A ship intelligent interception trajectory planning method and device based on time-varying point positions

Abstract

This invention discloses a method and device for intelligent ship interception trajectory planning based on time-varying points, relating to the field of ship autonomous navigation planning and control technology. The method includes: acquiring and confirming the target ship to be intercepted and its navigation status information; establishing a pursuit circle for the target ship, and determining the current behavioral stage based on the positional relationship between the ship and the pursuit circle, whereby the behavioral stage may be a pursuit stage or an engagement stage; dynamically generating time-varying reference target points based on the current behavioral stage; and generating the ship's planned trajectory based on the reference target points using trajectory planning methods corresponding to the pursuit and engagement stages, respectively, and performing real-time tracking and control of the planned trajectory. This invention, by constructing a hierarchical planning framework and adjusting strategies in real time, is more suitable for intercepting highly dynamic scenarios, possessing advantages such as high real-time performance and high flexibility, while ensuring trajectory feasibility.

Description

Technical Field

[0001] This invention relates to the field of autonomous navigation planning and control technology for ships, specifically to a method and device for intelligent interception trajectory planning of ships based on time-varying points. Background Technology

[0002] Existing autonomous navigation systems for ships mainly include typical functions such as route planning and autonomous collision avoidance, and have been widely used. However, for certain unmanned surface vessels and law enforcement vessels that need to undertake target monitoring, tracking, and interception tasks, the functions of their autonomous navigation systems should be further expanded. In these tasks, the interception mission targets non-cooperative targets, and the autonomous navigation decision-making and planning algorithms are significantly different from conventional autonomous navigation algorithms that are mainly based on collision avoidance. There will be scenarios such as target movement confrontation and target malicious escape, requiring the design of countermeasure strategies tailored to the characteristics of the mission.

[0003] Existing research on interception missions often analogizes them to guidance problems, employing methods such as optimal control to control the target to reach a reference position within a set time by designing a controller. However, such methods suffer from complex controller designs, difficult parameter tuning, and insufficient adaptability to highly maneuverable targets. By designing the target location, the guidance problem can be transformed into a trajectory tracking problem. The future position of the target ship can be predicted, and path planning and trajectory planning algorithms can be used to plan the trajectory for the interception mission. The ship then achieves interception by tracking the reference trajectory. This method has strong capabilities in handling dynamic environments and generates stable trajectories, but some planning algorithms have low computational efficiency. Summary of the Invention

[0004] This invention provides a method and apparatus for intelligent interception trajectory planning of ships based on time-varying locations, which solves the problem of efficient and safe interception of moving targets in highly dynamic environments.

[0005] In a first aspect, the present invention provides a method for intelligent ship interception trajectory planning based on time-varying locations, comprising: Obtain and confirm the target vessel to be intercepted and its navigation status information; Establish a target vessel pursuit circle, and determine the current behavior stage based on the positional relationship between the ship and the pursuit circle. The behavior stage includes a pursuit stage or an confrontation stage. Based on the current stage of behavior, dynamically generate time-varying reference target points; Based on the reference target point, trajectory planning methods corresponding to the pursuit phase and the confrontation phase are adopted respectively to generate the planned trajectory of the ship, and the planned trajectory is tracked and controlled in real time.

[0006] In some instances, the pursuit circle is defined as: a pre-aiming interception threshold along the target vessel's course from its current position. With the center at point , and A circular region is formed with radius , where This is the velocity vector of the ship. For the target ship's velocity vector, In order to catch up with the interception threshold of the target vessel; If the ship is outside the pursuit circle, it is determined to be in the pursuit phase; If the ship is located within or on the pursuit circle, it is considered to be in the confrontation phase.

[0007] In some instances, during the pursuit phase, the reference target point is the point on the pursuit circle that is closest to the ship, and the azimuth of the reference target point satisfies a preset directional constraint to avoid head-on encounters and overtaking from behind. During the confrontation phase, the reference target point is determined based on the prediction of the target vessel's future trajectory and serves as a favorable interception point for seizure.

[0008] In some instances, the directional constraint is such that the angle θ between the reference target point and the bow of the target ship satisfies: θ∈[θmin,θmax], where θmin and θmax are preset angle thresholds, ensuring that the reference target point is located in the side area of ​​the target ship.

[0009] In some instances, a hierarchical trajectory planning method is employed during the pursuit phase, including: Based on static environmental information, a path search algorithm is used to plan a collision-free global path from the ship's position to the reference target point, and the path is then smoothed. Horizontal and vertical sampling is performed near the smoothed global path to generate multiple candidate trajectories. The optimal trajectory is selected as the planned trajectory by optimizing the cost function.

[0010] In some instances, the path search algorithm is algorithm; The smoothing process employs a Bezier curve fitting method. A fifth-order polynomial is used to perform parameterized fitting on the candidate trajectory.

[0011] In some instances, during the adversarial phase, a spatiotemporal joint trajectory planning method is employed, including: Based on the current state and kinematic constraints of the ship, construct the ship's reachable motion space for a period of time in the future, i.e., a three-dimensional spacetime cone. Spatiotemporal sampling is performed within the spatiotemporal three-dimensional cone to generate multiple candidate trajectories. The optimal trajectory that meets the interception requirements is selected as the planned trajectory through a multi-objective optimization evaluation function.

[0012] In some instances, the multi-objective optimization evaluation function includes at least an interception success rate evaluation term, a security evaluation term, and a maneuverability evaluation term.

[0013] In some instances, a trajectory feasibility verification step is included before outputting the planned trajectory. This step verifies whether the planned trajectory meets the ship's kinematic constraints, dynamic constraints, and collision avoidance safety constraints. If not, the trajectory is replanned.

[0014] Secondly, the present invention provides a ship intelligent interception trajectory planning device based on time-varying points, comprising: The perception module is used to acquire and confirm the target vessel to be intercepted and its navigation status information; The behavior determination module is used to establish a target vessel pursuit circle and determine the current behavior stage based on the positional relationship between the ship and the pursuit circle. The behavior stage includes a pursuit stage or an confrontation stage. The point generation module is used to dynamically generate time-varying reference target points based on the current behavior stage; The trajectory planning module is used to generate the planned trajectory of the ship based on the reference target point, using trajectory planning methods corresponding to the pursuit phase and the confrontation phase respectively. The tracking control module is used to perform real-time tracking control on the planned trajectory.

[0015] In summary, compared with the prior art, the above-described technical solutions conceived by this invention can achieve the following beneficial effects: This invention addresses the problem of efficient and safe interception of moving targets in highly dynamic environments by dividing the action phases using a pursuit circle model and combining it with a time-varying point dynamic generation and switching planning method. By constructing a hierarchical planning framework to adjust strategies in real time, this invention is more suitable for highly dynamic scenarios such as interception, possessing advantages of high real-time performance and flexibility, while ensuring trajectory feasibility. This invention can serve as a planning method for unmanned surface vessel (USV) interception missions, effectively supporting the realization of USV adversarial game theory, and can also provide auxiliary references for law enforcement vessel operators regarding heading and speed suggestions during interception operations, making it widely applicable to various maritime law enforcement scenarios. Attached Figure Description

[0016] 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.

[0017] Figure 1 This is a schematic diagram of a ship intelligent interception trajectory planning method based on time-varying points provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of a target ship pursuit circle provided by an embodiment of the present invention; Figure 3This is a schematic diagram of a reference target point setting during the pursuit phase provided by an embodiment of the present invention; Figure 4 This is a schematic diagram of a reference target point setting during the confrontation phase provided by an embodiment of the present invention; Figure 5 This is a schematic diagram of a pursuit and confrontation phase strategy provided by an embodiment of the present invention; Figure 6 This is a schematic diagram of a trajectory planning method for the pursuit phase provided by an embodiment of the present invention; Figure 7 This is a schematic diagram of an adversarial phase trajectory planning method provided by an embodiment of the present invention; Figure 8 This is a schematic diagram of an embodiment of the device provided in this invention. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. 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 are within the scope of protection of the present invention.

[0019] In the following description, specific embodiments of the invention will be illustrated with reference to steps and symbols performed by one or more computers, unless otherwise stated. Therefore, these steps and operations will be referred to several times as being performed by a computer, and computer execution as referred to herein includes operations by a computer processing unit representing electronic signals of data in a structured format. This operation transforms the data or maintains it at a location in the computer's memory system, which can be reconfigured or otherwise alter the operation of the computer in a manner well known to those skilled in the art. The data structure maintained by the data is the physical location of the memory, which has specific characteristics defined by the data format. However, the principles of the invention described above are not intended to be limiting, and those skilled in the art will understand that many of the following steps and operations can also be implemented in hardware.

[0020] The terms "module" or "unit" as used herein can be considered as software objects executing on the computing system. Different components, modules, engines, and services described herein can be considered as implementations on the computing system. The apparatus and methods described herein are preferably implemented in software, but can also be implemented in hardware, both of which are within the scope of this invention.

[0021] Those skilled in the art will understand that, unless specifically stated otherwise, the singular forms “a,” “an,” and “the” used herein may also include the plural forms. It should be further understood that the term “comprising” as used in this specification means the presence of features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. It should be understood that when we say an element is “connected” or “coupled” to another element, it can be directly connected or coupled to the other element, or there may be intermediate elements. Furthermore, “connected” or “coupled” as used herein can include wireless connections or wireless coupling. The term “and / or” as used herein includes all or any units and all combinations of one or more associated listed items.

[0022] In embodiments of the present invention, such as Figure 1 As shown, a method for intelligent ship interception trajectory planning based on time-varying points is provided, including the following steps: S1: Target Status Awareness. The awareness system acquires target instances within the scene, confirms the target vessel to be intercepted, and obtains its navigation status information; The perception system integrates the outputs from shipboard radar, cameras, and the Automatic Identification System (AIS) to obtain fused situational information about each target within the perception range. Users then set up interception tasks, specifying the target vessel to be intercepted and acquiring its navigation status information.

[0023] Furthermore, in step S1, the surrounding dynamic objects are accurately tracked and their states estimated by the perception system deployed on the ship (the controlled ship), and the ship to be intercepted is selected by the personnel on board from the target results and set as the interception target.

[0024] The perception system utilizes a multi-sensor system (such as navigation radar, millimeter-wave radar, lidar, visual cameras, and AIS automatic identification system) to perceive the surrounding environment in real time, detecting the position and heading of targets on the sea surface around the vessel (the controlled vessel). Based on multi-source sensor fusion technology, the detection results are fused in real time to construct a target motion model for estimating the navigation state of each detected target, denoted as a constant turn rate and velocity (CTRV) model. Specifically, it is expressed as follows:

[0025] in, The x-axis is... The vertical axis is , This is the yaw angle. From... Time's up The time interval is , The target speed at any given time is angular velocity is Therefore, the state variable is defined as follows: .

[0026] The system performs correlated tracking of target results from multiple sensors and multiple frames. For example, it uses the Hungarian algorithm to correlate results based on features such as target distance and size, and employs state estimation methods such as extended Kalman filtering to fuse and calculate the motion parameters (including position, velocity, and heading) of each target, achieving accurate state perception and trajectory prediction of the target vessel. Finally, the perception results are integrated into a target instance list and pushed to the bridge software on the control console.

[0027] In this process, the user selects a single target from the target instances displayed on the bridge control console as the target vessel to be intercepted. The system reads dynamic data such as the target's position, speed, heading, and predicted trajectory for the next N steps from the perception system results, which are then used for subsequent trajectory planning.

[0028] S2: Behavioral Phase Determination. Establish a target vessel pursuit circle and determine the behavioral phase of the interception mission. The behavioral phase includes the pursuit phase and the confrontation phase; In the Cartesian coordinate system O-xy, a ship motion model is established, modeling both the ship and the target ship as point masses with no difference in shape or size. The position of the ship is denoted as... The velocity vector is The target vessel's location is The velocity vector is Set the interception threshold for the target ship that is expected to be caught up with. Pre-aiming distance forward from the target vessel's current position. At the point where the center of the circle is pursued, it is defined as:

[0029] The set of positions satisfying the above formula is the pursuit circle, where This is the distance from the point to the center of the pursuing circle. For example... Figure 2 As shown. If the target ship has not yet entered the pursuit circle, it is in the pursuit phase. If the target ship has entered the pursuit circle, it is in the confrontation phase. The pursuit circle means: if the ship is on the pursuit circle, it can catch up with the target ship at the center of the pursuit circle by maintaining the current speed and course.

[0030] By the position of this ship By determining the phase of the mission based on its positional relationship with the pursuit circle, the mission can be divided into a pursuit phase and a confrontation phase.

[0031] When the following condition is met, the pursuit phase is determined:

[0032] At this point, the ship has not yet entered the pursuit circle. The ship needs to adjust its course / speed to enter the pursuit circle area and reach a certain range in its vicinity.

[0033] When the following condition is met, the game is considered to be in the adversarial phase:

[0034] At this point, the ship has entered the pursuit circle and is considered to have entered the effective interception range, meeting the conditions for confrontation, and will carry out the confrontation mission.

[0035] S3: Dynamic setting of time-varying points. Based on the action phase (pursuit / confrontation), time-varying points are dynamically generated. These points represent reference positions that are dynamically updated according to the target ship's movement state and are used to guide the ship's course. During the pursuit phase, the position and angle of the reference target are determined based on the range of the pursuit circle. The current position of the ship is then calculated based on the pursuit circle model. The shortest path to the boundary point of the pursuit circle is used, and the point on the pursuit circle closest to the ship is set as the reference target point. To avoid head-on encounters and overtaking from behind, pursuit is preferred from the port and starboard sides. The reference target point is set as follows: Figure 3 As shown.

[0036] Set reference target point constraints: 1. Distance constraint: Reference target point P, coordinates are ,satisfy:

[0037] in To pursue the center of the circle; 2. Directional constraint: Refer to the azimuth of the target point. The azimuth of the target ship's bow direction is ,satisfy:

[0038] To avoid a head-on confrontation and being overtaken from behind.

[0039] During the confrontation phase, the ship's final position is determined based on the target ship's predicted trajectory and pre-aiming time. The area where the ship has seized a favorable position is selected as the ship's final position, with reference to the target point settings as follows: Figure 4 As shown, the waters surrounding the target vessel are divided into four quadrants based on its bow and stern lines and its transverse bearing. Generally, the vessel should prioritize occupying the position forward of the target's transverse bearing (i.e., quadrants I and IV). Once this position is successfully secured, the intercepting vessel can maintain the same direction and speed as the target, or slightly deviate from the target's course, to establish an interception posture.

[0040] S4: Trajectory Planning for Different Behavioral Stages. Based on time-varying locations, corresponding trajectory planning methods are adopted according to different behavioral stages (pursuit / confrontation). Furthermore, in step S4, each stage has its corresponding trajectory planning method. The trajectory planning method strategy is as follows: Figure 5 As shown.

[0041] During the pursuit phase, Figure 6 This diagram illustrates a trajectory planning method for the pursuit phase. Real-time online path planning is performed based on the dynamic changes of the target vessel and its surrounding environment. Replanning is divided into low-frequency replanning and high-frequency replanning. Low-frequency online replanning considers the constraints of static obstacles in the nautical chart and sensor data, providing a smooth, collision-free reference path and avoiding redundant calculations. High-frequency online replanning can quickly adjust speed or replan the path when new obstacles or hazards are detected to avoid collisions and improve real-time response capabilities.

[0042] Specifically, low-frequency replanning refers to path planning based on static obstacles and chart information, with a low update frequency (e.g., 1Hz).

[0043] High-frequency replanning refers to trajectory adjustments based on dynamic obstacles and real-time perception, with a high update frequency (e.g., 10Hz).

[0044] When performing low-frequency online replanning, use The path planning algorithm is used to find the path between the ship and the reference target point. It is a heuristic algorithm and an efficient and direct search method for finding the shortest path in static networks. When planning a path, the algorithm uses a heuristic function based on the current state of the point to calculate the possible nodes for the next time step, and selects the point that minimizes the function cost as the next node. The heuristic function of an algorithm can usually be expressed as:

[0045] In the formula, n represents the current node, f represents the minimum cost estimate for the point, g represents the minimum cost from the corresponding point to the starting point, and h represents the minimum cost estimate from the corresponding point to the ending point. When applying path planning, g(n) and h(n) are generally distance functions.

[0046] The electronic nautical chart is processed to generate a two-dimensional raster map. Navigable and non-navigable areas are marked with 0 and 1 respectively, and then applied... The algorithm finds a collision-free path from the starting point to the ending point. The paths generated by the algorithm are often formed by connecting a series of adjacent grid center points. These paths are not smooth enough and will significantly impact the stability of the ship's motion. Bézier curves can create smooth curves and surfaces, thus... The algorithm, combined with the Bézier curve algorithm, can effectively solve the problem. The problem is that the path generated by the algorithm is not smooth enough.

[0047] Bézier curves are a class of curves formed by multiple control points, with their shape determined by these control points. A Bézier curve that passes only through the first and last control points, but not through any intermediate control points, is called an (n-1)-th degree Bézier curve. The parametric curve of each point on an n-th degree Bézier curve can be represented as:

[0048] In the formula, t represents the normalized time variable, 0 <t<1; These are the control points of the Bézier curve. Let represent the Bessel basis function of degree n.

[0049]

[0050] A quartic Bézier curve can be determined using only 5 control points. Therefore, we first solve for the planar coordinates of the 5 control points and then parametrically represent the curve. The key points returned by the algorithm are used as control points for the Bézier curve, and the route is locally optimized using a quartic Bézier curve. For each local Bézier curve, the objective function is to minimize the average curvature of the path, and parameters are optimized to address the issue of uneven path smoothness at inflection points. Finally, the path smoothed using the Bézier curve method is output as a reference path for low-frequency replanning.

[0051] After receiving the reference path from the low-frequency replanning, the high-frequency online replanning method uses a sampling-based trajectory planning method to determine the trajectory that satisfies the manipulation constraints. Based on the Bellman optimality principle, an optimal control problem is constructed. Given... The initial state at time (representing displacement, velocity, and acceleration along the reference path, respectively), and Termination state of time Given any function and ,and Minimize the cost function:

[0052] The cost function can be composed of sub-terms such as minimizing time, minimizing end-position error, and minimizing jerk during the process. It can be proven that the solution to this optimization problem is a fifth-order polynomial problem, and subsequent trajectory optimization can be based on the fifth-order polynomial.

[0053] Lateral sampling is performed by setting different endpoint points near the reference path. Longitudinal sampling is performed by setting different positions, velocities, accelerations, and times. The lateral and longitudinal samples are combined to form a candidate trajectory cluster, and a fifth-order polynomial fitting method is used to plan the trajectory. Finally, the optimal trajectory is selected by scoring the trajectories. Scoring criteria may include trajectory curvature, speed, and acceleration / deceleration frequency. Additional constraints can be added when combining candidate trajectory clusters and defining scoring criteria to determine the trajectory that satisfies these constraints.

[0054] During the confrontation phase, Figure 7 This diagram illustrates a trajectory planning method for the adversarial phase. The adversarial process between the ship and the target ship requires the integration of multiple factors to ensure navigational safety and mission completion. First, it is necessary to monitor the target ship's position, heading, and speed in real time to predict its future trajectory and determine the ship's position and heading in the terminal state, providing a basis for path planning. Second, because interception missions against non-cooperative targets are highly adversarial, the planning of the ship's path must consider both time and space constraints, employing spatiotemporal joint planning. The spatiotemporal joint planning method considers both spatial (position, direction) and temporal (velocity, acceleration, time) dimensions when planning the path, comprehensively optimizing multiple objectives such as path length, travel time, and energy consumption to generate a feasible path that meets the mission objective (denial) and avoids collision.

[0055] After determining the initial and final states of the ship using S4, the ship's achievable motion space under the constraints of maximum acceleration and maximum turning rate can be calculated. This space constitutes the ship's motion planning space, referred to as the spatiotemporal three-dimensional cone. It represents the achievable motion range in the time-space three-dimensional coordinate system under the ship's motion constraints (maximum acceleration and turning rate). The spatiotemporal three-dimensional cone consists of the range achievable with maximum acceleration and maximum turning rate after determining the final state, the range achievable with maximum acceleration and maximum turning rate after determining the initial state, and the regional range within this range. Finally, within the spatiotemporal three-dimensional cone, the ship's trajectory satisfying the maneuvering constraints is determined using the aforementioned sampling-based trajectory planning method.

[0056] The method for constructing the spatiotemporal three-dimensional cone is as follows: Let the current state of this ship be... The terminal state is The maximum acceleration is Maximum steering ratio .

[0057] In time Within the vessel, the reachable range in position space is a gradually expanding conical region, the boundaries of which are determined by extreme maneuvers (maximum acceleration, maximum steering).

[0058] The mathematical model of the spacetime three-dimensional cone can be expressed as:

[0059] in, It is calculated from the kinematic equations under extreme control conditions.

[0060] S5: Trajectory Tracking. A trajectory tracking algorithm enables real-time tracking of the planned trajectory, correcting deviations between the actual flight path and the planned trajectory.

[0061] A closed-loop feedback control mechanism is adopted to obtain the trajectory reference point on the trajectory. Combined with the ship dynamics model (such as the six-degree-of-freedom motion equation) and sensor data, the deviation between the current ship state and the target trajectory is calculated in real time. A proportional-integral-derivative PID controller is used to solve and adjust the actuator parameters such as rudder angle and thrust to achieve tracking of the reference trajectory.

[0062] In summary, the trajectory of the target vessel is time-varying, requiring real-time prediction of its future position. By transforming the problem into a path planning and tracking problem for time-varying points, a sampling-based trajectory planning method and a spatiotemporal three-dimensional cone-based trajectory planning method are employed in the pursuit and confrontation phases, respectively, ultimately achieving the interception of the moving target. The method proposed in this embodiment of the invention has advantages such as high real-time performance and high flexibility.

[0063] In another embodiment of the present invention, to facilitate better implementation of the method provided in the embodiments of the present invention, an apparatus based on the above method is also provided. The meanings of the terms used are the same as in the above method, and specific implementation details can be found in the description of the method embodiments.

[0064] Please see Figure 8 , Figure 8 This is a schematic diagram of the structure of a device provided in an embodiment of the present invention. The device may include a sensing module 801, a behavior judgment module 802, a point generation module 803, a trajectory planning module 804, and a tracking control module 805, wherein: The perception module 801 is used to acquire and confirm the target vessel to be intercepted and its navigation status information; The behavior judgment module 802 is used to establish a target vessel pursuit circle and determine the current behavior stage based on the positional relationship between the ship and the pursuit circle. The behavior stage includes a pursuit stage or an confrontation stage. The point generation module 803 is used to dynamically generate time-varying reference target points based on the current behavior stage; The trajectory planning module 804 is used to generate the planned trajectory of the ship based on the reference target point, using trajectory planning methods corresponding to the pursuit phase and the confrontation phase respectively. The tracking control module 805 is used to perform real-time tracking control on the planned trajectory.

[0065] In another specific example, the point generation module dynamically generates time-varying reference target points based on the current action phase. The goal of the pursuit phase is to approach the target ship via the shortest, fastest, and collision-free path. During the pursuit phase, the point on the pursuit circle closest to the current ship is set as the reference target point. To avoid head-on encounters and overtaking from behind, the pursuit range is limited to the port and starboard sides.

[0066] The objective of the confrontation phase is to predict the target ship's path and seize the interception point. During this phase, an extended Kalman filter is used to predict the target ship's future trajectory, and the terminal state of the ship is determined based on the predicted trajectory and pre-aiming time, which is then set as a reference target point. The reference target point dynamically changes according to the target ship's navigation state.

[0067] In another specific example, within the trajectory planning module, real-time online planning is performed based on the current behavioral stage and the time-varying reference target point. During the pursuit phase, online replanning is divided into low-frequency and high-frequency replanning. Low-frequency online replanning considers the constraints of static obstacles in the nautical chart and perception, and employs... The path planning algorithm provides a smooth, collision-free reference path. High-frequency online replanning uses a sampling-based trajectory planning method, which can quickly adjust speed or replan the path when new obstacles or hazards are detected, thus improving real-time response capabilities.

[0068] During the confrontation phase, based on the ship's motion state and the time-varying reference target point, a space of motion for the ship under constraints such as maximum acceleration and maximum turning rate is constructed, which is called a spatiotemporal three-dimensional cone. Within the spatiotemporal three-dimensional cone, considering both spatial and temporal dimensions, spatiotemporal joint planning under multi-objective constraints is carried out to determine the ship's trajectory that satisfies the mission objectives and maneuvering constraints.

[0069] In another specific example, the tracking control module uses a trajectory tracking algorithm to achieve real-time tracking of the planned trajectory and correct deviations between the actual and planned trajectories. A closed-loop feedback control mechanism is employed, combining ship dynamics models (such as six-degree-of-freedom equations of motion) and sensor data to calculate the deviation between the current ship state and the target trajectory in real time. This allows for the calculation and adjustment of actuator parameters such as rudder angle and thrust, ultimately achieving tracking of the reference trajectory.

[0070] The above provides a detailed description of a ship intelligent interception trajectory planning method and device based on time-varying point locations provided by the embodiments of the present invention. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for intelligent ship interception trajectory planning based on time-varying locations, characterized in that, include: Obtain and confirm the target vessel to be intercepted and its navigation status information; Establish a target vessel pursuit circle, and determine the current behavior stage based on the positional relationship between the ship and the pursuit circle. The behavior stage includes a pursuit stage or an confrontation stage. Based on the current stage of behavior, dynamically generate time-varying reference target points; Based on the reference target point, trajectory planning methods corresponding to the pursuit phase and the confrontation phase are adopted respectively to generate the planned trajectory of the ship, and the planned trajectory is tracked and controlled in real time.

2. The method according to claim 1, characterized in that, The pursuit circle is defined as: a pre-aiming interception threshold along the target vessel's course from its current position. With the center of the circle, A circular region is formed with radius , where This is the velocity vector of the ship. The target ship's velocity vector, In order to catch up with the interception threshold of the target vessel; If the ship is outside the pursuit circle, it is determined to be in the pursuit phase; If the ship is located within or on the pursuit circle, it is considered to be in the confrontation phase.

3. The method according to claim 2, characterized in that, During the pursuit phase, the reference target point is the point on the pursuit circle that is closest to the ship, and the azimuth of the reference target point satisfies the preset directional constraints to avoid head-on encounters and overtaking from behind. During the confrontation phase, the reference target point is determined based on the prediction of the target vessel's future trajectory and serves as a favorable interception point for seizure.

4. The method according to claim 3, characterized in that, The directional constraint is to ensure that the angle θ between the reference target point and the bow of the target ship satisfies: θ∈[θmin,θmax], where θmin and θmax are preset angle thresholds, ensuring that the reference target point is located in the side area of ​​the target ship.

5. The method according to claim 4, characterized in that, During the pursuit phase, a hierarchical trajectory planning method is employed, including: Based on static environmental information, a path search algorithm is used to plan a collision-free global path from the ship's position to the reference target point, and the path is then smoothed. Horizontal and vertical sampling is performed near the smoothed global path to generate multiple candidate trajectories. The optimal trajectory is selected as the planned trajectory by optimizing the cost function.

6. The method according to claim 5, characterized in that, The path search algorithm is as follows: algorithm; The smoothing process employs a Bezier curve fitting method. A fifth-order polynomial is used to perform parameterized fitting on the candidate trajectory.

7. The method according to claim 6, characterized in that, In the aforementioned adversarial phase, a spatiotemporal joint trajectory planning method is employed, including: Based on the current state and kinematic constraints of the ship, construct the ship's reachable motion space for a period of time in the future, i.e., a three-dimensional spacetime cone. Spatiotemporal sampling is performed within the spatiotemporal three-dimensional cone to generate multiple candidate trajectories. The optimal trajectory that meets the interception requirements is selected as the planned trajectory through a multi-objective optimization evaluation function.

8. The method according to claim 7, characterized in that, The multi-objective optimization evaluation function includes at least an interception success rate evaluation item, a security evaluation item, and a maneuverability evaluation item.

9. The method according to claim 1, characterized in that, Before outputting the planned trajectory, a trajectory feasibility verification step is also included to verify whether the planned trajectory meets the ship's kinematic constraints, dynamic constraints and collision avoidance safety constraints. If not, the trajectory is replanned.

10. A ship intelligent interception trajectory planning device based on time-varying points, characterized in that, include: The perception module is used to acquire and confirm the target vessel to be intercepted and its navigation status information; The behavior determination module is used to establish a target vessel pursuit circle and determine the current behavior stage based on the positional relationship between the ship and the pursuit circle. The behavior stage includes a pursuit stage or an confrontation stage. The point generation module is used to dynamically generate time-varying reference target points based on the current behavior stage; The trajectory planning module is used to generate the planned trajectory of the ship based on the reference target point, using trajectory planning methods corresponding to the pursuit phase and the confrontation phase respectively. The tracking control module is used to perform real-time tracking control on the planned trajectory.

Images