A method and device for ship collision avoidance decision support in restricted waters
By using differential innovative search and sparrow search algorithms in confined waters to optimize ship collision avoidance paths, the problem of collision avoidance decision-making in complex waters is solved and navigation safety is improved.
Patent Information
- Application Number
- CN202410746964.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-06-11
- Publication Date
- 2024-12-24
- Estimated Expiration
- 2044-06-11
AI Technical Summary
The prior art is difficult to effectively support ship collision avoidance decisions in complex restricted waters, especially in the case of navigation restricted waters, which fail to fully consider international maritime collision avoidance rules and multi-constraint issues.
Generate initial population locations by using a differential innovative search algorithm in determining the collision avoidance space of the target ship, and update these locations based on the sparrow search algorithm until the fitness threshold or number of iterations is reached, and adjust the trajectory prediction results in combination with the timing update of the weight factor to determine the avoidance Touch the path.
It has achieved effective collision avoidance decision support for ships under restricted waters, expanded collision avoidance implementation scenarios, and improved navigation safety.
Smart Images
Figure CN118571073B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of ship collision avoidance, and in particular to a method and device for ship collision avoidance decision support in restricted waters. Background Art
[0002] The research on collision avoidance decision-making of marine vessels has attracted more and more attention in the maritime industry and is considered to be one of the effective solutions to reduce the number of marine traffic accidents caused by human factors. However, most of the research is based on open waters or coastal waters with simpler navigation scenarios, because their navigation environment is relatively simple compared with other complex restricted waters.
[0003] Since the navigation environment in confined waters is more complex and the navigation waters are restricted, it is more likely to encounter difficulties in human maneuverability and decision-making. Therefore, the need for research on collision avoidance in confined waters is more urgent.
[0004] Most of the current research on collision avoidance is conducted in open waters or coastal waters, and there is little research on collision avoidance decision-making in restricted waters. In addition, most of them do not consider deviations from the International Regulations for Preventing Collisions at Sea (COLREG) and multi-constraint issues under restricted navigation scenarios. Therefore, studying how ships can avoid collisions when navigating in restricted waters has become a technical problem that needs to be solved urgently. Summary of the invention
[0005] In view of this, it is necessary to provide a method and device for ship collision avoidance decision support in confined waters to solve the problem that the current decision support scheme for ship collision avoidance in complex confined waters is lacking.
[0006] In order to solve the above problems, the present invention provides a method for supporting collision avoidance decisions of ships in restricted waters, comprising:
[0007] When it is determined that there is a risk of collision with the target ship, the collision avoidance space of the target ship is determined based on the characteristics of restricted waters, the maneuverability of the ship and the collision avoidance principle;
[0008] Based on the difference innovation search algorithm, an initial population is generated in the collision avoidance space, and a trajectory prediction is performed on the position of the initial population to obtain the fitness corresponding to the position of the initial population;
[0009] The initial population position is updated multiple times based on the sparrow search algorithm until the fitness corresponding to the updated initial population position is greater than a preset fitness threshold, or the number of iterations is greater than a preset maximum number of iterations;
[0010] Based on the time series update weight factor, the discoverer position is adjusted, and the trajectory prediction result of the updated initial population position is used as the collision avoidance path of the target ship.
[0011] In a possible implementation, the fitness corresponding to the initial population position is obtained based on a trajectory set obtained by performing trajectory prediction on the initial population position.
[0012] In a possible implementation, the initial population generated by the difference innovation search algorithm in the collision avoidance space is calculated based on the following formula:
[0013]
[0014] in, Indicates Candidate solution The elements in the positions have randomly generated upper and lower bounds. and , Representation interval The uniform distribution on The collision avoidance decision problem is The lower bound of the dimensional space, The collision avoidance decision problem is The upper bound of the dimensional space;
[0015] The fitness corresponding to the initial population position is calculated based on the following formula:
[0016]
[0017] in, represents fitness, represents the distance coefficient, represents the time coefficient, and The sum is 1, Indicates The distance between the avoidance trajectory point and the channel boundary, Indicates The minimum longitudinal distance between the avoidance track point and other vessels, represents half the channel width, Indicates the maximum avoidance time, Indicates the shortest avoidance time.
[0018] In a possible implementation, the performing trajectory prediction on the initial population position includes:
[0019] Predict ship trajectory, ship heading and ship speed.
[0020] In a possible implementation, the ship trajectory motion prediction is performed based on the following formula:
[0021]
[0022] in, Indicates the bow angle, represents the first derivative of the bow angle, represents the second-order derivative of the bow angle, and represents the parameters of the Nomoto model, for A nonlinear function of Indicates the rudder angle.
[0023] In a possible implementation, the ship heading prediction is performed based on the following formula:
[0024]
[0025] in, express The ship's heading at the moment, express Systematic deviation of time, represents the proportionality coefficient, represents the integral coefficient, represents the differential coefficient, Represents the restricted waters constraint coefficient.
[0026] In a possible implementation, the ship speed prediction is performed based on the following formula:
[0027]
[0028] in, Indicates the ship speed, represents the first derivative of the ship's velocity, represents the first derivative of the bow angle, represents the rudder angle, Indicates the propeller speed, and represents the thrust coefficient, , and Represents the drag coefficient.
[0029] The present invention also provides a restricted waters ship collision avoidance decision support device, comprising:
[0030] A determination module, for determining the collision avoidance space of the target ship based on the characteristics of restricted waters, the maneuverability of the ship and the collision avoidance principle when it is determined that the target ship has a collision risk;
[0031] A prediction module, used for generating an initial population in the collision avoidance space based on a difference innovation search algorithm, and performing trajectory prediction on the position of the initial population to obtain a fitness corresponding to the position of the initial population;
[0032] An updating module, used for updating the initial population position multiple times based on a sparrow search algorithm, until the fitness corresponding to the updated initial population position is greater than a preset fitness threshold, or the number of iterations is greater than a preset maximum number of iterations;
[0033] The application module is used to update the weight factor based on the time series, adjust the position of the discoverer, and use the trajectory prediction result of the updated initial population position as the collision avoidance path of the target ship.
[0034] The present invention also provides an electronic device, including a memory and a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the above-mentioned method for supporting ship collision avoidance decision in restricted waters is implemented.
[0035] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned method for supporting ship collision avoidance decision in restricted waters is implemented.
[0036] The beneficial effects of the present invention are as follows: a method and device for supporting collision avoidance decisions for ships in restricted waters provided by the present invention first determine the collision avoidance space of a target ship through the collision avoidance principle, thereby providing a prerequisite for determining a subsequent collision avoidance path, and then randomly select an initial population position in the collision avoidance space and perform trajectory prediction and fitness calculation, thereby providing a discrimination condition for a subsequent sparrow search algorithm, and finally continuously optimizing the collision avoidance path through the sparrow search algorithm until an iterative termination condition is reached, thereby obtaining a final collision avoidance path, thereby realizing collision avoidance decision support for ships in restricted waters, expanding the ship collision avoidance implementation scenario, and improving the safety of ship navigation. BRIEF DESCRIPTION OF THE DRAWINGS
[0037] Figure 1 A schematic diagram of a flow chart of an embodiment of a method for supporting collision avoidance decisions of ships in restricted waters provided by the present invention;
[0038] Figure 2 A schematic diagram of a flow chart of an embodiment of an algorithm for estimating a collision avoidance path for ships in restricted waters provided by the present invention;
[0039] Figure 3 A schematic structural diagram of an embodiment of a collision avoidance decision support device for ships in restricted waters provided by the present invention;
[0040] Figure 4 A schematic structural diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION
[0041] The preferred embodiments of the present invention are described in detail below in conjunction with the accompanying drawings, wherein the accompanying drawings constitute a 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 used to limit the scope of the present invention.
[0042] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.
[0043] In the description of the present invention, reference to an "embodiment" means that a particular feature, structure, or characteristic described in conjunction with the embodiment may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive of other embodiments. It is explicitly and implicitly understood by those skilled in the art that the described embodiments may be combined with other embodiments.
[0044] The research on collision avoidance decision-making of marine vessels has attracted more and more attention in the maritime industry and is considered to be one of the effective solutions to reduce the number of marine traffic accidents caused by human factors. However, most of the research is based on open waters or coastal waters with simpler navigation scenarios, because their navigation environment is relatively simple compared with other complex restricted waters.
[0045] Since the navigation environment in confined waters is more complex and the navigation waters are restricted, it is more likely to encounter difficulties in human maneuverability and decision-making. Therefore, the need for research on collision avoidance in confined waters is more urgent.
[0046] Most of the current research on collision avoidance is conducted in open waters or coastal waters, and there is little research on collision avoidance decision-making in restricted waters. In addition, most of them do not consider the deviation from COLREG and the multi-constraint problem under restricted navigation scenarios. Therefore, studying how ships can avoid collisions when navigating in restricted waters has become a technical problem that needs to be solved urgently.
[0047] In order to solve the above problems, the present invention provides a collision avoidance decision support solution for ships in restricted waters, so that ships can avoid collisions in restricted waters.
[0048] The specific embodiments are described in detail below:
[0049] A specific embodiment of the present invention discloses a method for supporting ship collision avoidance decision in restricted waters, combining Figure 1 Come and see, Figure 1The flowchart of an embodiment of the method for ship collision avoidance decision support in restricted waters provided by the present invention includes steps S101 to S104, wherein:
[0050] In step S101, when it is determined that there is a collision risk with the target ship, the collision avoidance space of the target ship is determined based on the characteristics of the restricted waters, the maneuverability of the ship and the collision avoidance principle;
[0051] In step S102, an initial population is generated in the collision avoidance space based on a difference innovation search algorithm, and a trajectory prediction is performed on the initial population position to obtain a fitness corresponding to the initial population position;
[0052] In step S103, the initial population position is updated multiple times based on the sparrow search algorithm until the fitness corresponding to the updated initial population position is greater than a preset fitness threshold, or the number of iterations is greater than a preset maximum number of iterations;
[0053] In step S104, the weight factor is updated based on the time series, the discoverer position is adjusted, and the trajectory prediction result of the updated initial population position is used as the collision avoidance path of the target ship.
[0054] During implementation, it can be first determined whether there is a collision risk for the target ship. For example, a velocity obstacle (VO) algorithm can be used to determine whether there is a collision risk for the target ship.
[0055] When it is determined that there is a collision risk with the target ship, the collision avoidance space of the target ship can be determined according to the collision avoidance principle. For example, the collision avoidance space of the target ship can be determined according to the collision avoidance principle based on COLREGs, the collision avoidance principle based on navigation practice, etc.
[0056] After determining the collision avoidance space of the target ship, an initial population can be generated in the collision avoidance space according to the difference innovation search algorithm, and then the trajectory of the initial population position is predicted, and the fitness corresponding to the initial population position is calculated according to the predicted avoidance trajectory.
[0057] Then, the initial population position can be updated multiple times by the sparrow search algorithm until the fitness corresponding to the updated initial population position is greater than the preset fitness threshold, or the number of iterations is greater than the preset maximum number of iterations, and the algorithm can be terminated. Finally, the weight factor is updated according to the time sequence, the discoverer position is adjusted, and the final trajectory prediction result of the initial population position is used as the collision avoidance path of the target ship.
[0058] The restricted waters ship collision avoidance decision support method provided by the present invention can be applied to ship collision avoidance scenarios in restricted waters, or ship collision avoidance scenarios in other restricted waters, and the present invention does not make specific limitations on this.
[0059] Compared with the prior art, the method for ship collision avoidance decision support in restricted waters provided in this embodiment first determines the collision avoidance space of the target ship through the collision avoidance principle, providing a prerequisite for the subsequent collision avoidance path determination, and then randomly selects the initial population position in the collision avoidance space and performs trajectory prediction and fitness calculation, providing discrimination conditions for the subsequent sparrow search algorithm, and finally continuously optimizes the collision avoidance path through the sparrow search algorithm until the iteration termination condition is reached, thereby obtaining the final collision avoidance path, realizing collision avoidance decision support for ships in restricted waters, expanding the ship collision avoidance implementation scenario, and improving the safety of ship navigation.
[0060] Exemplarily, the fitness corresponding to the initial population position is obtained based on a trajectory set obtained by performing trajectory prediction on the initial population position.
[0061] Specifically, the fitness corresponding to the initial population position can be calculated based on a trajectory set obtained by performing trajectory prediction on the initial population position.
[0062] Exemplarily, the initial population generated by the difference innovation search algorithm in the collision avoidance space is calculated based on the following formula:
[0063]
[0064] in, Indicates Candidate solution The elements in the positions have randomly generated upper and lower bounds. and , Representation interval The uniform distribution on The collision avoidance decision problem is The lower bound of the dimensional space, The collision avoidance decision problem is The upper bound of the dimensional space;
[0065] The fitness corresponding to the initial population position is calculated based on the following formula:
[0066]
[0067] in, represents fitness, represents the distance coefficient, represents the time coefficient, and The sum is 1, Indicates The distance between the avoidance trajectory point and the channel boundary, Indicates The minimum longitudinal distance between the avoidance track point and other vessels, represents half the channel width, Indicates the maximum avoidance time, Indicates the shortest avoidance time.
[0068] Specifically, the fitness corresponding to the initial population and the initial population position can be calculated according to the above formula.
[0069] Exemplarily, the performing trajectory prediction on the initial population position includes:
[0070] Predict ship trajectory, ship heading and ship speed.
[0071] Specifically, when performing trajectory prediction on the initial population position, three aspects, namely ship motion, ship heading and ship speed, can be predicted respectively.
[0072] Exemplarily, the ship trajectory motion prediction is performed based on the following formula:
[0073]
[0074] in, Indicates the bow angle, represents the first derivative of the bow angle, represents the second-order derivative of the bow angle, and represents the parameters of the Nomoto model, for A nonlinear function of Indicates the rudder angle.
[0075] Specifically, the ship motion can be predicted according to the above formula.
[0076] Exemplarily, the ship heading prediction is performed based on the following formula:
[0077]
[0078] in, express The ship's heading at the moment, express Systematic deviation of time, represents the proportionality coefficient, represents the integral coefficient, represents the differential coefficient, Represents the restricted waters constraint coefficient.
[0079] Specifically, the ship's heading can be predicted according to the above formula.
[0080] Exemplarily, the ship speed prediction is performed based on the following formula:
[0081]
[0082] in, Indicates the ship speed, represents the first derivative of the ship's velocity, represents the first derivative of the bow angle, represents the rudder angle, Indicates the propeller speed, and represents the thrust coefficient, , and Represents the drag coefficient.
[0083] Specifically, the ship speed can be predicted according to the above formula.
[0084] The following is a specific application scenario to better illustrate the technical solution of the present invention:
[0085] The purpose of path estimation is to find the best avoidance path while considering constraints such as ship maneuverability, navigation environment, and navigation rules. Figure 2 Come and see, Figure 2 This is a flow chart of an embodiment of the collision avoidance path estimation algorithm for ships in restricted waters provided by the present invention. The path estimation of the present invention is mainly divided into a trajectory prediction module, a fitness function construction module and a sparrow search algorithm module. After detecting the collision risk and constructing the collision avoidance principle, the avoidance space that can be used for path estimation is obtained. First, the initial population position is randomly generated in the avoidance space. Second, the trajectory prediction module is used to generate the trajectory set corresponding to the initial population position. Then, the established fitness function can calculate the fitness set When the optimal fitness value Greater than the set fitness threshold Or the number of iterations is greater than the maximum number of iterations set When , the termination condition will occur. Otherwise, the population position is updated by the sparrow search algorithm To get a better population location , and then repeat the above process until the termination condition is met. The sparrow search algorithm used in the present invention can refer to the sparrow search algorithm in the prior art.
[0086] The embodiment of the present invention also provides a device for supporting ship collision avoidance decision in restricted waters, Figure 3 Come and see, Figure 3This is a schematic diagram of the structure of an embodiment of a ship collision avoidance decision support device in restricted waters provided by the present invention. The ship collision avoidance decision support device 300 in restricted waters includes:
[0087] A determination module 301 is used to determine the collision avoidance space of the target ship based on the characteristics of the restricted waters, the maneuverability of the ship and the collision avoidance principle when it is determined that the target ship has a collision risk;
[0088] A prediction module 302 is used to generate an initial population in the collision avoidance space based on a difference innovation search algorithm, and to perform trajectory prediction on the initial population position to obtain a fitness corresponding to the initial population position;
[0089] An updating module 303 is used to update the initial population position multiple times based on the sparrow search algorithm until the fitness corresponding to the updated initial population position is greater than a preset fitness threshold, or the number of iterations is greater than a preset maximum number of iterations;
[0090] The application module 304 is used to update the weight factor based on the time series, adjust the discoverer position, and use the trajectory prediction result of the updated initial population position as the collision avoidance path of the target ship.
[0091] The specific implementation methods of each module of the restricted waters ship collision avoidance decision support device can refer to the description of the above-mentioned restricted waters ship collision avoidance decision support method, and have similar beneficial effects, which will not be repeated here.
[0092] It should be noted that the restricted waters ship collision avoidance decision support device can be set in the ship control computer or in the ship's scanning radar, and the present invention does not make specific limitations on this.
[0093] The embodiment of the present invention further provides an electronic device, Figure 4 Come and see, Figure 4 This is a structural diagram of an embodiment of an electronic device provided by the present invention. The electronic device 400 includes a processor 401, a memory 402, and a computer program stored in the memory 402 and executable on the processor 401. When the processor 401 executes the program, the restricted waters ship collision avoidance decision support method as described above is implemented.
[0094] As a preferred embodiment, the electronic device 400 further includes a display 403 for displaying that the processor 401 executes the above-mentioned restricted waters ship collision avoidance decision support method.
[0095] Exemplarily, the computer program may be divided into one or more modules / units, one or more modules / units are stored in the memory 402, and executed by the processor 401 to complete the present invention. One or more modules / units may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program in the electronic device 400. For example, the computer program may be divided into the determination module 301, the prediction module 302, the update module 303, and the application module 304 in the above embodiment, and the specific functions of each module are as described above, and are not described one by one here.
[0096] The electronic device 400 may be a desktop computer, a notebook, a PDA or a smart phone with an adjustable camera module.
[0097] Among them, the processor 401 may be an integrated circuit chip with signal processing capabilities. The above-mentioned processor 401 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present invention can be implemented or executed. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.
[0098] The memory 402 may be, but is not limited to, a random access memory (RAM), a read only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electric erasable programmable read-only memory (EEPROM), etc. The memory 402 is used to store programs, and the processor 401 executes the program after receiving the execution instruction. The process definition method disclosed in any of the embodiments of the present invention may be applied to the processor 401 or implemented by the processor 401.
[0099] The display 403 may be an LCD display screen or an LED display screen, for example, a display screen on a mobile phone.
[0100] Understandably, Figure 4 The structure shown is only a schematic diagram of the structure of the electronic device 400. The electronic device 400 may also include Figure 4 More or fewer components as shown. Figure 4 Each component shown in the figure can be implemented by hardware, software or a combination thereof.
[0101] The electronic device provided according to the above-mentioned embodiment of the present invention can be implemented with reference to the specific description of the above-mentioned method for supporting collision avoidance decisions of ships in restricted waters according to the present invention, and has similar beneficial effects as the above-mentioned method for supporting collision avoidance decisions of ships in restricted waters, which will not be repeated here.
[0102] An embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the above-mentioned method for supporting ship collision avoidance decision in restricted waters is implemented.
[0103] Generally speaking, the computer instructions for implementing the method of the present invention can be carried by any combination of one or more computer-readable storage media. Non-transitory computer-readable storage media can include any computer-readable media except for the signal itself that is temporarily propagating.
[0104] Computer-readable storage media may be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more conductors, 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), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium that contains or stores a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.
[0105] Computer program codes for performing the operations of the present invention may be written in one or more programming languages or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages, in particular, Python suitable for neural network computing and platform frameworks based on TensorFlow, PyTorch, etc. may be used. The program code may be executed entirely on the user's computer, partially on the user's computer, as an independent 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 may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0106] Those skilled in the art will appreciate that all or part of the processes of the above-mentioned embodiments can be implemented by instructing related hardware through a computer program, and the program can be stored in a computer-readable storage medium, wherein the computer-readable storage medium is a disk, an optical disk, a read-only storage memory, or a random access memory, etc.
[0107] The present invention discloses a method and device for supporting collision avoidance decision of ships in restricted waters. Firstly, the collision avoidance space of a target ship is determined by the collision avoidance principle, so as to provide a prerequisite for determining a subsequent collision avoidance path. Then, the initial population position is randomly selected in the collision avoidance space and trajectory prediction and fitness calculation are performed, so as to provide a discrimination condition for the subsequent sparrow search algorithm. Finally, the collision avoidance path is continuously optimized by the sparrow search algorithm until the iteration termination condition is reached, so as to obtain the final collision avoidance path. The method realizes collision avoidance decision support for ships in restricted waters, expands the ship collision avoidance implementation scenario, and improves the safety of ship navigation.
[0108] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by any technician familiar with the technical field within the technical scope disclosed by the present invention should be covered within the protection scope of the present invention.
Claims
1. A decision support method for ship collision avoidance in restricted waters, characterized in that: include: When it is determined that there is a risk of collision with the target ship, the collision avoidance space of the target ship is determined based on the characteristics of restricted waters, the maneuverability of the ship and the collision avoidance principle; Based on the difference innovation search algorithm, an initial population is generated in the collision avoidance space, and a trajectory prediction is performed on the position of the initial population to obtain the fitness corresponding to the position of the initial population; The initial population position is updated multiple times based on the sparrow search algorithm until the fitness corresponding to the updated initial population position is greater than a preset fitness threshold, or the number of iterations is greater than a preset maximum number of iterations; Based on the time series update weight factor, the discoverer position is adjusted, and the trajectory prediction result of the updated initial population position is used as the collision avoidance path of the target ship; The fitness corresponding to the initial population position is obtained based on the trajectory set obtained by trajectory prediction of the initial population position; The initial population generated by the difference innovation search algorithm in the collision avoidance space is calculated based on the following formula: in, Indicates Candidate solution The elements in the positions have randomly generated upper and lower bounds. and , Representation interval The uniform distribution on The collision avoidance decision problem is The lower bound of the dimensional space, The collision avoidance decision problem is The upper bound of the dimensional space; The fitness corresponding to the initial population position is calculated based on the following formula: in, represents fitness, represents the distance coefficient, represents the time coefficient, and The sum is 1, Indicates The distance between the avoidance trajectory point and the channel boundary, Indicates The minimum longitudinal distance between the avoidance track point and other vessels, represents half the channel width, Indicates the maximum avoidance time, Indicates the shortest avoidance time; The trajectory prediction of the initial population position includes: Predict ship trajectory, ship heading and ship speed; The ship speed prediction is based on the following formula: in, Indicates the ship speed, represents the first derivative of the ship's velocity, represents the first derivative of the bow angle, represents the rudder angle, Indicates the propeller speed, and represents the thrust coefficient, , and Represents the drag coefficient.
2. The method for ship collision avoidance decision support in restricted waters according to claim 1, characterized in that: The ship trajectory motion prediction is based on the following formula: in, Indicates the bow angle, represents the first derivative of the bow angle, represents the second-order derivative of the bow angle, and represents the parameters of the Nomoto model, for A nonlinear function of Indicates the rudder angle.
3. The method for ship collision avoidance decision support in restricted waters according to claim 1, characterized in that: The ship heading prediction is based on the following formula: in, express The ship's heading at the moment, express Systematic deviation of time, represents the proportionality coefficient, represents the integral coefficient, represents the differential coefficient, Represents the restricted waters constraint coefficient.
4. A collision avoidance decision support device for ships in restricted waters, characterized in that: include: A determination module, for determining the collision avoidance space of the target ship based on the characteristics of restricted waters, the maneuverability of the ship and the collision avoidance principle when it is determined that the target ship has a collision risk; A prediction module generates an initial population in the collision avoidance space based on a difference innovation search algorithm, and performs trajectory prediction on the initial population position to obtain a fitness corresponding to the initial population position; An updating module, used for updating the initial population position multiple times based on a sparrow search algorithm, until the fitness corresponding to the updated initial population position is greater than a preset fitness threshold, or the number of iterations is greater than a preset maximum number of iterations; An application module, based on a time-series update weight factor, adjusts the position of the discoverer, and is used to use the trajectory prediction result of the updated initial population position as the collision avoidance path of the target ship; The fitness corresponding to the initial population position is obtained based on the trajectory set obtained by trajectory prediction of the initial population position; The initial population generated by the difference innovation search algorithm in the collision avoidance space is calculated based on the following formula: in, Indicates Candidate solution The elements in the positions have randomly generated upper and lower bounds. and , Representation interval The uniform distribution on The collision avoidance decision problem is The lower bound of the dimensional space, The collision avoidance decision problem is The upper bound of the dimensional space; The fitness corresponding to the initial population position is calculated based on the following formula: in, represents fitness, represents the distance coefficient, represents the time coefficient, and The sum is 1, Indicates The distance between the avoidance trajectory point and the channel boundary, Indicates The minimum longitudinal distance between the avoidance track point and other vessels, represents half the channel width, Indicates the maximum avoidance time, Indicates the shortest avoidance time; The trajectory prediction of the initial population position includes: Predict ship trajectory, ship heading and ship speed; The ship speed prediction is based on the following formula: in, Indicates the ship speed, represents the first derivative of the ship's velocity, represents the first derivative of the bow angle, represents the rudder angle, Indicates the propeller speed, and represents the thrust coefficient, , and Represents the drag coefficient.
5. An electronic device, characterized in that: The invention comprises a memory and a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the method for supporting collision avoidance decision of ships in restricted waters according to any one of claims 1 to 3 is implemented.
6. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the method for supporting ship collision avoidance decision in restricted waters as claimed in any one of claims 1 to 3 is implemented.