Robot motion track planning method and system

Abstract

The invention relates to the technical field of robot control, in particular to a robot motion track planning method and system. The method comprises the following steps: carrying out noise reduction processing on optimization target data through a sensor and a data noise reduction algorithm, and carrying out demand analysis processing on the optimization target data to obtain robot motion track motion demand data; optimizing a trajectory planning algorithm by using a particle swarm optimization algorithm on the basis of the motion demand data of the robot motion trajectory, optimizing a control algorithm, and performing system parameter optimization through the optimized trajectory planning algorithm and the optimized control algorithm to obtain optimized parameters of the robot motion trajectory fuzzy control system; and carrying out updating estimation and performance verification processing by utilizing a system identification method, and executing a corresponding motion track planning task according to a verification result. According to the invention, the performance and robustness of the robot motion track fuzzy control system can be improved so as to adapt to different environments and changing planning task requirements.

Description

Technical Field

[0001] The present invention relates to the technical field of robot control, and particularly to a method and system for robot motion trajectory planning. Background Art

[0002] Traditional robot motion trajectory planning methods usually use precise mathematical models and control algorithms to achieve. However, the uncertainties and complexities in the real environment make this method difficult and limited. To solve this problem, in recent years, fuzzy control technology has been widely applied in the field of robot control. Through fuzzy control, a robot can make decisions and controls according to fuzzy rules and empirical knowledge, so as to adapt to uncertain environments and changing task requirements. However, there are still some problems in the existing robot motion trajectory fuzzy control systems, such as problems in performance optimization and the accuracy of motion trajectory planning. Summary of the Invention

[0003] Based on this, it is necessary for the present invention to provide a method for robot motion trajectory planning to solve at least one of the above technical problems.

[0004] To achieve the above object, a method for robot motion trajectory planning includes the following steps:

[0005] Step S1: Obtain the optimization target data of the robot motion trajectory fuzzy control system through a sensor to obtain the robot motion trajectory optimization target data; and use a data denoising algorithm to perform denoising processing on the robot motion trajectory optimization target data to obtain the robot motion trajectory optimization target denoised data;

[0006] Step S2: Perform demand analysis processing on the robot motion trajectory optimization target denoised data to obtain the robot motion trajectory motion demand data; based on the robot motion trajectory motion demand data, use a particle swarm optimization algorithm to perform optimization processing on the trajectory planning algorithm of the robot motion trajectory fuzzy control system to obtain an optimized trajectory planning algorithm;

[0007] Step S3: Perform optimization processing on the control algorithm of the robot motion trajectory fuzzy control system based on the robot motion trajectory motion demand data to obtain an optimized control algorithm;

[0008] Step S4: Perform system parameter tuning processing on the robot motion trajectory fuzzy control system through the optimized trajectory planning algorithm and the optimized control algorithm to obtain the optimized parameters of the robot motion trajectory fuzzy control system; and use a system identification method to perform update estimation processing on the optimized parameters of the robot motion trajectory fuzzy control system to obtain an optimized robot motion trajectory fuzzy control system;

[0009] Step S5: Perform performance evaluation processing on the optimized robot motion trajectory fuzzy control system to obtain the performance evaluation result of the robot motion trajectory fuzzy control system; perform optimization verification processing based on the performance evaluation result of the robot motion trajectory fuzzy control system to obtain the optimization verification result of the robot motion trajectory fuzzy control system, so as to execute the corresponding motion trajectory planning task.

[0010] In the present invention, the optimization target data of the robot motion trajectory fuzzy control system is obtained through sensors, and the data noise reduction algorithm is used to perform noise reduction processing on the data to obtain the noise-reduced data of the robot motion trajectory optimization target. The data obtained by the sensors reflects the motion state of the robot in the environment and its interaction with the environment, and they are the basic data for the optimization process. Through noise reduction processing, the noise and interference in the data can be reduced, thereby improving the quality and reliability of the data, and providing a more accurate data basis for subsequent analysis and optimization. Secondly, through the requirement analysis processing of the noise-reduced data of the robot motion trajectory optimization target, the requirement analysis mainly sorts, analyzes, and extracts the data to determine the requirements and goals of the robot motion trajectory. At the same time, based on the motion requirement data of the robot motion trajectory, the particle swarm optimization algorithm is used to optimize the trajectory planning algorithm of the robot motion trajectory fuzzy control system to obtain the optimized trajectory planning algorithm. This can enable the robot to reach the predetermined goal more efficiently and accurately when planning the motion trajectory. Then, through the optimization processing of the control algorithm of the robot motion trajectory fuzzy control system based on the motion requirement data of the robot motion trajectory, where the control algorithm is the key part determining the motion behavior of the robot, and by optimizing the control algorithm, the motion performance and intelligence level of the robot can be improved. Optimizing based on the requirement data can make the control algorithm better adapt to the actual motion requirements, thereby improving the motion effect and control accuracy of the robot. Next, by using the optimized trajectory planning algorithm and the optimized control algorithm to perform system parameter tuning processing on the robot motion trajectory fuzzy control system, the motion performance and control effect of the robot can be further optimized, making the system more stable, reliable, and efficient. At the same time, the system identification method is used to update and estimate the optimized parameters, and the parameters of the system can be continuously optimized according to the actual operation data, enabling the system to adapt to different working environments and task requirements. Finally, through the performance evaluation processing of the optimized robot motion trajectory fuzzy control system, the performance evaluation can be carried out through indicators such as the stability, robustness, energy consumption, and response time of the system. By evaluating the performance of the system, the advantages and disadvantages of the system can be understood, and guidance and basis for further optimization can be provided. And, according to the performance evaluation result, the optimization verification processing is performed to verify the effect and feasibility of the optimized robot motion trajectory fuzzy control system in actual applications, further verifying the reliability and effectiveness of the system, so as to improve the performance of the robot motion trajectory fuzzy control system, thereby improving the accuracy of the robot motion trajectory planning task.

[0011] Preferably, the present invention further provides a robot motion trajectory planning system for executing the robot motion trajectory planning method as described above. The robot motion trajectory planning system includes:

[0012] A motion trajectory optimization target processing module, configured to obtain the optimization target data of the robot motion trajectory fuzzy control system through a sensor to obtain the robot motion trajectory optimization target data; and perform noise reduction processing on the robot motion trajectory optimization target data by using a data noise reduction algorithm, so as to obtain the robot motion trajectory optimization target noise reduction data;

[0013] A trajectory planning algorithm optimization module, configured to perform requirement analysis processing on the robot motion trajectory optimization target noise reduction data to obtain the robot motion trajectory motion requirement data; and optimize the trajectory planning algorithm of the robot motion trajectory fuzzy control system by using the particle swarm optimization algorithm based on the robot motion trajectory motion requirement data, so as to obtain an optimized trajectory planning algorithm;

[0014] A control algorithm optimization module, configured to optimize the control algorithm of the robot motion trajectory fuzzy control system by using the robot motion trajectory motion requirement data, so as to obtain an optimized control algorithm;

[0015] A fuzzy control system parameter optimization module, configured to perform system parameter tuning processing on the robot motion trajectory fuzzy control system by using the optimized trajectory planning algorithm and the optimized control algorithm to obtain the optimized parameters of the robot motion trajectory fuzzy control system; and perform update estimation processing on the optimized parameters of the robot motion trajectory fuzzy control system by using a system identification method, so as to obtain an optimized robot motion trajectory fuzzy control system;

[0016] A performance evaluation and verification processing module, configured to perform performance evaluation processing on the optimized robot motion trajectory fuzzy control system to obtain the performance evaluation result of the robot motion trajectory fuzzy control system; and perform optimization verification processing according to the performance evaluation result of the robot motion trajectory fuzzy control system to obtain the optimization verification result of the robot motion trajectory fuzzy control system, so as to execute the corresponding motion trajectory planning task.

[0017] In summary, the present invention provides a robot motion trajectory planning system. The optimization system consists of a motion trajectory optimization target processing module, a trajectory planning algorithm optimization module, a control algorithm optimization module, a fuzzy control system parameter optimization module, and a performance evaluation and verification processing module. It can implement any one of the robot motion trajectory planning methods described in the present invention, and is used to jointly realize a robot motion trajectory planning method through the operations between computer programs running on each module. The internal structure of the system cooperates with each other, and optimizes the trajectory planning algorithm and control algorithm of the robot motion trajectory fuzzy control system by using a variety of algorithms and technologies, and tunes the parameters of the robot motion trajectory fuzzy control system to achieve precise control of the robot motion trajectory, thereby improving the control performance and robustness. This can greatly reduce repetitive work and manpower investment, and can quickly and effectively provide a more accurate and efficient optimization process for the robot motion trajectory fuzzy control system, thus simplifying the operation process of the robot motion trajectory planning system. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] By reading the detailed description of the non-restrictive embodiments with reference to the following drawings, other features, objects, and advantages of the present invention will become more apparent:

[0019] Figure 1 It is a schematic flow chart of the steps of the robot motion trajectory planning method of the present invention;

[0020] Figure 2 is Figure 1 a detailed schematic flow chart of step S1 in

[0021] Figure 3 is Figure 2 a detailed schematic flow chart of step S13 in DETAILED DESCRIPTION OF THE EMBODIMENTS

[0022] The technical method of the present invention will be clearly and completely described below with reference to the drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of them. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0023] In addition, the attached drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus repeated descriptions thereof will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor methods and / or microcontroller methods.

[0024] It should be understood that although terms such as "first" and "second" may be used herein to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the associated listed items.

[0025] To achieve the above object, please refer to Figures 1 to 3 , the present invention provides a method for robot motion trajectory planning, and the method includes the following steps:

[0026] Step S1: Obtain the optimization target data of the robot motion trajectory fuzzy control system through a sensor to obtain the robot motion trajectory optimization target data; and use a data denoising algorithm to perform denoising processing on the robot motion trajectory optimization target data to obtain the robot motion trajectory optimization target denoised data;

[0027] Step S2: Perform requirement analysis processing on the robot motion trajectory optimization target denoised data to obtain the robot motion trajectory motion requirement data; based on the robot motion trajectory motion requirement data, use the particle swarm optimization algorithm to optimize the trajectory planning algorithm of the robot motion trajectory fuzzy control system to obtain an optimized trajectory planning algorithm;

[0028] Step S3: Optimize the control algorithm of the robot motion trajectory fuzzy control system based on the robot motion trajectory motion requirement data to obtain an optimized control algorithm;

[0029] Step S4: Perform system parameter tuning processing on the robot motion trajectory fuzzy control system through the optimized trajectory planning algorithm and the optimized control algorithm to obtain the optimized parameters of the robot motion trajectory fuzzy control system; and use the system identification method to perform update estimation processing on the optimized parameters of the robot motion trajectory fuzzy control system to obtain an optimized robot motion trajectory fuzzy control system;

[0030] Step S5: Perform performance evaluation processing on the optimized robot motion trajectory fuzzy control system to obtain the performance evaluation result of the robot motion trajectory fuzzy control system; perform optimization verification processing based on the performance evaluation result of the robot motion trajectory fuzzy control system to obtain the optimization verification result of the robot motion trajectory fuzzy control system, so as to execute the corresponding motion trajectory planning task.

[0031] In the embodiment of the present invention, please refer to Figure 1 As shown in the schematic diagram of the step flow of the robot motion trajectory planning method of the present invention. In this example, the steps of the robot motion trajectory planning method include:

[0032] Step S1: Obtain the optimization target data of the robot motion trajectory fuzzy control system through sensors to obtain the robot motion trajectory optimization target data; and use a data denoising algorithm to perform denoising processing on the robot motion trajectory optimization target data to obtain the robot motion trajectory optimization target denoised data.

[0033] In the embodiment of the present invention, corresponding sensor devices such as lidar, cameras, and inertial measurement units are used to obtain the optimization target data of the robot motion trajectory fuzzy control system to obtain optimization target information such as the position, attitude, and speed of the robot in the environment, and obtain the robot motion trajectory optimization target data. Then, a suitable data denoising algorithm is constructed to perform denoising processing on the robot motion trajectory optimization target data to eliminate the influence of noise in the robot motion trajectory optimization target data, and finally obtain the robot motion trajectory optimization target denoised data.

[0034] Step S2: Perform requirement analysis processing on the robot motion trajectory optimization target denoised data to obtain the robot motion trajectory motion requirement data; based on the robot motion trajectory motion requirement data, use the particle swarm optimization algorithm to optimize the trajectory planning algorithm of the robot motion trajectory fuzzy control system to obtain the optimized trajectory planning algorithm.

[0035] In the embodiment of the present invention, by performing requirement analysis on the robot motion trajectory optimization target denoised data and considering the motion ability, constraint conditions, task requirements, etc. of the robot, the motion requirements such as the motion target, motion planning range, and path constraints of the robot motion trajectory are determined to obtain the robot motion trajectory motion requirement data. Then, by combining the robot motion trajectory motion requirement data, the particle swarm optimization algorithm is used to optimize the trajectory planning algorithm of the robot motion trajectory fuzzy control system to find the best trajectory planning algorithm parameters in the search space, and finally obtain the optimized trajectory planning algorithm.

[0036] Step S3: Optimize the control algorithm of the robot motion trajectory fuzzy control system based on the robot motion trajectory motion requirement data to obtain the optimized control algorithm.

[0037] In an embodiment of the present invention, appropriate fuzzy variables are selected according to the motion trajectory motion requirement data of the robot to represent the motion trajectory of the robot, and a suitable fuzzy rule base is constructed according to the characteristics of the fuzzy variables and the range of the requirement data. Then, the control algorithm parameters of the fuzzy control system for the robot motion trajectory are optimized according to the fuzzy rule base, and finally an optimized control algorithm is obtained.

[0038] Step S4: The system parameters of the fuzzy control system for the robot motion trajectory are optimized by using the optimized trajectory planning algorithm and the optimized control algorithm to obtain the optimized parameters of the fuzzy control system for the robot motion trajectory; and the optimized parameters of the fuzzy control system for the robot motion trajectory are updated and estimated by using the system identification method to obtain the optimized fuzzy control system for the robot motion trajectory.

[0039] In an embodiment of the present invention, according to the operating characteristics and requirements of the robot, the system parameters to be optimized are selected, and the parameters of the selected fuzzy control system for the robot motion trajectory are optimized by using the optimized trajectory planning algorithm and the optimized control algorithm to obtain the optimized parameters of the fuzzy control system for the robot motion trajectory. Then, according to the characteristics and problem requirements of the fuzzy control system for the robot motion trajectory, corresponding system identification methods such as the least squares method and the maximum likelihood estimation method are selected to update and estimate the optimized parameters of the fuzzy control system for the robot motion trajectory, so as to estimate the behavioral characteristics and dynamic performance parameters of the fuzzy control system for the robot motion trajectory and perform real-time update of the system, and finally an optimized fuzzy control system for the robot motion trajectory is obtained.

[0040] Step S5: The performance of the optimized fuzzy control system for the robot motion trajectory is evaluated to obtain the performance evaluation result of the fuzzy control system for the robot motion trajectory; and the optimization verification process is performed according to the performance evaluation result of the fuzzy control system for the robot motion trajectory to obtain the optimization verification result of the fuzzy control system for the robot motion trajectory, so as to execute the corresponding motion trajectory planning task.

[0041] In an embodiment of the present invention, according to the motion requirements and control objectives of the robot, performance indicators in aspects such as appropriate motion accuracy, response speed, stability, and energy efficiency are defined, and the optimized fuzzy control system for the robot motion trajectory is analyzed based on the defined performance indicators to compare the gap between the analysis result and the expected objective, thereby obtaining the performance evaluation result of the fuzzy control system for the robot motion trajectory. Then, based on the performance evaluation result of the fuzzy control system for the robot motion trajectory, the problems or deficiencies existing in the fuzzy control system for the robot motion trajectory are identified, and corresponding optimization strategies such as parameter adjustment, algorithm improvement, and control strategy update are formulated according to the problem identification result. Meanwhile, the formulated optimization strategies are applied in the fuzzy control system for the robot motion trajectory for adjustment and improvement verification processing to verify the performance of the optimized fuzzy control system for the robot motion trajectory, obtaining the optimization verification result of the fuzzy control system for the robot motion trajectory. Finally, the corresponding robot motion trajectory planning task is executed according to the verified fuzzy control system for the robot motion trajectory.

[0042] The present invention obtains the optimization target data of the robot motion trajectory fuzzy control system through sensors, and uses a data denoising algorithm to process the data for denoising, so as to obtain the denoised data of the robot motion trajectory optimization target. The data obtained by the sensors reflects the motion state of the robot in the environment and its interaction with the environment, and they are the basic data for the optimization process. Through denoising processing, the noise and interference in the data can be reduced, thereby improving the quality and reliability of the data, and providing a more accurate data basis for subsequent analysis and optimization. Secondly, through the requirement analysis and processing of the denoised data of the robot motion trajectory optimization target, the requirement analysis mainly sorts, analyzes and extracts the data to determine the requirements and goals of the robot motion trajectory. At the same time, based on the motion requirement data of the robot motion trajectory, the particle swarm optimization algorithm is used to optimize the trajectory planning algorithm of the robot motion trajectory fuzzy control system, so as to obtain an optimized trajectory planning algorithm. This can enable the robot to reach the predetermined goal more efficiently and accurately when planning the motion trajectory. Then, through the optimization processing of the control algorithm of the robot motion trajectory fuzzy control system based on the motion requirement data of the robot motion trajectory, where the control algorithm is the key part that determines the motion behavior of the robot, and by optimizing the control algorithm, the motion performance and intelligence level of the robot can be improved. Optimizing based on the requirement data can make the control algorithm better adapt to the actual motion requirements, thereby improving the motion effect and control accuracy of the robot. Next, by using the optimized trajectory planning algorithm and the optimized control algorithm to perform system parameter tuning on the robot motion trajectory fuzzy control system, the motion performance and control effect of the robot can be further optimized, making the system more stable, reliable and efficient. At the same time, using the system identification method to update and estimate the optimized parameters can continuously optimize the system parameters according to the actual operation data, so that the system can adapt to different working environments and task requirements. Finally, through the performance evaluation of the optimized robot motion trajectory fuzzy control system, the performance evaluation can be carried out through indicators such as the stability, robustness, energy consumption, and response time of the system. By evaluating the performance of the system, the advantages and disadvantages of the system can be understood, and guidance and basis for further optimization can be provided. And, according to the performance evaluation results, the optimization verification process can be carried out to verify the effect and feasibility of the optimized robot motion trajectory fuzzy control system in actual applications, further verify the reliability and effectiveness of the system, so as to improve the performance of the robot motion trajectory fuzzy control system, thereby improving the accuracy of the robot motion trajectory planning task.

[0043] Preferably, step S1 includes the following steps:

[0044] Step S11: Obtain the optimization target data of the robot motion trajectory fuzzy control system through sensors to obtain the robot motion trajectory optimization target data;

[0045] Step S12: Perform data preprocessing on the robot motion trajectory optimization target data to obtain the robot motion trajectory optimization target data to be denoised;

[0046] Step S13: Use a data denoising algorithm to perform denoising processing on the robot motion trajectory optimization target data to be denoised, and obtain the robot motion trajectory optimization target denoised data.

[0047] As an embodiment of the present invention, refer to Figure 2 shown, for Figure 1 the detailed step flow schematic diagram of step S1 in

[0048] Step S11: Obtain the optimization target data of the robot motion trajectory fuzzy control system through sensors to obtain the robot motion trajectory optimization target data;

[0049] In the embodiment of the present invention, corresponding sensor devices such as lidar, cameras, and inertial measurement units are used to obtain the optimization target data of the robot motion trajectory fuzzy control system, so as to obtain optimization target information such as the position, attitude, and speed of the robot in the environment, and finally obtain the robot motion trajectory optimization target data.

[0050] Step S12: Perform data preprocessing on the robot motion trajectory optimization target data to obtain the robot motion trajectory optimization target data to be denoised;

[0051] In the embodiment of the present invention, after performing preprocessing such as missing value filling, duplicate data removal, abnormal data, invalid data, normalization, and standardization on the robot motion trajectory optimization target data, the robot motion trajectory optimization target data to be denoised is finally obtained.

[0052] Step S13: Use a data denoising algorithm to perform denoising processing on the robot motion trajectory optimization target data to be denoised, and obtain the robot motion trajectory optimization target denoised data.

[0053] In the embodiment of the present invention, a suitable data denoising algorithm is constructed by combining the initial time of noise value calculation, the end time of noise value calculation, the noise smoothing fitting parameter, the Gaussian noise standard deviation, the motion trajectory time variable, the motion trajectory state variable, the trajectory position, the trajectory speed, the noise probability distribution function, and related parameters to perform denoising processing on the robot motion trajectory optimization target data to be denoised, so as to eliminate the influence of noise in the robot motion trajectory optimization target data to be denoised, and finally obtain the robot motion trajectory optimization target denoised data.

[0054] The present invention first obtains the optimization target data of the robot motion trajectory fuzzy control system by using sensors. The sensors can be various types of devices, such as lidar, cameras, inertial measurement units, etc., which are used to obtain optimization target information such as the position, attitude, and speed of the robot in the environment. The data obtained through the sensors can reflect the current state of the robot and its interaction with the environment, and they provide key input data for the optimization process. Then, data preprocessing is performed on the obtained robot motion trajectory optimization target data. The process of this data preprocessing includes operations such as data cleaning, detection and processing of duplicate values and outliers, and handling of missing values, so as to better adapt to the subsequent noise reduction algorithm processing. Through data preprocessing, duplicate data and abnormal data in the data can be removed, missing data can be filled, and the data can be normalized or standardized for subsequent analysis and optimization processes. This preprocessing process can improve the quality of the data, reduce the adverse effects on subsequent analysis and decision-making, and ensure the accuracy and reliability of the data used. In addition, through data preprocessing, the effect of the subsequent noise reduction algorithm can be improved, and a more accurate and reliable data basis can be provided for the optimization process. Finally, by using a suitable data noise reduction algorithm to perform noise reduction processing on the robot motion trajectory optimization target data to be denoised after data preprocessing, the noise, interference, and unreasonable fluctuations in the data can be removed, thereby revealing the true motion trajectory optimization target. Through data noise reduction processing, more stable and reliable robot motion trajectory optimization target denoised data can be obtained, improving the accuracy and reliability of the motion trajectory data, and thus providing more accurate basic data for subsequent analysis and optimization.

[0055] Preferably, step S13 includes the following steps:

[0056] Step S131: Calculate the noise value of the robot motion trajectory optimization target data to be denoised by using a data noise reduction algorithm to obtain the trajectory optimization target data noise value;

[0057] Among them, the function formula of the data noise reduction algorithm is as follows:

[0058]

[0059] In the formula, N is the trajectory optimization target data noise value, t0 is the initial time of noise value calculation, t f is the end time of noise value calculation, λ is the noise smoothing fitting parameter, σ is the standard deviation of Gaussian noise, t is the motion trajectory time variable, s is the motion trajectory state variable, x(t, s) is the trajectory position of the actual robot motion trajectory optimization target data at time t and state s, is the trajectory position of the robot motion trajectory optimization target data to be denoised at time t and state s, T is the transpose symbol, v is the trajectory speed of the actual robot motion trajectory optimization target data, The trajectory speed of the data to be denoised for the robot motion trajectory optimization target is the noise probability distribution function of the data to be denoised for the robot motion trajectory optimization target. p(x, v) is the noise probability distribution function of the actual robot motion trajectory optimization target data, and μ is the correction value of the noise value of the trajectory optimization target data;

[0060] Step S132: Judge the noise value of the trajectory optimization target data according to the preset noise threshold of the trajectory optimization target data. When the noise value of the trajectory optimization target data is greater than or equal to the preset noise threshold of the trajectory optimization target data, the data to be denoised for the robot motion trajectory optimization target corresponding to the noise value of the trajectory optimization target data is removed to obtain the denoised data for the robot motion trajectory optimization target;

[0061] Step S133: Judge the noise value of the trajectory optimization target data according to the preset noise threshold of the trajectory optimization target data. When the noise value of the trajectory optimization target data is less than the preset noise threshold of the trajectory optimization target data, the data to be denoised for the robot motion trajectory optimization target corresponding to the noise value of the trajectory optimization target data is directly defined as the denoised data for the robot motion trajectory optimization target.

[0062] As an embodiment of the present invention, refer to Figure 3 shown, for Figure 2 the detailed step flow diagram of step S13 in

[0063] Step S131: Calculate the noise value of the data to be denoised for the robot motion trajectory optimization target by using a data denoising algorithm to obtain the noise value of the trajectory optimization target data;

[0064] In the embodiment of the present invention, a suitable data denoising algorithm is constructed by combining the initial time of noise value calculation, the end time of noise value calculation, the noise smoothing fitting parameter, the standard deviation of Gaussian noise, the motion trajectory time variable, the motion trajectory state variable, the trajectory position, the trajectory speed, the noise probability distribution function, and related parameters to calculate the noise value of the data to be denoised for the robot motion trajectory optimization target, and finally obtain the noise value of the trajectory optimization target data.

[0065] Among them, the function formula of the data denoising algorithm is as follows:

[0066]

[0067] In the formula, N is the noise value of the trajectory optimization target data, t0 is the initial time of noise value calculation, t fis the end time of noise value calculation, λ is the noise smoothing fitting parameter, σ is the standard deviation of Gaussian noise, t is the time variable of the motion trajectory, s is the state variable of the motion trajectory, x(t, s) is the trajectory position of the actual robot motion trajectory optimization target data at time t and state s, is the trajectory position of the data to be denoised for the robot motion trajectory optimization target at time t and state s, T is the transpose symbol, v is the trajectory speed of the actual robot motion trajectory optimization target data, is the trajectory speed of the data to be denoised for the robot motion trajectory optimization target, is the noise probability distribution function of the data to be denoised for the robot motion trajectory optimization target, p(x, v) is the noise probability distribution function of the actual robot motion trajectory optimization target data, μ is the correction value of the noise value of the trajectory optimization target data;

[0068] The present invention constructs a functional formula of a data denoising algorithm for calculating the noise value of the data to be denoised for the robot motion trajectory optimization target. In order to eliminate the influence of the noise introduced due to sensor errors or data acquisition in the data to be denoised for the robot motion trajectory optimization target on the subsequent optimization process of the robot motion trajectory fuzzy control system, it is necessary to perform denoising processing on the data to be denoised for the robot motion trajectory optimization target to obtain cleaner and more accurate denoised data for the robot motion trajectory optimization target. Through this data denoising algorithm, the noise and interference data in the data to be denoised for the robot motion trajectory optimization target can be effectively removed, thereby improving the accuracy and reliability of the data to be denoised for the robot motion trajectory optimization target. This algorithm functional formula fully considers the noise value N of the trajectory optimization target data, the initial time t0 of noise value calculation, the end time t f , the noise smoothing fitting parameter λ, the standard deviation σ of Gaussian noise, the time variable t of the motion trajectory, the state variable s of the motion trajectory, the trajectory position x(t, s) of the actual robot motion trajectory optimization target data at time t and state s, the trajectory position of the data to be denoised for the robot motion trajectory optimization target at time t and state s the transpose symbol T, the trajectory speed v of the actual robot motion trajectory optimization target data, the trajectory speed of the data to be denoised for the robot motion trajectory optimization target the noise probability distribution function of the data to be denoised for the robot motion trajectory optimization target the noise probability distribution function p(x, v) of the actual robot motion trajectory optimization target data, the correction value μ of the noise value of the trajectory optimization target data, and a functional relationship is formed according to the mutual correlation relationship between the noise value N of the trajectory optimization target data and the above parameters:

[0069]

[0070] The algorithm function formula can achieve the calculation process of the noise value of the data to be denoised for the robot motion trajectory optimization target. At the same time, through the introduction of the correction value μ of the noise value of the trajectory optimization target data, it can be adjusted according to the actual situation, so as to improve the accuracy and applicability of the data denoising algorithm.

[0071] Step S132: Judge the noise value of the trajectory optimization target data according to the preset noise threshold of the trajectory optimization target data. When the noise value of the trajectory optimization target data is greater than or equal to the preset noise threshold of the trajectory optimization target data, then eliminate the data to be denoised for the robot motion trajectory optimization target corresponding to the noise value of the trajectory optimization target data, and obtain the denoised data for the robot motion trajectory optimization target.

[0072] In the embodiment of the present invention, according to the preset noise threshold of the trajectory optimization target data, it is judged whether the calculated noise value of the trajectory optimization target data exceeds the preset noise threshold of the trajectory optimization target data. When the noise value of the trajectory optimization target data is greater than or equal to the preset noise threshold of the trajectory optimization target data, it indicates that the interference effect of the noise value in the data to be denoised for the robot motion trajectory optimization target corresponding to the noise value of the trajectory optimization target data is relatively large. Then, eliminate the data to be denoised for the robot motion trajectory optimization target corresponding to the noise value of the trajectory optimization target data, and finally obtain the denoised data for the robot motion trajectory optimization target.

[0073] Step S133: Judge the noise value of the trajectory optimization target data according to the preset noise threshold of the trajectory optimization target data. When the noise value of the trajectory optimization target data is less than the preset noise threshold of the trajectory optimization target data, then directly define the data to be denoised for the robot motion trajectory optimization target corresponding to the noise value of the trajectory optimization target data as the denoised data for the robot motion trajectory optimization target.

[0074] In the embodiment of the present invention, according to the preset noise threshold of the trajectory optimization target data, it is judged whether the calculated noise value of the trajectory optimization target data exceeds the preset noise threshold of the trajectory optimization target data. When the noise value of the trajectory optimization target data is less than the preset noise threshold of the trajectory optimization target data, it indicates that the interference effect of the noise value in the data to be denoised for the robot motion trajectory optimization target corresponding to the noise value of the trajectory optimization target data is relatively small. Then, directly define the data to be denoised for the robot motion trajectory optimization target corresponding to the noise value of the trajectory optimization target data as the denoised data for the robot motion trajectory optimization target.

[0075] The present invention calculates the noise value of the data to be denoised for the optimized target of the robot motion trajectory after preprocessing by using a suitable data denoising algorithm. Since there may be noise source interference or abnormal noise sources in the data to be denoised for the optimized target of the robot motion trajectory, it will have an adverse impact on the accuracy and reliability of the subsequent optimization process of the robot motion trajectory fuzzy control system. Therefore, it is necessary to set an appropriate data denoising algorithm to denoise the data to be denoised for the optimized target of the robot motion trajectory. This data denoising algorithm can identify and measure the noise source data and interference data existing in the data to be denoised for the optimized target of the robot motion trajectory, and remove the noise frequency from the source, thereby improving the accuracy and reliability of the data to be denoised for the optimized target of the robot motion trajectory. In addition, this data denoising algorithm denoises the data to be denoised for the optimized target of the robot motion trajectory by combining the initial time of noise value calculation, the end time of noise value calculation, the noise smoothing fitting parameter, the Gaussian noise standard deviation, the motion trajectory time variable, the motion trajectory state variable, the trajectory position, the trajectory speed, the noise probability distribution function, and related parameters, and adjusts and optimizes the denoising process through the correction value to obtain the best denoising effect and calculation result, so as to calculate the noise value of the trajectory optimization target data more accurately. Then, according to the specific data denoising processing requirements and quality standards, by setting a suitable noise threshold for the trajectory optimization target data, the calculated noise value of the trajectory optimization target data is judged to determine which data to be denoised for the optimized target of the robot motion trajectory needs to be eliminated and which data to be denoised for the optimized target of the robot motion trajectory can be retained. It can effectively eliminate the data to be denoised for the optimized target of the robot motion trajectory with a large noise value of the trajectory optimization target data, avoid the influence of these data to be denoised for the optimized target of the robot motion trajectory with a large noise value of the trajectory optimization target data on the overall data, help to further improve the quality of the data to be denoised for the optimized target of the robot motion trajectory, reduce unnecessary interference and errors, and thus ensure the accuracy and reliability of the data to be denoised for the historical price of regional steel. Finally, by using the set noise threshold for the trajectory optimization target data to judge the calculated noise value of the trajectory optimization target data, the data to be denoised for the optimized target of the robot motion trajectory with a small noise value of the trajectory optimization target data is defined as the denoised data for the optimized target of the robot motion trajectory, and more accurate and reliable data to be denoised for the optimized target of the robot motion trajectory can be obtained. These data are less affected by noise and can provide a more stable data basis for the subsequent optimization process of the robot motion trajectory fuzzy control system, thereby improving the usability and effectiveness of the denoised data for the optimized target of the robot motion trajectory.

[0076] Preferably, step S2 includes the following steps:

[0077] Step S21: Obtain environmental data through an environmental perception sensor to obtain robot motion environment condition data;

[0078] In an embodiment of the present invention, according to the environmental parameters to be monitored, a suitable environmental perception sensor is selected, such as a lidar, a camera, an infrared sensor, etc. And the corresponding environmental perception sensor is installed on the robot to obtain environmental data such as the position, shape, size, motion state of obstacles in the environment around the robot, and the height and slope of the terrain, and finally obtain the robot motion environment condition data.

[0079] Step S22: Perform requirement analysis and processing on the noise-reduced data of the robot motion trajectory optimization target to obtain the robot motion trajectory motion requirement data;

[0080] In an embodiment of the present invention, by performing requirement analysis on the noise-reduced data of the robot motion trajectory optimization target and considering the motion ability, constraint conditions, task requirements, etc. of the robot, the motion requirements such as the motion target, motion planning range, and path constraint of the robot motion trajectory are determined, and finally the robot motion trajectory motion requirement data is obtained.

[0081] Step S23: Optimize the trajectory planning algorithm of the robot motion trajectory fuzzy control system by using the particle swarm optimization algorithm according to the robot motion trajectory motion requirement data and the robot motion environment condition data, so as to obtain an optimized trajectory planning algorithm.

[0082] In an embodiment of the present invention, by combining the robot motion trajectory motion requirement data and the robot motion environment condition data, the particle swarm optimization algorithm is used to optimize the trajectory planning algorithm of the robot motion trajectory fuzzy control system, so as to find the best trajectory planning algorithm parameters in the search space, enabling the robot to better adapt to the environment and achieve the motion requirement target, and finally obtaining an optimized trajectory planning algorithm.

[0083] The present invention first obtains information data about the environment around the robot by using environmental perception sensors, such as environmental data including the position, shape, size, motion state of obstacles, and the height and slope of the terrain. These environmental data are crucial for the motion trajectory planning and control of the robot. Through the environmental perception sensors, the robot can perceive and understand the conditions of the surrounding environment, and thus make corresponding decisions according to the environmental conditions, such as avoiding obstacles, adjusting the motion speed and direction, etc., so as to improve the safety and efficiency of the robot. Then, through the requirement analysis and processing of the noise-reduced target data of the robot motion trajectory optimization, the motion requirements of the robot can be further understood and defined. By analyzing the noise-reduced data, the motion target, motion planning range, path constraints, etc. of the robot can be determined. These motion requirement data are to ensure that the robot can meet the predetermined goals and requirements during the motion process. Through the requirement analysis and processing, the motion requirements of the robot can be accurately defined, providing specific goals and constraint conditions for the subsequent trajectory planning and control. Finally, by using the particle swarm optimization algorithm to optimize the trajectory planning algorithm of the robot motion trajectory fuzzy control system, the performance and effect of the trajectory planning algorithm can be improved. The particle swarm optimization algorithm is a heuristic optimization algorithm that can help the robot system find a better trajectory planning scheme. Moreover, by combining the motion requirement data of the robot motion trajectory and the environmental condition data of the robot motion environment, the particle swarm optimization algorithm can find the best trajectory planning parameters in the search space, enabling the robot to better adapt to the environment and achieve the motion goal. By optimizing the trajectory planning algorithm, the efficiency, stability and safety of the robot motion can be improved, so that the robot can move and execute tasks more intelligently and efficiently in a complex environment.

[0084] Preferably, step S23 includes the following steps:

[0085] Step S231: Use the particle swarm optimization algorithm to perform particle generation processing on the trajectory planning algorithm of the robot motion trajectory fuzzy control system to generate trajectory planning algorithm parameter combination particles;

[0086] In the embodiment of the present invention, the particle swarm optimization algorithm is used to explore the parameter space of the trajectory planning algorithm of the robot motion trajectory fuzzy control system, and a group of particles is initialized to represent a set of trajectory planning algorithm parameter combinations, and finally trajectory planning algorithm parameter combination particles are generated.

[0087] Step S232: Use the fitness function to perform trajectory smoothing evaluation processing on the trajectory planning algorithm parameter combination particles according to the robot motion trajectory motion requirement data and the robot motion environment condition data to obtain the trajectory planning algorithm parameter combination particle smoothing fitness;

[0088] In an embodiment of the present invention, a suitable fitness function is constructed by combining the position of the robot motion trajectory planning, the motion requirement data of the robot motion trajectory, the motion environment condition data of the robot, the trajectory smoothing evaluation function, the weight adjustment parameter, the time interval of the planning effect evaluation, the time variable, the planning effect evaluation function, the trajectory planning speed influence function, and related parameters to perform trajectory smoothing evaluation processing on the trajectory planning algorithm parameter combination particles, and finally obtain the trajectory smoothing fitness of the trajectory planning algorithm parameter combination particles.

[0089] Among them, the formula of the fitness function is as follows:

[0090]

[0091] In the formula, is the trajectory smoothing fitness of the trajectory planning algorithm parameter combination particles, P is the position of the robot motion trajectory planning, D is the motion requirement data of the robot motion trajectory, C is the motion environment condition data of the robot, f(P, D, C) is the trajectory smoothing evaluation function, w1 is the weight adjustment parameter of the trajectory smoothing evaluation function, τ is the time interval of the planning effect evaluation, t ′ is the time variable of the planning effect evaluation, F is the trajectory planning algorithm parameter combination particle, g(t ′ , F) is the planning effect evaluation function of the trajectory planning algorithm parameter combination particle F at time t ′ , w2 is the weight adjustment parameter of the planning effect evaluation function, h(t ′ , F) is the trajectory planning speed influence function of the trajectory planning algorithm parameter combination particle F at time t ′ , w3 is the weight adjustment parameter of the trajectory planning speed influence function, and ε is the correction value of the trajectory smoothing fitness of the trajectory planning algorithm parameter combination particles;

[0092] The present invention constructs a formula for a fitness function to perform trajectory smoothing evaluation processing on the parameter combination particles of a trajectory planning algorithm. This fitness function can comprehensively evaluate the performance of the parameter combination particles of the trajectory planning algorithm. Among them, the trajectory smoothing evaluation function can be used to measure the smoothing performance of the trajectory planning. By evaluating indicators such as the shape and curvature change of the trajectory, the smoothness of the trajectory can be judged. The planning effect evaluation function can be used to evaluate the planning effect of the parameter combination particles of the trajectory planning algorithm at different time points. Indicators such as the error of the trajectory and the time to reach the target point can be considered for evaluation. The trajectory planning speed influence function can be used to consider the speed influence of the parameter combination particles of the trajectory planning algorithm at different time points and pay more attention to the speed planning performance in different time periods as needed. The importance of different indicators is also adjusted through weight adjustment parameters to adapt to specific application scenarios and requirements. In addition, the smoothing fitness is corrected by using a correction value to further optimize the performance of the particles. This function formula fully considers the smoothing fitness of the parameter combination particles of the trajectory planning algorithm The robot motion trajectory planning position P, the robot motion trajectory motion demand data D, the robot motion environment condition data C, the trajectory smoothing evaluation function f(P, D, C), the weight adjustment parameter w1 of the trajectory smoothing evaluation function, the time interval τ of the planning effect evaluation, and the time variable t of the planning effect evaluation ′ , the parameter combination particle F of the trajectory planning algorithm, the parameter combination particle F of the trajectory planning algorithm at time t ′ The planning effect evaluation function g(t ′ , F) at this point, the weight adjustment parameter w2 of the planning effect evaluation function, the parameter combination particle F of the trajectory planning algorithm at time t ′ The trajectory planning speed influence function h(t ′ , F) at this point, the weight adjustment parameter w3 of the trajectory planning speed influence function, the correction value ε of the smoothing fitness of the parameter combination particles of the trajectory planning algorithm. Among them, through the time interval τ of the planning effect evaluation and the time variable t of the planning effect evaluation ′ , the parameter combination particle F of the trajectory planning algorithm, the parameter combination particle F of the trajectory planning algorithm at time t ′ The planning effect evaluation function g(t ′ , F) at this point and the weight adjustment parameter w2 of the planning effect evaluation function constitute the function relationship of the planning effect evaluation item Also through the time interval τ of the planning effect evaluation and the time variable t of the planning effect evaluation ′ , the parameter combination particle F of the trajectory planning algorithm, the parameter combination particle F of the trajectory planning algorithm at time t ′ The trajectory planning speed influence function h(t ′ , F) at this point and the weight adjustment parameter w3 of the trajectory planning speed influence function constitute a kind of function relationship of the planning speed influence item Particle smoothing fitness according to the parameter combination of the trajectory planning algorithm The mutual correlation relationship among the above parameters constitutes a functional relationship:

[0093]

[0094] This function formula can realize the trajectory smoothing evaluation process of the parameter combination particles of the trajectory planning algorithm. At the same time, through the introduction of the correction value ε of the particle smoothing fitness of the trajectory planning algorithm parameter combination, it can be adjusted according to the actual situation, so as to improve the accuracy and applicability of the fitness function.

[0095] Step S233: Judge the particle smoothing fitness of the trajectory planning algorithm parameter combination by setting the particle smoothing fitness threshold as the iteration termination condition. When the particle smoothing fitness of the trajectory planning algorithm parameter combination meets the iteration termination condition, the optimized trajectory planning algorithm parameter combination particles can be obtained;

[0096] In the embodiment of the present invention, according to the previously set particle smoothing fitness threshold as the iteration termination condition, it is judged whether the calculated particle smoothing fitness of the trajectory planning algorithm parameter combination meets the iteration termination condition. If it meets the iteration termination condition, the iteration process is ended, and finally the optimized trajectory planning algorithm parameter combination particles are obtained.

[0097] Step S234: When the particle smoothing fitness of the trajectory planning algorithm parameter combination does not meet the iteration termination condition, re-iterate for trajectory smoothing evaluation until the particle smoothing fitness of the trajectory planning algorithm parameter combination meets the iteration termination condition;

[0098] In the embodiment of the present invention, it is judged whether the calculated particle smoothing fitness of the trajectory planning algorithm parameter combination meets the iteration termination condition through the previously set particle smoothing fitness threshold. If the particle smoothing fitness of the trajectory planning algorithm parameter combination does not meet the iteration termination condition, it means that further optimization is needed, then re-iterate for trajectory smoothing evaluation, update the parameter combination particles of the trajectory planning algorithm and calculate the smoothing fitness again, and repeat this iteration process until the iteration termination condition is met.

[0099] Step S235: Update the trajectory planning algorithm of the robot motion trajectory fuzzy control system according to the optimized trajectory planning algorithm parameter combination particles to obtain an optimized trajectory planning algorithm.

[0100] In the embodiment of the present invention, the trajectory planning algorithm parameters combination in the optimized trajectory planning algorithm parameter combination particles is applied to the trajectory planning algorithm of the robot motion trajectory fuzzy control system, and the corresponding parameters are updated to finally obtain an optimized trajectory planning algorithm.

[0101] First, the present invention can effectively explore the parameter space of the trajectory planning algorithm of the robot motion trajectory fuzzy control system by using the particle swarm optimization algorithm to generate particles for the trajectory planning algorithm. The particle swarm optimization algorithm searches for the optimal solution in the parameter space by imitating the group behavior of bird flocks or fish schools. By generating a set of initial particles, each particle representing a set of trajectory planning algorithm parameter combinations, various possible parameter configurations can be explored, and parameter combinations with excellent performance can be generated. Secondly, according to the motion demand data and environmental condition data of the robot motion trajectory, a suitable fitness function is used to perform a smoothing evaluation process on the trajectory planning algorithm parameter combination particles. Through the calculation of the fitness function, the smoothness of the parameter combination particles can be evaluated, so as to obtain the smooth fitness of each particle, which helps to measure whether the parameter combination particles can produce reasonable trajectory planning results, and thus provides a basis for subsequent optimization. In addition, the calculation formula of the fitness function includes a trajectory smoothness evaluation function and a planning effect evaluation function, and the weight adjustment parameter and the correction value are used to weigh each evaluation, comprehensively evaluate the fitness and smoothness of each particle, so as to achieve a better trajectory planning result. The time interval and time variable in the formula are used to evaluate the planning effect of the particle at different time points. Through the calculation of these parameters, the smoothness, effect and speed influence of the trajectory planning can be comprehensively considered, so as to obtain the smooth fitness of the particle. Then, by setting a suitable particle smooth fitness threshold as the iteration termination condition to judge the smooth fitness of the trajectory planning algorithm parameter combination particles, it is judged whether the smooth fitness of the trajectory planning algorithm parameter combination particles meets the termination condition. If the condition is met, it means that the optimized trajectory planning algorithm parameter combination particles have been obtained, and the iteration process can be ended, which helps to improve the efficiency of the algorithm and ensure that the optimal parameter combination that meets the requirements is obtained. However, when the smooth fitness of the trajectory planning algorithm parameter combination particles does not meet the iteration termination condition, the trajectory smoothing evaluation process is performed again. Through continuous iterative evaluation processes, the parameter combination particles can be gradually adjusted to improve their smooth fitness until the iteration termination condition is met, which can ensure that the algorithm can be continuously optimized, and thus continuously improve the quality of the trajectory planning. Finally, the trajectory planning algorithm of the robot motion trajectory fuzzy control system is updated according to the optimized trajectory planning algorithm parameter combination particles. By applying the optimized parameter combination to the trajectory planning algorithm, a higher-quality and more accurate trajectory planning result can be obtained to improve the motion control performance of the robot, so that the robot can move and navigate better.

[0102] Preferably, step S3 includes the following steps:

[0103] Step S31: Create a fuzzy rule base according to the motion demand data of the robot motion trajectory to obtain a motion trajectory fuzzy control rule base;

[0104] In the embodiments of the present invention, appropriate fuzzy variables are selected according to the motion trajectory motion demand data of the robot to represent the motion trajectory of the robot, and each fuzzy variable is divided into fuzzy sets according to the characteristics of the fuzzy variable and the range of the demand data. Then, fuzzy rules are defined according to the fuzzy sets to describe the motion trajectory control strategy of the robot, and at the same time, the defined fuzzy rules are organized into a fuzzy rule base, which contains the fuzzy sets of the input variables and the corresponding output variables, so as to ensure that the rule base contains comprehensive and accurate control demand rules, and finally a motion trajectory fuzzy control rule base is obtained.

[0105] Step S32: Perform fuzzy control processing on the control algorithm of the robot motion trajectory fuzzy control system through the motion trajectory fuzzy control rule base to obtain motion trajectory fuzzy control parameters;

[0106] In the embodiments of the present invention, according to the design of the robot motion trajectory fuzzy control system, the input and output variables of the control algorithm are determined. The input variable is the state or environmental information of the robot, and the output variable is the control instruction or control parameter. Then, the input variable is mapped into the fuzzy sets of the motion trajectory fuzzy control rule base, and is converted into fuzzy rules that match the fuzzy sets in the motion trajectory fuzzy rule base by using a fuzzification method. At the same time, reasoning is performed according to the fuzzy rules, and finally motion trajectory fuzzy control parameters are obtained.

[0107] Step S33: Optimize the motion trajectory fuzzy control parameters by using a fuzzy control optimization algorithm to obtain optimized motion trajectory fuzzy control parameters;

[0108] In the embodiments of the present invention, a suitable fuzzy control optimization algorithm is constructed by combining the membership degree of the fuzzy rule, the error of the fuzzy rule, the error ratio control parameter, the error change rate differential control parameter, the error change rate, the integral time variable, the error cumulative integral control parameter, the deviation adjustment parameter of the fuzzy rule input variable, the shape control parameter, the attenuation control parameter, the expected value of the fuzzy rule, the actual output value and related parameters to optimize the motion trajectory fuzzy control parameters, and finally optimized motion trajectory fuzzy control parameters are obtained.

[0109] Step S34: Update and improve the control algorithm of the robot motion trajectory fuzzy control system through the optimized motion trajectory fuzzy control parameters to obtain an optimized control algorithm.

[0110] In the embodiments of the present invention, by applying the optimized motion trajectory fuzzy control parameters to the control algorithm of the robot motion trajectory fuzzy control system, the original control algorithm parameters are replaced with the optimized parameters, and finally an optimized control algorithm is obtained.

[0111] The present invention first creates a fuzzy rule base according to the motion requirement data of the robot's motion trajectory. By analyzing the motion requirement data, including information such as the target position, motion speed, and environmental conditions, a set of fuzzy rules can be established to describe the control strategy of the robot's motion trajectory. The fuzzy rule base can map the input (such as the deviation between the target position and the current position) to fuzzy control parameters (such as the robot's steering angle), thereby guiding the generation and control process of the robot's motion trajectory. Then, the control algorithm of the robot's motion trajectory fuzzy control system is subjected to fuzzy control processing by using the established motion trajectory fuzzy control rule base. By utilizing fuzzy inference and fuzzy control techniques, the motion requirement data is used as the input, and inferences are made according to the fuzzy rules in the fuzzy rule base to obtain the fuzzified control parameters. These parameters can be used to control the robot's motion trajectory, such as adjusting the speed, steering angle, and acceleration, etc., to achieve a motion trajectory that meets the requirements. Next, by using a suitable fuzzy control optimization algorithm to optimize the motion trajectory fuzzy control parameters, the quality and efficiency of the robot's motion trajectory can be improved. The fuzzy control optimization algorithm can adjust and search the fuzzy control parameters according to the defined optimization objective function to find the optimal parameter combination. Through optimization, the motion performance of the robot can be improved, making it better adapt to different motion requirements and environmental conditions. Finally, by using the optimized motion trajectory fuzzy control parameters to update and improve the control algorithm of the robot's motion trajectory fuzzy control system, the effects of the robot's motion trajectory planning and trajectory tracking can be improved. The optimized parameters can provide more accurate control instructions and a more stable motion trajectory, thereby improving the motion control performance of the robot. The updated and improved control algorithm can better meet the motion requirements and have stronger adaptability and robustness, thus providing a basic guarantee for the subsequent parameter tuning process of the robot's motion trajectory fuzzy control system.

[0112] Preferably, the function formula of the fuzzy control optimization algorithm in step S33 is specifically as follows:

[0113]

[0114] e j (k) = l j (k) - y j (k);

[0115] In the formula, Δu(k) is the optimized motion trajectory fuzzy control parameter, k is the optimization time variable, m is the number of fuzzy rules of the motion trajectory fuzzy control parameter, ρ j (k) is the membership degree of the jth fuzzy rule, e j (k) is the error of the jth fuzzy rule at time k, G is the error proportional control parameter, E is the differential control parameter of the error change rate, is the error change rate of the j-th fuzzy rule at time k, s is the integral time variable, I is the error cumulative integral control parameter, M is the number of fuzzy rule input variables, is the deviation adjustment parameter of the r-th input variable in the fuzzy rule, a r is the shape control parameter of the r-th input variable in the fuzzy rule, b r is the attenuation control parameter of the r-th input variable in the fuzzy rule, l j (k) is the expected value of the j-th fuzzy rule at time k, y j (k) is the actual output value of the j-th fuzzy rule at time k, η is the correction value of the optimized motion trajectory fuzzy control parameter.

[0116] The present invention constructs a function formula of a fuzzy control optimization algorithm for optimizing the motion trajectory fuzzy control parameters. The fuzzy control optimization algorithm can adaptively adjust the control parameters according to the actual error situation of the motion trajectory fuzzy control parameters. By calculating the membership degree and error of each fuzzy rule, it can adjust the proportional, differential, and integral parts of the fuzzy control parameters according to the magnitude and change rate of the error. This adaptive adjustment can ensure that the control system has better adaptability and robustness to different motion trajectory requirements. And by accumulating the error integral and adjusting the error proportional control parameter, the error of the robot motion trajectory can be optimized. Through the superposition and accumulation of the integral term, the algorithm can continuously correct the error and minimize the error by adjusting the control parameter. Also, by optimizing the number of fuzzy rules, the parameters of the membership function, and the deviation adjustment, shape control, and attenuation control parameters of the input variables, more accurate and optimized motion trajectory control results can be obtained, thereby improving the accuracy, stability, and robustness of the motion trajectory control, enabling the robot to better meet the motion trajectory requirements. The algorithm function formula fully considers the optimized motion trajectory fuzzy control parameter Δu(k), the optimization time variable k, the number of fuzzy rules m of the motion trajectory fuzzy control parameters, the membership degree ρ j (k) of the j-th fuzzy rule, the error e j (k) of the j-th fuzzy rule at time k, the error proportional control parameter G, the error change rate differential control parameter E, the error change rate of the j-th fuzzy rule at time k the integral time variable s, the error cumulative integral control parameter I, the number M of fuzzy rule input variables, the deviation adjustment parameter of the r-th input variable in the fuzzy rule the shape control parameter a of the r-th input variable in the fuzzy rule r , the attenuation control parameter b of the r-th input variable in the fuzzy rule r , the expected value l j (k) of the j-th fuzzy rule at time k, the actual output value y of the j-th fuzzy rule at time kj (k), the correction value η of the optimized motion trajectory fuzzy control parameter, where by optimizing the time variable k, the expected value l of the j-th fuzzy rule at time k j (k) and the actual output value y of the j-th fuzzy rule at time k j (k) constitute an error e j (k) functional relationship l j (k) - y j (k), also by optimizing the time variable k, the number m of fuzzy rules of the motion trajectory fuzzy control parameter, the error e of the j-th fuzzy rule at time k j (k), the number M of input variables of the fuzzy rule, the deviation adjustment parameter of the r-th input variable in the fuzzy rule The shape control parameter a of the r-th input variable in the fuzzy rule r And the decay control parameter b of the r-th input variable in the fuzzy rule r constitute a membership degree ρ of the j-th fuzzy rule j (k) functional relationship According to the mutual correlation relationship between the optimized motion trajectory fuzzy control parameter Δu(k) and the above parameters, a functional relationship is formed:

[0117]

[0118] This algorithm function formula can realize the optimization process of the motion trajectory fuzzy control parameter. At the same time, by introducing the correction value η of the optimized motion trajectory fuzzy control parameter, it can be adjusted according to the actual situation, so as to improve the accuracy and applicability of the fuzzy control optimization algorithm.

[0119] Preferably, step S4 includes the following steps:

[0120] Step S41: Perform system parameter tuning on the robot motion trajectory fuzzy control system through the optimized trajectory planning algorithm and the optimized control algorithm to obtain the optimized parameters of the robot motion trajectory fuzzy control system;

[0121] In the embodiment of the present invention, according to the operating characteristics and requirements of the robot, the system parameters to be tuned are selected, and the parameters of the selected robot motion trajectory fuzzy control system are tuned by using the optimized trajectory planning algorithm and the optimized control algorithm. According to the performance indicators and optimization objectives of the robot, an evaluation index or objective function is defined to measure the performance of the tuned robot motion trajectory fuzzy control system. Then, parameter tuning iteration processing is performed according to the evaluation results. In each iteration, the system parameters are adjusted according to the feedback information of the objective function, and at the same time, termination conditions are set to judge whether the parameter tuning process reaches convergence, and finally the optimized parameters of the robot motion trajectory fuzzy control system are obtained.

[0122] Step S42: Use the system identification method to identify and estimate the optimization parameters of the robot motion trajectory fuzzy control system, and obtain the estimated parameters of the robot motion trajectory fuzzy control system;

[0123] In the embodiment of the present invention, according to the characteristics and problem requirements of the robot motion trajectory fuzzy control system, corresponding system identification methods such as the least squares method and the maximum likelihood estimation method are selected to identify and estimate the optimization parameters of the robot motion trajectory fuzzy control system, and to estimate the behavioral characteristics and dynamic performance parameters of the robot motion trajectory fuzzy control system, and finally the estimated parameters of the robot motion trajectory fuzzy control system are obtained.

[0124] Step S43: Use the estimated parameters of the robot motion trajectory fuzzy control system to update and optimize the robot motion trajectory fuzzy control system, and obtain an optimized robot motion trajectory fuzzy control system.

[0125] In the embodiment of the present invention, the estimated parameters of the robot motion trajectory fuzzy control system are applied to the robot motion trajectory fuzzy control system by updating fuzzy control rules, adjusting weights, modifying constraint conditions, etc., to replace the original parameters for real-time updating of the system, and finally an optimized robot motion trajectory fuzzy control system is obtained.

[0126] The present invention optimizes the system parameters of the robot motion trajectory fuzzy control system by using an optimized trajectory planning algorithm and an optimized control algorithm to obtain an optimized parameter configuration. The purpose of this is to improve the performance and robustness of the control system. By optimizing the system parameters, the planning and tracking effects of the robot motion trajectory can be improved, enabling the robot to reach the target position more accurately and quickly when performing tasks. The optimization process usually involves using different optimization algorithms, such as genetic algorithms, simulated annealing algorithms, etc., to search for and optimize the optimal parameter configuration. Then, by using corresponding system identification methods, such as the least squares method, maximum likelihood estimation method, etc., the optimized parameters of the robot motion trajectory fuzzy control system are identified and estimated to obtain more accurate parameter estimation results. Using the input and output data of the actual system, the optimized parameters can be identified and estimated to obtain parameters that more accurately reflect the dynamic characteristics of the system. Through system identification, the dynamic behavior, time delay characteristics, etc. of the system can be studied in depth, thereby better understanding the motion control mechanism of the robot. These estimated parameters can guide the further optimization of the system design and control strategy in subsequent processes, thereby improving the motion stability and accuracy of the robot. Finally, by using the estimated parameters of the robot motion trajectory fuzzy control system, the robot motion trajectory fuzzy control system is updated and optimized to obtain an optimized control system. By applying the estimated parameters to the control system, the control ability and adaptability of the system can be improved. The updated and improved control system can more accurately perceive the environment and motion requirements, and then generate more optimized control instructions. This will help improve the motion trajectory planning and tracking effects of the robot, enabling the robot to complete tasks more efficiently when performing tasks. The optimized control system can also adapt to different working scenarios and motion requirements, with stronger flexibility and adaptability, enabling the robot to complete tasks more accurately and efficiently, and at the same time having strong adaptability and robustness, thus bringing better control effects and motion performance.

[0127] Preferably, step S5 includes the following steps:

[0128] Step S51: Perform simulation processing on the robot through the optimized robot motion trajectory fuzzy control system to obtain the simulation result of the robot motion trajectory fuzzy control system;

[0129] In the embodiment of the present invention, first, a robot model simulation platform is created by using the kinematic and dynamic models of the robot and a simulation tool, and the simulation parameters are set according to the purpose and requirements of the simulation. Then, the optimized robot motion trajectory fuzzy control system is used to perform motion trajectory simulation processing on the robot in the created simulation environment, and the input and output results during the simulation processing are recorded. Finally, the simulation result of the robot motion trajectory fuzzy control system is obtained.

[0130] Step S52: Perform performance evaluation processing on the simulation results of the robot motion trajectory fuzzy control system to obtain the performance evaluation results of the robot motion trajectory fuzzy control system;

[0131] In the embodiment of the present invention, according to the motion requirements and control objectives of the robot, performance indicators in aspects such as appropriate motion accuracy, response speed, stability, and energy efficiency are defined, and the simulation results of the robot motion trajectory fuzzy control system are analyzed according to the defined performance indicators to compare the gap between the simulation results and the expected objectives, evaluate the performance of the robot motion trajectory fuzzy control system, and finally obtain the performance evaluation results of the robot motion trajectory fuzzy control system.

[0132] Step S53: Perform optimization verification processing according to the performance evaluation results of the robot motion trajectory fuzzy control system to obtain the optimization verification results of the robot motion trajectory fuzzy control system, so as to execute the corresponding motion trajectory planning task.

[0133] In the embodiment of the present invention, problems or deficiencies existing in the robot motion trajectory fuzzy control system are identified according to the performance evaluation results of the robot motion trajectory fuzzy control system, such as problems that the performance indicators fail to meet the requirements and the system response is unstable, etc., and corresponding optimization strategies such as parameter adjustment, algorithm improvement, and control strategy update are formulated according to the problem identification results. At the same time, the formulated optimization strategies are applied in the robot motion trajectory fuzzy control system for adjustment and improvement, and then simulation or experimental verification is carried out again to verify the performance of the optimized robot motion trajectory fuzzy control system, so as to obtain the optimization verification results of the robot motion trajectory fuzzy control system. Finally, the corresponding robot motion trajectory planning task is executed according to the verified robot motion trajectory fuzzy control system.

[0134] The present invention performs simulation processing on a robot by using an optimized fuzzy control system for the robot's motion trajectory, thereby obtaining the motion trajectory and control effect of the robot in a virtual environment. Through simulation, the robot can be tested and evaluated in a safe, convenient, and low-cost environment. The purpose of doing this is to understand the performance of the robot in advance, help discover potential problems and improvement spaces. In addition, through simulation, the performance of the robot in aspects such as path planning, motion trajectory tracking, and stability can be observed, thus providing important references for further optimizing the system. Then, performance evaluation processing is carried out on the simulation results of the fuzzy control system for the robot's motion trajectory to obtain an objective evaluation of the system performance. Performance evaluation can involve various indicators, such as motion accuracy, path planning accuracy, control stability, etc. By evaluating the simulation results, the control performance of the robot in different task scenarios can be understood, and the advantages and disadvantages of the system can be discovered. The evaluation results can provide a basis for subsequent optimization, help locate and solve potential problems, and thus improve the overall performance of the system. Finally, optimization verification processing is carried out on the performance evaluation results of the fuzzy control system for the robot's motion trajectory to obtain the optimization verification results of the fuzzy control system for the robot's motion trajectory. Through optimization verification, it can be further verified and confirmed whether the adopted optimization measures are effective, thereby verifying the performance of the improved control system in actual applications. The optimization verification results can provide a decision-making basis for the deployment and application of the final system, ensuring the stability, reliability, and performance optimization of the system. After optimization verification, an improved fuzzy control system for the robot's motion trajectory can be obtained, which can better meet the requirements of the motion trajectory planning task. The optimized system can improve the motion performance, accuracy, and robustness of the robot, thereby more effectively executing various motion trajectory planning tasks.

[0135] Preferably, the present invention further provides a robot motion trajectory planning system for executing the robot motion trajectory planning method as described above. The robot motion trajectory planning system includes:

[0136] A motion trajectory optimization target processing module, configured to obtain the optimization target data of the fuzzy control system for the robot's motion trajectory through a sensor to obtain the optimization target data of the robot's motion trajectory; and perform noise reduction processing on the optimization target data of the robot's motion trajectory by using a data noise reduction algorithm, thereby obtaining the noise-reduced optimization target data of the robot's motion trajectory;

[0137] A trajectory planning algorithm optimization module, configured to perform requirement analysis processing on the noise-reduced optimization target data of the robot's motion trajectory to obtain the motion requirement data of the robot's motion trajectory; and optimize the trajectory planning algorithm of the fuzzy control system for the robot's motion trajectory by using a particle swarm optimization algorithm based on the motion requirement data of the robot's motion trajectory, thereby obtaining an optimized trajectory planning algorithm;

[0138] A control algorithm optimization module, which is used to optimize the control algorithm of the fuzzy control system of the robot motion trajectory by using the motion requirement data of the robot motion trajectory, so as to obtain an optimized control algorithm;

[0139] A fuzzy control system parameter optimization module, which is used to optimize the system parameters of the fuzzy control system of the robot motion trajectory through the optimized trajectory planning algorithm and the optimized control algorithm, so as to obtain the optimized parameters of the fuzzy control system of the robot motion trajectory; and use the system identification method to update and estimate the optimized parameters of the fuzzy control system of the robot motion trajectory, so as to obtain an optimized fuzzy control system of the robot motion trajectory;

[0140] A performance evaluation and verification processing module, which is used to perform performance evaluation processing on the optimized fuzzy control system of the robot motion trajectory to obtain the performance evaluation result of the fuzzy control system of the robot motion trajectory; perform optimization verification processing according to the performance evaluation result of the fuzzy control system of the robot motion trajectory to obtain the optimization verification result of the fuzzy control system of the robot motion trajectory, so as to execute the corresponding motion trajectory planning task.

[0141] In summary, the present invention provides a robot motion trajectory planning system. This optimization system consists of a motion trajectory optimization target processing module, a trajectory planning algorithm optimization module, a control algorithm optimization module, a fuzzy control system parameter optimization module, and a performance evaluation and verification processing module. It can implement any one of the robot motion trajectory planning methods described in the present invention. It is used to jointly realize a robot motion trajectory planning method through the operations between the computer programs running on each module. The internal structure of the system cooperates with each other, and optimizes the trajectory planning algorithm and the control algorithm of the fuzzy control system of the robot motion trajectory by using a variety of algorithms and technologies, and optimizes the parameters of the fuzzy control system of the robot motion trajectory, so as to achieve precise control of the robot motion trajectory, thereby improving the control performance and robustness. This can greatly reduce repetitive work and labor input, and can quickly and effectively provide a more accurate and efficient optimization processing process of the fuzzy control system of the robot motion trajectory, thereby simplifying the operation process of the robot motion trajectory planning system.

[0142] Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, it is intended to cover all changes falling within the meaning and scope of the equivalent elements of the application documents within the present invention.

[0143] The above are only specific embodiments of the present invention, enabling those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to these embodiments shown herein, but rather will be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for robot motion trajectory planning, characterized in that, Including the following steps: Step S1: Obtain the optimization target data of the robot motion trajectory fuzzy control system through a sensor to obtain the robot motion trajectory optimization target data; and use a data denoising algorithm to perform denoising processing on the robot motion trajectory optimization target data to obtain the robot motion trajectory optimization target denoised data; Step S2: Perform requirement analysis processing on the robot motion trajectory optimization target denoised data to obtain the robot motion trajectory motion requirement data; based on the robot motion trajectory motion requirement data, use the particle swarm optimization algorithm to optimize the trajectory planning algorithm of the robot motion trajectory fuzzy control system to obtain an optimized trajectory planning algorithm; Step S3: Optimize the control algorithm of the robot motion trajectory fuzzy control system based on the robot motion trajectory motion requirement data to obtain an optimized control algorithm; Step S4: Perform system parameter tuning processing on the robot motion trajectory fuzzy control system through the optimized trajectory planning algorithm and the optimized control algorithm to obtain the optimized parameters of the robot motion trajectory fuzzy control system; and use the system identification method to perform update estimation processing on the optimized parameters of the robot motion trajectory fuzzy control system to obtain an optimized robot motion trajectory fuzzy control system; Step S5: Perform performance evaluation processing on the optimized robot motion trajectory fuzzy control system to obtain the performance evaluation result of the robot motion trajectory fuzzy control system; perform optimization verification processing according to the performance evaluation result of the robot motion trajectory fuzzy control system to obtain the optimization verification result of the robot motion trajectory fuzzy control system to execute the corresponding motion trajectory planning task.

2. The robot motion trajectory planning method according to claim 1, wherein, Step S1 includes the following steps: Step S11: Obtain the optimization target data of the robot motion trajectory fuzzy control system through a sensor to obtain the robot motion trajectory optimization target data; Step S12: Perform data preprocessing on the robot motion trajectory optimization target data to obtain the robot motion trajectory optimization target data to be denoised; Step S13: Use a data denoising algorithm to perform denoising processing on the robot motion trajectory optimization target data to be denoised to obtain the robot motion trajectory optimization target denoised data.

3. The robot motion trajectory planning method according to claim 2, characterized in that, Step S13 includes the following steps: Step S131: Use a data denoising algorithm to calculate the noise value of the robot motion trajectory optimization target data to be denoised to obtain the trajectory optimization target data noise value; Among them, the function formula of the data denoising algorithm is as follows: where N is the noise value of the trajectory optimization target data, t0 is the initial time for calculating the noise value, t f is the end time for calculating the noise value, λ is the noise smoothing fitting parameter, σ is the standard deviation of Gaussian noise, t is the time variable of the motion trajectory, s is the state variable of the motion trajectory, x(t, s) is the trajectory position of the actual robot motion trajectory optimization target data at time t and state s, is the trajectory position of the data to be denoised for the robot motion trajectory optimization target at time t and state s, T is the transpose symbol, v is the trajectory speed of the actual robot motion trajectory optimization target data, is the trajectory speed of the data to be denoised for the robot motion trajectory optimization target, is the noise probability distribution function of the data to be denoised for the robot motion trajectory optimization target, p(x, v) is the noise probability distribution function of the actual robot motion trajectory optimization target data, and μ is the correction value of the noise value of the trajectory optimization target data; Step S132: Judge the trajectory optimization target data noise value according to the preset trajectory optimization target data noise threshold. When the trajectory optimization target data noise value is greater than or equal to the preset trajectory optimization target data noise threshold, the robot motion trajectory optimization target data to be denoised corresponding to the trajectory optimization target data noise value is removed to obtain the robot motion trajectory optimization target denoised data; Step S133: Determine the trajectory optimization target data noise value according to the preset trajectory optimization target data noise threshold. When the trajectory optimization target data noise value is less than the preset trajectory optimization target data noise threshold, directly define the robot motion trajectory optimization target data to be denoised corresponding to the trajectory optimization target data noise value as the robot motion trajectory optimization target denoised data.

4. The robot motion trajectory planning method according to claim 1, characterized in that, Step S2 includes the following steps: Step S21: Obtain environmental data through an environmental perception sensor to get the robot motion environment condition data; Step S22: Conduct demand analysis and processing on the robot motion trajectory optimization target denoised data to obtain the robot motion trajectory motion demand data; Step S23: Optimize the trajectory planning algorithm of the robot motion trajectory fuzzy control system according to the robot motion trajectory motion demand data and the robot motion environment condition data by using the particle swarm optimization algorithm to obtain an optimized trajectory planning algorithm.

5. The robot motion trajectory planning method according to claim 4, wherein Step S23 includes the following steps: Step S231: Use the particle swarm optimization algorithm to perform particle generation processing on the trajectory planning algorithm of the robot motion trajectory fuzzy control system to generate trajectory planning algorithm parameter combination particles; Step S232: According to the robot motion trajectory motion demand data and the robot motion environment condition data, use the fitness function to perform trajectory smoothing evaluation processing on the trajectory planning algorithm parameter combination particles to obtain the trajectory planning algorithm parameter combination particle smoothing fitness; Among them, the formula of the fitness function is as follows: Wherein, F is the smooth fitness of the parameter combination particles of the trajectory planning algorithm, P is the position of the robot motion trajectory planning, D is the motion requirement data of the robot motion trajectory, C is the motion environment condition data of the robot, f(P, D, C) is the trajectory smoothing evaluation function, w1 is the weight adjustment parameter of the trajectory smoothing evaluation function, τ is the time interval for evaluating the planning effect, and t ′ is the time variable for evaluating the planning effect, F is the parameter combination particle of the trajectory planning algorithm, and g(t ′ , F) is the planning effect evaluation function of the parameter combination particle F of the trajectory planning algorithm at time t ′ . w2 is the weight adjustment parameter of the planning effect evaluation function, and h(t ′ , F) is the trajectory planning speed influence function of the parameter combination particle F of the trajectory planning algorithm at time t ′ . w3 is the weight adjustment parameter of the trajectory planning speed influence function, and ε is the correction value of the smooth fitness of the parameter combination particles of the trajectory planning algorithm; Step S233: Determine the trajectory planning algorithm parameter combination particle smoothing fitness by setting the particle smoothing fitness threshold as the iteration termination condition. When the trajectory planning algorithm parameter combination particle smoothing fitness meets the iteration termination condition, obtain the optimized trajectory planning algorithm parameter combination particles; Step S234: When the trajectory planning algorithm parameter combination particle smoothing fitness does not meet the iteration termination condition, re-iterate for trajectory smoothing evaluation processing until the trajectory planning algorithm parameter combination particle smoothing fitness meets the iteration termination condition; Step S235: Update the trajectory planning algorithm of the robot motion trajectory fuzzy control system according to the optimized trajectory planning algorithm parameter combination particles to obtain an optimized trajectory planning algorithm.

6. The robot motion trajectory planning method according to claim 1, wherein, Step S3 includes the following steps: Step S31: Create a fuzzy rule base according to the robot motion trajectory motion demand data to obtain a motion trajectory fuzzy control rule base; Step S32: Perform fuzzy control processing on the control algorithm of the robot motion trajectory fuzzy control system through the motion trajectory fuzzy control rule base to obtain motion trajectory fuzzy control parameters; Step S33: Optimize the motion trajectory fuzzy control parameters by using the fuzzy control optimization algorithm to obtain optimized motion trajectory fuzzy control parameters; Step S34: Update and improve the control algorithm of the robot motion trajectory fuzzy control system through the optimized motion trajectory fuzzy control parameters to obtain an optimized control algorithm.

7. The robot motion trajectory planning method according to claim 6, wherein, The function formula of the fuzzy control optimization algorithm in Step S33 is specifically: e j f(k) = l j f(k) - y j f(k); where, Δu(k) is the optimized motion trajectory fuzzy control parameter, k is the optimization time variable, m is the number of fuzzy rules of the motion trajectory fuzzy control parameter, ρ j (k) is the membership degree of the j-th fuzzy rule, e j (k) is the error of the j-th fuzzy rule at time k, G is the error proportional control parameter, E is the differential control parameter of the error change rate, is the error change rate of the j-th fuzzy rule at time k, s is the integral time variable, I is the error cumulative integral control parameter, M is the number of fuzzy rule input variables, is the deviation adjustment parameter of the r-th input variable in the fuzzy rule, a r is the shape control parameter of the r-th input variable in the fuzzy rule, b r is the attenuation control parameter of the r-th input variable in the fuzzy rule, l j (k) is the expected value of the j-th fuzzy rule at time k, y j (k) is the actual output value of the j-th fuzzy rule at time k, η is the correction value of the optimized motion trajectory fuzzy control parameter.

8. The robot motion trajectory planning method according to claim 1, characterized in that Step S4 includes the following steps: Step S41: The system parameters of the robot motion trajectory fuzzy control system are tuned through an optimized trajectory planning algorithm and an optimized control algorithm to obtain the optimized parameters of the robot motion trajectory fuzzy control system; Step S42: The optimized parameters of the robot motion trajectory fuzzy control system are identified and estimated through a system identification method to obtain the estimated parameters of the robot motion trajectory fuzzy control system; Step S43: The robot motion trajectory fuzzy control system is updated and optimized using the estimated parameters of the robot motion trajectory fuzzy control system to obtain an optimized robot motion trajectory fuzzy control system.

9. The robot motion trajectory planning method according to claim 1, wherein, Step S5 includes the following steps: Step S51: The robot is simulated through the optimized robot motion trajectory fuzzy control system to obtain the simulation results of the robot motion trajectory fuzzy control system; Step S52: The performance of the simulation results of the robot motion trajectory fuzzy control system is evaluated to obtain the performance evaluation results of the robot motion trajectory fuzzy control system; Step S53: Optimization verification is performed based on the performance evaluation results of the robot motion trajectory fuzzy control system to obtain the optimization verification results of the robot motion trajectory fuzzy control system for performing corresponding motion trajectory planning tasks.

10. A robot motion trajectory planning system, characterized in that, For implementing the robot motion trajectory planning method as described in Claim 1, the robot motion trajectory planning system includes: A motion trajectory optimization target processing module, configured to obtain the optimization target data of the robot motion trajectory fuzzy control system through a sensor to obtain the optimization target data of the robot motion trajectory; and perform noise reduction processing on the optimization target data of the robot motion trajectory using a data noise reduction algorithm to obtain the noise-reduced optimization target data of the robot motion trajectory; A trajectory planning algorithm optimization module, configured to perform requirement analysis on the noise-reduced optimization target data of the robot motion trajectory to obtain the motion requirement data of the robot motion trajectory; and optimize the trajectory planning algorithm of the robot motion trajectory fuzzy control system using a particle swarm optimization algorithm based on the motion requirement data of the robot motion trajectory to obtain an optimized trajectory planning algorithm; A control algorithm optimization module, configured to optimize the control algorithm of the robot motion trajectory fuzzy control system using the motion requirement data of the robot motion trajectory to obtain an optimized control algorithm; A fuzzy control system parameter optimization module, configured to tune the system parameters of the robot motion trajectory fuzzy control system through an optimized trajectory planning algorithm and an optimized control algorithm to obtain the optimized parameters of the robot motion trajectory fuzzy control system; and update and estimate the optimized parameters of the robot motion trajectory fuzzy control system using a system identification method to obtain an optimized robot motion trajectory fuzzy control system; A performance evaluation and verification processing module, configured to perform performance evaluation on the optimized robot motion trajectory fuzzy control system to obtain the performance evaluation results of the robot motion trajectory fuzzy control system; and perform optimization verification based on the performance evaluation results of the robot motion trajectory fuzzy control system to obtain the optimization verification results of the robot motion trajectory fuzzy control system for performing corresponding motion trajectory planning tasks.

Images