An unmanned ship adaptive path tracking control method, device, equipment and medium

Abstract

The present invention discloses an unmanned ship adaptive path tracking control method, device, equipment and medium. The method comprises: establishing a dynamic model of an unmanned ship without parameter requirements, determining dynamic characteristics according to a simplified dynamic model of the directional force of the propeller of the unmanned ship, wherein the dynamic characteristics include unmodeled dynamic characteristics; fitting dynamic characteristics to the unmodeled dynamic characteristics through an RBF neural network; determining an integral sliding surface by using a preset construction method to determine the integral sliding surface by using a swell velocity error and a bow roll angle error; adaptively calculating the integral sliding surface to determine an adaptive rate, adaptively updating the fitted dynamic characteristics according to the adaptive rate, and obtaining real-time fitted dynamic characteristics; determining a real-time target thrust according to real-time swell and bow roll direction speeds and real-time fitted dynamic characteristics, and controlling the propeller motor according to the target thrust. The problem of being unable to effectively track and control the adaptive path of an unmanned ship can be solved by implementing the method of the present invention.

Description

Technical Field

[0001] The present invention relates to the technical field of neural networks and adaptive control, and in particular to an unmanned ship adaptive path tracking control method, device, equipment and medium. Background Art

[0002] With the continuous development of intelligent technology, unmanned ships are gradually being applied to multiple fields, such as marine science research, business, and tourism. Therefore, the motion control of unmanned ships has gradually received attention, especially the trajectory tracking control technology of unmanned ships. However, in the prior art, the existing models for unmanned ship trajectory control have poor versatility and cannot be applied to all unmanned ship systems. In addition, in the process of unmanned ship trajectory tracking, due to excessive focus on reducing steady-state errors, the speed response in the trajectory tracking process is ignored, making it impossible to efficiently and safely track and control the adaptive path of unmanned ships in the prior art. Summary of the invention

[0003] The embodiments of the present invention provide an unmanned ship adaptive path tracking control method, device, equipment and medium, aiming to solve the problem in the prior art that the unmanned ship adaptive path tracking control cannot be performed efficiently and safely.

[0004] In the first aspect, an embodiment of the present invention provides an adaptive path tracking control method for an unmanned ship, which includes: establishing a dynamic model of an unmanned ship without parameter requirements, simplifying the dynamic model according to the directional force of the propeller of the unmanned ship to determine the dynamic characteristics, wherein the dynamic characteristics include unmodeled dynamic characteristics; fitting the unmodeled dynamic characteristics through an RBF neural network to determine the fitted dynamic characteristics; determining the integral sliding surface of the longitudinal swell speed error and the bow roll angle error through a preset construction method; adaptively calculating the integral sliding surface to determine the adaptive rate, and adaptively updating the fitted dynamic characteristics according to the adaptive rate to obtain real-time fitted dynamic characteristics; determining a real-time target thrust according to the real-time longitudinal swell and bow roll directional speeds and the real-time fitted dynamic characteristics, and controlling the motor of the propeller according to the target thrust.

[0005] In the second aspect, an embodiment of the present invention also provides an unmanned ship adaptive path tracking control device, which includes: an establishment unit, used to establish a dynamic model of an unmanned ship without parameter requirements, and simplify the dynamic model according to the directional force of the propeller of the unmanned ship to determine the dynamic characteristics, wherein the dynamic characteristics include unmodeled dynamic characteristics; a fitting unit, used to fit the unmodeled dynamic characteristics through an RBF neural network to determine the fitted dynamic characteristics; a construction unit, used to determine the integral sliding surface of the longitudinal swell speed error and the bow roll angle error through a preset construction method; an updating unit, used to adaptively calculate the integral sliding surface to determine the adaptive rate, and adaptively update the fitted dynamic characteristics according to the adaptive rate to obtain real-time fitted dynamic characteristics; a control unit, used to determine the real-time target thrust according to the real-time longitudinal swell and bow roll direction speed and the real-time fitted dynamic characteristics, and control the motor of the propeller according to the target thrust.

[0006] In a third aspect, an embodiment of the present invention further provides a computer device, which includes a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the above method when executing the computer program.

[0007] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the storage medium stores a computer program, wherein the computer program includes program instructions, and the program instructions can implement the above method when executed by a processor.

[0008] The embodiment of the present invention provides an unmanned ship adaptive path tracking control method, device, equipment and medium. The method includes: establishing a dynamic model of an unmanned ship without parameter requirements, simplifying the dynamic model according to the directional force of the propeller of the unmanned ship to determine the dynamic characteristics, wherein the dynamic characteristics include unmodeled dynamic characteristics; fitting the unmodeled dynamic characteristics through RBF neural network to determine the fitted dynamic characteristics; determining the integral sliding surface by the preset construction method for the swell speed error and the bow angle error; adaptively calculating the integral sliding surface to determine the adaptive rate, and adaptively updating the fitted dynamic characteristics according to the adaptive rate to obtain the real-time fitted dynamic characteristics; determining the real-time target thrust according to the real-time swell and bow direction speed and the real-time fitted dynamic characteristics, and controlling the motor of the propeller according to the target thrust. The embodiment of the present invention fits the unmodeled dynamic characteristics through RBF neural network, solves the problem of difficulty in establishing the unmanned ship model and designing control parameters, updates the fitted dynamic characteristics and unknown interference data through the adaptive rate, reduces the control system parameter design amount and improves the robustness of the unmanned ship in the unknown environment, so as to improve the safety of the unmanned ship adaptive path tracking control. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying any creative work.

[0010] Figure 1 A schematic diagram of a flow chart of an adaptive path tracking control method for an unmanned ship provided by an embodiment of the present invention;

[0011] Figure 2 A schematic diagram of a sub-process of an adaptive path tracking control method for an unmanned ship provided by an embodiment of the present invention;

[0012] Figure 3 A schematic diagram of a sub-process of an adaptive path tracking control method for an unmanned ship provided by an embodiment of the present invention;

[0013] Figure 4 A schematic diagram of a sub-process of an adaptive path tracking control method for an unmanned ship provided by an embodiment of the present invention;

[0014] Figure 5 A schematic diagram of a sub-process of an adaptive path tracking control method for an unmanned ship provided by an embodiment of the present invention;

[0015] Figure 6 A schematic block diagram of an adaptive path tracking control device for an unmanned ship provided by an embodiment of the present invention;

[0016] Figure 7 A schematic block diagram of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0019] It should also be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0020] It should be further understood that the term "and / or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0021] See also Figure 1 , Figure 1 A flow chart of an unmanned ship adaptive path tracking control method provided by an embodiment of the present invention. The unmanned ship adaptive path tracking control method in this embodiment can be applied to the adaptive control of unmanned ships, especially unmanned ships with dual fixed thrusters and equipped with multiple sensors, where the sensors detect information such as swaying speed, and the unmanned ship power model processes the information to determine the required thrust to control the operation of the thrusters, so as to improve the robustness of the unmanned ship in the unknown environment and the safety of the unmanned ship adaptive path tracking control.

[0022] Figure 1 1 is a flow chart of an unmanned ship adaptive path tracking control method provided by an embodiment of the present invention. As shown in the figure, the method includes the following steps S110-S150.

[0023] S110, establishing a dynamic model of an unmanned ship without parameter requirements, simplifying the dynamic model according to the directional force of the propeller of the unmanned ship to determine dynamic characteristics, wherein the dynamic characteristics include unmodeled dynamic characteristics.

[0024] In this embodiment, the dynamic model is a model for analyzing dynamics, which can help understand and predict the behavior of unmanned ships. The dynamic characteristic is the resistance generated according to the running speed of the unmanned ship. For example, the longitudinal resistance is 500N when the ship speed is 1m / s. At this time, the propeller needs to generate a force greater than 500N to accelerate the ship forward. And this 500N longitudinal resistance is the dynamic characteristic. The parameter-free requirement is that there is no limitation and definition on the parameters in the dynamic model. The dynamic model is: , where M is the mass matrix, , C is the inertia matrix, , D is the resistance matrix, in, is the velocity in the swell and pitch directions. u and r are the velocities in the swell and pitch directions, respectively. is the target thrust, and the other parameters are unknown parameters. In this embodiment, a dual fixed propeller is taken as an example. Since the dual fixed propeller has no swaying force, the dynamic characteristics of the unmanned ship can be obtained by simplification. Specifically, the dynamic characteristics are: in, are the target force in the swell direction and the target thrust in the yaw direction, u and r are the speed in the swell direction and the yaw direction, respectively. The unknown interference data, and are the unmodeled dynamic characteristics in the swell direction and the bow roll direction, respectively. The other parameters are defined in the same way as the above parameters and will not be repeated here. The unmodeled dynamic characteristics are: Among them, the are the unmodeled dynamic characteristics in the sway direction and the bow roll direction, respectively. The remaining parameters are the same as the above parameters, which are all unknown parameters. By simplifying the unmanned ship model to obtain the unmodeled dynamic characteristics, the construction and calculation of parameters are reduced, which facilitates the fitting of unknown parameters.

[0025] S120, fitting the unmodeled dynamic characteristics through an RBF neural network to determine fitted dynamic characteristics.

[0026] In this embodiment, the RBF network (Radial Basis Function Network) is an artificial neural network, and the unmodeled dynamic characteristics are fitted by the RBF network to determine the fitted dynamic characteristics. Specifically, the RBF neural network is: in, is the preset weight vector, for

[0027] Compensation error, are Gaussian radial basis vectors, is the fitting dynamic characteristic. are Gaussian radial basis vectors and 。 Specifically, in this embodiment, ,initial The unmodeled kinetic characteristics are fitted by a neural network to determine the fitted kinetic characteristics, which facilitates data processing and avoids the complex steps of processing each parameter.

[0028] S130, determining an integral sliding surface by using a preset construction method based on the surge velocity error and the yaw angle error.

[0029] In this embodiment, the surge speed error is the error between the preset surge speed and the real-time surge speed, and the yaw angle error is the error between the preset yaw angle and the real-time yaw. The surge speed error and the yaw angle error are used to determine the integral sliding surface through a preset construction method. Specifically, the preset construction method is: in, is the integral sliding surface, are the yaw angle error and the swell speed error, where are the design coefficients of the sliding surface. Specifically, the specific parameters in this embodiment are Among them, it can be understood that since the swell speed error and the bow roll angle error are updated in real time, the integral sliding surface is also updated in real time. By confirming the integral sliding surface, the trajectory tracking steady-state error can be reduced and the robustness of the unmanned ship in an unknown propeller attenuation environment can be improved.

[0030] In one embodiment, if Figure 2 As shown, the step S130 also includes steps S1301-S1303 before the step S130.

[0031] S1301, performing deviation calculation based on the preset tangential angle queue and the preview point coordinates to determine the lateral angle deviation;

[0032] S1302, determining a yaw angle queue by calculating a preset yaw angle according to the preset tangential angle queue and the lateral angle deviation;

[0033] S1303: Determine a heading angle error by calculating a first difference between the lateral angle deviation and the heading angle, wherein the heading angle is a heading angle in the heading angle queue at the same time as the lateral angle deviation.

[0034] In this embodiment, the tangent angle is the angle between the tangent direction of a certain point on the curve and the reference direction, which is called the tangent azimuth. For example, in the plane coordinate system, the positive direction of the y-axis is used as the reference direction, and the angle between the tangent direction of a certain point on the curve and the positive direction of the y-axis is the tangent azimuth. Through the control terminal, the calibrated route starts at the middle point to generate the planned path information, wherein the planned path information includes the longitude and latitude queue of the reference trajectory of the unmanned ship. According to the trajectory characteristics (such as the turning radius), the longitudinal speed queue and the tangent angle queue of the unmanned ship can be calculated. The current longitude and latitude information of the unmanned ship and the longitude and latitude information of the path point are obtained through GPS to determine the preview point. The lateral angle deviation is determined by performing deviation calculation based on the preset tangent angle queue and the preview point coordinates. Specifically, the current coordinate point of the current ship is obtained as the reference point, and the corresponding tangent angle of the reference point in the preset tangent angle queue is determined, and the coordinates of the north-east coordinate system point corresponding to the preview point are obtained. , calculate the lateral error distance and longitudinal error distance of the preview point relative to the reference point, and determine the lateral angle deviation according to the lateral error distance and the longitudinal error distance. The specific calculation method is: , , Among them, the are the lateral error distance, the longitudinal error distance and the lateral angle deviation respectively. is the north-east coordinate corresponding to the preview point, The tangential angle corresponding to the reference point in the preset tangential angle queue is determined by calculating the preset tangential angle queue and the lateral angle deviation through the preset yaw angle. Specifically, the unmanned ship yaw angle queue ,in and is the fusion reference coefficient of the heading angle. is the tangent angle of the current coordinate in the preset tangent angle queue, is the lateral angle deviation, is the bowing angle in the bowing angle queue. The real-time bowing angle r of the unmanned ship is obtained through the built-in GPS and IMU sensors of the unmanned ship, and the real-time bowing angle error of the unmanned ship is calculated. Specifically, Among them, the is the heading angle error, r is the heading angle obtained in real time, The bow angle of the bow angle queue at the same time. By determining the bow angle error through the first difference calculation based on the lateral angle deviation and the bow angle, an accurate real-time error can be obtained to improve the stability of the unmanned ship during navigation.

[0035] In addition, this embodiment also includes a method for obtaining the swell speed error. The real-time swell speed of the unmanned ship is obtained by the built-in GPS and IMU sensors of the unmanned ship, wherein the swell refers to the horizontal linear oscillation movement of an object immersed in water along the longest extension direction. The swell speed error can be determined by calculation based on the swell speed queue obtained above and the real-time swell speed. Specifically, the calculation method is: in, is the surge velocity error, is the real-time swing speed, is the swell speed in the swell speed queue at the same time. By determining the swell speed error and the bow angle error, the integral sliding film surface can be constructed, and the tracking control of the unmanned ship according to the path can be realized.

[0036] In one embodiment, if Figure 3 As shown, the step S130 also includes steps S1304-S1306 before the step S130.

[0037] S1304, constructing a first adaptive rate by using a preset adaptive model based on the error between the ideal output of the thruster and the preset output threshold;

[0038] S1305, determining an error adaptation rate through a second difference calculation according to the first adaptation rate, the yaw angle error, and the sway speed error;

[0039] S1306. Update the yaw angle error and the surge speed error in real time according to the error adaptation rate.

[0040] In this embodiment, the ideal output of the propeller is the preset output value of the propeller, and the preset output threshold is the preset maximum output value of the propeller. Specifically, the propeller saturation phenomenon can be described as: in, is the ideal output of the thruster, is a preset output threshold of the propeller, and a first adaptive rate is constructed by a preset adaptive model. Specifically, in, is a normal number, is the error between the ideal thruster output and the actual thruster output. The error adaptation rate is determined by calculating the second difference according to the first adaptation rate, the yaw angle error and the sway speed error. Specifically, , , are the error adaptation rates of the swell speed and the bow pitch angle, are respectively the adaptation rates of the swell and yaw direction forces in the first adaptation, and the other parameters have the same meanings as in the above content and are not repeated here. The yaw angle error and the swell speed error are updated in real time according to the error adaptation rate. By updating the yaw angle error and the swell speed error in real time, the robustness of the unmanned ship sailing in an unknown environment can be improved.

[0041] S140, performing adaptive calculation on the integral sliding surface to determine an adaptive rate, and adaptively updating the fitted dynamic characteristics according to the adaptive rate to obtain real-time fitted dynamic characteristics.

[0042] In this embodiment, the integral sliding surface is a kind of system that is set to the sliding surface from the beginning by reasonably setting the initial state of the integrator, thereby eliminating the arrival section and improving the robustness of the control system. The integral sliding surface is adaptively calculated to determine the adaptive rate. For example, the adaptive rate of the interference data in the fitted dynamic characteristics can be determined based on the adaptive calculation and the integral sliding surface, and the interference data of the fitted dynamic characteristics can be updated in real time according to the adaptive rate to update the fitted dynamic characteristics in real time. By updating the fitted dynamic characteristics in real time, the thrust required by the unmanned ship in real time can be obtained, thereby improving the stability of the unmanned ship in sailing in an unknown environment.

[0043] In one embodiment, if Figure 4 As shown, the step S140 also includes steps S141-S142.

[0044] S141, determining the weight adaptation rate by multiplying the integral sliding surface and the Gaussian radial basis function;

[0045] S142: Update the preset weight vector in real time according to the weight adaptation rate.

[0046] In this embodiment, the fitted dynamic characteristics include a preset weight vector, the adaptive rate includes a weight adaptive rate, and the adaptive rate is determined by adaptively calculating the integral sliding surface. The Gaussian radial basis function is also called a Gaussian function, which is a mathematical function commonly used in machine learning, number analysis, signal processing and other fields. The weight adaptive rate is determined by multiplying the integral sliding surface with the Gaussian radial basis function, specifically, ,in is a real-time Gaussian radial basis function, is the integral sliding surface, is the weight adaptation rate. The preset weight vector is updated in real time according to the weight adaptation rate. Specifically, when the weight adaptation rate is updated, the value of the weight vector is updated accordingly. The weight adaptation rate is determined by multiplying the integral sliding surface with the Gaussian radial basis function so that the preset weight vector included in the fitted dynamic characteristics can be updated at any time, which is convenient for controlling the stability of the unmanned ship during operation.

[0047] In one embodiment, if Figure 5 As shown, step S140 also includes steps S143-S144.

[0048] S143, determining the interference data adaptation rate by absolute value calculation of the integral sliding surface;

[0049] S144. Update the unknown interference data in real time according to a preset adaptive relationship and the interference data adaptive rate.

[0050] In this embodiment, the fitted dynamic characteristics include unknown interference data, and the adaptive rate includes the adaptive rate of interference data, wherein it should be noted that the adaptive rate of the unknown interference data is the same as the adaptive rate of the compensation error. The adaptive rate of interference data is determined by calculating the absolute value of the integral sliding surface, according to (The parameter definitions of the two formulas are the same as those above and will not be repeated here). By deriving the data, it can be known that the compensation error Equal to the integral sliding surface The absolute value of , that is, the interference data adaptation rate Therefore, when the interference data adaptive rate is updated, the unknown interference data and the compensation error can also be updated. The external interference and the compensation error are updated by the interference data adaptive rate, so that the unmanned ship is more stable during operation.

[0051] In addition, this embodiment also includes another method for updating the integral sliding surface. Specifically, it can be learned through experiments that the integral sliding surface, the interference data adaptation rate, the weight adaptation rate and the first adaptation rate are combined to fit the dynamic characteristics and the Lyapunov function (a function used to prove the stability of a dynamic system or an autonomous differential equation) to obtain the integral sliding mode output: ,in are the design coefficients of the sliding surface, is the switching function gain, which is a positive real number, is the directional force of the surge and pitch. Specifically, in this embodiment The coefficients of the integral sliding surface can be updated through the output.

[0052] S150, determining a real-time target thrust according to the real-time surge and yaw direction speeds and the real-time fitted dynamic characteristics, and controlling the motor of the propeller according to the target thrust.

[0053] In this embodiment, the target thrust is the thrust required by the thrusters in total. The thrusters in this embodiment are dual fixed thrusters, i.e., a port thruster and a starboard thruster. The target thrust is distributed to the two thrusters according to a preset thrust distribution formula, which is: in, is the thrust of the port thruster, The starboard thruster The thrust in the swell and pitch directions of the target thrust is controlled according to the target thrust. Specifically, the speed of the propeller motor is controlled according to the target speed formula, and the target speed formula is: in, is the port propeller speed, is the starboard thruster speed, represents the water flow density, represents the diameter of the propeller, is the propeller thrust coefficient. The propeller motor is controlled according to the obtained rotation speed of the port propeller and the rotation speed of the starboard propeller, thereby controlling the trajectory tracking of the unmanned ship.

[0054] Figure 6 FIG. 2 is a schematic block diagram of an unmanned ship adaptive path tracking control device 200 provided by an embodiment of the present invention. Figure 6 As shown, corresponding to the above unmanned ship adaptive path tracking control method, the present invention also provides an unmanned ship adaptive path tracking control device. The unmanned ship adaptive path tracking control device includes a unit for executing the above unmanned ship adaptive path tracking control method, and the device can be configured in a desktop computer, a tablet computer, a laptop computer, and other terminals. Specifically, please refer to Figure 6 The unmanned ship adaptive path tracking control device includes an establishing unit 210, a fitting unit 220, a constructing unit 230, an updating unit 240 and a control unit 250.

[0055] The establishing unit 210 is used to establish a dynamic model of the unmanned ship without parameter requirements, and to simplify the dynamic model according to the directional force of the propeller of the unmanned ship to determine the dynamic characteristics, wherein the dynamic characteristics include unmodeled dynamic characteristics.

[0056] The fitting unit 220 is used to fit the unmodeled dynamic characteristics through an RBF neural network to determine the fitted dynamic characteristics.

[0057] The construction unit 230 is used to determine the integral sliding surface by using a preset construction method based on the surge velocity error and the yaw angle error.

[0058] In one embodiment, the construction unit 230 includes a deviation unit, an angle unit, and a difference unit.

[0059] A deviation unit, used to determine the lateral angle deviation by performing deviation calculation based on the preset tangential angle queue and the preview point coordinates;

[0060] An angle unit, used for determining a yaw angle queue by calculating a preset yaw angle according to the preset tangential angle queue and the lateral angle deviation;

[0061] A difference unit is used to determine a heading angle error by calculating the first difference between the lateral angle deviation and the heading angle, wherein the heading angle is a heading angle in the heading angle queue at the same time as the lateral angle deviation.

[0062] In one embodiment, the construction unit 230 includes an adaptation unit, a determination unit, and an error updating unit.

[0063] An adaptive unit, configured to construct a first adaptive rate by using a preset adaptive model to calculate an error between an ideal output of the thruster and a preset output threshold;

[0064] a determining unit, configured to determine an error adaptation rate through a second difference calculation according to the first adaptation rate, the yaw angle error, and the sway speed error;

[0065] An error updating unit is used to update the yaw angle error and the surge speed error in real time according to the error adaptation rate.

[0066] The updating unit 240 is used to perform adaptive calculation on the integral sliding surface to determine an adaptive rate, and adaptively update the fitted dynamic characteristics according to the adaptive rate to obtain real-time fitted dynamic characteristics.

[0067] In one embodiment, the updating unit 240 includes a multiplication unit and a weight updating unit.

[0068] A product unit, used for determining the weight adaptation rate by multiplying the integral sliding surface and the Gaussian radial basis function;

[0069] A weight updating unit is used to update the preset weight vector in real time according to the weight adaptation rate.

[0070] In one embodiment, the updating unit 240 includes an absolute value calculation unit and an interference updating unit.

[0071] An absolute value calculation unit, used for determining the interference data adaptation rate by calculating the absolute value of the integral sliding surface;

[0072] The interference updating unit is used to update the unknown interference data in real time according to a preset adaptive relationship and the interference data adaptive rate.

[0073] The control unit 250 is used to determine the real-time target thrust according to the real-time surge and pitch direction speeds and the real-time fitted dynamic characteristics, and control the motor of the propeller according to the target thrust.

[0074] It should be noted that technicians in the relevant field can clearly understand that the specific implementation process of the above-mentioned unmanned ship adaptive path tracking control device 200 and each unit can refer to the corresponding description in the aforementioned method embodiment, and for the convenience and conciseness of the description, it will not be repeated here.

[0075] The above-mentioned unmanned ship adaptive path tracking control device can be implemented in the form of a computer program, which can be used in Figure 7 Runs on the computer device shown.

[0076] See also Figure 7 , Figure 7 5 is a schematic block diagram of a computer device provided in an embodiment of the present application. The computer device 500 may be a terminal or a server, wherein the terminal may be an electronic device with communication functions such as a smart phone, a tablet computer, a laptop computer, a desktop computer, a personal digital assistant, and a wearable device. The server may be an independent server or a server cluster composed of multiple servers.

[0077] See also Figure 7 The computer device 500 includes a processor 502 , a memory and a network interface 505 connected via a system bus 501 , wherein the memory may include a non-volatile storage medium 503 and an internal memory 504 .

[0078] The non-volatile storage medium 503 can store an operating system 5031 and a computer program 5032. The computer program 5032 includes program instructions, and when the program instructions are executed, the processor 502 can execute the unmanned ship adaptive path tracking control method.

[0079] The processor 502 is used to provide computing and control capabilities to support the operation of the entire computer device 500 .

[0080] The internal memory 504 provides an environment for the operation of the computer program 5032 in the non-volatile storage medium 503. When the computer program 5032 is executed by the processor 502, the processor 502 can execute the unmanned ship adaptive path tracking control method.

[0081] The network interface 505 is used to communicate with other devices over the network. Figure 7 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present application, and does not constitute a limitation on the computer device 500 to which the solution of the present application is applied. The specific computer device 500 may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0082] The processor 502 is used to run a computer program 5032 stored in the memory to implement the steps of the above method.

[0083] It should be understood that in the embodiment of the present application, the processor 502 may be a central processing unit (CPU), and the processor 502 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0084] It can be understood by those skilled in the art that all or part of the processes in the method for implementing the above embodiment can be completed by instructing the relevant hardware through a computer program. The computer program includes program instructions, and the computer program can be stored in a storage medium, which is a computer-readable storage medium. The program instructions are executed by at least one processor in the computer system to implement the process steps of the embodiment of the above method.

[0085] Therefore, the present invention also provides a storage medium. The storage medium may be a computer-readable storage medium. The storage medium stores a computer program, wherein the computer program includes program instructions. When the program instructions are executed by a processor, the processor executes the steps of the above method.

[0086] The storage medium may be a USB flash drive, a mobile hard disk, a read-only memory (ROM), a magnetic disk, or an optical disk, etc., which are computer-readable storage media that can store program codes.

[0087] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0088] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of each unit is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0089] The steps in the method of the embodiment of the present invention can be adjusted in order, combined and deleted according to actual needs. The units in the device of the embodiment of the present invention can be combined, divided and deleted according to actual needs. In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0090] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, terminal, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention.

[0091] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. An adaptive path tracking control method for an unmanned ship, characterized in that: include: Establishing a dynamic model of an unmanned ship without parameter requirements, simplifying the dynamic model according to the directional force of the propeller of the unmanned ship to determine the dynamic characteristics, wherein the dynamic characteristics include unmodeled dynamic characteristics; Fitting the unmodeled kinetic characteristics by means of an RBF neural network to determine fitted kinetic characteristics; The integral sliding surface is determined by using the preset construction method to determine the swell velocity error and the bow pitch angle error; Adaptively calculating the integral sliding surface to determine an adaptive rate, and adaptively updating the fitted dynamic characteristics according to the adaptive rate to obtain real-time fitted dynamic characteristics; Determining a real-time target thrust according to the real-time surge and pitch direction speeds and the real-time fitted dynamic characteristics, and controlling the motor of the propeller according to the target thrust; Before the step of determining the integral sliding mode surface by using the surge velocity error and the yaw angle error through a preset construction method, the method includes: The lateral angle deviation is determined by performing deviation calculation based on the preset tangential angle queue and the preview point coordinates, wherein the planned path information is generated by calibrating the starting point and the middle point of the route by the control terminal, and the preset tangential angle queue is calculated based on the trajectory characteristics in the planned path information; The yaw angle queue is determined by calculating the preset yaw angle according to the preset tangential angle queue and the lateral angle deviation, wherein the yaw angle queue is a queue composed of yaw angles, and the formula for constituting the yaw angle is: ,in and is the fusion reference coefficient of the heading angle, is the tangent angle of the current coordinate in the preset tangent angle queue, is the lateral angle deviation, is the yaw angle in the yaw angle queue; Determine the yaw angle according to the lateral angle deviation and the yaw angle queue, and determine the yaw angle error by calculating the yaw angle through a first difference, wherein the yaw angle is the yaw angle in the yaw angle queue at the same time as the lateral angle deviation; Before the step of determining the integral sliding surface by using the preset construction method for the swell velocity error and the yaw angle error, the method further includes: The error between the ideal output of the thruster and the preset output threshold is used to construct a first adaptive rate through a preset adaptive model, wherein the first adaptive rate is: , , is a normal number, , is the output error value of the thruster; The error adaptation rate is determined by calculating the second difference according to the first adaptation rate, the yaw angle error, and the sway speed error, wherein the error adaptation rate includes the yaw angle error adaptation rate: , and the error adaptation rate of the surge velocity: , the first adaptive rate includes the adaptive rate of thrust in the surge and yaw directions, 、 are the adaptive rates of the first adaptive rate in thrust in the sloshing and yaw directions, is the swell speed in the swell speed queue at the same time, r is the yaw angle obtained in real time, is the heading angle of the heading angle array at the same moment; The yaw angle error and the surge speed error are updated in real time according to the error adaptation rate.

2. The method according to claim 1, characterized in that The fitting dynamic characteristic includes a preset weight vector, the adaptive rate includes a weight adaptive rate, and the step of adaptively calculating the integral sliding surface to determine the adaptive rate, and adaptively updating the fitting dynamic characteristic according to the adaptive rate includes: Determine the weight adaptation rate by multiplying the integral sliding surface and the Gaussian radial basis function; The preset weight vector is updated in real time according to the weight adaptation rate.

3. The method according to claim 1, characterized in that The fitted dynamic characteristics include unknown interference data, the adaptive rate includes an interference data adaptive rate, and the step of adaptively calculating the integral sliding surface to determine the adaptive rate, and adaptively updating the fitted dynamic characteristics according to the adaptive rate includes: Determine the interference data adaptation rate by calculating the absolute value of the integral sliding surface; The unknown interference data is updated in real time according to a preset adaptive relationship and the interference data adaptive rate.

4. The method according to claim 1, characterized in that: The kinetic model is: ； Among them, M is the mass matrix, C is the inertia matrix, and D is the resistance matrix. is the velocity in the surge and pitch direction, Thrust for the target; and The dynamic characteristics are: ； in, , are the target thrust in the swell direction and the target thrust in the yaw direction, u and r are the speed in the swell direction and the yaw direction, respectively. and is the unknown interference data, and the other unspecified parameters are unknown parameters; and The unmodeled dynamic characteristics are: ； ； Among them, the and are the unmodeled dynamic characteristics in the surge direction and the bow pitch direction, and the other unspecified parameters are unknown parameters.

5. The method according to claim 1, characterized in that: The fitted kinetic characteristics are: ； in, is the preset weight vector, To compensate for the error, is the Gaussian radial basis vector, is the fitted kinetic properties, and The integral sliding surface is: ； in, is the integral sliding surface, are the yaw angle error and the swell speed error, where 、 、 Both are sliding surface design coefficients.

6. An unmanned ship adaptive path tracking control device, characterized in that: The apparatus comprises means for executing the method according to any one of claims 1-5.

7. A computer device, characterized in that: The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the method according to any one of claims 1 to 5 when executing the computer program.

8. A storage medium, characterized in that: The storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the method according to any one of claims 1 to 5 can be implemented.

Images