Track tracking method, device, medium and product based on dynamic prediction step length

Abstract

The application discloses a kind of based on dynamic prediction step's track tracking method, equipment, medium and product, the method includes: in the process of navigation of water surface unmanned platform, current time's real-time running state information is acquired by sensor carried by platform;According to real-time running state information and the disturbance observer constructed in advance, estimate the unknown time-varying disturbance of ocean at current time;According to real-time state and reference path, calculate curvature time function, obtain path curvature by filtering, and dynamically adjust prediction step accordingly;Based on model predictive controller, combine real-time state, disturbance estimation and dynamic prediction step, predict the motion state of future multiple times;Optimization function is used to solve current optimal command rudder angle, and control is implemented;In each control cycle, by updating platform real-time state, loop execution until track tracking is completed, and the technical scheme of the embodiment of the application effectively improves the precision and adaptive control ability of water surface unmanned platform track tracking under complex sea conditions.

Description

Technical Field

[0001] This invention relates to the field of control technology for unmanned surface platforms, and in particular to a trajectory tracking method, device, medium, and product based on dynamic prediction step size. Background Technology

[0002] With the rapid growth in demand for marine resource development and hydrological and meteorological monitoring, high-precision autonomous trajectory tracking of unmanned surface platforms in complex sea conditions has become a key technological bottleneck restricting their operational efficiency. How to effectively cope with time-varying interferences such as wind, waves, and currents, as well as model uncertainties, and achieve high-precision path tracking control has become the core challenge in the development of intelligent control systems for unmanned surface platforms.

[0003] In existing technologies, traditional PID (Proportional-Integral-Derivative) control or fixed-parameter model predictive control methods are mainly used to achieve trajectory tracking of unmanned surface platforms. However, traditional PID control has poor robustness to disturbances in complex environments; while model predictive control methods with fixed prediction step sizes struggle to balance control accuracy and computational efficiency under uncertain conditions in complex marine environments, and cannot effectively adapt to the dynamic control requirements under complex sea conditions. Summary of the Invention

[0004] This invention provides a path tracking method, device, medium, and product based on dynamic prediction step size, which can significantly improve the path tracking accuracy and adaptive control capability of unmanned surface platforms under complex sea conditions.

[0005] According to one aspect of the present invention, a trajectory tracking method based on dynamic prediction step size is provided, executed by a main controller in an unmanned surface platform, the method comprising:

[0006] During the autonomous navigation of the unmanned surface platform according to the reference path trajectory, the real-time operating status information of the unmanned surface platform at the current moment is obtained through at least one sensor carried on the platform.

[0007] Based on real-time operational status information and a pre-built nonlinear disturbance observer, real-time unknown time-varying disturbance information of the ocean at the current moment is obtained;

[0008] Based on the curvature time function determined by real-time operating status information and reference path trajectory, the target path curvature of the unmanned surface platform under the preset sliding window is calculated, and the dynamic prediction step size used for this round of trajectory tracking is calculated based on the target path curvature.

[0009] Based on real-time operational status information, real-time unknown time-varying disturbance information of the ocean, dynamic prediction step size and pre-built model prediction controller, the predicted motion status information of the surface unmanned platform at future moments with a dynamic prediction step size is obtained.

[0010] The optimal command rudder angle at the current moment is solved by using the path tracking deviation optimization function constructed based on the predicted motion state information and the reference path trajectory, and the motion control of the unmanned surface platform is performed based on the optimal command rudder angle.

[0011] Upon reaching the new current moment, return to execute the operation of acquiring the real-time operating status information of the unmanned surface platform at the current moment through at least one sensor carried on the platform, until the entire trajectory tracking process is completed.

[0012] According to another aspect of the present invention, a trajectory tracking device based on dynamic prediction step size is provided, configured in the main controller of an unmanned surface platform, the device comprising:

[0013] The data acquisition module is used to acquire the real-time operating status information of the unmanned surface platform at the current moment through at least one sensor carried on the platform during the autonomous navigation of the unmanned surface platform according to the reference path trajectory.

[0014] The interference information acquisition module is used to acquire real-time unknown time-varying interference information of the ocean at the current moment based on real-time operating status information and a pre-built nonlinear interference observer.

[0015] The adaptive prediction step size generation module is used to calculate the target path curvature of the unmanned surface platform under a preset sliding window based on the curvature time function determined by real-time operating status information and reference path trajectory, and to calculate the dynamic prediction step size used for this round of trajectory tracking based on the target path curvature.

[0016] The multi-moment state prediction module is used to obtain the predicted motion state information of the surface unmanned platform at future moments based on real-time operating status information, real-time unknown time-varying disturbance information of the ocean, dynamic prediction step size and pre-built model prediction controller.

[0017] The optimal command generation module is used to solve for the optimal command rudder angle at the current moment using the path tracking deviation optimization function constructed based on each predicted motion state information and reference path trajectory, and to perform motion control on the unmanned surface platform based on the optimal command rudder angle.

[0018] The iterative update module is used to return to the operation of obtaining the real-time operating status information of the unmanned surface platform at the current moment through at least one sensor carried on the platform after reaching a new current moment, until the entire trajectory tracking process is completed.

[0019] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0020] At least one processor; and

[0021] A memory communicatively connected to the at least one processor; wherein,

[0022] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform a trajectory tracking method based on dynamic prediction step size as described in any embodiment of the present invention.

[0023] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement a trajectory tracking method based on dynamic prediction step size as described in any embodiment of the present invention.

[0024] According to another aspect of the present invention, a computer program product is also provided, including computer instructions that, when executed by a processor, implement the steps of the method as described in any embodiment of the present invention.

[0025] The technical solution of this invention involves the following steps: During autonomous navigation of a surface unmanned platform (UAV) following a reference path trajectory, at least one sensor mounted on the UAV acquires real-time operational status information at the current moment. Then, based on this real-time operational status information and a pre-built nonlinear disturbance observer, real-time unknown time-varying ocean disturbance information is acquired. Next, the curvature of the target path of the UAV within a preset sliding window is calculated according to the curvature-time function determined by the real-time operational status information and the reference path trajectory. The prediction step size used for this round of trajectory tracking is dynamically adjusted accordingly. Finally, by combining the real-time operational status information, real-time unknown time-varying ocean disturbance information, dynamic prediction step size, and a pre-built model prediction controller, multiple future... The system predicts the motion state information at each moment, then uses the path tracking deviation optimization function to solve for the optimal command rudder angle at the current moment, and performs motion control on the unmanned surface platform based on the optimal command rudder angle. After reaching a new current moment, the real-time operating state information is updated again through sensors, and the above process is repeated until the entire trajectory tracking process is completed. This novel trajectory tracking method based on dynamic prediction step size can not only significantly improve the accuracy of trajectory tracking and adaptive control capability of unmanned surface platforms under complex sea conditions, but also effectively overcome the problem of insufficient adaptability of traditional fixed parameter control in dynamic environments. Moreover, by intelligently adjusting the prediction step size, it achieves the optimal balance between computational efficiency and control performance, and greatly enhances the robust stability of the system under time-varying disturbance conditions.

[0026] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0027] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0028] Figure 1 This is a flowchart of a trajectory tracking method based on dynamic prediction step size provided in Embodiment 1 of the present invention;

[0029] Figure 2 This is a flowchart of another trajectory tracking method based on dynamic prediction step size provided in Embodiment 2 of the present invention;

[0030] Figure 3 This is a diagram illustrating the effect of trajectory tracking in a specific scenario applicable to an embodiment of the present invention.

[0031] Figure 4 This is a trajectory tracking deviation curve effect diagram under a specific scenario applicable to the embodiments of the present invention;

[0032] Figure 5 This is a schematic diagram of a trajectory tracking device based on dynamic prediction step size according to Embodiment 3 of the present invention;

[0033] Figure 6 This is a schematic diagram of the structure of an electronic device that implements a trajectory tracking method based on dynamic prediction step size according to an embodiment of the present invention. Detailed Implementation

[0034] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0035] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0036] Example 1

[0037] Figure 1 This is a flowchart of a trajectory tracking method based on dynamic prediction step size provided in Embodiment 1 of the present invention. This embodiment is applicable to high-precision autonomous trajectory tracking control of unmanned surface platforms under complex sea conditions. The method can be executed by a trajectory tracking device based on dynamic prediction step size. This device can be implemented in hardware and / or software and is generally configured in the main controller of the unmanned surface platform.

[0038] Correspondingly, such as Figure 1 As shown, the method includes:

[0039] S110. During the autonomous navigation of the unmanned surface platform according to the reference path trajectory, the real-time operating status information of the unmanned surface platform at the current moment is obtained through at least one sensor carried on the platform.

[0040] The reference path trajectory can be understood as a pre-planned ideal navigation route, typically consisting of a series of continuous geographic coordinates, used to guide unmanned surface platforms in completing specific tasks (such as marine monitoring or topographic mapping). This reference path trajectory includes requirements for parameters such as position, heading, and speed, and serves as the benchmark for track tracking and control.

[0041] In this embodiment, multi-source sensor fusion technology, including the BeiDou-2 navigation system, integrated navigation equipment, and AIS (Automatic Identification System) onboard the unmanned surface platform, can be used to collect real-time six-degree-of-freedom motion parameters of the unmanned surface platform in the geodetic coordinate system, such as its northward position, eastward position, heading angle, ground-based forward speed, ground-based lateral speed, and bow angular velocity. The collected data may also include hydrodynamic parameters such as the unmanned surface platform's water velocity and drift angle, serving as real-time operational status information that comprehensively reflects the actual motion state of the unmanned surface platform.

[0042] S120. Based on real-time operating status information and a pre-built nonlinear disturbance observer, obtain real-time unknown time-varying disturbance information of the ocean at the current moment.

[0043] Among them, unknown time-varying interference information can be understood as the disturbance caused by the marine environment (such as wind, waves, and currents) during the navigation of unmanned surface platforms, which is difficult to measure accurately through traditional sensors and changes dynamically over time. This type of interference has characteristics such as uncertainty (amplitude and frequency are unpredictable), time-varying (changing in real time with sea conditions), and nonlinearity (coupled with the motion state of the unmanned surface platform). It usually manifests as additional forces and torques on the unmanned surface platform, directly affecting the accuracy of track tracking.

[0044] In this embodiment, based on a pre-designed nonlinear disturbance observer structure and combined with real-time acquired motion state information, the time-varying disturbance forces and torques generated by marine environments such as wind, waves, and currents are estimated online. The observer achieves dynamic compensation for unknown disturbances by coupling internal state variables with nonlinear functions.

[0045] S130. Calculate the target path curvature of the unmanned surface platform under a preset sliding window based on the curvature time function determined by the real-time operating status information and the reference path trajectory, and calculate the dynamic prediction step size used for this round of trajectory tracking based on the target path curvature.

[0046] The curvature-time function can be understood as a mathematical expression describing the change in path curvature over time; essentially, it is a function of path curvature with respect to time parameters. This function is dynamically calculated through the geometric relationship between real-time motion states (such as position and heading angle) and the reference path, reflecting the instantaneous changing trend of the path curvature characteristics that the unmanned surface platform must follow during navigation. The target path curvature can be understood as the smoothed curvature value of the reference path. Since the original curvature data may contain noise or abrupt changes, it needs to be filtered using a preset sliding window (such as a Hanning window) to extract stable and reliable curvature features. The dynamic prediction step size can be understood as a prediction time-domain parameter that is adaptively adjusted according to the path curvature. Its core principle is: a longer prediction step size is used on high-curvature path segments (such as sharp curves) to improve control foresight, and a shorter step size is used on low-curvature path segments (such as straight lines) to reduce computational load.

[0047] In this embodiment, the target path curvature can be calculated using differential geometry methods, deriving the instantaneous curvature from the rate of change of the tangential angle between the real-time motion state and the reference path. The sliding window filter uses a Hanning window function for weighted averaging, with the window length adaptively adjusted according to the speed of the unmanned surface platform: shortening the window at high speeds improves response speed, and lengthening the window at low speeds enhances smoothing. The dynamic prediction step size adjustment algorithm uses the radius of curvature as the input variable and generates a prediction step size mapping table through piecewise linear interpolation, ensuring that shorter step sizes are used on straight sections to save computational resources, while longer step sizes are used on curved sections to maintain tracking accuracy.

[0048] S140. Based on real-time operating status information, real-time unknown time-varying disturbance information of the ocean, dynamic prediction step size and pre-built model prediction controller, the predicted motion status information of the unmanned surface platform at future time points with a dynamic prediction step size is obtained.

[0049] Model predictive controllers can be understood as an advanced control algorithm based on dynamic models for rolling optimization. Its core principle is to predict the system behavior over a future period using the current system state and the predictive model, and then, considering constraints, generate the optimal control sequence by solving the optimization problem online, ultimately implementing only the control command for the current moment.

[0050] In this embodiment, real-time motion state information, time-varying interference estimates output by the interference observer, and dynamic prediction step size are input together into a pre-established model prediction controller. By solving a discretized prediction model that includes the dynamics of the unmanned surface platform, servo response, and environmental interference terms, the predicted state sequence of the unmanned surface platform's position, velocity, and heading angle at multiple future moments is obtained.

[0051] S150. Using the path tracking deviation optimization function constructed based on each predicted motion state information and reference path trajectory, the optimal command rudder angle at the current moment is solved, and the motion control of the unmanned surface platform is performed based on the optimal command rudder angle.

[0052] The path tracking deviation optimization function can be understood as a mathematical objective function used to quantify the deviation between the actual trajectory of an unmanned surface platform and a reference path. This function typically takes the form of a weighted quadratic form, comprehensively evaluating multi-dimensional errors such as lateral position deviation, heading angle deviation, and velocity deviation to construct the performance index that needs to be minimized. The optimal command rudder angle can be understood as the optimal control output obtained by solving the path tracking deviation optimization function.

[0053] In this embodiment, a path tracking optimization function is constructed based on the lateral deviation between the predicted motion state sequence and the reference path. An improved artificial bee colony algorithm is used to solve the function to obtain the optimal rudder angle command that minimizes the tracking deviation at the current moment. This command is then output to the servo actuator to achieve motion control.

[0054] S160. After reaching the new current moment, return to execute the operation of obtaining the real-time operating status information of the unmanned surface platform at the current moment through at least one sensor carried on the platform, until the entire trajectory tracking process is completed.

[0055] In this embodiment, the system timestamp is updated at the end of each control cycle, the latest real-time motion state data is collected again through the sensors, and the above-mentioned disturbance estimation, prediction step size adjustment, state prediction and optimization control process are executed cyclically to form a cyclic control structure until the unmanned surface platform completes the tracking task of all reference path trajectories.

[0056] The technical solution of this invention involves the following steps: During autonomous navigation of a surface unmanned platform following a reference path trajectory, at least one sensor on the platform acquires real-time operational status information at the current moment. Then, based on this real-time operational status information and a pre-built nonlinear disturbance observer, real-time unknown time-varying ocean disturbance information is acquired. Next, the curvature of the target path of the surface unmanned platform within a preset sliding window is calculated according to the curvature-time function determined by the real-time operational status information and the reference path trajectory. The prediction step size used for this round of trajectory tracking is dynamically adjusted accordingly. Finally, by combining the real-time operational status information, the real-time unknown time-varying ocean disturbance information, the dynamic prediction step size, and the pre-built model prediction controller, multiple future time points are obtained. The system predicts the motion state information and then uses the path tracking deviation optimization function to solve for the optimal command rudder angle at the current moment. Based on the optimal command rudder angle, the system controls the motion of the unmanned surface platform. After reaching a new current moment, the system updates the real-time operating status information through sensors and repeats the above process until the entire trajectory tracking process is completed. This novel trajectory tracking method based on dynamic prediction step size can significantly improve the accuracy and adaptive control capability of unmanned surface platforms in complex sea conditions, effectively overcome the problem of insufficient adaptability of traditional fixed parameter control in dynamic environments, and achieve the optimal balance between computational efficiency and control performance by intelligently adjusting the prediction step size, greatly enhancing the robust stability of the system under time-varying disturbance conditions.

[0057] Optionally, based on the above embodiments, obtaining real-time unknown time-varying ocean disturbance information at the current moment according to real-time operating status information and a pre-built nonlinear disturbance observer may include:

[0058] From the real-time operational status information, the real-time lateral velocity v of the unmanned surface platform (i.e., the ground-based lateral velocity mentioned earlier) is extracted and calculated according to the formula... Calculate the nonlinear function in the nonlinear disturbance observer. ,in, This is a preset positive definite gain matrix;

[0059] According to the formula: Calculate the real-time unknown time-varying disturbance information of the ocean at the current moment. Where z represents the internal state of the nonlinear disturbance observer at the current moment. ,in This is an estimate of the roll disturbance of the unmanned surface platform. This is an estimate of the pitch disturbance of the unmanned surface platform. The estimated value of heave disturbance for unmanned surface platforms;

[0060] According to the formula: The internal state of the nonlinear disturbance observer is updated to obtain the observer's state at the next time step. For use in the next round of track tracking;

[0061] in, Let M be the observer gain matrix, and M be a preset inertia matrix, which is a positive definite pairwise matrix. For Coriolis and, Here is the damping matrix. To control the input force.

[0062] Generally, after acquiring the real-time operational status information of an unmanned surface platform (USP), it is necessary to extract the crucial real-time lateral velocity. This lateral velocity reflects the USP's velocity perpendicular to the reference path at the current moment. Based on this real-time lateral velocity and a pre-defined positive definite gain matrix, the nonlinear function required for the nonlinear disturbance observer is calculated using specific mathematical formulas. This nonlinear function is designed to achieve sensitive capture and dynamic response to environmental disturbances, and its construction must satisfy the Lyapunov stability condition to ensure the convergence and reliability of the observer's output.

[0063] Generally, during the operation of a nonlinear disturbance observer, it is necessary to combine the observer's internal state variables at the current moment with the aforementioned calculated nonlinear function, and solve for the unknown time-varying disturbance information of the ocean acting on the platform at the current moment (i.e., real-time unknown time-varying disturbance information of the ocean) through differential equations involving the observer's gain matrix and inertia matrix. This disturbance information covers the lateral disturbance forces and moments caused by environmental factors such as wind, waves, and currents. The calculation process fully considers the coupling relationship between the dynamic characteristics of the platform and external disturbances, providing accurate disturbance estimates for subsequent control compensation.

[0064] Generally, to maintain the continuous operation of a nonlinear disturbance observer and ensure its adaptability under different sea states, it is necessary to derive the observer's internal state variables for the next moment through an internal state update mechanism based on the current disturbance estimation results and system state within each control cycle. This update process strictly follows the dynamic equations of the nonlinear observer, involving the adjustment of the observer's gain matrix and the coupling effect of the inertia matrix. This ensures that the observer can continuously track the changing trend of time-varying disturbances, providing an accurate disturbance feedforward compensation basis for the next round of track tracking control.

[0065] Based on the above embodiments, before calculating the target path curvature of the unmanned surface platform within a preset sliding window according to the curvature-time function determined by real-time operating status information and reference path trajectory, the method may further include:

[0066] Extract real-time location information and real-time speed from the real-time operational status information;

[0067] Based on real-time location information and reference path trajectory, the sub-path to be navigated is determined, and the curvature time function is dynamically calculated based on real-time speed information and the sub-path to be navigated.

[0068] Generally, after acquiring the real-time operational status information of an unmanned surface platform, it is necessary to extract key real-time location information and real-time speed parameters. Real-time location information, obtained through the platform's onboard navigation equipment, reflects the platform's specific geographical coordinates at the current moment, while real-time speed characterizes the instantaneous velocity of the platform moving along a reference path. These two types of information together constitute the fundamental data source for subsequent path planning and control decisions, and their accuracy and real-time performance directly affect the performance of the entire trajectory tracking process.

[0069] Generally, based on real-time acquired position information and a pre-set reference path trajectory, the sub-path segment to be navigated must first be determined. The selection of this sub-path segment must consider the shortest distance between the platform's current position and the reference path, as well as heading consistency, to ensure the continuity and feasibility of path planning. Subsequently, combining real-time speed information and the geometric characteristics of the sub-path to be navigated, a curvature-time function is dynamically calculated using differential geometry methods. This function reflects the change in the curvature of the path that the platform must follow while navigating on the sub-path segment over time. Its calculation process fully considers the impact of speed changes on path tracking characteristics, providing crucial input for the subsequent dynamic adjustment of the prediction step size.

[0070] In an optional implementation of this embodiment, a target location point that is closest to the real-time location information can be located in the reference path trajectory based on the real-time location information. Then, starting from the target location point, a trajectory of a set arc length is extracted along the extension direction of the reference path trajectory to obtain the sub-path to be navigated.

[0071] Furthermore, after obtaining the sub-path to be navigated, the different path points in the sub-path can be time-parameterized based on the real-time speed. For example, the discrete point set in the sub-path r to be navigated can be... Updated to In this form, the first derivative of the time-parameterized path can then be solved. and second derivative .

[0072] Then, using the time-parameterized curvature formula: Calculate the curvature time function .

[0073] Example 2

[0074] Figure 2 This is a flowchart of another trajectory tracking method based on dynamic prediction step size provided in Embodiment 2 of the present invention. This embodiment is based on and optimized from the above embodiments. Specifically, the operation of "using the path tracking deviation optimization function constructed based on each predicted motion state information and the reference path trajectory to solve for the optimal command rudder angle at the current moment" has been refined.

[0075] Correspondingly, such as Figure 2 As shown, the method includes:

[0076] S210. During the autonomous navigation of the unmanned surface platform according to the reference path trajectory, the real-time operating status information of the unmanned surface platform at the current moment is obtained through at least one sensor carried on the platform.

[0077] S220. Based on real-time operational status information and a pre-built nonlinear disturbance observer, obtain real-time unknown time-varying disturbance information of the ocean at the current moment.

[0078] S230. Based on the curvature time function determined by the real-time operating status information and the reference path trajectory, calculate the target path curvature of the unmanned surface platform under the preset sliding window, and calculate the dynamic prediction step size used for this round of trajectory tracking based on the target path curvature.

[0079] S240. Based on real-time operating status information, real-time unknown time-varying disturbance information of the ocean, dynamic prediction step size and pre-built model prediction controller, the predicted motion status information of the unmanned surface platform at future time points with a dynamic prediction step size is obtained.

[0080] In an optional implementation of this embodiment, the pre-built model prediction controller can be:

[0081]

[0082] In the motion coordinates of an unmanned surface platform, the x-axis is defined as pointing due north, and the angle between the bow and stern centerlines and the x-axis is called the bow angle. express. and These represent the flow direction and velocity, respectively. For the speed of water movement, For the lateral velocity of water, for the combined velocity of water The components of the surface unmanned platform's velocity along the x-axis and y-axis in the oxyz coordinate system are respectively... and , For ground-based forward speed, Let r be the lateral velocity relative to the ground, r be the angular velocity of the bow rotating about the z-axis, and r be the resultant velocity relative to the ground. drift angle , For rudder angle. To command the rudder angle, For servo control gain, Let m be the servo motor time constant, and m be the mass of the unmanned surface platform. and For added mass, , and For viscous hydrodynamics acting on the hull, , and For propeller force, , and For wind power, , and For the force of the waves, Let be the moment of inertia of the unmanned surface platform about its vertical axis. To add a moment of inertia, , and As rudder force, It is the reduction in rudder drag. It is the ratio of the additional lateral force on the hull caused by steering to the lateral force of the rudder. It is the distance from the center of the lateral force acting on the steering-guided hull to the center of gravity of the unmanned surface platform. It is the rudder positive pressure.

[0083] In the trajectory tracking and control process, real-time operational status information, real-time unknown time-varying disturbance information of the ocean, and dynamic prediction step size are input as input parameters to a pre-built model predictive controller. The specific implementation method for predicting the motion state of the unmanned surface platform at future moments is as follows:

[0084] in, , , , , , , For the future The dynamic status of the unmanned surface platform at any given time. , , , , , , for The movement status of the unmanned platform on the water surface at any given time. It refers to the prediction sampling time, which is the time interval between two consecutive predicted values. , , , , , and These are the discretizations of the differential equations in the model predictive controller;

[0085] , , , , , and The calculation method is as follows:

[0086]

[0087] in, , , This is an estimate of unknown time-varying disturbances in the ocean, estimated and compensated using the nonlinear disturbance observer proposed in this embodiment of the invention. Tracking is performed considering only lateral displacement, from the current k-time to the future... Predict the output at each time step:

[0088]

[0089] S250. Construct a path tracking deviation optimization function based on the predicted motion state information and the reference path trajectory.

[0090] In this embodiment, a path tracking deviation optimization function is constructed based on the multi-step predicted motion state sequence output by the model predictive controller and combined with the expected value of the reference path trajectory. This function adopts a weighted quadratic form, focusing on evaluating multi-dimensional errors such as lateral position deviation, heading angle deviation, and velocity deviation. Lateral displacement deviation is given a high weight to ensure path tracking accuracy, heading angle deviation is given a medium weight to maintain motion stability, and velocity deviation is given a low weight to avoid over-adjustment. The optimization function also introduces a penalty term for the rate of change of control variables to prevent drastic changes in rudder angle commands and ensure smooth control.

[0091] In an optional implementation of this embodiment, based on the prediction results and the reference lateral displacement... Calculate path prediction error :

[0092]

[0093] in, Based on the prediction error, construct an optimization function:

[0094]

[0095]

[0096] Here, Q is the weight matrix. This is achieved by solving the quadratic form of QP or under constraints. Solve the equation below The optimal control rudder angle can be calculated. :

[0097]

[0098] in, This represents the output of the entire optimization problem. In this embodiment, it represents the optimal control rudder angle, and argmin represents finding a control variable that minimizes the objective function. This is represented as the minimum control rudder angle. This represents the maximum control rudder angle. It is represented as the objective function that needs to be minimized.

[0099] S260. Under the constraints of state variables and control inputs, the optimal solution of the path tracking deviation optimization function is obtained by using the improved artificial bee colony algorithm to obtain the optimal command rudder angle at the current moment.

[0100] Among them, the Artificial Bee Colony Algorithm can be understood as a swarm intelligence optimization algorithm that simulates the foraging behavior of bee colonies. It solves complex optimization problems by mimicking the division of labor, cooperation, and information sharing mechanisms that bees use in the process of finding nectar sources. Its core idea is to map the solution space of the optimization problem to the location of nectar sources, and gradually approach the global optimum through the collaborative search of three roles: hired bees (developing known nectar sources), follower bees (selecting high-quality nectar sources), and scout bees (exploring new nectar sources).

[0101] In this embodiment, an improved artificial bee colony algorithm is used to solve for the optimal solution of the path tracking deviation optimization function. This algorithm simulates bee colony foraging behavior and introduces a sensitivity-pheromone hybrid selection mechanism to replace the traditional roulette wheel selection, effectively avoiding premature convergence. During the search process, a cross-learning strategy is used to guide inferior solutions to learn from elite solutions, accelerating the convergence speed. The algorithm retains the elite solution set in each generation of evolution and dynamically adjusts the search neighborhood, quickly finding the optimal command rudder angle that minimizes the deviation function while satisfying the physical constraints of the rudder angle and the response limitations of the actuator.

[0102] In an optional implementation of this embodiment, a sensitivity-based free search algorithm is used to select nectar sources by combining sensitivity with pheromones instead of the roulette wheel method. This includes the following steps: Step 1: Calculate the fitness values ​​of N nectar sources. ;

[0103] Step 2, calculate the first A honey source's pheromones :

[0104]

[0105] in, To minimize fitness, The maximum fitness value;

[0106] Step 3: Randomly generate the sensitivity of the i-th following bee. ;

[0107] Step 4: Find the bee source that matches the sensitivity of the i-th follower bee: Randomly find i that satisfies... .

[0108] Furthermore, because the artificial bee colony algorithm inherently possesses randomness, it cannot guarantee a global search capability for all solutions, making it prone to getting trapped in local minima. Therefore, during bee observation, this invention proposes randomly crossing over discovered honey sources to simulate the location with the highest honey source concentration, and dynamically generating new honey source vectors. Dimensional components As described below:

[0109]

[0110] in Let w represent the w-th dimension component of the optimal honey source vector, and This represents the w-th dimension component in the worst honey source vector. This is represented by a randomly generated number within the range of 0 to 2. The proposed method effectively utilizes information from neighboring honey sources, especially in the early stages of optimization when the quality of honey sources varies greatly. By guiding the search for new honey sources with optimal honey sources, bee colonies that discover the worst honey sources learn from those with optimal honey sources, accelerating convergence towards the optimal colony. Ranking and selecting honey sources based on fitness discards fewer effective sources and retains elite sources with high fitness values, minimizing inefficient local searches, reducing iterations, and improving the algorithm's convergence speed and global search performance.

[0111] S270: Perform motion control on the unmanned surface platform according to the optimal command rudder angle.

[0112] S280. After reaching the new current moment, return to execute the operation of obtaining the real-time operating status information of the unmanned surface platform at the current moment through at least one sensor carried on the platform, until the entire trajectory tracking process is completed.

[0113] The technical solution of this invention involves the following steps during autonomous navigation of a surface unmanned platform following a reference path trajectory. Real-time operational status information is acquired via sensors mounted on the platform. Then, based on this real-time operational status information and a pre-built nonlinear disturbance observer, real-time unknown time-varying ocean disturbance information is obtained. Next, the target path curvature within a preset sliding window is calculated using a curvature-time function determined by the real-time operational status information and the reference path trajectory. The prediction step size used for this round of trajectory tracking is dynamically adjusted accordingly. Combining the real-time operational status information, real-time unknown time-varying ocean disturbance information, dynamic prediction step size, and a pre-built model predictive controller, predicted motion status information for multiple future moments is obtained. A path tracking deviation optimization function is then constructed based on each predicted motion status information and the reference path trajectory. An improved artificial bee colony algorithm is used to solve this function under state variable and control input constraints to obtain the optimal command rudder angle for the current moment. Finally, the surface unmanned platform is controlled based on the optimal command rudder angle. Upon reaching a new current moment, the real-time operational status information is updated again via sensors, and the above process is repeated until the entire trajectory tracking process is completed. This novel track tracking method based on dynamic prediction step size improves the solution process of the path tracking deviation function by optimizing the artificial bee colony algorithm, significantly enhancing the efficiency and accuracy of control command generation under complex sea conditions. At the same time, relying on the collaborative mechanism of nonlinear disturbance observer and model predictive control, it effectively enhances the system's adaptive compensation capability to time-varying environmental disturbances, achieving highly reliable autonomous track tracking.

[0114] Optionally, based on the above embodiments, calculating the dynamic prediction step size used for this round of trajectory tracking according to the target path curvature may include:

[0115] According to the formula: Calculate the dynamic prediction step size used in this round of trajectory tracking. ;

[0116] in, The preset sea state adjustment factor is L, where L is the waterline length of the unmanned surface platform. For the real-time speed of unmanned surface platforms, The preset base prediction step size, The preset minimum step size threshold, The Clip() function is used to set the preset maximum step size threshold. Constraints and between.

[0117] Generally, during track tracking, the dynamic prediction step size needs to be calculated based on real-time sea conditions and platform motion characteristics. This calculation process is based on preset sea state adjustment factors, the platform's main waterline length, and real-time speed, and is derived comprehensively through specific mathematical relationships. The sea state adjustment factor reflects the degree of influence of the current marine environment on control accuracy, the waterline length reflects the platform's inertial characteristics, and the real-time speed directly determines the timeliness requirements of the control response. These parameters together constitute the basis for step size calculation.

[0118] Generally, the calculation of dynamic prediction step size also requires combining a preset base prediction step size and minimum and maximum step size thresholds. Specific constraint functions are used to limit the calculation results within a reasonable range. The base prediction step size provides a reference value, the minimum step size threshold ensures computational efficiency and control stability, and the maximum step size threshold avoids error accumulation caused by over-prediction. The constraint function, through an intelligent adjustment mechanism, ensures that the final step size meets both accuracy and real-time requirements, thus adapting to track tracking control under different sea conditions.

[0119] Optionally, based on the above embodiments, motion control of the unmanned surface platform according to the optimal command rudder angle may include:

[0120] The optimal command rudder angle is input into the motion control system of the unmanned surface platform;

[0121] The motion control system controls the motion of the unmanned surface platform based on the optimal command rudder angle.

[0122] Generally, after obtaining the optimal command rudder angle, the control command needs to be input into the motion control unit of the unmanned surface platform. This unit, as the execution terminal of the entire control process, is responsible for receiving and parsing the control commands generated by the optimization algorithm and converting them into specific servo motor operation signals. The motion control unit contains a signal conversion module and an execution drive module to ensure that the control commands can be accurately and timely transmitted to the servo motor mechanism, laying the foundation for subsequent motion control implementation.

[0123] Generally, the motion control unit (ECU) performs precise motion control of the unmanned surface platform based on the received optimal command rudder angle, using preset control logic and servo response characteristics. This process first calculates the required servo rotation angle and direction based on the rudder angle command, then controls the servo to execute the corresponding deflection action through the drive circuit, thereby adjusting the platform's heading and trajectory. Throughout the control process, the motion control unit monitors the servo's execution status in real time to ensure that the actual rudder angle remains consistent with the command value, and dynamically compensates for any possible execution deviations to ensure the platform can navigate stably along the expected path.

[0124] It is important to note that the motion control unit continuously collaborates with the upper-level decision-making module throughout the entire trajectory tracking process, forming a closed-loop control structure. At the start of each new control cycle, the motion control unit feeds back the latest execution status to the decision-making module, providing data support for subsequent optimization calculations. This ensures the continuity and stability of the entire control process, ultimately achieving high-precision autonomous trajectory tracking.

[0125] For ease of understanding, the specific application scenarios applicable to each embodiment of the invention are described. In this specific embodiment, in order to improve the autonomous trajectory tracking accuracy and anti-interference capability of unmanned surface platforms under complex sea conditions, this embodiment of the invention designs a complete trajectory tracking scheme based on dynamic prediction step size.

[0126] This invention achieves high-precision trajectory tracking through a multi-module collaborative control architecture. In a specific example, the scheme first uses a multi-source sensor fusion network consisting of the BeiDou-2 navigation system, integrated navigation equipment, and AIS automatic identification system carried by the unmanned surface platform to collect the six-degree-of-freedom motion state parameters of the unmanned surface platform in the geodetic coordinate system in real time, and uses the Kalman filter algorithm for data fusion and noise suppression. Then, based on the nonlinear disturbance observer, the disturbance forces and torques generated by wind, waves, and current in the three degrees of freedom are estimated in real time, effectively compensating for model uncertainties and unmodeled dynamics. Next, based on the geometric relationship between the real-time motion state and the reference path, the curvature features of the target path are extracted through a sliding window filter, and the prediction time domain of the model predictive control is dynamically adjusted based on these features. After obtaining the results of the preprocessing, the real-time motion state, disturbance estimates, and dynamic prediction step size are input together to the model predictive controller. The future state prediction sequence is solved by rolling, and finally, the optimal rudder angle command sequence is solved using an improved artificial bee colony algorithm, forming an efficient and reliable closed-loop control structure.

[0127] To verify the effectiveness of the scheme, simulation and field measurements were conducted using a certain type of unmanned surface surveying platform for oceanographic surveying. The parameters of the unmanned surface surveying platform are as follows: draft 0.4 meters, full-load displacement 4.1 tons, length 7.5 meters, beam 2.8 meters, block coefficient 0.07, and propeller diameter 0.8 meters. To verify the controller's performance, two trajectory modes were designed, including a straight trajectory and a curved trajectory. The simulation results are shown below. Figure 3 and Figure 4 As shown.

[0128] Figure 3 This is a diagram illustrating the trajectory tracking effect, such as... Figure 3 As shown, even under time-varying wind and air disturbance conditions, the unmanned surface platform can still accurately track the curved path. Figure 4 The effect diagram of the trajectory tracking deviation curve, such as Figure 4As shown, the maximum tracking error of the surface unmanned platform is 1.37 meters, and the average tracking error for the entire tracking process is 1.09 meters. The results of the curve tracking and tracking error demonstrate that the designed controller can achieve stable tracking of various paths under complex sea conditions. Further verification of the effectiveness of this method was achieved through tests on the surface unmanned platform at sea. Track tracking tests were conducted on the surface unmanned platform under sea state 3, and the results showed that the maximum tracking deviation did not exceed 3.2 meters, indicating that the method has high feasibility and practicality. This embodiment of the scheme can achieve the following beneficial effects:

[0129] (1) By constructing a nonlinear disturbance observer to estimate and compensate for unknown time-varying disturbances such as wind, waves and currents in real time, the dependence of traditional control methods on accurate hydrodynamic models is effectively overcome, and the anti-interference ability and robustness of the system under complex sea conditions are significantly enhanced, providing a stable and reliable control basis for high-precision track tracking.

[0130] (2) A model predictive control mechanism based on adaptive adjustment of prediction step size based on path curvature was designed. When the path curvature is large, the prediction time domain is automatically extended to improve tracking accuracy, and when the path is straight, the prediction time domain is shortened to improve computational efficiency, thus achieving the optimal balance between control performance and computational load.

[0131] (3) An improved artificial bee colony algorithm is used to solve the path tracking deviation optimization function. The traditional roulette wheel selection is replaced by a sensitivity-pheromone hybrid selection mechanism and a cross-learning strategy, which effectively avoids local optima, speeds up global convergence, and ensures that the generated optimal rudder angle command has both high precision and smoothness.

[0132] Example 3

[0133] Figure 5 This is a schematic diagram of a trajectory tracking device based on dynamic prediction step size provided in Embodiment 3 of the present invention. The device is configured in the main controller of an unmanned surface platform.

[0134] Correspondingly, such as Figure 5 As shown, the device includes:

[0135] The data acquisition module 510 is used to acquire the real-time operating status information of the unmanned surface platform at the current moment through at least one sensor carried on the platform during the autonomous navigation of the unmanned surface platform according to the reference path trajectory.

[0136] The interference information acquisition module 520 is used to acquire real-time unknown time-varying interference information of the ocean at the current moment based on real-time operating status information and a pre-built nonlinear interference observer;

[0137] The adaptive prediction step size generation module 530 is used to calculate the target path curvature of the unmanned surface platform under a preset sliding window based on the curvature time function determined by the real-time running status information and the reference path trajectory, and to calculate the dynamic prediction step size used for this round of trajectory tracking based on the target path curvature.

[0138] The multi-moment state prediction module 540 is used to obtain the predicted motion state information of the surface unmanned platform at future moments based on real-time operating status information, real-time unknown time-varying disturbance information of the ocean, dynamic prediction step size and pre-built model prediction controller.

[0139] The optimal command generation module 550 is used to solve the optimal command rudder angle at the current moment using the path tracking deviation optimization function constructed based on each predicted motion state information and reference path trajectory, and to perform motion control on the unmanned surface platform based on the optimal command rudder angle.

[0140] The iterative update module 560 is used to return to the operation of obtaining the real-time operating status information of the unmanned surface platform at the current moment through at least one sensor carried on the platform after reaching a new current moment, until the entire trajectory tracking process is completed.

[0141] The technical solution of this invention involves the following steps: During autonomous navigation of a surface unmanned platform following a reference path trajectory, at least one sensor on the platform acquires real-time operational status information at the current moment. Then, based on this real-time operational status information and a pre-built nonlinear disturbance observer, real-time unknown time-varying ocean disturbance information is acquired. Next, the curvature of the target path of the surface unmanned platform within a preset sliding window is calculated according to the curvature-time function determined by the real-time operational status information and the reference path trajectory. The prediction step size used for this round of trajectory tracking is dynamically adjusted accordingly. Finally, by combining the real-time operational status information, the real-time unknown time-varying ocean disturbance information, the dynamic prediction step size, and the pre-built model prediction controller, multiple future time points are obtained. The system predicts the motion state information and then uses the path tracking deviation optimization function to solve for the optimal command rudder angle at the current moment. Based on the optimal command rudder angle, the system controls the motion of the unmanned surface platform. After reaching a new current moment, the system updates the real-time operating status information through sensors and repeats the above process until the entire trajectory tracking process is completed. This novel trajectory tracking method based on dynamic prediction step size can significantly improve the accuracy and adaptive control capability of unmanned surface platforms in complex sea conditions, effectively overcome the problem of insufficient adaptability of traditional fixed parameter control in dynamic environments, and achieve the optimal balance between computational efficiency and control performance by intelligently adjusting the prediction step size, greatly enhancing the robust stability of the system under time-varying disturbance conditions.

[0142] Based on the above embodiments, the interference information acquisition module 520 is specifically used for:

[0143] From the real-time operational status information, the real-time lateral velocity v of the unmanned surface platform is extracted, and then calculated according to the formula... Calculate the nonlinear function in the nonlinear disturbance observer. ,in, This is a preset positive definite gain matrix;

[0144] According to the formula: Calculate the real-time unknown time-varying disturbance information of the ocean at the current moment. Where z represents the internal state of the nonlinear disturbance observer at the current moment. ,in This is an estimate of the roll disturbance of the unmanned surface platform. This is an estimate of the pitch disturbance of the unmanned surface platform. The estimated value of heave disturbance for unmanned surface platforms;

[0145] According to the formula: The internal state of the nonlinear disturbance observer is updated to obtain the observer's state at the next time step. For use in the next round of track tracking;

[0146] in, Let M be the observer gain matrix, and M be a preset inertia matrix, which is a positive definite pairwise matrix. For Coriolis and, Here is the damping matrix. To control the input force.

[0147] Furthermore, based on the above embodiments, a trajectory tracking device based on dynamic prediction step size may further include:

[0148] The information extraction module is used to extract real-time position information and real-time speed from the real-time operating status information before calculating the curvature of the target path of the unmanned surface platform under a preset sliding window based on the curvature time function determined by the real-time operating status information and the reference path trajectory.

[0149] The calculation module is used to determine the sub-path to be navigated based on real-time location information and reference path trajectory, and to dynamically calculate the curvature time function based on real-time speed information and the sub-path to be navigated.

[0150] Based on the above embodiments, the adaptive prediction step size generation module 530 is specifically used for:

[0151] According to the formula: The calculation of the unmanned surface platform within the preset sliding window Target path curvature ;

[0152] in, For the preset control cycle, It is a curvature-time function.

[0153] Based on the above embodiments, the adaptive prediction step size generation module 530 is specifically used for:

[0154] According to the formula: Calculate the dynamic prediction step size used in this round of trajectory tracking. ;

[0155] in, The preset sea state adjustment factor is L, where L is the waterline length of the unmanned surface platform. For the real-time speed of unmanned surface platforms, The preset base prediction step size, The preset minimum step size threshold, The Clip() function is used to set the preset maximum step size threshold. Constraints and between.

[0156] Based on the above embodiments, the optimal command generation module 550 is specifically used for:

[0157] A path tracking deviation optimization function is constructed based on the predicted motion state information and the reference path trajectory.

[0158] Under the constraints of state variables and control inputs, the optimal solution for the path tracking deviation optimization function is obtained by using an improved artificial bee colony algorithm, thus obtaining the optimal command rudder angle at the current moment.

[0159] Based on the above embodiments, the optimal command generation module 550 is specifically used for:

[0160] The optimal command rudder angle is input into the motion control system of the unmanned surface platform;

[0161] The motion control system controls the motion of the unmanned surface platform based on the optimal command rudder angle.

[0162] The trajectory tracking device based on dynamic prediction step size provided in the embodiments of the present invention can execute the trajectory tracking method based on dynamic prediction step size provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method execution.

[0163] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0164] Example 4

[0165] Figure 6 A schematic diagram of an electronic device 10, which can be used to implement embodiments of the present invention, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0166] like Figure 6 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0167] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0168] Processor 11 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, central processing unit (CPU), graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as performing a trajectory tracking method based on dynamic prediction step size as described in any embodiment of the present invention, i.e.:

[0169] During the autonomous navigation of the unmanned surface platform according to the reference path trajectory, the real-time operating status information of the unmanned surface platform at the current moment is obtained through at least one sensor carried on the platform.

[0170] Based on real-time operational status information and a pre-built nonlinear disturbance observer, real-time unknown time-varying disturbance information of the ocean at the current moment is obtained;

[0171] Based on the curvature time function determined by real-time operating status information and reference path trajectory, the target path curvature of the unmanned surface platform under the preset sliding window is calculated, and the dynamic prediction step size used for this round of trajectory tracking is calculated based on the target path curvature.

[0172] Based on real-time operational status information, real-time unknown time-varying disturbance information of the ocean, dynamic prediction step size and pre-built model prediction controller, the predicted motion status information of the surface unmanned platform at future moments with a dynamic prediction step size is obtained.

[0173] The optimal command rudder angle at the current moment is solved by using the path tracking deviation optimization function constructed based on the predicted motion state information and the reference path trajectory, and the motion control of the unmanned surface platform is performed based on the optimal command rudder angle.

[0174] Upon reaching the new current moment, return to execute the operation of acquiring the real-time operating status information of the unmanned surface platform at the current moment through at least one sensor carried on the platform, until the entire trajectory tracking process is completed.

[0175] In some embodiments, the path tracking method based on dynamic prediction step size as described in any of the embodiments of the present invention can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the path tracking method based on dynamic prediction step size as described above can be performed. Alternatively, in other embodiments, processor 11 can be configured by any other suitable means (e.g., by means of firmware) to perform the path tracking method based on dynamic prediction step size as described in any of the embodiments of the present invention.

[0176] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0177] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0178] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0179] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0180] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0181] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0182] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0183] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A trajectory tracking method based on dynamically predicted step size, executed by the main controller in an unmanned surface platform, the method comprising: During the autonomous navigation of the unmanned surface platform according to the reference path trajectory, the real-time operating status information of the unmanned surface platform at the current moment is obtained through at least one sensor carried on the platform. Based on real-time operational status information and a pre-built nonlinear disturbance observer, real-time unknown time-varying disturbance information of the ocean at the current moment is obtained; Based on the curvature time function determined by real-time operating status information and reference path trajectory, the target path curvature of the unmanned surface platform under the preset sliding window is calculated, and the dynamic prediction step size used for this round of trajectory tracking is calculated based on the target path curvature. Based on real-time operational status information, real-time unknown time-varying disturbance information of the ocean, dynamic prediction step size and pre-built model prediction controller, the predicted motion status information of the surface unmanned platform at future time points with a dynamic prediction step size is obtained. The optimal command rudder angle at the current moment is solved by using the path tracking deviation optimization function constructed based on the predicted motion state information and the reference path trajectory, and the motion control of the unmanned surface platform is performed based on the optimal command rudder angle. Upon reaching the new current moment, return to execute the operation of acquiring the real-time operating status information of the unmanned surface platform at the current moment through at least one sensor carried on the platform, until the entire trajectory tracking process is completed.

2. The method according to claim 1, characterized in that, Based on real-time operational status information and a pre-built nonlinear disturbance observer, real-time unknown time-varying disturbance information of the ocean at the current moment is obtained, including: From the real-time operational status information, the real-time lateral velocity v of the unmanned surface platform is extracted, and then calculated according to the formula... Calculate the nonlinear function in the nonlinear disturbance observer. ,in, This is a preset positive definite gain matrix; According to the formula: Calculate the real-time unknown time-varying disturbance information of the ocean at the current moment. Where z represents the internal state of the nonlinear disturbance observer at the current moment. ,in This is an estimate of the roll disturbance of the unmanned surface platform. This is an estimate of the pitch disturbance of the unmanned surface platform. This is an estimate of the heave disturbance of the unmanned surface platform. According to the formula: The internal state of the nonlinear disturbance observer is updated to obtain the observer's state at the next time step. For use in the next round of track tracking; in, Let M be the observer gain matrix, and M be a preset inertia matrix, which is a positive definite pairwise matrix. For Coriolis and, Here is the damping matrix. To control the input force.

3. The method according to claim 1, characterized in that, Before calculating the target path curvature of the unmanned surface platform within a preset sliding window based on the curvature-time function determined by real-time operational status information and reference path trajectory, the following steps are also included: Extract real-time location information and real-time speed from the real-time operational status information; Based on real-time location information and reference path trajectory, the sub-path to be navigated is determined, and the curvature time function is dynamically calculated based on real-time speed information and the sub-path to be navigated.

4. The method according to claim 3, characterized in that, Based on the curvature-time function determined by real-time operational status information and reference path trajectory, the target path curvature of the unmanned surface platform within a preset sliding window is calculated, including: According to the formula: The calculation of the unmanned surface platform within the preset sliding window Target path curvature ; in, For the preset control cycle, It is a curvature-time function. This is the index variable for the summation loop, used to iterate through each data point within the sliding window.

5. The method according to claim 3, characterized in that, Based on the target path curvature, calculate the dynamic prediction step size used in this round of trajectory tracking, including: According to the formula: Calculate the dynamic prediction step size used in this round of trajectory tracking. ; in, The preset sea state adjustment factor is L, where L is the waterline length of the unmanned surface platform. For the real-time speed of unmanned surface platforms, The preset base prediction step size, The preset minimum step size threshold, The Clip() function is used to set the preset maximum step size threshold. Constraints and between.

6. The method according to any one of claims 1-5, characterized in that, The optimal command rudder angle at the current moment is solved using a path tracking deviation optimization function constructed based on the predicted motion state information and the reference path trajectory, including: A path tracking deviation optimization function is constructed based on the predicted motion state information and the reference path trajectory. Under the constraints of state variables and control inputs, the optimal solution for the path tracking deviation optimization function is obtained by using an improved artificial bee colony algorithm, thus obtaining the optimal command rudder angle at the current moment.

7. The method according to any one of claims 1-5, characterized in that, Motion control of the unmanned surface platform is performed based on the optimal command rudder angle, including: The optimal command rudder angle is input into the motion control system of the unmanned surface platform; The motion control system controls the motion of the unmanned surface platform based on the optimal command rudder angle.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the trajectory tracking method based on dynamic prediction step size as described in any one of claims 1-7.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the trajectory tracking method based on dynamic prediction step size as described in any one of claims 1-7.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the trajectory tracking method based on dynamic prediction step size according to any one of claims 1-7.

Images