Polar coordinate trajectory particle swarm optimization method and system for maritime search buoy

Abstract

The invention discloses a polar coordinate trajectory particle swarm optimization method and system for searching a buoy on the sea, and the method comprises the steps: initializing the coordinates of the buoy at the disconnection moment, and obtaining the ocean data; starting coordinates are randomly initialized on the sea surface near coordinates at the buoy disconnection moment, a polar coordinate path is randomly generated from the starting coordinates, and a particle swarm is formed; creating an initial probability distribution function of the buoy on the ocean, and setting related parameters; initializing a historical optimal path considered by each particle in the particle swarm as a particle path; calculating and updating a next-generation particle swarm, and converting the polar coordinate paths of the particles into a Cartesian space and evaluating the polar coordinate paths; and updating the initial probability distribution function to obtain a historical optimal path of each particle in a next-generation particle swarm so as to select a global optimal path. The method has good dynamic buoy adaptive capacity and search robustness, and can still keep higher discovery probability even under the condition that the buoy moves quickly or the search information is incomplete.

Description

Technical Field

[0001] The present invention relates to a polar coordinate trajectory particle swarm optimization method and system for searching for buoys at sea, belonging to the technical field of unmanned aerial vehicle (UAV) maritime search and rescue. Background Art

[0002] With the rapid development of the Internet of Things (IoT) technology, a large number of smart devices have been deployed in human environments, making life more convenient. The Argo program has deployed thousands of buoy sensors across the world's oceans, providing real-time ocean observation data for climate, weather, oceanography, and fisheries research. However, buoys operate in harsh environments for long periods of time, and the antennas and positioning modules used for data upload are prone to corrosion or damage. However, the collected ocean data is extremely important, and there is an urgent need to retrieve the data stored by the buoys. As time passes, the probability of finding a buoy in the ocean decreases dramatically. Therefore, designing an efficient intelligent search algorithm is a major challenge in this field.

[0003] Particle swarm optimization (PSO) has been widely used in target search and path planning due to its advantages, including strong global search capabilities, simple parameter settings, and fast convergence. However, traditional PSO methods generally represent the search path as a sequence of Cartesian coordinate nodes, which often results in discontinuous paths and fails to meet the dynamic constraints of UAV flight. Some methods address this issue by attempting to improve the probability of finding a buoy while satisfying flight constraints. However, these methods often have complex structures, numerous parameters, or introduce additional heuristic rules, increasing algorithmic overhead and making them unsuitable for hardware-restricted UAV systems. Greedy search algorithms are simple to implement, computationally efficient, and fast, but they are prone to falling into local optima and failing to adjust their strategies promptly after target movement. Phase-angle-based PSO algorithms, while less expensive, are limited in their search capabilities in high-dimensional spaces and struggle to handle complex dynamic target environments. Summary of the Invention

[0004] In view of this, the present invention provides a polar coordinate trajectory particle swarm optimization method, system, computer device and storage medium for searching for buoys at sea. It reduces computational overhead by using polar coordinates to describe the search space of the particle swarm optimization algorithm, and then establishes a probability distribution function of the buoy on the ocean, thereby guiding the search path to evolve towards high-probability areas. It has good dynamic buoy adaptability and search robustness, and can maintain a high probability of discovery even when the buoy moves quickly or the search information is incomplete.

[0005] The first object of the present invention is to provide a polar coordinate trajectory particle swarm optimization method for searching for buoys at sea.

[0006] The second object of the present invention is to provide a polar coordinate trajectory particle swarm optimization system for searching for buoys at sea.

[0007] A third object of the present invention is to provide a computer device.

[0008] A fourth object of the present invention is to provide a computer-readable storage medium.

[0009] The first object of the present invention can be achieved by adopting the following technical solutions:

[0010] A polar coordinate trajectory particle swarm optimization method for searching for buoys at sea, the method comprising:

[0011] Initialize the coordinates of the buoy when it loses contact and obtain ocean data;

[0012] According to the ocean data, the starting coordinates are randomly initialized on the sea surface near the coordinates of the moment when the buoy lost contact, and a polar coordinate path is randomly generated from the starting coordinates to form a particle swarm;

[0013] According to the coordinates of the buoy at the time of loss of contact and the starting coordinates, the initial probability distribution function of the buoy on the ocean is created, and the polar coordinate trajectory particle swarm optimization parameters are set;

[0014] According to the initial probability distribution function, the historical optimal path considered by each particle in the initial particle swarm is the particle's own path;

[0015] Calculate and update the next generation of particle swarm based on the polar coordinate path, the particle's own path, and the polar coordinate trajectory particle swarm optimization parameters;

[0016] The polar coordinate paths of particles in the next generation particle swarm are converted into Cartesian space, and the particles converted into Cartesian space are evaluated using the evaluation function;

[0017] According to the evaluation results, the initial probability distribution function is updated to obtain the historical optimal path of each particle in the next generation of particle swarms in order to select the global optimal path;

[0018] The operation of selecting the global optimal path is repeated until the set number of iterations is met.

[0019] Furthermore, the particle swarm optimization parameters based on the polar coordinate path, the particle's own path, and the polar coordinate trajectory are used to calculate and update the next generation particle swarm, specifically including:

[0020] Use the evaluation function to evaluate each particle in the particle swarm and select the best particle path in the particle swarm as the optimal path;

[0021] Multiply the polar coordinate path, the difference between the particle's own path and the polar coordinate path, and the difference between the optimal path and the polar coordinate path by the corresponding parameters, and sum them up to calculate the update direction of each particle in the particle swarm;

[0022] Update the next generation of particle swarm according to the polar coordinate path and update direction of each particle in the particle swarm.

[0023] Furthermore, the evaluation function is as follows:

[0024]

[0025]

[0026] Among them, f i represents the probability that no buoy is detected from the first time to the i-th time, p t represents the probability of detecting the buoy for the first time at the tth time, It represents the cumulative probability function and characterizes the evaluation function.

[0027] Furthermore, the polar coordinate path, the difference between the particle's own path and the polar coordinate path, and the difference between the optimal path and the polar coordinate path are multiplied by corresponding parameters, and the sum is calculated to obtain the update direction of each particle in the particle swarm, as shown in the following formula:

[0028]

[0029] Among them, ΔU k+1 Indicates the update direction of each particle, w, is the weight, U k Represents the polar coordinate path, L k represents the particle path, G k Indicates the optimal path.

[0030] Furthermore, the next generation particle swarm is updated according to the polar coordinate path and update direction of each particle in the particle swarm, as shown in the following formula:

[0031] U k+1 ←U k +ΔU k+1

[0032] Among them, U k+1 represents the polar coordinate path of each particle in the next generation particle swarm, U k Indicates the polar coordinate path of each particle in the current particle swarm, ΔU k+1 Indicates the update direction of each particle.

[0033] Furthermore, the initial probability distribution function is as follows:

[0034] ρ(x0)=N(x0|μ=xm ,Σ)

[0035] Among them, x0 is the starting coordinate, x m is the coordinate of the buoy when it loses contact, and Σ is the covariance matrix.

[0036] Furthermore, the polar coordinate paths of the particles in the next generation particle swarm are converted into Cartesian space as follows:

[0037] X k+1 ←U k+1

[0038] x k+1 =x k +l k cosα k

[0039] y k+1 =y k +l k sinα k

[0040] Among them, U k+1 represents the polar coordinate path of each particle in the next generation particle swarm, X k+1 represents the Cartesian coordinate path of each particle in the next generation particle swarm, l k represents the travel length of the drone, α k Indicates the direction of the drone's movement.

[0041] The second object of the present invention can be achieved by adopting the following technical solutions:

[0042] A polar coordinate trajectory particle swarm optimization system for searching for buoys at sea, the system comprising:

[0043] The first initialization module is used to initialize the coordinates of the buoy when it loses contact and obtain ocean data;

[0044] The second initialization module is used to randomly initialize the starting coordinates on the sea surface near the coordinates of the time when the buoy lost contact based on the ocean data, and randomly generate polar coordinate paths from the starting coordinates to form a particle swarm;

[0045] A creation module is used to create the initial probability distribution function of the buoy on the ocean based on the coordinates of the buoy when it lost contact and the starting coordinates, and to set the polar coordinate trajectory particle swarm optimization parameters;

[0046] The third initialization module is used to initialize the historical optimal path considered by each particle in the particle swarm as the particle's own path according to the initial probability distribution function;

[0047] The first updating module is used to calculate and update the next generation particle swarm according to the polar coordinate path, the particle's own path and the polar coordinate trajectory particle swarm optimization parameters;

[0048] Evaluation module, used to convert the polar coordinate paths of particles in the next generation particle swarm into Cartesian space and evaluate the particles converted into Cartesian space using evaluation function;

[0049] The second updating module is used to update the initial probability distribution function according to the evaluation results, obtain the historical optimal path of each particle in the next generation particle swarm, and select the global optimal path;

[0050] The iteration module is used to repeatedly execute the operation of selecting the global optimal path until the set number of iterations is met.

[0051] The third object of the present invention can be achieved by adopting the following technical solutions:

[0052] A computer device includes a processor and a memory for storing a program executable by the processor, wherein the processor implements the above-mentioned polar coordinate trajectory particle swarm optimization method when executing the program stored in the memory.

[0053] The fourth object of the present invention can be achieved by adopting the following technical solutions:

[0054] A computer-readable storage medium stores a program, which, when executed by a processor, implements the polar coordinate trajectory particle swarm optimization method.

[0055] The present invention has the following beneficial effects compared to the prior art:

[0056] 1. The present invention adopts polar coordinates (direction, distance) to improve the particle swarm optimization algorithm, avoiding the common path incoherence or jump problems in traditional coordinates. The generated path is more in line with the actual dynamics and flight control requirements of platforms such as drones.

[0057] 2. The search space and update rules of the present invention are concise and clear, do not rely on complex deep models or multi-stage optimization processes, have lower computational overhead, and are suitable for operation in environments such as low-power drones and embedded chips.

[0058] 3. This paper designs a buoy position probability distribution function based on Bayesian theorem, guiding the PTPSO to adjust the search path in real time according to the buoy movement trend. It is suitable for dynamic environments such as uncertain and rapidly changing target positions and has excellent actual combat response capabilities.

[0059] 4. The present invention retains the "inertia" and "group behavior" of particles, making particles more coherent and directional in the search space, reducing the risk of falling into local optimality, and improving global search capabilities and algorithm convergence speed. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without paying any creative work.

[0061] Figure 1 This is a schematic diagram of a drone searching for buoys at sea according to Example 1 of the present invention.

[0062] Figure 2 This is a flow chart of a polar coordinate trajectory particle swarm optimization method for searching for buoys at sea according to Example 1 of the present invention.

[0063] Figure 3 This is a schematic diagram of the principle of the polar coordinate trajectory particle swarm optimization method for searching for buoys at sea according to Example 1 of the present invention.

[0064] Figure 4 This is a northwest-facing ocean heat map with a fast flow rate according to Example 1 of the present invention.

[0065] Figure 5 for Figure 4 Drone trajectory diagram in the scenario.

[0066] Figure 6 This is a structural block diagram of a polar coordinate trajectory particle swarm optimization system for searching for buoys at sea according to embodiment 2 of the present invention.

[0067] Figure 7 This is a structural block diagram of a computer device according to embodiment 3 of the present invention. DETAILED DESCRIPTION

[0068] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0069] Example 1:

[0070] like Figure 1As shown in the figure, a buoy in a certain sea area is collecting ocean environmental information, such as seawater salinity information. However, due to some unexpected events, such as antenna failure, it is unable to establish a connection, and thus becomes an isolated buoy drifting in the ocean. People are eager to use drones to find this buoy with important salinity data, hoping to find it as soon as possible. However, even if we know the location x of the buoy at the moment of loss of contact, m Due to the reaction time and the flight time of the drone, the buoy has already deviated from x m We can only roughly know the starting position of the buoy at coordinate x m The starting coordinate is x0. Obviously, different buoy starting points x0 will lead to multiple drift paths. However, the ocean environment is not completely chaotic. The Argo ocean monitoring system program, which has lasted for more than 20 years, has provided real data. These data can be used to simulate the direction and rate of ocean currents in the regional ocean more accurately. In this way, the search problem is no longer a completely blind search, but to judge which drift trajectory is more likely to be the true path of the buoy among multiple possible starting coordinates x0, and plan the drone to go to the most likely area first. In a complex ocean environment and when the buoy moves, this embodiment provides a polar coordinate trajectory particle swarm optimization method for searching for buoys at sea, which aims to calculate a drone path that maximizes the probability of the drone detecting the buoy while reducing the search time. Figure 2 and Figure 3 As shown, the method specifically includes the following steps:

[0071] S201. Initialize the coordinates of the buoy when it loses contact, and obtain ocean data.

[0072] In this embodiment, the coordinate of the moment when the buoy loses contact is marked as x m , ocean data includes ocean current speed and direction data provided by the Argo program.

[0073] S202. Based on the ocean data, randomly initialize the starting coordinates on the sea surface near the coordinates at the time when the buoy loses contact, and randomly generate a polar coordinate path from the starting coordinates to form a particle swarm.

[0074] In this embodiment, only the coordinate x of the moment when the buoy lost contact is available. m When the drone is sent out for search, the buoy has actually moved. The starting coordinate is x0, and the polar coordinate path U is randomly generated from the starting coordinate x0. k , forming a particle group U.

[0075] S203. According to the coordinates of the buoy at the time of loss of contact and the starting coordinates, an initial probability distribution function of the buoy on the ocean is created, and polar coordinate trajectory particle swarm optimization parameters are set.

[0076] like Figure 4 As shown, the yellow area is the coordinate x at the time when the buoy lost contact m The color depth of the high probability area near x0 represents the probability distribution map. The initial probability distribution map ρ(x0) can be modeled using a normal distribution centered at that location. The idea is actually a simple uniform decreasing distribution (indicates the distance from x0 to the original location). m The farther away the position is, the less likely it is to be the initial position x0). The probability distribution function of the specific starting coordinate x0 is implemented based on Bayes' theorem, and the formula is as follows:

[0077] ρ(x0)=N(x0|μ=x m ,Σ)

[0078] Where Σ is the covariance matrix, which is used to control the distribution range. The coordinate x at the time of buoy loss of contact in this embodiment is m =(25,17).

[0079] This embodiment sets the polar coordinate trajectory particle swarm optimization parameters, that is, sets three weight parameters w,

[0080] S204: According to the initial probability distribution function, the historical optimal path considered by each particle in the particle swarm is initialized as the particle's own path.

[0081] S205, calculating and updating the next generation particle swarm according to the polar coordinate path, the particle's own path and the polar coordinate trajectory particle swarm optimization parameters.

[0082] Furthermore, step S205 specifically includes:

[0083] S2051. Evaluate each particle in the particle swarm using an evaluation function, and select the best particle path in the particle swarm as the optimal path.

[0084] The evaluation function of this embodiment is as follows:

[0085]

[0086] Among them, f i represents the probability that no buoy is detected from the first time to the i-th time. Similarly, f t represents the probability that no buoy is detected from the first time to the tth time, [ t represents the probability of detecting the buoy for the first time at the tth time, represents the cumulative probability function, characterizes the evaluation function, The larger the value, the better the particle path.

[0087] S2052: Multiply the polar coordinate path, the difference between the particle's own path and the polar coordinate path, and the difference between the optimal path and the polar coordinate path by corresponding parameters, and sum them up to calculate the update direction of each particle in the particle swarm.

[0088] In this embodiment, the update direction of each particle in the particle swarm is calculated as follows:

[0089]

[0090] Among them, ΔU k+1 Indicates the update direction of each particle, w, is the weight, r1 and r2 are random numbers in the interval [0,1], which are used to increase the randomness of the search path, U k Represents the polar coordinate path, L k represents the particle path, G k Indicates the optimal path.

[0091] S2053. Update the next generation particle swarm according to the polar coordinate path and update direction of each particle in the particle swarm.

[0092] In this embodiment, the next generation particle swarm is updated as follows:

[0093] U k+1 ←U k +ΔU k+1

[0094] Among them, U k+1 represents the polar coordinate path of each particle in the next generation particle swarm, U k Indicates the polar coordinate path of each particle in the current particle swarm, ΔU k+1 Indicates the update direction of each particle.

[0095] S206 , converting the polar coordinate paths of the particles in the next generation particle swarm into Cartesian space, and evaluating the particles converted into Cartesian space using an evaluation function.

[0096] In this embodiment, the polar coordinate paths of the particles in the next generation particle swarm are converted to Cartesian space as follows:

[0097] X k+1 ←U k+1

[0098] x k+1 =x k +l k cosα k

[0099] x k+1 =y k +l k sinαk

[0100] Among them, U k+1 represents the polar coordinate path of each particle in the next generation particle swarm, X k+1 represents the Cartesian coordinate path of each particle in the next generation particle swarm, l k represents the travel length of the drone, α k Indicates the direction of the drone's movement.

[0101] S207. Based on the evaluation results, the initial probability distribution function is updated to obtain the historical optimal path of each particle in the next generation particle swarm, so as to select the global optimal path.

[0102] In this embodiment, the process of updating the initial probability distribution function according to the evaluation results is as follows:

[0103] Figure 5 for Figure 4 The trajectory of the drone in the scenario, assuming that the drone has searched for t-1 steps, but still cannot find the buoy position, so the drone tries to find the buoy position at time t, with the help of prior information such as ocean currents, such as Figure 3 The direction of the red arrow is used to obtain the state transition probability p(x t |x t-1 ), obviously this is also a probability distribution function, which means that the probability of updating from the red direction is higher, and the probability of updating from other directions is lower, so the drone estimates the buoy position x t The probability distribution function of is:

[0104]

[0105] It should be noted that this is the probability distribution of the buoy position estimated by the drone at time t-1. Select an action and enter the next time t. If the buoy position is not observed at this time, the probability distribution diagram at time t is updated as follows:

[0106]

[0107] Among them, η t is the normalization factor, p(o t |x t ) is the conditional probability, indicating that the drone is already at x t Perform observation behavior t , which involves the likelihood probability, so there will be p(o t |x t ).

[0108] About the conditional probability p(o t |x t), specifically as follows:

[0109] The UAV is equipped with detection equipment such as cameras or radars to perform the mission. The UAV moves once in each time period t and performs a scan and observation around itself. t , all detection behaviors are independent of each other (a certain detection result will affect other detection results), and the detection result is defined as a binary variable:

[0110]

[0111] Considering that there may be misjudgments and missed detections in the detection of cameras or radars and other equipment, for example, when searching for salinity buoy sensors, due to internal and external factors such as flight speed and light interference, a seabird flying by or debris floating in the ocean may be mistaken by the camera as a buoy, which is a misjudgment. Alternatively, a buoy may be nearby but obscured by high waves, which is a missed detection. This embodiment introduces a detection likelihood function to characterize this uncertainty, denoted as p(o t ∣x t ), describes that if the target is at x t , UAV detected o t Then, the probability of not being detected can be expressed as:

[0112]

[0113] S208 : Repeat the operation of selecting the global optimal path until the set number of iterations is met.

[0114] In this embodiment, the operation of selecting the global optimal path is repeatedly performed, that is, steps S205 to S207 are repeatedly performed until a set number of iterations is met.

[0115] It should be noted that although the method operations of the above embodiments are described in a particular order, this does not require or imply that the operations must be performed in that particular order, or that all of the illustrated operations must be performed to achieve the desired results. Rather, the depicted steps may be performed in a different order. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into a single step, and / or a single step may be broken down into multiple steps.

[0116] Example 2:

[0117] like Figure 6 As shown, this embodiment provides a polar coordinate trajectory particle swarm optimization system for searching for buoys at sea. The system includes a first initialization module 601, a second initialization module 602, a creation module 603, a third initialization module 604, a first update module 605, an evaluation module 606, a second update module 607, and an iteration module 608. The specific functions of each module are as follows:

[0118] The first initialization module 601 is used to initialize the coordinates of the buoy at the time of loss of contact and obtain ocean data;

[0119] The second initialization module 602 is used to randomly initialize the starting coordinates at the sea surface near the coordinates of the time when the buoy lost contact based on the ocean data, and randomly generate a polar coordinate path from the starting coordinates to form a particle swarm;

[0120] A creation module 603 is used to create an initial probability distribution function of the buoy on the ocean based on the coordinates of the buoy at the time of loss of contact and the starting coordinates, and set polar coordinate trajectory particle swarm optimization parameters;

[0121] The third initialization module 604 is used to initialize the historical optimal path considered by each particle in the particle swarm as the particle's own path according to the initial probability distribution function;

[0122] The first updating module 605 is used to calculate and update the next generation particle swarm according to the polar coordinate path, the particle's own path and the polar coordinate trajectory particle swarm optimization parameters;

[0123] Evaluation module 606, used to convert the polar coordinate paths of particles in the next generation particle swarm into Cartesian space, and evaluate the particles converted into Cartesian space using an evaluation function;

[0124] The second updating module 607 is used to update the initial probability distribution function according to the evaluation result, obtain the historical optimal path of each particle in the next generation particle swarm, and select the global optimal path;

[0125] The iteration module 608 is used to repeatedly perform the operation of selecting the global optimal path until a set number of iterations is met.

[0126] It should be noted that the system provided in this embodiment is only illustrated by the division of the above-mentioned functional modules. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure can be divided into different functional modules to complete all or part of the functions described above.

[0127] Example 3:

[0128] This embodiment provides a computer device, such as Figure 7As shown, it includes a processor 702, a memory, an input device 703, a display device 704, and a network interface 705 connected via a device bus 701. The processor is used to provide computing and control capabilities. The memory includes a non-volatile storage medium 706 and an internal memory 707. The non-volatile storage medium 706 stores an operating device, a computer program, and a database. The internal memory 707 provides an environment for the operation of the operating device and the computer program in the non-volatile storage medium. When the processor 702 executes the computer program stored in the memory, the polar coordinate trajectory particle swarm optimization method of the above-mentioned embodiment 1 is implemented as follows:

[0129] Initialize the coordinates of the buoy at the time of loss of contact and obtain ocean data; based on the ocean data, randomly initialize the starting coordinates on the sea surface near the coordinates of the buoy at the time of loss of contact, and randomly generate polar coordinate paths from the starting coordinates to form a particle swarm; based on the coordinates of the buoy at the time of loss of contact and the starting coordinates, create an initial probability distribution function of the buoy on the ocean, and set the polar coordinate trajectory particle swarm optimization parameters; based on the initial probability distribution function, initialize the historical optimal path considered by each particle in the particle swarm as the particle's own path; based on the polar coordinate path, the particle's own path and the polar coordinate trajectory particle swarm optimization parameters, calculate and update the next generation particle swarm; convert the polar coordinate paths of the particles in the next generation particle swarm into Cartesian space, and use the evaluation function to evaluate the particles converted to Cartesian space; based on the evaluation results, update the initial probability distribution function, obtain the historical optimal path of each particle in the next generation particle swarm, and select the global optimal path; repeat the operation of selecting the global optimal path, and iterate until the set number of iterations is met.

[0130] Example 4:

[0131] This embodiment provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the polar coordinate trajectory particle swarm optimization method of the above embodiment 1 is implemented as follows:

[0132] Initialize the coordinates of the buoy at the time of loss of contact and obtain ocean data; based on the ocean data, randomly initialize the starting coordinates on the sea surface near the coordinates of the buoy at the time of loss of contact, and randomly generate polar coordinate paths from the starting coordinates to form a particle swarm; based on the coordinates of the buoy at the time of loss of contact and the starting coordinates, create an initial probability distribution function of the buoy on the ocean, and set the polar coordinate trajectory particle swarm optimization parameters; based on the initial probability distribution function, initialize the historical optimal path considered by each particle in the particle swarm as the particle's own path; based on the polar coordinate path, the particle's own path and the polar coordinate trajectory particle swarm optimization parameters, calculate and update the next generation particle swarm; convert the polar coordinate paths of the particles in the next generation particle swarm into Cartesian space, and use the evaluation function to evaluate the particles converted to Cartesian space; based on the evaluation results, update the initial probability distribution function, obtain the historical optimal path of each particle in the next generation particle swarm, and select the global optimal path; repeat the operation of selecting the global optimal path, and iterate until the set number of iterations is met.

[0133] It should be noted that the computer-readable storage medium of the present embodiment may be a computer-readable signal medium or a computer-readable storage medium or any combination thereof. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor device, apparatus or component, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0134] In this embodiment, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution device, apparatus, or device. Furthermore, in this embodiment, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable program. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable storage medium other than a computer-readable storage medium that can transmit, propagate, or transfer a program for use by or in conjunction with an instruction execution device, apparatus, or device. The computer program contained on a computer-readable storage medium may be transmitted using any suitable medium, including but not limited to wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.

[0135] The computer readable storage medium can be written in one or more programming languages ​​or a combination thereof to execute the computer program for performing the present embodiment, including object-oriented programming languages ​​such as Java, Python, C++, and conventional procedural programming languages ​​such as C or similar programming languages. The program can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect via the Internet).

[0136] In summary, this method can derive a path that maximizes the probability of a drone detecting a buoy in complex ocean environments and under moving buoys, while maintaining low overhead and achieving global convergence in a short period of time. This method has a wide range of applications in drone target search.

[0137] The foregoing description is merely a preferred embodiment of the present invention. It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention. Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive. The scope of the present invention is defined by the appended claims, not the foregoing description, and all variations that come within the meaning and range of equivalents of the claims are intended to be included within the present invention.

Claims

1. A polar coordinate trajectory particle swarm optimization method for searching for buoys at sea, characterized in that: The method comprises: Initialize the coordinates of the buoy when it loses contact and obtain ocean data; According to the ocean data, the starting coordinates are randomly initialized on the sea surface near the coordinates of the moment when the buoy lost contact, and a polar coordinate path is randomly generated from the starting coordinates to form a particle swarm; According to the coordinates of the buoy at the time of loss of contact and the starting coordinates, the initial probability distribution function of the buoy on the ocean is created, and the polar coordinate trajectory particle swarm optimization parameters are set; According to the initial probability distribution function, the historical optimal path considered by each particle in the initial particle swarm is the particle's own path; Calculate and update the next generation of particle swarm based on the polar coordinate path, the particle's own path, and the polar coordinate trajectory particle swarm optimization parameters; The polar coordinate paths of particles in the next generation particle swarm are converted into Cartesian space, and the particles converted into Cartesian space are evaluated using the evaluation function; According to the evaluation results, the initial probability distribution function is updated to obtain the historical optimal path of each particle in the next generation of particle swarms in order to select the global optimal path; The operation of selecting the global optimal path is repeated until the set number of iterations is met.

2. The polar coordinate trajectory particle swarm optimization method according to claim 1, characterized in that: The particle swarm optimization parameters based on the polar coordinate path, the particle's own path, and the polar coordinate trajectory are calculated and updated to the next generation of particle swarms, specifically including: Use the evaluation function to evaluate each particle in the particle swarm and select the best particle path in the particle swarm as the optimal path; Multiply the polar coordinate path, the difference between the particle's own path and the polar coordinate path, and the difference between the optimal path and the polar coordinate path by the corresponding parameters, and sum them up to calculate the update direction of each particle in the particle swarm; Update the next generation of particle swarm according to the polar coordinate path and update direction of each particle in the particle swarm.

3. The polar coordinate trajectory particle swarm optimization method according to claim 2, characterized in that: The evaluation function is as follows: Among them, f i represents the probability that no buoy is detected from the first time to the i-th time, p t represents the probability of detecting the buoy for the first time at the tth time, It represents the cumulative probability function and characterizes the evaluation function.

4. The polar coordinate trajectory particle swarm optimization method according to claim 2, characterized in that: The polar coordinate path, the difference between the particle's own path and the polar coordinate path, and the difference between the optimal path and the polar coordinate path are multiplied by the corresponding parameters, and the sum is calculated to obtain the update direction of each particle in the particle swarm, as shown in the following formula: Among them, ΔU k+1 Indicates the update direction of each particle, w, is the weight, U k Represents the polar coordinate path, L k represents the particle path, G k Indicates the optimal path.

5. The polar coordinate trajectory particle swarm optimization method according to claim 2, characterized in that: The next generation of particle swarm is updated according to the polar coordinate path and update direction of each particle in the particle swarm, as follows: U k+1 ←U k +ΔU k+1 Among them, U k+1 represents the polar coordinate path of each particle in the next generation particle swarm, U k Indicates the polar coordinate path of each particle in the current particle swarm, ΔU k+1 Indicates the update direction of each particle.

6. The polar coordinate trajectory particle swarm optimization method according to claim 1, characterized in that: The initial probability distribution function is as follows: ρ(x0)=N(x0∣μ=x m ,S) Among them, x0 is the starting coordinate, x m is the coordinate of the buoy when it loses contact, and Σ is the covariance matrix.

7. The polar coordinate trajectory particle swarm optimization method according to claim 1, characterized in that: The polar coordinate path of the particles in the next generation particle swarm is converted to Cartesian space as follows: X k+1 ←U k+1 x k+1 =x k +l k cosα k x k+1 =y k +l k sinα k Among them, U k+1 represents the polar coordinate path of each particle in the next generation particle swarm, X k+1 represents the Cartesian coordinate path of each particle in the next generation particle swarm, l k represents the travel length of the drone, α k Indicates the direction of the drone's movement.

8. A polar coordinate trajectory particle swarm optimization system for searching for buoys at sea, characterized in that: The system comprises: The first initialization module is used to initialize the coordinates of the buoy when it loses contact and obtain ocean data; The second initialization module is used to randomly initialize the starting coordinates on the sea surface near the coordinates of the time when the buoy lost contact based on the ocean data, and randomly generate polar coordinate paths from the starting coordinates to form a particle swarm; A creation module is used to create the initial probability distribution function of the buoy on the ocean based on the coordinates of the buoy when it lost contact and the starting coordinates, and to set the polar coordinate trajectory particle swarm optimization parameters; The third initialization module is used to initialize the historical optimal path considered by each particle in the particle swarm as the particle's own path according to the initial probability distribution function; The first updating module is used to calculate and update the next generation particle swarm according to the polar coordinate path, the particle's own path and the polar coordinate trajectory particle swarm optimization parameters; Evaluation module, used to convert the polar coordinate paths of particles in the next generation particle swarm into Cartesian space and evaluate the particles converted into Cartesian space using evaluation function; The second updating module is used to update the initial probability distribution function according to the evaluation results, obtain the historical optimal path of each particle in the next generation particle swarm, and select the global optimal path; The iteration module is used to repeatedly execute the operation of selecting the global optimal path until the set number of iterations is met.

9. A computer device comprising a processor and a memory for storing a program executable by the processor, characterized in that: When the processor executes the program stored in the memory, the polar coordinate trajectory particle swarm optimization method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing a program, characterized in that: When the program is executed by a processor, the polar coordinate trajectory particle swarm optimization method according to any one of claims 1 to 7 is implemented.

Images