CN111709571A

CN111709571A - Ship collision avoidance route determining method, device, equipment and storage medium

Info

Publication number: CN111709571A
Application number: CN202010528259.9A
Authority: CN
Inventors: 王红波; 赵毅; 李金鑫; 赵巍; 张展硕; 周正; 王岩
Original assignee: Jilin University
Current assignee: Jilin University
Priority date: 2020-06-09
Filing date: 2020-06-09
Publication date: 2020-09-25
Anticipated expiration: 2040-06-09
Also published as: CN111709571B

Abstract

The invention is suitable for the technical field of ship navigation, and provides a method, a device, equipment and a storage medium for determining a ship collision avoidance route, wherein the method comprises the following steps: when the collision risk degree between the first ship and the second ship is larger than a preset threshold value, acquiring a collision avoidance parameter array set of the first ship; determining an optimal collision avoidance parameter array set according to the collision avoidance parameter array set and a preset dual-standard multi-target collision avoidance algorithm; and determining a collision avoidance route of the first ship according to the optimal collision avoidance parameter array set. The ship collision avoidance method adopts a dual-standard multi-target genetic algorithm combining pareto evolution and non-pareto evolution to solve a ship collision avoidance route, and accelerates the convergence speed of a population and increases the diversity of the population by improving the updating mode of the non-pareto evolved population, so that the calculation efficiency of the algorithm is accelerated, and the uniformity of a front edge solution set is ensured; meanwhile, analysis of simulation results proves that the method can solve safe and economic paths in various meeting scenes.

Description

Ship collision avoidance route determining method, device, equipment and storage medium

Technical Field

The invention belongs to the technical field of ship navigation, and particularly relates to a method, a device and equipment for determining a ship collision avoidance route and a storable medium.

Background

Since the marine transportation of ships, ship collision avoidance has been one of the major concerns for people on ships. In the last century, international maritime collision avoidance regulations (COLREGS) were established by various countries and international maritime organizations in a united manner. The COLREGS rules stipulate ship collision prevention responsibility under various meeting conditions, ship driving and navigation rules under different visibility conditions, light sign representing information on ships and the like. However, collision avoidance of a ship is a complex process, collision danger cannot be identified only through the COLREGS rule, and a safe collision avoidance route cannot be obtained at the same time.

At present, a large number of algorithms for planning a ship collision avoidance route are proposed, and Szlapczynski et al find an optimal collision avoidance path by using an evolutionary computing method in 2012. The evolutionary computation is an optimization tool, is a group of random optimization algorithms, and is based on a charles darwinian biological evolution theory, namely the basic principle of the evolutionary computation is survival of a suitable person. Kang et al, in an effort to reduce the effect of human factors, plan ship paths using Particle Swarm Optimization (PSO). Xu et al use a risk-immune algorithm to speed up the search for the optimal path. Lyu, etc. with the good real-time performance of the artificial potential field method, the collision avoidance route planning under the condition that a plurality of ships meet is solved. Most of the above collision avoidance studies assume that the ship implements a collision avoidance strategy, while other target ships keep their course unchanged. Aiming at the problem, Kim et al apply a distributed algorithm to collision avoidance research and improve the conventional method, wherein the algorithm obtains the navigation intention of other ships by utilizing communication between the ships, and determines the navigation route of each ship in the current time period through comparison. However, the above methods for planning the collision avoidance route of the ship do not fully consider the unpredictable behavior of the own behavior of the ship, and still have the problems of long time for planning the collision avoidance route and poor coordination of the collision avoidance behaviors of the ships.

Disclosure of Invention

The embodiment of the invention aims to provide a method for determining a ship collision avoidance route, and aims to solve the problems that the existing ship collision avoidance route planning methods do not fully consider unpredictable behavior of the ship, and the time length for planning the collision avoidance route and the coordination of avoidance behaviors among all ships are poor.

The embodiment of the invention is realized in such a way that a ship collision avoidance route determining method comprises the following steps:

when the collision risk degree between a first ship and a second ship is larger than a preset threshold value, acquiring a collision avoidance parameter array set of the first ship;

determining an optimal collision avoidance parameter array set according to the collision avoidance parameter array set and a preset dual-standard multi-target collision avoidance algorithm; the preset double-standard multi-target collision avoidance algorithm is obtained by combining a rapid non-dominated sorting genetic algorithm and a multi-target evolutionary algorithm based on decomposition based on a double-standard frame;

and determining the collision avoidance route of the first ship according to the optimal collision avoidance parameter array set.

Another object of an embodiment of the present invention is to provide a ship collision avoidance line determining apparatus, including:

the collision avoidance parameter array set acquisition unit is used for acquiring a collision avoidance parameter array set of the first ship when the collision risk degree between the first ship and the second ship is greater than a preset threshold value;

the optimal collision avoidance parameter array set determining unit is used for determining an optimal collision avoidance parameter array set according to the collision avoidance parameter array set and a preset dual-standard multi-target collision avoidance algorithm; the preset double-standard multi-target collision avoidance algorithm is obtained by combining a rapid non-dominated sorting genetic algorithm and a multi-target evolutionary algorithm based on decomposition based on a double-standard frame; and

and the collision avoidance route determining unit is used for determining the collision avoidance route of the first ship according to the optimal collision avoidance parameter array set.

Another object of an embodiment of the present invention is a computer apparatus, comprising a memory and a processor, the memory having stored therein a computer program, which, when executed by the processor, causes the processor to execute the steps of the ship collision avoidance route determination method.

Another object of an embodiment of the present invention is a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, causes the processor to execute the steps of the ship collision avoidance route determining method.

The ship collision avoidance route determining method provided by the embodiment of the invention quantizes a collision avoidance route by using a collision avoidance parameter array set, determines an optimal collision avoidance parameter array set by using a double-standard multi-target collision avoidance algorithm obtained by combining a fast non-dominated sorting genetic algorithm based on a double-standard frame and a multi-target evolution algorithm based on decomposition, and determines the collision avoidance route according to the optimal collision avoidance parameter array set; in consideration of the fact that the final pareto front edge can be in an irregular shape due to the complexity of a multi-target meeting environment, the ship collision avoidance route is solved by adopting a dual-standard multi-target genetic algorithm combining pareto evolution and non-pareto evolution, the convergence speed of the population is accelerated and the diversity of the population is increased by improving the updating mode of the non-pareto evolved population, so that the calculation efficiency of the algorithm is improved, and meanwhile, the uniformity of front edge solution set can be guaranteed; meanwhile, analysis of simulation results proves that the method can solve safe and economic paths in various meeting scenes.

Drawings

Fig. 1 is a flowchart illustrating an implementation of a method for determining a collision avoidance line of a ship according to an embodiment of the present invention;

fig. 2 is a flowchart of an implementation of a collision risk determining method according to an embodiment of the present invention;

FIG. 3 is a schematic diagram of a quarter ship domain provided by an embodiment of the invention;

FIG. 4 is a schematic diagram of a velocity barrier method in conjunction with the field of ships according to an embodiment of the present invention;

fig. 5 is a schematic diagram of the degree of congestion provided by the embodiment of the present invention;

FIG. 6 is a schematic exploded view of a Chebyshev according to an embodiment of the present invention;

FIG. 7 is a diagram of dual standard (BCE) implementation provided in accordance with an embodiment of the present invention;

FIG. 8 is a flowchart illustrating the steps of determining an optimal collision avoidance parameter array set according to an embodiment of the present invention;

FIG. 9 is a schematic view of a collision avoidance path according to an embodiment of the present invention;

fig. 10 is a schematic diagram of the ant lion algorithm provided by the embodiment of the present invention;

FIG. 11 is a graph of the results of the operation of ZDT1 and ZDT2 provided by embodiments of the present invention;

fig. 12 is a flowchart illustrating an implementation of another method for determining a collision avoidance line of a ship according to an embodiment of the present invention;

FIG. 13 is a schematic diagram of a step-by-step cooperative collision avoidance strategy according to an embodiment of the present invention;

fig. 14 is a flowchart of an implementation of another method for determining a ship collision avoidance line according to an embodiment of the present invention;

FIG. 15 is a GUI interface of a collision avoidance planning simulation design platform according to an embodiment of the present invention;

fig. 16 is a schematic view of a collision-avoidance route under a cross meeting situation of two ships according to an embodiment of the present invention;

fig. 17 is a schematic view of a collision-preventing route under a meeting situation of two ships according to an embodiment of the present invention;

fig. 18 is a schematic view of a collision-avoidance route under a situation where two ships overtake and meet according to an embodiment of the present invention;

fig. 19 is a multi-ship collision avoidance scene 1 (left) and a collision avoidance route map (right) provided in the embodiment of the present invention;

fig. 20 is a diagram of a collision avoidance situation 1 of a ship at each time according to an embodiment of the present invention;

fig. 21 is a multi-ship collision avoidance scene 2 (left) and a collision avoidance route map (right) provided by the embodiment of the present invention;

fig. 22 is a diagram of collision avoidance at various times of a ship according to an embodiment of the present invention;

fig. 23 is a view of a multi-ship collision avoidance scene (left) and a collision avoidance route map (right) under a static obstacle according to the embodiment of the present invention;

fig. 24 is a diagram illustrating another collision avoidance situation of the ship at various times according to the embodiment of the present invention;

fig. 25 is a block diagram of a structure of a ship collision avoidance line determining apparatus according to an embodiment of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

Fig. 1 is a flowchart of an implementation of a method for determining a ship collision avoidance line according to an embodiment of the present invention, which is described in detail below.

Step S101, when the collision risk degree between a first ship and a second ship is larger than a preset threshold value, acquiring a collision avoidance parameter array set of the first ship.

In the embodiment of the invention, the collision avoidance parameter array set is generated by a numerical range corresponding to a plurality of collision avoidance parameters, the collision avoidance parameter array set comprises a plurality of collision avoidance parameter arrays, and the collision avoidance parameter arrays comprise numerical values of the collision avoidance parameters randomly determined from the numerical range corresponding to the collision avoidance parameters; the collision avoidance parameters comprise straight voyage time, avoidance amplitude at an avoidance point, avoidance time and re-voyage amplitude.

In the embodiment of the present invention, the risk of collision between the first vessel and the second vessel may be represented by a minimum meeting distance DCPA between the first vessel (own vessel) and the second vessel (target vessel) and a time to reach the closest meeting distance TCPA, where DCPA is a positive value when the target vessel is going to pass through the bow of the own vessel; otherwise, it is a negative value. When the TCPA is positive, the collision risk still exists between the ship and the target ship; when TCPA is negative, the ship passes through the target ship, and no collision risk exists between the ship and the target ship.

In a preferred embodiment of the present invention, the risk of collision between the first vessel and the second vessel may also be calculated from a vessel domain, and the motion parameters related to the first vessel and the second vessel are calculated based on a risk model, as shown in fig. 2, before the step S101, the method includes:

step S201, obtaining obstacle area related parameters of the first ship.

In the embodiment of the invention, the acquisition of the relevant parameters of the obstacle area is to determine the field of the ship, and the parameters comprise the position of the ship, the speed of the ship, the length of the ship, the course of the ship, the advance distance of the ship steering capacity and the initial diameter value of the turning circle.

Step S202, determining a speed obstacle area of the first ship according to the obstacle area related parameters of the first ship.

In the embodiment of the present invention, the speed obstacle area is a ship field, the ship field is a quaternion ship field, as shown in fig. 3, the position of the ship is (x, y), the speed of the ship is v, the length of the ship is L, and an equation in the ship field can be expressed as:

wherein R is_fore，R_aft，R_starbAnd R_portRepresenting the radial length of the marine field. θ is the heading of the vessel.

Wherein A is_DAnd D_TIs the advance and the initial diameter of the rotation representing the steering capacity of the ship. Normally, the ship will indicate the values of its own advance and initial diameter of the spin, but for the target ship in the meeting, it may be difficult to obtain the relevant parameters of its spin test. Therefore, according to the parameters of other ships, the advance distance value and the initial diameter value of the spin of the ship are calculated by an empirical formula:

step S203, acquiring a velocity vector of the first ship and a velocity vector of the second ship.

Step S204, determining the collision risk between the first ship and the second ship according to the speed vector of the first ship, the speed vector of the second ship and the speed obstacle area of the first ship.

In the embodiment of the invention, by combining the speed obstacle method and the quarter ship field, the speed obstacle method not only accords with COLREGS rules, but also can change the shape according to different ships, as shown in figure 4. The navigation danger of the ship is obtained by judging whether the speed vector of the ship is in the speed obstacle area, and the fact that the speed vector of the ship is in the speed obstacle area means that the ship travels at the speed is inevitably invaded into the field of the target ship at a certain future time, and the invasion degree is related to the degree of the ship field in which the target ship is reduced, wherein the speed of the ship is in the speed obstacle area. Thus, the risk between vessels can be calculated as:

wherein L is₀，L₁And L₂The distance between the intersection point of the ship speed vector and the central line of the cutting line and the center point of the target ship and the intersection point of the cutting line and the boundary of the speed obstacle area. (x)₀，y₀) Is the position of the ship, (v)_x，v_y) Is the own ship velocity vector. x is the number of₀·v_y-y₀·v_xTo determine whether the velocity vector of the ship is above or below the center line. Since the centerline represents the course of the target vessel in geometric space, this means that the closer to the centerline the greater the hazard, and the farther from the centerline the lesser the hazard. The risk calculated by the formula (5) has a value of 1 at the center line and 0.5 at the boundary, and eventually tends to 0 as it becomes farther from the boundary.

And S102, determining an optimal collision avoidance parameter array set according to the collision avoidance parameter array set and a preset double-standard multi-target collision avoidance algorithm.

In the embodiment of the invention, the preset double-standard multi-target collision avoidance algorithm is obtained by combining a fast non-dominated sorting genetic algorithm (NSGA-II) and a multi-target evolutionary algorithm (MOEA/D) based on decomposition based on a double-standard frame. The NSGA-II algorithm has an improved point that a solution set is graded by adopting a rapid non-dominated sorting method, so that the running speed of the algorithm is increased. The algorithm sets two parameters as non-dominant ordering, i.e. dominant count n_pFor calculating a dominant solution pAnd a dominating set S_pFor storing the solution governed by solution p. The criterion for determining whether one solution dominates the other solution is that if all target values of one solution are better than the target values of the other solution, the solution dominates the other solution, while the other case considers the two solutions to be in a non-dominated state or a dominated state with respect to each other. The solutions governed by the solution p are judged by the criterion and stored in S_pIn the set, the dominant count n values corresponding to these solutions are incremented by one at the same time. The dominating set and dominating count values of all solutions are thus updated, and the solution in which the dominating count value is zero is considered as the first non-dominated leading edge solution, all the first non-dominated leading edge solutions being stored in the set F₁. All at the same time in F₁The dominance count of the solution in the dominance set corresponding to the solution in the set is reduced by one, and then the solution with the dominance count of zero is judged to be used as a second non-dominated leading edge solution and stored in the set F₂. The above contents are continuously circulated, and the process of fast non-dominated sorting is completed. The leading edge solution set obtained by non-dominated sorting is the so-called pareto leading edge solution set, where the first pareto leading edge solution set is considered as the optimal solution set at the current iteration. Another improvement of the NSGA-II algorithm is to use crowding to ensure diversity among population members. In order to evaluate the degree of congestion, a parameter I of the congestion distance is defined_distance。I_distanceRepresenting the degree of decryption around a solution. I is_distanceThe value of (d) is calculated by the length of the rectangle formed by the surrounding solutions of solution i, as shown in fig. 5, the calculation formula is as follows:

wherein I [ I]_distanceIs the crowding distance of the ith solution,

is the mth target value for the (i + 1) th solution. Further, the crowding distance of the solution set at the boundary is infinite. To overcome the magnitude difference between different objective functions, the crowding distance is usedThe distances were normalized. And in the iterative process of the population, eliminating and updating the solution by using the crowding distance and the sequencing level. That is, for solutions in different non-dominant solution sets, the more optimal solution is a solution with a low non-dominant level, and for solutions of the same non-dominant level, the more optimal solution is a solution with a large crowdedness. Therefore, the NSGA-II algorithm can obtain a uniformly and comprehensively distributed pareto optimal leading edge solution set. While MOEA/D does not require ranking of populations, its overall population is composed of all the best solutions found for each sub-problem from the beginning of the algorithm to the moment. There are various methods for decomposing the multi-objective problem into scalar problems, such as weighted summation, Chebyshev, and boundary crossing. The chebyshev method is mainly used in the embodiment of the present invention, and the decomposition principle of the method is shown in fig. 6. The chebyshev decomposition formula is as follows:

wherein g is^tc(x|λ，z^*) Where x is the variable to be optimized, λ ═ λ (λ)₁，...，λ_m) Is a vector of the weights that is,

is a reference point, f_i(x) Is the value of the objective function, hence for

There is always a weight vector λ such that the solution of the above equation is a pareto optimal solution x^*And the solution is also the optimal solution of the original problem, so the required optimal solution set is obtained by changing the weight vector lambda. Thus by comparing the newly generated solution with the original solution g^tcAnd updating the population to finish the movement of the population to the optimal pareto frontier. In general, each sub-problem in the MOEA/D algorithm is optimized only by using the information of the adjacent sub-problems, so that the calculation of each generation of MOEA/D is realizedThe computational complexity is lower than that of NSGA-II, meaning that MOEA/D algorithm takes shorter computation time than NSGA-II algorithm.

In the embodiment of the invention, considering that the final pareto front edge may be in an irregular shape due to a complex environment of multi-ship collision avoidance, the NSGA-II algorithm and the MOEA/D algorithm are combined through the dual-standard algorithm, so that the calculation efficiency of the algorithm is improved, and the uniformity of the front edge solution set can be ensured, wherein the specific flow of the algorithm is shown in FIG. 7.

In an embodiment of the present invention, as shown in fig. 8, the step 102 includes:

step S801, determining the collision avoidance parameter array set of the first ship as a parent collision avoidance parameter array set.

And S802, generating a child non-domination collision avoidance parameter array set according to the parent collision avoidance parameter array set and the rapid non-domination sorting genetic algorithm.

And S803, generating a child preferred collision avoidance parameter array set according to the parent collision avoidance parameter array set and a multi-objective evolutionary algorithm based on decomposition.

Step S804, according to non-pareto selection, utilizing the offspring non-dominance collision avoidance parameter array set to make up the unexplored optimal solution of the offspring preferred collision avoidance parameter array set, and generating a new generation collision avoidance parameter array set;

step S805, judging whether the new generation collision avoidance parameter array set meets a preset termination condition; if yes, go to step S806; if not, the process returns to step S802.

Step S806, determining the new generation collision avoidance parameter array set as an optimal collision avoidance parameter array set.

In the embodiment of the present invention, the NPC evolution part in fig. 7 adopts MOEA/D algorithm, while the PC evolution part uses NSGA-II algorithm for reference, and it can be seen that the two parts are performed substantially in parallel. Starting from the initialization of the population, the initial population enters NPC evolution and PC evolution at the same time, and the population is updated and iterated by utilizing the advantage complementation of the two parts. Wherein the PC selection component is configured to select pareto non-dominant individuals from a mixed set of a population resulting from PC evolution and new individuals resulting from NPC evolution. And the NPC selection part compares the population obtained by PC evolution with the NPC population to make up individuals in an unsearched area in the NPC population and search for individuals with better performance. Promising individuals in the PC population employ crowdedness criteria to replace individuals in the NPC population in this context to keep the number of the entire NPC population unchanged. Population maintenance in PC evolution is achieved by ensuring that the number of PC populations does not change. Through the non-dominant level and the crowding degree, solutions with poor performance can be eliminated, and meanwhile the diversity of the whole population can be guaranteed. The individual exploration part is a key part of mutual information exchange between NPC evolution and PC evolution in the whole algorithm. Because the NPC evolution-based algorithm has a higher selection pressure than the PC evolution, it may sometimes focus on a partial region of the pareto frontier, resulting in the whole algorithm continuously searching for a specific region repeatedly. The individual exploration part attempts to explore promising individuals in the PC population, which may be eliminated or not explored during NPC evolution. Thus, there is no NPC individual within a certain distance r around these individuals, or there is one NPC individual. The formula for the distance r is as follows:

r＝(N′/N)·r₀(8)

where N is the number of populations before PC population maintenance, N is the initial size of the population, r₀Is the niche radius. Since the PC selects a non-pareto individual, N will have a value less than N early in the algorithm and greater than N but not more than twice later in the algorithm. This means that at the early stage of the algorithm, the r value is smaller, so that more exploration is performed on the PC population, and at the later stage of the algorithm, because the NPC population is already complete, the dependence on the PC population is smaller, the r value is larger, and the exploration on the PC population is reduced. Invention r₀The value is set to the length from the third closest individual to the individual.

In the embodiment of the present invention, since most collision avoidance actions are only one avoidance operation, four parameters are used to represent the whole collision avoidance route in the present invention, as shown in fig. 9. The four parameters respectively represent the time of collision avoidance and the time of return journeyThe complete collision avoidance process is described. Wherein, T_oRepresenting the straight-through time, namely the time from the starting point to the avoidance point; c_aRepresenting an avoidance magnitude at an avoidance point; t is_aRepresenting the avoidance time, i.e. the time from the avoidance point to the re-navigation point; c_rRepresenting the magnitude of the fly-back. The present invention sets the ranges of these four parameters to 0, 60 in consideration of the speed of the ship, the length of the collision avoidance line, and the steering capability of the ship itself]. Since the present invention uses a genetic algorithm, parameters need to be encoded. There are generally two types of coding, one is binary coding and the other is real coding. With reference to the range of parameters, if binary coding is used, a chromosome may require 24 bits, which makes the algorithm very stressful to run. With real number encoding, only 4 parameters are needed, while no decoding operation is performed. And in the process of comparing the advantages and disadvantages of the collision avoidance route, the complexity of calculation is reduced. In summary, the encoding scheme adopted in the present invention is real number encoding.

In the embodiment of the invention, because the adopted algorithm is a dual-standard multi-target genetic algorithm, some basic parameters need to be determined firstly, and the parameters are as follows:

(1) size of population N: the number of individuals in each generation of population is specified as a standard for PC evolution and partial population maintenance. The larger the population number, the greater the likelihood of obtaining the desired solution, but at the same time the longer the running time of the algorithm. Herein, the value of N is set to 50.

(2) Probability of variation P_MAnd cross probability P_C: used for judging the conditions generated by new individuals in the population. Probability of variation P_MThe size of (A) determines the local search capability of the algorithm, and the cross probability P_CThe size of (d) determines the global search capability of the algorithm. Let us P_MIs 0.2, P_CIs 0.7.

(3) Maximum number of iterations T: for determining a decision condition for stopping the algorithm. Too small a maximum number of iterations may cause the final solution set to be suboptimal, while too large may affect the operating efficiency of the algorithm. The final setting T is 60 generations after experimental adjustment.

(4) Selecting the upper and lower bounds of the solution set C_uAnd C_d: a selection area for selecting a final solution. The pareto optimal solution set is obtained through algorithm optimization, and therefore the optimal solution is selected through a random method by determining a selection area of a final solution on the solution set. The present invention takes the risk objective as a criterion for selecting a solution set.

After the above parameters are initialized, the population needs to be initialized. Since the invention adopts the parameters of the collision avoidance route as the genetic factors of the algorithm, the initial population is difficult to generate by experience, so that the method of randomly generating the population within the allowable range of each parameter is adopted. After the population is initialized, the population needs to be continuously updated and iterated by using an algorithm. The first is mutation operation, which is an operation for enhancing the local search capability of the algorithm. But mutation operations should generally not be performed too much, as this will result in a reduction in the efficiency and accuracy of the genetic algorithm. The variation operation adopted by the invention is a non-uniform variation operation, the variation mode is related to the iteration times, the variation range is larger at the initial stage of iteration, and the variation range is gradually reduced along with the iteration of the algorithm, so that the whole population tends to be convergent. Setting the current iteration times as t and the parent individuals as A_kThe new individual is A_k1The range of the parameter is [ down, up ]]Then the variation formula is:

and secondly, cross operation, also called gene recombination, enhances the global search capability of the algorithm and prevents the algorithm from falling into local optimum. The cross operation adopts the analog binary operation, and the specific formula is as follows:

wherein A is_k2And A_k3Is a newly generated individual of the crossover operation, A_mAnd A_nAre parents of the crossover operation. And b_qIs a set parameter, the formula is as follows:

although the population can be updated and iterated through the above operations, the convergence speed of the multi-target algorithm is always a problem. Therefore, the method uses the population updating principle of the ant lion algorithm for reference, and introduces the population updating principle into a new individual generation part of NPC evolution to accelerate the convergence speed of the algorithm. The ant lion algorithm is an algorithm developed with reference to the phenomenon that ant lions prey on ants in nature, as shown in fig. 10. The ant lion algorithm has two populations, one is the ant lion population for retaining the actual individuals in the current iteration, and the other is the ant population for updating the ant lion individuals. The ant population is generated based on the ant lion population, a trap exists around each ant lion, ant individuals are generated in the trap area through a random walking method, then the fitness of the newly generated ant individuals and the ant lion individuals is compared, if the fitness of the ant individuals is higher, the ant lions move to the positions of the ant individuals, the ant lions are updated continuously, and finally the optimal solution is obtained.

The invention is a generation method for borrowing the ant population and supplementing the ant population into a population updating method of a dual-standard multi-target genetic algorithm. Since the range of the traps around the ant lion is continuously reduced along with the iteration number, the convergence speed of the algorithm is increased. The random walk formula of ants is as follows:

Ant_i(t)＝[0，cumsum(2r(t₁)-1)，...，cumsum(2r(t_n)-1)](12)

the generation formula of the ant individuals is as follows:

wherein

Is the ant individual position generated by randomly selected ant lion individuals,

the ant individual positions generated by the current optimal ant lion individuals take global information into account in individual generation.

In the embodiment of the invention, as the multi-objective algorithm is adopted, a current optimal individual cannot be evaluated, and therefore in combination with the actual conditions in the text, the non-dominated solution set evolved by the PC is taken as the current optimal ant lion population, and the solution closer to the pareto optimal frontier is generated by transferring the non-dominated solution set to the new individual generation part evolved by the NPC, such as the dashed line in fig. 7, which transfers the information of the non-dominated solution set. In order to verify the practical effect of the method, the convergence rates of the MOEA/D algorithm added with the ant generation method and the original MOEA/D algorithm are compared through a multi-objective test function, as shown in FIG. 11. In FIG. 11, ZDT1 and ZDT2 are multi-objective test functions, and the specific equations are shown in Table 1. In addition, MOEA/D-M refers to a modified algorithm, and it can be seen from the figure that the modified MOEA/D algorithm is closer to the expected pareto optimal leading edge than the original algorithm in the same 200 generations. Therefore, the MOEA/D added with the ant generation rule has a better convergence effect, and can enhance the convergence speed of the dual-standard multi-target genetic algorithm, which is also the reason that the iteration number set in the text is smaller.

TABLE 1 Multi-objective test function

In a preferred embodiment of the present invention, the decomposition-based multi-objective evolutionary algorithm includes a path objective function and a risk objective function.

In the embodiment of the invention, the objective function refers to the requirement of selecting a route in the process of ship collision avoidance at sea. In this context, the objectives of ship collision avoidance mainly include safety and economy of collision avoidance routes. Generally, the higher the safety of a collision avoidance route, the poorer the economy of the route. The economy is generally expressed by the length of the collision avoidance line, where the collision avoidance line refers to the distance from the starting point to the return point, as shown in fig. 9, and the specific formula is as follows:

where (x, y) is the position of the vessel and k is the serial number of the vessel at each time. Since the shorter the risk of the ship going, the longer the collision avoidance line length, the safety of the ship going is represented by the risk of the collision avoidance going in order to form the pareto condition. The risk degree of the collision avoidance route is calculated by a formula (5), and the formula of the risk degree target is as follows:

F_risk＝max{Risk_a，Risk_r，Risk_o} (15)

in order to better represent the danger of the collision avoidance line, the danger degree of the ship at the collision avoidance point, the return point and the return point is considered, and the maximum value is taken as the target function of the danger degree. Therefore, the greater the risk degree of the ship during collision avoidance navigation, the shorter the route length of the ship during navigation, and the two objective functions are mutually refuted to form the condition of pareto front formation. The criteria for selecting the final solution herein is in accordance with F_riskThe target is selected, and the selection range is set to [0.2, 0.5 ].

And S103, determining a collision avoidance route of the first ship according to the optimal collision avoidance parameter array set.

Fig. 12 is a flowchart of another method for determining a ship collision avoidance line according to an embodiment of the present invention, and for convenience of description, only parts related to the embodiment of the present invention are shown, which are similar to the above embodiment, except that, in the embodiment of the present invention, the step 101 includes:

step 1201, when collision risk degrees of the first ship, the second ship and the third ship are all larger than a preset threshold value, acquiring collision avoidance parameter array sets of the first ship, the second ship and the third ship respectively.

In the embodiment of the present invention, the collision risk between the first ship, the second ship, and the third ship may be calculated by referring to the method for determining collision risk between the first ship and the second ship, and the specific risk threshold may be set according to an actual situation, which is not described and limited herein.

The step 102 includes:

step 1202, determining optimal collision avoidance parameter array sets of the first ship, the second ship and the third ship respectively according to the collision avoidance parameter array sets of the first ship, the second ship and the third ship and a preset dual-standard multi-target collision avoidance algorithm.

In the embodiment of the present invention, the method for determining the optimal collision avoidance parameter array set of the first ship, the second ship and the third ship may refer to the method for determining the optimal collision avoidance parameter array set of the first ship, which is not described in detail herein.

The step 103 includes:

step 1203, determining collision avoidance routes of the first ship, the second ship and the third ship respectively according to the optimal collision avoidance parameter array sets of the first ship, the second ship and the third ship.

And 1204, determining a unique avoidance ship according to the collision avoidance routes of the first ship, the second ship and the third ship and the step-by-step cooperative collision avoidance strategy, so that the avoidance ship navigates according to the corresponding collision avoidance routes.

In the embodiment of the invention, although the collision avoidance route of the ship can be planned according to the preset dual-standard multi-target collision avoidance algorithm, the possible collision avoidance behaviors of other ships are not considered in the planning. Therefore, the invention provides a step-by-step cooperative collision avoidance strategy by using the idea of a distributed local search algorithm, as shown in fig. 13. As can be seen in FIG. 13, the step-by-step collaborative strategy can be roughly divided into four steps. The first step is the transfer of information through onboard communication equipment. The information includes the speed, heading, and collision avoidance intent of the ship. And secondly, planning collision avoidance of each ship according to the acquired information of other ships. During the algorithm planning process, each ship takes the influence of other ships on the ship into consideration by using a collision risk model. After this step is completed, each ship has its own collision avoidance intention. In the third step, a progress-changing index ImpRS is provided according to the safety degree and the smoothness degree of the collision-avoiding route, and the collision-avoiding routes of all ships are compared by using the index, so that which ship carries out collision avoidance can be analyzed, and the benefit is greater. The progress index ImpRS formula is as follows:

wherein

And

the collision danger between the original navigation route of the ship and the avoidance route of the ship and the ith target shipThe maximum risk degree in three positions of the yielding point, the re-voyage point and the return voyage point, and n is the number of the target ships. If the ship approaches the collision point, the ship needs to avoid as soon as possible. Based on the situation, a time factor T is introduced, the closer the ship is to the avoidance point, the larger the value of T is, so that the value of ImpRS is increased, and the possibility of avoiding the ship is improved, and the formula is as follows:

T＝exp(-α(t_f-Kt)) (17)

wherein t is_fThe Time when the ship collides in accordance with the original course of the ship, which is set herein as the minimum value of all the Time when the collision occurs, t is the Time step, K is the K-th generation cycle α is a constant that ensures that the Time does not prematurely affect the value of ImpRS by adjusting the value of α. α is set herein as 0.3 in accordance with the collision scenario and the handling performance of the ship itself, that is, for a ship having a speed of 15kn, when t is_fLess than 10 minutes, T had a significant effect on ImpRS. Therefore, in the formula (16), three factors, namely the reduction amount of the danger of the ship avoidance, the urgency degree of the avoidance and the smoothness of the avoidance route, are considered, each ship calculates the value of the ImpRS, compares the advantages of the ships after the avoidance, and selects the ship with the maximum value of the ImpRS as the avoidance ship in the fourth step. Except for avoiding the ship, other ships keep the original navigation intention to navigate in the current time step length. And if the other ships still have collision risks, entering the next circulation. In the next cycle, the avoidance ship does not plan an avoidance route, and only an avoidance intention is provided as a reference for planning avoidance of other ships, so that the next cycle is continued until all ships can safely navigate. The invention sets the time step t of one cycle to be 3 minutes.

In this embodiment of the present invention, as shown in fig. 14, the step S1204 includes:

step S1401, determining progress change index values of the first ship, the second ship, and the third ship according to the collision avoidance lines of the first ship, the second ship, and the third ship and a preset progress change index function.

And step S1402, determining the ship with the maximum progress rate index value as the only avoidance ship according to the progress rate index values of the first ship, the second ship and the third ship.

According to the method for determining the ship collision avoidance route, the NSGA-II algorithm and the MOEA/D algorithm are combined through the double standard frames, the advantages of the two algorithms are complemented, and the algorithm is more suitable for planning the ship collision avoidance route in a complex scene; further quantifying collision avoidance routes, researching basic parameters and basic operations of the dual-standard multi-target genetic algorithm, and setting a target function of the algorithm under the condition of fully considering the safety and the economy of a collision avoidance process; and finally, a step-by-step cooperative collision prevention strategy is provided, and a progress-improving index is provided under the consideration of the advantages of collision prevention and the urgency of collision prevention, so that the COLREGS rule is considered in the whole collision prevention planning process, and the possible collision prevention behaviors of other ships are considered.

Simulation and result analysis:

in order to verify the effectiveness of the collision avoidance algorithm, the invention is realized by using MATLAB software for coding, and an experimental simulation GUI interface based on the intelligent ship collision avoidance algorithm is shown in FIG. 15. The simulation platform is constructed to have a better visualization effect on the experimental verification result of the algorithm, and a GUI interface is briefly introduced below, and as can be seen from fig. 15, the whole GUI interface can be roughly divided into six parts.

The first part is a graphic display part which mainly displays the ship navigation environment, the ship collision avoidance route and the distribution condition of a solution set in the algorithm iteration process; the second part is a data display area on the graphic display part, wherein navigation data of each ship, such as the speed, the length and the course of the ship and the position of the ship changing along with the iteration time, are displayed when the algorithm is operated, and the states of algorithm proceeding, such as the current loop algebra, the iteration times of the algorithm, collision avoidance parameters of each ship, the value of the progress of collision avoidance tracks of each ship and the like are also displayed; the third part is a Map information part, wherein the latitude and longitude range of the ship navigation area is set, and then the Map is displayed on the first part by using an m _ Map function; the fourth part is an Algorithm part which sets parameters of a collision avoidance Algorithm, including the population size, the maximum iteration times, the cross and variation probability and the selection range of the final solution; the fifth part is an Import data part, and basic parameters of all ships are imported to be used as initial parameters for algorithm starting; the sixth part is a Mode selection part, and selects two-ship and multi-ship collision prevention modes, wherein the only difference of the two models is that collision prevention planning is performed without a step-by-step cooperation strategy under the condition of the two ships. Besides the six parts, a plurality of buttons are used for result display, such as planned routes for ship collision avoidance, distances among ships and dynamic collision avoidance sailing display.

Collision avoidance simulation and result analysis of the two ships:

the collision avoidance complexity of two ships is weaker than that of multiple ships, and the collision avoidance behavior can be selected according to COLREGS rules. Therefore, collision avoidance planning of the two ships does not need to consider collision avoidance behaviors of other ships, and collision avoidance between the ships only needs to be planned according to COLREGS rules. And once other ships do not avoid according to the collision avoidance behavior, the ship carries out the emergency avoidance behavior at the moment. The simulation analysis is mainly performed aiming at three situations encountered by ships, and the specific contents are as follows:

(1) the intersection meets the situation. Setting the course of the ship to be 0 degrees, the navigation speed to be 15kn, the length of the ship to be 250m, the course of the target ship to be 300 degrees, the navigation speed to be 7.5kn and the length of the ship to be 250 m. The collision-prevention route of the ship after the ship is planned by the collision-prevention algorithm is shown in fig. 16, wherein the area enclosed by the circle is the field of the quarter ship, the solid line is the collision-prevention route of the ship, the dotted line is the navigation route of the target ship and the original navigation route of the ship, and the dotted line is the collision-prevention route represented by all pareto front solution sets of the ship after the ship is planned by the algorithm. It can be seen that the ship follows COLREGS rules to avoid the target ship, the ship fields of the two ships are not invaded, and the ship safely passes around the target ship. The ship domain parameters of the two ships are shown in table 2, and it can be seen that the ship speed of the ship is greater than that of the target ship, and thus the ship domain is greater than that of the target ship. And the final solution is randomly selected from the pareto solution set according to the required range.

TABLE 2 Collision avoidance parameter table for ships in cross situation

(2) Meeting situations. Setting the course of the ship to be 0 degrees, the navigation speed to be 15kn, the length of the ship to be 250m, the course of the target ship to be 172 degrees, the navigation speed to be 15kn and the length of the ship to be 250 m. At this time, the ship should turn to the starboard to complete collision avoidance, and the specific collision avoidance route planned by the algorithm is shown in fig. 17. In the figure, it can be seen that the ship fields of both ships are not invaded by each other, and the ship safely drives over the target ship. And the collision prevention behavior of the ship conforms to the regulation of COLREGS rules. The behavior of the target ship is not considered in the collision avoidance process of the ship, and the ship needs to carry out collision avoidance operation no matter how the behavior of the target ship is, so that the target ship does not change the course and is taken as a collision avoidance planning reference of the ship. The parameters of the ship collision avoidance are shown in table 3, and it can be seen that the ship fields of the two ships are the same in size.

TABLE 3 Collision avoidance parameter table for ships in meeting situation

(3) The overtaking meeting situation. The course of the ship is set to be 330 degrees, the navigation speed is 15kn, the length of the ship is 250m, the course of the target ship is 0 degree, the navigation speed is 7.5kn, and the length of the ship is 250 m. At this time, the states of the two ships belong to the state that the ship tracks over the target ship, the two ships are in a small-angle tracking state, the ship needs to turn to the starboard according to the COLREGS rule, and the specific collision avoidance route planned by the algorithm is shown in FIG. 18. As can be seen from the figure, no collision occurs between the two ships, and the ship fields of the two ships are not invaded. In addition, the collision prevention behavior of the ship also complies with the collision prevention rules. At the beginning, the ship is positioned at the right rear part of the target ship, and because the navigational speed of the ship is higher than that of the target ship, the ship finally drives over from the right front part of the target ship, and the navigational route meets the requirements of safety and economy. As can be seen from table 4, the range of the ship field is wider due to the faster speed of the ship.

TABLE 4 Collision avoidance parameter table for ships in meeting situation

Multi-ship collision avoidance simulation and result analysis:

the invention designs three different simulation experiments: and (3) multi-ship encounter collision avoidance simulation and multi-ship collision avoidance simulation with static obstacles, verifying the effectiveness and reliability of the collision avoidance algorithm solving route problem under different scenes respectively, and analyzing and explaining simulation results.

The invention designs two collision avoidance scenes: the situations of intersection and encounter situation and the situations of intersection and encounter situation are verified through the two scenarios, and the condition of complying with COLREGS rules in the multi-ship collision avoidance process and the safety of ship collision avoidance navigation are verified through the two scenarios.

(1) Simulation and analysis of cross and encounter situation scene

Fig. 19 shows a specific case of this scenario, and table 5 shows basic parameters of each ship. As can be seen from the right drawing of FIG. 19, S₁The ship turns to the starboard to avoid collision, and S can be judged according to the danger degree information in the table 5₁Is based on S₃The collision avoidance behavior of the ship conforms to COLREGS rules. Similarly, the behavior of other ships conforms to the rules of COLREGS.

TABLE 5 basic parameter information for each ship

The states of the vessels at the respective times are listed in fig. 20, and it can be seen that the respective vessel areas exist around each vessel. At each time, each ship does not invade the field of other ships, and each ship safely carries out avoidance sailing. The results of the comparison of the ship progress functions in the respective generations of cycles are shown in table 6, and it can be seen that in the first cycle, S₁The improvement function of the ship is maximized, its dodge data being shown after this line, followed by S in the second cycle₃Ship, finally S₂Ships, due to the avoidance lines of three other shipsMovement causes S₄The ship does not have a collision risk in the fourth cycle, so S₄The ship sails in a straight way, so far, all ships sail safely, and the whole algorithm stops running.

TABLE 6 ImpRS values in each cycle

	S₁	S₂	S₃	S₄	T_o	C_a	T_a	C_r
									First cycle	1.98	1.21	1.58	0.91	0.6	13.4	19.9	57.8
Second circulation	0	0.4794	0.6079	0.5899	4	21.5	14.3	53.2
									The third cycle	0	0.9746	0	0.1939	6.3	30.4	11.2	60.0
The fourth cycle	0	0	0	0	-	-	-	-

(2) Simulation and analysis of crossing and crossing meeting situation scene

The details of this scenario are shown in FIG. 21, S₁And S₃The two ships are in a tracking state, and other ships are in a cross meeting state. As can be seen from the right drawing of FIG. 21, S₁And twoThe ship carries out avoidance operation S₃And S₄The original course is kept to continue the navigation. And the avoidance behavior of all ships conforms to the provisions of the COLREGS rule. The basic parameters of each vessel are shown in table 7, and it can be seen that the vessels of different vessel speeds have different vessel sizes. In addition, for S₃The greatest danger of the ship is S₁Ship due to S₁Avoidance operation of the ship so that S₃The ship does not have a collision risk, so S₃Direct sailing and the same principle S₄As is the case with ships.

TABLE 7 basic parameter information of each ship

The values of the ImpRS for the vessels at each cycle stage are listed in table 8, and it can be seen that in the first cycle stage, due to S₁Vessel and S₄Danger of collision between ships, S₄Planning collision-preventing route of ship, and judging S according to COLREGS rule₃The ship belongs to a straight-ahead ship, and does not need to carry out collision avoidance planning, so S is set₃The ImpRS of the ship is 0. In the second cycle stage, S is generated due to the last cycle₁The ship is selected as the avoidance ship, so that only S exists in the circulation₂The ship performs collision avoidance planning, and the planning result is shown in table 8. The navigation conditions of all the vessels at each time are shown in fig. 22. It can be seen that S is at 900S₄Vessel and S₃The ships pass each other from the edge of the ship field of the other, and the ship field is not invaded. At 1400S, S₁The ship exceeds S₃The ship finishes the process of overtaking collision avoidance, and all ships sail safely in the whole process.

TABLE 8 ImpRS values in each cycle

	S₁	S₂	S₃	S₄	T_o	C_a	T_a	C_r
									First cycle	0.903	0.385	0	0.8537	3.3	19.3	14.6	45.5
Second circulation	0	02985	0	0	9.6	22.2	11.2	57.2
									The third cycle	0	0	0	0	-	-	-	-

Simulating and analyzing the meeting situation of multiple ships under the existence of static obstacles:

this scenario is illustrated in fig. 23, where three vessels are at risk of collision with each other, and there are static obstacles such as islands around the vessels. It can be seen that when the course of the three ships is not changed, the three ships do not collide with the surrounding static obstacles, but because the ships need to avoid other ships, the influence of the static obstacles on the collision avoidance route planning needs to be considered here. The avoidance path of the vessel is shown in the right-hand drawing of fig. 23, where it can be seen that the vessel makes an avoidance voyage in compliance with the COLREGS rule, where S₁Keeping the ship in direct voyage S₂And S₃The ship carries out avoidance operation. The basic parameters of each ship are listed in table 9, and it can be seen that there is a risk of collision between the ships.

TABLE 9 basic parameter information for each ship

The ImpRS values for each ship are listed in table 10. As can be seen from the table, each ship has been planned for collision avoidance during the first cycle, where S is used₃The maximum ImpRS value of the ship is used as the avoidance ship of the current cycle. In the second cycle, due to the avoidance of the ship, the COLREGS rule S is followed₁The ship does not need to carry out avoidance operation, so S in the cycle₂The ship is used for avoiding the current cycleA ship. From fig. 24, it can be seen that the vessels sailed at the respective times, each vessel avoids the vessel having a conflict with itself, and each vessel sails safely.

TABLE 10 ImpRS values in each cycle

	S₁	S₂	S₃	T_o	C_a	T_a	C_r
								First cycle	0.568	0.642	0.661	0.7	17.3	16.9	58.3
Second circulation	0	1.052	0	8.1	24.1	14..2	49.5
								The third cycle	0	0	0	-	-	-	-

In conclusion, the double-standard multi-target collision avoidance algorithm provided by the invention is subjected to simulation verification in two-ship meeting and multi-ship meeting, and the reliability and the effectiveness of the algorithm are proved. Firstly, introducing an MATLAB simulation platform of a collision avoidance algorithm, and displaying the effect of the algorithm by utilizing the good graphical function of MATLAB software; then, simulation test is carried out aiming at the meeting situation of two ships, and whether the collision-prevention route planned by the algorithm complies with the COLREGS rule or not is analyzed by considering three situations of ship meeting, and the collision-prevention route which accords with the optimization target of safety and economy can be obtained by the algorithm as seen from the final result; finally, aiming at the situation of multi-ship meeting, 3 collision scenes are designed, the effectiveness and the reliability of the algorithms in the two aspects of collision prevention planning among multiple ships and the collision prevention planning with static obstacles are verified respectively, and the final results show that the algorithm provided by the invention can obtain good results, which shows that the algorithm provided by the invention is reasonable and effective.

Fig. 25 is a schematic structural diagram of a ship collision avoidance line determining apparatus according to an embodiment of the present invention, and for convenience of description, only parts related to the embodiment of the present invention are shown.

In an embodiment of the present invention, the ship collision avoidance line determining apparatus includes:

the collision avoidance parameter array set acquisition unit 2501 is configured to acquire the collision avoidance parameter array set of the first ship when the collision risk degree between the first ship and the second ship is greater than a preset threshold.

In an embodiment of the present invention, the risk of collision between the first vessel and the second vessel may be represented by a minimum encounter distance DCPA between the first vessel (own vessel) and the second vessel (target vessel) and a time to reach closest encounter distance TCPA; the risk degree calculation method can be obtained by calculating the related motion parameters of the first ship and the second ship based on the risk degree model in the ship field, and specifically see the above explanation, which is not described herein again.

The optimal collision avoidance parameter array set determining unit 2502 is configured to determine an optimal collision avoidance parameter array set according to the collision avoidance parameter array set and a preset dual-standard multi-target collision avoidance algorithm.

In the embodiment of the invention, the preset double-standard multi-target collision avoidance algorithm is obtained by combining a fast non-dominated sorting genetic algorithm (NSGA-II) and a decomposition-based multi-target evolutionary algorithm (MOEA/D) based on a double-standard frame.

In the embodiment of the invention, considering that the final pareto front edge may be in an irregular shape due to a complex environment of multi-ship collision avoidance, the NSGA-II algorithm and the MOEA/D algorithm are combined by the dual-standard algorithm, so that the uniformity of the front edge solution set can be ensured while the calculation efficiency of the algorithm is improved, and the specific flow of the algorithm is shown in fig. 7, which is specifically described above, and is not repeated herein.

And a collision avoidance route determining unit 2503, configured to determine a collision avoidance route of the first ship according to the optimal collision avoidance parameter array set.

The ship collision avoidance route determining device quantifies collision avoidance routes by using a collision avoidance parameter array set, determines an optimal collision avoidance parameter array set by using a double-standard multi-target collision avoidance algorithm obtained by combining a fast non-dominated sorting genetic algorithm and a multi-target evolution algorithm based on decomposition based on a double-standard frame, and determines the collision avoidance routes according to the optimal collision avoidance parameter array set; in consideration of the fact that the final pareto front edge can be in an irregular shape due to the complexity of a multi-target meeting environment, the ship collision avoidance route is solved by adopting a dual-standard multi-target genetic algorithm combining pareto evolution and non-pareto evolution, the convergence speed of the population is accelerated and the diversity of the population is increased by improving the updating mode of the non-pareto evolved population, so that the calculation efficiency of the algorithm is improved, and meanwhile, the uniformity of front edge solution set can be guaranteed; meanwhile, analysis of simulation results proves that the method can solve safe and economic paths in various meeting scenes.

In one embodiment, a computer device is proposed, the computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program:

determining an optimal collision avoidance parameter array set according to the collision avoidance parameter array set and a preset dual-standard multi-target collision avoidance algorithm; the preset double-standard multi-target collision avoidance algorithm is obtained by combining a rapid non-dominated sorting genetic algorithm and a multi-target evolutionary algorithm based on decomposition on the basis of a double-standard frame;

In one embodiment, a computer readable storage medium is provided, having a computer program stored thereon, which, when executed by a processor, causes the processor to perform the steps of:

It should be understood that, although the steps in the flowcharts of the embodiments of the present invention are shown in sequence as indicated by the arrows, the steps are not necessarily performed in sequence as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a portion of the steps in various embodiments may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a non-volatile computer-readable storage medium, and can include the processes of the embodiments of the methods described above when the program is executed. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.

Claims

1. A ship collision avoidance route determining method is characterized by comprising the following steps:

2. The method for determining the ship collision avoidance line according to claim 1, wherein the step of determining the optimal collision avoidance parameter array set according to the collision avoidance parameter array set and a preset dual-standard multi-target collision avoidance algorithm comprises:

determining the collision avoidance parameter array set of the first ship as a parent collision avoidance parameter array set;

generating a child non-domination collision avoidance parameter array set according to the parent collision avoidance parameter array set and a rapid non-domination sorting genetic algorithm;

generating a child preferred collision avoidance parameter array set according to the parent collision avoidance parameter array set and a multi-objective evolutionary algorithm based on decomposition;

according to non-pareto selection, utilizing the offspring non-domination collision avoidance parameter array set to make up the undetected optimal solution of the offspring preferred collision avoidance parameter array set, and generating a new generation collision avoidance parameter array set;

judging whether the new generation collision avoidance parameter array set meets a preset termination condition or not; if so, determining the new generation of collision avoidance parameter array set as an optimal collision avoidance parameter array set; and if not, determining the new generation of collision avoidance parameter array set as a parent collision avoidance parameter array set, and returning to the step of generating a child non-dominated collision avoidance parameter array set according to the parent collision avoidance parameter array set and the fast non-dominated sorting genetic algorithm.

3. The method for determining the ship collision avoidance line according to claim 1, wherein the step of acquiring the collision avoidance parameter array set of the first ship when the collision risk between the first ship and the second ship is greater than a preset threshold value comprises:

when collision risk degrees among a first ship, a second ship and a third ship are all larger than a preset threshold value, acquiring collision avoidance parameter array sets of the first ship, the second ship and the third ship respectively;

the step of determining the optimal collision avoidance parameter array set according to the collision avoidance parameter array set and a preset dual-standard multi-target collision avoidance algorithm comprises the following steps:

respectively determining the optimal collision avoidance parameter array sets of the first ship, the second ship and the third ship according to the collision avoidance parameter array sets of the first ship, the second ship and the third ship and a preset double-standard multi-target collision avoidance algorithm;

the step of determining the collision avoidance line of the first ship according to the optimal collision avoidance parameter array set comprises the following steps:

determining collision avoidance routes of the first ship, the second ship and the third ship respectively according to the optimal collision avoidance parameter array sets of the first ship, the second ship and the third ship;

and determining the only avoiding ship according to the collision avoidance routes of the first ship, the second ship and the third ship and the step-by-step cooperative collision avoidance strategy so that the avoiding ship navigates according to the corresponding collision avoidance routes.

4. The method for determining the ship collision avoidance line according to claim 3, wherein the step of determining the only ship to avoid according to the collision avoidance lines of the first ship, the second ship and the third ship and the step-by-step cooperative collision avoidance strategy comprises:

determining progress changing index values of the first ship, the second ship and the third ship according to collision avoidance routes of the first ship, the second ship and the third ship and a preset progress changing index function;

and determining the ship with the maximum progress change index value as the only avoiding ship according to the progress change index values of the first ship, the second ship and the third ship.

5. The ship collision avoidance route determining method according to claim 1 or 2, wherein the decomposition-based multi-objective evolutionary algorithm includes a path objective function and a risk degree objective function.

6. The ship collision avoidance route determining method according to claim 1, wherein the collision avoidance parameter array set is generated from a numerical range corresponding to a plurality of collision avoidance parameters, the collision avoidance parameter array set includes a plurality of collision avoidance parameter arrays, and the collision avoidance parameter arrays include numerical values of the collision avoidance parameters randomly determined from the numerical range corresponding to the collision avoidance parameters; the collision avoidance parameters comprise straight voyage time, avoidance amplitude at an avoidance point, avoidance time and re-voyage amplitude.

7. The method for determining a ship collision avoidance line according to claim 1, wherein before the step of obtaining the collision avoidance parameter array set of the first ship when the risk of collision between the first ship and the second ship is greater than a preset threshold, the method further comprises:

acquiring relevant parameters of an obstacle area of a first ship;

determining a speed obstacle area of the first ship according to the obstacle area related parameters of the first ship;

acquiring a speed vector of the first ship and a speed vector of a second ship;

and determining the collision risk degree between the first ship and the second ship according to the speed vector of the first ship, the speed vector of the second ship and the speed obstacle area of the first ship.

8. A collision avoidance line determining apparatus for a ship, comprising:

9. A computer arrangement, comprising a memory and a processor, the memory having stored therein a computer program which, when executed by the processor, causes the processor to carry out the steps of the ship collision avoidance route determination method as claimed in any one of claims 1 to 7.

10. A computer-readable storage medium, having stored thereon a computer program which, when executed by a processor, causes the processor to carry out the steps of the ship collision avoidance route determination method according to any one of claims 1 to 7.