Robot trajectory tracking method, device and equipment and readable storage medium

Abstract

The invention relates to the technical field of robot trajectory tracking, and discloses a robot trajectory tracking method, device and equipment and a readable storage medium, and the method comprises the steps: setting an expected trajectory of a robot; acquiring a current position and a posture angle of the robot, and constructing a robot kinetic model in combination with the expected trajectory and preset disturbance; designing a position control law and an attitude control law of the robot according to the robot kinetic model and a preset fractional order terminal sliding mode surface in combination with a preset fixed time reaching law to obtain a fractional order terminal sliding mode controller, the position control law and the attitude control law performing fractional order integral operation on a switching item causing system buffeting; and determining a target trajectory of the robot based on the fractional order terminal sliding mode controller. The effect of improving the trajectory tracking control precision of the mobile robot can be achieved.

Description

Technical Field

[0001] This application relates to the field of robot trajectory tracking technology, and in particular to a robot trajectory tracking method, apparatus, device, and readable storage medium. Background Technology

[0002] In existing technologies, mobile robot trajectory tracking control solutions involve methods based on disturbance observers, PID control methods, sliding mode control, and other technical approaches.

[0003] Mobile robot trajectory tracking methods based on disturbance observers require prior information about the disturbance, such as upper bounds on the disturbance value and derivative. However, in real-world scenarios, obtaining disturbance information is generally difficult, and the selection of observer parameters is subject to stringent conditions, which can easily lead to system instability. PID control-based mobile robot trajectory tracking methods often underperform in complex environments and nonlinear disturbances, prone to overshoot and oscillations, exhibiting low control accuracy and requiring complex parameter tuning with a strong reliance on experience. Sliding mode control-based mobile robot trajectory tracking methods, due to the introduction of switching functions, can introduce system chattering, resulting in significant noise and, in severe cases, even wear and damage to the robot's actuators, affecting controller performance.

[0004] Regarding the aforementioned technologies, the inventors discovered that existing mobile robot trajectory tracking methods suffer from problems such as high system noise and low control precision. Summary of the Invention

[0005] To improve the trajectory tracking control accuracy of mobile robots, this application provides a robot trajectory tracking method, apparatus, device, and readable storage medium.

[0006] Firstly, this application provides a robot trajectory tracking method.

[0007] This application is achieved through the following technical solution: A robot trajectory tracking method includes the following steps: Set the desired trajectory for the robot; Obtain the robot's current position and orientation angle, and construct a robot dynamics model by combining the desired trajectory and preset perturbation; Based on the robot dynamics model, a fractional-order terminal sliding surface is preset, and combined with a preset fixed-time approach law, the robot's position control law and attitude control law are designed to obtain a fractional-order terminal sliding controller. The position control law and the attitude control law perform fractional-order integral operations on the switching terms that cause system chattering. The target trajectory of the robot is determined based on the fractional-order terminal sliding mode controller.

[0008] In a preferred embodiment, this application can be further configured such that the expression of the position control law includes,

[0009]

[0010]

[0011] In the formula, For the robot's desired pose angle, Control law in the horizontal direction The switching gain, The tracking error of the robot in the horizontal direction, It is a fractional-order terminal sliding surface in the horizontal direction. For vertical control law The switching gain, The tracking error of the robot in the vertical direction, For fractional-order terminal sliding surfaces in the vertical direction, , , , , express Fractional integral operations of order order, and These are the error tracking equations for the robot in the horizontal and vertical directions, respectively.

[0012] In a preferred embodiment, this application can be further configured such that the expression of the attitude control law includes,

[0013] In the formula, This is the attitude control law. The gain of the switching term in the attitude control law. For the fractional-order terminal sliding surface of the attitude, The error tracking equation is for the robot's desired pose angle. The error is the desired pose angle of the robot. , , , , express Fractional integral operations.

[0014] In a preferred embodiment, this application can be further configured to include the following steps: The switching term gain parameter of the fractional-order terminal sliding mode controller is adjusted using the RBF neural network algorithm.

[0015] In a preferred embodiment, this application can be further configured such that the step of adjusting the switching term gain parameter of the fractional-order terminal sliding mode controller using the RBF neural network algorithm includes, The system sliding mode variable and fractional integral signal are input into the RBF neural network; Using a Gaussian function as the activation function and combined with online adjusted weights, the RBF neural network outputs the switching term gain of the robot's control law in the horizontal direction, control law in the vertical direction, and attitude control law, respectively.

[0016] In a preferred embodiment, this application can be further configured to include the following steps: Using the target trajectory, the robot's actuator is driven to move to the target position.

[0017] Secondly, this application provides a robot trajectory tracking device.

[0018] This application is achieved through the following technical solution: A robot trajectory tracking device, comprising, The initial module is used to set the robot's desired trajectory; The modeling module is used to obtain the robot's current position and attitude angle, and to construct a robot dynamics model by combining the desired trajectory and preset perturbations; The sliding mode control module is used to design the robot's position control law and attitude control law based on the robot dynamics model, preset the fractional-order terminal sliding surface, and combine it with the preset fixed-time approach law to obtain the fractional-order terminal sliding mode controller. The position control law and the attitude control law perform fractional-order integral operations on the switching terms that cause system chattering. The target trajectory module is used to determine the robot's target trajectory based on the fractional-order terminal sliding mode controller.

[0019] Thirdly, this application provides a computer device.

[0020] This application is achieved through the following technical solution: A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of any of the robot trajectory tracking methods described above.

[0021] Fourthly, this application provides a computer-readable storage medium.

[0022] This application is achieved through the following technical solution: A computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of any of the above-described robot trajectory tracking methods.

[0023] Fifthly, this application provides a computer program product.

[0024] This application is achieved through the following technical solution: A computer program product includes a computer program that, when executed by a processor, implements the steps of any of the above-described robot trajectory tracking methods.

[0025] In summary, compared with the prior art, the beneficial effects of the technical solution provided in this application include at least the following: The desired trajectory of the robot is set; the current position and attitude angle of the robot are obtained, and a robot dynamics model is constructed by combining the desired trajectory and preset disturbances; based on the robot dynamics model, a fractional-order terminal sliding surface is preset, and the position control law and attitude control law of the robot are designed by combining a preset fixed-time approach law, resulting in a fractional-order terminal sliding mode controller. The position control law and attitude control law perform fractional-order integral operations on the switching terms that cause system chattering, and introduce fractional-order calculus operators into the design of the mobile robot controller. By further reducing the controller chattering on the basis of 1 through the fractional-order integral terms in the controller, the serious chattering problem caused by using sliding mode control of robot movement is avoided; at the same time, the tracking error is converged in finite time; the system noise is reduced and the trajectory tracking control accuracy of the mobile robot is improved. Attached Figure Description

[0026] Figure 1 A control flowchart of a robot trajectory tracking method is provided as an exemplary embodiment of this application.

[0027] Figure 2 This is a schematic diagram of a mobile robot working in a planar configuration, which is another exemplary embodiment of this application, providing a robot trajectory tracking method.

[0028] Figure 3 A structural diagram of an RBF neural network for a robot trajectory tracking method provided as another exemplary embodiment of this application. Detailed Implementation

[0029] This specific embodiment is merely an explanation of this application and is not intended to limit it. After reading this specification, those skilled in the art can make modifications to this embodiment without contributing any inventive step, but such modifications are protected by patent law as long as they fall within the scope of the claims of this application. To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0030] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article, unless otherwise specified, generally indicates that the preceding and following related objects have an "or" relationship.

[0031] Disturbance observer-based control is a strategy that achieves precise control by estimating external disturbances in the system in real time. This method has significant advantages in disturbance rejection control for mobile robots. By introducing a disturbance observer to estimate external disturbances in the environment in real time and then compensating for them in the controller design, this method can improve the system's robustness to environmental changes and external disturbances, thereby enhancing the control performance of the mobile robot. The disadvantages of this method are that it requires prior knowledge of disturbance information, such as the upper bound of the disturbance value and the upper bound of the disturbance derivative. However, in real-world scenarios, obtaining disturbance information is generally difficult. Furthermore, observer-based control requires a certain level of accuracy in disturbance estimation; inappropriate observer parameter selection can easily lead to system instability, meaning its parameter selection conditions are stringent. Therefore, although most researchers use observer-based disturbance rejection control for mobile robots, parameter selection is difficult in application, and the introduction of the observer significantly increases the complexity of the entire closed-loop system.

[0032] In PID control, robot position control can be achieved using two PID controllers, one for the X-axis and the other for the Y-axis. Based on the error between the current and target positions, the PID controllers calculate the necessary adjustment to correct the robot's position. Attitude control can also be achieved by adjusting the robot's steering angle using PID controllers. Based on the error between the target and current directions, the PID controllers calculate the required steering angle adjustment to ensure the robot moves along the correct trajectory. However, traditional PID control is inadequate in handling complex environments and nonlinear disturbances. When external disturbances are nonlinear, the control effect is unsatisfactory, prone to overshoot and oscillation, resulting in low control accuracy. Furthermore, the parameter tuning process is complex and highly dependent on experience. Therefore, it is not very effective for trajectory tracking control of mobile robots. Additionally, because this method is asymptotically convergent, the tracking accuracy of the mobile robot remains low.

[0033] Sliding Mode Control (SMC) is a nonlinear control strategy renowned for its robustness and resistance to system uncertainties and external disturbances. SMC has wide applications in mobile robot control, particularly excelling in trajectory tracking, attitude stabilization, and speed control. This control method first designs a sliding surface to ensure the robot's tracking error converges on this surface. Then, a switching controller is designed to overcome external disturbances, bringing the robot system to the sliding surface. This design ensures the stability of the entire system, allowing the robot to move along a preset trajectory. However, due to the introduction of a switching function, this directly designed control method introduces system chattering, resulting in significant noise. In severe cases, it can even wear down and damage the robot's actuators, sacrificing controller performance. Therefore, while this method boasts robustness in overcoming external disturbances, it also introduces negative effects such as vibration in the mobile robot.

[0034] To address this, this application utilizes terminal sliding mode control to move the robot, performing fractional integral operations on the switching terms that cause system chattering, thereby reducing system chattering and achieving finite-time convergence. This results in faster convergence speed and reduced steady-state error. Furthermore, it ensures that the robot system can overcome external disturbances without requiring prior information about the disturbances, thus improving the robot's control accuracy.

[0035] This application provides a robot trajectory tracking method, the main steps of which are described below.

[0036] Set the desired trajectory for the robot; Obtain the robot's current position and orientation angle, and construct a robot dynamics model by combining the desired trajectory and preset perturbation; Based on the robot dynamics model, a fractional-order terminal sliding surface is preset, and combined with a preset fixed-time approach law, the robot's position control law and attitude control law are designed to obtain a fractional-order terminal sliding controller. The position control law and the attitude control law perform fractional-order integral operations on the switching terms that cause system chattering. The target trajectory of the robot is determined based on the fractional-order terminal sliding mode controller. Using the target trajectory, the robot's actuator is driven to move to the target position.

[0037] The embodiments of this application will now be described in further detail with reference to the accompanying drawings.

[0038] Reference Figure 1 The control flow of the entire mobile robot system is shown in the figure. By designing a novel fractional-order sliding mode controller and adjusting the gain of the switching term in the controller based on an RBF neural network, system disturbances are overcome, minimizing system vibration without the need to obtain information about system disturbances. The target trajectory is obtained through the fractional-order sliding mode controller, which is used to set the target trajectory or position of the robot's work task, and drives the motion actuator of the mobile robot to move to the desired target.

[0039] In one embodiment, the expression of the position control law includes,

[0040]

[0041]

[0042] In the formula, For the robot's desired pose angle, Control law in the horizontal direction The switching gain, The tracking error of the robot in the horizontal direction, It is a fractional-order terminal sliding surface in the horizontal direction. For vertical control law The switching gain, The tracking error of the robot in the vertical direction, For fractional-order terminal sliding surfaces in the vertical direction, , , , , express Fractional integral operations of order order, and These are the error tracking equations for the robot in the horizontal and vertical directions, respectively.

[0043] In one embodiment, the expression of the attitude control law includes,

[0044] In the formula, This is the attitude control law. The gain of the switching term in the attitude control law. For the fractional-order terminal sliding surface of the attitude, The error tracking equation is for the robot's desired pose angle. The error is the desired pose angle of the robot. , , , , express Fractional integral operations.

[0045] Specifically, first determine the dynamic model of the mobile robot. (Refer to...) Figure 2 A schematic diagram of a robot moving on a plane. Indicates the robot's current position. For the robot's posture angle, The desired trajectory of the robot, i.e., the destination the robot needs to reach during task execution, is determined by the task pre-set for the robot, or by combining trajectory planning algorithms to determine the robot's path, thus determining the desired trajectory of the mobile robot. This data is collected by sensors and positioning devices installed on the robot. Therefore, the dynamic model of the mobile robot can be represented as follows: (1) in , , This includes system uncertainties and the first, second, and third disturbances from the external environment to the system. For position control law, These two control laws are used to control the attitude of the robot and achieve its position. Tracking and achieving the included angle The movement is responsive.

[0046] Design a position control law to achieve position tracking; the robot tracking error is... , Therefore, the error tracking equation is: (2) make (3) To improve the robustness of the system, a sliding mode control algorithm is adopted, and a novel fractional-order terminal sliding surface is designed as follows:

[0047] in , , , All of these are freely set random numbers; , , express Fractional-order differential operations, express Fractional integral operations. Differentiating the above equation yields... (4) Design a fixed-time convergence law as follows: (5) It is a freely designed random number. For disturbance d The upper bound of 1 is an unknown parameter.

[0048] Sliding surfaces converge in finite time, while traditional PID (Proportional-Integral-Derivative) can only achieve asymptotic convergence. Therefore, it can improve the tracking speed and accuracy of mobile robots.

[0049] Combining formulas (4) and (5), we can obtain (6) To demonstrate the effectiveness of the designed control algorithm, the Lyapunov function is selected as... Taking its derivative, we get (7) According to Lyapunov stability theory, if we can find Therefore, the above equation is satisfied, and the tracking error... It will converge to 0, that is However, in practice, this parameter is generally unknown, and due to the existence of fractional-order operations, it is difficult to directly estimate the disturbance by designing an observer for the system. Therefore, this application, based on this control method, also designs a switching term gain based on an RBF (Radial Basis Function Network) neural network. The automatic parameter adjustment method.

[0050] Similarly, in y Direction, command Control laws can be designed. (8) In the attitude subsystem direction, Therefore, the desired pose angle for the robot. Therefore, the actual position control law is as follows: Design attitude control law Achieve angle From the perspective of expectations Tracking.

[0051] (9) From formulas (6), (8), and (9), it can be seen that the control law affects the switching term that causes chattering. Fractional integration is performed, therefore, by adjusting the fractional order, the chattering of the controller can be significantly reduced, thereby mitigating the negative impacts of traditional sliding mode controllers, such as system vibration and operating noise.

[0052] In one embodiment, a robot trajectory tracking method further includes the following steps: The switching term gain parameter of the fractional-order terminal sliding mode controller is adjusted using the RBF neural network algorithm.

[0053] Specifically, in x Taking directional control as an example, let the input of the RBF network be... The absolute value of the output is the gain of the switching term. .Pick (10) in These are the weight parameters of the neural network, which are Gaussian functions.

[0054] (11) in It is the first i The central location of each neuron It is the first i The width of each neuron. The neural network weight learning algorithm is as follows: (12) The weight adjustment algorithm is as follows (13) In the formula, For network learning rate, This is the inertia coefficient.

[0055] Reference Figure 3 , xThe RBF neural network model for the direction control channel, with system sliding mode variables and its fractional integral signal Constructing the input vector As input to the RBF neural network, the system sliding mode variable and fractional integral signal are input into the RBF neural network; The input layer of the RBF neural network structure receives... u 1; The hidden layers of the RBF neural network structure use a Gaussian function as the activation function. i The output of each neuron is ; Online learning of RBF neural network structure weights: weights w Dynamically adjust based on real-time system status: The weight adjustment amount is: ; The output layer of the RBF neural network structure: The output is the absolute value of the switching term gain. ,in w This is the weight vector of the neural network.

[0056] and x With the same direction, the above structures are applied synchronously. y Direction control channel and attitude angle Control channels, output respectively 、 To achieve control law 、 、 Automatic adjustment of gain for switching items.

[0057] Finally, the RBF neural network outputs the switching term gain of the robot's control law in the horizontal direction, control law in the vertical direction, and attitude control law.

[0058] Through real-time learning of the RBF network, the system can operate under unknown disturbances. 、 、 Under certain conditions, the gain of each channel is automatically adjusted. Based on the robot's real-time motion state, the most suitable switching gain is learned, so that the mobile robot can track the desired trajectory even under unknown disturbance information. While ensuring trajectory tracking accuracy, the gain is minimized, effectively suppressing chattering in sliding mode control and improving system smoothness and robustness.

[0059] In summary, a robot trajectory tracking method involves setting the desired trajectory of the robot; obtaining the robot's current position and attitude angle; constructing a robot dynamics model by combining the desired trajectory and preset perturbations; designing the robot's position control law and attitude control law based on the robot dynamics model and a preset fractional-order terminal sliding surface, combined with a preset fixed-time approach law, thus obtaining a fractional-order terminal sliding controller. The position control law and attitude control law perform fractional-order integral operations on the switching terms that cause system chattering, introducing fractional-order calculus operators into the design of the mobile robot controller. By further reducing controller chattering based on 1 through the fractional-order integral terms in the controller, the severe chattering problem caused by using sliding mode control for robot movement is avoided; simultaneously, finite-time convergence of tracking errors is achieved; system noise is reduced; the trajectory tracking control accuracy of the mobile robot is improved; and the tracking speed and accuracy of the mobile robot are enhanced.

[0060] A robot trajectory tracking method utilizes fractional-order calculus operators combined with sliding mode control to design a fractional-order terminal sliding mode control algorithm for mobile robots. On the one hand, it can achieve finite-time convergence of tracking errors, and on the other hand, it can further reduce controller chattering based on 1 through the fractional-order integral term in the controller, thereby avoiding the serious chattering problem caused by using sliding mode control.

[0061] A robot trajectory tracking method also designs an RBF neural network algorithm, which uses an RBF neural network to learn and adjust the switching term gain. Since the switching term can overcome external disturbances, it can overcome disturbances without prior knowledge of the disturbance information, reducing the control algorithm's dependence on disturbance information. Furthermore, the parameter adjustment will find the minimum gain, reducing controller jitter. The self-adjustment of the switching term gain parameter of the mobile robot controller can learn the most suitable switching term gain based on the robot's real-time motion state. While ensuring that the mobile robot can track the target trajectory, it can reduce jitter and avoid noise during robot operation.

[0062] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0063] This application also provides a robot trajectory tracking device, which corresponds one-to-one with the robot trajectory tracking method described in the above embodiments. The robot trajectory tracking device includes... The initial module is used to set the robot's desired trajectory; The modeling module is used to obtain the robot's current position and attitude angle, and to construct a robot dynamics model by combining the desired trajectory and preset perturbations; The sliding mode control module is used to design the robot's position control law and attitude control law based on the robot dynamics model, preset the fractional-order terminal sliding surface, and combine it with the preset fixed-time approach law to obtain the fractional-order terminal sliding mode controller. The position control law and the attitude control law perform fractional-order integral operations on the switching terms that cause system chattering. The target trajectory module is used to determine the robot's target trajectory based on the fractional-order terminal sliding mode controller.

[0064] A robot trajectory tracking device also includes, The control module is used to drive the robot's actuator to move to the target position using the target trajectory.

[0065] A robot trajectory tracking device also includes, The parameter self-adjustment module is used to adjust the switching term gain parameter of the fractional-order terminal sliding mode controller using the RBF neural network algorithm.

[0066] For specific limitations regarding a robot trajectory tracking device, please refer to the limitations regarding a robot trajectory tracking method mentioned above, which will not be repeated here.

[0067] The various modules in the aforementioned robot trajectory tracking device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0068] In one embodiment, a computer device is provided, which may be a server. The computer device includes a processor, memory, a network interface, and a database connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The network interface is used to communicate with external terminals via a network connection. When the computer program is executed by the processor, it implements any of the robot trajectory tracking methods described above.

[0069] In one embodiment, a computer-readable storage medium is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any of the robot trajectory tracking methods described above.

[0070] In one embodiment, a computer program product is provided, the computer program product including a computer program that, when executed by a processor, implements any of the robot trajectory tracking methods described above.

[0071] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. When executed, the computer program may include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0072] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above.

Claims

1. A robot trajectory tracking method, characterized in that, Includes the following steps, Set the desired trajectory for the robot; Obtain the robot's current position and orientation angle, and construct a robot dynamics model by combining the desired trajectory and preset perturbation; Based on the robot dynamics model, a fractional-order terminal sliding surface is preset, and combined with a preset fixed-time approach law, the robot's position control law and attitude control law are designed to obtain a fractional-order terminal sliding controller. The position control law and the attitude control law perform fractional-order integral operations on the switching terms that cause system chattering. The target trajectory of the robot is determined based on the fractional-order terminal sliding mode controller.

2. The robot trajectory tracking method according to claim 1, characterized in that, The expression of the position control law includes, In the formula, For the robot's desired pose angle, Control law in the horizontal direction The switching gain, The tracking error of the robot in the horizontal direction, It is a fractional-order terminal sliding surface in the horizontal direction. For vertical control law The switching gain, The tracking error of the robot in the vertical direction, For fractional-order terminal sliding surfaces in the vertical direction, , , , , express Fractional integral operations of order order, and These are the error tracking equations for the robot in the horizontal and vertical directions, respectively.

3. The robot trajectory tracking method according to claim 1, characterized in that, The expression of the attitude control law includes, In the formula, This is the attitude control law. The gain of the switching term in the attitude control law. For the fractional-order terminal sliding surface of the attitude, The error tracking equation is for the robot's desired pose angle. The error is the desired pose angle of the robot. , , , , express Fractional integral operations.

4. The robot trajectory tracking method according to claim 1, characterized in that, It also includes the following steps, The switching term gain parameter of the fractional-order terminal sliding mode controller is adjusted using the RBF neural network algorithm.

5. The robot trajectory tracking method according to claim 4, characterized in that, The step of adjusting the switching term gain parameter of the fractional-order terminal sliding mode controller using the RBF neural network algorithm includes: The system sliding mode variable and fractional integral signal are input into the RBF neural network; Using a Gaussian function as the activation function and combined with online adjusted weights, the RBF neural network outputs the switching term gain of the robot's control law in the horizontal direction, control law in the vertical direction, and attitude control law, respectively.

6. The robot trajectory tracking method according to any one of claims 1-5, characterized in that, It also includes the following steps, Using the target trajectory, the robot's actuator is driven to move to the target position.

7. A robot trajectory tracking device, characterized in that, include, The initial module is used to set the robot's desired trajectory; The modeling module is used to obtain the robot's current position and attitude angle, and to construct a robot dynamics model by combining the desired trajectory and preset perturbations; The sliding mode control module is used to design the robot's position control law and attitude control law based on the robot dynamics model, preset the fractional-order terminal sliding surface, and combine it with the preset fixed-time approach law to obtain the fractional-order terminal sliding mode controller. The position control law and the attitude control law perform fractional-order integral operations on the switching terms that cause system chattering. The target trajectory module is used to determine the robot's target trajectory based on the fractional-order terminal sliding mode controller.

8. A computer device, characterized in that, The method includes a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, characterized in that, It includes a computer program that, when executed by a processor, implements the steps of the method according to any one of claims 1 to 6.

Images