Limited water area multi-ship intelligent avoidance optimization method considering fixed line system and medium

Abstract

The invention relates to a limited water area multi-ship intelligent avoidance optimization method considering a routing system and a medium. The method comprises the following steps: acquiring environment information in a limited water area and state information of each ship; constructing a navigation scene portrait by adopting an artificial potential field algorithm on the basis of the environment information and the state information in combination with a fixed-line navigation mark; under the navigation scene portrait, calculating a ship collision risk degree and defining a safety distance of a ship; and taking the ship collision risk degree and the defined safe distance of the ship as collision avoidance conditions, planning an optimal navigation path of each ship by adopting a global and local combined path planning algorithm, and optimizing the navigation state of each ship by adopting a search algorithm to complete the multi-ship intelligent avoidance optimization process. Compared with the prior art, the method has the advantages that the multi-ship avoiding effect is improved, and the sailing safety of the water area near the port is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of ship avoidance, and in particular to an optimization method and medium for intelligent avoidance of multiple ships in restricted waters taking into account a routing system. Background Art

[0002] Intelligent ship collision avoidance is a challenging core issue in maritime traffic safety, especially in the waterways entering and leaving ports. There is an urgent need for technologies that adapt to restricted waters to ensure the safety and reliability of autonomous avoidance between encountering ships. The traffic environment faced by ships navigating in the waterways entering and leaving ports is extremely complex, including not only natural obstacles such as land and islands and reefs, but also crisscrossing ships. Although many researchers have conducted research on intelligent ship collision avoidance methods in restricted waters, they have not fully considered the routing factors and the principles of "early, large, wide, and clear". In view of this, how to develop multi-ship intelligent avoidance optimization technology for the routing system in restricted waters is a key issue to ensure ship navigation safety and achieve risk control.

[0003] Multi-ship intelligent collision avoidance is the primary problem facing the safety of ship navigation in confined waters. On the one hand, ship intelligent collision avoidance is manifested as a path planning problem, and on the other hand, it is manifested as an avoidance problem. Classic intelligent collision avoidance algorithms include A*, APF, VO, and DWA. These algorithms can well solve single collision avoidance problems such as static obstacle avoidance, dynamic obstacle avoidance, global planning, and local planning. In actual navigation, multiple problems mentioned above are often faced at the same time. For this reason, hybrid algorithms are favored by more people. For example, A* and DWA are combined to solve the problems of local path planning and global path planning. With the inclusion of more factors that need to be considered, such as multi-ship navigation, complex waters, and COLREGs, simple algorithm fusion can no longer solve such complex problems. Ship avoidance in open waters mainly considers turning avoidance, but in confined waters, not only turning avoidance needs to be considered, but also deceleration avoidance should be emphasized.

[0004] When facing the risk of collision in extremely complex waters, it is often difficult to ensure safety if only one ship unilaterally adopts avoidance measures. According to the principle of "early, large, wide and clear", in order to avoid imminent danger, all ships should be regarded as ships that can take avoidance measures to ensure the safe navigation of ships. Summary of the invention

[0005] The purpose of the present invention is to provide a method and medium for optimizing intelligent avoidance of multiple ships in restricted waters taking into account a fixed-line system in order to improve the safety of multiple-ship navigation in restricted waters.

[0006] The purpose of the present invention can be achieved by the following technical solutions:

[0007] A multi-vessel intelligent avoidance optimization method in restricted waters considering a fixed-line system comprises the following steps:

[0008] Obtain environmental information in restricted waters and status information of each ship;

[0009] Based on the environmental information and state information, and in combination with the route-fixed navigation mark, an artificial potential field algorithm is used to construct a navigation scene portrait;

[0010] Under the navigation scenario portrait, calculate the risk of ship collision and define the safe distance of ships;

[0011] Based on the navigation scene portrait, the ship collision risk and the safe distance between ships are used as collision avoidance conditions, and a path planning algorithm combining global and local methods is adopted to plan the optimal navigation path for each ship. At the same time, a search algorithm is used to optimize the navigation status of each ship to complete the multi-ship intelligent avoidance optimization process.

[0012] Furthermore, the step of constructing the navigation scene portrait includes:

[0013] According to the environmental information in the restricted waters, a convex hull algorithm is used to extract the outline of the natural obstacle to obtain the natural obstacle area;

[0014] An artificial potential field algorithm is used based on the natural obstacle areas, route navigation marks and status information to construct a navigation scene portrait.

[0015] Furthermore, the step of obtaining the natural obstacle area includes:

[0016] Let X be any subset of the Euclidean space W, and the smallest convex set containing X is called the convex hull of X, denoted by conv(X) = {X1,X2,…,X n}, where each convex hull corresponds to a natural obstacle object;

[0017] Connect the outermost points of each convex hull to form a convex polygon as a natural obstacle area.

[0018] Furthermore, the step of constructing the navigation scene portrait includes:

[0019] Based on the repulsive relationship between the natural obstacle objects and the navigation mark in the natural obstacle area, a repulsive field is constructed, wherein the expression of the repulsive field is:

[0020]

[0021] K(t,t0)=||t-t0||2

[0022] In the formula, G k(t) is the repulsive potential field function, g is the proportional coefficient, K(t,t0) is a vector whose direction is from the obstacle to the ship and whose magnitude is the Euclidean distance between the ship and the obstacle |t-t0|. t0 is a constant, which indicates the maximum influence range of the obstacle on the ship. K λ is a constant, indicating the maximum distance at which an obstacle affects a ship;

[0023] Based on the gravitational relationship between the position of each ship and the target position, a gravitational field is constructed, wherein the expression of the gravitational field is:

[0024]

[0025] k(t,t i )=||tt i ||2

[0026] In the formula, G ω (t) is the gravitational field function, k(t,t i ) is a vector, representing the position of the ship t and the position of the target point t i The Euclidean distance between |tt i |, k λ is a constant, β is the proportional gain coefficient;

[0027] The repulsive field and the gravitational field are used as navigation scene images.

[0028] Furthermore, the calculation process of the ship collision risk includes:

[0029] According to the status information of each ship, the DCPA parameters and TCPA parameters are calculated, wherein the expressions of the DCPA and TCPA parameters are respectively:

[0030]

[0031] In the formula, DCPA t is the DCPA parameter, α rt is the relative heading of the target ship at time t, TCPA t is the TCPA parameter, μ r is the speed of the target ship relative to the own ship at time t, μ1 is the speed of the own ship at time t, μ2 is the speed of the target ship at time t, D t is the distance between the two ships at time t, β Tt is the direction of the target ship relative to the own ship at time t;

[0032] Based on the DCPA parameters and TCPA parameters, a negative exponential function is used to fit and calculate the ship collision risk, wherein the expression of the ship collision risk is:

[0033] CRI t=ω×RDCPA t +τ×RTCPA t

[0034]

[0035] Where, CRI t is the risk of ship collision, ω and τ are weight coefficients, a and b are adjustment coefficients, DCPA′ t is the dimensionless DCPA, TCPA′ is the dimensionless TCPA, RDCPA t For DCPA risk components, RTCPA t It is a TCPA risk component.

[0036] Furthermore, the quaternion ship domain is used to define the safety distance of the ship, and the safety distance is expressed as:

[0037]

[0038] in:

[0039]

[0040] Where η k is the boundary of the ship area, (x, y) is the position of the ship, S is the quaternion, and D fore is the distance to the front of the ship, D aft is the stern distance, D starb is the distance to the starboard side of the ship, D portt is the distance to the port side of the ship, ξ AD is the gain of the advance distance, ξ DT is the gain of the swing diameter, L is the length of the ship, A D is the advance distance, D T is the initial diameter of the cycle, V own is the ship's speed.

[0041] Furthermore, the A* algorithm is used as the global path planning algorithm to plan the global shortest path, and the artificial potential field algorithm is used as the local path planning algorithm to plan the local path to obtain the optimal navigation path for the ship. In the A* algorithm path planning process, the value function is used to evaluate the cost of each ship from the starting point S i To the target point G i The total cost estimate is used to find the shortest path. When f(k)>0 and 0<g(k)≤g*(k), the shortest path is obtained, where the expression of the value function is:

[0042] φ*(k)=f*(k)+g*(k)

[0043] Where φ*(k) is the value function, f*(k) is the distance function from the starting point, g*(k) is the distance function to the target point, f(k) is the actual cost from the initial state to state k, and g(k) is the estimated cost of the best path from state k to the target state.

[0044] Furthermore, the local path planning step includes:

[0045] The artificial potential field algorithm forms a resultant potential field by acting the repulsive field and the gravitational field on the ship, so as to guide the ship to move on a local path according to the resultant potential field, wherein the expression of the resultant potential field is:

[0046] G(q)=G k (t)+G ω (t)

[0047] In the formula, G(q) is the artificial potential field, that is, the resultant potential field, G k (t) is the gravitational field, G ω (t) is the repulsive field.

[0048] Furthermore, the search algorithm is an artificial bee colony algorithm, and the steps of using the artificial bee colony algorithm to optimize the navigation status of each ship include:

[0049] Initial stage: All nectar sources are initialized using scout bees, where the location of the nectar source represents the navigation status of the ship, including heading and speed. The initialization expression is:

[0050] f nj =k j +rand(0,1)×(ω j -k j )

[0051] In the formula, f nj is the nectar source, n is the population size, j is the number of variables, k j ,ω j f nj The upper and lower limits of the value;

[0052] Employment Phase:

[0053] Honey bees search for neighbors based on the location of the nectar source in their memory and calculate the fitness to determine the neighboring nectar source:

[0054]

[0055] Among them, the fitness is converted into a minimization problem by the following formula for solution:

[0056]

[0057] In the formula, gnj Honey source for neighbors, f tj is a randomly selected nectar source. is a random number used to calculate the fitness value of a new nectar source. is the objective function value of the nth nectar source;

[0058] Observation phase:

[0059] The observer bee randomly selects a nectar source based on the nectar source information obtained by the honey bees, generates a new nectar source near the selected nectar source, and calculates the fitness of the new nectar source. The probability of being selected by the observer bee is:

[0060]

[0061] In the formula, ψ n is the probability of the nectar source being selected;

[0062] Reconnaissance phase:

[0063] If a honey bee decides to give up the nectar source it has after a given number of attempts, it will become a scout bee and restart the initial stage until it finds the best nectar source.

[0064] The present invention also provides a computer-readable storage medium, comprising one or more programs for execution by one or more processors of an electronic device, wherein the one or more programs include instructions for executing the multi-ship intelligent avoidance optimization method in restricted waters considering the routing system as described above.

[0065] Compared with the prior art, the present invention has the following beneficial effects:

[0066] (1) The present invention considers the environmental information and routing information in restricted waters to construct a scenario portrait of ship avoidance, combines collision risk and safety distance, and adopts a path planning algorithm that combines global and local elements to plan the navigation path of each ship. At the same time, the navigation status of each ship is optimized according to the search algorithm, thereby achieving simultaneous optimization of the navigation paths and navigation status of multiple ships, and improving the safety of multiple ships' navigation in restricted waters.

[0067] (2) The present invention uses the convex hull algorithm to extract the contours of natural obstacles and considers the navigation mark system to construct a static obstacle map. The artificial potential field method is used to process the static obstacle map into a potential field, which can obtain a static obstacle image in the restricted waters that includes multiple information such as natural obstacles and navigation marks, providing a scenario for the following steps.

[0068] (3) The present invention uses the A* algorithm to obtain the global path planning effect, and uses APF to perform local planning to consider the safe distance between static obstacles and dynamic ships. It can autonomously adjust the safety factor according to the perceived size of the ship collision risk and the size of the ship area, and provide personalized avoidance solutions for ships.

[0069] (4) The present invention introduces an artificial bee colony algorithm to optimize the avoidance path, avoidance speed and steering amplitude, and realizes steering avoidance and deceleration avoidance in confined waters. It can fully consider the factors of the fixed line system, scientifically allocate the steering amplitude and speed, realize efficient and intelligent collision avoidance when multiple ships meet in confined waters, and ensure the navigation safety of ships. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] Figure 1 It is a schematic diagram of the method flow of the present invention;

[0071] Figure 2 It is an environmental perception map under the convex hull algorithm of the present invention, wherein (a) represents local islands and reefs in the nautical map, (b) represents grayscale processing, (c) represents contour extraction of the convex hull, (d) represents local islands and reefs in the nautical map, (e) represents the appearance of the global nautical map, (f) represents the overlay of the global nautical map, (g) represents contour extraction, and (h) represents the division of the waterway;

[0072] Figure 3 It is a picture of a waterway scene based on the artificial potential field method of the present invention, wherein (a) represents a repulsive field, and (b) represents a gravitational field;

[0073] Figure 4 The present invention is aware of the risks that may occur at a certain moment in the situation;

[0074] Figure 5 The restricted waters avoidance optimization results of the present invention, wherein (a) shows the A*+APF multi-objective avoidance result, (b) shows the artificial bee colony optimization result, (c) shows the optimization result under a three-dimensional perspective, and (d) shows the optimization result under a sea chart overlay;

[0075] Figure 6 This is an evaluation of the effect of multiple ship avoidance in restricted waters of the present invention, wherein (a) shows the ship heading, (b) shows the ship speed, (c) shows the distance between two ships, and (d) shows the risk between two ships. DETAILED DESCRIPTION

[0076] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. This embodiment is implemented based on the technical solution of the present invention, and provides a detailed implementation method and specific operation process, but the protection scope of the present invention is not limited to the following embodiments.

[0077] This embodiment provides a multi-vessel intelligent avoidance optimization method in restricted waters considering the fixed-line system. Figure 1 As shown, the method comprises the following steps:

[0078] Step 1: Perceive natural obstacles. Based on the convex hull algorithm, identify the natural obstacles on the nautical chart and use the convex hull concept to reconstruct the avoidance scenario considering the fixed-line navigation mark, providing a scenario basis for the following experiments.

[0079] (1) Natural obstacle contour extraction

[0080] Land and islands are common natural obstacles. In order to ensure the safety of ships, the location and outline of natural obstacles need to be fully considered. The convex hull is a geometric concept. The mathematical definition of the convex hull is: Let X be any subset of the Euclidean space W. The smallest convex set containing X is called the convex hull of X, denoted as conv(X) = {X1, X2, ..., Xn}. Therefore, it can form a convex polygon by connecting the outermost points, so that it can contain all the points in the point set as comprehensively as possible, that is, the natural obstacle area.

[0081] (2) Integration of route navigation aids and natural obstacle contours

[0082] The environment of restricted waters is extremely complex, and the ship traffic flow is also large. The emergence of the routing system has greatly reduced the occurrence of ship collision accidents in restricted waters. Therefore, the navigation mark of the routing system is another key factor that needs to be considered in the intelligent collision avoidance scenario of ships in restricted waters. At the same time, considering the problem that the route in restricted waters is relatively certain, the original natural obstacle subset and the navigation mark of the routing system are set as new points. With the help of the convex hull idea, each point is connected to obtain the static obstacle environment of the restricted waters.

[0083] Step 2: Construct a navigation scene portrait. Given that ships need to maintain a sufficient safe distance from static obstacles, an artificial potential field is introduced to profile the identified scene, so that personalized avoidance and safe distance limitation can be achieved in the subsequent avoidance phase.

[0084] Navigation scene profiling method based on artificial potential field algorithm:

[0085] In intelligent collision avoidance, the static obstacles constructed by environmental factors can be considered to have a repulsive field with the ship, which can be expressed by mathematical formula (1):

[0086] Commonly used repulsive potential field functions:

[0087]

[0088] Where g is the proportional coefficient, K(t,t0) is a vector pointing from the obstacle to the ship, and its magnitude is the Euclidean distance between the ship and the obstacle |t-t0|. t0 is a constant, which indicates the maximum influence range of the obstacle on the ship.

[0089] It is assumed that there is a gravitational field between the target position and the current position, which can be described by mathematical formula (3):

[0090]

[0091] Among them, β is the proportional gain coefficient, k is a vector, representing the position t of the ship and the position t of the target point n The Euclidean distance between |tt n |, the vector direction is from the position of the ship to the position of the target point.

[0092] k(t,t i )=||tt i ||2 (4)

[0093] Step 3: Perceive ship risks. Risk perception obtains ship collision risks and ship areas, and determines the priority of ship avoidance and the safe distance for avoidance.

[0094] This step considers the avoidance obligation and the avoidance mode of dangerous situations, that is, the avoidance principle and the ship field of the principle of "early, large, wide and clear", and establishes a multi-ship avoidance mechanism that conforms to restricted waters based on the risk cognition results, providing an avoidance basis for the subsequent intelligent algorithm to achieve avoidance. Risk cognition is also called situational awareness. Perception is the premise of intelligent collision avoidance. Ships encounter situational awareness to determine whether to avoid and the priority of avoidance by determining the danger of the ship currently forming a dangerous situation and the target ship.

[0095] (1) Ship collision risk calculation

[0096] DCPA (Distance to Closest Point of Approach) and TCPA (Time to Closest Point of Approach) have always been the key factors in determining whether there is a risk of collision between two ships. The calculation formula is as follows:

[0097]

[0098] Where μ1 is the speed of the own ship at time t, μ2 is the speed of the target ship at time t, and μ rt is the speed of the target ship relative to the own ship at time t, α rt μ is the time t r direction.

[0099] The Collison Risk Index (CRI) is a standard for measuring the risk of ship collision. The present invention uses a negative exponential function to fit and calculate the collision risk, and the formula is as follows:

[0100] CRI t =ω×RDCPAt +τ×RTCPA t (8)

[0101]

[0102] Where a and b are adjustment coefficients, which are generally set according to the characteristics of offshore applications; ω and τ are weight coefficients.

[0103] (2) Definition of the scope of the ship sector

[0104] The present invention uses the quaternion ship domain (QSD) to define the safe distance of the ship. The formula can be expressed as:

[0105]

[0106] Where sgn(.) is defined as follows:

[0107]

[0108] The radius parameters are as follows:

[0109]

[0110] Where L is the captain; AD and DT The calculation is as follows:

[0111]

[0112] Step 4: Plan the navigation path. Based on the basic work of the first three steps, the A* algorithm and APF algorithm are introduced to realize the intelligent collision avoidance of multiple ships in restricted waters.

[0113] Taking the above-mentioned ship collision risk and ship field range as safety constraints, a multi-ship intelligent avoidance method based on A* and APF algorithms is used for path planning:

[0114] (1) Global path planning based on A*

[0115] The A* algorithm is a global planning algorithm. It is a heuristic search algorithm obtained by adding certain restrictions to the evaluation function φ(k)=f(k)+g(k) of the A algorithm. The specific process of the A* algorithm is as follows: If the starting point S i and the target point G i . Let f*(k) be the distance function from the starting point; g*(k) be the distance function to the target point. Then the value function of the A* algorithm is φ*(k)=f*(k)+g*(k). If the A* algorithm takes out an element with the smallest f from the priority queue each time, and then updates the adjacent states. When f(k)>0 and 0<g(k)≤g*(k), then the A* algorithm has the optimal solution.

[0116] (2) Local path planning based on APF

[0117] Artificial potential field method (APF) is a classic path planning method, which is often used for local path planning of mobile robots. Its main idea is to guide the movement of the ship through the combined force potential field of the target's gravity and the repulsion of obstacles. The expression of the combined force potential field is:

[0118] G(q)=G k (t)+G ω (t) (15)

[0119] In the formula, G(q) is the artificial potential field, that is, the resultant potential field, G k (t) is the gravitational field, G ω (t) is the repulsive field. The expressions of the repulsive potential field and the attractive potential field are given in formulas (1) and (3).

[0120] The optimal navigation path for the ship is formed based on the shortest path planned globally and the path of the local navigable area.

[0121] Step 5: Optimize the ship's traffic status. Consider the avoidance conditions in restricted waters, optimize steering avoidance and deceleration avoidance, and obtain a smooth avoidance trajectory and a scientific and safe avoidance method. In addition, it also has the function of evaluating the avoidance effect. Finally, the avoidance effect under the electronic chart is presented with the help of coordinate conversion technology.

[0122] Optimization of multi-vessel intelligent avoidance involving artificial bee swarms:

[0123] Multi-ship intelligent collision avoidance requires not only a reasonable avoidance path, but also a more scientific heading and speed distribution to maintain heading safety during avoidance. The artificial bee colony algorithm is a meta-heuristic algorithm based on bee colonies. It can optimize numerical problems to achieve the optimization of heading and speed during avoidance. The method mainly includes four steps:

[0124] Initial stage

[0125] All nectar sources are initialized using scout bees, where the location of the nectar source represents the navigation status of the ship, including heading and speed. The initialization expression is:

[0126] f nj =k j +rand(0,1)×(ω j -k j ) (16)

[0127] Employment stage

[0128] Honey bees search for neighbors based on the location of the nectar source in their memory and calculate the fitness to determine the neighboring nectar source:

[0129]

[0130] Among them, the fitness is converted into a minimization problem by the following formula for solution:

[0131]

[0132] In the formula, g nj Honey source for neighbors, f tj is a randomly selected nectar source. It is a random number used to calculate the fitness value after a new nectar source is generated.

[0133] Observation phase

[0134] The observer bee randomly selects a nectar source based on the nectar source information obtained by the honey bees, generates a new nectar source near the selected nectar source, and calculates the fitness of the new nectar source. The probability of being selected by the observer bee is:

[0135]

[0136] In the formula, ψ n is the probability formula of nectar source. RM is the number of honey bees and observer bees.

[0137] Reconnaissance phase

[0138] If a honey bee does not improve due to the observation of an observer bee within a certain number of optimization searches, then after reaching this number of searches, the initial stage will be restarted, and the expression will still be formula (16) until the optimal nectar source is found.

[0139] The present invention takes the waters near a certain place in the deep-water channel of the Yangtze River Estuary as a case scenario. This water area is one of the busiest waterways. This water area uses a fixed-line system and a "north main and south auxiliary" navigation situation diversion to guide the diversion of ships of different sizes, each going its own way without affecting each other, thereby improving the navigation safety guarantee rate. However, the types of ships in this water area are diverse and the traffic environment is complex. In addition to the normal passage of merchant ships, there are also small ships such as fishing boats that sail in between. This poses a safety hazard to the navigation safety of ships in this water area. The purpose of the present invention is to establish a multi-ship avoidance mode that fully considers the risk of collision, to avoid the formation of an emergency situation by both parties taking avoidance actions as soon as possible, and to scientifically formulate avoidance plans with the help of intelligent optimization algorithms.

[0140] Table 1 Initial ship parameters

[0141] S1 S2 S3 S4 S5 Starting point (nm) (15,0) (2.5,12) (0,14.2) (18,7.7) (5.3 8.9) End point (nm) (1,15.5) (18,6.5) (13.9,0) (1,15.5) (18,6.5) Heading(°) 314 127 136 237 46 Speed(kn) 10 8 12 15 7

[0142] In order to identify the natural obstacles and navigation marks in the waters, the embodiment of the present invention uses the convex hull algorithm to extract the contour information of land and islands and reefs and reconstruct the scene from the intercepted nautical chart image of the waters ( Figure 2 ). Figure 2 Figures (a)-(d) show the process of grayscale processing of a nautical island image and extracting its contour using the convex hull algorithm; Figure 2 Figures (e)-(h) show the process of geometrically processing the outline of the entire selected water area and reconstructing the experimental scene considering the fixed-line navigation aids. Figure 2 (h) The gray line segment in the upper left corner indicates that the route is divided into two parts, left and right, in the route setting system, to guide the ships to follow their own paths. At the same time, the present invention also uses the artificial potential field method to profile the environmental scene ( Figure 3 ), the image part includes the repulsive potential field ( Figure 3 (a)) and the gravitational potential field ( Figure 3 (b) Figure). Prepare for the next multi-ship intelligent collision avoidance. Focusing on the multi-ship collision avoidance problem under the complex encounter situation of ships in restricted waters, firstly, 5 ships sailing in different directions are designed in the above scenario (Table 1), and then the priority of avoidance is determined by calculating the collision risk of the 5 ships in the encounter situation, and then the ship field is considered to ensure that the ships have a sufficiently safe distance to navigate, and finally a multi-ship intelligent collision avoidance mode considering the collision risk of ships and the ship field is established ( Figure 4 ). Figure 4 The results depict that at a certain moment, the S3 ship feels the collision danger of the target ships S1, S2, S4, and S5, among which S2 is the top priority target for S3 to avoid, followed by S1. According to the above avoidance mode, the collision danger threshold is set to 0.2, the ship area boundary is 0.5nm, and the A* algorithm and APF algorithm are combined to realize multi-ship intelligent collision avoidance ( Figure 5 (a) in the figure). Figure 5 Figure (a) shows that the A* and APF algorithms can achieve multi-ship intelligent collision avoidance in confined waters, but the problem of uneven trajectory still exists in the enlarged effect diagram in the upper right corner. At the same time, in order to further optimize the avoidance speed and heading, the present invention introduces an artificial bee colony algorithm. The optimization effect is shown in Figure 1. Figure 5 As shown in Figure (b), the distribution of the ship area positions in the figure can illustrate the demarcation of the area without invading ships that is always maintained during avoidance. In addition, in order to more clearly reflect the avoidance effect, the present invention expands the avoidance effect from the time dimension. Figure 5 Figure (c) shows the temporal and spatial motion trajectories of multiple ships avoiding each other. Finally, with the help of coordinate transformation technology, the effect display of electronic chart is realized.

[0143] In order to highlight the multi-ship intelligent collision avoidance decision-making scheme designed for confined waters, the present invention analyzes the speed and heading of the ship during the avoidance process ( Figure 6 (a)-(b) in Figure 1). Since lane separation and diversion under the fixed-route system already exist in the implementation scenario, no turning measures will be taken unless necessary, especially in the established route. Figure 6The course change result of Figure (a) in FIG. 1 is consistent with the actual course operation. In view of the steering limitation, the present invention considers deceleration and avoidance, and the optimized speed change curve ( Figure 6 Figure (b) shows the speed changes of the five ships during the avoidance process. In order to judge the safety and scientificity of the avoidance scheme, the present invention performs real-time ship-to-ship distance analysis and ship-to-ship collision risk analysis on the avoidance process ( Figure 6 (c)-(d) in the figure). Figure 6 Figure (c) shows that the minimum distance between ships during the avoidance process is 0.6nm, which is in line with the limitations in the ship field. Figure 6 Figure (d) shows that the maximum collision risk of the ship during the avoidance process is about 0.7, and there is no emergency situation in the encounter. In view of the above experimental verification, the present invention is effective for multiple ship avoidance in restricted waters and meets the restriction requirements of the ship field and collision risk.

[0144] In summary, the embodiment of the present invention proposes an optimization method for intelligent avoidance of multiple ships in restricted waters taking into account the routing system, taking into account natural obstacles and routing system information to obtain avoidance scenarios, combining collision risks and ship fields to introduce artificial potential field methods and A* algorithms to obtain multi-ship avoidance paths, integrating artificial bee colony algorithms to achieve multi-ship intelligent collision avoidance in restricted waters, and obtaining optimal routes, avoidance headings and speeds, providing supervision guidance for shore-based supervisors. The present invention applies classical intelligent algorithms and bionic algorithms to the fields of water traffic risk management and complex water traffic risk engineering, fully considering multiple information such as routing systems in restricted waters and artificial intelligence algorithms, providing avoidance optimization solutions for ship navigation in restricted waters, realizing intelligent port traffic control demonstration applications and knowledge discovery, and is conducive to ensuring navigation safety in waters near ports. The present invention can be used as an auxiliary tool for shore-based control personnel to regulate ship navigation.

[0145] If the above functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program code.

[0146] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes. The schemes in the embodiments of the present invention may be implemented in various computer languages, for example, object-oriented programming language Java and literal scripting language JavaScript, etc.

[0147] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0148] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0149] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0150] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0151] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A multi-vessel intelligent avoidance optimization method in restricted waters considering a fixed-line system, characterized in that: The following steps are involved: Obtain environmental information in restricted waters and status information of each ship; Based on the environmental information and state information, and in combination with the route-fixed navigation mark, an artificial potential field algorithm is used to construct a navigation scene portrait; Under the navigation scenario portrait, calculate the risk of ship collision and define the safe distance of ships; Based on the navigation scene portrait, the ship collision risk and the safe distance between ships are used as collision avoidance conditions, and a path planning algorithm combining global and local methods is adopted to plan the optimal navigation path for each ship. At the same time, a search algorithm is used to optimize the navigation status of each ship to complete the multi-ship intelligent avoidance optimization process.

2. The method for optimizing multi-vessel intelligent avoidance in restricted waters considering the fixed-line system according to claim 1 is characterized in that: The steps of constructing the navigation scene portrait include: According to the environmental information in the restricted waters, a convex hull algorithm is used to extract the outline of the natural obstacle to obtain the natural obstacle area; An artificial potential field algorithm is used based on the natural obstacle areas, route navigation marks and status information to construct a navigation scene portrait.

3. The method for optimizing multi-vessel intelligent avoidance in restricted waters considering the fixed-line system according to claim 2 is characterized in that: The step of obtaining the natural obstacle area comprises: Let X be any subset of the Euclidean space W, and the smallest convex set containing X is called the convex hull of X, denoted by conv(X) = {X1,X2,…,X n }, where each convex hull corresponds to a natural obstacle object; Connect the outermost points of each convex hull to form a convex polygon as a natural obstacle area.

4. The method for optimizing multi-vessel intelligent avoidance in restricted waters considering the fixed-line system according to claim 2 is characterized in that: The steps of constructing the navigation scene portrait include: Based on the repulsive relationship between the natural obstacle objects and the navigation mark in the natural obstacle area, a repulsive field is constructed, wherein the expression of the repulsive field is: K(t,t0)=||t-t0||2 In the formula, G k (t) is the repulsive potential field function, g is the proportional coefficient, K(t,t0) is a vector whose direction is from the obstacle to the ship and whose magnitude is the Euclidean distance between the ship and the obstacle |t-t0|. t0 is a constant, which indicates the maximum influence range of the obstacle on the ship. K λ is a constant, indicating the maximum distance at which an obstacle affects a ship; Based on the gravitational relationship between the position of each ship and the target position, a gravitational field is constructed, wherein the expression of the gravitational field is: k(t,t i )=||t-t i ||2 In the formula, G ω (t) is the gravitational field function, k(t,t i ) is a vector, representing the position of the ship t and the position of the target point t i The Euclidean distance between |tt i |, k λ is a constant, β is the proportional gain coefficient; The repulsive field and the gravitational field are used as navigation scene images.

5. The method for optimizing multi-vessel intelligent avoidance in restricted waters considering the fixed-line system according to claim 1 is characterized in that: The calculation process of the ship collision risk degree includes: According to the status information of each ship, the DCPA parameters and TCPA parameters are calculated, wherein the expressions of the DCPA and TCPA parameters are respectively: In the formula, DCPA t is the DCPA parameter, α rt is the relative heading of the target ship at time t, TCPA t is the TCPA parameter, μ r is the speed of the target ship relative to the own ship at time t, μ1 is the speed of the own ship at time t, μ2 is the speed of the target ship at time t, D t is the distance between the two ships at time t, β Tt is the direction of the target ship relative to the own ship at time t; Based on the DCPA parameters and TCPA parameters, a negative exponential function is used to fit and calculate the ship collision risk, wherein the expression of the ship collision risk is: CRI t =ω×RDCPA t +τ×RTCPA t Where, CRI t is the risk of ship collision, ω and τ are weight coefficients, a and b are adjustment coefficients, DCPA′ t is the dimensionless DCPA, TCPA′ is the dimensionless TCPA, RDCPA t For DCPA risk components, RTCPA t It is a TCPA risk component.

6. The method for optimizing multi-vessel intelligent avoidance in restricted waters considering the routing system according to claim 1 is characterized in that: The safety distance of the ship is defined by using the quaternion ship field, and the safety distance is expressed as: in: Where η k is the boundary of the ship area, (x, y) is the position of the ship, S is the quaternion, and D fore is the distance to the front of the ship, D aft is the stern distance, D starb is the distance to the starboard side of the ship, D portt is the distance to the port side of the ship, ξ AD is the gain of the advance distance, ξ DT is the gain of the swing diameter, L is the length of the ship, A D is the advance distance, D T is the initial diameter of the cycle, V own is the ship's speed.

7. The method for optimizing multi-vessel intelligent avoidance in restricted waters considering the fixed-line system according to claim 1 is characterized in that: The A* algorithm is used as the global path planning algorithm to plan the global shortest path, and the artificial potential field algorithm is used as the local path planning algorithm to plan the local path to obtain the optimal navigation path for the ship. In the A* algorithm path planning process, the value function is used to evaluate the value of each ship from the starting point S i To the target point G i The total cost estimate is used to find the shortest path. When f(k)>0 and 0<g(k)≤g*(k), the shortest path is obtained, where the expression of the value function is: φ*(k)=f*(k)+g*(k) Where φ*(k) is the value function, f*(k) is the distance function from the starting point, g*(k) is the distance function to the target point, f(k) is the actual cost from the initial state to state k, and g(k) is the estimated cost of the best path from state k to the target state.

8. The method for optimizing multi-vessel intelligent avoidance in restricted waters considering the fixed-line system according to claim 7 is characterized in that: The steps of local path planning include: The artificial potential field algorithm forms a resultant potential field by acting the repulsive field and the gravitational field on the ship, so as to guide the ship to move on a local path according to the resultant potential field, wherein the expression of the resultant potential field is: G(q)=G k (t)+G ω (t) In the formula, G(q) is the artificial potential field, that is, the resultant potential field, G k (t) is the gravitational field, G ω (t) is the repulsive field.

9. The method for optimizing multi-vessel intelligent avoidance in restricted waters considering the fixed-line system according to claim 1 is characterized in that: The search algorithm is an artificial bee colony algorithm. The steps of using the artificial bee colony algorithm to optimize the navigation status of each ship include: Initial stage: All nectar sources are initialized using scout bees, where the location of the nectar source represents the navigation status of the ship, including heading and speed. The initialization expression is: f nj =k j +rand(0,1)×(ω j -k j ) In the formula, f nj is the nectar source, n is the population size, j is the number of variables, k j ,ω j f nj The upper and lower limits of the value; Employment Phase: Honey bees search for neighbors based on the location of the nectar source in their memory and calculate the fitness to determine the neighboring nectar source: Among them, the fitness is converted into a minimization problem by the following formula for solution: In the formula, g nj Honey source for neighbors, f tj is a randomly selected nectar source. is a random number used to calculate the fitness value of a new nectar source. is the objective function value of the nth nectar source; Observation phase: The observer bee randomly selects a nectar source based on the nectar source information obtained by the honey bees, generates a new nectar source near the selected nectar source, and calculates the fitness of the new nectar source. The probability of being selected by the observer bee is: In the formula, ψ n is the probability of the nectar source being selected; Reconnaissance phase: If a honey bee decides to give up the nectar source it has after a given number of attempts, it will become a scout bee and restart the initial stage until it finds the best nectar source.

10. A computer-readable storage medium, characterized in that: It includes one or more programs for execution by one or more processors of an electronic device, and the one or more programs include instructions for executing the multi-vessel intelligent avoidance optimization method in restricted waters considering the routing system as described in any one of claims 1-9.

Images