Task allocation method based on plant water absorption thought
By simulating the flow process of plant water molecules in plant tissues and combining the pressure gradient update strategy to adjust the particle positions in the unmanned boat task allocation, the problems of insufficient flexibility and adaptability in traditional methods are solved, and efficient and globally optimized task allocation is achieved.
Patent Information
- Application Number
- CN202510968682.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-07-08
- Publication Date
- 2025-09-16
AI Technical Summary
Traditional task allocation methods lack flexibility and adaptability, are difficult to cope with task adjustments in complex dynamic environments, and lack global optimization.
Based on the idea of plant water absorption, the particle swarm optimization algorithm is used to simulate the flow process of water molecules in plant tissues. The particle positions in task allocation are adjusted through the pressure gradient update strategy to gradually approach the optimal solution.
It improves the flexibility and adaptability of task allocation, can achieve efficient resource allocation and task optimization in complex environments, and overcomes the local optimal problem.
Smart Images
Figure CN120655053A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of artificial intelligence, optimization algorithm and unmanned boat task allocation, relates to an optimization method for task allocation, and particularly relates to a task allocation method based on the idea of plant water absorption. Background Art
[0002] With the advancement of technology, intelligent task allocation has become a critical issue for automated systems such as unmanned aerial vehicles (UAVs). When performing missions, UAVs require precise task allocation based on specific mission requirements to ensure the proper scheduling of resources and efficient task completion. Currently, traditional task allocation methods often rely on preset rules or static algorithms, lacking flexibility and adaptability, making them difficult to adapt to complex and dynamic environments. Furthermore, existing algorithms often fail to consider the inter-task interactions and global optimization issues.
[0003] To overcome these issues, the present invention proposes a task allocation method based on the concept of plant water absorption. This method simulates the flow of water molecules from roots to leaves within a plant, analogizing the movement of water molecules with the task allocation process. Using a pressure gradient update strategy, the method adjusts the positions of particles in the task allocation process, achieving global optimization. Compared to traditional methods, this method significantly improves the flexibility and adaptability of task allocation, enabling dynamic adjustment of task allocation schemes to ensure efficient operation of the unmanned vehicle and optimal resource allocation in diverse mission environments. Summary of the Invention
[0004] In order to solve the above problems in the prior art, the present invention provides a task allocation method based on the idea of plant water absorption.
[0005] To achieve the above object, the present invention provides the following technical solution: a task allocation method based on the idea of plant water absorption, the method comprising the following steps:
[0006] S1. Initialize the population. The initial position of each particle represents the initial plan of the unmanned boat in task allocation, and randomly generate an initial population matrix;
[0007] S2. Initialize the water molecule motion model within the plant membrane. Simulate the flow of water molecules within the plant and determine its initial pressure gradient.
[0008] S3. Update particle positions. Particles adjust their positions in the task allocation space by simulating the flow of water molecules in plants. By using the pressure gradient update strategy, particles gradually approach the optimal solution in the search space.
[0009] S4. After each iteration, the particle adjusts its position in the task allocation according to the updated pressure gradient and gradually approaches the optimal solution. The algorithm stops after reaching the maximum number of iterations and outputs the optimal solution as the optimal task allocation plan for the surface unmanned vehicle.
[0010] Preferably, the specific content of S1 is:
[0011] Initialize the population. The water particles of the initial population are randomly created between the lower limit and the upper limit.
[0012] y i =LB j +rand×(UB j -LB j )
[0013] Among them, LB j and UB j They represent the lower and upper limits of the i-th particle in the j-th dimension, and rand represents a random value uniformly distributed between 0 and 1.
[0014] Preferably, the specific content of S2 is:
[0015] In the m-dimensional problem, the leaf of a plant is a matrix of dimension 1×m, which can be expressed as follows
[0016] Leaves=[l1,l2,...,l i ,...,l m ]
[0017] Where m represents the number of design variables (i.e., the dimension of the problem), l i represents the i-th design variable, l m represents the last design variable. The movement of water molecules in the plant membrane can be represented as an array 1×n, which can be defined as follows
[0018] Particles=[p1, p2,...,p n ]
[0019] Where n is the number of water molecules flowing through the plant membrane. In order for the water molecules to reach the plant leaves, sufficient hydrostatic pressure P is required to enable the water molecules to flow a certain distance x to reach the leaves (i.e., the target). In this case, the water molecules need a pressure gradient To push water molecules to flow a certain distance x to reach the leaves, or in other words, the roots absorb water molecules from the soil and i =0 absorbs water, and then through the pressure difference This pushes these water molecules through the plant tissues, eventually reaching the leaves.
[0020] pressure gradient is the force required to allow plant roots to absorb water molecules and transport them to leaves, Represents the pressure gradient of water molecules
[0021]
[0022] Where m represents the number of variables in the problem, n specifies the number of water molecules, and y i,m represents the position of the i-th particle in the m-th dimension.
[0023] Preferably, the specific content of S3 is:
[0024] Driven by the pressure difference between the xylem vessels and the leaves, water particles rise from the vessels to the leaves. The following formula describes the movement of water from the xylem vessels to the leaves:
[0025]
[0026] in, is the updated hydrostatic pressure gradient obtained under the influence of multiple factors, is the current hydrostatic pressure gradient of the initial particle, is the current water flow rate of the initial particle, g represents the dynamic viscosity coefficient of water, which is 0.0018, a is the radius of the plant conduit, which is approximately 1, and c is a random number generated in the interval (0, 1).
[0027] δ rand =v(LB j -(LB j -UB j )×rand)
[0028] Among them, rand is a random value in the interval [0, 1], and v shows a decreasing fluctuation pattern during the iteration process and gradually decreases with the increase of the number of iterations.
[0029] Preferably, the specific content of S4 is:
[0030] After each iteration, the particles adjust their positions in the task allocation according to the updated pressure gradient and gradually approach the optimal solution. The algorithm stops after reaching the maximum number of iterations and outputs the optimal solution as the optimal task allocation plan for the surface unmanned vehicle.
[0031] The implementation of the present invention will have the following beneficial effects:
[0032] This paper proposes a task allocation method based on the concept of plant water absorption. By combining a particle swarm optimization algorithm with a plant water molecule flow model, it can gradually approach the optimal solution during the task allocation process. This method not only improves the efficiency and accuracy of task allocation, but also has good adaptability and can demonstrate strong optimization capabilities in complex task environments. BRIEF DESCRIPTION OF THE DRAWINGS
[0033] To more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the following briefly describes the relevant drawings. These drawings only illustrate some specific embodiments of the present invention and are intended to provide sufficient information for technicians to extract other relevant content without the need for creative thinking. The drawings intuitively illustrate the structure, components, or workflow of the present invention, which can better illustrate the specific details of the embodiments. The specific content is as follows:
[0034] Figure 1 A flowchart of a task allocation method based on the idea of plant water absorption;
[0035] Figure 2 This is a diagram of the task allocation results described in one embodiment. DETAILED DESCRIPTION
[0036] Next, the technical solution will be described in detail with reference to the accompanying drawings in the embodiments of the present invention. It should be noted that the embodiments are only part of the present invention and do not represent all implementation methods. Any other implementation methods derived from the embodiments of the present invention by any person skilled in the art without creative thinking should be included in the scope of protection of the present invention. This embodiment proposes a task allocation method based on the plant water absorption mechanism, such as Figures 1-2 As shown, the specific methods include:
[0037] S1. Initialize the population. The initial position of each particle represents the initial solution for the UAV in task allocation, and an initial population matrix is randomly generated. S2. Initialize the motion model of water molecules in the plant membrane. Simulate the flow process of water molecules inside the plant and determine its initial pressure gradient. S3. Update the particle position. Particles adjust their positions in the task allocation space by simulating the flow of water molecules in the plant. By using the pressure gradient update strategy, particles gradually approach the optimal solution in the search space. S4. After each iteration, particles adjust their positions in the task allocation according to the updated pressure gradient and gradually approach the optimal solution. The algorithm stops after reaching the maximum number of iterations and outputs the optimal solution as the optimal task allocation solution for the surface UAV.
[0038] In some specific embodiments, the specific content of S1 is:
[0039] Initialize the population. The water particles of the initial population are randomly created between the lower limit and the upper limit.
[0040] y i =LB j +rand×(UB j -LB j )
[0041] Among them, LB j and UB j They represent the lower and upper limits of the i-th particle in the j-th dimension, and rannd represents a random value uniformly distributed between 0 and 1.
[0042] In some specific embodiments, the specific content of S2 is:
[0043] In the m-dimensional problem, the leaf of a plant is a matrix of dimension 1×m, which can be expressed as follows
[0044] Leaves=[l1,l2,...,l i ,...,l m ]
[0045] Where m represents the number of design variables (i.e., the dimension of the problem), l i represents the i-th design variable, l m represents the last design variable. The movement of water molecules in the plant membrane can be represented as an array 1×n, which can be defined as follows
[0046] Particles=[p1, p2,...,p n ]
[0047] Where n is the number of water molecules flowing through the plant membrane. In order for the water molecules to reach the plant leaves, sufficient hydrostatic pressure P is required to enable the water molecules to flow a certain distance x to reach the leaves (i.e., the target). In this case, the water molecules need a pressure gradient To push water molecules to flow a certain distance x to reach the leaves, or in other words, the roots absorb water molecules from the soil and i =0 absorbs water, and then through the pressure difference This pushes these water molecules through the plant tissues, eventually reaching the leaves.
[0048] pressure gradient is the force required to allow plant roots to absorb water molecules and transport them to leaves, Represents the pressure gradient of water molecules
[0049]
[0050] Where m represents the number of variables in the problem, n specifies the number of water molecules, and y i，m represents the position of the i-th particle in the m-th dimension.
[0051] In some specific embodiments, the specific content of S3 is:
[0052] Driven by the pressure difference between the xylem vessels and the leaves, water particles rise from the vessels to the leaves. The following formula describes the movement of water from the xylem vessels to the leaves:
[0053]
[0054] in, is the updated hydrostatic pressure gradient obtained under the influence of multiple factors, is the current hydrostatic pressure gradient of the initial particle, is the current water flow rate of the initial particle, g represents the dynamic viscosity coefficient of water, which is 0.0018, a is the radius of the plant conduit, which is approximately 1, and c is a random number generated in the interval (0, 1).
[0055] δ rand =v(LB j -(LB j -UB j )×rand)
[0056] Among them, rand is a random value in the interval [0, 1], and v shows a decreasing fluctuation pattern during the iteration process and gradually decreases with the increase of the number of iterations.
[0057] In some specific embodiments, the specific content of S4 is:
[0058] After each iteration, the particle adjusts its position in the task allocation according to the updated pressure gradient and gradually approaches the optimal solution. The algorithm stops after reaching the maximum number of iterations, outputs the global optimal solution, and uses the result of the task allocation for the collaborative obstacle removal of the surface unmanned boat. Figure 2 This is a diagram of the task allocation results described in one embodiment.
[0059] This paper addresses the task allocation problem for unmanned surface vehicles (UAVs) by providing a task allocation method based on plant water absorption mechanisms. Existing task allocation algorithms typically rely on traditional optimization methods, which can suffer from high computational complexity and slow convergence. This paper, however, significantly improves task allocation efficiency and solution quality by simulating the flow of water molecules within plant tissues and incorporating a pressure gradient update strategy.
[0060] Compared to traditional algorithms, this method, by simulating the update mechanism of water molecule flow, can quickly approach the optimal solution within the search space, with greater adaptability and higher computational efficiency. Specifically, by incorporating the mechanism of plant water absorption, this method makes the task allocation process for unmanned vehicles more natural and reasonable, while also overcoming the local optimality problem common in traditional optimization methods.
[0061] The above description is only a preferred implementation scheme in the field of unmanned boat task allocation, and does not limit the scope of application of the present invention. In fact, the protection scope of the present invention covers more implementation methods and technical solutions. The technical solution cited is only a specific example based on the principle of the present invention, and is not the only implementation method. It should be noted that within the framework of the basic principles of the present invention, any improvement, change, application or other implementation scheme should be included in the scope of protection. Therefore, all modifications and adjustments that do not deviate from the core idea of the present invention should be regarded as the content protected by the present invention.
Claims
1. A task allocation method based on the idea of plant water absorption, characterized in that It includes the following steps: S1. Initialize the population. The initial position of each particle represents the initial plan of the unmanned boat in task allocation, and randomly generate an initial population matrix; S2. Initialize the water molecule motion model within the plant membrane. Simulate the flow of water molecules within the plant and determine its initial pressure gradient. S3. Update particle positions. Particles adjust their positions in the task allocation space by simulating the flow of water molecules in plants. By using the pressure gradient update strategy, particles gradually approach the optimal solution in the search space. S4. After each iteration, the particle adjusts its position in the task allocation according to the updated pressure gradient and gradually approaches the optimal solution. The algorithm stops after reaching the maximum number of iterations and outputs the optimal solution as the optimal task allocation plan for the surface unmanned vehicle.
2. The task allocation method based on the plant water absorption concept according to claim 1 is characterized by: The specific content of S1 is: Initialize the population. The water particles of the initial population are randomly created between the lower limit and the upper limit. y i =LB j +rand×(UB j -LB j ) Among them, LB j and UB j They represent the lower and upper limits of the i-th particle in the j-th dimension, and rand represents a random value uniformly distributed between 0 and 1.
3. The task allocation method based on the plant water absorption concept according to claim 1 is characterized by: The specific content of S2 is: In the m-dimensional problem, the leaf of a plant is a matrix of dimension 1×m, which can be expressed as follows Leaves=[l1,l2,...,l i ,...,l m ] Where m represents the number of design variables (i.e., the dimension of the problem), l i represents the i-th design variable, l m represents the last design variable. The movement of water molecules in the plant membrane can be represented as an array 1×n, which can be defined as follows Particles=[p1,p2,...,p n ] Where n is the number of water molecules flowing through the plant membrane. In order for the water molecules to reach the plant leaves, sufficient hydrostatic pressure P is required to enable the water molecules to flow a certain distance x to reach the leaves (i.e., the target). In this case, the water molecules need a pressure gradient To push water molecules to flow a certain distance x to reach the leaves, or in other words, the roots absorb water molecules from the soil and i =0 absorbs water, and then through the pressure difference Propel these water molecules through plant tissues and eventually reach the leaves; pressure gradient is the force required to allow plant roots to absorb water molecules and transport them to leaves, Represents the pressure gradient of water molecules Where m represents the number of variables in the problem, n specifies the number of water molecules, and y i,m represents the position of the i-th particle in the m-th dimension.
4. The task allocation method based on the plant water absorption concept according to claim 1 is characterized by: The specific content of S3 is: Driven by the pressure difference between the xylem vessels and the leaves, water particles rise from the vessels to the leaves. The following formula describes the movement of water from the xylem vessels to the leaves: in, is the updated hydrostatic pressure gradient obtained under the influence of multiple factors, is the current hydrostatic pressure gradient of the initial particle, is the current water flow rate of the initial particle, g represents the dynamic viscosity coefficient of water, which is 0.0018, a is the radius of the plant tube, which is approximately 1, and c is a random number generated in the interval (0, 1); δ rand =v(LB j -(LB j -UB j )×rand) Among them, rand is a random value in the interval [0, 1], and v shows a decreasing fluctuation pattern during the iteration process and gradually decreases with the increase of the number of iterations.
5. The task allocation method based on the plant water absorption concept according to claim 1 is characterized by: The specific content of S4 is: After each iteration, the particles adjust their positions in the task allocation according to the updated pressure gradient and gradually approach the optimal solution. The algorithm stops after reaching the maximum number of iterations and outputs the optimal solution as the optimal task allocation plan for the surface unmanned vehicle.