Coupling output limited Mecanum wheel trolley motion control method based on neural network and event triggering, storage medium, equipment and computer program product

Abstract

The invention provides a motion control method of a coupled output limited Mecanum wheel trolley based on a neural network and event triggering, a storage medium, equipment and a computer program product. The motion control method comprises the following steps: adopting a conversion matrix of Mecanum wheels; establishing a dynamic model of the Mecanum wheel trolley; decoupling the coupling output limitation, and converting the coupling output limitation into time-varying non-coupling limitation; improving the design of a sliding mode surface by adopting an error conversion function and a barrier function, and constructing a sliding mode controller of a trolley with limited coupling output; constructing a neural network controller; introducing an event triggering mechanism, and constructing a neural network sliding mode controller for the coupled output limited trolley based on the neural network and sliding mode control; and verifying the stability of the designed controller. According to the invention, the trajectory tracking problem of the Mecanum wheel trolley with limited coupling output based on the neural network and event triggering is solved.

Description

Technical Field

[0001] This invention relates to the field of automatic control technology, specifically to a motion control method, storage medium, device, and computer program product for a coupled output-limited Mecanum wheel trolley based on neural networks and event triggering. Background Technology

[0002] As work environments become increasingly complex, societal demands for unmanned systems are also rising. Ackerman steering models, such as those used in passenger cars, are finding it increasingly difficult to adapt to complex operating environments. Mecanum wheeled omnidirectional vehicles (MWOVs) typically consist of a chassis and four Mecanum wheels. Unlike traditional Ackerman steering vehicles, Mecanum wheel vehicles possess unique structural characteristics that allow them to move in any direction without requiring multiple reorientations. Due to their high mobility, the demand for Mecanum wheeled omnidirectional vehicles is rapidly increasing in applications such as industrial transportation and search operations.

[0003] Since real-world constraints are not always singular, coupled output constraints are crucial for unmanned McLaren robots. The existence of coupled output constraints requires the robot to consider the dynamic characteristics of multiple output variables simultaneously, preventing optimization of a single variable from causing other variables to deviate from the desired trajectory. In trajectory tracking tasks, coupled constraints ensure the coordination of the vehicle's movement and rotation angles in the x and y directions, thereby improving tracking accuracy. Furthermore, traditional sliding surface designs always consider both position and velocity simultaneously, which is practically meaningless. Therefore, improving the design of the sliding surface to constrain only the position of the unmanned McLaren robot is more practically significant. Simultaneously, both the system model itself and the friction and mass variations in the working environment introduce uncertainties into the robot's system parameters, making it susceptible to external disturbances. Therefore, addressing the adverse effects of uncertainty and external disturbances on the unmanned McLaren robot is also critical. Finally, focusing on the computational speed of the equipment hardware and minimizing resource waste also urgently needs to be addressed. Summary of the Invention

[0004] The purpose of this invention is to provide a motion control method, storage medium, device, and computer program product for a Mecanum wheel trolley based on neural networks and event triggering with coupled output constraints, in order to solve the problem that the Mecanum wheel trolley cannot achieve high-precision trajectory tracking under model uncertainty and external interference, while saving computing resources.

[0005] To achieve the above objectives, the technical solution provided by this invention is: a motion control method for a coupled output-constrained Mecanum wheel trolley based on neural networks and event triggering, comprising the following steps: S1: Use the transformation matrix of the Mecanum wheel to convert the rotational speed of the Mecanum wheel into the velocity information of the Mecanum wheel trolley in Cartesian space; S2: Establish a dynamic model of the Mecanum wheel trolley based on its speed information; S3: Decouple the coupled output constraint of the Mecanum wheel trolley and convert it into a time-varying uncoupled constraint; S4: The sliding surface is improved by using error transformation function and barrier function, and a sliding controller suitable for Mecanum wheel trolley with limited coupling output is constructed based on this. S5: Based on the sliding mode controller, construct a neural network controller for fitting the uncertainties and external disturbances of the Mecanum wheel trolley; S6: Based on a neural network controller, a neural network sliding mode controller under an event-triggered mechanism is constructed to control the movement of the Mecanum wheel trolley through the neural network sliding mode controller.

[0006] To optimize the above technical solution, the specific measures also include: In step S1, the transformation matrix of the Mecanum wheel is specifically as follows:

[0007]

[0008] in, This indicates the rotational speed of each Mecanum wheel; This indicates the position of the Mecanum wheel trolley in Cartesian space; Indicates the lateral position of the Mecanum wheel cart; Indicates the longitudinal position of the Mecanum wheel trolley; This indicates the turning angle of the Mecanum wheel cart; This represents the velocity information of the Mecanum wheel trolley in Cartesian space; R represents the radius of the Mecanum wheel. and These represent the lateral and longitudinal distances from the center of the Mecanum wheel to the center of the Mecanum wheel trolley, respectively.

[0009] In step S2, the dynamic model of the Mecanum wheel trolley is represented as follows:

[0010] in, Let represent the positive definite system inertia matrix of the Mecanum wheel trolley; The matrix representing the viscous friction coefficient of the Mecanum wheel; and This indicates the uncertainty of the Mecanum wheel cart; This represents the velocity vector of the Mecanum wheel cart; This represents the acceleration vector of the Mecanum wheel cart; This indicates the input voltage of each drive motor of the Mecanum wheel trolley; This indicates external interference.

[0011] In step S3, the coupled output constraint of the Mecanum wheel trolley is decoupled and converted into a time-varying uncoupled constraint, specifically as follows:

[0012]

[0013] in, This represents the lateral coordinate of the Mecanum wheel trolley in Cartesian space; This represents the longitudinal coordinate of the Mecanum wheel trolley in Cartesian space; This indicates the steering angle of the Mecanum wheel trolley; Indicates a restricted range; and These represent the upper and lower limits of the rotation angle, respectively. Furthermore, let Let represent the position vector of the Mecanum wheel trolley, and the diamond constraint is represented as:

[0014]

[0015] in, It is a time-varying variable. This represents the lateral coordinate of the Mecanum wheel trolley before decoupling. This represents the longitudinal coordinate of the Mecanum wheel trolley before decoupling. This represents the steering angle of the Mecanum wheel trolley before decoupling; a rotation matrix is ​​designed to simplify the limited coupled output:

[0016] in, Indicates the rotation angle; Furthermore, by transforming the matrix, Converted to :

[0017] in, This represents the position vector of the decoupled Mecanum wheel trolley. This represents the lateral position coordinates of the Mecanum wheel trolley after decoupling. This represents the longitudinal position coordinates of the Mecanum wheel trolley after decoupling. The time-varying uncoupled constraint represents the steering angle of the decoupled Mecanum wheel trolley.

[0018] in, This indicates a limited scope; In step S4, the design of the error transformation function and barrier function to improve the sliding surface, and the design of a sliding mode controller suitable for a Mecanum wheel trolley with limited coupling output, specifically involves: The design of the sliding surface is represented as follows:

[0019]

[0020] in, Indicates tracking error The derivative; Represents the desired trajectory. and Let x and y represent the desired horizontal and vertical coordinates, respectively. Indicates the desired steering angle. It is a constant representing gain. Represents an unrestricted error variable; Furthermore, the limitation of tracking error is expressed as:

[0021] in, and These represent the lower and upper bounds of the tracking error, respectively. and They represent The lower and upper bounds of a variable.

[0022] Tracking error transformation function and barrier function They are represented as follows:

[0023]

[0024] in, Represents an unrestricted error variable; The derivative with respect to time is expressed as:

[0025] Furthermore, the improved sliding surface is represented as follows:

[0026] The synovial controller is:

[0027]

[0028] in, This represents the transformation matrix in the above design; Represents gain; It represents an uncertain variable.

[0029] Further, in step S5, the neural network controller is represented as:

[0030]

[0031]

[0032]

[0033] in, and Indicates the relevant uncertain variables; This indicates the overall uncertainty and disturbances; The velocity vector of the Mecanum wheel cart; through the activation function in the neural network. Come to Perform fitting; in, Indicates the drift term; Represents the weight matrix of the neural network; This represents the activation function of the neural network.

[0034] In step S6, the process of constructing a neural network sliding mode controller based on an event-triggered mechanism, and controlling the movement of the Mecanum wheel trolley through the neural network sliding mode controller, is as follows: The event triggering mechanism is designed as follows:

[0035] in, Indicates the first i The state-triggered time j+1 of a sequence of states; This represents the (j+1)th time when the state of the kth state sequence is triggered. The infimum represents the minimum time required to satisfy the condition; express The trigger threshold; This represents the threshold threshold for triggering neural network weight updates. This represents the derivative of the weighted observations of the (k-2)th state sequence; Indicates tracking error; Furthermore, based on the neural network controller, the neural network sliding mode controller under the event-triggered mechanism is represented as:

[0036] in, This represents the input voltage of each drive motor of the Mecanum wheel trolley after the event triggering mechanism is activated; This represents the synovial surface obtained after the event triggering mechanism; This represents the derivative of the unrestricted error variable with respect to time after the event triggering mechanism. This represents the estimated total uncertainty and disturbances of the Mecanum wheel trolley; yes The second derivative of represents the expected acceleration of the Mecanum wheel trolley.

[0037] The present invention also proposes a computer-readable storage medium storing a computer program that enables a computer to execute a motion control method for a coupled output-constrained Mecanum wheel trolley based on a neural network and event triggering, as described above.

[0038] The present invention also proposes an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, it implements a motion control method for a coupled output-constrained Mecanum wheel trolley based on a neural network and event triggering as described above.

[0039] Furthermore, the present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the motion control method for a coupled output-constrained Mecanum wheel trolley based on neural networks and event triggering.

[0040] Compared with the prior art, the beneficial effects of the present invention are: This invention precisely decouples complex coupled geometric constraints by designing a rotation matrix, transforming them into time-varying uncoupled constraints. It then seamlessly integrates these constraints into the controller design using error transformation and obstacle functions. This innovation fundamentally solves the problem that traditional control methods cannot directly handle such complex constraints, ensuring that the vehicle's motion state never exceeds physical limits, and greatly improving the system's safety and reliability.

[0041] This invention combines an event-triggered mechanism with neural network sliding mode control, enabling the controller to update only when the tracking error or network weight changes exceed a predetermined threshold. Compared to traditional periodic control, this significantly reduces the consumption of computing resources and the frequency of actuator actions, effectively conserves the computing power of the onboard computing unit, extends system life, and makes it possible to implement complex control algorithms on resource-constrained embedded platforms.

[0042] This invention introduces a radial basis function neural network to approximate and compensate for unmodeled dynamics, parameter uncertainties, and external disturbances in the system online. The controller has strong adaptive capabilities and robustness, significantly reducing model dependence, and thus can maintain extremely high trajectory tracking accuracy even under complex and time-varying working conditions.

[0043] This invention is not only applicable to Mecanum wheel vehicles, but its core concept can also be extended to other mobile robot systems facing similar coupling constraints, demonstrating good versatility and broad engineering application prospects. Attached Figure Description

[0044] Figure 1 This is a model of the Mecanum wheel cart in an embodiment of the present invention.

[0045] Figure 2 The images shown are actual pictures and scene diagrams of the Mecanum wheel cart in the embodiments of the present invention.

[0046] Figure 3 This describes the tracking performance and output characteristics of the vehicle in a simulated environment in this embodiment of the invention.

[0047] Figure 4 This illustrates the triggering mechanism of the vehicle in this embodiment of the invention.

[0048] Figure 5 This describes the tracking performance and output characteristics of the vehicle under experimental conditions in this embodiment of the invention. Detailed Implementation

[0049] The present invention will be further described in detail below through specific embodiments, but it should not be construed as limiting the scope of the subject matter of the present invention to the following embodiments. All technologies implemented based on the above content of the present invention fall within the scope of the present invention.

[0050] This invention proposes a motion control method for a coupled output-constrained Mecanum wheel trolley based on neural networks and event triggering, comprising the following steps: S1: The rotational speed of the Mecanum wheel is converted into the speed information of the Mecanum wheel trolley in Cartesian space using the transformation matrix of the Mecanum wheel.

[0051] In this embodiment, the transformation matrix is ​​specifically:

[0052]

[0053] in, This indicates the rotational speed of each Mecanum wheel; This indicates the position of the Mecanum wheel trolley in Cartesian space; Indicates the lateral position of the Mecanum wheel cart; Indicates the longitudinal position of the Mecanum wheel trolley; This indicates the turning angle of the Mecanum wheel cart; This represents the velocity information of the Mecanum wheel trolley in Cartesian space; R represents the radius of the Mecanum wheel. and These represent the lateral and longitudinal distances from the center of the Mecanum wheel to the center of the Mecanum wheel trolley, respectively.

[0054] S2: Establish a dynamic model of the Mecanum wheel trolley based on its speed information.

[0055] In this embodiment, the dynamic model of the Mecanum wheel trolley is represented as follows:

[0056] in, Let represent the positive definite system inertia matrix of the Mecanum wheel trolley; The matrix representing the viscous friction coefficient of the Mecanum wheel; and This indicates the uncertainty of the Mecanum wheel cart; This represents the velocity vector of the Mecanum wheel cart; This represents the acceleration vector of the Mecanum wheel cart; This indicates the input voltage of each drive motor of the Mecanum wheel trolley; This indicates external interference.

[0057] S3: Decouple the coupled output of the Mecanum wheel trolley and convert it into a time-varying uncoupled restricted output.

[0058] In this embodiment, the coupling output of the Mecanum wheel trolley is limited as follows:

[0059]

[0060] in, This represents the lateral coordinate of the Mecanum wheel trolley in Cartesian space; This represents the longitudinal coordinate of the Mecanum wheel trolley in Cartesian space; This indicates the steering angle of the Mecanum wheel trolley; Indicates a restricted range; and These represent the upper and lower limits of the rotation angle, respectively. Rename the variable to make represents the position vector of the Mecanum wheel trolley. Decoupling the coupled output constraint is performed, transforming the coupled-constrained problem into a time-varying output uncoupled-constrained problem, represented by the diamond constraint:

[0061]

[0062] in, It is a time-varying variable. This represents the lateral coordinate of the Mecanum wheel trolley before decoupling. This represents the longitudinal coordinate of the Mecanum wheel trolley before decoupling. This indicates the steering angle of the Mecanum wheel trolley before decoupling.

[0063] Design a rotation matrix to transform the rhombus constraint into a square constraint, making its upper and lower bounds equal to those of a square:

[0064] in, Indicates the rotation angle.

[0065] In some implementations, the transformation matrix is ​​used to make , Converted to :

[0066] in, This represents the position vector of the decoupled Mecanum wheel trolley. This represents the lateral position coordinates of the Mecanum wheel trolley after decoupling. This represents the longitudinal position coordinates of the Mecanum wheel trolley after decoupling. The time-varying uncoupled constraint represents the steering angle of the decoupled Mecanum wheel trolley.

[0067] in, This indicates a limited scope.

[0068] The decoupling method designed in this invention can be applied to many geometric shapes, such as spheres.

[0069] In this embodiment, At this point, the time-varying output uncoupled constraint is expressed as:

[0070] in, , , At this point, the time-varying output uncoupled and restricted of the Mecanum wheel trolley is expressed as:

[0071]

[0072] in, and These represent the upper and lower bounds of the time-varying constraint, respectively.

[0073] In this embodiment, when a three-dimensional graphic is projected onto a two-dimensional plane, the constraints become:

[0074]

[0075] S4: The sliding surface is improved by using error transformation function and barrier function, and a sliding controller suitable for Mecanum wheel trolley with limited coupling output is constructed based on this.

[0076] In this embodiment, the sliding surface is designed as follows:

[0077] in, Indicates tracking error The derivative; Represents the desired trajectory. and Let x and y represent the desired horizontal and vertical coordinates, respectively. Indicates the desired steering angle. It is a constant representing gain. This represents an unrestricted error variable.

[0078] The limitation of tracking error is expressed as follows:

[0079] in, and These represent the lower and upper bounds of the tracking error, respectively.

[0080] Preferably, the error transformation function and the barrier function transform the error-constrained problem into an unconstrained error problem, which is expressed as:

[0081]

[0082] The derivative with respect to time is expressed as:

[0083] The improved sliding surface is represented as follows:

[0084] At this point, the improved sliding surface only restricts the position, instead of using position and velocity information uniformly to design the sliding surface, which does not consider practical significance, as is the case with traditional sliding surface design.

[0085] Consider the following Lyapunov function:

[0086] right Differentiation yields:

[0087] Based on Lyapunov theory and dynamics, the sliding membrane controller is designed as follows:

[0088]

[0089]

[0090] in, Indicates gain; and This represents the relevant uncertain variables.

[0091] S5: Based on the sliding mode controller, construct a neural network controller for fitting the uncertainties and external disturbances of the Mecanum wheel trolley.

[0092] In this embodiment, to fit uncertainties and external disturbances, the neural network sliding membrane controller is designed as follows:

[0093] in, and Indicates the relevant uncertain variables, This represents the overall uncertainty and disturbances in the system. Radial basis functions (RBFs) are used to fit uncertainties and disturbances. Indicates the drift term; Represents the weight matrix of the neural network; This represents the activation function of the neural network.

[0094] The Gaussian function is expressed as:

[0095] in, and It is a constant.

[0096] The estimated values ​​of the total uncertainty and disturbances of the system are expressed as follows:

[0097] in, Let be the weight vector. The observation error is expressed as:

[0098] The update rate of the neural network weights is:

[0099] in, This represents the weighting error.

[0100] Preferably, the control law of the neural network is updated as follows:

[0101] S6: Based on a neural network controller, a neural network sliding mode controller under an event-triggered mechanism is constructed to control the movement of the Mecanum wheel trolley through the neural network sliding mode controller.

[0102] In this embodiment, the event triggering mechanism is designed as follows:

[0103] in, Indicates the first i The state-triggered time j+1 of a sequence of states; This represents the (j+1)th time when the state of the kth state sequence is triggered. The infimum represents the minimum time required to satisfy the condition; express The trigger threshold; This represents the threshold threshold for triggering neural network weight updates. This represents the derivative of the weighted observations of the (k-2)th state sequence; This indicates the tracking error.

[0104] The event-triggered, coupled neural network synovial controller is represented as follows:

[0105] in, This represents the input voltage of each drive motor of the Mecanum wheel trolley after the event triggering mechanism is activated; This represents the synovial surface obtained after the event triggering mechanism; This represents the derivative of the unrestricted error variable with respect to time after the event triggering mechanism. This represents the estimated total uncertainty and disturbances of the Mecanum wheel trolley; yes The second derivative of represents the expected acceleration of the Mecanum wheel trolley.

[0106] In summary, consider the following Lyapunov function:

[0107] in, It is a positive definite matrix. For Differentiation yields:

[0108] As a preferred embodiment, the analysis of the key components yields the following results:

[0109] Based on the designed event-triggered mechanism, a stability analysis of the neural network sliding mode controller is performed:

[0110] in,

[0111]

[0112] In some implementations, the stability of the designed output-coupled limited Mecanum wheel trolley controller is verified.

[0113] The effectiveness of the method proposed in this embodiment is demonstrated through specific experiments, including the following steps: Step A: Establish the dynamic model of the Mecanum wheel trolley:

[0114] Step B: Set the parameters of the Mecanum wheel trolley as follows:

[0115] Step C: Based on the set controller logic and parameter design, conduct simulation and experimentation.

[0116] The simulations and experiments in this embodiment included three comparative tests: neural network-based and event-triggered coupled output limited (ETSMNNC), model-based synovial membrane (MBSMC), and PD.

[0117] Numerical simulation results and physical experiment results demonstrate that the control method proposed in this embodiment has good feasibility and can improve the tracking accuracy and robustness of the Mecanum wheel trolley. The simulation platform is based on Matlab R2022a under a Windows 11 64-bit operating system, and the simulation object is as follows... Figure 1 and 2The model of the Mecanum wheel car shown.

[0118] In this embodiment, the experimental subject is Figure 1 and 2 As shown, code is programmed and written based on ROS, and the initial state of the Mecanum wheel cart is set to... .

[0119] External interference settings: . , , P=0.4, D=4.0. In this embodiment, the parameters are set to... , , P=10.4, D=4.7.

[0120] The reference trajectory for the Mecanum wheel cart is:

[0121] In this embodiment, Figure 3 The tracking performance of the Mecanum wheel trolley in simulation. Figure 3 (a) Comparison of the actual trajectory of the Mecanum wheel trolley on a two-dimensional plane with the expected trajectory, visually demonstrating the accuracy of the tracking. Figure 3 (b) and Figure 3 (c) shows the changes in the position of the Mecanum wheel trolley in the lateral and longitudinal directions over time, and compares them with the expected values, demonstrating the performance of the controller under time-varying constraints after decoupling. Figure 3 (e) demonstrates the case where the Mecanum wheel trolley's steering angle tracks the desired angle over time, validating the ability to handle rotational constraints. Figure 3 (f) Quantifies the overall trajectory tracking error and demonstrates the convergence and steady-state performance of the error. Figure 3 (g) shows the change in the input motor torque of the controller, reflecting the smoothness and feasibility of the control.

[0122] Figure 4 This illustrates the triggering mechanism of the Mecanum wheel car, where the length of the vertical line represents the time interval since the last update, and the position of the vertical line indicates the update time. Figure 4 (a) shows the actual trajectory of the Mecanum wheel trolley under event-triggered control. Compared to periodic control, the trajectory remains smooth and accurate, but the number of control updates is significantly reduced. Figure 4 (b) and Figure 4 (c) By setting two different thresholds, the specific moments of controller state and neural network weight updates were marked.

[0123] Figure 5The figure shows the tracking performance of the Mecanum wheel cart under experimental conditions. As shown, the Mecanum wheel cart consistently tracks the set trajectory within the specified range and does not exceed the coupling-limited area, demonstrating good control performance. The designed event triggering mechanism is also effectively implemented, significantly reducing the waste of computational resources.

[0124] In another embodiment of the present invention, an electronic device is proposed, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements a motion control method for a coupled output-constrained Mecanum wheel trolley based on a neural network and event triggering, as described above.

[0125] In another embodiment of the present invention, a computer-readable storage medium is provided storing a computer program that causes a computer to execute a motion control method for a coupled output-constrained Mecanum wheel trolley based on a neural network and event triggering, as described above.

[0126] In one technical solution of the present invention, a computer program product is also provided, including a computer program, which, when executed by a processor, implements the deployment optimization method for the end-to-end integrated operation and maintenance machine. In the embodiments disclosed in this application, a computer storage medium may be a tangible medium that may contain or store programs for use by or in conjunction with an instruction execution system, apparatus, or device. The computer storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of computer storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0127] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Any simple modifications, equivalent substitutions, and improvements made by those skilled in the art to the above embodiments without departing from the scope of the technical solution of the present invention, based on the technical essence of the present invention, shall still fall within the protection scope of the technical solution of the present invention.

Claims

1. A motion control method for a coupled output-constrained Mecanum wheel trolley based on neural networks and event triggering, characterized in that, Includes the following steps: S1: Use the transformation matrix of the Mecanum wheel to convert the rotational speed of the Mecanum wheel into the velocity information of the Mecanum wheel trolley in Cartesian space; S2: Establish a dynamic model of the Mecanum wheel trolley based on its speed information; S3: Decouple the coupled output constraint of the Mecanum wheel trolley and convert it into a time-varying uncoupled constraint; S4: The sliding surface is improved by using error transformation function and barrier function, and a sliding controller suitable for Mecanum wheel trolley with limited coupling output is constructed based on this. S5: Based on the sliding mode controller, construct a neural network controller for fitting the uncertainties and external disturbances of the Mecanum wheel trolley; S6: Based on a neural network controller, a neural network sliding mode controller under an event-triggered mechanism is constructed to control the movement of the Mecanum wheel trolley through the neural network sliding mode controller.

2. The motion control method for a coupled output-constrained Mecanum wheel trolley based on neural networks and event triggering as described in claim 1, characterized in that: In step S1, the transformation matrix of the Mecanum wheel is specifically as follows: in, This indicates the rotational speed of each Mecanum wheel; This indicates the position of the Mecanum wheel trolley in Cartesian space; Indicates the lateral position of the Mecanum wheel cart; Indicates the longitudinal position of the Mecanum wheel trolley; This indicates the turning angle of the Mecanum wheel cart; This represents the velocity information of the Mecanum wheel trolley in Cartesian space; R represents the radius of the Mecanum wheel. and These represent the lateral and longitudinal distances from the center of the Mecanum wheel to the center of the Mecanum wheel trolley, respectively.

3. The motion control method for a coupled output-constrained Mecanum wheel trolley based on neural networks and event triggering as described in claim 1, characterized in that: In step S2, the dynamic model of the Mecanum wheel trolley is represented as follows: in, Let represent the positive definite system inertia matrix of the Mecanum wheel trolley; The matrix representing the viscous friction coefficient of the Mecanum wheel; and This indicates the uncertainty of the Mecanum wheel cart; This represents the velocity vector of the Mecanum wheel cart; This represents the acceleration vector of the Mecanum wheel cart; This indicates the input voltage of each drive motor of the Mecanum wheel trolley; This indicates external interference.

4. The motion control method for a coupled output-constrained Mecanum wheel trolley based on neural networks and event triggering as described in claim 1, characterized in that: In step S3, the coupled output constraint of the Mecanum wheel trolley is decoupled and converted into a time-varying uncoupled constraint, specifically as follows: in, This represents the lateral coordinate of the Mecanum wheel trolley in Cartesian space; This represents the longitudinal coordinate of the Mecanum wheel trolley in Cartesian space; This indicates the steering angle of the Mecanum wheel trolley; Indicates a restricted range; and These represent the upper and lower limits of the rotation angle, respectively. make Let represent the position vector of the Mecanum wheel trolley, and the diamond constraint is represented as: in, It is a time-varying variable. This represents the lateral coordinate of the Mecanum wheel trolley before decoupling. This represents the longitudinal coordinate of the Mecanum wheel trolley before decoupling. This represents the steering angle of the Mecanum wheel trolley before decoupling; a rotation matrix is ​​designed to simplify the limited coupled output: in, Indicates the rotation angle; By transforming the matrix Converted to : in, This represents the position vector of the decoupled Mecanum wheel trolley. This represents the lateral position coordinates of the Mecanum wheel trolley after decoupling. This represents the longitudinal position coordinates of the Mecanum wheel trolley after decoupling. The time-varying uncoupled constraint represents the steering angle of the decoupled Mecanum wheel trolley. in, This indicates a limited scope.

5. The motion control method for a coupled output-constrained Mecanum wheel trolley based on neural networks and event triggering as described in claim 4, characterized in that: In step S4, the design of the error transformation function and barrier function to improve the sliding surface, and the design of a sliding mode controller suitable for a Mecanum wheel trolley with limited coupling output, specifically involves: The design of the sliding surface is represented as follows: in, Indicates tracking error The derivative; Represents the desired trajectory. and Let x and y represent the desired horizontal and vertical coordinates, respectively. Indicates the desired steering angle. It is a constant representing gain. Represents an unrestricted error variable; The limitation of tracking error is expressed as follows: in, and These represent the lower and upper bounds of the tracking error, respectively. and They represent The lower and upper bounds of a variable; Tracking error transformation function and barrier function They are represented as follows: The derivative with respect to time is expressed as: The improved sliding surface is represented as follows: The synovial controller is: in, This represents the transformation matrix in the above design; Represents gain; Represents uncertain variables; Let represent the positive definite system inertia matrix of the Mecanum wheel trolley.

6. The motion control method for a coupled output-constrained Mecanum wheel trolley based on neural networks and event triggering as described in claim 5, characterized in that: In step S5, the neural network controller is represented as: in, and d represents the relevant uncertain variable; d represents external disturbance. This indicates the overall uncertainty and disturbances; The velocity vector of the Mecanum wheel cart; through the activation function in the neural network. Come to Perform fitting; in, Indicates the drift term; Represents the weight matrix of the neural network; This represents the activation function of the neural network.

7. The motion control method for a coupled output-constrained Mecanum wheel trolley based on neural networks and event triggering as described in claim 1, characterized in that: In step S6, the process of constructing a neural network sliding mode controller based on an event-triggered mechanism, and controlling the movement of the Mecanum wheel trolley through the neural network sliding mode controller, is as follows: The event triggering mechanism is designed as follows: in, Indicates the first i The state-triggered time j+1 of a sequence of states; This represents the (j+1)th time when the state of the kth state sequence is triggered. The infimum represents the minimum time required to satisfy the condition; express The trigger threshold; This represents the threshold threshold for triggering neural network weight updates. This represents the derivative of the weighted observations of the (k-2)th state sequence; Indicates tracking error; Based on a neural network controller, the neural network sliding mode controller under the event-triggered mechanism is represented as follows: in, This represents the positive definite system inertia matrix of the Mecanum wheeled vehicle. T Represents the transformation matrix; This represents the input voltage of each drive motor of the Mecanum wheel trolley after the event triggering mechanism is activated; This represents the synovial surface obtained after the event triggering mechanism; This represents the derivative of the unrestricted error variable with respect to time after the event triggering mechanism. This represents the estimated total uncertainty and disturbances of the Mecanum wheel trolley; Represents gain; It is a constant representing gain; yes The second derivative of represents the expected acceleration of the Mecanum wheel trolley.

8. A computer-readable storage medium storing a computer program, characterized in that, The computer program causes the computer to execute the motion control method for a coupled output-constrained Mecanum wheel trolley based on neural networks and event triggering as described in any one of claims 1 to 6.

9. An electronic device, characterized in that, include: The invention includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the motion control method for a coupled output-constrained Mecanum wheel trolley based on neural networks and event triggering as described in any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the motion control method for a coupled output-constrained Mecanum wheel trolley based on neural networks and event triggering as described in any one of claims 1 to 6.

Images