Underwater vehicle path planning method of self-adaptive mechanism
By introducing an adaptive mechanism in UUV path planning, combined with real-time environment perception and dynamic optimization strategies, the problem that traditional methods are difficult to achieve rapid obstacle avoidance and efficient navigation in complex underwater environments is solved, and more efficient and safe path planning is achieved.
Patent Information
- Application Number
- CN202510179587.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-02-14
- Publication Date
- 2025-06-03
AI Technical Summary
Traditional path planning methods are difficult to achieve rapid obstacle avoidance and efficient navigation of UUVs in complex and dynamically changing underwater environments, especially in challenges in current fluctuations, obstacle avoidance, communication delays and motion restrictions.
A method of underwater vehicle path planning with an adaptive mechanism is proposed. Combined with real-time perception of dynamic environmental changes, the inertial weight and learning factors are adjusted adaptively, and the balance of exploration and development is improved and path planning is optimized.
It significantly improves the computing speed of path planning, ensures the safety and efficiency of planned paths, enhances the autonomous navigation and obstacle avoidance capabilities of UUVs, and can perform tasks safely and efficiently in complex environments.
Smart Images
Figure CN120085673A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the field of automation control technology, and relates to the fields of path planning, autonomous navigation, and intelligent control of UUVs. In particular, it relates to a path planning method for underwater vehicles with an adaptive mechanism. Background Art
[0002] The applications of Unmanned Underwater Vehicles (UUVs) in the fields of ocean exploration, environmental monitoring, military reconnaissance, underwater search and rescue, etc. are becoming increasingly widespread. Therefore, the path planning technology of UUVs has become one of the key technologies to ensure the efficient and safe execution of tasks. However, due to the extremely complex and dynamically changing underwater environment, the path planning of UUVs faces many challenges, such as ocean current fluctuations, obstacle avoidance, communication delays, and motion limitations. These problems make it difficult for traditional path planning methods to meet the requirements of UUVs in terms of rapid obstacle avoidance, precise navigation, and efficient task execution.
[0003] In past research, many bio-inspired methods have been applied to the autonomous navigation and obstacle avoidance of UUVs, mainly including the whale optimization algorithm, the dung beetle algorithm, the artificial fish swarm algorithm, etc. Among them, the dung beetle algorithm has been widely used in path planning and optimization problems because it can achieve global optimal search in complex environments, especially in dynamic obstacle avoidance problems. However, the dung beetle algorithm also has some deficiencies, mainly reflected in aspects such as slow convergence speed and sensitivity to local optimal solutions.
[0004] To address these problems, the present invention proposes a path planning method for underwater vehicles with an adaptive mechanism, aiming to improve the adaptability and search strategy of the dung beetle algorithm. This method combines the real-time perception of dynamic environmental changes, enabling the algorithm to more efficiently optimize the path in a three-dimensional underwater environment, thus providing a more stable and reliable solution for the rapid obstacle avoidance and efficient navigation of UUVs in complex environments. Summary of the Invention
[0005] The present invention provides a path planning method for underwater vehicles with an adaptive mechanism to solve the problems existing in the above-mentioned prior art.
[0006] To achieve the above object, the present invention provides the following technical solution: A path planning method for underwater vehicles with an adaptive mechanism, the method comprising the following steps:
[0007] S1. Initialize parameters and the environmental model. In a three-dimensional underwater environment, establish an environmental model containing information such as obstacles, seabed terrain, and dangerous areas, initialize the starting position, target position of the UUV, and relevant parameters in the dung beetle algorithm, such as inertia weight, learning factor, maximum number of iterations, etc., conduct a preliminary analysis of the path planning problem, and determine the constraint conditions, such as the minimum safety distance, path length limit, etc.;
[0008] S2. Define the fitness function. Considering factors such as the distance, feasibility, smoothness, and safety of the path, construct a fitness function, calculate the fitness based on the relative positions of each UUV's position and the target point, and evaluate it;
[0009] S3. Update the position and speed. According to the fitness function, combine the historical speed, local optimal position, and global optimal position to update the speed of the UUV, and update the position of the UUV through the speed to ensure that it moves towards the target point while avoiding obstacles;
[0010] S4. Adjust the adaptive mechanism. As the number of iterations increases, dynamically adjust the inertia weight, and according to the changes in the current environment and the path optimization effect, adjust the learning factor in real time to improve the balance between exploration and exploitation;
[0011] S5. Path optimization and result output. After several iterations, output the curve of the fitness function converging with the number of iterations, and generate a three-dimensional path trajectory map of the UUV.
[0012] Preferably, the specific content of S1 is:
[0013] Initialize the parameters and the environmental model. In a three-dimensional underwater environment, establish an environmental model containing information such as obstacles, seabed topography, and dangerous areas, initialize the starting position, target position of the UUV, and relevant parameters in the dung beetle algorithm, such as inertia weight, learning factor, maximum number of iterations, etc., conduct a preliminary analysis of the path planning problem, and determine the constraint conditions, such as the minimum safety distance, path length limit, etc.
[0014] Preferably, the specific content of S2 is:
[0015] Define the fitness function. Considering factors such as the distance, feasibility, smoothness, and safety of the path, construct a fitness function, calculate the fitness based on the relative positions of each UUV's position and the target point, and evaluate it.
[0016] The fitness function is used to measure the quality of the current position of the UUV, combining the distance to the target point, the feasibility, and smoothness of the path. Let the fitness of the current position be f(x, y, z), then the fitness function can be expressed as:
[0017] f(x, y, z) = ω 1 ·d(x, y, z) + ω 2 ·h(x, y, z) + ω 3 ·s(x, y, z) (1)
[0018] Where: d(x, y, z) is the distance from the current position to the target point, which can be calculated using the Euclidean distance:
[0019]
[0020] h(x, y, z) is the risk function at the current position. If the position is within an obstacle or a dangerous area, it returns a relatively large value; otherwise, it returns a relatively small value.
[0021] s(x, y, z) is the smoothness of the path, which can usually be evaluated by calculating the curvature of the path.
[0022] ω 1 、ω 2 and ω 3 are weighting coefficients used to adjust the importance of each factor in the fitness function.
[0023] Preferably, the specific content of S3 is as follows:
[0024] Position and speed update. According to the fitness function, the speed of the UUV is updated by combining the historical speed, the local optimal position, and the global optimal position. The speed update formula is:
[0025] V i (t + 1) = ω·V i (t) + c 1 ·r 1 ·(X l (t) - X i (t)) + c 2 ·r 2 ·(X g (t) - X i (t)) (3)
[0026] Where: the current speed of the UUV is V i (t), the global optimal position is X g (t), the local optimal position is X l (t), ω is the inertia weight used to control the influence of the historical speed, c 1 and c 2 are learning factors used to control the exploration (local optimal) and exploitation (global optimal) capabilities of the UUV, r 1 and r 2 are random numbers within the interval [0, 1] used to introduce randomness, and V i (t + 1) is the updated speed.
[0027] In each iteration, the current position of the UUV is updated to the weighted sum of the position at the previous moment and the speed. The position update formula is:
[0028] X i (t + 1) = X i (t) + V i(t + 1)(4)
[0029] Where: X i (t) = (x i (t), y i (t), z i (t)) is the current position of the UUV, and V i (t) = (v xi (t), v yi (t), v zi (t)) is the current speed of the UUV, and X i (t + 1) is the updated speed.
[0030] Preferably, the specific content of S4 is as follows:
[0031] Adaptive mechanism adjustment. As the number of iterations increases, the inertia weight is dynamically adjusted. According to the changes in the current environment and the path optimization effect, the learning factor is adjusted in real time to improve the balance between exploration and exploitation.
[0032] Preferably, the specific content of S5 is as follows:
[0033] Path optimization and result output. After several iterations, the curve of the fitness function converging with the number of iterations is output, and a three-dimensional path trajectory map of the UUV is generated.
[0034] Implementing the embodiments of the present invention will have the following beneficial effects:
[0035] A path planning method for an underwater vehicle with an adaptive mechanism proposed by the present invention significantly improves the calculation speed of path planning through an optimization strategy of adaptive adjustment and dynamic optimization. At the same time, by comprehensively considering factors such as the distance, feasibility, smoothness, and safety of the path, the safety and efficiency of the planned path are ensured. This method can effectively cope with the dynamically changing underwater environment, enhance the autonomous navigation and obstacle avoidance capabilities of the UUV, and ensure that the UUV can safely and efficiently perform tasks in a complex environment. This method can adjust the path planning strategy in real time to adapt to environmental changes in a timely manner, thereby improving the overall task execution ability of the UUV. In summary, this path planning method not only improves the navigation accuracy and task execution efficiency of the UUV, but also enhances its autonomy and adaptability, and has broad application prospects and practical value. Description of the Drawings
[0036] To more clearly illustrate the technical solutions of the embodiments of the present invention or the prior art, the following briefly introduces the relevant drawings. The drawings show some embodiments of the present invention, aiming to provide sufficient reference information for technicians so that they can obtain other relevant content therefrom without creative thinking. These drawings intuitively present the structure, components or processes of the present invention, helping to better understand the specific details of the embodiments. Generally speaking, the purpose of the drawings is to help professionals in the technical field understand the implementation manner of the present invention and provide necessary support and reference for them to design and implement similar or equivalent solutions. The specific content is as follows:
[0037] Figure 1 It is a flowchart of a path planning method for an underwater vehicle with an adaptive mechanism;
[0038] Figure 2 It is a convergence curve of the fitness function with the increase of the number of iterations in an embodiment;
[0039] Figure 3 It is the 3D path planning result of the UUV in an embodiment. Specific Embodiments
[0040] Next, the technical solutions will be described in detail and clearly in combination with the drawings in the embodiments of the present invention. It should be particularly noted that the described embodiments are only a part of the present invention and do not represent the only form of all embodiments. Based on the embodiments of the present invention, any other embodiments that can be deduced by those skilled in the art without creative work should be regarded as a part of the protection scope of the present invention. Implementing the embodiments of the present invention will bring the following beneficial effects: To solve the deficiencies in the prior art, this embodiment proposes a path planning method for an underwater vehicle with an adaptive mechanism, as Figures 1 to 3 shown, and the specific method includes:
[0041] S1. Initialization. Set the initial position and target position of the UUV, initialize the gray wolf population, and define the fitness function of the optimization problem; S2. Gray wolf population simulation and position update. Each individual in the wolf pack searches by simulating the hunting behavior of gray wolves (tracking prey and surrounding prey), and gradually updates its own position according to the guidance of the positions of the lead wolf, the second lead wolf, and the third lead wolf. A spherical vector constraint is introduced to ensure that the search of the wolf pack in the underwater environment is carried out within the specified three-dimensional space range (i.e., to avoid out-of-bounds or collisions); S3. Fitness evaluation. After each position update, evaluate the current path through the fitness function. The fitness function performs a weighted sum according to different factors (such as path length, obstacle avoidance, depth limit) to evaluate the quality of the path; S4. Speed and position update. The speed update considers the inertia of the UUV and the influence of the water flow, and adjusts the speed in combination with the guidance of the target path point. The position update is to update the position in an integral manner under the guidance of the speed to ensure that the UUV moves towards the optimal path in the three-dimensional space; S5. Result output. Repeat the position update, fitness evaluation, and speed update until the predetermined maximum number of iterations is reached and then terminate. Finally, output the optimized fitness function curve and the UUV path.
[0042] In some specific embodiments, the specific content of S1 is as follows:
[0043] Initialize parameters and the environmental model. In the three-dimensional underwater environment, establish an environmental model including information such as obstacles, seabed topography, and dangerous areas. Initialize the starting position (0, 0, -80) of the UUV, the target position (100, 100, 0), the maximum number of iterations is 1000 times, determine the constraint conditions, and the minimum safety distance is 10 meters.
[0044] In some specific embodiments, the specific content of S2 is as follows:
[0045] Define the fitness function. Consider factors such as the distance, feasibility, smoothness, and safety of the path comprehensively, construct the fitness function, calculate the fitness according to the relative positions of each UUV's position and the target point, and evaluate it.
[0046] The fitness function is used to measure the quality of the current position of the UUV, combining the distance to the target point, the feasibility, and the smoothness of the path. Let the fitness of the current position be f(x, y, z), then the fitness function can be expressed as:
[0047] f(x, y, z) = ω 1 ·d(x, y, z) + ω 2 ·h(x, y, z) + ω 3 ·s(x, y, z) (5)
[0048] where: d(x, y, z) is the distance from the current position to the target point, which can be calculated using the Euclidean distance:
[0049]
[0050] h(x, y, z) is the risk function of the current position. If the position is within an obstacle or a dangerous area, a relatively large value is returned; otherwise, a relatively small value is returned.
[0051] s(x, y, z) is the smoothness of the path, which can usually be evaluated by calculating the curvature of the path.
[0052] ω 1 、ω 2 and ω 3 are weighting coefficients used to adjust the importance of each factor in the fitness function.
[0053] In some specific embodiments, the specific content of S3 is:
[0054] Position and speed update. According to the fitness function, the speed of the UUV is updated by combining the historical speed, the local optimal position, and the global optimal position. The speed update formula is:
[0055] V i (t + 1) = ω·V i (t) + c 1 ·r 1 ·(X l (t) - X i (t)) + c 2 ·r 2 ·(X g (t) - X i (t)) (7)
[0056] where: the current speed of the UUV is V i (t), the global optimal position is X g (t), the local optimal position is X l (t), ω is the inertial weight used to control the influence of the historical speed, c 1 and c 2 are learning factors used to control the exploration (local optimal) and exploitation (global optimal) capabilities of the UUV, r 1 and r 2 are random numbers within the interval [0, 1] used to introduce randomness, and V i (t + 1) is the updated speed.
[0057] In each iteration, the current position of the UUV is updated to the weighted sum of the position and speed at the previous moment. The position update formula is:
[0058] Xi (t + 1) = X i (t) + V i (t + 1)(8)
[0059] Where: X i (t) = (x i (t), y i (t), z i (t)) is the current position of the UUV, V i (t) = (v xi (t), v yi (t), v zi (t)) is the current speed of the UUV, X i (t + 1) is the updated speed.
[0060] In some specific embodiments, the specific content of S4 is as follows:
[0061] Adaptive mechanism adjustment. As the number of iterations increases, the inertial weight is dynamically adjusted, and according to the changes in the current environment and the path optimization effect, the learning factor is adjusted in real time to improve the balance between exploration and exploitation.
[0062] In some specific embodiments, the specific content of S5 is as follows:
[0063] Path optimization and result output. After several iterations, the curve of the fitness function converging with the number of iterations is output, and a three-dimensional path trajectory map of the UUV is generated. Finally, the optimized fitness function curve is output as Figure 2 shown, and the path of the UUV in the three-dimensional environment, as Figure 3 shown.
[0064] In view of the problems of the existing algorithms in path planning in a three-dimensional underwater environment, the present invention proposes a path planning method for an underwater vehicle with an adaptive mechanism. This method effectively improves the accuracy and adaptability of path planning, enhances the obstacle avoidance ability and path optimization ability, and ensures the safety of the path and high computational performance.
[0065] The above content is only an example of the present invention in the field of UUV path planning and does not limit the application scope of the present invention. The protection scope of the present invention includes more possible implementation manners and technical solutions. The technical solutions mentioned here are only specific implementation manners based on the principle of the present invention and are not the only implementation forms. It should be particularly emphasized that the protection scope of the present invention far exceeds the above specific examples, and any improvement, change, application or other implementation manners based on the basic principle of the present invention are included in the protection scope of the present invention. For those skilled in the art, as long as the core idea of the present invention is not violated, any modification or adjustment should be regarded as within the protection scope. Therefore, the protection scope of the present invention covers various implementation manners and allows technicians to make reasonable adjustments and innovations according to the actual situation without deviating from the basic principle of the present invention.
Claims
1. A method for underwater vehicle path planning with an adaptive mechanism, characterized in that It includes the following steps: S1. Initialize parameters and environment model. In a three-dimensional underwater environment, establish an environment model containing information such as obstacles, seabed terrain, and dangerous areas, initialize the starting position and target position of the UUV, and related parameters in the dung beetle algorithm, such as inertia weight, learning factor, and maximum number of iterations, conduct a preliminary analysis of the path planning problem, and determine the constraints, such as the minimum safe distance and path length limit; S2. Define the fitness function. Consider the distance, feasibility, smoothness and safety of the path, construct the fitness function, calculate the fitness according to the relative position of each UUV and the target point, and evaluate it; S3, position and speed update. According to the fitness function, the speed of the UUV is updated by combining the historical speed, the local optimal position and the global optimal position. The position of the UUV is updated by the speed to ensure that it moves towards the target point while avoiding obstacles. S4, adaptive mechanism adjustment. As the number of iterations increases, the inertia weight is adjusted dynamically, and the learning factor is adjusted in real time according to the changes in the current environment and the path optimization effect to improve the balance between exploration and development; S5. Path optimization and result output. After several iterations, the curve of the fitness function converging with the number of iterations is output to generate a three-dimensional path trajectory diagram of the UUV.
2. The method for underwater vehicle path planning with an adaptive mechanism according to claim 1, characterized in that: The specific content of S1 is: Initialize parameters and environmental models. In a three-dimensional underwater environment, establish an environmental model containing information such as obstacles, seabed terrain, and dangerous areas, initialize the starting position and target position of the UUV, and related parameters in the dung beetle algorithm, such as inertia weight, learning factor, and maximum number of iterations, conduct a preliminary analysis of the path planning problem, and determine constraints such as the minimum safe distance and path length limit.
3. The method for underwater vehicle path planning with an adaptive mechanism according to claim 1, characterized in that: The specific content of S2 is: Define the fitness function. Consider the distance, feasibility, smoothness and safety of the path, construct the fitness function, calculate the fitness based on the relative position of each UUV and the target point, and evaluate it; The fitness function is used to measure the quality of the UUV's current position, combining the distance to the target point, the feasibility and smoothness of the path. If the fitness of the current position is f(x, y, z), the fitness function can be expressed as: f(x,y,z)=ω1·d(x,y,z)+ω2·h(x,y,z)+ω3·s(x,y,z) (1) Where: d(x, y, z) is the distance from the current position to the target point, which can be calculated using the Euclidean distance: h(x, y, z) is the danger function of the current position. If the position is within an obstacle or danger zone, a larger value is returned, otherwise a smaller value; s(x, y, z) is the smoothness of the path, which can usually be evaluated by calculating the curvature of the path; ω1, ω2, and ω3 are weighting coefficients used to adjust the importance of each factor in the fitness function.
4. The method for underwater vehicle path planning with an adaptive mechanism according to claim 1, characterized in that: The specific content of S3 is: Position and speed update. According to the fitness function, the speed of the UUV is updated by combining the historical speed, local optimal position and global optimal position. The speed update formula is: V i (t+1)=ω·V i (t)+c1·r1·(X l (t)-X i (t))+c2·r2·(X g (t)-X i (t)) (3) Where: The current speed of UUV is V i (t), the global optimal position is X g (t), the local optimal position is X l (t), ω is the inertia weight used to control the influence of historical speed, c1 and c2 are learning factors used to control the exploration (local optimum) and exploitation (global optimum) capabilities of the UUV, r1 and r2 are random numbers in the interval [0, 1] used to introduce randomness, V i (t+1) is the updated speed; In each iteration, the current position of the UUV is updated as the weighted sum of the position and velocity at the previous moment. The position update formula is: X i (t+1)=X i (t)+V i (t+1) (4) Where: X i (t) = (x i (t), y i (t), z i (t)) is the current position of the UUV, V i (t)=(v xi (t), v yi (t), v zi (t)) is the current speed of the UUV, X i (t+1) is the updated speed.
5. The method for underwater vehicle path planning with an adaptive mechanism according to claim 1, characterized in that: The specific content of S4 is: Adaptive mechanism adjustment: As the number of iterations increases, the inertia weight is adjusted dynamically, and the learning factor is adjusted in real time according to the changes in the current environment and the effect of path optimization to improve the balance between exploration and development.
6. The method for underwater vehicle path planning with an adaptive mechanism according to claim 1, characterized in that: The specific content of S5 is: Path optimization and result output: After several iterations, the curve of the fitness function convergence with the number of iterations is output to generate the three-dimensional path trajectory diagram of the UUV.