An unmanned ship unmanned aerial vehicle cooperative cruising method, device, equipment and medium

Abstract

The present application relates to a kind of unmanned ship unmanned aerial vehicle cooperative cruise method, device, equipment and medium, belong to trajectory planning technical field, unmanned ship unmanned aerial vehicle cooperative cruise method constructs time-varying wind and current environment model, constructs ship dynamics model considering the influence of uncertain factor based on time-varying wind and current environment model;Based on ship dynamics model and obstacle data, obtain the planning trajectory of unmanned ship;Comprehensive cost function is constructed, with comprehensive cost function as the fitness function of chaos optimization particle swarm algorithm, the planning trajectory of unmanned ship is optimized using chaos optimization particle swarm algorithm, obtain the global optimal planning path of unmanned ship;Based on the starting point, target point and wind field data of unmanned aerial vehicle, the three-dimensional path of unmanned aerial vehicle is planned using dandelion optimization algorithm, obtain the planning trajectory of unmanned aerial vehicle;To realize autonomous cooperative cruise under complex environment, reduce the time of path planning, improve the positioning accuracy of unmanned aerial vehicle.

Description

Technical Field

[0001] This invention relates to the field of trajectory planning technology, and in particular to a method, apparatus, equipment and medium for cooperative cruising of unmanned ships and drones. Background Technology

[0002] Unmanned surface vessel and drone (USV) patrols focus on addressing the challenges of vessel-drone patrols caused by uncertainties in complex aquatic environments.

[0003] Existing unmanned surface vessel (USV) path planning algorithms suffer from problems such as long processing time and rigid path generation when facing uncertainties (wind, waves, and current interference). Meanwhile, existing unmanned aerial vehicle (UAV) path planning algorithms face difficulties in acquiring real-time data when facing uncertainties (complex terrain and weather changes), which leads to a significant decrease in the accuracy of UAV visual positioning. Summary of the Invention

[0004] In view of this, it is necessary to provide a method, device, equipment and medium for unmanned surface vessel and unmanned aerial vehicle (UAV) cooperative cruise, in order to solve the technical problems of long path planning time for UAV and low positioning accuracy of UAV under the influence of uncertain factors when UAV and UAV are cooperatively cruised.

[0005] To address the aforementioned problems, in a first aspect, the present invention provides a method for cooperative cruising of unmanned surface vessels and unmanned aerial vehicles, comprising:

[0006] A time-varying wind, wave, and current environment model is constructed based on the acquired real-time wind, wave, and current data. A ship dynamics model considering the influence of uncertain factors is then constructed based on the time-varying wind, wave, and current environment model.

[0007] The planned trajectory of the unmanned vessel is obtained based on the starting point, target point, ship dynamics model, and obstacle data collected in real time by the UAV. A comprehensive cost function considering path length, travel time, wave influence, and water flow influence is constructed. The comprehensive cost function is used as the fitness function of the chaotic optimization particle swarm algorithm. The chaotic optimization particle swarm algorithm is used to optimize the planned trajectory of the unmanned vessel to obtain the globally optimal planned path of the unmanned vessel.

[0008] The wind field data collected in real time by the unmanned vessel is obtained. Based on the starting point, target point and wind field data of the UAV, the dandelion optimization algorithm is used to plan the three-dimensional path of the UAV to obtain the planned trajectory of the UAV.

[0009] Autonomous collaborative cruising in complex environments is achieved based on the globally optimal planned path of the unmanned vessel and the planned trajectory of the unmanned aerial vehicle.

[0010] In one possible implementation, the time-varying wind, wave, and flow environment model is as follows:

[0011] ,

[0012] ,

[0013] ,

[0014] in, Due to the influence of wind, Due to the influence of waves, Due to the influence of water flow, For wind speed, For wind direction, The heading angle of the unmanned vessel. Wave height The direction of the wave. For water flow velocity, For flow direction;

[0015] The ship dynamics model is as follows:

[0016] ,

[0017] ,

[0018] ,

[0019] ,

[0020] in, for The state vector of the unmanned ship at any given time. for The control input vector of the unmanned surface vessel at any given time. External disturbances Let x be the x-coordinate of the unmanned surface vessel's position. Let be the ordinate of the unmanned surface vessel's position. For the unmanned ship's speed, As the rudder angle, For propulsion, This is a transpose.

[0021] In one possible implementation, the comprehensive cost function is:

[0022] ,

[0023] ,

[0024] ,

[0025] in, For the comprehensive cost function, This is the total path length. Total sailing time For the first Wave encounter angle cost at each path node For the first The cost of water flow at each path node The angle between the heading and the wave direction. , , , These are the weighting coefficients. These are the weighting coefficients. , These are the weighting coefficients. For water flow velocity, This indicates the direction of water flow.

[0026] In one possible implementation, the step of using the comprehensive cost function as the fitness function of the chaotic optimized particle swarm optimization algorithm, and optimizing the planned trajectory of the unmanned vessel using the chaotic optimized particle swarm optimization algorithm to obtain the globally optimal planned path of the unmanned vessel, includes:

[0027] Set the initial values ​​and control parameters for the chaotic optimization particle swarm algorithm;

[0028] A chaotic sequence is generated based on the initial values ​​and control parameters;

[0029] The particle swarm of the chaotic optimization particle swarm algorithm is initialized based on the planned trajectory of the unmanned vessel and the chaotic sequence to obtain the particle velocity and particle position.

[0030] The fitness value of the particle swarm is determined based on the comprehensive cost function;

[0031] The fitness values ​​of the particle swarm are filtered using an elite adaptive truncation average update strategy to obtain elite particles;

[0032] The particle position and particle velocity are updated based on the fitness value of the elite particles and the chaotic sequence to obtain the individual optimal solution of the particles and the global optimal solution of the population particles.

[0033] The optimal total path length and total travel time are determined based on the individual optimal solution and the global optimal solution. The global optimal planned path of the unmanned vessel is obtained based on the optimal total path length and total travel time.

[0034] In one possible implementation, the dandelion optimization algorithm includes an ascent phase, a decay phase, and a landing phase; the step of using the dandelion optimization algorithm to plan the three-dimensional path of the UAV based on the UAV's starting point, target point, and wind field data to obtain the UAV's planned trajectory includes:

[0035] A three-dimensional spatial model is constructed based on the starting point, target point, obstacles, and wind field vector of the UAV;

[0036] The seed group of the dandelion optimization algorithm is initialized based on the three-dimensional spatial model, wherein each seed corresponds to a path.

[0037] During the ascent phase, after updating the velocity and position of the seeds, the fitness value of each seed is calculated, and the seeds are evaluated based on the fitness value of each seed to determine the optimal solution region.

[0038] During the decay phase, the fitness value of the seed in the optimal solution region is determined, and the search range is dynamically adjusted based on the fitness value of the seed, wherein the influence of wind field and path length are balanced by dynamic weighting.

[0039] During the landing phase, a refined search is conducted near the target point to obtain the optimal solution, and the planned trajectory of the UAV is determined based on the optimal solution.

[0040] In one possible implementation, the seed speed is updated as follows:

[0041] ,

[0042] in, for During the nth iteration The seed of the first Dimensional speed, For inertial weights, , , For acceleration coefficient, , , It is a random number. for The global optimal position at the next iteration. for During the nth iteration The optimal location for each seed for During the nth iteration The seed of the first Dimensional position, The influence of wind;

[0043] The position of the seed is updated as follows:

[0044] ,

[0045] in, for During the nth iteration The seed of the first Dimensional position.

[0046] In one possible implementation, the autonomous cooperative cruise in complex environments based on the globally optimal planned path of the unmanned vessel and the planned trajectory of the unmanned aerial vehicle includes:

[0047] When an emergency is detected, the target point of the UAV is determined based on the globally optimal planned path of the unmanned vessel, and the planned trajectory of the UAV is updated based on the target point, so that the UAV can land accurately on the unmanned vessel.

[0048] Secondly, the present invention also provides a collaborative patrol device for unmanned ships and unmanned aerial vehicles, comprising:

[0049] The dynamic model construction module is used to construct a time-varying wind, wave and flow environment model based on the acquired real-time wind, wave and flow data, and to construct a ship dynamics model considering the influence of uncertain factors based on the time-varying wind, wave and flow environment model.

[0050] The unmanned vessel path optimization module is used to obtain the planned trajectory of the unmanned vessel based on the starting point, target point, ship dynamics model, and obstacle data collected in real time by the UAV. It constructs a comprehensive cost function that considers path length, travel time, wave influence, and water flow influence. The comprehensive cost function is used as the fitness function of the chaotic optimization particle swarm algorithm. The chaotic optimization particle swarm algorithm is used to optimize the planned trajectory of the unmanned vessel to obtain the globally optimal planned path of the unmanned vessel.

[0051] The UAV path planning module is used to acquire wind field data collected in real time by the unmanned vessel. Based on the UAV's starting point, target point, and wind field data, the dandelion optimization algorithm is used to plan the UAV's three-dimensional path to obtain the UAV's planned trajectory.

[0052] The cooperative cruise module is used to achieve autonomous cooperative cruise in complex environments based on the globally optimal planned path of the unmanned vessel and the planned trajectory of the UAV landing.

[0053] Thirdly, the present invention also provides an electronic device, comprising: a processor and a memory;

[0054] The memory stores a computer-readable program that can be executed by the processor;

[0055] When the processor executes the computer-readable program, it implements the steps in the unmanned ship / unmanned aerial vehicle cooperative cruise method described above.

[0056] Fourthly, the present invention also provides a computer-readable storage medium for storing a computer-readable program or instruction, which, when executed by a processor, can implement the steps in the unmanned vessel / unmanned aerial vehicle cooperative cruise method described in any of the above-mentioned method items.

[0057] The beneficial effects of this invention are as follows: A comprehensive cost function considering path length, travel time, wave influence, and water flow influence is constructed. This comprehensive cost function serves as the fitness function for a chaotic optimization particle swarm optimization algorithm. The chaotic optimization particle swarm optimization algorithm optimizes the planned trajectory of the unmanned surface vessel (USV) to obtain the globally optimal planned path. By coupling the cost function with the environment through particle selection, the chaotic optimization particle swarm optimization algorithm prioritizes path solutions adapted to real-time wind and waves, reducing the path planning time of the USV under the influence of uncertain factors. Real-time wind field data collected by the USV is acquired. Based on the USV's starting point, target point, and wind field data, the dandelion optimization algorithm is used to plan the USV's three-dimensional path, obtaining the USV's planned trajectory. The dandelion optimization algorithm improves the USV's positioning accuracy under the influence of uncertain factors. Autonomous collaborative cruising in complex environments is achieved based on the globally optimal planned path of the USV and the planned landing trajectory of the USV. Global environmental perception is achieved through environmental data collected by the USV and USV, thus realizing collaborative cruising between the USV and USV. Attached Figure Description

[0058] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the 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.

[0059] Figure 1 A flowchart illustrating an embodiment of the unmanned vessel and unmanned aerial vehicle cooperative cruise method provided by the present invention;

[0060] Figure 2 A schematic diagram comparing the robust route trajectory map and the optimized trajectory of the unmanned ship and unmanned aerial vehicle cooperative cruise method provided by the present invention;

[0061] Figure 3 A schematic diagram of the entire process of unmanned vessel and unmanned ship collaborative operation in the unmanned ship and unmanned vessel collaborative patrol method provided by the present invention;

[0062] Figure 4 A schematic diagram of the UAV take-off and landing platform for the unmanned vessel and unmanned aerial vehicle cooperative cruise method provided by the present invention;

[0063] Figure 5 A schematic diagram of a structure of an embodiment of the unmanned ship and unmanned aerial vehicle cooperative cruise device provided by the present invention;

[0064] Figure 6 A schematic diagram of an embodiment of the electronic device provided by the present invention. Detailed Implementation

[0065] Preferred embodiments of the present invention will now be described in detail with reference to the accompanying drawings, which form part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not intended to limit the scope of the present invention.

[0066] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0067] This invention discloses a method, apparatus, device, and medium for cooperative cruise of unmanned surface vessels and unmanned aerial vehicles (UAVs), which can be used in a computer. The method, apparatus, or computer-readable storage medium involved in this invention can be integrated with the aforementioned devices or can be relatively independent.

[0068] One specific embodiment of the present invention discloses a method for cooperative cruising between unmanned surface vessels and unmanned aerial vehicles (UAVs), which can be executed by a computer, specifically by one or more processors of that computer. For example... Figure 1 As shown, the unmanned surface vessel and unmanned aerial vehicle (UAV) cooperative cruise method includes:

[0069] S101. Construct a time-varying wind, wave and current environment model based on the acquired real-time wind, wave and current data, and construct a ship dynamics model considering the influence of uncertain factors based on the time-varying wind, wave and current environment model.

[0070] It should be noted that by constructing a ship dynamics model, the relationship between the unmanned vessel's state variables such as position, velocity, and acceleration and the control inputs is described.

[0071] S102. Based on the starting point, target point, ship dynamics model, and obstacle data collected in real time by the UAV, the planned trajectory of the UAV is obtained. A comprehensive cost function considering path length, travel time, wave influence, and water flow influence is constructed. The comprehensive cost function is used as the fitness function of the chaotic optimization particle swarm algorithm. The chaotic optimization particle swarm algorithm is used to optimize the planned trajectory of the UAV and obtain the globally optimal planned path of the UAV.

[0072] It should be noted that the chaotic optimization particle swarm optimization algorithm is used to optimize the planned trajectory of the unmanned vessel, taking into account the impact of changes in uncertain factors on the planned trajectory of the vessel, thus reducing the path planning time of the unmanned vessel.

[0073] S103. Obtain wind field data collected in real time by the unmanned vessel. Based on the starting point, target point and wind field data of the UAV, use the dandelion optimization algorithm to plan the three-dimensional path of the UAV and obtain the planned trajectory of the UAV.

[0074] It should be noted that using the dandelion optimization algorithm to plan the three-dimensional path of the UAV improves the UAV's anti-interference ability and positioning accuracy under the influence of uncertain factors.

[0075] S104. Autonomous collaborative cruising in complex environments is achieved based on the global optimal planning path of unmanned ships and the planning trajectory of UAV landing.

[0076] It should be noted that by receiving obstacle data collected in real time by drones from unmanned surface vessels (USVs) and wind field data collected in real time by USVs from USVs, the entire environment can be perceived, enabling coordinated patrols by USVs and drones.

[0077] In some embodiments, in step S101, a time-varying wind, wave, and current environment model is constructed based on the acquired real-time wind, wave, and current data. Based on this model, a ship dynamics model considering the influence of uncertain factors is constructed. The unmanned surface vessel (USV) is equipped with an RTK-GPS positioning unit to upload real-time high-precision positioning data. Real-time wind, wave, and current data are collected using onboard sensors such as current meters, wave height meters, weather radar, and lidar. This data is then uploaded to the unmanned aerial vehicle (UAV) in real-time via a two-way communication module (5.8GHz short-range link). Wind, waves, and current have a significant impact on the motion of the unmanned surface vessel. The influence of wind on the vessel is typically expressed as wind speed. and wind direction The effect of wind speed on navigation is described by treating it as a disturbance term in the dynamic equations of the USV; the effect of waves can be described by wave height. The direction of the wave is described by the wave period T. It should also be considered that, in the equations of motion, the influence of waves is usually reflected by adding a wave disturbance term; the effects of water flow velocity and direction on unmanned vessels are similar to those of wind, and their wind-wave-current environment model is as follows:

[0078] ,

[0079] ,

[0080] ,

[0081] in, Due to the influence of wind, Due to the influence of waves, Due to the influence of water flow, For wind speed, For wind direction, The heading angle of the unmanned vessel. Wave height The direction of the wave. For water flow velocity, For flow direction;

[0082] A ship dynamics model considering the influence of uncertain factors is constructed based on the wind, wave, and current environment model. The ship dynamics model is as follows:

[0083] ,

[0084] ,

[0085] ,

[0086] ,

[0087] in, for The state vector of the unmanned ship at any given time. for The control input vector of the unmanned surface vessel at any given time. External disturbances Let x be the x-coordinate of the unmanned surface vessel's position. Let be the ordinate of the unmanned surface vessel's position. For the unmanned ship's speed, As the rudder angle, For propulsion, This is a transpose; since the changes in wind, waves, and currents are time-varying, external disturbances... The path planning process requires estimation based on forecast data for the current and future times.

[0088] In some embodiments, in step S102, obstacle data collected in real time by the UAV is acquired, a turbulent zone distribution map of the bridge pier is constructed based on the Mike21 hydrodynamic model, and a dynamic obstacle field is generated by combining the LiDAR point cloud. The UAV collects three-dimensional obstacle data in the environment in real time through a LiDAR sensor, and transmits the collected obstacle three-dimensional data to the unmanned vessel through a two-way communication module. Based on the starting point, target point, ship dynamics model, and obstacle data collected in real time by the UAV, the planned trajectory of the UAV is obtained. The planned trajectory of the UAV consists of multiple global candidate paths. A comprehensive cost function considering path length, travel time, wave influence, and water flow influence is constructed. The comprehensive cost function is used as the fitness function of the chaotic optimization particle swarm algorithm. In path planning, the cost function is usually composed of multiple factors, including path length, travel time, and environmental influence. The comprehensive cost function of the global path is:

[0089] ,

[0090] in, For the comprehensive cost function, This is the total path length. Total sailing time For the first Wave encounter angle cost at each path node For the first The cost of water flow at each path node The angle between the heading and the wave direction. , , , These are the weighting coefficients;

[0091] Wave encounter angle cost function in the comprehensive cost function The wave encounter angle cost function is used to evaluate the angular difference between the heading and wave direction of an unmanned surface vessel (USV):

[0092] ,

[0093] in, As a weighting coefficient, it determines the impact on the overall cost. Its characteristic is that when... The cost is lowest when (i.e., sailing with the waves), when The highest cost is incurred when sailing against the waves.

[0094] The impact of water flow on navigation is usually represented by a water flow cost function, which is used to penalize deviations from the navigation path caused by upstream or cross-currents. Upstream flow reduces navigation speed, and its water flow cost function is:

[0095] ,

[0096] in, , These are weighting coefficients, which control the degree of influence of water flow direction deviation and water flow velocity, respectively. For water flow velocity, Indicates the direction of water flow;

[0097] Using the comprehensive cost function as the fitness function of the chaotic optimization particle swarm optimization algorithm, the algorithm is employed to optimize the planned trajectory of an unmanned surface vessel (USV) and obtain the globally optimal planned path. Initial values ​​and control parameters for the chaotic optimization particle swarm optimization algorithm are set. A chaotic sequence is generated based on the initial values ​​and control parameters. The particle swarm is initialized based on the USV's planned trajectory and the chaotic sequence to obtain particle velocities and positions. The fitness values ​​of the particle swarm are determined according to the comprehensive cost function. An elite adaptive truncation average update strategy is used to filter the fitness values ​​of the particle swarm, obtaining elite particles. Based on the fitness values ​​of the elite particles and the chaotic sequence, the particle positions and velocities are updated to obtain the individual optimal solutions of the particles and the globally optimal solutions of the swarm. The optimal total path length and total travel time are determined based on the individual optimal solutions and the globally optimal solutions. The globally optimal planned path of the USV is obtained based on the optimal total path length and total travel time. The chaotic optimization particle swarm optimization algorithm is an improvement on the traditional particle swarm optimization (PSO) algorithm. In traditional PSO, the velocity update formula for each particle is:

[0098] ,

[0099] in, , Random numbers, typically generated from a uniform distribution, are used in chaotic optimization particle swarm optimization algorithms. , To improve this, replace the values ​​in the chaotic sequence. , This approach makes the search process more uniform, increases population diversity, balances multiple objectives through mechanisms such as non-dominated sorting, and improves population diversity and global search capability by introducing chaotic mapping, indirectly improving the distribution of the Pareto front. In the optimization process of the chaotic particle swarm optimization algorithm, an elite adaptive truncation average update strategy is adopted to improve the performance of the algorithm. This strategy retains a number of optimal particles (elite set), and the position or velocity of the elite set is truncated and averaged to accelerate the convergence of the chaotic particle swarm optimization algorithm and improve its accuracy. Once the chaotic particle swarm optimization algorithm reaches the maximum number of iterations or convergence of the target cost, it outputs the path corresponding to the optimal particle, i.e., the globally optimal planned path of the unmanned surface vessel. After obtaining the globally optimal planned path, the optimal discrete path is smoothed using Bézier or spline curves to remove abrupt changes. Feasibility verification verifies that the smoothed path still satisfies constraints such as navigation area boundaries and obstacle avoidance at each node. Finally, a robust route track map is generated, and key nodes are marked. For a comparison diagram of the robust route track map and the optimized trajectory, please refer to [link to diagram]. Figure 2 .

[0100] The chaotic optimized particle swarm optimization algorithm selects elite particles and couples the cost function with the environment, prioritizing the retention of path solutions that adapt to real-time wind and waves. Through the chaotic optimized particle swarm optimization algorithm, the path planning speed of unmanned vessels is improved, and the convergence time of global path optimization is shortened by 60% (the traditional particle swarm optimization algorithm requires 200 iterations, while the chaotic optimized particle swarm optimization algorithm only requires 120 iterations).

[0101] In some embodiments, in step S103, wind field data collected in real time by the unmanned surface vessel (USV) is acquired. Based on the USV's starting point, target point, and wind field data, the Dandelion optimization algorithm is used to plan the USV's three-dimensional path to obtain the planned trajectory. The Dandelion optimization algorithm includes an ascent phase, a decay phase, and a landing phase. The Dandelion optimization algorithm performs global optimization by simulating the natural propagation process of dandelion seeds. A three-dimensional spatial model is constructed based on the USV's starting point, target point, obstacles, and wind field vectors. The seed population of the Dandelion optimization algorithm is initialized based on the three-dimensional spatial model. An initial seed population is randomly generated, and algorithm parameters (such as population size, maximum number of iterations, etc.) are set. Each seed corresponds to a path. During the ascent phase, the speed and position of the seeds are updated. The fitness value of each seed is calculated, and its value is the objective function value. Seeds are evaluated based on their fitness values ​​to determine the optimal solution region. During the decay phase, the fitness values ​​of seeds within the optimal solution region are determined, and the search range is dynamically adjusted based on the seed fitness values. This involves balancing the influence of wind field and path length through dynamic weighting. During the landing phase, a refined search is performed near the target point to obtain the optimal solution, and the planned trajectory of the UAV is determined based on the optimal solution. Iteration stops if the termination condition is met (such as reaching the maximum number of iterations or the fitness value meeting the accuracy requirements). The particle position and velocity update formulas in the Dandelion algorithm are similar to those in the Particle Swarm Optimization (PSO) algorithm, but it incorporates the characteristics of dandelion seed propagation, enabling it to plan flight paths under uncertainties. The seed velocity update is as follows:

[0102] ,

[0103] in, for During the nth iteration The seed of the first Dimensional speed, For inertial weights, , , For acceleration coefficient, , , It is a random number. for The global optimal position at the next iteration. for During the nth iteration The optimal location for each seed for During the nth iteration The seed of the first Dimensional position, To simulate the wind-borne dispersal characteristics of dandelion seeds, a random perturbation term was added. To achieve;

[0104] The seed location has been updated to:

[0105] ,

[0106] in, for During the nth iteration The seed of the first Dimensional position;

[0107] If the current seed's fitness value is better than the historical best fitness value, then the individual optimal position and fitness value are updated. Among all the individual optimal positions of all seeds, the position with the smallest fitness value is selected as the global optimal position. The fitness function is used to evaluate the fitness of each seed, that is, the value of the objective function. In path planning problems, the fitness function is usually related to the path length, obstacle avoidance ability, accuracy of reaching the target point, etc. In specific implementations, the fitness function is defined according to the needs of the specific problem.

[0108] The Dandelion algorithm, by simulating the natural propagation mechanism of dandelion seeds and combining it with the basic framework of swarm intelligence algorithms, has strong global search capabilities and greatly improves the probability of finding the optimal route for UAVs when faced with uncertainties.

[0109] In some embodiments, in step S104, autonomous cooperative cruising in complex environments is achieved based on the globally optimal planned path of the unmanned surface vessel and the planned trajectory of the unmanned aerial vehicle (UAV). For a schematic diagram of the entire process of UAV-UAV cooperative operation, please refer to [link / reference needed]. Figure 3 ,like Figure 3As shown, after the unmanned surface vessel (USV) and unmanned aerial vehicle (UAV) have completed their path planning, they conduct autonomous cruises. During the cruise, the USV receives real-time electronic nautical chart data, ship AIS (Automatic Identification System) data, and acquires real-time wind, wave, and current data (via onboard sensors). The UAV acquires meteorological data required for flight (such as weather forecasts and wind field data), receives airspace usage permits and no-fly zone data, and acquires 3D data of obstacles in the environment (via sensors such as LiDAR). Data interaction occurs as follows: the USV uploads high-precision wind field data to the UAV via a two-way communication module, and the UAV downloads LiDAR scan data to the USV via a communication module. The ship's two-way communication module combines a 5.8GHz short-range link (100Mbps, <10ms latency) with a 4G / 5G remote channel, supporting AES-128 encrypted transmission. Under level 5 electromagnetic interference, the command transmission success rate is improved from 85% to 99.9%. Cooperative response is accelerated, with the latency of UAV triggering USV path pre-adjustment reduced from 50ms to 10ms, and the cooperative efficiency improved by 60%. The unmanned ship and drone share data such as no-fly zone boundaries and obstacle heat maps in real time through the two-way communication module. The unmanned ship and drone integrate the received data to complete environmental perception and status updates, realizing cooperative cruise between the unmanned ship and drone.

[0110] During cooperative patrol, when an emergency is detected, the target point of the UAV is determined based on the globally optimal planned path of the unmanned surface vessel (USV). The planned trajectory of the UAV is updated based on the target point, enabling the UAV to land precisely on the USV. When sudden severe weather (such as strong winds or heavy rain) is detected, the UAV's emergency landing procedure is triggered. The USV activates the positioning and guidance system of its intelligent take-off and landing platform, achieving a precise landing through optical guidance and a magnetic attraction mechanism. After landing, the UAV is secured to the take-off and landing platform to ensure safety. After landing, the USV returns to port. For a schematic diagram of the UAV take-off and landing platform, please refer to [link / reference needed]. Figure 4 The drone take-off and landing platform is located above the unmanned vessel. It is disc-shaped with a small-angle funnel-shaped interior and a central landing trough. Drones land smoothly within the disc and slide towards the center, eventually landing in the trough where a securing hook extends to hold the drone, ensuring stable transport. Charging and data transmission interfaces can be added to the auxiliary landing disc attached to the drone for charging and control. The disc-shaped platform, approximately 2 meters in diameter, uses a lightweight aluminum alloy frame and carbon fiber composite panels, combining strength and corrosion resistance to adapt to aquatic environments. The disc's interior features a funnel-shaped guide surface, with the inner surface designed as… The inclined funnel structure, with added anti-slip textures and drainage channels, guides the UAV to glide smoothly towards the center during landing, while preventing water accumulation. A circular landing trough, located at the platform's geometric center, has a diameter of 35 cm and a depth of 0.3 meters. Combined with a circular base mounted on the UAV, it guides and positions the UAV during landing. The inner wall of the trough is covered with a rubber cushioning layer to ensure buffering and deceleration during UAV descent, preventing impacts. The takeoff and landing platform has dynamic balance adjustment capabilities. A six-axis gyroscope and hydraulic compensation device are installed at the bottom of the platform to adjust the platform's level in real time according to the UAV's swaying amplitude, with an error range of [missing information]. The platform also features an emergency release mechanism. In emergencies, the fixed hook can be unlocked with a single click via remote command or autonomous decision-making by the unmanned vessel, allowing the drone to quickly initiate detachment. Optical guidance has been added to the positioning and guidance system of the intelligent take-off and landing platform. The platform has visual navigation and assisted positioning functions, with RGB programmable LED light strips arranged around the platform's edge. The color and flashing frequency indicate the landing status, and the drone can identify the light strips to determine the landing status. In addition, signal positioning points are arranged in a ring around the platform's circumference for positioning assistance. This part can integrate an RTK differential GPS module, which can be linked with the drone's flight control system to provide centimeter-level landing guidance accuracy. The wireless slave unit adopts a magnetic docking mechanism with a charging power of 200W and an efficiency of ≥92%, supporting stable docking in sea state 5. The success rate of take-off and landing in sea state 5 has increased from 70% of traditional platforms to 98%, reducing the need for manual intervention.

[0111] Through multimodal perception fusion, dynamic algorithm optimization, and hardware-software co-design, it comprehensively surpasses existing technologies in terms of positioning accuracy, task efficiency, energy management, communication reliability, and environmental adaptability. Actual test data shows that its waterway modeling accuracy is improved to 0.15m (compared to 0.5m in traditional solutions), energy consumption per unit mileage is reduced by 35%, and the response speed to sudden obstacles is increased by 50%, providing a high-precision, low-cost intelligent solution for scenarios such as inland waterway inspection and marine monitoring.

[0112] In summary, the unmanned surface vessel (USV) and unmanned aerial vehicle (UAV) cooperative cruise method provided by this invention constructs a time-varying wind, wave, and current environment model based on acquired real-time wind, wave, and current data. Based on this model, a ship dynamics model considering the influence of uncertain factors is constructed. The planned trajectory of the USV is obtained based on its starting point, target point, ship dynamics model, and obstacle data collected in real-time by the UAV. A comprehensive cost function considering path length, travel time, wave influence, and current influence is constructed. This comprehensive cost function serves as the fitness function for a chaotic optimization particle swarm optimization (PSO) algorithm, which optimizes the USV's planned trajectory to obtain the globally optimal planned path. Real-time wind field data collected by the USV is acquired. Based on the UAV's starting point, target point, and wind field data, a dandelion optimization algorithm is used to plan the UAV's three-dimensional path, obtaining its planned trajectory. Autonomous cooperative cruise in complex environments is achieved based on the USV's globally optimal planned path and the UAV's planned trajectory, reducing the path planning time for the USV under the influence of uncertain factors and improving the UAV's positioning accuracy.

[0113] To better implement the unmanned vessel and unmanned aerial vehicle cooperative cruise method in this embodiment of the invention, based on the unmanned vessel and unmanned aerial vehicle cooperative cruise method, correspondingly, as follows: Figure 5 As shown, this embodiment of the invention also provides an unmanned surface vessel and unmanned aerial vehicle (UAV) cooperative cruise device. The unmanned surface vessel and UAV cooperative cruise device 500 includes:

[0114] The dynamic model construction module 501 is used to construct a time-varying wind, wave and flow environment model based on the acquired real-time wind, wave and flow data, and to construct a ship dynamics model considering the influence of uncertain factors based on the time-varying wind, wave and flow environment model.

[0115] The unmanned vessel path optimization module 502 is used to obtain the planned trajectory of the unmanned vessel based on the starting point, target point, ship dynamics model and obstacle data collected in real time by the UAV. It constructs a comprehensive cost function that considers path length, travel time, wave influence and water flow influence. The comprehensive cost function is used as the fitness function of the chaotic optimization particle swarm algorithm. The chaotic optimization particle swarm algorithm is used to optimize the planned trajectory of the unmanned vessel to obtain the globally optimal planned path of the unmanned vessel.

[0116] The UAV path planning module 503 is used to acquire wind field data collected in real time by the unmanned vessel. Based on the UAV's starting point, target point, and wind field data, the dandelion optimization algorithm is used to plan the UAV's three-dimensional path to obtain the UAV's planned trajectory.

[0117] The cooperative cruise module 504 is used to achieve autonomous cooperative cruise in complex environments based on the globally optimal planned path of the unmanned vessel and the planned trajectory of the UAV landing.

[0118] like Figure 6As shown, the present invention also provides an electronic device 600, which can be a mobile terminal, desktop computer, laptop, handheld computer, server, or other computing device. The electronic device 600 includes a processor 601, a memory 602, and a display 603. Figure 6 Only some components of the electronic device 600 are shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0119] In some embodiments, memory 602 may be an internal storage unit of the electronic device 600, such as a hard disk or memory of the electronic device 600. In other embodiments, memory 602 may be an external storage device of the electronic device 600, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the electronic device 600. Furthermore, memory 602 may include both internal and external storage units of the electronic device 600. Memory 602 is used to store application software and various types of data installed on the electronic device 600, such as program code installed on the electronic device 600. Memory 602 may also be used to temporarily store data that has been output or will be output. In one embodiment, memory 602 stores an unmanned surface vessel (USV) and unmanned aerial vehicle (UAV) cooperative cruise program, which can be executed by processor 601 to implement the USV and UAV cooperative cruise methods of various embodiments of the present invention.

[0120] In some embodiments, processor 601 may be a central processing unit (CPU), microprocessor, or other data processing chip, used to run program code stored in memory 602 or process data, such as a method for cooperative cruise between unmanned ships and drones.

[0121] In some embodiments, display 603 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. Display 603 is used to display identification information for the unmanned surface vessel / drone cooperative cruise procedure and to display a visual user interface. Components 601-603 of electronic device 600 communicate with each other via a system bus.

[0122] In some embodiments, when the processor 601 executes the unmanned vessel and unmanned aerial vehicle (UAV) cooperative cruise program in the memory 602, it implements each step of the unmanned vessel and UAV cooperative cruise method as described in the above embodiments. Since the unmanned vessel and UAV cooperative cruise method has been described in detail above, it will not be repeated here.

[0123] Accordingly, the present invention also provides a computer-readable storage medium for storing computer-readable programs or instructions, which, when executed by a processor, can realize the steps or functions of the unmanned vessel / unmanned aerial vehicle cooperative cruise method provided in the above-described method embodiments.

[0124] Those skilled in the art will understand that all or part of the processes of the methods described in the above embodiments can be implemented by a computer program instructing related hardware, and the program can be stored in a computer-readable storage medium. The computer-readable storage medium may be a disk, optical disk, read-only memory, or random access memory, etc.

[0125] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for cooperative cruising between unmanned surface vessels and unmanned aerial vehicles, characterized in that, include: A time-varying wind, wave, and current environment model is constructed based on the acquired real-time wind, wave, and current data. A ship dynamics model considering the influence of uncertain factors is then constructed based on the time-varying wind, wave, and current environment model. The planned trajectory of the unmanned vessel is obtained based on the starting point, target point, ship dynamics model, and obstacle data collected in real time by the UAV. A comprehensive cost function considering path length, travel time, wave influence, and water flow influence is constructed. The comprehensive cost function is used as the fitness function of the chaotic optimization particle swarm algorithm. The chaotic optimization particle swarm algorithm is used to optimize the planned trajectory of the unmanned vessel to obtain the globally optimal planned path of the unmanned vessel. Real-time wind field data collected by the unmanned surface vessel (USV) is acquired. Based on the USV's starting point, target point, and wind field data, the dandelion optimization algorithm is used to plan the USV's three-dimensional path, obtaining the planned trajectory. The dandelion optimization algorithm includes ascent, decay, and landing phases. The process of planning the USV's three-dimensional path using the dandelion optimization algorithm based on the USV's starting point, target point, and wind field data to obtain the planned trajectory includes: A three-dimensional spatial model is constructed based on the starting point, target point, obstacles, and wind field data of the UAV. The seed group of the dandelion optimization algorithm is initialized based on the three-dimensional spatial model, wherein each seed corresponds to a path. During the ascent phase, after updating the velocity and position of the seeds, the fitness value of each seed is calculated. Based on the fitness value of each seed, the seeds are evaluated to determine the optimal solution region. The velocity of the seeds is then updated as follows: ， in, for During the nth iteration The seed of the first Dimensional speed, For inertial weights, , , For acceleration coefficient, , , It is a random number. for The global optimal position at the next iteration. for During the nth iteration The optimal location for each seed for During the nth iteration The seed of the first Dimensional position, The influence of wind; The position of the seed is updated as follows: ， in, for During the nth iteration The seed of the first Dimensional position; During the decay phase, the fitness value of the seed in the optimal solution region is determined, and the search range is dynamically adjusted based on the fitness value of the seed, wherein the influence of wind field and path length are balanced by dynamic weighting. During the landing phase, a refined search is conducted near the target point to obtain the optimal solution, and the planned trajectory of the UAV is determined based on the optimal solution; Autonomous collaborative cruising in complex environments is achieved based on the globally optimal planned path of the unmanned vessel and the planned trajectory of the unmanned aerial vehicle.

2. The unmanned surface vessel and unmanned aerial vehicle cooperative cruise method according to claim 1, characterized in that, The time-varying wind, wave, and current environment model is as follows: ， ， ， in, Due to the influence of wind, Due to the influence of waves, Due to the influence of water flow, For wind speed, For wind direction, The heading angle of the unmanned vessel. Wave height The direction of the wave. For water flow velocity, For flow direction; The ship dynamics model is as follows: ， ， ， ， in, for The state vector of the unmanned ship at any given time. for The control input vector of the unmanned surface vessel at any given time. External disturbances Let x be the x-coordinate of the unmanned surface vessel's position. Let be the ordinate of the unmanned surface vessel's position. For the unmanned ship's speed, As the rudder angle, For propulsion, This is a transpose.

3. The unmanned surface vessel and unmanned aerial vehicle cooperative cruise method according to claim 1, characterized in that, The comprehensive cost function is: ， ， ， in, For the comprehensive cost function, This is the total path length. Total sailing time For the first Wave encounter angle cost at each path node For the first The cost of water flow at each path node The angle between the heading and the wave direction. , , , These are the weighting coefficients. These are the weighting coefficients. , These are the weighting coefficients. For water flow velocity, This indicates the direction of water flow.

4. The unmanned surface vessel and unmanned aerial vehicle cooperative cruise method according to claim 1, characterized in that, The step of using the comprehensive cost function as the fitness function of the chaotic optimized particle swarm optimization algorithm to optimize the planned trajectory of the unmanned vessel and obtain the globally optimal planned path of the unmanned vessel includes: Set the initial values ​​and control parameters for the chaotic optimization particle swarm algorithm; A chaotic sequence is generated based on the initial values ​​and control parameters; The particle swarm of the chaotic optimization particle swarm algorithm is initialized based on the planned trajectory of the unmanned vessel and the chaotic sequence to obtain the particle velocity and particle position. The fitness value of the particle swarm is determined based on the comprehensive cost function; The fitness values ​​of the particle swarm are filtered using an elite adaptive truncation average update strategy to obtain elite particles; The particle position and particle velocity are updated based on the fitness value of the elite particles and the chaotic sequence to obtain the individual optimal solution of the particles and the global optimal solution of the population particles. The optimal total path length and total travel time are determined based on the individual optimal solution and the global optimal solution. The global optimal planned path of the unmanned vessel is obtained based on the optimal total path length and total travel time.

5. The unmanned surface vessel and unmanned aerial vehicle cooperative cruise method according to claim 1, characterized in that, The autonomous cooperative cruise in complex environments, based on the globally optimal planned path of the unmanned vessel and the planned trajectory of the unmanned aerial vehicle, includes: When an emergency is detected, the target point of the UAV is determined based on the globally optimal planned path of the unmanned vessel, and the planned trajectory of the UAV is updated based on the target point, so that the UAV can land accurately on the unmanned vessel.

6. A collaborative patrol device for unmanned surface vessels and unmanned aerial vehicles, characterized in that, include: The dynamic model construction module is used to construct a time-varying wind, wave and flow environment model based on the acquired real-time wind, wave and flow data, and to construct a ship dynamics model considering the influence of uncertain factors based on the time-varying wind, wave and flow environment model. The unmanned vessel path optimization module is used to obtain the planned trajectory of the unmanned vessel based on the starting point, target point, ship dynamics model, and obstacle data collected in real time by the UAV. It constructs a comprehensive cost function that considers path length, travel time, wave influence, and water flow influence. The comprehensive cost function is used as the fitness function of the chaotic optimization particle swarm algorithm. The chaotic optimization particle swarm algorithm is used to optimize the planned trajectory of the unmanned vessel to obtain the globally optimal planned path of the unmanned vessel. The UAV path planning module is used to acquire real-time wind field data collected by the unmanned surface vessel. Based on the UAV's starting point, target point, and wind field data, the dandelion optimization algorithm is used to plan the UAV's three-dimensional path to obtain the planned trajectory. The dandelion optimization algorithm includes an ascent phase, a decay phase, and a landing phase. The process of planning the UAV's three-dimensional path using the dandelion optimization algorithm based on the UAV's starting point, target point, and wind field data to obtain the planned trajectory includes: A three-dimensional spatial model is constructed based on the starting point, target point, obstacles, and wind field data of the UAV. The seed group of the dandelion optimization algorithm is initialized based on the three-dimensional spatial model, wherein each seed corresponds to a path. During the ascent phase, after updating the velocity and position of the seeds, the fitness value of each seed is calculated. Based on the fitness value of each seed, the seeds are evaluated to determine the optimal solution region. The velocity of the seeds is then updated as follows: ， in, for During the nth iteration The seed of the first Dimensional speed, For inertial weights, , , For acceleration coefficient, , , It is a random number. for The global optimal position at the next iteration. for During the nth iteration The optimal location for each seed for During the nth iteration The seed of the first Dimensional position, The influence of wind; The position of the seed is updated as follows: ， in, for During the nth iteration The seed of the first Dimensional position; During the decay phase, the fitness value of the seed in the optimal solution region is determined, and the search range is dynamically adjusted based on the fitness value of the seed, wherein the influence of wind field and path length are balanced by dynamic weighting. During the landing phase, a refined search is conducted near the target point to obtain the optimal solution, and the planned trajectory of the UAV is determined based on the optimal solution; The cooperative cruise module is used to achieve autonomous cooperative cruise in complex environments based on the globally optimal planned path of the unmanned vessel and the planned trajectory of the UAV landing.

7. An electronic device, characterized in that, Including memory and processor; The memory stores a computer-readable program that can be executed by the processor; When the processor executes the computer-readable program, it implements the steps in the unmanned vessel and unmanned aerial vehicle cooperative cruise method as described in any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, Used to store computer-readable programs or instructions, which, when executed by a processor, can implement the steps in the unmanned vessel / unmanned aerial vehicle cooperative cruise method according to any one of claims 1-5.

Images