robot rapidly assembles the modular kitchen knife is determined; and the assembly alignment action of the assembly robot is calibrated according to the assembly alignment compensation amount. By the adoption of the scheme, efficient, accurate and automatic assembling alignment of the assembling robot on the modular kitchen knife can be achieved in the scene that switching and assembling of the modular kitchen knife are frequent.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent manufacturing equipment industry, more particularly, the present application relates to a modular kitchen knife rapid assembly robot and method. BACKGROUND

[0002] Modular kitchen knives are an important application direction of intelligent manufacturing in the kitchen utensil industry. Through the rapid and accurate assembly of modular components such as blades and handles, personalized and efficient kitchen knife production is achieved. In the actual assembly process, the assembly robot needs to complete the high-precision alignment and joint of multiple types of blades and handles. The assembly quality directly affects the structural stability and safety of the product.

[0003] The modular kitchen knife rapid assembly robot is an automatic equipment applied to the kitchen knife production field, based on the modular design concept, which can quickly and accurately assemble each part of the modular kitchen knife into a finished product, improve production efficiency and quality, and reduce cost. However, in the prior art, traditional assembly robots usually execute assembly actions based on preset assembly programs, or only detect single-dimensional deviations through simple sensors. In actual production, when the assembly robot switches to assemble different specifications of blades or handles, the parameter changes caused by long-term movement of each axis of the mechanical arm will accumulate to form regular errors, resulting in precision fluctuations when the same assembly program is used for assembly of different modules. In addition, due to factors such as small vibration and small changes in the position of the blade and handle during the assembly of the modular kitchen knife, real-time changes in alignment deviation will occur, causing assembly failure or product reliability to decrease, resulting in unstable assembly alignment accuracy, low assembly efficiency, and poor assembly adaptability. Therefore, it is difficult to meet the high-mixing and fast-paced production needs of modular kitchen knives. Therefore, how to realize efficient and accurate automatic assembly of modular kitchen knives by the assembly robot in the scenario of frequent switching of modular kitchen knives has become a difficult problem in the industry. SUMMARY

[0004] The present application provides a modular kitchen knife rapid assembly robot and method, which can realize efficient and accurate automatic assembly of modular kitchen knives by the assembly robot in the scenario of frequent switching of modular kitchen knives.

[0005] In a first aspect, the present application provides a modular kitchen knife rapid assembly method for the rapid assembly and alignment of a modular kitchen knife by a modular kitchen knife rapid assembly robot. The method includes the following steps: Obtain historical assembly data of the assembly robot for the blade and handle of the modular kitchen knife; extracting a parameter drift feature of the assembly robot when switching assembly of different kitchen knife modules from the historical assembly data, determining a structural error of the assembly robot when switching assembly of different kitchen knife modules by the parameter drift feature in combination with coupling stiffness coefficients of each axis movement of the assembly robot; collecting dynamic alignment images of the blade and the handle in the rapid assembly process of the modular kitchen knife by a binocular vision sensor in real time, and then extracting an alignment deviation sequence of the blade and the handle in the rapid assembly process of the modular kitchen knife based on the collected dynamic alignment images, and determining a dynamic disturbance deviation in the rapid assembly process of the modular kitchen knife by fluctuation characteristics of the alignment deviation sequence; determining an assembly alignment compensation amount of the blade and the handle when the assembly robot performs rapid assembly of the modular kitchen knife according to the structural error and the dynamic disturbance deviation; calibrating assembly alignment actions of the assembly robot according to the assembly alignment compensation amount.

[0006] In some embodiments, extracting a parameter drift feature of the assembly robot when switching assembly of different kitchen knife modules from the historical assembly data specifically includes: classifying the historical assembly data according to kitchen knife module model combinations; determining the parameter drift feature of the assembly robot when switching assembly of different kitchen knife modules by the classified historical assembly data.

[0007] In some embodiments, determining a structural error of the assembly robot when switching assembly of different kitchen knife modules by the parameter drift feature in combination with coupling stiffness coefficients of each axis movement of the assembly robot specifically includes: obtaining coupling stiffness coefficients of each axis movement of the assembly robot; determining a pose deviation of the assembly robot affected by drift when switching assembly of kitchen knife modules from the coupling stiffness coefficients of each axis movement of the assembly robot and the parameter drift feature; determining the structural error of the assembly robot when switching assembly of different kitchen knife modules according to the pose deviation.

[0008] In some embodiments, extracting an alignment deviation sequence of the blade and the handle in the rapid assembly process of the modular kitchen knife based on the collected dynamic alignment images specifically includes: extracting edge contours of the blade and the handle assembly interface region from the collected dynamic alignment images; identifying key feature points in the blade and the handle assembly interface region respectively through the edge contours; determining the alignment deviation sequence of the blade and the handle in the rapid assembly process of the modular kitchen knife based on the identified key feature points.

[0009] In some embodiments, determining the dynamic interference deviation in the rapid assembly process of the modular kitchen knife based on the fluctuation characteristics of the alignment deviation sequence specifically comprises: performing time-domain fluctuation analysis on the alignment deviation sequence to obtain fluctuation characteristics of the alignment deviation sequence; extracting high-frequency fluctuation items from the fluctuation characteristics; determining the dynamic interference deviation in the rapid assembly process of the modular kitchen knife based on the extracted high-frequency fluctuation items.

[0010] In some embodiments, determining the assembly alignment compensation amount of the blade and the handle of the modular kitchen knife during the rapid assembly of the modular kitchen knife by the assembly robot based on the structural error and the dynamic interference deviation specifically comprises: determining the comprehensive deviation amount of the blade and the handle of the modular kitchen knife during the real-time state of the rapid assembly of the modular kitchen knife by the assembly robot based on the structural error and the dynamic interference deviation; determining the assembly alignment compensation amount of the blade and the handle of the modular kitchen knife during the rapid assembly of the modular kitchen knife by the assembly robot based on the comprehensive deviation amount and the geometric assembly relationship of the blade and the handle of the modular kitchen knife.

[0011] In some embodiments, calibrating the assembly alignment action of the assembly robot based on the assembly alignment compensation amount specifically comprises: converting the assembly alignment compensation amount into correction instructions for each axis of the assembly robot; performing trajectory calibration adjustment on the current assembly path of the assembly alignment action of the assembly robot based on the correction instructions.

[0012] In a second aspect, the present application provides a rapid assembly robot for modular kitchen knives, comprising a rapid assembly unit, wherein the rapid assembly unit comprises: an acquisition module, configured to acquire historical assembly data of a blade and a handle of a modular kitchen knife by an assembly robot; a processing module, configured to extract a parameter drift feature of the assembly robot when switching assembly of different kitchen knife modules from the historical assembly data, and determine a structural error of the assembly robot when switching assembly of different kitchen knife modules based on the parameter drift feature and a coupling stiffness coefficient of each axis of the assembly robot; the processing module is further configured to collect dynamic alignment images of the blade and the handle in a rapid assembly process of the modular kitchen knife by a binocular vision sensor in real time, and then extract an alignment deviation sequence of the blade and the handle in the rapid assembly process of the modular kitchen knife based on the collected dynamic alignment images, and determine a dynamic interference deviation in the rapid assembly process of the modular kitchen knife based on fluctuation characteristics of the alignment deviation sequence. The processing module is further configured to determine an assembly alignment compensation amount of the blade and the handle of the modular kitchen knife during rapid assembly by the assembly robot according to the structural error and the dynamic interference deviation. The execution module is configured to calibrate an assembly alignment action of the assembly robot according to the assembly alignment compensation amount.

[0013] In a third aspect, the present application provides a computer device, which comprises a memory and a processor, the memory is configured to store a computer program, and the processor is configured to call and run the computer program from the memory, so that the computer device executes the modular kitchen knife rapid assembly method described above.

[0014] In a fourth aspect, the present application provides a computer readable storage medium, which stores instructions or codes, when the instructions or codes are run on a computer, so that the computer executes the modular kitchen knife rapid assembly method described above.

[0015] The technical scheme provided by the embodiments of the present application has the following beneficial effects: In the present application, historical assembly data of a blade and a handle of a modular kitchen knife by an assembly robot is acquired, parameter drift features of the assembly robot during assembly switching of different kitchen knife modules are extracted from the historical assembly data, the structural error of the assembly robot during assembly switching of different kitchen knife modules is determined by the parameter drift features in combination with coupling stiffness coefficients of each axis movement of the assembly robot, dynamic alignment images of the blade and the handle during rapid assembly of the modular kitchen knife are collected in real time by a binocular vision sensor, alignment deviation sequences of the blade and the handle during rapid assembly of the modular kitchen knife are extracted based on the collected dynamic alignment images, the dynamic interference deviation during rapid assembly of the modular kitchen knife is determined by fluctuation features of the alignment deviation sequences, the assembly alignment compensation amount of the blade and the handle during rapid assembly of the modular kitchen knife by the assembly robot is determined according to the structural error and the dynamic interference deviation, and the assembly alignment action of the assembly robot is calibrated according to the assembly alignment compensation amount.

[0016] Therefore, in this application, firstly, by combining the parameter drift characteristics with the coupling stiffness coefficients of the motion of each axis of the assembly robot, the structural errors of the assembly robot during the switching assembly of different kitchen knife modules can be determined. This allows for the quantification of the inherent deformation and load response patterns between the different axes of the assembly robot, thereby identifying structural errors inherent to the mechanical system. This improves assembly alignment accuracy from the source, reduces assembly failures caused by accumulated mechanical errors, and effectively enhances the adaptability of the assembly robot in highly mixed production lines. Secondly, by determining the dynamic interference deviations in the rapid assembly process of modular kitchen knives through the fluctuation characteristics of the alignment deviation sequence, external disturbances during the assembly process, such as mechanical vibration or gripper jitter, can be automatically identified. This not only effectively separates static errors from dynamic disturbances but also enables rapid deviation detection and dynamic compensation in real-time assembly, allowing the assembly robot to maintain stable accuracy under fast-paced operation and avoiding assembly jams caused by short-term interference. To prevent lag or misfitting, the system ensures the reliability and efficiency of continuous production line operation. Then, based on the structural errors and dynamic disturbance deviations, the system determines the alignment compensation amount for the blade and handle during rapid assembly of modular kitchen knives by the assembly robot. This allows the assembly robot to comprehensively consider both mechanical structure and real-time disturbances in its decision-making, generating more accurate and comprehensive assembly corrections. For highly mixed production scenarios, this alignment compensation amount gives the assembly robot versatility and adaptability, enabling it to quickly adjust to a suitable state when switching between different blades and handles, improving the accuracy and reliability of assembly alignment. Finally, the assembly alignment action of the assembly robot is calibrated based on the alignment compensation amount, ensuring that the blade and handle of the modular kitchen knife remain in precise alignment. In summary, this solution enables efficient and accurate automated assembly alignment of modular kitchen knives by the assembly robot in scenarios with frequent switching between different blade and handle configurations. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is an exemplary flowchart of a modular kitchen knife rapid assembly method according to some embodiments of this application; Figure 2 This is an exemplary flowchart illustrating the determination of structural errors according to some embodiments of this application; Figure 3 This is an exemplary flowchart illustrating the determination of dynamic interference deviation according to some embodiments of this application; Figure 4 This is a schematic diagram of the structure of a rapid assembly unit according to some embodiments of this application; Figure 5 This is a schematic diagram of the structure of a computer device that implements a modular kitchen knife rapid assembly method according to some embodiments of this application. Detailed Implementation

[0019] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0020] refer to Figure 1 The figure is an exemplary flowchart of a modular kitchen knife quick assembly method according to some embodiments of this application. The modular kitchen knife quick assembly method mainly includes the following steps: In step 101, the historical assembly data of the modular kitchen knife blade and handle by the assembly robot is obtained.

[0021] In specific implementation, the historical assembly data of the modular kitchen knife blades and handles by the assembly robot can be obtained in the following way: Data records of all modular kitchen knife assembly operations completed by the assembly robot within a preset time period (e.g., the last 3 months) can be obtained from the assembly robot's historical record database. The data records may include: the kitchen knife module model of the blade and handle during rapid assembly of the modular kitchen knife by the assembly robot; motion parameters (such as displacement, velocity, and acceleration) of each axis of the assembly robot (e.g., base axis, upper arm axis, lower arm axis, etc.); the initial positioning coordinates of the blade and handle (obtained through positioning sensors installed at the end effector of the assembly robot); the assembly force value of the end effector during assembly; and the final completion status of each assembly (e.g., whether the docking was successful, and the position deviation detection value after docking). The set of all obtained parameter records is then used as the historical assembly data of the modular kitchen knife blades and handles by the assembly robot. The historical record database is a data repository storing all assembly records of the modular kitchen knife by the assembly robot. Other methods may also be used in other embodiments, and are not limited here.

[0022] It should be noted that the historical assembly data in this application refers to the collection of historical data such as motion, force, vision, and results generated by the assembly robot in previous tasks of assembling the blades and handles of modular kitchen knives.

[0023] In step 102, parameter drift characteristics of the assembly robot when switching assembly of different kitchen knife modules are extracted from the historical assembly data. The structural error of the assembly robot when switching assembly of different kitchen knife modules is determined by combining the parameter drift characteristics with the coupling stiffness coefficient of the motion of each axis of the assembly robot.

[0024] In some embodiments, extracting parameter drift characteristics of the assembly robot when switching between different kitchen knife modules from the historical assembly data can be achieved using the following steps: The historical assembly data is categorized according to the combination of kitchen knife module models; The parameter drift characteristics of the assembly robot when switching between different kitchen knife modules are determined by classifying historical assembly data.

[0025] In specific implementation, classifying the historical assembly data according to the combination of kitchen knife module models can be achieved in the following way: the historical assembly data can be classified according to the combination of kitchen knife module models (such as "blade model A + handle model X", "blade model B + handle model Y", etc.); determining the parameter drift characteristics of the assembly robot when switching assembly of different kitchen knife modules through the classified historical assembly data can be achieved in the following way: first, the switching scenario data of two adjacent assembly with different module combinations can be selected from the classified historical assembly data (i.e., the scenario of switching assembly of different kitchen knife modules), and then for each switching scenario, the motion parameters (such as displacement, velocity, acceleration), end effector positioning coordinates and assembly force values ​​of each axis of the assembly robot in the two assembly before and after the switching are extracted, and the time series is analyzed. Algorithms (such as dynamic time warping algorithms) match the parameter sequences before and after switching at the assembly stages (such as gripping, alignment, and joining stages). Secondly, statistical analysis methods (such as calculating the mean difference, standard deviation, and trend slope) can be used to compare the parameter differences before and after switching at the same assembly stage, identifying the systematic shifts in parameters caused by module switching. Then, the identified systematic shifts, such as direction, magnitude, and rate of change, are integrated into a drift pattern that characterizes the assembly robot during the kitchen knife module switching assembly (e.g., the average displacement deviation of a certain axis of the assembly robot increases by 0.02 mm after module switching, and the deviation fluctuation range expands by 15%). Finally, the obtained drift pattern is used as the parameter drift characteristics of the assembly robot during the switching assembly of different kitchen knife modules. Other methods can also be used in other embodiments for determination, which are not limited here.

[0026] It should be noted that the different kitchen knife module switching assembly in this application refers to the operation process of the assembly robot switching from assembling one kitchen knife module combination to assembling another kitchen knife module combination; the parameter drift feature in this application represents the cumulative deviation feature of the actual parameters from the theoretical set value when the assembly robot switches the kitchen knife module assembly, which is used to capture the systematic changes of the assembly robot in cross-model assembly during the rapid assembly of modular kitchen knives.

[0027] In some embodiments, reference Figure 2 As shown, this figure is an exemplary flowchart for determining structural errors in some embodiments of this application. In this embodiment, the structural errors of the assembly robot when switching assembly of different kitchen knife modules can be determined by combining the parameter drift characteristics with the coupling stiffness coefficients of the motion of each axis of the assembly robot. This can be achieved by the following steps: First, in step 1021, the coupling stiffness coefficients of the motion of each axis of the assembly robot are obtained; Secondly, in step 1022, the pose deviation of the assembly robot affected by the drift during the switching assembly of the kitchen knife module is determined by the coupling stiffness coefficient of the motion of each axis of the assembly robot and the parameter drift characteristics. Finally, in step 1023, the structural error of the assembly robot when switching assembly of different kitchen knife modules is determined based on the pose deviation.

[0028] In specific implementation, the coupling stiffness coefficients of the motion of each axis of the assembly robot can be obtained in the following way: They can be pre-acquired and stored using the assembly robot's factory calibration data or offline mechanical experiments (such as applying gradient loads to each axis of the assembly robot and measuring the displacement deviation of the associated axes). The positional deviation of the assembly robot affected by drift during the switching assembly of the kitchen knife module can be determined by using the coupling stiffness coefficients of the motion of each axis of the assembly robot and the parameter drift characteristics in the following way: An error propagation model of the multi-axis motion of the assembly robot can be established, and the parameter drift characteristics can be used as input variables. These variables are then substituted into the model and matrix operations are performed with the coupling stiffness coefficients of the motion of each axis of the assembly robot. For example, the inter-axis coupling error can be calculated by multiplying the matrix composed of the coupling stiffness coefficients with the drift vector in the parameter drift characteristics, thus obtaining the coupling error of the assembly robot. The associated axis error caused by single-axis drift is then superimposed with the direct drift error of all axes (the direct drift error refers to the independent error caused only by the performance change of a single axis, filtered by separating the inter-axis coupling effect from the drift characteristics of the parameters). The superposition result can then be fitted using the least squares method to eliminate random interference components. Finally, the position deviation (i.e. in the X, Y, Z axis directions) and attitude deviation (i.e. rotation angle) of the end effector (such as the component holding the kitchen knife module) of the assembly robot in three-dimensional space are obtained under different module switching scenarios (such as switching from blade A + handle X to blade B + handle Y). The position deviation and attitude deviation are then combined to form the pose deviation of the assembly robot affected by drift when switching the kitchen knife module. Other methods can also be used to determine this in other embodiments, which are not limited here.

[0029] In specific implementation, determining the structural error of the assembly robot when switching between different kitchen knife modules based on the pose deviation can be achieved in the following way: pose deviation samples can be collected for different switching scenarios. For example, for different module switching scenarios (such as "blade A + handle X → blade B + handle Y"), at least 20 samples of pose deviation affected by drift in the same scenario can be collected to form a sample set. After removing random errors from the sample set by Kalman filtering, trend analysis is performed on the filtered data through linear fitting to extract stable deviation components. Finally, the obtained stable deviation components are used as the structural error of the assembly robot when switching between different kitchen knife modules to accurately reflect the inherent accuracy defects of the assembly robot when switching between kitchen knife modules. Other methods can also be used to determine this in other embodiments, which are not limited here.

[0030] It should be noted that the coupling stiffness coefficient in this application represents the correlation influence coefficient on the motion accuracy of other axes when a certain axis of the assembly robot is deformed by force. It reflects the interaction law of each axis of the assembly robot due to the mechanical structure correlation and is the core parameter for quantifying the inter-axis coupling error. The pose deviation affected by drift in this application refers to the difference between the actual pose and the theoretical pose of the end effector of the assembly robot in the kitchen knife module switching scenario. It is caused by the drift of each axis parameter and the inter-axis coupling effect and is a specific quantitative manifestation of the parameter drift and coupling effect in the assembly alignment process. The structural error in this application refers to the regular assembly deviation that repeatedly occurs during the kitchen knife module switching assembly caused by the mechanical structure characteristics of the assembly robot. It reflects the inherent accuracy defects during the kitchen knife module switching assembly and is the basic accuracy that directly determines the assembly alignment during the kitchen knife module switching.

[0031] In step 103, dynamic alignment images of the blade and handle during the rapid assembly of the modular kitchen knife are acquired in real time using a binocular vision sensor. Then, the alignment deviation sequence of the blade and handle during the rapid assembly of the modular kitchen knife is extracted based on the acquired dynamic alignment images. The dynamic interference deviation during the rapid assembly of the modular kitchen knife is determined by the fluctuation characteristics of the alignment deviation sequence.

[0032] In practical implementation, the real-time acquisition of dynamic alignment images of the blade and handle during the rapid assembly of a modular kitchen knife using a binocular vision sensor can be achieved in the following way: First, a pair of binocular cameras, spaced a certain baseline distance apart, are installed at a fixed position in the assembly robot's workspace. A calibration board is used to geometrically calibrate the two cameras to obtain their intrinsic parameters (focal length, distortion coefficients) and extrinsic parameters (relative position and orientation). Second, during rapid assembly, the binocular vision sensor is activated to synchronously acquire image sequences of the blade and handle, and a time synchronization module ensures that both cameras capture the scene at the same timestamp. Then, A stereo matching algorithm is used to calculate the disparity between the two images, converting the two-dimensional pixel coordinates into three-dimensional spatial coordinates to obtain three-dimensional point cloud data of the blade and handle edges and assembly interface positions. Then, a dynamic tracking algorithm (such as optical flow tracking or feature point matching) is used to update the relative position and orientation of the blade and handle in three-dimensional space in real time. Finally, the tracked pose data is converted into dynamic alignment images of the blade and handle during the rapid assembly of the modular kitchen knife, so as to display the spatial alignment of the blade and handle in real time in the assembly robot control system. Other methods can also be used for data acquisition in other embodiments, which are not specifically limited here.

[0033] It should be noted that the binocular vision sensor in this application refers to a device that uses two cameras to acquire images of the same target from different angles and achieves three-dimensional positioning through parallax calculation; the dynamic alignment image in this application refers to a sequence of images showing the real-time changes in the relative position of the blade and handle of a modular kitchen knife during rapid assembly, which is image information reflecting the alignment state of the blade and handle of the modular kitchen knife.

[0034] In some embodiments, the following steps can be used to extract the alignment deviation sequence between the blade and the handle during the rapid assembly of a modular kitchen knife based on the acquired dynamic alignment image: Extract the edge contours of the blade and tool holder assembly interface area from the acquired dynamic alignment images; Key feature points were identified in the blade and shank assembly interface area using the edge contour; Based on the identified key feature points, the alignment deviation sequence between the blade and the handle during the rapid assembly of modular kitchen knives is determined.

[0035] In practical implementation, extracting the edge contours of the blade and tool holder assembly interface area from the acquired dynamic alignment image can be achieved in the following ways: Edge detection algorithms (such as the Canny operator) can be used to extract the edge contours of the blade and tool holder assembly interface area; identifying key feature points in the blade and tool holder assembly interface area can be achieved in the following ways: Feature point matching methods (such as scale-invariant feature transformation algorithms) can be used. FeatureTransform (SIFT) identifies key feature points in the assembly interface area of ​​the blade and handle based on the edge contour. The alignment deviation sequence between the blade and handle during the rapid assembly of the modular kitchen knife can be determined using the following method: Based on the identified key feature points and the 3D point cloud data obtained from binocular reconstruction, the displacement and angle differences between the blade assembly end and the handle assembly groove in 3D space are calculated. Then, a time series model is established, and the displacement and angle differences calculated in consecutive frame images are arranged in chronological order. The resulting sequence of real-time changes in the blade and handle during assembly is used as the alignment deviation sequence between the blade and handle during the rapid assembly of the modular kitchen knife. Other methods can also be used in other embodiments, which are not limited here.

[0036] It should be noted that, in this application, the blade and handle assembly interface area refers to the geometric area of ​​the physical contact part when the blade and handle are mechanically connected or assembled in a modular kitchen knife, and its edge contour is used to define the geometric boundary constraints for feature extraction and registration; the key feature points in this application refer to repeatable, trackable, and 3D quantizable geometric anchor points in the blade and handle assembly interface area, which are used to observe the alignment pose of the blade and handle during the rapid assembly of the modular kitchen knife; the alignment deviation sequence in this application refers to the continuous data sequence formed by the displacement difference and angle difference between the blade and handle at different time points during the rapid assembly of the modular kitchen knife, which is used to quantify the spatial alignment error between the blade and handle acquired by vision into temporal data so that the subsequent assembly robot can perform accurate error compensation in dynamic assembly.

[0037] In some embodiments, reference Figure 3 As shown, this figure is an exemplary flowchart for determining dynamic interference deviation in some embodiments of this application. The determination of dynamic interference deviation in the rapid assembly process of a modular kitchen knife based on the fluctuation characteristics of the alignment deviation sequence can be achieved through the following steps: Time-domain fluctuation analysis was performed on the alignment deviation sequence to obtain the fluctuation characteristics of the alignment deviation sequence; High-frequency fluctuation terms are extracted from the fluctuation characteristics; The dynamic interference deviation in the rapid assembly process of modular kitchen knives was determined by extracting the high-frequency fluctuation term.

[0038] In specific implementation, time-domain fluctuation analysis is performed on the alignment deviation sequence to obtain its fluctuation characteristics. This can be achieved by: performing time-domain fluctuation analysis on the alignment deviation sequence, for example, by using moving average filtering and standard deviation calculation to identify high-frequency disturbance components in the deviation curve corresponding to the alignment deviation sequence; extracting high-frequency fluctuation terms from the fluctuation characteristics can be achieved by: separating low-frequency and high-frequency components in the fluctuation characteristics using fast Fourier transform or wavelet transform to extract the rapidly changing high-frequency components caused by factors such as mechanical vibration, environmental disturbance, or sensor jitter during assembly, and using these as high-frequency fluctuation terms; determining the dynamic interference deviation in the rapid assembly process of the modular kitchen knife using the extracted high-frequency fluctuation terms can be achieved by: In other words, the extracted high-frequency fluctuation terms are subjected to feature calculations, such as calculating their root mean square value, standard deviation, and frequency distribution range, to obtain high-frequency fluctuation feature parameters characterizing the fluctuation intensity and frequency. The extracted high-frequency fluctuation feature parameters are used as the quantification result of dynamic interference deviation, and compared with a preset assembly accuracy threshold (e.g., setting the X-axis deviation threshold to 0.01mm according to the kitchen knife assembly requirements) to determine whether the current dynamic interference magnitude exceeds the acceptable range and the degree of impact on assembly accuracy. The quantification result is then combined with the impact assessment to determine the magnitude and degree of interference. The final assessment result is used as the dynamic interference deviation in the rapid assembly process of the modular kitchen knife, providing accurate input basis for the subsequent alignment action compensation control of the assembly robot. Other methods can also be used for determination in other embodiments, which are not limited here.

[0039] It should be noted that the fluctuation characteristics in this application refer to the rapid change pattern exhibited in the alignment deviation sequence, including amplitude, frequency distribution, and trend, used to reveal the difference between stable deviations and dynamic disturbances in the error; the high-frequency fluctuation term in this application refers to the rapidly changing component with a frequency higher than the set cutoff frequency separated from the alignment deviation between the blade and handle during the rapid assembly of the modular kitchen knife, used to explicitly characterize the instantaneous disturbances caused by vibration / shaking during the assembly process; the dynamic disturbance deviation in this application refers to the assembly error caused by unstable factors, which serves as the target parameter for correction control during the rapid alignment assembly of the modular kitchen knife, used to compensate for and reduce the influence of external disturbances during the rapid assembly of the modular kitchen knife, including unstable factors such as environmental vibration, instantaneous vibration of robot joints, and visual measurement noise.

[0040] In step 104, the assembly alignment compensation amount between the blade and the handle is determined based on the structural error and the dynamic interference deviation when the assembly robot performs rapid assembly of the modular kitchen knife.

[0041] In some embodiments, determining the alignment compensation amount between the blade and the handle when the assembly robot rapidly assembles a modular kitchen knife based on the structural error and the dynamic disturbance deviation can be achieved through the following steps: The combined deviation between the blade and the handle is determined based on the structural error and the dynamic disturbance deviation when the assembly robot performs rapid assembly of the modular kitchen knife in real time. The assembly alignment compensation amount of the blade and handle is determined by combining the comprehensive deviation amount with the geometric assembly relationship of the blade and handle of the modular kitchen knife when the assembly robot performs rapid assembly of the modular kitchen knife.

[0042] In specific implementation, the comprehensive deviation between the blade and handle of the assembly robot during rapid assembly of the modular kitchen knife in real-time, based on the structural error and the dynamic disturbance deviation, can be achieved in the following way: First, a compensation model is initialized, and the structural error (i.e., the constant or slowly varying deviation caused by insufficient coupling stiffness of the mechanical axes of the assembly robot and parameter drift) is input into the compensation model as a basic bias. Then, the dynamic disturbance deviation (i.e., the high-frequency attitude and position deviation caused by external vibration and mechanical disturbance during the assembly process) is superimposed on the above basic bias in the form of a time-series disturbance. Then, the two are fused and estimated through Kalman filtering or extended Kalman filtering. The fusion estimation process uses the covariance matrix of the two as weights (the smaller the covariance, the larger the weight). Thus, the actual assembly alignment deviation result obtained by the fusion estimation is used as the comprehensive deviation between the blade and handle of the assembly robot during rapid assembly of the modular kitchen knife in real-time. It should be noted that the compensation model in this application is used to calculate the assembly deviation between the blade and handle of the assembly robot during rapid assembly of the modular kitchen knife. A machine learning model for alignment deviation is provided. The algorithm framework of this compensation model can adopt the support vector regression algorithm. In other embodiments, the algorithm framework of this compensation model can also adopt other algorithm structures, which are not limited here. The alignment compensation amount of the blade and handle when the assembly robot performs rapid assembly of the modular kitchen knife can be determined by combining the comprehensive deviation amount with the geometric assembly relationship of the blade and handle of the modular kitchen knife. This can be achieved in the following way: the comprehensive deviation amount can be converted into a numerical six-dimensional compensation parameter along six degrees of freedom (X, Y, Z translation and rotation around α, β, γ) in space according to the geometric assembly relationship of the blade and handle of the modular kitchen knife. This six-dimensional compensation parameter is used as the alignment compensation amount of the blade and handle when the assembly robot performs rapid assembly of the modular kitchen knife. It includes translation compensation values ​​in the X / Y / Z axis directions and rotation compensation values ​​around each axis, so as to instruct the assembly robot to correct the position and attitude of the blade and handle in real time, so that the rapid assembly process of the modular kitchen knife can overcome structural errors and dynamic interference and achieve high-precision alignment. In other embodiments, other methods can also be used for determination, which are not limited here.

[0043] It should be noted that the comprehensive deviation in this application represents the six-degree-of-freedom error vector between the blade and the handle when the assembly robot rapidly assembles the modular kitchen knife in real time. It combines structural bias and instantaneous dynamic disturbance into a single, measurable target error input, which can be used as the basis for the alignment compensation decision in the rapid assembly of the modular kitchen knife. The assembly alignment compensation in this application represents the compensation parameter used to calibrate and adjust the assembly alignment action of the assembly robot to offset the structural error and dynamic disturbance deviation during the rapid assembly of the modular kitchen knife so as to ensure accurate alignment of the blade and the handle. It can be used as the direct control input for the registration action correction of the assembly robot to instantly correct the relative pose of the blade and the handle in the modular kitchen knife, ensuring high-precision alignment when rapidly assembling the blade and the handle of the modular kitchen knife.

[0044] In step 105, the assembly alignment action of the assembly robot is calibrated according to the assembly alignment compensation amount.

[0045] In some embodiments, calibrating the assembly alignment action of the assembly robot according to the assembly alignment compensation amount can be achieved by the following steps: The assembly alignment compensation amount is converted into correction instructions for each axis of the assembly robot; Based on the correction command, the current assembly path of the assembly robot's assembly alignment action is calibrated and adjusted.

[0046] In specific implementation, converting the assembly alignment compensation amount into correction instructions for each axis of the assembly robot can be achieved in the following way: the assembly alignment compensation amount can be input to the motion controller of the assembly robot, and the assembly alignment compensation amount is converted into correction instructions for each joint axis of the assembly robot through an inverse kinematics algorithm in the motion controller, such as the increment of the joint axis angle of the assembly robot; the trajectory calibration and adjustment of the current assembly path of the assembly robot's assembly alignment action based on the correction instructions can be achieved in the following way: first, the motion controller of the assembly robot performs trajectory calibration and adjustment of the current assembly path of the assembly robot's assembly alignment action according to the correction instructions, and generates a smooth motion curve through a trajectory interpolation algorithm to avoid jitter or impact during the motion correction of the assembly robot; second, when executing... During the correction process, the assembly robot monitors the alignment of the blade and handle in real time using binocular vision sensors and force / torque sensors. It compares the real-time collected data with the compensated expected alignment to verify if the assembly accuracy requirements are met. Then, if a small residual is detected, the motion controller iteratively fine-tunes the joint commands based on the residual until it falls below a preset threshold, achieving high-precision assembly. Finally, the assembly robot stores the compensated and calibrated movements as a new assembly benchmark in a record database for adaptive optimization during subsequent rapid assembly of modular kitchen knives. This allows the assembly robot to automatically correct deviations during actual rapid assembly, ensuring the blade and handle of the modular kitchen knife maintain precise alignment even in dynamic environments. Other methods can also be used in other embodiments, and are not limited here.

[0047] It should be noted that the assembly alignment action in this application refers to the end-effector motion behavior generated by the assembly robot when performing the assembly task, which is used to achieve spatial docking between the blade and handle of the modular kitchen knife; the correction instruction in this application refers to the specific control parameters used to adjust the movement of each joint of the assembly robot. It is a motion control signal directly executed by the assembly robot so that the end of the assembly robot can be adjusted in the actual space according to the required direction and amplitude, thereby eliminating alignment errors in the assembly process and achieving precise alignment between the blade and handle.

[0048] In another aspect, in some embodiments, this application provides a modular kitchen knife rapid assembly robot, which includes a rapid assembly unit, as referenced. Figure 4 The figure is a schematic diagram of the structure of a rapid assembly unit 400 according to some embodiments of this application. The rapid assembly unit 400 includes: an acquisition module 401, a processing module 402, and an execution module 403, which are described below: The acquisition module 401 in this application is mainly used to acquire historical assembly data of the blade and handle of the modular kitchen knife by the assembly robot. Processing module 402 in this application is mainly used to extract parameter drift characteristics of the assembly robot when switching assembly of different kitchen knife modules from the historical assembly data, and to determine the structural error of the assembly robot when switching assembly of different kitchen knife modules by combining the parameter drift characteristics with the coupling stiffness coefficient of the motion of each axis of the assembly robot. The processing module 402 described in this application is also used to acquire dynamic alignment images of the blade and handle during the rapid assembly of the modular kitchen knife in real time using a binocular vision sensor, and then extract the alignment deviation sequence of the blade and handle during the rapid assembly of the modular kitchen knife based on the acquired dynamic alignment images, and determine the dynamic interference deviation during the rapid assembly of the modular kitchen knife through the fluctuation characteristics of the alignment deviation sequence. The processing module 402 described in this application is also used to determine the assembly alignment compensation amount between the blade and the handle when the assembly robot performs rapid assembly of the modular kitchen knife based on the structural error and the dynamic interference deviation. The execution module 403 in this application is mainly used to calibrate the assembly alignment action of the assembly robot according to the assembly alignment compensation amount.

[0049] The foregoing has detailed examples of the modular kitchen knife rapid assembly robot and method provided in the embodiments of this application. It is understood that the corresponding device, in order to achieve the above functions, includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should readily recognize that, in conjunction with the units and algorithm steps of the various examples described in the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed by hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0050] In some embodiments, this application also provides a computer device, the computer device including a memory and a processor, the memory for storing a computer program, and the processor for calling and running the computer program from the memory, so that the computer device performs the above-described modular kitchen knife rapid assembly method.

[0051] In some embodiments, reference Figure 5 The dashed lines in the figure indicate that the unit or module is optional. This figure is a schematic diagram of the structure of a computer device implementing the modular kitchen knife rapid assembly method of this application. The modular kitchen knife rapid assembly method in the above embodiments can be achieved through… Figure 5The computer device 500 shown is used to implement this, and the computer device 500 includes at least one processor 501, a memory 502 and at least one communication unit 505. The computer device 500 may be a terminal device, a server or a chip.

[0052] The processor 501 can be a general-purpose processor or a special-purpose processor. For example, the processor 501 can be a central processing unit (CPU). The CPU can be used to control the computer device 500, execute software programs, and process data from the software programs. The computer device 500 may also include a communication unit 505 for inputting (receiving) and outputting (transmitting) signals.

[0053] For example, computer device 500 may be a chip, communication unit 505 may be the input and / or output circuit of the chip, or communication unit 505 may be the communication interface of the chip, and the chip may be a component of terminal device, network device or other device.

[0054] For example, computer device 500 may be a terminal device or a server, and communication unit 505 may be a transceiver of the terminal device or the server, or communication unit 505 may be a transceiver circuit of the terminal device or the server.

[0055] The computer device 500 may include one or more memories 502 storing a program 504. The program 504 can be executed by a processor 501 to generate instructions 503, causing the processor 501 to perform the methods described in the above method embodiments according to the instructions 503. Optionally, the memory 502 may also store data (such as a target audit model). Optionally, the processor 501 may also read data stored in the memory 502, which may be stored at the same storage address as the program 504, or the data may be stored at a different storage address than the program 504.

[0056] The processor 501 and memory 502 can be configured separately or integrated together, for example, integrated on the system-on-chip (SOC) of the terminal device.

[0057] It should be understood that each step of the above method embodiment can be completed by hardware logic circuits or software instructions in the processor 501. The processor 501 can be a CPU, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, such as discrete gates, transistor logic devices, or discrete hardware components.

[0058] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0059] For example, in some embodiments, this application also provides a computer-readable storage medium storing instructions or code that, when executed on a computer, cause the computer to implement the above-described modular kitchen knife rapid assembly method.

[0060] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0061] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for rapid assembly of modular kitchen knives, used by a modular kitchen knife rapid assembly robot to quickly assemble and align modular kitchen knives, characterized in that, The method includes the following steps: Acquire historical assembly data of the blades and handles of modular kitchen knives by the assembly robot; Extract the parameter drift characteristics of the assembly robot when switching assembly of different kitchen knife modules from the historical assembly data, and determine the structural error of the assembly robot when switching assembly of different kitchen knife modules by combining the parameter drift characteristics with the coupling stiffness coefficient of the motion of each axis of the assembly robot. The dynamic alignment images of the blade and handle during the rapid assembly of the modular kitchen knife are acquired in real time by a binocular vision sensor. Then, the alignment deviation sequence of the blade and handle during the rapid assembly of the modular kitchen knife is extracted based on the acquired dynamic alignment images. The dynamic interference deviation in the rapid assembly of the modular kitchen knife is determined by the fluctuation characteristics of the alignment deviation sequence. The assembly alignment compensation amount between the blade and the handle is determined based on the structural error and the dynamic interference deviation when the assembly robot performs rapid assembly of the modular kitchen knife. The assembly alignment action of the assembly robot is calibrated based on the assembly alignment compensation amount.

2. The method as described in claim 1, characterized in that, Extracting parameter drift features from the historical assembly data when the assembly robot switches between different kitchen knife modules specifically includes: The historical assembly data is categorized according to the combination of kitchen knife module models; The parameter drift characteristics of the assembly robot when switching between different kitchen knife modules are determined by classifying historical assembly data.

3. The method as described in claim 1, characterized in that, The structural errors of the assembly robot when switching between different kitchen knife modules are determined by combining the parameter drift characteristics with the coupling stiffness coefficients of the motion of each axis of the assembly robot. Specifically, these errors include: Obtain the coupling stiffness coefficients of the motion of each axis of the assembly robot; The pose deviation of the assembly robot affected by the drift during the switching assembly of the kitchen knife module is determined by the coupling stiffness coefficient of the motion of each axis of the assembly robot and the parameter drift characteristics; The structural error of the assembly robot when switching between different kitchen knife modules is determined based on the posture deviation.

4. The method as described in claim 1, characterized in that, Based on the acquired dynamic alignment images, the sequence of alignment deviations between the blade and handle during the rapid assembly of a modular kitchen knife is extracted, specifically including: Extract the edge contours of the blade and tool holder assembly interface area from the acquired dynamic alignment images; Key feature points were identified in the blade and shank assembly interface area using the edge contour; Based on the identified key feature points, the alignment deviation sequence between the blade and the handle during the rapid assembly of modular kitchen knives is determined.

5. The method as described in claim 1, characterized in that, The dynamic interference deviations identified through the fluctuation characteristics of the alignment deviation sequence during the rapid assembly of modular kitchen knives specifically include: Time-domain fluctuation analysis was performed on the alignment deviation sequence to obtain the fluctuation characteristics of the alignment deviation sequence; High-frequency fluctuation terms are extracted from the fluctuation characteristics; The dynamic interference deviation in the rapid assembly process of modular kitchen knives was determined by extracting the high-frequency fluctuation term.

6. The method as described in claim 1, characterized in that, The specific compensation amount for the alignment of the blade and handle during the rapid assembly of the modular kitchen knife by the assembly robot, based on the structural error and the dynamic disturbance deviation, includes: The combined deviation between the blade and the handle is determined based on the structural error and the dynamic disturbance deviation when the assembly robot performs rapid assembly of the modular kitchen knife in real time. The assembly alignment compensation amount of the blade and handle is determined by combining the comprehensive deviation amount with the geometric assembly relationship of the blade and handle of the modular kitchen knife when the assembly robot performs rapid assembly of the modular kitchen knife.

7. The method as described in claim 1, characterized in that, The calibration of the assembly alignment action of the assembly robot based on the assembly alignment compensation amount specifically includes: The assembly alignment compensation amount is converted into correction instructions for each axis of the assembly robot; Based on the correction command, the current assembly path of the assembly robot's assembly alignment action is calibrated and adjusted.

8. A modular kitchen knife rapid assembly robot, comprising a rapid assembly unit, characterized in that, The rapid assembly unit includes: The acquisition module is used to acquire historical assembly data of the blades and handles of the modular kitchen knife by the assembly robot; The processing module is used to extract parameter drift characteristics of the assembly robot when switching assembly of different kitchen knife modules from the historical assembly data, and to determine the structural error of the assembly robot when switching assembly of different kitchen knife modules by combining the parameter drift characteristics with the coupling stiffness coefficient of the motion of each axis of the assembly robot. The processing module is also used to acquire dynamic alignment images of the blade and handle during the rapid assembly of the modular kitchen knife in real time through a binocular vision sensor, and then extract the alignment deviation sequence of the blade and handle during the rapid assembly of the modular kitchen knife based on the acquired dynamic alignment images, and determine the dynamic interference deviation in the rapid assembly of the modular kitchen knife through the fluctuation characteristics of the alignment deviation sequence. The processing module is also used to determine the assembly alignment compensation amount between the blade and the handle when the assembly robot performs rapid assembly of the modular kitchen knife based on the structural error and the dynamic interference deviation. An execution module is used to calibrate the assembly alignment action of the assembly robot according to the assembly alignment compensation amount.

9. A computer device, characterized in that, The computer device includes a memory and a processor, the memory being used to store a computer program, and the processor being used to retrieve and run the computer program from the memory, causing the computer device to perform the modular kitchen knife rapid assembly method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions or code that, when executed on a computer, cause the computer to perform the modular kitchen knife rapid assembly method as described in any one of claims 1 to 7.

Images