Intelligent leveling control method and system for flexible mechanical arm

Abstract

The invention discloses an intelligent leveling control method and system for a flexible mechanical arm, and relates to the technical field of mechanical intelligent control, and the intelligent leveling control method comprises the following steps: collecting data of the flexible mechanical arm in a static and inclined state, and constructing a gravity field inclined reverse mapping model based on the collected data; extracting disturbance signal characteristics by adopting an FFT frequency domain analysis method, and generating a leveling control instruction in combination with a gravitational field inclination reverse mapping model; the controller is used for sending the leveling control instruction to a driving flexible actuator for leveling operation, and closed-loop correction is carried out based on operation feedback; a gravitational field inclination reverse mapping model is constructed, FFT frequency domain analysis is utilized to extract disturbance characteristics and generate a leveling control instruction, and a closed-loop feedback mechanism is combined to perform adaptive adjustment on a flexible actuator, so that the problems of low leveling control precision and poor robustness of the flexible mechanical arm are effectively solved.

Description

Technical Field

[0001] This invention relates to the field of intelligent mechanical control technology, and in particular to an intelligent leveling control method and system for a flexible robotic arm. Background Technology

[0002] With the continuous advancement of robotics technology, flexible robotic arms have been widely used in various fields such as service robots, medical assistance, and flexible manufacturing due to their high compliance, lightweight structure, and good safety. Compared with traditional rigid robotic arms, flexible robotic arms have significant advantages in tasks such as human collaboration, coping with complex environmental interference, and performing flexible grasping. However, due to the high elasticity of their body structure and the complexity of posture control, their spatial posture adjustment and dynamic stability control have become one of the key issues in current research and engineering applications. Especially in dynamic scenarios or non-ideal working environments, external disturbances, gravity imbalances, and other factors can easily cause the robotic arm's posture to deviate, thereby affecting the overall control accuracy and response stability of the system. In recent years, related research has attempted to introduce various sensors to achieve state feedback, construct motion models using physical modeling methods, or use learning algorithms for adjustment and control. Although some progress has been made, there is still considerable room for improvement in real-time performance, adaptive capabilities, and control closed-loop accuracy.

[0003] In existing technologies, a common approach is to reduce the attitude leveling problem of flexible robotic arms to the direct calculation and error correction of position and angle sensor data. However, this method struggles to accurately reproduce the true tilt state of the flexible arm in a gravitational field under uncertain disturbance conditions. Furthermore, existing signal processing and control strategies, such as time-domain filtering and PID control, are slow to respond to complex frequency disturbances or coupled nonlinear behaviors, resulting in lag in leveling commands and impacting adjustment efficiency and accuracy. Moreover, current closed-loop feedback systems primarily focus on error compensation, lacking control strategy optimization mechanisms based on disturbance source characteristics. Therefore, a smart leveling method that integrates attitude modeling, disturbance identification, and control decision-making is urgently needed to improve the stability, autonomy, and leveling control performance of flexible robotic arms in non-ideal environments. Summary of the Invention

[0004] In view of the aforementioned existing problems, the present invention is proposed.

[0005] Therefore, this invention provides an intelligent leveling control method for a flexible robotic arm, which solves the problems of attitude leveling accuracy and control response lag under dynamic disturbance and gravity imbalance conditions.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution: In a first aspect, the present invention provides an intelligent leveling control method for a flexible robotic arm, which includes collecting data of the flexible robotic arm in a static and tilted state, and constructing a gravity field tilt inverse mapping model based on the collected data. The FFT frequency domain analysis method is used to extract the features of the disturbance signal, and the leveling control command is generated by combining the gravity field tilt inverse mapping model. The controller sends leveling control commands to the flexible actuator to perform leveling operations and performs closed-loop corrections based on the operation feedback.

[0007] As a preferred embodiment of the intelligent leveling control method for a flexible robotic arm described in this invention, the method of collecting data from the flexible robotic arm in both stationary and tilted states refers to deploying IMU sensors and flexible position coding sensors at both ends and joints of the flexible robotic arm to collect triaxial acceleration, triaxial angular velocity, and position coding information, and outputting a dataset of the robotic arm at each moment. Each data point in the dataset includes triaxial acceleration. Triaxial angular velocity and angle data ; The data set of the robotic arm at each moment is uploaded to the database for storage.

[0008] As a preferred embodiment of the intelligent leveling control method for a flexible robotic arm described in this invention, the step of constructing a gravity field tilt inverse mapping model based on the collected data refers to calculating the change in acceleration of the robotic arm under tilted posture. ; Under tilted attitude, the tilt angle of node M at time t is calculated using the included angle formula based on the change in acceleration and the stationary reference acceleration. cosine value ; The tilt angle of the robotic arm is obtained by taking the inverse cosine. ; Based on acceleration change Inclined angle of the robotic arm Obtain the gravity field tilt inverse mapping model .

[0009] As a preferred embodiment of the intelligent leveling control method for a flexible robotic arm described in this invention, the step of extracting disturbance signal features using the FFT frequency domain analysis method refers to performing a Fourier transform on the acceleration change of each axis to obtain the complex spectrum of the acceleration change of the i-th axis at node M at time t in the frequency domain. ; Calculate the power spectrum of the i-th axis at node M using complex spectrum. ; Extract the frequency corresponding to the maximum value in the power spectrum as the main perturbation frequency. ; Extracting perturbation features of M-node in the multi-axis frequency domain Including the main perturbation frequency at node Mx y-axis dominant perturbation frequency and the dominant perturbation frequency of the z-axis ; The final output is the perturbation characteristics in the multi-axis frequency domain. Used to generate leveling control commands.

[0010] As a preferred embodiment of the intelligent leveling control method for a flexible robotic arm described in this invention, the step of generating leveling control commands by combining a gravity field tilt reverse mapping model refers to constructing direction-aware weights through multi-axis frequency domain perturbation features. Based on perceptual weights Generate single-axis direction control commands ,pass Obtain control command vector Final output This is a leveling control command.

[0011] As a preferred embodiment of the intelligent leveling control method for a flexible robotic arm described in this invention, the step of sending the leveling control command to the flexible actuator using the controller to perform the leveling operation refers to using the controller to analyze the multi-axis target deformation of each node in the leveling control command, setting the actuator to the initial state, and using the controller to send the analyzed command to the flexible actuator, which then levels the robotic arm according to the command.

[0012] As a preferred embodiment of the intelligent leveling control method for a flexible robotic arm described in this invention, the step of performing closed-loop correction based on operation feedback refers to collecting angle data of each node of the leveled robotic arm. The collected angle data is compared with the angle data of the robotic arm in its standard leveling state. By comparison, the angle difference is obtained. Set an angle difference threshold. : like Greater than or equal to Regenerate the leveling command; like Less than The adjustment experience generated during the leveling process will be uploaded to the database.

[0013] Secondly, the present invention provides an intelligent leveling control system for a flexible robotic arm, comprising, The data acquisition module is used to collect data from the robotic arm in both stationary and tilted states. The modeling module is used to construct a gravity field tilt inverse mapping model using the collected data; The signal extraction module is used to perform frequency domain analysis on the robotic arm using FFT to extract disturbance features; The instruction generation module is used to generate leveling instructions based on the model and disturbance characteristics. The execution control module is used to control the flexible actuator to respond to leveling commands; The closed-loop correction module is used for error detection and correction based on operational feedback.

[0014] Thirdly, the present invention provides a computer device including a memory and a processor, wherein the memory stores a computer program, wherein when the computer program is executed by the processor, it implements any step of the intelligent leveling control method for a flexible robotic arm as described in the first aspect of the present invention.

[0015] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the intelligent leveling control method for a flexible robotic arm as described in the first aspect of the present invention.

[0016] The beneficial effects of this invention are as follows: It collects state data of the flexible robotic arm in both static and tilted states, constructs a gravity field tilt-back mapping model, and achieves a precise correlation between posture and gravity changes. This effectively overcomes the problems of strong nonlinearity in flexible structures and poor adaptability of traditional modeling methods, providing a high-precision data foundation for subsequent posture leveling control. Based on this, it introduces Fast Fourier Transform to perform frequency domain analysis on disturbance signals, extracts their frequency characteristics, and combines this with the tilt mapping model to generate leveling control commands. This achieves efficient linkage from disturbance identification to control response, not only improving the ability to identify periodic disturbances and transient interferences but also enhancing the adaptability of the control strategy to complex working environments. Furthermore, by sending the leveling control commands to the flexible actuator to execute actions and performing closed-loop error correction based on operational feedback, the system possesses dynamic adjustment and continuous optimization capabilities, significantly improving the robustness and real-time response performance of the control system. Attached Figure Description

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

[0018] Figure 1 This is a flowchart of an intelligent leveling control method for a flexible robotic arm in Example 1.

[0019] Figure 2 This is a structural diagram of an intelligent leveling control system for a flexible robotic arm in Example 1. Detailed Implementation

[0020] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0021] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0022] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0023] Example 1, referring to Figure 1 and Figure 2 This is the first embodiment of the present invention, which provides an intelligent leveling control method for a flexible robotic arm, comprising the following steps: S1: Collect data on the flexible robotic arm in both stationary and tilted states, and construct a gravity field tilt inverse mapping model based on the collected data.

[0024] Specifically, collecting data from the flexible robotic arm in both stationary and tilted states involves deploying IMU sensors and flexible position coding sensors at both ends and joints of the flexible robotic arm to collect triaxial acceleration, triaxial angular velocity, and position coding information, and outputting a dataset of the robotic arm at each moment. : , Where t is time t and M is the node number. The data collected by the sensor deployed on the Mth node at time t, Specifically, it is expressed as follows: , in, Let M be the triaxial acceleration collected at time t. Let M be the triaxial angular velocity collected by node M at time t. The angle data collected by node M at time t; Triaxial acceleration Specifically, it is expressed as follows: , in, , , These are the data collected by node M at time t. , , Acceleration on the axis; Triaxial angular velocity Specifically, it is expressed as follows: , in, , , These are the data collected by node M at time t. , , Angular velocity on the axis; The data set of the robotic arm at each moment is uploaded to the database for storage.

[0025] By constructing a multi-source sensing system consisting of an IMU and a flexible position coding sensor, and in conjunction with a high-frequency data upload mechanism, a high-precision, full-coverage flexible robotic arm status acquisition platform was formed. This not only improved the spatiotemporal consistency and information density of the data, but also laid a solid foundation for constructing a gravity field tilt mapping model, significantly enhancing the system's sensing capabilities.

[0026] Furthermore, based on the collected data, a gravity field tilt inverse mapping model is constructed to calculate the change in acceleration of the robotic arm under tilted posture. : , in, The stationary reference acceleration, which is contributed solely by the gravitational field and collected by the sensors when the robotic arm is in a fixed horizontal position, is specifically expressed as follows: , in, , , Let M be the rest reference acceleration of node M along the x, y, and z axes contributed solely by the gravitational field; Under tilted attitude, the tilt angle of node M at time t is calculated using the included angle formula based on the change in acceleration and the stationary reference acceleration. cosine value : , Among them, the modulus in the static direction Specifically, it is expressed as follows: , Specifically, the acceleration modulus is expressed as: : , The tilt angle of the robotic arm is obtained by taking the inverse cosine. : , A gravity field tilt inverse mapping model is obtained based on the acceleration change and the robotic arm tilt angle. : , Where n is the highest order of the tilt angle polynomial, p is the total order limit of the acceleration perturbation polynomial, and k is the current angle power. , , To control the number of acceleration disturbance terms on each axis, These are the polynomial coefficients obtained from model training.

[0027] By constructing a gravity field tilt inverse mapping model based on the relationship between acceleration change and attitude angle, accurate identification of the tilt state of a flexible robotic arm is achieved without relying on a complex dynamic model. By comparing and analyzing acceleration data from the static and tilted states, and combining the vector angle formula to calculate the tilt angle, the attitude estimation has good interpretability and feasibility. This model simplifies the system's attitude recognition process, improves computational efficiency and deployment convenience, and not only provides a high-precision tilt information foundation for subsequent leveling strategies, but also enhances the perception capability and control accuracy of the entire system.

[0028] S2: The FFT frequency domain analysis method is used to extract the features of the disturbance signal, and the leveling control command is generated by combining the gravity field tilt inverse mapping model.

[0029] Specifically, the FFT frequency domain analysis method is used to extract the features of the disturbance signal, which involves performing a Fourier transform on the acceleration change of each axis to obtain the complex spectrum of the acceleration change of the i-th axis at node M at time t in the frequency domain. : , in, This is a Fourier transform operation. Let i be the frequency variable, where i represents the i-th axis of the current node; Calculate the power spectrum of the i-th axis at node M using complex spectrum. : , Extract the frequency corresponding to the maximum value in the power spectrum as the main perturbation frequency. : , Extracting perturbation features of M-node in the multi-axis frequency domain : , in, , , These are the main perturbation frequencies of node M along the x, y, and z axes, respectively. The final output is the perturbation characteristics in the multi-axis frequency domain. Used to generate leveling control commands.

[0030] By performing a Fast Fourier Transform on the acceleration changes of each axis, the time-domain signal is converted to the frequency domain, extracting important frequency information containing the regularity of disturbances and enhancing the ability to identify periodic disturbances. By calculating the complex spectrum to obtain the power spectrum, the energy distribution of different frequency components is quantified, thereby accurately extracting the main disturbance frequency of each axis and solving the problem of difficulty in distinguishing interference components in the case of mixed multi-source disturbances. At the same time, the main disturbance frequency features of multiple axes at each node are extracted separately, realizing a comprehensive characterization of the disturbance state in multiple directions in space. The final output multi-axis frequency domain disturbance features provide a key reference for subsequent leveling control, making the control commands more accurately match the current disturbance mode.

[0031] Furthermore, by combining the gravity field tilt inverse mapping model to generate leveling control commands, direction-aware weights are constructed through multi-axis frequency domain perturbation features. : , Generate single-axis direction control commands :

[0032] Where K is the set weight; pass Obtain control command vector : , in, This is the leveling control command vector for node M; Final output This is a leveling control command.

[0033] By constructing direction-aware weights based on multi-axis frequency domain disturbance characteristics, the importance of each main disturbance direction is dynamically quantified, enhancing the system's real-time perception capability of different disturbance axis priorities. Single-axis direction control commands are generated based on the direction-aware weights, enabling the control strategy to respond differently to the disturbance intensity of each axis, solving the problem of uniform adjustment amplitude and lack of specificity of commands for each axis in existing control methods. By integrating single-axis control commands into multi-axis control command vectors, the coordination and real-time performance of control outputs in multiple spatial dimensions are ensured. The final generated control commands can effectively adapt to the current robot arm posture and main disturbance state, providing highly responsive and precisely matched control inputs for subsequent leveling operations.

[0034] S3: The controller sends the leveling control command to the flexible actuator to perform the leveling operation, and performs closed-loop correction based on the operation feedback.

[0035] Specifically, the controller sends the leveling control command to the flexible actuator to perform the leveling operation. The controller analyzes the multi-axis target deformation of each node in the leveling control command, sets the actuator to the initial state, and sends the analyzed command to the flexible actuator. The actuator then levels the robotic arm according to the command.

[0036] By using a controller to analyze the multi-axis target deformation of each node in the leveling control command, the decomposition and precise matching of the command are achieved, ensuring that the control requirements of each node in all directions of space are accurately identified, thus solving the problem of difficult effective decomposition of complex multi-axis commands at the execution end. By setting the actuator to its initial state, the interference of historical residual deformation on the current leveling action is effectively avoided, improving the stability of the execution process. The controller sends the analyzed commands to the flexible actuator in real time, enabling the flexible robotic arm to respond quickly and complete the leveling operation of each node in multiple directions, ensuring the continuity and coordination of the leveling action.

[0037] Furthermore, closed-loop correction based on operational feedback refers to collecting angle data from each node of the leveled robotic arm. The collected angle data is compared with the angle data of the robotic arm in its standard leveling state. By comparison, the angle difference is obtained. Set an angle difference threshold. : like Greater than or equal to Regenerate the leveling command; like Less than The adjustment experience generated during the leveling process will be uploaded to the database.

[0038] By collecting angle data from each node of the robotic arm after leveling and comparing it in real time with the standard leveling state, the deviation between the actual leveling result and the target state can be effectively monitored, solving the problem of not being able to dynamically confirm the leveling effect in traditional control. By setting an angle difference threshold, the system can determine whether to regenerate the leveling command based on the magnitude of the deviation, ensuring that the leveling process has adaptive correction capabilities and significantly improving leveling accuracy and process stability. When the angle difference is lower than the set threshold, the current leveling adjustment experience is uploaded to the database, realizing the continuous accumulation and optimization of control experience and providing historical data support for subsequent leveling control.

[0039] This embodiment also provides an intelligent leveling control system for a flexible robotic arm, including: The data acquisition module is used to collect data from the robotic arm in both stationary and tilted states. The modeling module is used to construct a gravity field tilt inverse mapping model using the collected data; The signal extraction module is used to perform frequency domain analysis on the robotic arm using FFT to extract disturbance features; The instruction generation module is used to generate leveling instructions based on the model and disturbance characteristics. The execution control module is used to control the flexible actuator to respond to leveling commands; The closed-loop correction module is used for error detection and correction based on operational feedback.

[0040] This embodiment also provides a computer device applicable to an intelligent leveling control method for a flexible robotic arm, comprising: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to realize an intelligent leveling control system for a flexible robotic arm as proposed in the above embodiment.

[0041] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0042] This embodiment also provides a storage medium on which a computer program is stored. When executed by a processor, the program implements an intelligent leveling control system for a flexible robotic arm as proposed in the above embodiments. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0043] In summary, this invention constructs a gravity field tilt-back mapping model by collecting state data of the flexible robotic arm in both static and tilted states. This model achieves a precise correlation between posture and gravity changes, effectively overcoming the problems of strong nonlinearity in flexible structures and poor adaptability of traditional modeling methods. It provides a high-precision data foundation for subsequent posture leveling control. Furthermore, a Fast Fourier Transform is introduced to perform frequency domain analysis on the disturbance signal, extracting its frequency characteristics. These characteristics are then combined with the tilt mapping model to generate leveling control commands, achieving efficient linkage from disturbance identification to control response. This not only improves the ability to identify periodic disturbances and transient interferences but also enhances the adaptability of the control strategy to complex working environments. Moreover, by sending the leveling control commands to the flexible actuator to execute actions and performing closed-loop error correction based on operational feedback, the system possesses dynamic adjustment and continuous optimization capabilities, significantly improving the robustness and real-time response performance of the control system.

[0044] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. An intelligent leveling control method for a flexible robotic arm, characterized in that: include, Data is collected on the flexible robotic arm in both stationary and tilted states, and a gravity field tilt inverse mapping model is constructed based on the collected data. The FFT frequency domain analysis method is used to extract the features of the disturbance signal, and the leveling control command is generated by combining the gravity field tilt inverse mapping model. The controller sends leveling control commands to the flexible actuator to perform leveling operations and performs closed-loop corrections based on the operation feedback.

2. The intelligent leveling control method for a flexible robotic arm as described in claim 1, characterized in that: The data acquisition of the flexible robotic arm in both stationary and tilted states refers to deploying IMU sensors and flexible position coding sensors at both ends and joints of the flexible robotic arm to collect triaxial acceleration, triaxial angular velocity, and position coding information, and outputting a dataset of the robotic arm at each moment. Each data point in the dataset includes triaxial acceleration. Triaxial angular velocity and angle data ; The data set of the robotic arm at each moment is uploaded to the database for storage.

3. The intelligent leveling control method for a flexible robotic arm as described in claim 2, characterized in that: The gravity field tilt inverse mapping model constructed based on the collected data refers to calculating the change in acceleration of the robotic arm under tilted posture. ; Under tilted attitude, the tilt angle of node M at time t is calculated using the included angle formula based on the change in acceleration and the stationary reference acceleration. cosine value ; The tilt angle of the robotic arm is obtained by taking the inverse cosine. ; Based on acceleration change Inclined angle of the robotic arm Obtain the gravity field tilt inverse mapping model .

4. The intelligent leveling control method for a flexible robotic arm as described in claim 3, characterized in that: The FFT frequency domain analysis method is used to extract the features of the disturbance signal. This involves performing a Fourier transform on the acceleration change of each axis to obtain the complex spectrum of the acceleration change of the i-th axis at node M at time t in the frequency domain. ; Calculate the power spectrum of the i-th axis at node M using complex spectrum. ; Extract the frequency corresponding to the maximum value in the power spectrum as the main perturbation frequency. ; Extracting perturbation features of M-node in the multi-axis frequency domain Including the main perturbation frequency at node Mx y-axis dominant perturbation frequency and the dominant perturbation frequency of the z-axis ; The final output is the perturbation characteristics in the multi-axis frequency domain. Used to generate leveling control commands.

5. The intelligent leveling control method for a flexible robotic arm as described in claim 4, characterized in that: The method of generating leveling control commands by combining the gravity field tilt inverse mapping model refers to constructing direction-aware weights through multi-axis frequency domain perturbation features. Based on perceptual weights Generate single-axis direction control commands ,pass Obtain control command vector Final output This is a leveling control command.

6. The intelligent leveling control method for a flexible robotic arm as described in claim 5, characterized in that: The step of using the controller to send the leveling control command to the drive flexible actuator for leveling operation refers to using the controller to parse the multi-axis target deformation of each node in the leveling control command, setting the actuator to the initial state, and using the controller to send the parsed command to the drive flexible actuator, and the actuator levels the robotic arm according to the command.

7. The intelligent leveling control method for a flexible robotic arm as described in claim 6, characterized in that: The closed-loop correction based on operation feedback refers to collecting angle data of each node of the leveled robotic arm. The collected angle data is compared with the angle data of the robotic arm in its standard leveling state. By comparison, the angle difference is obtained. Set an angle difference threshold. : like Greater than or equal to Regenerate the leveling command; like Less than The adjustment experience generated during the leveling process will be uploaded to the database.

8. An intelligent leveling control system for a flexible robotic arm, based on the intelligent leveling control method for a flexible robotic arm according to any one of claims 1 to 7, characterized in that: include, The data acquisition module is used to collect data from the robotic arm in both stationary and tilted states. The modeling module is used to construct a gravity field tilt inverse mapping model using the collected data; The signal extraction module is used to perform frequency domain analysis on the robotic arm using FFT to extract disturbance features; The instruction generation module is used to generate leveling instructions based on the model and disturbance characteristics. The execution control module is used to control the flexible actuator to respond to leveling commands; The closed-loop correction module is used for error detection and correction based on operational feedback.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the intelligent leveling control method for a flexible robotic arm as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the intelligent leveling control method for a flexible robotic arm as described in any one of claims 1 to 7.

Images