Action plan computable modeling method and system

Abstract

The invention discloses an action scheme computable modeling method and system, particularly relates to the field of simulated confrontation, is used for solving the problem of multi-platform collaborative path planning in a dynamic environment, takes a multi-constraint hierarchical hypergraph as a core, carries out fusion abstraction on space, time and resources, and compresses a search domain through convex hull relaxation expansion and gradient sampling so as to realize multi-platform collaborative path planning. Meanwhile, a stable factor is dynamically adjusted by means of resource phase mapping and quantum taboo migration, and it is ensured that a global optimal solution is rapidly approached; fine time sequence correction is further achieved through symplectic time window rearrangement and conjugate gradient slippage, the survival potential and coverage confidence coefficient of the path are verified through adversarial prediction simulation, and the reliability and safety of the scheme under the disturbance of a frequently-changing three-dimensional geographic space, a dynamic forbidden area and moving obstacles are enhanced; therefore, strict time sequence and resource requirements of the multi-platform collaborative task are effectively met, and advanced computational modeling support is provided for the multi-platform collaborative task.

Description

Technical Field

[0001] The present invention relates to the field of simulation confrontation, and more specifically, to a computable modeling method and system for action plans. Background Art

[0002] In a multi-role simulation confrontation environment, action entities need to perform collaborative tasks within a frequently changing three-dimensional geographical space. In such a scenario, task execution faces multiple complex challenges: no-go zones are instantaneously adjusted with the scene update, moving obstacles continuously interfere with the trajectories of action entities, and the task rhythm requires multiple platforms to synchronously reach the collaborative positioning points and share limited energy. With the increase in the number of participating platforms and the expansion of the task coverage, cross-coupling occurs among variables such as path nodes, timing windows, and energy margins, resulting in an exponential expansion of the search space with the dimension. Traditional traversal or heuristic path planning methods are prone to falling into local minima due to limited search depth and cannot generate global feasible solutions within the real-time simulation scale, ultimately leading to a deviation in the collaborative rhythm and a reduction in the task completion rate.

[0003] To solve the above problems, a technical solution is provided. Summary of the Invention

[0004] To overcome the above-mentioned defects of the prior art, embodiments of the present invention provide a computable modeling method and system for action plans, with a multi-constraint hierarchical hypergraph as the core, which fuses and abstracts space, time, and resources, and significantly improves the calculation efficiency by convex hull relaxation and outer expansion and gradient sampling compression of the search domain. At the same time, by means of resource phase mapping and quantum taboo walk to dynamically adjust the stability factor, it ensures a rapid approximation to the global optimal solution; symplectic time window rearrangement and conjugate gradient slip further achieve fine timing correction, while adversarial prediction simulation verifies the survival potential and coverage confidence of the path, enhancing the reliability and security of the plan under the frequently changing three-dimensional geographical space, dynamic no-go zones, and moving obstacle perturbations; thus effectively coping with the strict timing and resource requirements of multi-platform collaborative tasks and providing advanced computable modeling support for multi-platform collaborative tasks to solve the problems raised in the above background art.

[0005] To achieve the above object, the present invention provides the following technical solutions: A computable modeling method for action plans, comprising the steps of: S1: Construct a multi-constraint hierarchical hypergraph that integrates spatial region distribution, task timing windows, and platform resource status in a three-dimensional dynamic map, and extract an anchor node set by traversing all constraint intersection regions and establish a cross-layer mapping table; S2: First, perform convex hull relaxation boundary outer expansion calculation based on the anchor node set to generate a hexahedron envelope lattice, and then form a candidate lattice grid by non-uniform lattice point sampling guided by the resource margin gradient; S3: For the candidate lattice grid, first calculate the path phase dispersion and energy dissipation gradient of each candidate path, comprehensively calculate the two to obtain the global stability factor, and dynamically adjust the taboo table weight according to the factor size, and then perform the phase-encoding taboo roaming iteration. During the iteration process, record in real time that the taboo table suppresses loops and converges to the elite path cluster; S4: Input the elite path cluster into the symplectic time window rearrangement operator, and correct the time coordinates of each path node through the conjugate gradient slip strategy, so that the cross-platform cooperation margin converges to the allowable interval and then output the timing path; S5: Inject the timing path into the adversarial prediction simulation unit, perform cyclic calculations in the dynamic obstacle perturbation field and test with the survival probability threshold. When the requirements are met, solidify the timing path as the final command sequence.

[0006] In a preferred embodiment, step S1 includes the following contents: First, divide the spatial range into a set of spatial regions at multiple levels, where the bottom layer is a high-resolution spatial grid representing specific geographical coordinate points, and the top layer is a low-resolution macro region representing a large-scale geographical partition; Discretize the time axis into multiple time segments, and assign a task timing window defined by the start time and end time to each task; Maintain a resource status vector for the platform and divide it into multiple resource levels; Construct a hypergraph, the node set of which consists of sub-regions of the set of spatial regions, time segments, and resource levels, and the hyperedges connect the node sets that are compatible with each other in space, time, and resources; Traverse the hypergraph through breadth-first search to identify the constraint intersection regions that simultaneously meet the spatial, time, and resource constraints, and define the nodes therein as the set of anchor nodes; Establish a cross-layer mapping table to record the hierarchical correspondence of the anchor nodes on the set of spatial regions, time layer, and resource layer.

[0007] In a preferred embodiment, step S2 includes the following contents: First, calculate the minimum convex polyhedron of the set of anchor nodes in three-dimensional space, expand it by a fixed distance along the normal vector direction of the convex hull surface to generate the expanded convex polyhedron, and then approximate the expanded convex polyhedron as an axis-aligned hexahedron envelope lattice; subsequently, define a resource margin function within the hexahedron envelope lattice and calculate the gradient of the resource margin function. Determine the sampling density according to the gradient magnitude, so that the sampling density in the region where the resource changes violently is higher than that in the region where the resource changes gently. Finally, generate a non-uniformly distributed set of lattice points within the hexahedron envelope lattice to form a candidate lattice grid.

[0008] In a preferred embodiment, step S3 includes the following contents: Dynamically adjust the tabu duration of the paths in the tabu list according to the global stability factor, where the global stability factor is generated by comprehensively calculating the path phase dispersion and the energy dissipation gradient. Subsequently, perform phase-encoding tabu roaming iteration. By encoding the paths as phase vectors and randomly walking in the phase space, preferentially select the paths or nodes not recorded in the tabu list, and update the tabu list in real time during the iteration to suppress loops, and finally converge to the elite path cluster where the global stability factor value meets the standard.

[0009] In a preferred embodiment, step S3 includes the following content: For each node on the candidate path, calculate the time difference and space difference between it and the next node; then, calculate the average value of all node pairs' time differences and the average value of all node pairs' space differences; next, for each node pair, calculate the absolute value of the difference between its time difference and the average value of all time differences, and the absolute value of the difference between its space difference and the average value of all space differences, and multiply the absolute values of the two to obtain the product of each node pair; finally, accumulate the products of all node pairs to obtain the path phase dispersion to quantify the fluctuations of the path in time and space.

[0010] In a preferred embodiment, step S3 includes the following content: The calculation process of the energy dissipation gradient is as follows: for each node on the candidate path, determine its resource consumption value; then, for adjacent nodes, calculate the absolute value of the resource consumption difference between the two, and find the maximum absolute value of the resource consumption among all adjacent node pairs; next, multiply the absolute value of the resource consumption difference of each adjacent node pair by the maximum absolute value of the resource consumption of all adjacent node pairs to obtain the product of each adjacent node pair; finally, accumulate the products of all adjacent node pairs to obtain the energy dissipation gradient to quantify the changes in resource utilization of the path.

[0011] In a preferred embodiment, step S4 includes the following content: Through inputting the elite path cluster into the symplectic time window rearrangement operator for timing optimization, adjust the time coordinates of the path nodes to meet the requirements of the task timing window. Subsequently, use the conjugate gradient slip strategy. By calculating the sensitivity of the collaborative margin to the time coordinates and iteratively adjusting the time coordinates along the conjugate direction, gradually reduce the timing deviation between multiple platforms until the collaborative margin converges to the preset timing tolerance threshold, and finally output the timed path containing the corrected time coordinates to ensure that multiple platforms arrive at the collaborative positioning point synchronously.

[0012] In a preferred embodiment, step S4 includes the following content: After each iteration, recalculate the arrival time deviation of multiple platforms at the collaborative positioning point, that is, the collaborative margin. When this deviation is less than or equal to the preset timing tolerance threshold, it is determined that the adjustment of the time coordinates meets the requirements and the iteration is stopped.

[0013] In a preferred embodiment, step S5 includes the following: By inputting the timing path into the adversarial prediction simulation unit, performing multiple simulation calculations in the dynamic obstacle perturbation field, calculating the survival probability, and comparing the survival probability with a preset survival probability threshold, when the survival probability is greater than or equal to the preset survival probability threshold, the timing path is solidified into the final command sequence.

[0014] The action plan computable modeling system includes: a hypergraph modeling module, a grid generation module, a path optimization module, a timing correction module, and a survival verification module; Hypergraph modeling module: Construct a multi-constraint hierarchical hypergraph that integrates spatial region distribution, task timing window, and platform resource status in a three-dimensional dynamic map, and extract the set of anchor nodes by traversing all constraint intersection regions and establish a cross-layer mapping table; Grid generation module: First, perform convex hull relaxation boundary expansion calculation based on the set of anchor nodes to generate a hexahedron envelope grid, and then use the resource margin gradient to guide non-uniform grid point sampling to form a candidate grid point grid; Path optimization module: For the candidate grid point grid, first calculate the path phase dispersion and energy dissipation gradient of each candidate path, comprehensively calculate the global stability factor for the two, dynamically adjust the taboo table weight according to the factor size, and then perform phase-encoded taboo roaming iteration. During the iteration process, record the taboo table suppression loop in real time and converge to the elite path cluster; Timing correction module: Input the elite path cluster into the symplectic time window rearrangement operator, correct the time coordinates of each path node through the conjugate gradient slip strategy, and output the timing path after the cross-platform cooperation margin converges to the allowable interval; Survival verification module: Inject the timing path into the adversarial prediction simulation unit, perform cyclic calculations in the dynamic obstacle perturbation field and test with the survival probability threshold, and solidify the timing path into the final command sequence when the requirements are met.

[0015] The technical effects and advantages of the action plan computable modeling method and system of the present invention: The present invention realizes the ability to efficiently generate reliable action plans in a multi-role simulation and confrontation environment through constructing a multi-constraint hierarchical hypergraph, compressing the search space, optimizing path selection and timing correction, and verifying through adversarial prediction simulation. This solution integrates spatial distribution, timing window, and resource status into a unified abstract model, effectively compresses the search domain by using convex hull relaxation and gradient sampling, quickly approximates the global optimal path through phase mapping and tabu walk, and combines symplectic geometric timing optimization to ensure multi-platform coordination consistency. Finally, it verifies the path survivability in a dynamic obstacle perturbation field and generates a high-quality command sequence. The present invention breaks through the limitation that traditional methods are prone to falling into local minima in complex dynamic scenarios, significantly improves the robustness, efficiency, and portability of path planning, is applicable to frequently changing three-dimensional geographical spaces and resource-constrained confrontation tasks. The overall technical solution demonstrates excellent innovation and practical value in terms of path quality, computational efficiency, and task success rate, providing advanced computational modeling support for multi-platform collaborative tasks. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a schematic flowchart of the computable modeling method for the action plan of the present invention.

[0017] Figure 2 It is a schematic structural diagram of the computable modeling system for the action plan of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0019] Embodiment 1: Figure 1 The computable modeling method for the action plan of the present invention is given, including: S1: Construct a multi-constraint hierarchical hypergraph integrating spatial region distribution, task timing window, and platform resource status in a three-dimensional dynamic map, and extract the set of anchor nodes by traversing all constraint intersection regions and establish a cross-layer mapping table.

[0020] S2: Based on the set of anchor nodes, first perform convex hull relaxation boundary expansion calculation to generate a hexahedron envelope grid, and then use the resource margin gradient to guide non-uniform grid point sampling to form a candidate grid raster.

[0021] S3: For the candidate grid raster, first calculate the path phase dispersion and energy dissipation gradient of each candidate path, obtain the global stability factor through the exponential decay - hyperbolic tangent composite mapping, and execute the phase - encoded taboo search iteration after dynamically adjusting the taboo list weight according to the factor size. During the iteration process, record in real - time that the taboo list suppresses loops and converges to the elite path cluster.

[0022] S4: Input the elite path cluster into the symplectic time - window rearrangement operator, correct the time coordinates of each path node through the conjugate - gradient slip strategy, and output the timed path after the cross - platform coordination margin converges to the allowable interval.

[0023] S5: Inject the timed path into the adversarial prediction simulation unit, perform cyclic calculations in the dynamic obstacle perturbation field and test with a survival probability threshold. When the threshold is met, solidify the timed path as the final command sequence.

[0024] In a multi - role simulation and confrontation environment, action entities need to execute collaborative tasks within a frequently changing three - dimensional geographical space. In such a scenario, task execution faces multiple complex challenges: no - go zones are instantaneously adjusted as the scenario is updated, moving obstacles continuously interfere with the trajectories of action entities, and the task rhythm requires multiple platforms to synchronously reach the collaborative positioning points and share limited energy. With the increase in the number of participating platforms and the expansion of the task coverage, cross - coupling occurs among variables such as path nodes, time windows, and energy margins, resulting in an exponential expansion of the search space with the dimension. Traditional traversal or heuristic path - planning methods are prone to falling into local minima due to limited search depth and cannot generate globally feasible solutions within the real - time simulation scale, ultimately leading to a deviation in the collaborative rhythm and a reduction in the task completion rate. Therefore, a computable modeling method for action plans is needed, which can effectively integrate spatial, temporal, and resource constraints and quickly converge to the global optimal solution to improve the efficiency and robustness of task execution. The present invention constructs a multi - constraint hierarchical hypergraph and extracts the set of anchor nodes, providing a solid foundation for subsequent path planning and resource allocation, and solving the limitations of traditional methods in complex dynamic environments.

[0025] The goal of step S1 is to construct a multi - constraint hierarchical hypergraph that integrates spatial region distribution, task time windows, and platform resource status in a three - dimensional dynamic map, extract the set of anchor nodes by traversing all constraint cross - regions, and establish an inter - layer mapping table. This process transforms complex spatial, temporal, and resource constraints into a unified abstract model, providing a data basis and search framework for subsequent steps.

[0026] Step S1 includes the following: S1 - 1. Construct a multi - constraint hierarchical hypergraph: The process of constructing a multi-constrained hierarchical hypergraph aims to integrate the spatial area distribution, task time window, and platform resource status in a three-dimensional dynamic map into a unified abstract model, forming a multi-dimensional network structure. The specific processing logic is as follows: First, divide the spatial range of the three-dimensional dynamic map into multiple levels of spatial area sets. The bottom layer of the spatial area set consists of high-resolution spatial grids, and each spatial grid represents a specific geographical coordinate point; the top layer of the spatial area set consists of low-resolution macro regions, and each macro region represents a larger geographical partition. Each level of the spatial area set contains several sub-regions, and through this hierarchical method, multi-scale modeling of the geographical space is achieved.

[0027] Second, discretize the time axis into multiple time segments, and each time segment corresponds to a time layer in the hypergraph; assign a task time window to each task, and the task time window is defined by the start time and end time range of the task to ensure that the task is executed within the specified time.

[0028] Then, maintain a resource status vector for each platform, and the resource status vector includes the remaining energy and load status; divide the resource status into multiple resource levels, and each resource level corresponds to a resource layer in the hypergraph. For example, the remaining energy is divided into multiple levels from low to high.

[0029] Finally, the node set of the hypergraph is jointly composed of the sub-regions in the spatial area set, the time segments in the time layer, and the resource levels in the resource layer; the hyper-edges of the hypergraph connect node sets that are compatible in space, time, and resources, and the compatibility is defined as the node combination simultaneously satisfying the spatial location requirements of the task, the task time window constraints, and the platform resource availability requirements.

[0030] The purpose of constructing a multi-constrained hierarchical hypergraph is to integrate complex spatial area distributions, task time windows, and platform resource status constraints into a unified model, facilitating efficient path planning in a multi-dimensional search space. The hierarchical structure of the spatial area set supports problem-solving at different abstraction levels. Macro regions are used for rough planning, and spatial grids are used for fine-tuning, thereby reducing the computational complexity while retaining key details. The introduction of the time layer and resource layer incorporates time and resource constraints into the model, ensuring that path planning comprehensively considers task requirements. The hypergraph naturally represents the relationships between multi-dimensional constraints through hyper-edges, ensuring that the generated paths meet all conditions and improving the accuracy and reliability of the planning.

[0031] S1-2. Extract the set of anchor nodes The process of extracting the set of anchor nodes aims to screen out the key nodes that meet the task constraints from the multi-constrained hierarchical hypergraph, providing a reference for subsequent path planning. The specific processing logic is as follows: First, identify the set of nodes in the multi-constraint hierarchical hypergraph that simultaneously satisfy spatial, temporal, and resource constraints to form a constraint intersection region. Nodes in the constraint intersection region are required to be spatially located in non-prohibited areas and avoid moving obstacles, temporally belong to the task time sequence window, and resource-wise meet the energy margin and payload requirements of the platform.

[0032] Next, starting from the start node of the task, traverse the multi-constraint hierarchical hypergraph using the breadth-first search method, gradually marking all nodes that satisfy the constraints; the breadth-first search method explores the hypergraph according to the principle of shortest path first and records each node in the constraint intersection region.

[0033] Finally, define the set of nodes in the constraint intersection region as the anchor node set, and the anchor node set represents the key positions where tasks can be executed under specific time, location, and resource states.

[0034] The purpose of extracting the anchor node set is to narrow the search space for subsequent path planning and improve computational efficiency by screening out nodes that satisfy all task constraints. The identification of the constraint intersection region ensures the feasibility of the anchor node set in terms of space, time, and resources, avoiding wasting computational resources in invalid regions. The breadth-first search method guarantees exploring the hypergraph with the optimal path first and quickly locating key nodes. The anchor node set, as the benchmark point for path planning, provides a clear direction for generating feasible paths, enhancing the practicality and pertinence of the solution.

[0035] S1-3. Establish a cross-layer mapping table: The process of establishing a cross-layer mapping table aims to record the corresponding relationships between different layers in the multi-constraint hierarchical hypergraph to support subsequent queries and dynamic adjustments. The specific processing logic is as follows: First, establish mapping relationships among the spatial region set, time layer, and resource layer in the multi-constraint hierarchical hypergraph. The mapping relationship of the spatial region set maps the top-level macroscopic region to the bottom-level spatial grid, the mapping relationship of the time layer maps the time segment to the specific time point, and the mapping relationship of the resource layer maps the resource level to the specific energy value and payload state. Then, create a cross-layer mapping table. The cross-layer mapping table is a multi-level index structure that records the hierarchical information of each anchor node on the spatial region set, time layer, and resource layer; the cross-layer mapping table stores the detailed corresponding relationships of all anchor nodes in an indexed manner for easy and quick access to data at different layers.

[0036] The purpose of establishing a cross-layer mapping table is to provide an efficient data structure to support fast navigation and retrieval of data between different layers in the multi-constraint hierarchical hypergraph. The design of the mapping relationships allows the system to flexibly switch between macroscopic regions and spatial grids, time segments and specific time points, and resource levels and specific resource values to adapt to the requirements of different granularities in path planning. The multi-level index structure of the cross-layer mapping table optimizes the query efficiency and ensures the ability to generate feasible paths in real time in complex adversarial environments.

[0037] In a multi-role simulated confrontation environment, the acting entity needs to cope with the dynamically changing geospatial space, strict task timing requirements, and limited platform resource supply. Step S1 constructs a multi-constraint hierarchical hypergraph to transform the spatial region distribution, task timing window, and platform resource status into a structured network model, extracts the set of anchor nodes, and establishes a cross-layer mapping table, laying the foundation for subsequent path planning and resource allocation. After step S1 is completed, the multi-constraint hierarchical hypergraph integrates multi-dimensional constraints in the three-dimensional dynamic map, the set of anchor nodes provides key reference points, and the cross-layer mapping table supports efficient data access, thus ensuring the applicability and efficiency of the computable modeling of the action plan in complex environments.

[0038] Step S1 provides structured basic data support for the planning of the action plan by constructing a multi-constraint hierarchical hypergraph and extracting the set of anchor nodes. However, relying solely on the set of anchor nodes cannot effectively cope with the exponential expansion of the search space and the demand for solving the global optimal solution, especially in dynamic scenarios with limited resources and high task complexity. Therefore, step S2 aims to further compress the search domain and generate an efficient set of candidate points based on the set of anchor nodes, laying the foundation for subsequent path planning.

[0039] Step S2 includes the following: S2-1. Implement the convex hull relaxation boundary outward expansion calculation to generate a hexahedron envelope lattice: The process of implementing the convex hull relaxation boundary outward expansion calculation to generate a hexahedron envelope lattice aims to construct an extended and regular search area for the set of anchor nodes to cope with the uncertainties in the dynamic environment. The specific processing logic is as follows: First, based on the set of anchor nodes extracted in step S1, calculate its minimum convex polyhedron in three-dimensional space. The minimum convex polyhedron is the smallest geometric boundary that contains all the anchor nodes, ensuring that the search area covers all key positions.

[0040] Next, to adapt to the changes in dynamic obstacles and no-go areas, perform a relaxation boundary outward expansion on the minimum convex polyhedron. The outward expansion method is: translate a certain distance outward along the normal vector direction of each convex hull face to generate an outward-expanded convex polyhedron. The translation distance is determined according to the dynamics of the scenario, specifically the product of the average speed of the moving obstacle and the time step. This operation ensures that the search area has a certain buffer space in the face of dynamic perturbations.

[0041] Finally, approximate the outward-expanded convex polyhedron as an axis-aligned hexahedron envelope lattice. The specific method is: calculate the projection ranges of the outward-expanded convex polyhedron on the x, y, and z axes in space, and determine the minimum and maximum values on each axis respectively, so as to construct a regular hexahedron envelope lattice. This hexahedron envelope lattice covers the set of anchor nodes and its relaxation boundary, providing a standardized search area for subsequent lattice point sampling.

[0042] The purpose of implementing the convex hull relaxation boundary expansion calculation to generate a hexahedral envelope lattice is to provide a search area that not only contains key nodes but also has a buffer margin for path planning in a dynamic environment. The calculation of the minimum convex polyhedron ensures that the search area is compact and contains all the anchor nodes, and the expansion operation reserves space for the movement of dynamic obstacles, enhancing the robustness of path planning. Approximating to a hexahedral envelope lattice simplifies the spatial representation, facilitating efficient lattice point sampling and calculation on a regular grid structure and reducing the complexity of subsequent processing.

[0043] S2-2. Use the resource margin gradient to guide non-uniform lattice point sampling to form a candidate lattice grid: The process of using the resource margin gradient to guide non-uniform lattice point sampling to form a candidate lattice grid aims to generate a resource-sensitive candidate point set within the hexahedral envelope lattice to optimize the resource utilization efficiency of path planning. The specific processing logic is as follows: First, define a resource margin function within the hexahedral envelope lattice, representing the estimated resource margin at each spatial point. The resource margin comprehensively considers factors such as energy margin and load status.

[0044] Next, calculate the gradient of the resource margin function in space. The gradient direction points to the direction of increasing resource margin, and the magnitude of the gradient represents the severity of resource change. The gradient is obtained by calculating the partial derivative of the resource margin function in the direction: .

[0045] Then, based on the resource margin gradient, perform non-uniform lattice point sampling within the hexahedral envelope lattice. The sampling density is proportional to the magnitude of the gradient. Specifically: the sampling density is higher in areas where the resource changes severely and lower in areas where the resource changes gently. The calculation method of the sampling density is: normalize the magnitude of the gradient between the minimum sampling density and the maximum sampling density to ensure that there are more candidate points in the resource-sensitive areas.

[0046] For example, based on the resource margin gradient , perform non-uniform lattice point sampling within the hexahedral envelope lattice . The sampling density is proportional to the gradient norm , and the calculation formula is: where is the minimum sampling density, is the maximum sampling density, and is the maximum value of the gradient norm within the hexahedral envelope lattice . This formula ensures that the sampling density is higher in areas where the resource changes severely and lower in areas where the resource changes gently.

[0047] Finally, according to the sampling density, a set of non-uniformly distributed lattice points is generated within the hexahedron envelope grid to form a candidate lattice point grid. The lattice points in this candidate lattice point grid serve as candidate nodes for subsequent path planning, especially with higher density in resource-constraint sensitive areas.

[0048] The purpose of using the resource margin gradient to guide non-uniform lattice point sampling to form a candidate lattice point grid is to optimize the distribution of the search space, make the candidate point set denser in resource-constraint sensitive areas, and thus improve the resource adaptability of path planning. The calculation of the resource margin gradient reveals the key areas of resource change, and non-uniform sampling ensures more candidate points in these areas, which helps to generate paths with higher resource utilization efficiency. At the same time, reducing the number of candidate points in areas with stable resources reduces the computational burden and balances the accuracy and efficiency of the planning.

[0049] Step S1 provides structured basic data support for the planning of action plans by constructing a multi-constraint hierarchical hypergraph and extracting the set of anchor nodes. On this basis, step S2 uses the set of anchor nodes to perform convex hull relaxation boundary expansion calculation to generate a hexahedron envelope grid, and forms a candidate lattice point grid through non-uniform lattice point sampling guided by the resource margin gradient. After step S2 is completed, the candidate lattice point grid provides an efficient and resource-sensitive search space for subsequent path planning, ensuring the rapid generation of high-quality path solutions under dynamic environments and resource constraints.

[0050] Step S2 has generated a hexahedron envelope grid and a candidate lattice point grid based on the set of anchor nodes, providing an efficient and resource-sensitive candidate point set for path planning. Based on this, step S3 calculates the path phase dispersion and energy dissipation gradient of each candidate path in the candidate lattice point grid, obtains the global stability factor through composite mapping, and performs phase-encoded tabu search iteration using a dynamically adjusted tabu list weight, and finally converges to an elite path cluster, providing high-quality path candidates for the timing correction in step S4.

[0051] Step S3 includes the following: S3-1. Calculate the path phase dispersion and energy dissipation gradient of each candidate path: The process of calculating the path phase dispersion and energy dissipation gradient of each candidate path aims to quantify the characteristics of candidate paths in terms of time, space, and resource utilization, providing basic data for subsequent path quality assessment. The specific processing logic is as follows: First, generate multiple candidate paths from the candidate lattice grid. Each candidate path consists of a series of lattice points, connecting the starting point and the ending point of the task. Then, calculate the path phase dispersion, which is used to measure the degree of fluctuation of the candidate path in time and space. The calculation method is as follows: for each node on the candidate path, determine the time difference and space difference with the next node; then, calculate the average value of all node pairs' time differences and the average value of all node pairs' space differences; next, for each node pair, calculate the absolute value of the difference between its time difference and the average value of all time differences, and the absolute value of the difference between its space difference and the average value of all space differences, and multiply the absolute values of the two to obtain the product of each node pair; finally, sum up the products of all node pairs to get the path phase dispersion.

[0052] For example, the path phase dispersion of each candidate path can be calculated in the following way: 1). Candidate path generation: In the candidate lattice grid multiple candidate paths are generated by connecting adjacent lattice points, denoted as the path set . Each path consists of a series of lattice points, meeting the connection requirements of the task starting point and ending point. The lattice points are denoted as , where represents the -th node on path .

[0053] 2). Path phase dispersion calculation: The path phase dispersion is used to measure the degree of fluctuation of the path in time and space, reflecting the smoothness and continuity of the path. The calculation process is as follows: For each node on path , calculate its time difference and space difference with the next node . Among them, is the time interval between the two nodes, and is the space distance between the two nodes.

[0054] Define the path phase dispersion as the non - linear cumulative quantity of the time and space differences between nodes, using the following formula: where, is the total number of nodes on path , is the average value of all time differences on path , and is the average value of all space differences on path .

[0055] Parameter Explanation: : Time interval from node to .

[0056] Three-dimensional spatial distance from node to .

[0057] and : Represent the reference values of time and space differences respectively, used to measure local fluctuations.

[0058] This formula amplifies the combined fluctuations of time and space in a multiplicative form, avoids the smoothing effect of linear summation, and highlights the local discontinuity of the path.

[0059] Calculate the energy dissipation gradient, which is used to measure the rate of change of resource consumption on the candidate path. The calculation method is as follows: For each node on the candidate path, determine its resource consumption value; then, for adjacent nodes, calculate the absolute value of the difference in resource consumption between the two, and find the maximum absolute value of resource consumption among all adjacent node pairs; next, multiply the absolute value of the difference in resource consumption of each adjacent node pair by the maximum absolute value of resource consumption of all adjacent node pairs to obtain the product of each adjacent node pair; finally, sum up the products of all adjacent node pairs to obtain the energy dissipation gradient.

[0060] For example, the energy dissipation gradient of each candidate path can be calculated in the following way: The energy dissipation gradient is used to measure the rate of change of resource consumption on the path and reflects the efficiency of resource utilization. The calculation process is as follows: For each node on the path , calculate its resource consumption . The resource consumption comprehensively considers factors such as energy and load, and the unit is the standardized resource unit.

[0061] Define the energy dissipation gradient as the non-linear cumulative amount of the difference in resource consumption between adjacent nodes, using the following formula: Parameter Explanation: : Resource consumption value of node , which is comprehensively calculated by factors such as energy and load.

[0062] : Absolute difference in resource consumption between adjacent nodes.

[0063] : The maximum absolute value of the resource consumption of adjacent nodes, which is used to amplify the impact of local changes.

[0064] This formula amplifies the local drastic changes in resource consumption by multiplying by the maximum value, avoids the smoothing of simple differences, and highlights the non-uniformity of the path in resource utilization.

[0065] The purpose of calculating the path phase dispersion and the energy dissipation gradient is to quantify the characteristics of candidate paths through multiple dimensions and provide a comprehensive basis for subsequent evaluation. The path phase dispersion amplifies the local fluctuations of candidate paths through the product of time difference and space difference, highlighting the joint discontinuity of time and space. The energy dissipation gradient amplifies the local drastic changes through the product of the resource consumption difference and the maximum value, highlighting the non-uniformity of candidate paths in resource utilization. This calculation method ensures that the evaluation index can accurately reflect the smoothness and resource efficiency of candidate paths.

[0066] S3-2. Obtain the global stability factor through the exponential decay - hyperbolic tangent composite mapping: The process of obtaining the global stability factor through the exponential decay - hyperbolic tangent composite mapping aims to synthesize the path phase dispersion and the energy dissipation gradient to generate a unified candidate path quality index. The specific processing logic is as follows: Construct a composite mapping function to transform the path phase dispersion and the energy dissipation gradient into the global stability factor. The composite mapping function consists of two parts: the first part is the exponential decay term, which takes the path phase dispersion as the input. When the path phase dispersion increases, the output value decreases rapidly, indicating that a greater penalty is imposed on candidate paths with larger fluctuations; the second part is the hyperbolic tangent term, which takes the energy dissipation gradient as the input. When the energy dissipation gradient increases, the output value increases slowly, indicating the smoothing of the resource consumption change. The global stability factor is the product of the output values of the exponential decay term and the hyperbolic tangent term, and its value range is limited between 0 and 1. The larger the value, the higher the quality of the candidate path.

[0067] For example, the composite mapping function can be constructed in the following way: To comprehensively evaluate the path phase dispersion and the energy dissipation gradient , design the composite mapping function , generate the global stability factor , and the formula is as follows: Parameter explanation: : The adjustment coefficient of the path phase dispersion, , which controls the penalty strength of the dispersion on the stability factor.

[0068] : The adjustment coefficient of the energy dissipation gradient, , which controls the influence degree of the dissipation gradient on the stability factor.

[0069] : The exponential decay term. When is small, it is close to 1, indicating good path smoothness; when is large, it approaches 0, indicating a large penalty.

[0070] : The hyperbolic tangent term. When is small, its value is small, indicating high resource efficiency; when is large, it approaches 1, indicating significant fluctuations in resource consumption.

[0071] The global stability factor ranges from [0, 1), and the larger the value, the higher the path quality.

[0072] The purpose of obtaining the global stability factor through the exponential decay - hyperbolic tangent composite mapping is to fuse multi - dimensional evaluation indicators into a single quality value, facilitating the comparison and screening of candidate paths. The non - linear penalty of the exponential decay term on the path phase discreteness ensures strict requirements for smoothness and highlights the continuity of candidate paths; the gentle treatment of the hyperbolic tangent term on the energy dissipation gradient balances the evaluation of resource efficiency. This composite mapping method takes into account both the smoothness of candidate paths and the stability of resource utilization, enhancing the comprehensiveness and accuracy of the global stability factor in quality evaluation.

[0073] S3 - 3. Perform the phase - encoded tabu search iteration after dynamically adjusting the tabu list weight according to the factor size: The process of performing the phase - encoded tabu search iteration after dynamically adjusting the tabu list weight according to the factor size aims to optimize the search strategy using the global stability factor and improve the efficiency and quality of candidate path screening. The specific processing logic is as follows: First, initialize the tabu list. The tabu list is used to record recently visited candidate paths or nodes to prevent repeated searches. Then, adjust the tabu duration of candidate paths in the tabu list according to the global stability factor: for candidate paths with a larger global stability factor, set a shorter tabu duration to allow more frequent exploration; for candidate paths with a smaller global stability factor, set a longer tabu duration to limit repeated visits. Then, perform the phase - encoded tabu search iteration: encode each candidate path as a phase vector, and the phase vector fuses the time and space information of the candidate path nodes; perform a random walk in the phase space, preferentially selecting candidate paths or nodes not recorded in the tabu list; after each iteration, update the tabu list to record the newly visited candidate paths or nodes, and evaluate the quality of candidate paths according to the global stability factor, retaining high - quality candidate paths.

[0074] The purpose of performing phase - coded tabu search iteration after dynamically adjusting the tabu list weight according to the factor size is to optimize the search process and improve the efficiency of generating high - quality candidate paths. Dynamically adjusting the tabu duration guides the search towards the area of high - quality candidate paths according to the global stability factor, accelerating the convergence speed; phase coding integrates time and space information into the candidate path representation, enhancing the pertinence of the search; tabu search iteration ensures search diversity and globality by restricting repeated visits.

[0075] S3 - 4. During the iteration process, the tabu list is recorded in real - time to suppress loops and converge to the elite path cluster: The process of recording the tabu list in real - time during the iteration process to suppress loops and converge to the elite path cluster aims to form a set of high - quality candidate paths through continuous optimization and recording. The specific processing logic is as follows: In the phase - coded tabu search iteration, the tabu list records the visited candidate paths or nodes in real - time, preventing the search from re - entering the same area repeatedly and maintaining the diversity of the search. As the iteration progresses, the search gradually converges to the set of candidate paths whose global stability factor values meet the criteria, and finally forms an elite path cluster. The elite path cluster, as the output of step S3, provides input for subsequent timing correction.

[0076] The purpose of recording the tabu list in real - time during the iteration process to suppress loops and converge to the elite path cluster is to ensure the output of a set of high - quality candidate paths through continuous optimization. The real - time update of the tabu list effectively suppresses the loop phenomenon in the search and enhances the exploration ability; converging to the elite path cluster filters out the candidate paths with a higher global stability factor, providing high - quality input for subsequent timing correction. This method improves the efficiency and result quality of path planning and meets the requirements of complex dynamic scenarios.

[0077] In a multi - role simulation confrontation environment, step S2 provides an efficient and resource - sensitive search space for step S3 by generating candidate grid rasters. Based on this, step S3 calculates the path phase dispersion and energy dissipation gradient of the candidate paths in sequence to generate the global stability factor; then, it dynamically adjusts the tabu list weight using the global stability factor and performs phase - coded tabu search iteration, finally converging to the elite path cluster. After step S3 is completed, the elite path cluster, as a set of high - quality candidate paths, is directly input into the subsequent timing correction step to ensure the rapid generation of high - quality action plans in complex dynamic scenarios.

[0078] Step S3 has generated an elite path cluster, which provides a high-quality candidate path set for path planning. Each path consists of a sequence of nodes, and each node contains spatial coordinates and initial time coordinates. However, due to the strict timing requirements of multi-platform collaborative tasks, there may be deviations in the time dimension of the paths in the elite path cluster, resulting in the inability to reach the collaborative positioning point synchronously. Based on this, step S4 takes the elite path cluster as the input, and corrects the time coordinates of each path node through the symplectic time window rearrangement operator and the conjugate gradient slip strategy, so that the cross-platform collaborative margin converges to the preset allowable interval, and finally outputs the timed path.

[0079] Step S4 includes the following: S4-1. Input the elite path cluster into the symplectic time window rearrangement operator: The process of inputting the elite path cluster into the symplectic time window rearrangement operator aims to use the timing optimization method of symplectic geometry to adjust the time coordinates of the path nodes to meet the timing window requirements of multi-platform collaborative tasks. The specific processing logic is as follows: The symplectic time window rearrangement operator is an optimization technique based on symplectic geometry, which focuses on optimizing the timing characteristics of the path by adjusting the time coordinates of the nodes while keeping the path space structure unchanged.

[0080] Each path in the elite path cluster consists of a series of nodes, and each node contains spatial coordinates and initial time coordinates. The symplectic time window rearrangement operator receives these paths as inputs and uses the task timing window as a constraint condition. The task timing window defines the time range of each collaborative positioning point and requires all platforms to arrive within this range. The symplectic time window rearrangement operator operates in the phase space. By analyzing the coupling relationship between the time coordinates and the spatial coordinates, it adjusts the time coordinates of each node to make the path coordinated in time and space while keeping the overall structure and characteristics of the path intact.

[0081] The reason for inputting the elite path cluster into the symplectic time window rearrangement operator is that the characteristics of symplectic geometry can maintain the integrity of the path space structure when adjusting the time coordinates, ensuring that the optimization process does not affect the physical feasibility of the path. By optimizing in the phase space, the symplectic time window rearrangement operator can effectively handle the interaction between time and space and improve the timing coordination of the path. This method provides high-quality initial inputs for the subsequent conjugate gradient slip strategy, making the timing correction more efficient and accurate, so as to meet the strict timing requirements of multi-platform collaborative tasks.

[0082] S4-2. Correct the time coordinates of each path node through the conjugate gradient slip strategy: The process of correcting the time coordinates of each path node through the conjugate gradient slip strategy aims to use the iterative optimization method to gradually reduce the timing deviation between multi-platforms until the timing requirements of the collaborative task are met. The specific processing logic is as follows: The conjugate gradient slip strategy is an efficient iterative optimization technique that adjusts the time coordinate along a specific direction by analyzing the sensitivity of the collaborative margin to the time coordinate, so as to rapidly reduce the timing deviation between multiple platforms.

[0083] The collaborative margin is defined as the maximum deviation of the arrival times of multiple platforms at the collaborative positioning point, that is, the maximum value of the difference between the arrival times of all platforms and the preset synchronous arrival time. The optimization goal is to converge this deviation to the preset allowable interval. The correction process includes the following steps: First, starting from the initial time coordinate of the path, calculate the initial collaborative margin; Then, analyze the sensitivity of the collaborative margin to the change in the time coordinate to determine the adjustment direction. The sensitivity reflects the degree of influence of time adjustment on the deviation; Next, combine the current adjustment direction with the direction of the previous iteration to calculate the new search direction. The new search direction is determined by integrating the information of the two directions to improve the search efficiency; Subsequently, update the time coordinate along the new search direction. The adjustment amplitude is determined by gradual trial to maximize the reduction effect of the collaborative margin; Finally, repeat the above steps until the collaborative margin is less than or equal to the preset timing tolerance threshold.

[0084] The reason for correcting the time coordinate through the conjugate gradient slip strategy is that this method utilizes the fast convergence characteristic of iterative optimization and can efficiently handle the timing coordination problem between multiple platforms. Compared with the traditional point-by-point adjustment method, the conjugate gradient slip strategy avoids inefficient repetition in the adjustment process by integrating historical direction information, improving the convergence speed and stability. The collaborative margin, as the optimization goal, directly quantifies the requirements of timing coordination, ensuring that the adjustment process has clear directionality and measurability. This method can quickly optimize the time coordinate in complex dynamic scenarios, providing a reliable timing coordination path for subsequent adversarial prediction simulations.

[0085] S4-3. Output the timing path after converging the cross-platform collaborative margin to the allowable interval: The process of outputting the timing path after converging the cross-platform collaborative margin to the allowable interval aims to ensure the timing coordination of the path through iterative optimization and generate the final timing path. The specific processing logic is as follows: After each iteration, recalculate the arrival time deviation of multiple platforms at the collaborative positioning point, that is, the collaborative margin. When this deviation is less than or equal to the preset timing tolerance threshold, it is determined that the time coordinate adjustment meets the requirements and the iteration stops. At this time, the node time coordinates in the path have been optimized to ensure that multiple platforms arrive at the collaborative positioning point synchronously. Output the adjusted path as the timing path. Each timing path contains the corrected time coordinate and the original spatial coordinate, providing input for subsequent adversarial prediction simulations.

[0086] The reason for outputting the timed path after converging the cross-platform coordination margin to the allowable interval is that by iteratively optimizing until the timing tolerance threshold is met, the timing deviation between multiple platforms can be completely eliminated, ensuring the synchronization of task execution. The generation of the timed path marks the completion of the path planning optimization in the time dimension and provides a high-quality input path for the subsequent steps.

[0087] Step S3 provides a high-quality candidate path set for Step S4 by generating an elite path cluster. Step S4 receives the elite path cluster as input. First, it inputs it into the symplectic time window rearrangement operator for preliminary timing optimization, and then further corrects the time coordinates of each path node through the conjugate gradient slip strategy. Finally, it converges the cross-platform coordination margin to the allowable interval and outputs the timed path. After Step S4 is completed, the timed path ensures that multiple platforms synchronously reach the cooperative positioning point in the frequently changing three-dimensional geographical space, meeting the strict timing requirements of the task. As the output of Step S4, the timed path directly provides a reliable timing coordination path for the adversarial prediction simulation in Step S5, thus ensuring the coherence and efficiency of the entire task planning process.

[0088] In a multi-role simulated adversarial environment, the acting entities need to execute cooperative tasks within a frequently changing three-dimensional geographical space, facing dynamically adjusted no-go zones, disturbances from moving obstacles, and the strict timing and resource requirements of multi-platform cooperative tasks. Steps S1 to S4 have generated a timed path by constructing a multi-constraint hierarchical hypergraph, generating candidate grid rasters, optimizing paths, and performing timing correction. This path meets the task requirements under spatial, temporal, and resource constraints. However, in the actual adversarial environment, there are unpredictable dynamic obstacles and emergencies, and the execution of the timed path may be blocked due to insufficient survivability. To address this challenge, Step S5 introduces an adversarial prediction simulation unit to conduct a survivability test on the timed path to ensure its reliability and task success rate in a dynamic environment.

[0089] Step S5 includes the following: S5-1. Inject the timed path into the adversarial prediction simulation unit: The process of injecting the timed path into the adversarial prediction simulation unit aims to evaluate the execution performance of the timed path in a dynamic adversarial environment through the simulation module. The specific processing logic is as follows: The adversarial prediction simulation unit is a specially designed simulation module for testing the survivability of a timed path in a dynamic adversarial environment. The timed path consists of multiple paths, each path contains a series of nodes, and each node is represented by spatial coordinates and time coordinates, guiding the movement and collaborative behavior of the acting entity in the three-dimensional geographical space. The adversarial prediction simulation unit constructs a perturbation field close to the real adversarial scenario by simulating the trajectory changes of moving obstacles and the dynamic adjustment of no-go zones. After injecting the timed path into the adversarial prediction simulation unit, the simulation module evaluates whether the timed path can successfully avoid moving obstacles and no-go zones during actual execution by reproducing the uncertain factors in the dynamic environment, ensuring the smooth completion of the task.

[0090] The reason for injecting the timed path into the adversarial prediction simulation unit is that by simulating the dynamic adversarial environment, the survivability of the timed path when facing the adjustment of moving obstacles and no-go zones can be evaluated in advance, ensuring the reliability of the path and the safety of task execution. The advantage of this method is that it can discover potential path failure risks before actual execution and provide a basis for subsequent optimization, thereby improving the robustness and task success rate of the action plan in complex dynamic scenarios.

[0091] S5-2. Conduct cyclic calculations in the dynamic obstacle perturbation field: The process of conducting cyclic calculations in the dynamic obstacle perturbation field aims to evaluate the survivability of the timed path in the dynamic environment through multiple simulation calculations. The specific processing logic is as follows: The dynamic obstacle perturbation field simulates the uncertain factors in the adversarial environment, including the random movement of moving obstacles and the immediate adjustment of no-go zones. The movement trajectory of the moving obstacle is generated by a Markov chain model, and the state transition model defines the probability of the moving obstacle transitioning from one state to another. The states include the spatial position and speed of the moving obstacle. The adjustment of the no-go zone is driven by a random process, and the adjustment frequency is preset according to the dynamics of the adversarial scenario, reflecting the randomness of the no-go zone change. In the dynamic obstacle perturbation field, multiple simulation calculations are performed on the timed path, and each calculation records whether the timed path fails due to encountering a moving obstacle or being blocked by a no-go zone. The number of calculations is set to a sufficiently large value to ensure the reliability of the survival probability statistical results.

[0092] The reason for conducting cyclic calculations in the dynamic obstacle perturbation field is that through multiple simulation calculations, the survivability of the timed path in different dynamic scenarios can be comprehensively evaluated, ensuring the accuracy and reliability of the evaluation results. The advantage of this method is that it can simulate various possible dynamic environment changes, discover potential risks of the timed path when facing uncertain factors in advance, and provide a solid data basis for the subsequent calculation of the survival probability.

[0093] S5-3. Conduct tests with a survival probability threshold: The process of testing with the survival probability threshold aims to judge whether the timed path meets the task requirements by calculating the survival probability of the timed path and comparing it with the preset threshold. The specific processing logic is as follows: The survival probability is defined as the probability that the timed path is successfully executed in multiple calculations, and the calculation method is the ratio of the number of successful calculations to the total number of calculations. The number of successful calculations represents the number of calculations in which the timed path is not interfered by moving obstacles or blocked by no-go areas, and the total number of calculations is the total number of simulation calculations. The preset survival probability threshold is determined by the task requirements and reflects the specific requirements of the task for survivability. If the survival probability is greater than or equal to the preset survival probability threshold, it is considered that the timed path has sufficient survivability in the dynamic environment; if the survival probability is less than the preset survival probability threshold, return to the previous steps to re-optimize the candidate path or adjust the timing parameters.

[0094] The reason for testing with the survival probability threshold is that by comparing the survival probability with the preset survival probability threshold, it is possible to intuitively judge whether the timed path meets the survivability requirements of the task and ensure the reliability of the path in the dynamic environment and the safety of task execution.

[0095] S5-4. Fix the timed path as the final command sequence when the threshold is met: The process of fixing the timed path as the final command sequence when the threshold is met aims to convert the timed path that passes the survivability test into an actual command for execution. The specific processing logic is as follows: When the survival probability is greater than or equal to the preset survival probability threshold, it is considered that the timed path has sufficient survivability in the dynamic environment, and the timed path is fixed as the final command sequence. The final command sequence contains specific instructions for the action entities, that is, the spatial coordinates, time coordinates, and resource allocation plans of each path, which are used to guide the actual execution of the task.

[0096] The reason for fixing the timed path as the final command sequence when the threshold is met is to ensure the reliability of the timed path in the dynamic environment and the safety of task execution through the survivability test, and provide a high-quality action plan for the action entities. The advantage of this method is that it can comprehensively evaluate and optimize the timed path before actual execution to ensure the smooth completion of the task and the survivability of the action entities.

[0097] In a multi-role simulation and confrontation environment, the aforementioned step S4 generates a timing path through a symplectic time window rearrangement operator and a conjugate gradient slip strategy, providing a high-quality candidate path set for path planning. Step S5 receives the timing path as input. First, it injects it into the confrontation prediction simulation unit for survivability verification, then performs cyclic calculations in the dynamic obstacle perturbation field, calculates the survival probability, and compares it with a preset survival probability threshold. Finally, the timing path that passes the survivability verification is solidified into the final command sequence. After step S5 is completed, the final command sequence provides a high-quality action plan for the acting entity to cope with moving obstacles and no-go zone adjustments in the frequently changing three-dimensional geographical space, ensuring the smooth completion of the task and the survivability of the acting entity.

[0098] Embodiment 2: Figure 2 The computable modeling system for the action plan of the present invention is given, including: a hypergraph modeling module, a grid generation module, a path optimization module, a timing correction module, and a survival verification module; Hypergraph modeling module: Construct a multi-constraint hierarchical hypergraph that integrates spatial region distribution, task time window, and platform resource status in a three-dimensional dynamic map, and extract an anchor node set by traversing all constraint intersection regions and establish a cross-layer mapping table.

[0099] Grid generation module: Based on the anchor node set, first perform convex hull relaxation boundary expansion calculation to generate a hexahedron envelope grid, and then use the resource margin gradient to guide non-uniform lattice point sampling to form a candidate lattice grid.

[0100] Path optimization module: For the candidate lattice grid, first calculate the path phase dispersion and energy dissipation gradient of each candidate path, comprehensively calculate the two to obtain a global stability factor, and dynamically adjust the taboo table weight according to the factor size and then perform phase-encoded taboo roaming iteration. During the iteration process, record the taboo table suppression loopback in real time and converge to the elite path cluster.

[0101] Timing correction module: Input the elite path cluster into the symplectic time window rearrangement operator, correct the time coordinates of each path node through the conjugate gradient slip strategy, and output the timing path after the cross-platform coordination margin converges to the allowable interval.

[0102] Survival verification module: Inject the timing path into the confrontation prediction simulation unit, perform cyclic calculations in the dynamic obstacle perturbation field and verify it with a survival probability threshold, and solidify the timing path into the final command sequence when the requirements are met.

[0103] The above formulas are all dimensionless and take their numerical calculations. The formulas are obtained by collecting a large amount of data for software simulation to get a formula closest to the real situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0104] It should be noted that the system of the present invention can be deployed on the device itself to achieve embedded applications, or can also run on a PC or other terminal with a user interface, so as to meet various hardware environments and usage requirements.

[0105] Only some exemplary embodiments of the present invention have been described above by way of illustration. Undoubtedly, for those of ordinary skill in the art, without departing from the spirit and scope of the present invention, the described embodiments can be modified in various different ways. Therefore, the above drawings and description are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

[0106] It should be noted that in this text, if there are relational terms such as first and second, they are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprising", "including" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the element.

[0107] As described above, the above are only the specific embodiments of the present application, but the scope of protection of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed in the present application can easily think of changes or substitutions, and all should be covered within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be subject to the scope of protection of the claims.

Claims

1. A computable modeling method for action plans, characterized in that Includes steps: S1: Construct a multi-constraint hierarchical hypergraph that integrates spatial area distribution, task timing window and platform resource status in a three-dimensional dynamic map, extract the anchor node set by traversing all constraint intersection areas and establish a cross-layer mapping table; S2: Based on the anchor node set, the convex hull relaxation boundary expansion calculation is first performed to generate a hexahedral envelope grid, and then the resource margin gradient is used to guide the non-uniform grid point sampling to form a candidate grid point grid; S3: For the candidate grid, the path phase dispersion and energy dissipation gradient of each candidate path are calculated first, and the global stability factor is obtained by comprehensive calculation of the two. The taboo table weight is dynamically adjusted according to the factor size, and then the phase-coded taboo roaming iteration is performed. During the iteration process, the taboo table is recorded in real time to suppress loops and converge to the elite path cluster; S4: Input the elite path cluster into the symplectic time window rearrangement operator, correct the time coordinates of each path node through the conjugate gradient sliding strategy, make the cross-platform coordination margin converge to the allowed interval, and then output the timing path; S5: Inject the timing path into the confrontation prediction simulation unit, perform cyclic calculations in the dynamic obstacle disturbance field, and test it with the survival probability threshold. When the requirements are met, solidify the timing path as the final command sequence.

2. The computable modeling method for the action plan according to claim 1, characterized in that, Step S1 includes the following contents: First, the spatial range is divided into a set of spatial regions at multiple levels, where the bottom layer is a high-resolution spatial grid representing specific geographic coordinate points, and the top layer is a low-resolution macro region representing a large-scale geographic division; Discretize the timeline into multiple time segments and assign each task a task timing window defined by the start time and end time; Maintain resource status vector for the platform and divide it into multiple resource levels; Construct a hypergraph whose node set consists of sub-regions of a set of spatial regions, time slices, and resource levels, and whose hyperedges connect node sets that are compatible with each other in space, time, and resources; Traverse the hypergraph by breadth-first search to identify constraint intersection regions that simultaneously satisfy space, time, and resource constraints, and define the nodes therein as the anchor node set; A cross-layer mapping table is established to record the hierarchical correspondence between anchor nodes in the spatial region set, time layer and resource layer.

3. The computable modeling method for the action plan according to claim 2, wherein Step S2 includes the following contents: Firstly, the smallest convex polyhedron of the anchor node set in three-dimensional space is calculated, and the expanded convex polyhedron is generated by expanding the convex hull surface by a fixed distance in the direction of the convex hull normal vector. The expanded convex polyhedron is then approximated as an axis-aligned hexahedral envelope lattice. Subsequently, the resource margin function is defined in the hexahedral envelope lattice and the gradient of the resource margin function is calculated. The sampling density is determined according to the gradient, so that the sampling density in the area with drastic resource changes is higher than that in the area with gentle resource changes. Finally, a non-uniformly distributed grid point set is generated in the hexahedral envelope lattice according to the sampling density to form a candidate grid point grid.

4. The computable modeling method for the action plan according to claim 3, wherein Step S3 includes the following contents: Dynamically adjust the tabu duration of the paths in the tabu list according to the global stability factor, where the global stability factor is generated by comprehensively calculating the path phase dispersion and the energy dissipation gradient. Subsequently, perform the phase-encoding tabu roaming iteration. By encoding the paths as phase vectors and randomly walking in the phase space, preferentially select the paths or nodes not recorded in the tabu list, and update the tabu list in real time during the iteration to suppress loops, and finally converge to the elite path cluster where the global stability factor value meets the standard.

5. The computable modeling method for the action plan according to claim 3, wherein Step S3 includes the following: For each node on the candidate path, calculate the time difference and space difference between it and the next node; then, calculate the average value of all node pairs' time differences and the average value of all node pairs' space differences; next, for each node pair, calculate the absolute value of the difference between its time difference and the average value of all time differences, and the absolute value of the difference between its space difference and the average value of all space differences, and multiply the absolute values of the two to obtain the product of each node pair; finally, sum up the products of all node pairs to obtain the path phase dispersion to quantify the fluctuations of the path in time and space.

6. The computable modeling method for the action plan according to claim 3, wherein Step S3 includes the following: The calculation process of the energy dissipation gradient is as follows: for each node on the candidate path, determine its resource consumption value; then, for adjacent nodes, calculate the absolute value of the resource consumption difference between the two, and find the maximum absolute value of the resource consumption among all adjacent node pairs; next, multiply the absolute value of the resource consumption difference of each adjacent node pair by the maximum absolute value of the resource consumption of all adjacent node pairs to obtain the product of each adjacent node pair; finally, sum up the products of all adjacent node pairs to obtain the energy dissipation gradient to quantify the changes in resource utilization of the path.

7. The computable modeling method for the action plan according to claim 4, wherein Step S4 includes the following: Through inputting the elite path cluster into the symplectic time window rearrangement operator for timing optimization, adjust the time coordinates of the path nodes to meet the requirements of the task timing window. Subsequently, use the conjugate gradient slip strategy. By calculating the sensitivity of the collaborative margin to the time coordinates and iteratively adjusting the time coordinates along the conjugate direction, gradually reduce the timing deviation between multiple platforms until the collaborative margin converges to the preset timing tolerance threshold. Finally, output the timed path containing the corrected time coordinates to ensure that multiple platforms arrive at the collaborative positioning point synchronously.

8. The computable modeling method for the action plan according to claim 7, wherein Step S4 includes the following: After each iteration, recalculate the arrival time deviation of multiple platforms at the collaborative positioning point, that is, the collaborative margin. When this deviation is less than or equal to the preset timing tolerance threshold, it is determined that the adjustment of the time coordinates has met the requirements and the iteration is stopped.

9. The computable modeling method for the action plan according to claim 8, characterized in that, Step S5 includes the following: By inputting the timed path into the adversarial prediction simulation unit, perform multiple simulation calculations in the dynamic obstacle perturbation field, calculate the survival probability, and compare the survival probability with the preset survival probability threshold. When the survival probability is greater than or equal to the preset survival probability threshold, solidify the timed path into the final command sequence.

10. An actionable plan computable modeling system for implementing the actionable plan computable modeling method according to any one of claims 1-9, characterized in that, Including: Hypergraph modeling module, grid generation module, path optimization module, timing correction module, and survival verification module; Hypergraph Modeling Module: Construct a multi-constraint hierarchical hypergraph that integrates spatial region distribution, task time series window, and platform resource status in a 3D dynamic map, and extract an anchor node set by traversing all constraint intersection regions and establish a cross-layer mapping table; Raster Generation Module: Based on the anchor node set, first perform convex hull relaxation boundary expansion calculation to generate a hexahedron envelope grid, and then use the resource margin gradient to guide non-uniform lattice point sampling to form a candidate lattice raster; Path Optimization Module: For the candidate lattice raster, first calculate the path phase dispersion and energy dissipation gradient of each candidate path, comprehensively calculate the two to obtain the global stability factor, and dynamically adjust the taboo table weight according to the factor size and then perform phase-encoded taboo roaming iteration. During the iteration process, record the taboo table in real time to suppress loops and converge to the elite path cluster; Time Series Correction Module: Input the elite path cluster into the symplectic time window rearrangement operator, correct the time coordinates of each path node through the conjugate gradient slip strategy, and output the timed path after the cross-platform cooperation margin converges to the allowable interval; Survival Verification Module: Inject the timed path into the adversarial prediction simulation unit, perform cyclic calculations in the dynamic obstacle perturbation field and test with the survival probability threshold, and solidify the timed path as the final command sequence when the requirements are met.

Images