Path tracking-based water surface unmanned ship control method and system

Abstract

The application discloses a water surface unmanned ship control method and system under path tracking, relates to the technical field of attitude control, and comprises the following steps: establishing a dynamic model of a water surface unmanned ship; establishing a path tracking error equation for describing system error of the water surface unmanned ship relative to an expected path under a Serret-Frenet coordinate system; constructing a path tracking controller based on a linear active disturbance rejection controller; inputting the system error and a water surface unmanned ship control signal into a fuzzy RBF neural network to minimize the system error and output optimized control parameters of the path tracking controller; updating the path tracking controller according to the optimized control parameters; re-estimating external disturbance by using the updated path tracking controller, outputting an optimized water surface unmanned ship control signal, and controlling the water surface unmanned ship to travel along the expected path. The application improves the attitude control precision under strong sea currents and variable weather, and greatly improves the path tracking precision of the water surface unmanned ship.

Description

Technical Field

[0001] This invention belongs to the field of attitude control technology, and relates to a control method and system for unmanned surface vessels, particularly a control method and system for unmanned surface vessels under path tracking. Background Technology

[0002] Unmanned surface vehicles (USVs) are vessels that do not require human piloting and typically navigate automatically through a pre-defined control system. These vessels are widely used in fields such as marine research, environmental monitoring, and military reconnaissance, possessing capabilities including autonomous navigation, data collection, and remote operation. Driven by their own propulsion or natural forces such as waves and wind, they can perform tasks on the water for extended periods.

[0003] Autonomous control capabilities are crucial for unmanned surface vessels (USVs) as they often operate in harsh marine environments. An effective control system ensures stable navigation and precise path tracking amidst complex currents, waves, and other natural disturbances. Furthermore, the robustness and adaptability of the control system are essential for enabling USVs to respond to unforeseen circumstances and avoid collisions or deviations from their paths during remote missions.

[0004] However, current surface unmanned vessel control systems lack high precision in complex marine environments, especially under conditions of strong currents or variable weather. The control system cannot effectively cope with nonlinear disturbances in the dynamic environment and internal system noise, resulting in large errors in heading control and path tracking. Summary of the Invention

[0005] In view of the shortcomings of the prior art, the present invention provides a path-tracking control method and system for unmanned surface vessels, which can solve the technical problems of low control accuracy of current unmanned surface vessels in complex marine environments, especially under strong currents or variable weather conditions, where the control system cannot effectively cope with nonlinear disturbances in the dynamic environment and internal system noise, resulting in large errors in heading control and path tracking.

[0006] The technical solution adopted in this invention is as follows:

[0007] A method for controlling an unmanned surface vessel using path tracking includes the following steps:

[0008] Construct a dynamic model of an unmanned surface vessel;

[0009] Based on the aforementioned dynamic model, a path tracking error equation is established in the Serret-Frenet coordinate system. This path tracking error equation is used to quantify the systematic error between the actual navigation state of the unmanned surface vessel and the desired path.

[0010] A path tracking controller based on a linear active disturbance rejection controller is constructed. The path tracking controller estimates and compensates for the external disturbances faced by the unmanned surface vessel and outputs the initial control signal of the unmanned surface vessel.

[0011] The system error and the initial unmanned surface vessel control signal are input into a fuzzy RBF neural network to minimize the system error and output the optimized control parameters of the path tracking controller.

[0012] The path tracking controller is updated according to the optimized control parameters. The external disturbance is re-estimated using the updated path tracking controller, and an optimized surface unmanned vessel control signal is output. Based on the optimized surface unmanned vessel control signal, the surface unmanned vessel is controlled to travel along the desired path.

[0013] Furthermore, the specific steps for constructing the dynamic model of the unmanned surface vessel include:

[0014] Based on the Newton-Euler equations, the position and velocity vectors of the unmanned surface vessel in the preset coordinate system are determined, and then the dynamic model is constructed by combining the position and velocity vectors.

[0015] Furthermore, the preset coordinate system includes a system coordinate system and a ground-fixed coordinate system;

[0016] The origin of the system coordinate system is the center of the unmanned surface vessel. The x-axis points in the direction of the unmanned surface vessel's movement, the y-axis is perpendicular to the x-axis and points to the starboard side of the unmanned surface vessel, and the z-axis is determined based on the x-axis and y-axis using the right-hand rule.

[0017] The origin of the Earth-fixed coordinate system is the Earth's center of mass, the x-axis points towards the geographic North Pole, the y-axis points towards the geographic East Pole, and the z-axis points vertically downwards.

[0018] Furthermore, the system error includes lateral error and heading error; the lateral error is the vertical offset between the unmanned surface vessel and the desired path; the heading error is the angular deviation between the actual heading of the unmanned surface vessel and the heading corresponding to the desired path.

[0019] Furthermore, the path tracking controller introduces multiple feedback control gains and multiple observer gains. The observer gains are used to estimate the current heading, heading rate of change, and total external disturbance of the unmanned surface vessel in real time. The control parameters are adjusted in combination with the feedback control gains to compensate for the external disturbance.

[0020] Furthermore, the fuzzy RBF neural network includes an input layer, a fuzzification layer, a fuzzy inference layer, and an output layer connected in sequence, and the fuzzification layer is directly connected to the output layer.

[0021] Furthermore, the input layer receives system errors and initial surface unmanned vessel control signals, and transmits the input data using a linear activation function;

[0022] The fuzzification layer performs fuzzification processing on the input data and calculates the fuzzy quantities of the system error and the initial unmanned surface vessel control signal, which belong to different fuzzy sets respectively.

[0023] The fuzzy inference layer performs pairwise multiplication of the fuzzy quantities of different fuzzy sets corresponding to each input data, and outputs the inference result.

[0024] The output layer receives the inference results output by the fuzzy inference layer and calculates the initial optimization control parameters based on the preset connection weight matrix.

[0025] Furthermore, the fuzzy RBF neural network optimizes the connection weight matrix by introducing a learning momentum factor and a learning rate. It calculates a performance index function based on the deviation between the ideal output and the actual output of the output layer at the current iteration number. When the value of the performance index function is less than a preset threshold, the initial optimization control parameters are output as the final optimization control parameters. If the threshold is not met, the learning momentum factor and learning rate are updated, the initial optimization control parameters are recalculated, and the optimization process is repeated.

[0026] Furthermore, the optimized control parameters include the observer bandwidth assumption, the estimated value of the external disturbance effect, and the feedback control gain.

[0027] A path-tracking-based unmanned surface vessel control system includes:

[0028] One or more processors;

[0029] Memory, used to store one or more programs;

[0030] When the one or more programs are executed by the one or more processors, the one or more processors implement the above-described path-tracking unmanned surface vessel control method.

[0031] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0032] This invention constructs a dynamic model to accurately describe the motion characteristics of an unmanned surface vessel (USV), and establishes a path tracking error equation using the Serret-Frenet coordinate system, thereby improving the accuracy of error estimation. Secondly, it employs a linear active disturbance rejection controller (ADRC) for estimating and compensating for external disturbances, enabling the USV to effectively cope with nonlinear disturbances and internal noise in complex marine environments, significantly improving the accuracy of heading control. By dynamically optimizing the controller using a fuzzy RBF neural network, it can not only adjust control parameters in real time but also reduce errors caused by disturbances, ensuring the USV's stable navigation along the desired path. This further improves control accuracy and enhances robustness, particularly demonstrating excellent performance under strong currents and variable weather conditions, greatly improving the path tracking accuracy of the USV. Attached Figure Description

[0033] Figure 1 This is a schematic flowchart of a path-tracking-based unmanned surface vessel control method provided in an embodiment of the present invention.

[0034] Figure 2 This is a schematic diagram of the coordinate system in an embodiment of the present invention.

[0035] Figure 3 This is a schematic diagram of a path-tracking unmanned surface vessel control system according to an embodiment of the present invention. Detailed Implementation

[0036] The technical solution of the present invention will be further described clearly and in detail below with reference to the accompanying drawings and specific examples.

[0037] like Figure 1 The diagram shown is a flowchart illustrating a path-tracking-based unmanned surface vessel control method provided in an embodiment of the present invention.

[0038] This invention provides a method for controlling unmanned surface vessels under path tracking, which may include the following steps:

[0039] S1: Establish a dynamic model of the unmanned surface vessel.

[0040] The dynamics model refers to the mathematical description of the motion behavior of unmanned surface vessels (USVs), which is usually expressed by equations to represent the vessel's mechanical characteristics, velocity, acceleration, direction, and other factors. This model is typically based on physical laws, such as the Newton-Euler equations, and takes into account factors such as the USV's mass, inertia, external forces (such as water flow and wind) and internal forces (such as propulsion), thereby enabling the prediction of the USV's motion state in different environments.

[0041] It should be noted that establishing a dynamic model of the unmanned surface vessel provides an accurate mathematical basis for subsequent control strategies, ensuring that the control system can make reasonable adjustments based on the vessel's actual motion characteristics. This model provides a precise dynamic description for path tracking, which helps improve control accuracy and system response robustness in complex environments.

[0042] In one possible implementation, S1 specifically includes:

[0043] S11: Determine the position and velocity vectors of the unmanned surface vessel in the Earth-fixed coordinate system based on the Newton-Euler equations:

[0044]

[0045]

[0046]

[0047]

[0048]

[0049]

[0050] in, Indicates the course of the unmanned surface vessel. Represents the arctangent function. and Let represent the lateral and longitudinal velocities of the unmanned surface vessel in the Earth-fixed coordinate system, respectively. This represents the yaw angle of the unmanned surface vessel's floating body in the system coordinate system. This represents the yaw angle of the unmanned surface vessel in the system coordinate system. express and The deviation between Represents the velocity vector. and These represent the lateral and longitudinal velocities of the unmanned surface vessel relative to the ocean current in the system coordinate system, respectively, with the subscript T indicating transpose. This represents the roll angle of the unmanned surface vessel in the system coordinate system. This represents the pitch angle of the underwater drone in the system coordinate system. ) represents the position vector. Let represent the heading angle of the unmanned surface vessel, p represent the angular depth of the unmanned surface vessel around the x-axis, and q represent the angular velocity of the unmanned surface vessel around the y-axis. This represents the yaw angle and angular velocity of an unmanned surface vessel. This represents the yaw angle and angular velocity of the unmanned surface vessel's traction mechanism. This represents the velocity of the unmanned surface vessel along the x-axis. This represents the velocity of the unmanned surface vessel along the y-axis. Indicates the longitudinal velocity of the ocean current. Indicates the lateral velocity of ocean currents. Indicates the longitudinal velocity of the wind. The first derivative representing the lateral position of the unmanned surface vessel. express cosine value, express cosine value, express The sine value, express The sine value, express The cosine value, express The first derivative, express The tangent value, express The sine value, This represents the roll angle and angular velocity of the unmanned surface vessel. The first derivative representing the longitudinal position of the unmanned surface vessel. express The first derivative, express The first derivative, express The first derivative, This represents the angular velocity of the unmanned surface vessel's buoyancy. ω represents the heading angle and angular velocity of the unmanned surface vessel's tractor, and w represents the vertical velocity of the unmanned surface vessel. Indicates and , , The relevant component of the unmanned surface vessel along the z-axis.

[0051] Specifically, It is the component of the unmanned surface vessel's velocity along the z-axis. Through Euler angles (especially , , () Transform a portion of the projection into an inertial or geographic coordinate system.

[0052] Among them, the position vector and velocity vector describe the position and velocity of the unmanned surface vessel in space.

[0053] In one possible implementation, the origin of the system coordinate system is the center of the unmanned surface vessel, the x-axis points in the direction of the unmanned surface vessel's movement, the y-axis is perpendicular to the x-axis and points to the starboard side of the unmanned surface vessel, and the z-axis points in a vertical direction determined by the right-hand rule based on the x-axis and y-axis.

[0054] The origin of the Earth-fixed coordinate system is the Earth's center of mass, the x-axis points towards the geographic North Pole, the y-axis points towards the geographic East Pole, and the z-axis points vertically downwards.

[0055] Specifically, such as Figure 2 As shown, the system coordinate system (superscript: ) S ): Fix it at the system's center of gravity, i.e., on the armored cable of the unmanned surface vessel. Define the coordinate system. Perpendicular to the armored cable, and the arrow points in the direction of the system's forward velocity. Definition From the origin O of the system coordinate system S Pointing towards the glider along the armored cable, and in the system coordinate system The right-hand rule is satisfied.

[0056] Earth-fixed coordinate system (superscript in the upper right corner) N The location of the unmanned surface vessel can be well represented using a northeast-oriented coordinate system, where... Pointing due north, Pointing due east, and Vertically downwards.

[0057] S12: Establish a dynamic model by combining position and velocity vectors:

[0058]

[0059] in, Represents the rigid mass matrix. Indicates and The relevant inertial hydrodynamic matrix, Indicates and The relevant Coriolis centripetal force coefficient matrix, Indicates and The relevant hydrodynamic Coriolis centripetal force matrix, Indicates and The relevant damping force matrix, Indicates and The relevant restoring force matrix, Let R represent the active control force matrix, and let R represent the real number field. This represents a real matrix with six rows and six columns. This represents a real matrix with six rows and one column. This represents the disturbance vector.

[0060] Specifically, the process of establishing a dynamic model for an unmanned surface vessel (USV) involves determining its position and velocity vectors using the Newton-Euler equations, and then describing its motion behavior by combining the USV's inertia, external forces (such as ocean currents and wind), and internal forces (such as propulsion). By introducing mechanical parameters such as the rigid mass matrix, Coriolis force matrix, damping force matrix, and restoring force matrix, the model can comprehensively consider the USV's dynamic response in complex environments. This model provides a precise theoretical basis for control strategies, enabling the control system to better adapt to external disturbances, improve path tracking accuracy, and enhance the system's robustness and stability under different sea conditions.

[0061] S2: Combining the dynamic model, establish the path tracking error equation in the Serret-Frenet coordinate system to describe the systematic error of the unmanned surface vessel relative to the desired path.

[0062] The Serret-Frenet coordinate system is used to describe the coordinate system of points on a curve that are tangent to the curve. It defines a local coordinate system where the x-axis is along the tangent direction of the curve; the y-axis is perpendicular to the tangent and points in the direction of the curve's normal; and the z-axis is perpendicular to the plane and is usually used to represent the curve's normal. The desired path refers to the ideal navigation route that the unmanned surface vessel (USV) needs to follow. This path is pre-defined, usually planned according to mission requirements or target location. The path tracking error equation is used to measure the deviation between the USV's actual path and the desired path, typically including lateral error (representing the vertical deviation of the vessel from the path) and heading error (representing the deviation between the vessel's actual heading and the desired heading).

[0063] It should be noted that by establishing a path tracking error equation in the Serret-Frenet coordinate system, the deviation between the actual motion of the unmanned surface vessel and the desired path can be effectively quantified. This method can accurately describe the changes in error, helping to design more precise control strategies and thus achieve higher-precision path tracking. Especially in complex environments, it can effectively reduce error accumulation and improve system stability.

[0064] In one possible implementation, the systematic error includes lateral error and heading error.

[0065] In this context, lateral error refers to the deviation along the path, while heading error is the deviation of the heading angle from the desired direction. Dividing system errors into lateral and heading errors allows for precise quantification of the deviations made by the unmanned surface vessel (USV) during path tracking. Lateral error directly reflects the vertical deviation of the vessel from the predetermined path, while heading error reveals the deviation between the vessel's heading and the target direction. This segmentation facilitates the design of more precise control strategies, enabling separate adjustments to the vessel's lateral position and heading angle, ensuring more accurate path tracking, and enhancing the system's stability and robustness.

[0066] In one possible implementation, the path tracking error equation is specifically as follows:

[0067]

[0068]

[0069]

[0070] in, Indicates the speed of the unmanned surface vessel. Indicates the yaw angle of an unmanned surface vessel. Indicates lateral error. express The first derivative, Indicates heading error The first derivative, Indicates the yaw angle error of the unmanned surface vessel. The first derivative, This represents the lateral velocity of the unmanned surface vessel in the Serret-Frenet coordinate system. This represents the yaw rate at reference point p. This represents the longitudinal error at reference point p. Indicates yaw angle error The cosine value, Indicates yaw angle error The sine value, This represents the yaw angle at reference point p.

[0071] It should be noted that in this path tracking error equation, lateral error measures the degree of deviation between the unmanned surface vessel (USV) and the desired path. Heading error represents the difference between the USV's actual heading and its desired heading. By explicitly distinguishing between lateral and heading errors, the control system can more precisely adjust the USV's motion, optimizing both position and heading control separately. This approach makes the path tracking process more nuanced and flexible, improving control accuracy in complex environments, reducing error accumulation, and thus enhancing system stability and robustness.

[0072] S3: Construct a path tracking controller based on a linear active disturbance rejection controller to estimate and compensate for external disturbances of the unmanned surface vessel and output the control signal of the unmanned surface vessel.

[0073] Among them, the Linear Active Disturbance Rejection Controller (LADRC) is a method based on the Extended State Observer (ESO) for real-time estimation and compensation of external and internal disturbances in a system. It improves the stability and robustness of the system by observing and compensating for disturbances. Compared to traditional controllers, LADRC does not rely on precise mathematical models and has stronger anti-interference capabilities. The path tracking controller is used to guide an unmanned surface vessel (USV) along a predetermined path. It adjusts the USV's heading and speed based on the path tracking error equation to ensure the vessel accurately follows the desired path. External disturbances refer to external factors affecting the motion of the USV, such as ocean currents, wind, and waves. These disturbances can cause the vessel's heading and position to deviate from the desired trajectory, affecting the accuracy of path tracking. The USV control signal is generated by the controller and uses actuators such as servos and propulsion systems to adjust the USV's heading and speed, guiding it towards the desired path.

[0074] It should be noted that by combining a linear active disturbance rejection controller, the influence of external disturbances such as ocean currents and waves on the unmanned surface vessel can be estimated and compensated in real time, significantly improving control accuracy. It not only effectively addresses uncertainties in dynamic environments but also ensures system stability, thereby achieving more precise path tracking.

[0075] In one possible implementation, the control law of the path tracking controller is specifically as follows:

[0076]

[0077]

[0078]

[0079]

[0080]

[0081]

[0082] in, This represents the control compensation signal for the unmanned surface vessel output by the path tracking controller at time k in response to external disturbances. This represents the control signal of the unmanned surface vessel output by the path tracking controller at time k. This represents the observer bandwidth assumption. Indicates the undamped natural frequency. and These represent the first feedback control gain and the second feedback control gain, respectively. , and These represent the gains of the first observer, the second observer, and the third observer, respectively. Indicates the heading at time k The estimate, This represents an estimate of the differential of the heading at time k. This represents an estimate of the total external disturbance at time k. This represents the error signal at time k of the path tracking controller. This represents the first-order error of the path tracking controller at time k. This represents the k-time bipolar error of the path tracking controller. This represents the first-level virtual control quantity of the path tracking controller at time k. This represents the second-level virtual control quantity of the path tracking controller at time k. This represents the estimated impact of external disturbances.

[0083] It should be noted that the control law of this path-tracking controller effectively addresses the impact of external disturbances by introducing multiple feedback gains and dynamic adjustment mechanisms. Through the optimization of control compensation signals and control signals, the control system can estimate heading error, heading derivative, and external disturbances in real time, thereby adjusting the controller parameters more accurately. Utilizing observer gain and feedback gain to adjust the controller effectively enhances the robustness of the control system. Especially when facing environmental changes and complex disturbances, the system can maintain high-precision path tracking, improving control stability and adaptability.

[0084] S4: Input the system error and the control signal of the unmanned surface vessel into the fuzzy RBF neural network, and output the optimized control parameters of the path tracking controller with the goal of minimizing the system error.

[0085] Among them, the fuzzy RBF neural network is a hybrid network combining fuzzy logic and radial basis function (RBF) neural networks. It first uses a fuzzification layer to transform input data (such as system errors and control signals) into fuzzy sets, and then processes these fuzzy inputs through the RBF neural network to output control parameters. The RBF network, through radial basis function mapping, can effectively extract features from the input space and perform optimization. In path tracking control, the fuzzy RBF neural network can dynamically optimize controller parameters according to the objective of minimizing system errors, adapting to environmental changes and disturbances.

[0086] It should be noted that by inputting system errors and control signals into a fuzzy RBF neural network, the parameters of the path tracking controller can be adaptively optimized. This process allows the controller to be adjusted in real time to minimize errors, thereby improving the system's accuracy and robustness. The introduction of the fuzzy RBF neural network enables the controller to respond better in complex and dynamic environments and optimize control performance, especially when facing nonlinear disturbances.

[0087] In one possible implementation, the optimized control parameters include the observer bandwidth assumption, the estimated external disturbance effect, the first feedback control gain, and the second feedback control gain.

[0088] It should be noted that by optimizing control parameters, including observer bandwidth, external disturbance estimates, and feedback control gain, the control system can be dynamically adjusted to more accurately respond to external disturbances and optimize path tracking accuracy. This enhances the system's adaptability and robustness, ensuring stable operation in complex environments.

[0089] In one possible implementation, the fuzzy RBF neural network includes an input layer, a fuzzification layer, a fuzzy inference layer, and an output layer connected in sequence, with the fuzzification layer connected to the output layer.

[0090] S4 specifically includes:

[0091] S41: Using system errors and unmanned surface vessel control signals as input data for the input layer, the activation function of the input layer is:

[0092]

[0093] Where x represents the input data, This represents the output data when the input data in the input layer is x.

[0094] S42: The input data is fuzzified using a fuzzification layer to calculate the fuzzy quantities of the system error and the control signal of the unmanned surface vessel, which belong to different fuzzy sets respectively.

[0095]

[0096] Wherein, variables i=1,2 represent input data labels, i=1 indicates that the input data is a system error, and i=2 indicates that the input data is a control signal for an unmanned surface vessel. Variables j=1,2,3,4,5,6 represent fuzzy set labels. The natural exponential function represents the output data of the input layer when the input data is i. Let represent the mean difference of the membership function of the j-th fuzzy set of the i-th input variable of the Gaussian function. Let represent the standard deviation of the membership function of the j-th fuzzy set of the i-th input variable of the Gaussian function. This represents the fuzzy quantity indicating that the i-th input data output by the fuzzification layer belongs to the j-th fuzzy set.

[0097] S43: Multiply the fuzzy values ​​corresponding to different fuzzy sets for each input data pairwise to obtain the output data of the fuzzy inference layer:

[0098]

[0099] in, This represents the output data of the fuzzy inference layer. express N represents the total number of input variables. Represents the total number of fuzzy sets. This represents the product of the membership degrees of each input variable in the i-th rule. This represents the product of the number of fuzzy subsets of all input variables.

[0100] S44: Input the output data of the fuzzy inference layer to the output layer to obtain the initial optimization control parameters:

[0101]

[0102]

[0103]

[0104]

[0105] in, , , and These represent the observer bandwidth assumption, the estimated external disturbance effect, the first feedback control gain, and the second feedback control gain, respectively. , , and The initial optimized control parameters are formed. Represents the connection weight matrix. This represents the weighted connection from the first output layer to the j-th node. This represents the weighted connection from the second output layer to the j-th node. This represents the weighted connection from the 3rd output layer to the j-th node. This represents the weighted connection from the 4th output layer to the j-th node.

[0106] Optionally, the connection weight matrix is ​​a 36-row, 4-column connection weight matrix.

[0107] S45: Optimize the connection weight matrix:

[0108]

[0109]

[0110]

[0111] in, This represents the learning momentum factor. Indicates the number of iterations. Indicates the learning rate, This represents the ideal output of the output layer in the k-th iteration. This represents the actual output of the output layer in the k-th iteration. This indicates finding the partial derivative. Represents a performance metric function. This represents the weight value of the j-th connection in the k-th iteration. This represents the j-th weight in the (k-1)-th iteration. This represents the increment of the weight in the k-th iteration. This represents the j-th weight value in the (k-2)-th iteration. This represents a portion of the partial derivative of the output layer with respect to the input. Indicates the actual output. Indicates input variables, This represents the center of the j-th node. This represents the output of the j-th neuron in the 4th layer. This represents the connection weight of the j-th node.

[0112] S46: If the performance index function value is less than the preset performance index value, the initial optimization control parameter is output as the optimization control parameter; otherwise, the hyperparameters of the fuzzy RBF neural network are updated, and the process returns to step S44. The hyperparameters include the learning momentum factor and the learning rate.

[0113] Specifically, this process utilizes a fuzzy RBF neural network to optimize the parameters of the path tracking controller. First, system errors and control signals are input to the input layer, then transformed into fuzzy sets by a fuzzification layer, calculating the membership degree of each input data point. Next, the fuzzy inference layer outputs data based on the interactions of the fuzzy sets and passes it to the output layer to calculate preliminary optimized control parameters, such as observer bandwidth, external disturbance estimates, and feedback gain. Then, by optimizing the connection weight matrix, the neural network continuously adjusts these control parameters, enabling the system to adaptively improve path tracking accuracy and stability under different environments. The advantages lie in its ability to handle dynamic changes and complex disturbances, enhancing the flexibility and robustness of the control system. Furthermore, through optimization iteration and hyperparameter adjustment, the system maintains high efficiency and low error during actual operation.

[0114] It should be noted that those skilled in the art can set the value of the preset energy function index according to actual needs, and this invention does not limit this.

[0115] S5: Update the path tracking controller based on optimized control parameters.

[0116] Understandably, the path tracking controller is updated based on the control parameters optimized by the fuzzy RBF neural network. This allows the controller to adjust its parameters in real time to adapt to environmental changes or new dynamic conditions, ensuring that the unmanned surface vessel always performs path tracking in the optimal state.

[0117] S6: Re-estimate external disturbances using the updated path tracking controller and output optimized control signals for unmanned surface vessels.

[0118] It should be noted that by re-estimating external disturbances using the updated path-tracking controller, the control system is able to self-adjust under new environmental conditions. Re-estimating disturbances helps improve control accuracy, ensuring the system can accurately respond to dynamic changes, such as variations in ocean currents or wind, and thus output optimized control signals. This adjustment process enhances the system's robustness, ensuring that the unmanned surface vessel maintains stable path-tracking capabilities in complex environments.

[0119] S7: Use optimized surface unmanned surface vessel control signals to control the surface unmanned surface vessel to travel along the desired path.

[0120] In practical applications, firstly, a dynamic model of the unmanned surface vessel (USV) is established to provide a theoretical foundation for subsequent control. Then, a path tracking error equation is established in the Serret-Frenet coordinate system to accurately quantify the deviation between the vessel and the desired path. Next, a linear active disturbance rejection controller (LADRC) is used to estimate and compensate for external disturbances in real time, ensuring the vessel can cope with dynamic changes such as ocean currents and waves. The control parameters are further optimized using a fuzzy RBF neural network, and the controller is adjusted in real time to reduce errors and improve control accuracy and stability. The advantage of this method is that it can effectively cope with nonlinear disturbances in complex environments, optimize control performance, and ensure that the USV navigates stably and accurately along the desired path under different conditions.

[0121] like Figure 3 The diagram shown is a structural schematic of a path-tracking unmanned surface vessel control system provided in an embodiment of the present invention.

[0122] This invention provides a path-tracking unmanned surface vessel control system 20, comprising: a processor 201 and a memory 202;

[0123] The memory 202 stores programs or instructions that can run on the processor 201. When the program or instructions are executed by the processor 201, they implement the steps of the above-described path-tracking unmanned surface vessel control method and achieve the same technical effect. To avoid repetition, the present invention will not elaborate further.

[0124] It should be understood that the processor 201 in this embodiment of the invention may be a central processing unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0125] It should also be understood that the memory 202 in the embodiments of the present invention can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of random access memory are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus RAM (DR RAM).

[0126] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0127] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1A device that provides the functions specified in one or more boxes.

[0128] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0129] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0130] The above specific embodiments are used to explain and illustrate the present invention, but not to limit the present invention. Any modifications and changes made to the present invention within the spirit and scope of the claims shall fall within the protection scope of the present invention.

Claims

1. A method for controlling an unmanned surface vessel under path tracking, characterized in that, Includes the following steps: Constructing a dynamic model of an unmanned surface vessel: ， in, Represents the rigid mass matrix. Indicates and The relevant inertial hydrodynamic matrix, Indicates and The relevant Coriolis centripetal force coefficient matrix, Indicates and The relevant hydrodynamic Coriolis centripetal force matrix, Indicates and The relevant damping force matrix, Indicates and The relevant restoring force matrix, Let R represent the active control force matrix, and let R represent the real number field. This represents a real matrix with six rows and six columns. This represents a real matrix with six rows and one column. Indicates the disturbance force vector; Based on the aforementioned dynamic model, a path tracking error equation is established in the Serret-Frenet coordinate system. This equation is used to quantify the systematic error between the actual navigation state and the desired path of the unmanned surface vessel. Specifically, the path tracking error equation is as follows: ， ， ， in, Indicates the speed of the unmanned surface vessel. Indicates the yaw angle of an unmanned surface vessel. Indicates lateral error. express The first derivative, Indicates heading error The first derivative, Indicates the yaw angle error of the unmanned surface vessel. The first derivative, This represents the lateral velocity of the unmanned surface vessel in the Serret-Frenet coordinate system. This represents the yaw rate at reference point p. This represents the longitudinal error at reference point p. Indicates yaw angle error The cosine value, Indicates yaw angle error The sine value, This represents the yaw angle at reference point p; A path tracking controller based on a linear active disturbance rejection controller is constructed. The path tracking controller estimates and compensates for the external disturbances faced by the unmanned surface vessel and outputs the initial control signal of the unmanned surface vessel. The system error and the initial unmanned surface vessel control signal are input into a fuzzy RBF neural network to minimize the system error and output the optimized control parameters of the path tracking controller. The path tracking controller is updated according to the optimized control parameters. The external disturbance is re-estimated using the updated path tracking controller, and an optimized surface unmanned vessel control signal is output. Based on the optimized surface unmanned vessel control signal, the surface unmanned vessel is controlled to travel along the desired path.

2. The path-tracking-based unmanned surface vessel control method according to claim 1, characterized in that, The specific steps for constructing the dynamic model of the unmanned surface vessel include: Based on the Newton-Euler equations, the position and velocity vectors of the unmanned surface vessel in the preset coordinate system are determined, and then the dynamic model is constructed by combining the position and velocity vectors.

3. The path-tracking unmanned surface vessel control method according to claim 2, characterized in that, The preset coordinate system includes the system coordinate system and the Earth-fixed coordinate system; The origin of the system coordinate system is the center of the unmanned surface vessel. The x-axis points in the direction of the unmanned surface vessel's movement, the y-axis is perpendicular to the x-axis and points to the starboard side of the unmanned surface vessel, and the z-axis is determined based on the x-axis and y-axis using the right-hand rule. The origin of the Earth-fixed coordinate system is the Earth's center of mass, the x-axis points towards the geographic North Pole, the y-axis points towards the geographic East Pole, and the z-axis points vertically downwards.

4. The path-tracking-based unmanned surface vessel control method according to claim 1, characterized in that, The system error includes lateral error and heading error; the lateral error is the vertical offset between the unmanned surface vessel and the desired path; the heading error is the angular deviation between the actual heading of the unmanned surface vessel and the heading corresponding to the desired path.

5. The path-tracking-based unmanned surface vessel control method according to claim 1, characterized in that, The path tracking controller introduces multiple feedback control gains and multiple observer gains. The observer gains are used to estimate the current heading, heading rate of change, and total external disturbance of the unmanned surface vessel in real time. The control parameters are adjusted in combination with the feedback control gains to compensate for the external disturbance.

6. The method for controlling unmanned surface vessels under path tracking according to claim 1, characterized in that, The fuzzy RBF neural network includes an input layer, a fuzzification layer, a fuzzy inference layer, and an output layer connected in sequence, with the fuzzification layer and the output layer being directly connected.

7. The path-tracking unmanned surface vessel control method according to claim 6, characterized in that, The input layer receives system errors and initial unmanned surface vessel control signals, and transmits the input data using a linear activation function; The fuzzification layer performs fuzzification processing on the input data and calculates the fuzzy quantities of the system error and the initial unmanned surface vessel control signal, which belong to different fuzzy sets respectively. The fuzzy inference layer performs pairwise multiplication of the fuzzy quantities of different fuzzy sets corresponding to each input data, and outputs the inference result. The output layer receives the inference results output by the fuzzy inference layer and calculates the initial optimization control parameters based on the preset connection weight matrix.

8. The path-tracking unmanned surface vessel control method according to claim 7, characterized in that, The fuzzy RBF neural network optimizes the connection weight matrix by introducing a learning momentum factor and a learning rate. It calculates a performance index function based on the deviation between the ideal output and the actual output of the output layer at the current iteration number. When the value of the performance index function is less than a preset threshold, the initial optimization control parameters are output as the final optimization control parameters. If the threshold is not met, the learning momentum factor and learning rate are updated, the initial optimization control parameters are recalculated, and the optimization process is repeated.

9. The path-tracking unmanned surface vessel control method according to claim 8, characterized in that, The optimized control parameters include the observer bandwidth assumption, the estimated value of the external disturbance effect, and the feedback control gain.

10. A path-tracking unmanned surface vessel control system, characterized in that, include: One or more processors; Memory, used to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the path tracking control method for unmanned surface vessels as described in any one of claims 1 to 9.

Images