Ship route planning method and device for near-shore environment and electronic equipment

Abstract

The application provides a ship path planning method and device for a near-shore environment and electronic equipment, and belongs to the technical field of artificial intelligence. The method comprises the following steps: rasterizing a near-shore environment image to obtain a sailing space model; setting initial parameters of an improved potential field-ant colony algorithm and initializing a path taboo table, then determining path point pheromone distribution and a combined potential field force, calculating a transfer probability of an ant transferring to other nodes to determine a next node, and updating the taboo table; after an ant traverses all nodes to reach a target point, updating the pheromone distribution and recording a traversal path; after all ants traverse all nodes, obtaining traversal paths of all ants and determining an optimal path. The application improves the potential field-ant colony algorithm, introduces potential field information, and dynamically adjusts a heuristic information function; adjusts a path selection probability optimization algorithm structure; and considers the sailing characteristics of a ship itself to ensure the demand for autonomous sailing of the ship.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular to a method, apparatus and electronic equipment for ship path planning in nearshore environments. Background Technology

[0002] The nearshore complex static environment contains a high density of static obstacles in a complex distribution, such as island and reef areas, ports, narrow waterways, and anchorages. Therefore, the nearshore complex static environment places extremely high demands on the ship's maneuverability.

[0003] Among related technologies, Ant Colony Optimization (ACO) is a computational optimization strategy that mimics the social behavior of insects. It possesses strong search capabilities and robustness and is widely used in path planning. However, when the basic ant colony algorithm is applied to complex static nearshore environments, it suffers from problems such as low computational efficiency, slow convergence, and jagged paths, making it difficult to meet actual navigation requirements. Summary of the Invention

[0004] This application provides a method, apparatus, and electronic device for ship path planning in nearshore environments, in order to at least solve the above-mentioned technical problems existing in the prior art.

[0005] The first aspect of this application provides a method for ship path planning in a nearshore environment, comprising:

[0006] The nearshore environment image is rasterized to obtain a navigation space model; the navigation space model includes the starting point, target point, and obstacle information.

[0007] Set the initial parameters for the improved potential field-ant colony algorithm and initialize the path taboo table;

[0008] Based on the initial parameters, the pheromone distribution and the combined potential force at each path point are determined;

[0009] Initiate a path traversal of multiple ants, and calculate the transfer probability of an ant moving to other nodes based on the heuristic information function obtained from the pheromone distribution and the combined potential force of each path point.

[0010] The next node is determined based on the transition probability, and the tabu table is updated; the next node is the node with the highest transition probability.

[0011] After an ant has traversed all the aforementioned nodes and reached the target point, update the pheromone distribution and path taboo table, and record the traversal path;

[0012] Update the number of ants, iterate until all ants have traversed all nodes, then update the global pheromone distribution to obtain the traversal path of all ants;

[0013] The optimal path is determined based on the traversal paths of all ants.

[0014] In one possible implementation, the step of rasterizing the nearshore environmental image to obtain a navigation space model includes:

[0015] The nearshore environment image is rasterized to obtain a raster map; the raster map includes ocean areas and obstacle areas.

[0016] Based on the actual position of the ship, the coordinates of the ship's starting point, the coordinates of the target point, and the spatial distribution characteristics of obstacles in the grid map are determined to obtain a navigation space model.

[0017] In one possible implementation, the initial parameters include:

[0018] Ant population, pheromone evaporation coefficient, pheromone intensity, gravitational potential field coefficient, repulsive potential field coefficient, and the boundary line of influence of artificial potential field.

[0019] In one possible implementation, the combined potential force is determined in the following manner:

[0020] The repulsive potential field function is:

[0021]

[0022] The boundary line of influence of the artificial potential field is determined by the gravitational potential field function, which is:

[0023]

[0024] The composite potential field is:

[0025]

[0026] The combined potential field force is:

[0027]

[0028] in, The force acting as a composite potential field; It is a repulsive force; Position of the ship; Location of the obstacle; It is the repulsive field enhancement factor; This represents the distance between the ship and the obstacle. The range of the repulsive field around the obstacle; Let be the gravitational potential field function; This is the gravitational potential field gain factor; The location of the target point; This represents the relative distance between the ship and the target point. The boundary line for the influence of artificial potential field.

[0029] In one possible implementation, the heuristic information function is:

[0030]

[0031] in, for t Time Node , Distance heuristic function; It is a constant; The force acting as a composite potential field; The interaction force between the ant's path direction and the combined potential field The angle between directions; For the current node To the next node The distance between them.

[0032] In one possible implementation, the probability of an ant moving to another node is calculated based on a heuristic information function using the following method:

[0033] Introducing random numbers and fixed constant ;

[0034] when When the transition probability is reached, it is calculated in the following way:

[0035]

[0036] when When the transition probability is reached, it is calculated in the following way:

[0037]

[0038] Among them, among them, , It is a random number; , For fixed parameters; t For time; For information heuristic factors, As a heuristic factor for expected value; This represents the set of nodes that the ant can choose in the next moment. For nodes , Inter-pheromone value; For nodes , s Inter-pheromone value; For distance; This represents the number of adjacent nodes from the current node. For nodes , s Distance heuristic function.

[0039] In one possible implementation, updating the pheromone distribution includes:

[0040] The pheromone distribution is updated based on path length, safe distance, and corner constraints.

[0041] In one possible implementation, the pheromone change value is calculated in the following manner:

[0042]

[0043] The pheromone distribution is calculated using the following method:

[0044]

[0045] in, For a moment t No. Only ants from the node Move to node The pheromone change value; For the first Only ants at all times t +1 node , The pheromone value between them; For the first Only ants at all times t node , Inter-pheromone value; The global pheromone evaporation coefficient;

[0046] in,

[0047]

[0048]

[0049]

[0050] in, For general constraints; C Pheromones intensity; , , All are weighting coefficients; It is a path length constraint; It is a safety distance constraint; It is a corner constraint; It is the total number of nodes on the path; It is the ant visiting the current node. To the next node The distance; The current node To the next node Path security level; The current node To the next node The steering angle; The current node To the next node The safety of ships may be affected by distance; For intelligent agents at nodes The x-coordinate; For intelligent agents at nodes The x-coordinate; For intelligent agents at nodes The ordinate; For intelligent agents at nodes The ordinate.

[0051] A second aspect of this application provides a vessel path planning device for nearshore environments, comprising:

[0052] The image raster module is used to rasterize nearshore environmental images to obtain a navigation space model; the navigation space model includes starting point, target point, and obstacle information;

[0053] The parameter setting module is used to set the initial parameters of the improved potential field-ant colony algorithm and initialize the path taboo table;

[0054] The first determining module is used to determine the pheromone distribution and the combined potential force of each path point based on the initial parameters.

[0055] The node calculation module is used to initiate the path traversal of multiple ants and calculate the transfer probability of an ant moving to other nodes based on the heuristic information function obtained from the pheromone distribution and the combined potential field force of each path point.

[0056] The second determining module is used to determine the next node based on the transition probability and update the tabu table; the next node is the node with the highest transition probability;

[0057] The first update module is used to determine the pheromone distribution and path taboo table after an ant has traversed all the nodes and reached the target point, and to record the traversal path.

[0058] The second update module is used to update the number of ants. It iterates until all ants have traversed all nodes, then updates the global pheromone distribution to obtain the traversal path of all ants.

[0059] The path determination module is used to determine the optimal path based on the traversal paths of all ants.

[0060] A third aspect of this application provides an electronic device comprising:

[0061] At least one processor;

[0062] and a memory communicatively connected to the at least one processor; wherein,

[0063] The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method described in this application.

[0064] A fourth aspect of this application provides a non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform the methods described in this application.

[0065] The method, apparatus, and electronic equipment for ship path planning in nearshore environments proposed in this application improve the potential field-ant colony algorithm by introducing potential field information and dynamically adjusting the heuristic information function; optimize the path selection probability algorithm structure by adjusting the algorithm structure; and ensure the ship's autonomous navigation needs by considering the ship's own navigation characteristics.

[0066] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent from the following description. Attached Figure Description

[0067] The above and other objects, features, and advantages of exemplary embodiments of this application will become readily apparent from the following detailed description taken in conjunction with the accompanying drawings. Several embodiments of this application are illustrated in the drawings by way of example and not limitation, in which:

[0068] In the accompanying drawings, the same or corresponding reference numerals indicate the same or corresponding parts.

[0069] Figure 1 This paper illustrates a flowchart of a ship path planning method for nearshore environments according to an embodiment of this application.

[0070] Figure 2 This paper illustrates another flowchart of a ship path planning method for nearshore environments according to an embodiment of this application.

[0071] Figure 3 A schematic diagram of the structure of a ship path planning device for nearshore environments according to an embodiment of this application is shown;

[0072] Figure 4 The following diagram shows a comparison of simulation results for an algorithm with a small number of obstacles in a simple environment according to an embodiment of this application.

[0073] Figure 5 This paper presents a comparison chart of iterative convergence of algorithms in a simple environment with a small number of obstacles, based on embodiments of this application.

[0074] Figure 6 The following diagram shows a comparison of simulation results for the algorithm in a simple environment with a moderate number of obstacles according to the embodiments of this application;

[0075] Figure 7 This paper presents a comparison chart of iterative convergence of algorithms in a simple environment with a moderate number of obstacles, based on embodiments of this application.

[0076] Figure 8 The following diagram shows a comparison of simulation results for algorithms used in simple environments with a large number of obstacles according to embodiments of this application.

[0077] Figure 9 This paper presents a comparison chart of iterative convergence of algorithms for simple environments with a large number of obstacles, based on embodiments of this application.

[0078] Figure 10 The following diagram shows a comparison of simulation results for an environmental algorithm with a small number of obstacles in a complex environment according to an embodiment of this application;

[0079] Figure 11 This paper presents a comparison chart of iterative convergence of algorithms for complex environments with a small number of obstacles according to embodiments of this application;

[0080] Figure 12 The following diagram shows a comparison of simulation results for the algorithm in a complex environment with a moderate number of obstacles according to the embodiments of this application;

[0081] Figure 13 The following diagram shows a comparison of iterative convergence of algorithms for complex environments with a moderate number of obstacles according to embodiments of this application;

[0082] Figure 14 The following diagram shows a comparison of simulation results for algorithms used in complex environments with a large number of obstacles according to embodiments of this application;

[0083] Figure 15 This paper presents a comparison chart of iterative convergence of algorithms for complex environments with a large number of obstacles, based on embodiments of this application.

[0084] Figure 16 A schematic diagram of the composition structure of an electronic device according to an embodiment of this application is shown. Detailed Implementation

[0085] To make the objectives, features, and advantages of this application more apparent and understandable, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0086] The following description, in conjunction with the accompanying drawings, introduces a method, apparatus, and electronic equipment for ship path planning in a nearshore environment provided in this application.

[0087] like Figure 1 As shown, this application provides a ship path planning method for nearshore environments, including:

[0088] S101, the nearshore environmental image is rasterized to obtain a navigation space model; the navigation space model includes the starting point, target point and obstacle information.

[0089] In this application, the nearshore environment may contain obstacles such as islands and reefs, ports, narrow waterways, and anchorages. The grid method can model the environment and simulate the physical boundaries of obstacles in the real environment. The navigation space model makes the processing of complex spatial information more intuitive.

[0090] In some embodiments, the step of rasterizing the nearshore environmental image to obtain a navigation space model includes:

[0091] The nearshore environment image is rasterized to obtain a raster map; the raster map includes ocean areas and obstacle areas.

[0092] Based on the actual position of the ship, the coordinates of the ship's starting point, the coordinates of the target point, and the spatial distribution characteristics of obstacles in the grid map are determined to obtain a navigation space model.

[0093] In this application, nearshore environmental images are first acquired and then rasterized into uniformly sized grids, each representing a discrete spatial unit. Image recognition is used to divide the raster map into ocean areas (representing waters where ships can safely navigate) and obstacle areas (shoals, islands, docks, shipwrecks, no-navigation zones, etc.). The ship's location data (latitude and longitude) is used, combined with the coordinate transformation relationships of the raster map (such as the mapping formula between latitude / longitude and raster row / column indices), to calculate the ship's corresponding raster coordinates in the raster map. For example, if the ship's actual location is (120°E, 30°N), after transformation, it corresponds to row 20 and column 50 in the raster map, so the starting point coordinates are (20, 50). Similarly, the latitude and longitude of the ship's destination (such as a port or anchorage) are converted into raster coordinates in the raster map, which is the target point.

[0094] S102, Set the initial parameters of the improved potential field-ant colony algorithm and initialize the path taboo table.

[0095] It's important to note that the ant colony algorithm relies on a positive feedback mechanism. While this accelerates the search process, it's prone to getting trapped in local optima, making it difficult to escape these regions and ultimately preventing the discovery of the optimal path. In the artificial potential field method, when obstacles are closely distributed around the target point, the repulsive force generated by the obstacles may outweigh the gravitational force generated by the target point. This affects the path planning algorithm's search capability, preventing the ant from reaching the target point. The taboo list records the nodes already visited by the ants, preventing duplicate visits. After the ants complete their traversal, the taboo list needs to be reset to support the next path search.

[0096] Therefore, this application improves the ant colony algorithm by combining the artificial potential field method, initializing the initial parameters and path taboo table of the improved potential field-ant colony algorithm. The improved potential field-ant colony algorithm can effectively reduce the range of influence of the gravitational potential field, reduce the risk of collision, strongly guide ants to choose the target direction, and finally obtain the optimal path.

[0097] S103, Based on the initial parameters, determine the pheromone distribution and the combined potential force at each path point.

[0098] In this application, the initial parameters include: ant population, pheromone evaporation coefficient, pheromone intensity, gravitational potential field coefficient, repulsive potential field coefficient, and the boundary line of artificial potential field influence.

[0099] To address the potential collision problem caused by the gravitational potential field function, this application introduces an artificial potential field influence boundary line. When the relative distance between the ship and the target point At that time, the gravitational potential field value and The squares are positively correlated; when At that time, the gravitational potential field value and They are positively correlated. This improvement effectively reduces the range of the gravitational potential field, thus lowering the risk of collision.

[0100] S104, initiate path traversal for multiple ants, and calculate the transfer probability of an ant moving to other nodes based on the heuristic information function obtained from the pheromone distribution and the combined potential field force of each path point.

[0101] The number of ants, pheromone evaporation coefficient, and pheromone intensity in the initial parameters determine the pheromone distribution, while the gravitational potential field coefficient and repulsive potential field coefficient summarized from the initial parameters determine the combined potential field force.

[0102] In this application, in a marine environment, it is assumed that an obstacle exerts a repulsive force on the ship. The strength of this repulsive force is negatively correlated with the distance between the ship and the obstacle. As the ship gradually approaches the obstacle, the force of the repulsive field increases as the distance decreases. When the distance between the ship and the obstacle almost disappears, the force of the repulsive field will increase infinitely, thus ensuring that the ship will not collide with the obstacle. If the distance between the ship and the obstacle gradually increases, the repulsive force will weaken accordingly. When the ship is very far from the obstacle, the value of the repulsive field will drop to zero.

[0103] In some embodiments, the combined potential force is determined in the following manner:

[0104] The repulsive potential field function is:

[0105]

[0106] Ships avoid obstacles due to the repulsive force exerted by the repulsive potential field, which originates from the negative gradient of the repulsive field.

[0107] In this application, an influence boundary line for the potential field function is introduced. .when At that time, the gravitational potential field value and The squares are positively correlated; when At that time, the gravitational potential field value and They are positively correlated. This improvement effectively reduces the range of influence of the gravitational potential field, thus lowering the risk of collision. Specifically, the boundary line of the artificial potential field's influence is determined by the gravitational potential field function, which is:

[0108]

[0109] The composite potential field is:

[0110]

[0111] The resultant force acting on this vessel is the negative gradient of the total potential field, and the force of the resultant potential field is:

[0112]

[0113] in, The force acting as a composite potential field; Let be the repulsive potential field function; Position of the ship; Location of the obstacle; It is the repulsive field enhancement factor; This represents the distance between the ship and the obstacle. The range of the repulsive field around the obstacle; Let be the gravitational potential field function; This is the gravitational potential field gain factor; The location of the target point; This represents the relative distance between the ship and the target point. The boundary line for the influence of artificial potential field.

[0114] In traditional ant colony optimization algorithms, the heuristic function is inversely proportional to the Euclidean distance from the current node to the target node. However, when the distance between the ship and the target point is large, this relationship becomes problematic. If the value is too small, the ant's probability of random exploration is relatively high; while at close range, If the value is too large, it will affect the ants' choice of the optimal path. This primitive method results in insufficient guidance at long distances and slow convergence at short distances. Therefore, the traditional heuristic information function is improved.

[0115] In this application, the traditional heuristic information function is improved by introducing a piecewise function as the ant approaches the target ( When the heuristic weights are amplified by 10 times, the ants are more inclined to move directly towards the target when choosing a path closer to it. In the transition probability formula, when... If the weight is increased tenfold, the weight of the heuristic information grows exponentially, thus strongly guiding the ants to choose the target direction.

[0116]

[0117] in, for t Time Node , Distance heuristic function; It is a constant; The force acting as a composite potential field; The interaction force between the ant's path direction and the combined potential field The angle between directions; For the current node To the next node The distance between them.

[0118] S105, determine the next node based on the transition probability and update the tabu table; the next node is the node with the highest transition probability.

[0119] In this application, random numbers are introduced. and fixed constant ,when When the algorithm selects the path that maximizes the product of heuristic information and pheromone concentration, this path is the optimal solution under the current exploration environment; when In this case, the roulette wheel strategy of the basic ant colony algorithm is used for path selection. Through this improvement, the algorithm can prioritize the selection of the optimal path and also has a certain degree of randomness, which can effectively solve the problem of low computational efficiency caused by over-exploration.

[0120] The improved method for calculating the transition probability is as follows:

[0121] when When the transition probability is reached, it is calculated in the following way:

[0122]

[0123] when When the transition probability is reached, it is calculated in the following way:

[0124]

[0125] in, , It is a random number; , For fixed parameters; t For time; For information heuristic factors, As a heuristic factor for expected value; This represents the set of nodes that the ant can choose in the next moment. For nodes , Inter-pheromone value; For nodes , s Inter-pheromone value; For distance; This represents the number of adjacent nodes from the current node. For nodes , s Distance heuristic function.

[0126] S106, after an ant has traversed all the nodes and reached the target point, update the pheromone distribution and path taboo table, and record the traversal path.

[0127] Specifically, in this application, ants that complete a path release pheromones along the path they traverse, with the release amount inversely proportional to the total path length. Updating the pheromone distribution provides feedback on the quality of the path (high-quality paths have stronger pheromones), the tabu list is reset to release node resources for the next search, and the path records provide data support for algorithm iteration.

[0128] In some embodiments, updating the pheromone distribution includes:

[0129] The pheromone distribution is updated based on path length, safe distance, and corner constraints.

[0130] In this application, in order to ensure the safety, smoothness and operability of the planned trajectory, the pheromone update strategy is redesigned, and factors such as path length, safety distance and turning angle restrictions are introduced, so that the path planning method is more in line with the navigation mechanism of ships.

[0131] The pheromone change value is calculated using the following method:

[0132]

[0133] The pheromone distribution is calculated using the following method:

[0134]

[0135] in, For a moment t No. Only ants from the node Move to node The pheromone change value; For the first Only ants at all times t +1 node , The pheromone value between them; For the first Only ants at all times t node , Inter-pheromone value; The global pheromone evaporation coefficient;

[0136] in,

[0137]

[0138]

[0139]

[0140] in, For general constraints; For nodes , The nth-order pheromone distribution between them; C is the pheromone intensity; These are the weighting coefficients for the path length constraint; These are the weighting coefficients for the safety distance constraint; These are the weighting coefficients for the corner constraints; It is a path length constraint; It is a safety distance constraint; It is a corner constraint; It is the total number of nodes on the path; It is the ant visiting the current node. To the next node The distance, in meters; The current node To the next node Path security level; The current node To the next node The steering angle; The current node To the next node The safety of ships may be affected by distance.

[0141] In addition, this application optimizes the path smoothness by using a Bézier curve to smooth the initial path. The nth-order Bézier curve is as follows:

[0142]

[0143]

[0144] in, These are the motion control points of the Bézier curve; For the location point, m For parameters, and These are the starting point and the target point, respectively. The parameters on the curve are m point; The coefficients are binomial coefficients.

[0145] It should be noted that the higher the order of the Bézier curve, the greater the optimization and the smoother the path. However, it also increases the likelihood of collisions. This application uses a third-order Bézier curve to smooth the initial path, which effectively eliminates uneven turns in the original path, making the ship's course change more gradual. At the same time, by adjusting the distance between the control point and the obstacle, it ensures that there is a sufficient safety threshold between the path and the obstacle.

[0146] Determine if the ant has reached the end of the path. If it has not reached the end, return to calculate the combined potential force; if it has reached the end, save the current path length value.

[0147] S107, update the number of ants, iterate until all ants have traversed all nodes, update the global pheromone distribution, and obtain the traversal path of all ants.

[0148] Specifically, update the ant count. ,judge Is it equal to If the total number is not reached, return to calculate the pheromone distribution of each path point; if the total number is reached, perform a global pheromone update and complete the current iteration cycle.

[0149] This application, based on the initial number of ants, completes the traversal of all nodes by all ants. Then, through global pheromone updates, path taboo table resets, and path aggregation, the algorithm gradually approximates the optimal path. Each ant completes the traversal from the starting point to the target point, and then performs a local update. After all ants have completed their path traversal, a global update is performed. After the global update, the system needs to record the traversal paths of all ants, forming a path set.

[0150] S108: Determine the optimal path based on the traversal paths of all ants.

[0151] Finally, the optimal path is determined from all the ants' traversal paths.

[0152] This application also includes simulation comparison experiments on the optimal ship path between the basic ant colony algorithm and the potential field-ant colony algorithm.

[0153] like Figure 2 As shown, this application obtains a navigation space model by rasterizing nearshore environmental images, and then determines the optimal path within the navigation space model. First, the parameters in the ant colony algorithm and the potential field algorithm are initialized to obtain initial parameters and a path taboo table. The pheromone distribution at each path point is calculated based on the ant colony algorithm, and the synthetic potential field force is calculated based on the potential field algorithm. Path traversal of multiple ants is initiated. Based on the improved heuristic information function obtained from the pheromone distribution at each path point and the synthetic potential field force, the transition probability of an ant moving to another node is calculated. The next node is then determined based on the transition probability. Finally, it is determined whether the ant has reached the destination, and the ant count is updated accordingly. ,judge Is it equal to If the total number is not reached, return to calculate the pheromone distribution of each path point; if the total number is reached, perform a global pheromone update and complete the current iteration cycle.

[0154] like Figure 3 As shown, this application provides a ship path planning device for nearshore environments, comprising:

[0155] Image raster module 301 is used to rasterize nearshore environmental images to obtain a navigation space model; the navigation space model includes starting point, target point and obstacle information.

[0156] The parameter setting module 302 is used to set the initial parameters of the improved potential field-ant colony algorithm and initialize the path taboo table;

[0157] The first determining module 303 is used to determine the pheromone distribution and the combined potential force of each path point based on the initial parameters.

[0158] The node calculation module 304 is used to initiate the path traversal of multiple ants and calculate the transfer probability of an ant moving to other nodes based on the heuristic information function obtained from the pheromone distribution and the combined potential field force of each path point.

[0159] The second determining module 305 is used to determine the next node based on the transition probability and update the tabu table; the next node is the node with the highest transition probability;

[0160] The first update module 306 is used to determine that after an ant has traversed all the nodes and reached the target point, it updates the pheromone distribution and path taboo table and records the traversal path.

[0161] The second update module 307 is used to update the number of ants. After all ants have traversed all nodes, the global pheromone distribution is updated to obtain the traversal path of all ants.

[0162] The determination module 308 is used to determine the optimal path based on the traversal paths of all ants.

[0163] This application designs obstacle environments ranging from simple to complex by randomly setting a certain number of obstacle points in 20×20 and 40×40 grid environments. Simulation experiments are conducted to test path planning against high-density, complex obstacles in environments such as islands, reefs, and ports.

[0164] In a simple environment, namely a 20×20 grid environment, 50 (small number), 75 (medium number), and 100 (large number) obstacle points were randomly generated, respectively. Global simulation experiments were conducted using the basic ant colony algorithm and the improved potential field-ant colony algorithm. The initial parameter settings are shown in Table 1.

[0165] Table 1 Simulation test parameter settings under simple environment

[0166]

[0167] Simulation Experiment 1: A 20×20 grid environment was set up, with 50 obstacle points randomly generated on the map. The starting point was (0,0), and the target point was (19,19). The simulation results of the basic ant colony algorithm and the improved potential field-ant colony algorithm are compared as follows. Figure 4 As shown in the figure. A comparison of iterative convergence of algorithms for environments with a smaller number of obstacles is shown in the figure. Figure 5 As shown.

[0168] Simulation Experiment 2: A 20×20 grid environment was set up, with 75 obstacle points randomly generated on the map. The starting point was (0,0), and the target point was (19,19). The simulation results of the basic ant colony algorithm and the improved potential field-ant colony algorithm are compared as follows. Figure 6 As shown in the figure. The iterative convergence comparison diagram for algorithms with a moderate number of obstacles is as follows. Figure 7 As shown.

[0169] Simulation Experiment 3: A 20×20 grid environment was set up, and 100 obstacle points were randomly generated on the map. The starting point was (0,0), and the target point was (19,19). The simulation results of the basic ant colony algorithm and the improved potential field-ant colony algorithm are compared as follows. Figure 8 As shown in the figure. A comparison of iterative convergence of algorithms for environments with a large number of obstacles is shown in the figure. Figure 9 As shown.

[0170] Based on the above simulation experiments, the specific performance evaluation index values ​​of the simulation experiments are shown in Table 2.

[0171] Table 2. Specific performance evaluation index values ​​for simulation experiments

[0172]

[0173] As shown in Table 2, the improved potential field-ant colony algorithm in this application shortens the optimal path length by 62.9%, 50.0%, and 32.4% in simulation experiments 1, 2, and 3, respectively. The improved algorithm converges extremely quickly. As shown in the iteration convergence comparison graph, the improved algorithm converges at iterations of 7, 6, and 3 in simulation experiments 1, 2, and 3, respectively, while the basic ant colony algorithm fails to converge even after reaching the maximum number of iterations, resulting in significant dispersion in the curve. The optimal ship path diagram shows that the improved potential field-ant colony algorithm provided in this application significantly improves path smoothness.

[0174] In a complex environment, specifically a 40×40 grid environment, 150, 200, and 250 obstacle points were randomly generated, respectively. Global simulation experiments were conducted using both the basic ant colony algorithm and the improved ant colony algorithm. The initial parameter settings are shown in Table 3.

[0175] Table 3 Simulation test parameter settings under simple environment

[0176]

[0177] Simulation Experiment 4: A 40×40 grid environment was set up, and 150 obstacle points were randomly generated on the map. The starting point was (0,0), and the target point was (39,39). The simulation results of the basic ant colony algorithm and the improved potential field-ant colony algorithm are compared as follows. Figure 10 As shown in the figure. A comparison of iterative convergence of algorithms for environments with a smaller number of obstacles is shown in the figure. Figure 11 As shown.

[0178] Simulation Experiment 5: A 40×40 grid environment is set up, and 200 obstacle points are randomly generated on the map. The starting point is (0,0), and the target point is (39,39). The simulation results of the basic ant colony algorithm and the improved potential field-ant colony algorithm are compared as follows. Figure 12 As shown in the figure. The iterative convergence comparison diagram for algorithms with a moderate number of obstacles is as follows. Figure 13 As shown.

[0179] Simulation Experiment 6: A 40×40 grid environment is set up, with 250 obstacle points randomly generated on the map. The starting point is (0,0), and the target point is (39,39). The simulation results of the basic ant colony algorithm and the improved potential field-ant colony algorithm are compared as follows. Figure 14 As shown in the figure. A comparison of iterative convergence of algorithms for environments with a large number of obstacles is shown in the figure. Figure 15 As shown.

[0180] Based on the above simulation experiments, the specific performance evaluation index values ​​of the simulation experiments are shown in Table 4.

[0181] Table 4. Specific performance evaluation index values ​​for simulation experiments

[0182]

[0183] As shown in Table 4, the improved potential field-ant colony algorithm in this application shortens the optimal path length by 65.7%, 45.4%, and 75.6% in simulation experiments 4, 5, and 6, respectively. The improved algorithm converges extremely quickly. As shown in the iteration convergence comparison graph, the improved algorithm converges at iterations of 30, 82, and 90 in simulation experiments 4, 5, and 6, respectively, while the basic ant colony algorithm fails to converge even after reaching the maximum number of iterations, resulting in significant dispersion in the curves. The optimal ship path diagram shows that the improved potential field-ant colony algorithm provided in this application significantly improves path smoothness.

[0184] This application provides a ship path planning method, device, and electronic equipment for nearshore environments. Combining the advantages of traditional ant colony algorithms and artificial potential field methods, an improved potential field-ant colony algorithm is proposed. First, potential field information is introduced into the heuristic information function of the traditional ant colony algorithm and dynamically adjusted to improve it. Second, the algorithm structure is optimized by adjusting the path selection probability. By considering the ship's own navigation characteristics, path length constraints, safety distance limits, and turning angle limits are introduced to improve the pheromone update rule, and the path is smoothed using Bézier curves. Finally, random obstacle points are set based on a grid method to simulate a complex static nearshore environment, and simulation experiments are conducted to verify the superiority of the improved algorithm. Simulation results show that compared with the traditional ant colony method, this algorithm has a faster convergence speed, shorter path length, and smoother path, verifying its practicality and reliability in the field of ship path planning.

[0185] It should be noted that the nearshore environment ship path planning device of this application embodiment solves the problem in a similar way to the aforementioned nearshore environment ship path planning method. Therefore, the implementation process, implementation principle, and beneficial effects of the nearshore environment ship path planning device can be found in the description of the implementation process, implementation principle, and beneficial effects of the aforementioned method. Repeated descriptions will not be repeated.

[0186] This application provides an electronic device, including:

[0187] At least one processor;

[0188] and a memory communicatively connected to the at least one processor; wherein,

[0189] The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method described in any of the above embodiments.

[0190] This application provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to perform the methods described in any of the above embodiments.

[0191] According to embodiments of this application, this application also provides an electronic device and a readable storage medium.

[0192] Figure 16 A schematic block diagram of an example electronic device 800 that can be used to implement embodiments of this application is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the application described and / or claimed herein.

[0193] like Figure 16As shown, the electronic device 800 includes a computing unit 801, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 into a random access memory (RAM) 803. The RAM 803 may also store various programs and data required for the operation of the device 800. The computing unit 801, ROM 802, and RAM 803 are interconnected via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0194] Multiple components in device 800 are connected to I / O interface 805, including: input unit 806, such as keyboard, mouse, etc.; output unit 807, such as various types of monitors, speakers, etc.; storage unit 808, such as disk, optical disk, etc.; and communication unit 809, such as network card, modem, wireless transceiver, etc. Communication unit 809 allows device 800 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0195] The computing unit 801 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 801 performs the various methods and processes described above, such as a ship path planning method for nearshore environments. For example, in some embodiments, the ship path planning method for nearshore environments can be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 808. In some embodiments, part or all of the computer program can be loaded and / or installed on device 800 via ROM 802 and / or communication unit 809. When the computer program is loaded into RAM 803 and executed by the computing unit 801, one or more steps of the ship path planning method for nearshore environments described above can be performed. Alternatively, in other embodiments, computing unit 801 may be configured by any other suitable means (e.g., by means of firmware) to perform a ship path planning method for nearshore environments.

[0196] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transferring data and instructions to the storage system, the at least one input device, and the at least one output device.

[0197] The program code used to implement the methods of this application may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing device, such that when executed by the processor or controller, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0198] In the context of this application, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0199] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0200] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0201] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0202] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this application can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this application can be achieved, and this is not limited herein.

[0203] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "a plurality of" means two or more, unless otherwise explicitly specified.

[0204] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method of ship path planning in an inshore environment, characterized by, The method comprises the following steps: rasterizing the nearshore environment image to obtain a navigation space model; the navigation space model comprises a starting point, a target point and obstacle information; setting initial parameters of the improved potential field-ant colony algorithm and initializing a path taboo list; determining pheromone distribution of each path point and a synthetic potential field force based on the initial parameters; starting path traversal of multiple ants, and calculating a transition probability of an ant transitioning to another node based on a heuristic information function obtained from the pheromone distribution of each path point and the synthetic potential field force; the heuristic information function is: wherein, is t a constant; , a distance heuristic function; is a constant; is a resultant potential field force; is an angle between the ant path direction and the resultant potential field force direction; is a distance between the current node to the next node ; the transition probability of the ant transitioning to another node is calculated based on the heuristic information function in the following manner, Introducing a random number and a fixed constant ; When the transition probabilities are calculated in the following way: When the transition probabilities are calculated in the following way: wherein, , is a random number; , is a fixed parameter; t is a time; is an information heuristic factor, is an expected value heuristic factor; is a set of nodes that the ant can select at the next time instant; is a node , inter-node pheromone value; is a node , s inter-node pheromone value; is a distance; is a number of adjacent nodes to the current node; is a node , s distance heuristic function; is the pheromone value between the th ant and the node t at time instant , ​ determining a next node according to the transition probability, and updating the taboo list; the next node is the node with the maximum transition probability; after an ant traverses all the nodes to reach the target point, updating the pheromone distribution and the path taboo list, and recording the traversal path; updating the number of ants, and updating the global pheromone distribution after all ants traverse all the nodes, to obtain the traversal paths of all the ants; determining an optimal path according to the traversal paths of all the ants; the initial parameters comprise: the number of ants, a pheromone evaporation coefficient, a pheromone intensity, a gravitational potential field coefficient, a repulsive potential field coefficient and an artificial potential field influence dividing line.

2. The method of claim 1, wherein, The rasterizing the nearshore environment image to obtain a navigation space model comprises: rasterizing the nearshore environment image to obtain a grid map; the grid map comprises a marine area and an obstacle area; determining a ship starting point coordinate, a target point coordinate and an obstacle space distribution feature of the ship in the grid map based on an actual position of the ship, to obtain a navigation space model.

3. The method of claim 1, wherein, The synthetic potential field force is determined in the following manner: the repulsive potential field function is: the artificial potential field influence dividing line is determined by a gravitational potential field function; the gravitational potential field function is: the synthetic potential field is: the synthetic potential field force is: wherein, is a synthetic potential force; is a repulsive potential field function; is a ship position; is an obstacle position; is a repulsive field enhancement factor; is a distance value between the ship and the obstacle; is a repulsive field action range around the obstacle; is an attractive potential field function; is an attractive potential field gain factor; is a goal point position; is a relative distance value of the ship to the goal point; is a synthetic potential field influence demarcation line.

4. The method of claim 1, wherein, the pheromone distribution is updated in the following manner: the pheromone distribution is updated based on a path length, a safety distance and a turning angle limit.

5. The method of claim 4, wherein, The pheromone distribution is updated in the following manner, The pheromone change value is calculated in the following manner: The pheromone distribution is calculated in the following manner: wherein, is the time instant t is the first is the pheromone change value of the ant from node to node ; is the pheromone value of the first ant between time instants t +1 node , ; is the pheromone value of the first ant between time instants t node , ; is the global pheromone evaporation coefficient; wherein, wherein, is the total constraint; C is the pheromone intensity; , , are weight coefficients; is the path length constraint; is the safety distance constraint; is the turning angle constraint; is the total number of nodes on the path; is the distance of the ant visiting the current node to the next node ; is the path safety degree of the current node to the next node ; is the turning angle of the current node to the next node ; is the ship safety meeting distance of the current node to the next node ; is the horizontal coordinate of the ship at the node ; is the horizontal coordinate of the ship at the node ; is the vertical coordinate of the ship at the node ; is the vertical coordinate of the ship at the node .

6. A vessel route planning apparatus for a coastal environment for performing the vessel route planning method for a coastal environment according to any one of claims 1 to 5, characterized in that, The method comprises the following steps: an image rastering module for rasterizing a nearshore environment image to obtain a navigation space model; the navigation space model comprises a starting point, a target point and obstacle information; a parameter setting module for setting initial parameters of the improved potential field-ant colony algorithm and initializing a path taboo list; a first determining module for determining pheromone distribution of each path point and a synthetic potential field force based on the initial parameters; a node calculation module for starting path traversal of multiple ants, and calculating a transition probability of an ant transitioning to another node based on a heuristic information function obtained from the pheromone distribution of each path point and the synthetic potential field force; a second determining module for determining a next node according to the transition probability, and updating the taboo list; the next node is the node with the maximum transition probability; a first updating module for updating the pheromone distribution and the path taboo list after an ant traverses all the nodes to reach the target point, and recording the traversal path; The second updating module is configured to update the number of ants, update the global pheromone distribution after all the ants traverse all the nodes, and obtain the traversal paths of all the ants; The path determining module is configured to determine the optimal path according to the traversal paths of all the ants. The parameter setting module is further configured to set the initial parameters to include the number of ants, the pheromone evaporation coefficient, the pheromone intensity, the gravitational potential field coefficient, the repulsive potential field coefficient, and the artificial potential field influence dividing line.

7. An electronic device, comprising: comprising: at least one processor; and a memory connected with the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method in any one of claims 1-5.

Images