Underwater three-dimensional route planning method

Abstract

The invention provides an underwater three-dimensional route planning method, which comprises the following steps of: generating a three-dimensional grid in an image interaction interface according to underwater geographic information; and inputting a starting point and an ending point of a route in the image interaction interface, calculating the route by applying a route planning algorithm, and optimizing the route by adopting an improved ant colony algorithm in the route planning algorithm. According to the method, the accurate three-dimensional submarine topography model is established according to the underwater geographic information, detailed environment information can be provided for route planning, meanwhile, the improved ant colony algorithm is integrated into the route planning algorithm, the optimal route is searched by utilizing the optimized search capability of the ant colony algorithm, the calculation search efficiency can be improved, and the route planning efficiency is improved. And the possible route can be evaluated and optimized, the optimal or suboptimal route meeting the constraint condition is found, the precision or ideal degree of the calculated route is improved, and high fusion of the algorithm and the geographical environment is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of underwater autonomous vehicle route planning, and in particular to an underwater three-dimensional route planning method. Background Art

[0002] Underwater three-dimensional route planning is the core part of the underwater autonomous vehicle (AUV) mission planning system. It needs to comprehensively consider factors such as time, fuel consumption, obstacle avoidance, and allowed working area to plan the optimal or most satisfactory navigation trajectory. Existing route planning methods are mainly divided into two categories: global trajectory planning and local trajectory planning. Global planning methods include the steepest descent method, dynamic programming, A* algorithm, etc., while local planning methods mainly include gradient method and artificial potential field method.

[0003] In order to speed up the search process, many algorithms project environmental information into two-dimensional space, which cannot fully include three-dimensional information, resulting in the inability of trajectory planning to comprehensively consider actual terrain conditions and dynamic target conditions. These methods also expose the problem of sacrificing optimization accuracy and efficiency in order to improve feasibility in practical applications. Summary of the invention

[0004] In view of this, the purpose of the present invention is to provide an underwater three-dimensional route planning method to solve the problem that the above-mentioned existing route planning methods project environmental information into two-dimensional space and cannot fully include three-dimensional information, resulting in the inability to comprehensively consider actual terrain conditions and dynamic target conditions in track planning. In practical applications, it also exposes the problem of sacrificing optimization accuracy and efficiency in order to improve feasibility.

[0005] In order to solve the above technical problems, the technical solution used in the present invention is:

[0006] The underwater three-dimensional route planning method of the present invention comprises generating a three-dimensional grid in an image interaction interface according to underwater geographic information;

[0007] The starting point and the end point of the route are input in the image interaction interface, and the route is calculated by applying a route planning algorithm, wherein the route planning algorithm uses an improved ant colony algorithm to optimize the route.

[0008] Preferably, the route planning algorithm comprises the steps of:

[0009] After the initialization settings, the data points are clustered and divided into regions;

[0010] Define key nodes, and generate an initial solution and a random number corresponding to the initial solution by gradually visiting customers in each area, and select the next visiting customer according to a probability rule;

[0011] According to the improved ant colony algorithm, a path is constructed and the best route is determined, and the pheromone concentration between the nodes is updated according to the quality and speed of the ants completing the path;

[0012] Repeat the path construction and the updating of the pheromone concentration, and obtain the step solution, and continuously iterate until the optimal solution can be determined according to the change range of the step solution and the set threshold;

[0013] The optimal solution route is smoothed and then outputted.

[0014] Preferably, various algorithm parameters including the number of ants, pheromone concentration decay rate, heuristic information coefficient, crossover threshold, and iteration threshold are set in the initialization;

[0015] And / or, using an improved K-means algorithm to cluster and divide the data points into regions, wherein the improved K-means algorithm determines a K value according to an objective function of minimizing a sum of squared errors.

[0016] Preferably, navigation constraints are taken into consideration when defining key nodes, and a taboo list is set.

[0017] Preferably, the improved ant colony algorithm includes:

[0018] Determine whether the random number is less than a crossover threshold, if so, perform a crossover operation on each of the initial solutions according to a crossover operation rule; if not, do not perform the crossover operation;

[0019] Each ant starts from the starting point, randomly selects the next node, and calculates the transfer probability to each adjacent node based on the current node, thereby constructing an initial route;

[0020] In the process of constructing the initial route, ants are allowed to perform local search to screen out the best route.

[0021] Further preferably, the crossover operation rule is: according to the characteristics of the genetic algorithm (GA), randomly select customers from the two initial solutions for exchange to generate a secondary solution, and according to the calculation of the crossover threshold and the optimal insertion position, insert the secondary solution into the route, and update the crossover threshold at the same time.

[0022] Further preferably, based on the initial value of the intersection threshold, after the first initial route is constructed, the first initial route is added to the best list;

[0023] The crossing threshold is decreased in sequence according to the number of times the first initial route is found, until the crossing threshold is equal to a preset end value, and then the crossing threshold is reset to an initial value.

[0024] Further preferably, during the continuous iteration process, when the change amplitude of the step solution is less than a preset threshold, the iteration is stopped and the corresponding step solution less than the preset threshold is taken as the optimal solution.

[0025] Preferably, the method further comprises, after generating the three-dimensional grid, performing loop rendering and visual effect enhancement processing on the underwater geographic information.

[0026] Preferably, the method further comprises looping and rendering the calculated route.

[0027] Compared with the prior art, the beneficial effects of the underwater three-dimensional route planning method described in the present invention are mainly reflected in:

[0028] The method of this embodiment establishes an accurate three-dimensional seabed terrain model based on underwater geographic information, which can provide detailed environmental information for route planning. At the same time, the improved ant colony algorithm is integrated into the route planning algorithm, and its optimization search capability is used to find the optimal route, which can improve the calculation search efficiency, and can evaluate and optimize possible routes, find the optimal or suboptimal route that meets the constraints, and improve the accuracy or ideality of the calculated route. It achieves a high degree of integration of the algorithm and the geographic environment, and can solve the problem that the existing route planning method projects environmental information into two-dimensional space and cannot fully include three-dimensional information, resulting in the inability to comprehensively consider the actual terrain conditions and dynamic target conditions in the track planning. In actual applications, it also exposes the problem of sacrificing optimization accuracy and efficiency in order to improve feasibility. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The above and other purposes, features and advantages of the present invention will become more clear by more specific description of the preferred embodiments of the present invention shown in the accompanying drawings. The same reference numerals indicate the same parts in all the accompanying drawings, and the accompanying drawings are not deliberately scaled to the actual size, and the focus is on illustrating the main purpose of the present invention.

[0030] Figure 1 A schematic diagram of a flow chart of a method for underwater three-dimensional route planning provided by an embodiment of the present invention;

[0031] Figure 2 A schematic diagram of the flow chart of the route planning algorithm provided in an embodiment of the present invention;

[0032] Figure 3 A schematic diagram of the process flow of the improved ant colony algorithm provided in an embodiment of the present invention;

[0033] Description of the drawings: None. DETAILED DESCRIPTION

[0034] The technical solution of the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments, so that those skilled in the art can better understand the present invention and implement it. However, the embodiments cited are not intended to limit the present invention. In the present embodiment, it should be understood that the orientations or positional relationships indicated by terms such as "longitudinal", "lateral", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", and "outside" are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation of the present invention.

[0035] It should be noted that when an element is considered to be "connected" to another element, it may be directly connected to the other element and integrated therewith, or there may be an intermediate element at the same time. The terms "installed", "one end", "the other end" and similar expressions used in the present invention are for illustrative purposes only.

[0036] This embodiment provides a method for underwater three-dimensional route planning. Figure 1 As shown, including:

[0037] According to the underwater geographic information, a three-dimensional grid is generated in the image interactive interface, and a user interface such as QT can be used; the underwater geographic information includes underwater terrain data, obstacle shape and distribution information, water flow and other relevant geographic environment information, all of which need to be obtained through precise environmental perception in order to provide accurate data support for route planning calculations;

[0038] The starting point and end point of the route are input in the graphical interactive interface, and the route planning algorithm is applied to calculate the route. The route planning algorithm uses the improved ant colony optimization (ACO) algorithm for route optimization, where ACO is a heuristic search algorithm that simulates the foraging behavior of ants.

[0039] The method of this embodiment establishes an accurate three-dimensional seabed terrain model based on underwater geographic information, which can provide detailed environmental information for route planning. At the same time, the improved ant colony algorithm is integrated into the route planning algorithm, and its optimization search capability is used to find the optimal route, which can improve the calculation search efficiency, and can evaluate and optimize possible routes, find the optimal or suboptimal route that meets the constraints, and improve the accuracy or ideality of the calculated route. It achieves a high degree of integration of the algorithm and the geographic environment, and can solve the problem that the existing route planning method projects environmental information into two-dimensional space and cannot fully include three-dimensional information, resulting in the inability to comprehensively consider the actual terrain conditions and dynamic target conditions in the track planning. In actual applications, it also exposes the problem of sacrificing optimization accuracy and efficiency in order to improve feasibility.

[0040] In a preferred embodiment, the above route planning algorithm is as follows: Figure 2 As shown, the steps include:

[0041] After the initialization settings, the data points are clustered and divided into regions; the initialization settings include various algorithm parameters including the number of ants, pheromone concentration decay rate, heuristic information coefficient, crossover threshold, and iteration threshold.

[0042] Define key nodes, and generate initial solutions and random numbers corresponding to the initial solutions by gradually visiting customers in each area, and select the next visiting customer according to probability rules; when defining key nodes, users can consider navigation constraints and set taboo lists based on route requirements.

[0043] According to the improved ant colony algorithm, paths are constructed and the best route is determined. The pheromone concentration between nodes is updated according to the quality and speed of the ants completing the path. Specifically, the pheromone concentration of routes with excellent performance can be increased to attract other ants. At the same time, the pheromone concentration of all paths is attenuated to avoid premature convergence.

[0044] Repeat the path construction and pheromone concentration update, obtain the step solution, monitor the convergence of the algorithm, and iterate continuously until the optimal solution can be determined according to the change range of the step solution and the set threshold. Specifically, when the change range of the step solution is less than the preset threshold, stop the iteration and take the corresponding step solution less than the preset threshold as the optimal solution;

[0045] The optimal solution route is output after smoothing, and the optimal solution route is the optimal or satisfactory route. The continuity and stability of the route can be optimized through smoothing.

[0046] It should be noted that the above-mentioned path search and calculation process can utilize multi-threaded or distributed computing resources and run multiple groups of ants at the same time to improve the search efficiency. Moreover, all parameters preset during initialization and used in the calculation process can be adjusted, which enables the algorithm to flexibly respond to environmental changes and introduces interactive operation, so that users can directly affect the route planning process through operation, which increases the flexibility and practicality of the system.

[0047] In a preferred embodiment, an improved K-means algorithm is used to cluster and divide the data points into regions, and the problem (such as underwater terrain, obstacle distribution, etc.) is divided into different regions. The improved K-means algorithm determines the K value according to the objective function of minimizing the sum of squared errors. This embodiment reasonably divides the data points into different regions so that the data points in each region have higher similarity, which can narrow the search space, improve the search efficiency of the algorithm, and enable ACO to better search in each clustering region to avoid falling into local optimality.

[0048] like Figure 3 As shown, the improved ant colony algorithm specifically includes:

[0049] Determine whether the random number is less than the crossover threshold. If so, perform a crossover operation on each initial solution according to the crossover operation rule; if not, do not perform a crossover operation. Further, the crossover operation rule is: according to the characteristics of the genetic algorithm (GA), randomly select customers from the two initial solutions for exchange, generate a secondary solution, increase the diversity of the search space, and insert the secondary solution into the route according to the calculation of the crossover threshold and the best insertion position, and update the crossover threshold at the same time to ensure that the algorithm can continuously explore new solution spaces during the search process. Specifically, based on the initial value of the crossover threshold, after the first initial route is constructed, the first initial route is added to the best list; according to the number of times the first initial route is found, the crossover threshold is successively reduced until the crossover threshold is equal to the preset end value, and the crossover threshold is reset to the initial value and the test is continued. Through this dynamic adjustment mechanism, the intensity of the crossover operation can be adaptively adjusted according to the search situation of the algorithm, and the possibility of finding the global optimal solution is increased. As an example, the initial value of the crossover threshold can be set to 1. If a better route is obtained in ten consecutive tests, that is, the first initial route, the first initial route is added to the best list. When the system finds that the path it is looking for is already in the best list, it can lower the cross threshold by 0.1 each time and perform ten consecutive tests again. When the cross threshold is less than 0.1, it resets the cross threshold to 1.0 and continues testing.

[0050] Each ant starts from the starting point, randomly selects the next node, and calculates the transfer probability to each adjacent node based on the current node, thereby constructing the initial route;

[0051] In the process of constructing the initial route, ants are allowed to perform local search to screen out the best route; illustratively, a 2-Opt local search method can be introduced to perform local search, generate new routes by exchanging the positions of adjacent customers, and select a better route that can improve the solution quality, so as to achieve the purpose of optimizing the solution.

[0052] In this embodiment, the ant colony algorithm is improved in view of the particularity of the underwater environment. Multi-scale search is performed through the improved ant colony algorithm to achieve fast search, which significantly improves the search efficiency and accuracy of the ant colony algorithm in three-dimensional space and takes into account the dynamic changes of the underwater environment such as ocean currents, thereby ensuring that the global optimal or highly satisfactory route is found.

[0053] In a preferred embodiment, the underwater three-dimensional route planning method further includes looping and rendering the underwater geographic information and enhancing the visual effects after generating the three-dimensional grid. By constructing an interactive three-dimensional visualization platform, the underwater terrain, obstacles and other environmental factors are rendered and displayed in real time, thereby improving the user's visual experience.

[0054] Taking the graphics pipeline rendering of Open GL as an example, the acquired underwater geographic information data must first be converted into a format compatible with Open GL, such as OBJ, STL or directly using the original vertex data. After generating the three-dimensional mesh, the graphics pipeline of Open GL is used to render the three-dimensional terrain and obstacles and other information, and texture mapping and shader technology are applied to enhance the visual effect. The shader code is compiled and linked into a shader program, and the rendering status and attributes of the terrain mesh and obstacles are set. Finally, the terrain and obstacles are drawn in the rendering loop.

[0055] In another preferred embodiment, the underwater three-dimensional route planning method also includes looping the calculated route, and intuitively presenting the route planning results through high-quality graphics rendering to achieve effective visualization of the route planning results. This requires not only that the rendering process has a high degree of real-time performance to reflect the dynamic changes of route planning in real time, but also that the rendering effect is attractive, and that the user experience is improved by optimizing visual elements such as lighting, texture, and shadow. It is understandable that after calculating and outputting the optimal solution route, the optimal solution route is converted into a format that Open GL can understand, and in the rendering loop, the drawing commands (glLineWidth and glBegin (GL_LINE_STRIP)) are used to render the route. And this embodiment, by combining efficient search algorithms and rendering technologies, can build a route planning system that can both quickly respond to environmental changes and provide a rich visual experience.

[0056] In this specification, unless otherwise clearly specified and limited, a first feature being "above" or "below" a second feature may mean that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. Moreover, a first feature being "above", "above" or "above" a second feature may mean that the first feature is directly above or obliquely above the second feature, or simply means that the first feature is higher in level than the second feature. A first feature being "below", "below" or "below" a second feature may mean that the first feature is directly below or obliquely below the second feature, or simply means that the first feature is lower in level than the second feature.

[0057] In the description of this specification, the description with reference to the terms "preferred embodiment", "further embodiment", "other embodiments" or "specific example" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are contradictory.

[0058] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for underwater three-dimensional route planning, characterized in that: include: Generate a three-dimensional grid in the image interactive interface based on underwater geographic information; The starting point and the end point of the route are input in the image interaction interface, and the route is calculated by applying a route planning algorithm, wherein the route planning algorithm uses an improved ant colony algorithm to optimize the route.

2. The method according to claim 1, characterized in that: The route planning algorithm comprises the steps of: After the initialization settings, the data points are clustered and divided into regions; Define key nodes, and generate an initial solution and a random number corresponding to the initial solution by gradually visiting customers in each area, and select the next visiting customer according to a probability rule; According to the improved ant colony algorithm, a path is constructed and the best route is determined, and the pheromone concentration between the nodes is updated according to the quality and speed of the ants completing the path; Repeat the path construction and the updating of the pheromone concentration, and obtain the step solution, and continuously iterate until the optimal solution can be determined according to the change range of the step solution and the set threshold; The optimal solution route is smoothed and then outputted.

3. The method according to claim 2, characterized in that: In the initialization, various algorithm parameters including the number of ants, pheromone concentration decay rate, heuristic information coefficient, crossover threshold, and iteration threshold are set; And / or, using an improved K-means algorithm to cluster and divide the data points into regions, wherein the improved K-means algorithm determines a K value according to an objective function of minimizing a sum of squared errors.

4. The method according to claim 2, characterized in that: When defining the key nodes, navigation constraints are considered and a taboo list is set.

5. The method according to claim 1 or 2, characterized in that: The improved ant colony algorithm comprises: Determine whether the random number is less than a crossover threshold, if so, perform a crossover operation on each of the initial solutions according to a crossover operation rule; if not, do not perform the crossover operation; Each ant starts from the starting point, randomly selects the next node, and calculates the transfer probability to each adjacent node based on the current node, thereby constructing an initial route; In the process of constructing the initial route, ants are allowed to perform local search to screen out the best route.

6. The method according to claim 5, characterized in that The crossover operation rule is: according to the characteristics of the genetic algorithm (GA), randomly select customers from the two initial solutions for exchange to generate a secondary solution, and according to the calculation of the crossover threshold and the best insertion position, insert the secondary solution into the route, and update the crossover threshold at the same time.

7. The method according to claim 6, characterized in that: Based on the initial value of the intersection threshold, after the first initial route is constructed, the first initial route is added to the best list; The crossing threshold is decreased in sequence according to the number of times the first initial route is found, until the crossing threshold is equal to a preset end value, and then the crossing threshold is reset to an initial value.

8. The method according to claim 2, characterized in that: During the continuous iteration process, when the change amplitude of the step solution is less than a preset threshold, the iteration is stopped and the corresponding step solution less than the preset threshold is used as the optimal solution.

9. The method according to claim 1, characterized in that: The method also includes, after generating the three-dimensional grid, performing loop rendering and visual effect enhancement processing on the underwater geographic information.

10. The method according to claim 1, characterized in that: The method also includes looping and rendering the calculated route.

Images