CN117555341A - Deep sea mining vehicle path planning method and system based on improved ant colony algorithm - Google Patents

Abstract

The invention relates to the field of marine engineering technology, and specifically provides a deep-sea mining vehicle path planning method and system based on an improved ant colony algorithm. The planning method includes: obtaining a three-dimensional environment model of the deep seabed mining area terrain, where the three-dimensional environment model includes multiple three-dimensional terrain coordinates, based on the three-dimensional terrain model, calculating the slope value of each three-dimensional terrain coordinate, based on the slope of each three-dimensional terrain coordinate value, a two-dimensional grid model of the deep-sea mining area was established. Based on the two-dimensional grid model, the corner heuristic function was introduced into the ant colony algorithm to obtain the optimal path of the deep-sea mining vehicle. When the above technical solution is adopted, the deep-sea mining vehicle path planning method based on the improved ant colony algorithm provided by the present invention can avoid a large number of turns, reduce the energy consumption of the mining vehicle, improve the quality of the optimal solution, and then obtain the deep-sea mining vehicle path planning method. The optimal path for the mining vehicle.

Description

Deep sea mining vehicle path planning method and system based on improved ant colony algorithm

Technical field

The invention relates to the field of marine engineering technology, and specifically provides a deep-sea mining vehicle path planning method and system based on an improved ant colony algorithm.

Background technique

The deep sea contains abundant mineral resources such as polymetallic nodules, cobalt-rich crusts, and polymetallic sulfides. Polymetallic nodules are rich in rare precious metal elements such as manganese, copper, cobalt, and nickel, and are of great commercial mining value. Different from cobalt-rich crusts and polymetallic sulfide deposits, deep-sea polymetallic nodules occur on the surface of seafloor sediments with water depths of 4000m-6000m, and are often semi-buried. The surface layer of the mining area is thin and soft sediments, and the overall terrain is relatively flat, with There are small raised obstacles and ravines.

Path planning is an important basic technology to ensure that deep-sea mining vehicles can safely complete mining operations. It is of great practical significance for deep-sea mining vehicles to efficiently complete mining operations, reduce energy consumption and drive safely. A reasonable path planning scheme can ensure that the mining vehicle can drive safely according to the preset path in the established seabed mining area, effectively reducing the distance and time cost of the mining vehicle during the transfer of mining sites, ore transportation, and reducing driving risks.

In the existing technology, the optimal path for deep sea mining is usually found through the ant colony algorithm. The basic idea of the ant colony algorithm is: using the walking path of ants to represent the feasible solution to the problem to be optimized, and all paths of the entire ant colony constitute the problem to be optimized. In the solution space, ants with shorter paths release more pheromones. As time goes by, the accumulated pheromone concentration on the shorter paths gradually increases, and the number of ants choosing this path also increases. Eventually, the entire ants will converge on the best path under the action of positive feedback, which corresponds to the optimal solution to the problem to be optimized. However, in the actual working environment of the mining vehicle, if the optimal path found by the ant colony algorithm has too many turns, it will cause the path trajectory to be uneven, increase the energy consumption during the walking process of the mining vehicle, and reduce the walking efficiency.

Accordingly, this field needs a deep-sea mining vehicle path planning method and system based on an improved ant colony algorithm to solve the above technical problems.

Contents of the invention

The present invention aims to solve the above technical problems, that is, the existing ant colony algorithm has problems such as too many path turns in deep-sea mining path planning, uneven path trajectories, large energy consumption during walking, and low walking efficiency.

The invention provides a deep-sea mining vehicle path planning method based on an improved ant colony algorithm. The path planning method includes:

S1, obtain a three-dimensional environment model of the deep seabed mining area terrain, where the three-dimensional environment model includes multiple three-dimensional terrain coordinates,

S2, based on the three-dimensional terrain model, calculate the slope value of each three-dimensional terrain coordinate,

S3, based on the slope value of each three-dimensional terrain coordinate, establish a two-dimensional grid model of the deep sea mining area,

S4. According to the two-dimensional grid model, introduce the corner heuristic function into the ant colony algorithm to obtain the optimal path of the deep-sea mining vehicle.

In the specific implementation of the above path planning method, the step "according to the two-dimensional grid model, introducing a corner heuristic function in the ant colony algorithm to obtain the optimal path of the deep-sea mining vehicle" further includes:

Obtain the number of ants, and determine the starting point position and target point position of the ants in the two-dimensional grid model,

Based on the ant colony algorithm that introduces the corner heuristic function, the path information of the current ant from the starting point to the target point is obtained.

Based on the number of ants, obtain the path information of all ants from the starting point position to the target point position,

Among the path information of all ants from the starting point position to the target point position, the optimal path information is selected.

In the specific implementation of the above path planning method, the step "based on the ant colony algorithm introducing the corner heuristic function, obtaining the path information of the current ant from the starting point position to the target point position" further includes:

Quoting the pseudo-random proportion rule, during the current ant's journey from the starting point to the target point, calculate the accessibility of the eight nodes around the current node and the transition probability of each accessible node,

Ant k located at node ( i , j ) selects the next accessible point according to the following formula,

,

In the formula, is the pseudo-random proportion rule, k is the number of iterations, m is the ants in the current iteration process,/> is the state transition probability,/> is the pheromone concentration, i and j are the current path nodes of the ant, a is the pheromone importance parameter, b is the heuristic factor importance parameter, γ is the importance parameter characterizing the corner heuristic function, q is the transition probability coefficient, q ₀ is the transition probability coefficient threshold, T ( k ) is the turning angle heuristic function to avoid too many turns;

Among them, the transition probability formula represents the transition probability of ant k choosing the next node after a period of time t ,

,

In the formula, is the node that ant m can choose to go to next, and T is the turn heuristic function to avoid too many turns;

Among them, the calculation formula of the corner heuristic function is:

,

In the formula, θ is the turning angle between three adjacent nodes in the path, and the smaller θ is, the smoother the path is.

,

In the formula, are the spatial coordinates of three adjacent nodes in the path.

In the specific implementation of the above path planning method, the calculation formula of the transition probability coefficient threshold is as follows:

,

In the formula, K is the maximum number of iterations of the algorithm.

In the specific implementation of the above path planning method, the normal distribution function is introduced into the ant colony algorithm to dynamically adjust the heuristic information. The adjusted heuristic information calculation formula is as follows:

,

,

In the formula, c is a constant, d _ij is the distance between two nodes, is the transformed normal distribution function.

In the specific implementation of the above path planning method, the step "selecting the shortest path information among the path information of all ants from the starting point position to the target point position" further includes:

The pheromone volatilization mechanism is introduced to continuously update the pheromone during each iteration. At the same time, the sigmoid function is introduced to improve the pheromone volatilization mechanism to control the changing range and rate of the pheromone volatilization factor during the entire iteration process.

Pheromone renewal strategy formulas include:

,

in the formula is the dynamic pheromone volatilization factor;/> is the pheromone from node i to node j in the k -th iteration; M is the total number of ants;/> is the pheromone increment of the m- th ant from node i to node j in the k -th iteration; Q is the pheromone intensity, and K is the maximum number of iterations of the algorithm.

Among them, the calculation formula of the improved pheromone volatilization factor is:

,

In the formula, A and B are the parameters of the sigmoid function respectively.

In the specific implementation of the above path planning method, the step "selecting the shortest path information among the path information of all ants from the starting point position to the target point position" further includes:

Introduce a reward and punishment mechanism to update the pheromones on the path, that is, take reward measures for the pheromones on the best path and add more pheromones; take punitive measures for the pheromones on the worst path, and appropriately reduce the pheromones on the path. of pheromones, thereby allowing the algorithm to converge quickly,

Pheromone renewal strategy formulas include:

,

In the formula, represents the pheromone increment of the m- th ant from node i to node j in the k -th iteration; L _m represents the total length of the path traveled by the m -th ant in this cycle; L _y and L _c are the current iterations The length of the best path and the worst path in , L _mean is the average path length in the current iteration, μ, /> are the weight coefficients of the best and worst paths respectively.

On the other hand, the present invention also provides a deep-sea mining vehicle path planning system based on an improved ant colony algorithm. The system implements the deep-sea mining vehicle path planning method based on an improved ant colony algorithm as described in the above embodiment. The system includes :

The three-dimensional model acquisition module is configured to obtain a three-dimensional environment model of the deep seabed mining area terrain, wherein the three-dimensional environment model includes a plurality of three-dimensional terrain coordinates,

a slope value calculation module configured to calculate the slope value of each three-dimensional terrain coordinate based on the three-dimensional terrain model,

The two-dimensional model building module is configured to establish a two-dimensional grid model of the deep sea mining area based on the slope value of each three-dimensional terrain coordinate,

The optimal path obtaining module is configured to introduce a corner heuristic function into the ant colony algorithm based on the two-dimensional grid model to obtain the optimal path of the deep-sea mining vehicle.

Combining all the above technical solutions, the deep-sea mining vehicle path planning method based on the improved ant colony algorithm provided by the present invention obtains a three-dimensional environmental model of the deep-sea mining area terrain, calculates the slope value of each three-dimensional terrain coordinate, and establishes a two-dimensional grid of the deep-sea mining area. The lattice model provides data support for the ant colony algorithm, and introduces a corner heuristic function into the ant colony algorithm, which can avoid a large number of turns, reduce the energy consumption of the mining vehicle, and improve the quality of the optimal solution. Therefore, the present invention can obtain deep-sea The optimal path for the mining vehicle.

Description of the drawings

The preferred embodiments of the present invention will be described below in conjunction with the accompanying drawings, in which:

Figure 1 is a flow chart of the first embodiment of the deep-sea mining vehicle path planning method based on the improved ant colony algorithm provided by the present invention;

Figure 2 is a schematic diagram of the three-dimensional environment model provided by the present invention;

Figure 3 is a schematic diagram of the two-dimensional grid model provided by the present invention;

Figure 4 is a flow chart of the second embodiment of the deep-sea mining vehicle path planning method based on the improved ant colony algorithm provided by the present invention;

Figure 5 is a structural block diagram of the deep-sea mining vehicle path planning system based on the improved ant colony algorithm of the present invention;

Figure 6 is a simulation experiment diagram of the deep-sea mining vehicle path planning method based on the improved ant colony algorithm and the traditional ant colony algorithm for path planning provided by the embodiment of the present invention.

Detailed ways

Preferred embodiments of the present invention will be described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the scope of the present invention. Those skilled in the art can make adjustments as needed to adapt to specific application situations. For example, although this specific embodiment is described with reference to the application of the mining vehicle path planning method in the deep sea, it is obvious that the mining vehicle path planning method of the present invention can also be used in other environments. Such changes in application scenarios do not deviate from the basic principles of the present invention and belong to the protection scope of the present invention.

The deep sea contains abundant mineral resources such as polymetallic nodules, cobalt-rich crusts, and polymetallic sulfides. Polymetallic nodules are rich in rare precious metal elements such as manganese, copper, cobalt, and nickel, and are of great commercial mining value. Different from cobalt-rich crusts and polymetallic sulfide deposits, deep-sea polymetallic nodules occur on the surface of seafloor sediments with water depths of 4000m-6000m, and are often semi-buried. The surface layer of the mining area is thin and soft sediments, and the overall terrain is relatively flat, with There are small raised obstacles and ravines.

Path planning is an important basic technology to ensure that deep-sea mining vehicles can safely complete mining operations. It is of great practical significance for deep-sea mining vehicles to efficiently complete mining operations, reduce energy consumption and drive safely. A reasonable path planning scheme can ensure that the mining vehicle can drive safely according to the preset path in the established seabed mining area, effectively reducing the distance and time cost of the mining vehicle during the transfer of mining sites, ore transportation, and reducing driving risks.

In the existing technology, the optimal path for deep-sea mining is usually found through the ant colony algorithm. The basic idea of the ant colony algorithm is: using the walking path of ants to represent the feasible solution to the problem to be optimized, and all paths of the entire ant colony constitute the problem to be optimized. In the solution space, ants with shorter paths release more pheromones. As time goes by, the accumulated pheromone concentration on the shorter path gradually increases, and the number of ants choosing this path also increases. Eventually, the entire ants will converge on the best path under the action of positive feedback, which corresponds to the optimal solution to the problem to be optimized. However, in the actual working environment of the mining vehicle, if the optimal path found by the ant colony algorithm has too many turns, it will cause the path trajectory to be uneven, increase the energy consumption during the walking process of the mining vehicle, and reduce the walking efficiency.

The purpose of this invention is to overcome the problems of excessive number of path turns, uneven path trajectories, large energy consumption during walking, and low walking efficiency in the path planning of deep sea mining caused by the existing ant colony algorithm, and solve the existing problems. Methods Technical Difficulties in Planning Deep Sea Mining Vehicle Paths. Therefore, it can be said that this technical solution overcomes technical biases and provides a more accurate and comprehensive planning method, providing more reliable support for engineering practices in related fields.

Referring to Figure 1 below, the first implementation of the deep sea mining vehicle path planning method based on the improved ant colony algorithm of the present invention is introduced. Among them, Figure 1 is a flow chart of the first embodiment of the deep-sea mining vehicle path planning method based on the improved ant colony algorithm of the present invention. In the first embodiment of the present invention, the deep-sea mining vehicle path planning method based on the improved ant colony algorithm Path planning methods include:

S1, obtain the three-dimensional environment model of the deep seabed mining area terrain, where the three-dimensional environment model includes multiple three-dimensional terrain coordinates,

S2, based on the three-dimensional terrain model, calculate the slope value of each three-dimensional terrain coordinate,

S3, based on the slope value of each three-dimensional terrain coordinate, establish a two-dimensional grid model of the deep sea mining area,

S4. According to the two-dimensional grid model, the corner heuristic function is introduced into the ant colony algorithm to obtain the optimal path of the deep-sea mining vehicle.

In this preferred embodiment, the deep-sea mining vehicle path planning method based on the improved ant colony algorithm provided by the present invention obtains a three-dimensional environmental model of the deep-sea mining area terrain, calculates the slope value of each three-dimensional terrain coordinate, and establishes a two-dimensional deep-sea mining area. The grid model provides data support for the ant colony algorithm, and introduces a corner heuristic function into the ant colony algorithm, which can avoid a large number of turns, reduce the energy consumption of the mining vehicle, and improve the quality of the optimal solution. Therefore, the present invention can obtain Optimal paths for deep sea mining vehicles.

In this embodiment, the above-mentioned step S1 further includes: obtaining multiple seabed environment coordinates and integrating them to form a three-dimensional environment model of the deep seabed mining area terrain; performing interpolation modeling analysis on the three-dimensional environment model; and generating multiple interpolated three-dimensional terrain coordinates. .

In some embodiments, due to the complex topographic environment of the mining area on the deep seabed, it is not only covered with exposed bedrock, but also underwater mud and gravel mixture, the terrain is undulating, and the seafloor is convex or recessed too large, which will make mining difficult. It is difficult for vehicles to pass through. Therefore, establishing a three-dimensional environmental model of the underwater mining area is a prerequisite for mining vehicle path planning.

Specifically, the three-dimensional environmental model of the deep seabed mining area is a process of discretizing real continuous underwater terrain values. However, it is very difficult for deep sea mining vehicles to detect the surrounding environment information online and process the environmental information in real time when performing mining collection work. Therefore, in order to obtain the environmental information of the seabed mining area, workers will generally use unmanned underwater robots to conduct topographic and geological surveys of the target mining area in advance, thereby obtaining the corresponding multiple seabed environment coordinates, and finally based on the multiple seabed environments Coordinates are used to model the environment of the target mining area. Further, the present invention performs data interpolation on the established three-dimensional environment model in three-dimensional space to generate multiple interpolated three-dimensional terrain coordinates ( X , Y , Z ). Optionally, as shown in Figure 2, the mining area range is 20×20 (km). Taking 100 grids in each direction as an example, a three-dimensional terrain model of the deep sea mining area is obtained.

In this implementation, based on the three-dimensional terrain model, the slope value of each three-dimensional terrain coordinate can be further calculated, and based on the slope value of each three-dimensional terrain coordinate, a two-dimensional grid model of the deep sea mining area is established, and finally the two-dimensional grid model is constructed based on the slope. The passable area of the grid model is divided.

Specifically, the calculation formula for the slope value of three-dimensional terrain coordinates is:

,

In the formula: ν is the terrain slope inclination angle; arctan is the arctangent function; is the height difference between adjacent grids;/> is the horizontal distance between adjacent grids.

Optionally, the two-dimensional grid model after dividing the passable area is shown in Figure 3, in which the black grid represents the inaccessible area, the light-colored grid represents the gentle slope area with a slope of 5-10°, and the white grid represents Flat areas with a slope less than 5° will not have any additional impact on the walking of mining vehicles. However, the green grid in the gently sloping area will take longer due to the larger slope. Time can be converted into distance for measurement, that is, the green grid It is equivalent to a white grid with a larger side length. After the conversion is completed, path optimization can be performed. Optionally, as shown in Figure 3, this method can simplify the 100 grids interpolated in each direction into 50 grids when establishing a two-dimensional grid model, which can more accurately reflect the terrain characteristics and improve calculations. efficiency.

Referring now to Figure 4, the second embodiment of the deep-sea mining vehicle path planning method based on the improved ant colony algorithm of the present invention is introduced. Among them, Figure 4 is a flow chart of the second embodiment of the deep-sea mining vehicle path planning method based on the improved ant colony algorithm of the present invention. In the second embodiment of the present invention, the deep-sea mining vehicle path planning method based on the improved ant colony algorithm Path planning methods include:

S201, obtain a three-dimensional environment model of the deep seabed mining area terrain, where the three-dimensional environment model includes multiple three-dimensional terrain coordinates,

S202, based on the three-dimensional terrain model, calculate the slope value of each three-dimensional terrain coordinate,

S203, based on the slope value of each three-dimensional terrain coordinate, establish a two-dimensional grid model of the deep sea mining area,

S204, obtain the number of ants, and determine the starting point position and target point position of the ants in the two-dimensional grid model,

S205, based on the ant colony algorithm introducing the corner heuristic function, obtain the path information of the current ant from the starting point position to the target point position,

S206, based on the number of ants, obtain the path information of all ants from the starting point position to the target point position,

S207: Select the optimal path information from the path information of all ants from the starting point position to the target point position.

In this embodiment, when ants in the basic ant colony algorithm start from the starting point to find a path to the end point, they need to constantly determine the accessibility of the eight nodes around the current node and the transition probability of each accessible node. , find a point as the next point for transfer. The transfer rule adopts the pseudo-random proportion rule. Ant k located at node ( i , j ) selects the next accessible point according to the following formula.

In addition, in the actual working environment of the mining vehicle, if the optimal path found has too many turns, it will cause the path trajectory to be uneven, increase the energy consumption during the walking process of the mining vehicle, and reduce the walking efficiency. Therefore, in order to avoid a large number of turns, reduce the energy consumption of mining vehicles, and improve the quality of the optimal solution, this paper chooses to introduce the corner heuristic function into the state transition probability of the ant colony algorithm to obtain optimal path information.

Therefore, the above-mentioned step S205 further includes: citing the pseudo-random proportion rule, calculating the accessibility of eight nodes around the current node and the transition probability of each accessible node during the current ant's journey from the starting point position to the target point position,

Ant k located at node ( i , j ) selects the next accessible point according to the following formula,

,

In the formula, is the pseudo-random proportion rule, k is the number of iterations, m is the ants in the current iteration process,/> is the state transition probability,/> is the pheromone concentration, i and j are the current path nodes of the ant, a is the pheromone importance parameter, b is the heuristic factor importance parameter, γ is the importance parameter characterizing the corner heuristic function, q is the transition probability coefficient, q ₀ is the transition probability coefficient threshold, T ( k ) is the turning angle heuristic function to avoid too many turns;

Among them, the transition probability formula represents the transition probability of ant k choosing the next node after a period of time t ,

,

In the formula, Ant m can choose the node to go to next;

Among them, the calculation formula of the corner heuristic function is:

,

In the formula, θ is the turning angle between three adjacent nodes in the path, and the smaller θ is, the smoother the path is.

,

In the formula, are the spatial coordinates of three adjacent nodes in the path.

In some embodiments, when ants transfer to the next node, they will select the node with the highest state transition probability with probability q ₀ . At the same time, ants also have a probability of (1 - q ₀ ) to select other nodes. Therefore, The state transfer mechanism allows ants to choose the optimal path with a high probability and at the same time, ants will also explore other paths. To sum up, the value of parameter q ₀ affects the extent to which ants search for paths other than the optimal path. When q ₀ takes a larger value, the ant colony algorithm will tend to search for paths near the current optimal path with the highest transition probability. area.

Therefore, in this preferred embodiment, the deep-sea mining vehicle path planning method based on the improved ant colony algorithm provided by the present invention sets a dynamically changing q ₀ threshold. In the early stage of the algorithm iteration, a larger q ₀ can enable the algorithm to follow the global path. Information can effectively search for the optimal path, improving the convergence speed and stability of the algorithm. As the number of iterations continues to increase, the q ₀ value gradually decreases, improving the algorithm's search ability for other paths and avoiding falling into the local optimal solution. This enables the algorithm to have good global search capabilities.

Therefore, the calculation formula of the transition probability coefficient threshold q ₀ is as follows:

,

In the formula, K is the maximum number of iterations of the algorithm.

In some embodiments, the heuristic information of the ant colony algorithm is calculated by the inverse of the Euclidean distance between two nodes, but this method can easily lead to low convergence efficiency of the ant colony algorithm in the process of searching for the optimal path. . Therefore, the deep-sea mining vehicle path planning method based on the improved ant colony algorithm provided by the present invention changes the distance between two nodes into the square of the distance in the traditional heuristic information calculation formula, so that the ants can determine the node to go next. There is a greater probability of selecting a relatively close grid, thereby improving the efficiency of the ant colony algorithm and shortening the time required for algorithm convergence.

In this preferred embodiment, the normal distribution function is introduced into the ant colony algorithm to dynamically adjust the heuristic information, strengthen the influence of the heuristic information when the number of iterations is small, enhance the algorithm's search ability for the shortest path in the early stage, and improve the algorithm Search efficiency reduces the impact of heuristic information in the later stages of the algorithm, thereby achieving the effect of enhancing global search performance. The adjusted heuristic information calculation formula is as follows:

,

,

In the formula, c is a constant, d _ij is the distance between two nodes, is the transformed normal distribution function.

In some embodiments, the ant colony is guided by pheromones in the process of searching for a path, and the way the pheromone is updated in the path will affect the path selection probability of the ant colony. The fixed pheromone volatilization used by the traditional ant colony algorithm Factors cannot optimize algorithm performance.

Therefore, the above step S207 further includes: introducing a pheromone volatilization mechanism to continuously update the pheromone during each iteration process, and at the same time, introducing a sigmoid function to improve the pheromone volatilization mechanism to control the changing range and rate of the pheromone volatilization factor during the entire iteration process. .

In this preferred embodiment, the deep-sea mining vehicle path planning method based on the improved ant colony algorithm provided by the present invention improves the pheromone volatilization mechanism by introducing a sigmoid function to control the changing range and rate of the pheromone volatilization factor during the entire iteration process. Therefore, In the process of the ant colony algorithm searching for the optimal path, the current iteration number is used to reconstruct the sigmoid function, so that the pheromone evaporates slowly in the early iteration of the algorithm, ensuring that the ant colony algorithm can bias the search for the optimal path in the early stage, so that the ant colony algorithm can bias the search for the optimal path in the early stage. The solution converges stably without being too discrete.

As the number of iterations increases, the pheromone volatilization factor on the path gradually increases, which increases the search space of the algorithm and ensures that the algorithm will not fall into a stagnant state and cause the solution to be too single. Improve the pheromone volatilization mechanism to appropriately adjust and intervene the pheromone volatilization intensity in the early, middle and late stages of the ant colony algorithm to avoid the accumulation of pheromones with the number of iterations and the loss of different path information during the algorithm's search for different walking paths. If the difference in nutrient concentration is too large and it falls into a local optimum, it improves the random search ability and global optimization ability of the algorithm.

Further, the pheromone update strategy formula includes:

,

in the formula is the dynamic pheromone volatilization factor;/> is the pheromone from node i to node j in the k -th iteration; M is the total number of ants;/> is the pheromone increment of the m- th ant from node i to node j in the k -th iteration; Q is the pheromone intensity, and K is the maximum number of iterations of the algorithm.

Among them, the calculation formula of the improved pheromone volatilization factor is:

,

In the formula, A and B are the parameters of the sigmoid function respectively.

In some embodiments, the pheromone update strategy of the traditional ant colony algorithm is to judge the path traveled by each ant after each iteration is completed, find out those ants that successfully reached the destination, and then search for the ants that have successfully reached their destination. Pheromones are added to the path, but the length of the path that some ants take to successfully reach their destination is too long and does not meet the optimization requirements. Such ants are usually called inferior ants. Adding pheromones to the path found by inferior ants will affect the ants' search for the optimal path in subsequent iterations.

Therefore, the above step S207 further includes: introducing a reward and punishment mechanism to update the pheromones on the path.

In this preferred embodiment, the deep-sea mining vehicle path planning method based on the improved ant colony algorithm provided by the present invention uses a reward and punishment mechanism to update the pheromones on the path, that is, taking reward measures for the pheromones on the optimal path. , add more pheromones; take punishment measures for the pheromones on the worst path, and appropriately reduce the pheromones on the path, so that the algorithm can quickly converge.

Further, the pheromone update strategy formula includes:

,

In the formula, represents the pheromone increment of the m- th ant from node i to node j in the k -th iteration; L _m represents the total length of the path traveled by the m -th ant in this cycle; L _y and L _c are the current iterations The length of the best path and the worst path in , L _mean is the average path length in the current iteration, μ, /> are the weight coefficients of the best and worst paths respectively.

It should be noted that the above embodiments are only used to illustrate the principles of the present invention and are not intended to limit the scope of the present invention. Without departing from the principles of the present invention, those skilled in the art can adjust the above structures so as to The present invention can be applied to more specific application scenarios.

Although each step is described in the above-mentioned order in the above embodiment, those skilled in the art can understand that in order to achieve the effects of this embodiment, different steps do not have to be executed in such an order, and they can be performed at the same time ( Parallel) execution or execution in reverse order, these simple changes are within the scope of the present invention.

In summary, the deep-sea mining vehicle path planning method based on the improved ant colony algorithm proposed by the present invention has positive effects such as improving efficiency and convergence speed, enhancing global search capabilities and random search capabilities, accelerating convergence, and optimizing path quality and energy consumption. The field of deep-sea mining vehicle path planning has superiority and feasibility, and provides theoretical and technical support for vehicle path planning in deep-sea mining areas. Its beneficial technical effects specifically include:

(1) Improved the efficiency and convergence speed of the algorithm: By introducing a heuristic information mechanism, the ant colony algorithm sets the path search guidance direction, shortens the time required for algorithm convergence, and enhances the early search capability of the algorithm. At the same time, by introducing the deformed normal distribution function, the impact of heuristic information on the later stage of the algorithm is reduced, thereby enhancing the global search performance.

(2) Improved global search ability and random search ability: by introducing dynamic pheromone volatilization factors, the search behavior of ant colonies is controlled. In the early stage of algorithm iteration, the convergence stability of the algorithm is improved; as the number of iterations increases, the positive feedback effect of pheromone is reduced, preventing the algorithm from stagnating, ensuring the diversity of understanding, and improving the random search capability of the algorithm.

(3) Accelerates the convergence of the algorithm: By introducing a reward and punishment mechanism into the pheromone update strategy of the ant colony algorithm, reward measures are taken for the best path and more pheromones are added; punitive measures are taken for the worst path and the amount of pheromone is appropriately reduced. Pheromones on the path. This can make the algorithm converge quickly and speed up finding the optimal solution.

(4) Optimized path quality and energy consumption: The corner heuristic function is introduced into the state transition probability of the ant colony algorithm to avoid too many turns of the mining vehicle, improve the quality of the optimal solution, make the optimal path smoother, and reduce the mining cost. Energy consumption during vehicle walking. At the same time, parameter adaptive pseudo-random transition rules are introduced to dynamically adjust the transition probability threshold, further improving the search efficiency and global optimization capabilities of the algorithm.

(5) It has superiority and feasibility in the field of deep-sea mining vehicle path planning: By comparing with the traditional ant colony algorithm, it is proved that this invention can not only produce high-quality optimal solutions, but also has significant advantages in terms of convergence speed and number of turns. . Compared with existing methods, the optimal path generated by the present invention is the smoothest and has the fewest turns. In addition, the average path length obtained by the present invention shows good stability.

On the other hand, the present invention also provides a deep-sea mining vehicle path planning system based on an improved ant colony algorithm. As shown in Figure 5, the system implements a deep-sea mining vehicle path based on an improved ant colony algorithm as in the above embodiment. Planning method, the system includes:

The three-dimensional model acquisition module 501 is configured to obtain a three-dimensional environment model of the deep seabed mining area terrain, where the three-dimensional environment model includes multiple three-dimensional terrain coordinates,

The slope value calculation module 502 is configured to calculate the slope value of each three-dimensional terrain coordinate based on the three-dimensional terrain model,

The two-dimensional model building module 503 is configured to establish a two-dimensional grid model of the deep sea mining area based on the slope value of each three-dimensional terrain coordinate,

The optimal path obtaining module 504 is configured to introduce a corner heuristic function into the ant colony algorithm based on the two-dimensional grid model to obtain the optimal path of the deep-sea mining vehicle.

In the above embodiments, each embodiment is described with its own emphasis. For parts that are not detailed or documented in a certain embodiment, please refer to the relevant descriptions of other embodiments.

Since the information interaction, execution process, etc. between the above devices/units are based on the same concept as the method embodiments of the present invention, its specific functions and technical effects can be found in the method embodiments section, and will not be described again here.

Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above functional units and modules is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs. Module completion means dividing the internal structure of the device into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be hardware-based. It can also be implemented in the form of software functional units. In addition, the specific names of each functional unit and module are only for the convenience of distinguishing each other and are not used to limit the scope of the present invention. For the specific working processes of the units and modules in the above system, please refer to the corresponding processes in the foregoing method embodiments.

An embodiment of the present invention also provides a computer device. The computer device includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor. The processor executes The computer program implements the steps in any of the above method embodiments.

Embodiments of the present invention also provide a computer-readable storage medium. The computer-readable storage medium stores a computer program. When the computer program is executed by a processor, the steps in each of the above method embodiments can be implemented.

Embodiments of the present invention also provide an information data processing terminal. The information data processing terminal is used to provide a user input interface to implement the steps in the above method embodiments when executed on an electronic device. The information data processing terminal Processing terminals are not limited to mobile phones, computers, and switches.

An embodiment of the present invention also provides a server, which is configured to provide a user input interface to implement the steps in the above method embodiments when executed on an electronic device.

Embodiments of the present invention provide a computer program product. When the computer program product is run on an electronic device, the steps in each of the above method embodiments can be implemented when the electronic device is executed.

If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it may be stored in a computer-readable storage medium. Based on this understanding, this application can implement all or part of the processes in the methods of the above embodiments by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. The computer program When executed by a processor, the steps of each of the above method embodiments may be implemented. Wherein, the computer program includes computer program code, which may be in the form of source code, object code, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device capable of carrying computer program code to a camera/terminal device, a recording medium, a computer memory, a read-only memory (ROM), or a random access memory. (Random AccessMemory, RAM), electrical carrier signals, telecommunications signals, and software distribution media. For example, U disk, mobile hard disk, magnetic disk or CD, etc.

In order to further illustrate the relevant effects of the embodiments of the present invention, the following experiments were conducted.

The method of the present invention and the traditional ant colony algorithm are used to perform mining vehicle path planning in the two-dimensional grid model of the deep sea mining area in Figure 3. The results are shown in Figure 6. The total length of the path of the method of the present invention is 31.1105 km, and the number of turns is 9 times. , the path length of the traditional ant colony algorithm is 36.7462 km, and the number of turns is 30 times. The simulation experiment results prove that compared with the traditional ant colony algorithm, the optimal path length and the number of turns obtained by the method of the present invention are significantly reduced, and the path length can be shortened. 18.12%, and the number of turns is reduced by 70%. This shows that the method of the present invention has obvious advantages in static path planning of mining vehicles by improving the four mechanisms of heuristic information, volatility factors, pheromone update strategies and state transition probability.

So far, the technical solution of the present invention has been described with reference to the preferred embodiments shown in the drawings. However, those skilled in the art can easily understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to relevant technical features, and technical solutions after these modifications or substitutions will fall within the protection scope of the present invention.

Claims (8)

1. A deep-sea mining vehicle path planning method based on an improved ant colony algorithm, characterized in that the path planning method includes: S1, obtain a three-dimensional environment model of the deep seabed mining area terrain, where the three-dimensional environment model includes multiple three-dimensional terrain coordinates, S2, based on the three-dimensional terrain model, calculate the slope value of each three-dimensional terrain coordinate, S3, based on the slope value of each three-dimensional terrain coordinate, establish a two-dimensional grid model of the deep sea mining area, S4. According to the two-dimensional grid model, introduce the corner heuristic function into the ant colony algorithm to obtain the optimal path of the deep-sea mining vehicle. 2. The deep-sea mining vehicle path planning method based on improved ant colony algorithm according to claim 1, characterized in that step "according to the two-dimensional grid model, introduce a corner heuristic function in the ant colony algorithm to obtain deep-sea mining "The optimal path of the vehicle" further includes: Obtain the number of ants, and determine the starting point position and target point position of the ants in the two-dimensional grid model, Based on the ant colony algorithm that introduces the corner heuristic function, the path information of the current ant from the starting point to the target point is obtained. Based on the number of ants, obtain the path information of all ants from the starting point position to the target point position, Among the path information of all ants from the starting point position to the target point position, the optimal path information is selected. 3. The deep-sea mining vehicle path planning method based on the improved ant colony algorithm according to claim 2, characterized in that the step "based on the ant colony algorithm introducing the corner heuristic function, obtains the current ant from the starting point position to the target point position. Path information" further includes: Quoting the pseudo-random proportion rule, during the current ant's journey from the starting point to the target point, calculate the accessibility of the eight nodes around the current node and the transition probability of each accessible node, Ant k located at node ( i , j ) selects the next accessible point according to the following formula, , In the formula, is the pseudo-random proportion rule, k is the number of iterations, m is the ants in the current iteration process,/> is the state transition probability,/> is the pheromone concentration, i and j are the current path nodes of the ant, a is the pheromone importance parameter, b is the heuristic factor importance parameter, γ is the importance parameter characterizing the corner heuristic function, q is the transition probability coefficient, q ₀ is the transition probability coefficient threshold, T ( k ) is the turning angle heuristic function to avoid too many turns; Among them, the transition probability formula represents the transition probability of ant k choosing the next node after a period of time t , , In the formula, is the node that ant m can choose to go to next, and T is the turn heuristic function to avoid too many turns; Among them, the calculation formula of the corner heuristic function is: , In the formula, θ is the turning angle between three adjacent nodes in the path, and the smaller θ is, the smoother the path is. , In the formula, are the spatial coordinates of three adjacent nodes in the path. 4. The deep-sea mining vehicle path planning method based on the improved ant colony algorithm according to claim 3, characterized in that, The calculation formula of the transition probability coefficient threshold is as follows: , In the formula, K is the maximum number of iterations of the algorithm. 5. The deep-sea mining vehicle path planning method based on the improved ant colony algorithm according to claim 3, characterized in that the normal distribution function is introduced into the ant colony algorithm, the heuristic information is dynamically adjusted, and the adjusted heuristic information is calculated. The formula is as follows: , , In the formula, c is a constant, d _ij is the distance between two nodes, is the transformed normal distribution function. 6. The deep-sea mining vehicle path planning method based on the improved ant colony algorithm according to claim 2, characterized in that step "select the shortest path among the path information of all ants from the starting point position to the target point position. "Information" further includes: The pheromone volatilization mechanism is introduced to continuously update the pheromone during each iteration. At the same time, the sigmoid function is introduced to improve the pheromone volatilization mechanism to control the changing range and rate of the pheromone volatilization factor during the entire iteration process. Pheromone renewal strategy formulas include: , in the formula is the dynamic pheromone volatilization factor;/> is the pheromone from node i to node j in the k -th iteration; M is the total number of ants;/> is the pheromone increment of the m- th ant from node i to node j in the k -th iteration; Q is the pheromone intensity, and K is the maximum number of iterations of the algorithm; Among them, the calculation formula of the improved pheromone volatilization factor is: , In the formula, A and B are the parameters of the sigmoid function respectively. 7. The deep-sea mining vehicle path planning method based on the improved ant colony algorithm according to claim 6, characterized in that step "select the shortest path among the path information of all ants from the starting point position to the target point position. "Information" further includes: Introduce a reward and punishment mechanism to update the pheromones on the path, that is, take reward measures for the pheromones on the best path and add more pheromones; take punitive measures for the pheromones on the worst path, and appropriately reduce the pheromones on the path. of pheromone, thereby making the algorithm converge quickly, Pheromone renewal strategy formulas include: , In the formula, represents the pheromone increment of the m- th ant from node i to node j in the k -th iteration; L _m represents the total length of the path traveled by the m -th ant in this cycle; L _y and L _c are the current iterations The length of the best path and the worst path in , L _mean is the average path length in the current iteration, μ, /> are the weight coefficients of the best and worst paths respectively. 8. A deep-sea mining vehicle path planning system based on an improved ant colony algorithm, characterized in that the system implements a deep-sea mining vehicle path planning method based on an improved ant colony algorithm as described in any one of claims 1 to 7, The system includes: The three-dimensional model acquisition module is configured to obtain a three-dimensional environment model of the deep seabed mining area terrain, wherein the three-dimensional environment model includes a plurality of three-dimensional terrain coordinates, a slope value calculation module configured to calculate the slope value of each three-dimensional terrain coordinate based on the three-dimensional terrain model, The two-dimensional model building module is configured to establish a two-dimensional grid model of the deep sea mining area based on the slope value of each three-dimensional terrain coordinate, The optimal path obtaining module is configured to introduce a corner heuristic function into the ant colony algorithm based on the two-dimensional grid model to obtain the optimal path of the deep-sea mining vehicle.