Multi-scene multi-stage task planning method and device for manned lunar surface activities

Abstract

The invention relates to the technical field of spacecraft task planning, operational research and mixed integer planning, in particular to a multi-scene multi-stage task planning method and device for manned lunar surface activities, and the method comprises the steps: constructing a plurality of to-be-planned tasks for the manned lunar surface activities into a task pool, and setting constraint parameters corresponding to the task pool; preprocessing the task pool and the constraint parameters to construct a mixed integer programming model; and inputting the mixed integer programming model into a preset mathematical solver to find a final task execution scheme. Therefore, the problems that global optimization is difficult to complete at one time in multiple scenes such as normal planning, sudden adjustment and emergency return voyage in the prior art, modeling solving needs to be conducted again every time scene switching is conducted, and efficiency is low are solved.

Description

Technical Field

[0001] This invention relates to the fields of spacecraft mission planning, operations research and mixed integer programming, and in particular to a multi-scenario, multi-stage mission planning method and apparatus for manned lunar activities. Background Technology

[0002] In recent years, human demand for manned exploration and operations on the lunar surface has been continuously increasing, involving various mission types such as sample collection, terrain surveying, equipment deployment, and emergency return. These missions often need to be completed under strict time, energy, and safety constraints, and require adjustments to plans as the situation on-site changes. Traditional space mission planning methods rely heavily on continuous optimization within a single scenario, which cannot efficiently cope with the demands of frequent switching between multiple scenarios.

[0003] In the field of operations research, the multi-phase orientation problem has been used to solve path and task selection problems with multi-day inspection or sampling scenarios. Related research has proposed several heuristic and exact algorithms, such as variable neighborhood search and metaheuristic methods in the multi-phase orientation problem, verifying the feasibility of balancing benefits and resource consumption in multi-phase task planning.

[0004] To address the uncertainties in space missions, researchers have proposed methods based on simulation and stochastic programming, such as integrated space mission planning methods under uncertain conditions, which achieve robust planning for various uncertain situations through generalized affine decision rules. In addition, research on multi-starting team orientation problems focuses on the rapid replanning of unmanned systems in dynamic environments, reconstructing mission paths in new environments through deep reinforcement learning and other methods.

[0005] While the aforementioned methods have achieved significant results in their respective fields, these technologies struggle to perform global optimization in a single operation across multiple scenarios, including normal planning, sudden adjustments, and emergency return missions. Each scenario switch necessitates remodeling and solving, resulting in low efficiency. Therefore, a comprehensive method is urgently needed that can uniformly express the requirements of multiple scenarios, accommodate the needs of manned lunar activities, and support rapid replanning to meet the complex and ever-changing demands of manned lunar missions. Summary of the Invention

[0006] This invention provides a multi-scenario, multi-stage mission planning method and apparatus for manned lunar activities, which solves the problems of related technologies being unable to complete global optimization in one go under multiple scenarios such as normal planning, sudden adjustments and emergency return, and the need to remodel and solve each scenario, resulting in low efficiency.

[0007] A first aspect of the present invention provides a multi-scenario, multi-stage mission planning method for manned lunar surface activities, comprising the following steps: Multiple unplanned tasks for manned lunar activities are constructed into a task pool, and the constraint parameters corresponding to the task pool are set. The task pool and the constraint parameters are preprocessed to construct a mixed integer programming model; The mixed integer programming model is input into a preset mathematical solver to find the final task execution scheme.

[0008] Optionally, the preprocessing of the task pool and the constraint parameters to construct a mixed-integer programming model includes: The single landing point in the task pool is split into multiple virtual landing points, and the starting landing point of each virtual landing point is numbered to obtain a set of virtual locations; A virtual task is introduced for each virtual landing point, and each virtual task is numbered to obtain a set of virtual tasks; The nodes of the original multiple real task geographical locations in the task pool are renumbered to obtain a set of real locations; All real tasks to be planned in the task pool are renumbered to obtain a set of real tasks; The mixed-integer programming model is constructed based on the set of virtual locations, the set of virtual tasks, the set of real locations, the set of real tasks, and the constraint parameters.

[0009] Optionally, inputting the mixed-integer programming model into a preset mathematical solver to find the final task execution scheme includes: The mixed-integer programming model is input into the preset mathematical solver, and the final task execution scheme is found using the unit utility maximization task insertion algorithm; or The mixed-integer programming model is input into the preset mathematical solver, and the execution-first-return algorithm is used to find the final task execution scheme; or The mixed integer programming model is input into the preset mathematical solver, and the unit utility maximization task insertion algorithm and the execution priority return algorithm are dynamically coordinated using an adaptive fusion strategy to find the final task execution scheme.

[0010] Optionally, the step of inputting the mixed-integer programming model into the preset mathematical solver and using the unit utility maximization task insertion algorithm to find the final task execution scheme includes: Determine if all tasks are currently incomplete. If none are, generate a blank task execution plan. Otherwise, obtain the current task completion status to generate a current task execution plan for completed tasks. Iterate through all candidate locations for any task in the mandatory task set, attempting to insert the current task into all possible positions in the current task execution plan, and sequentially determine whether the current position satisfies the constraint parameters. If it does, calculate the unit utility obtained by inserting the current task executed in all candidate locations into all possible positions, select the maximum unit utility, and insert the current task executed in a certain candidate location into a certain possible position in the current task execution plan based on the maximum unit utility to obtain a new task execution plan. Remove the current task from the mandatory task set; otherwise, skip the current task. The aforementioned process is executed iteratively until the set of required tasks is empty or no new tasks can be inserted. Determine if the set of mandatory tasks is empty. If the set of mandatory tasks is not empty, indicate that no feasible solution was found. Otherwise, iterate through all candidate locations for any task in the set of optional tasks, attempting to insert the current task into all possible positions in the current task execution plan. Sequentially determine if the current position satisfies the constraint parameters. If satisfied, calculate the unit utility obtained by inserting the current task executed at all candidate locations into all possible positions, select the maximum unit utility, and insert the current task executed at a certain candidate location into a possible position in the current task execution plan based on the maximum unit utility to obtain a new task execution plan. Remove the current task from the set of optional tasks. Otherwise, skip the current task. The aforementioned process is executed iteratively until the set of optional tasks is empty or no new tasks can be inserted, in order to obtain the final task execution plan.

[0011] Optionally, the step of inputting the mixed-integer programming model into the preset mathematical solver and using the execution-first-return algorithm to find the final task execution scheme includes: Determine if all tasks are currently incomplete. If none are, generate a blank task execution plan. Otherwise, obtain the current task completion status to generate a current task execution plan for completed tasks. At the end of all unfinished stages in the current task execution plan, insert a task that directly returns to the landing point to obtain a new task execution plan; Check whether the new task execution plan satisfies the constraint parameters. If it does not, indicate that no feasible solution was found. Otherwise, use the new task execution plan as the final task execution plan.

[0012] Optionally, the step of inputting the mixed-integer programming model into the preset mathematical solver and dynamically coordinating the unit utility maximization task insertion algorithm and the execution priority return algorithm using an adaptive fusion strategy to find the final task execution scheme includes: The mixed integer programming model is input into the preset mathematical solver, and the unit utility maximization task insertion algorithm and the execution priority return algorithm are dynamically coordinated by the adaptive fusion strategy to solve multiple feasible task execution schemes. The multiple feasible task execution schemes are evaluated and weighted in a multidimensional manner to determine the final task execution scheme.

[0013] A second aspect of the present invention provides a multi-scenario, multi-stage mission planning device for manned lunar activities, comprising: The construction module is used to build a task pool from multiple unplanned tasks for manned lunar activities and to set the constraint parameters corresponding to the task pool. A preprocessing module is used to preprocess the task pool and the constraint parameters to construct a mixed integer programming model; The search module is used to input the mixed integer programming model into a preset mathematical solver to find the final task execution scheme.

[0014] A third aspect of the present invention provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the multi-scenario, multi-stage mission planning method for manned lunar activities as described in the above embodiments.

[0015] A fourth aspect of the present invention provides a computer program product, which, when executed by a processor, implements the above-described multi-scenario, multi-stage mission planning method for manned lunar activities.

[0016] A fifth aspect of the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described multi-scenario, multi-stage mission planning method for manned lunar activities.

[0017] The multi-scenario, multi-stage mission planning method and apparatus for manned lunar activities proposed in this invention can uniformly express the complex requirements of manned lunar activities in a single model using a mixed integer programming model. It also combines a mathematical solver with a unit utility maximization task insertion algorithm to achieve one-time global planning and rapid replanning capabilities in different scenarios.

[0018] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0019] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 A flowchart illustrating a multi-scenario, multi-stage mission planning method for manned lunar activities according to an embodiment of the present invention; Figure 2 This is a detailed execution diagram of a multi-scenario, multi-stage mission planning method for manned lunar activities provided according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the architecture of a multi-scenario, multi-stage task planning platform provided according to an embodiment of the present invention; Figure 4 This is a block diagram of a multi-scenario, multi-stage mission planning device for manned lunar activities provided according to an embodiment of the present invention; Figure 5 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention.

[0020] Explanation of reference numerals in the attached figures: 40-Multi-scenario, multi-stage mission planning device for manned lunar activities, 401-Construction module, 402-Preprocessing module, 403-Search module, 501-Memory, 502-Processor and 503-Communication interface. Detailed Implementation

[0021] Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain the present invention, and should not be construed as limiting the present invention.

[0022] The following describes, with reference to the accompanying drawings, a multi-scenario, multi-stage mission planning method and apparatus for manned lunar activities according to embodiments of the present invention. As mentioned in the background section, the actual planning of manned lunar activities faces numerous key challenges. These challenges include constraints related to time, the lunar environment, and the capabilities of lunar facilities (e.g., the life support capabilities of spacesuits, lunar mobility, and total energy consumption), while simultaneously requiring the maximization of mission efficiency while ensuring astronaut safety. The mission types are highly heterogeneous, encompassing sample collection, topographic mapping, deployment of lunar facilities, scientific experiments, and emergency return missions. Each mission activity has significantly different requirements for tools, environment, and timing, necessitating a unified plan that considers multiple constraints. Some mission activities (such as life support system checks and safe return verification) are critical and cannot be ignored. Some mission activities have strict prerequisite dependencies; for example, scientific equipment must be deployed and geological surveys completed before sample collection to ensure the feasibility of subsequent operations. Sampling missions also require weighing scientific value against access costs among multiple alternative locations, seeking the optimal balance between energy consumption and efficiency. This invention provides a multi-scenario, multi-stage mission planning method for manned lunar activities. In this method, the process is executed according to the flow of "task input → task pool construction → constraint parameter configuration → automatic model generation → multi-algorithm solution → scheme fusion and recommendation → user selection / iterative iteration", thereby realizing a fully automated closed loop "from data to decision" and meeting the stringent requirements of manned lunar activities for planning efficiency, response speed and scheme reliability in different scenarios.

[0023] Specifically, Figure 1 This is a flowchart illustrating a multi-scenario, multi-stage mission planning method for manned lunar activities provided in an embodiment of the present invention.

[0024] like Figure 1 As shown, this multi-scenario, multi-stage mission planning method for manned lunar activities includes the following steps: In step S101, multiple planned tasks for manned lunar activities are constructed into a task pool, and the corresponding constraint parameters for the task pool are set.

[0025] In actual implementation, such as Figure 2 As shown, in order to achieve closed-loop automation from user input to task planning output, this embodiment of the invention pre-constructs a multi-scenario, multi-stage task planning platform, which is divided into a user interaction layer, a data management layer, an algorithm and service layer, an interface layer, and a communication layer.

[0026] Furthermore, such as Figure 3As shown, the user interaction layer includes a task entry interface and a parameter configuration panel. The task entry interface supports both graphical and scripted methods, allowing users to batch enter the attributes (location, type, priority, etc.) of tasks to be planned, either online or offline. The parameter configuration panel is used to set the total time budget, total power budget, prerequisite relationships, mandatory / optional task markers, and scenario modes (normal planning, emergency adjustment, emergency return). Furthermore, users can update the current tasks to be planned and the parameters required for task planning at any time through the user interaction layer, and the platform automatically recommends new task planning schemes.

[0027] Furthermore, such as Figure 3 As shown, the data management layer includes a task pool management module and a constraint parameter management module. The task pool management module aggregates all input tasks into a task pool. It maintains task status and attribute updates; supports dynamic addition, deletion and modification; the constraint parameter management module is used to manage global resource constraints (total time, total energy) and stage constraints (time period limit, energy limit), and maps them to the task pool in real time.

[0028] Specifically, in this embodiment of the invention, all tasks to be planned for manned lunar activities are entered through the user interaction layer, along with parameters such as the total time and total power required. The data management layer then summarizes all tasks to be planned into a manned lunar activity task pool and maps the parameters such as the total time and total power required to the task pool.

[0029] In addition, such as Figure 3 As shown, the interface layer and communication layer include a front-end API / RPC interface and a hardware driver interface, wherein, The front-end API / RPC interface provides a data interaction channel between the upper-layer interface and third-party systems (command center, simulation platform, etc.); the hardware driver interface supports real-time status docking with hardware devices such as lunar robots and communication base stations to obtain environmental and resource status feedback.

[0030] In step S102, the task pool and constraint parameters are preprocessed to construct a mixed integer programming model.

[0031] In some embodiments, the task pool and constraint parameters are preprocessed to construct a mixed-integer programming model, including: The single landing point in the mission pool is split into multiple virtual landing points, and the starting landing point of each virtual landing point is numbered to obtain a set of virtual locations; A virtual task is introduced for each virtual landing point, and each virtual task is numbered to obtain a set of virtual tasks; The nodes of the original multiple real-world task geographical locations in the task pool are renumbered to obtain a set of real locations; Renumber all real tasks to be planned in the task pool to obtain a set of real tasks; Construct a mixed-integer programming model based on the set of virtual locations, the set of virtual tasks, the set of real locations, the set of real tasks, and the constraint parameters.

[0032] In actual implementation, such as Figure 3 As shown, in this embodiment of the invention, the task pool and constraint parameters are preprocessed in the algorithm and service layer of the multi-scenario, multi-stage task planning platform to construct a mixed integer programming model.

[0033] Furthermore, the algorithm and service layer includes a model generation module, a solution module, and an adaptive fusion module. This process takes place in the model generation module, which receives parameters from the data management layer based on the manned lunar mission pool and mission planning requirements. The model generation module automatically performs preprocessing (base node splitting, virtual mission insertion, and number reorganization) and generates a mixed-integer programming model description file (MIP-LP / MPS format), as follows: First, the individual landing points in the mission pool are split into There are 1 virtual landing point, labeled as follows: (where each number) Corresponding to the The starting and landing point locations for each day, each numbered Corresponding to the (The final landing point location for the day). This split allows for a natural distinction between the departure and return nodes of each stage within the model.

[0034] Furthermore, a virtual task is introduced for each virtual landing point. and set it as a task Benefits Complete the task Required time Complete the task Required energy This means that the task has no revenue, no service duration, and no energy consumption, and is used to occupy a place in the model to facilitate the modeling of relevant constraints of the landing point.

[0035] Furthermore, the original task pool... Each real-world task geolocation node is renumbered as follows: To obtain a set of real locations; to include all real-world tasks to be planned in the task pool. Renumbered To obtain the real set of tasks, so that the set of locations is unified as The task set is unified as It includes both virtual landing sites (and corresponding tasks) and all real sampling or operation sites.

[0036] Furthermore, based on the first three preprocessing steps, a set of tasks to be planned is constructed accordingly. Required task set Optional task set It must be done in the stage Completed task set etc., among which, After this preprocessing, the variable indices and constraints in the model can be correctly represented by a unified numbering system, indicating the start, arrival, task execution, and return of each stage.

[0037] A mixed-integer programming model is constructed based on the aforementioned set of virtual locations, set of virtual tasks, set of real locations, set of real tasks, and constraint parameters. The mixed-integer programming model is achieved through... Optimization within a discrete period Each astronaut's mission execution route, to maximize in The total utility gained from each candidate node. In each cycle, all astronauts depart from and return from the landing site, subject to a cycle-specific time limit. and energy limit The constraints should take into account multi-cycle scheduling, multi-resource constraints, mandatory task completion, selection of multiple alternative nodes, precedence constraints, and safe return requirements.

[0038] The specific expression for the mixed-integer programming model is as follows: (1) (2) (3) (4) (5) (6) (7) (8) (9) (10) (11)

[0039] (12) (13) (14)

[0040] (15) (16) (17) (18) (19) (20) (twenty one) (twenty two) (twenty three) (twenty four) (25) (26) (27) (28)

[0041] (29) in, To label the astronauts , For the number of astronauts, Subscript for location ( The starting point of the split virtual landing point. , This represents the number of stages (days) in the task execution process. This represents the number of task location nodes (excluding landing points). For the number of tasks, For the task The benefits, For astronauts At the node Execute the task If it is 1, then it is 1; otherwise it is 0. The starting point of a certain segment in the path The index of the task to be completed ( (Indicates a virtual task) , For astronauts At the node Execute the task Then proceed to the node And perform the task If it is 1, then it is 1; otherwise it is 0. Subscript for location ( The endpoint of the split virtual landing point. The endpoint of a certain segment in the path The index of the task to be completed ( (Indicates a virtual task) , For astronauts At the node After completing task 0, proceed to the node. If task completion is 0, the value is 1; otherwise, it is 0. For astronauts At the node Then proceed to the node Complete the task If it is 1, then it is 1; otherwise it is 0. For astronauts At the node Complete the task Then proceed to the node Complete the task If it is 1, then it is 1; otherwise it is 0. For astronauts At the node Complete the task Then proceed to the node Complete the task If it is 1, then it is 1; otherwise it is 0. For astronauts At the node Complete the task Then proceed to the node Complete the task If it is 1, then it is 1; otherwise it is 0. For astronauts The cumulative time before task 0 is executed on node 0 For astronauts The accumulated energy before task 0 is executed at node 0. For astronauts At the node Execute the task Previous cumulative time, For nodes arrive The travel time, To complete the task Required time For astronauts At the node Complete the task Previous cumulative time, For astronauts At the node Execute the task Previous cumulative time, For astronauts At the node Execute the task Previous cumulative time, For time period The time limit, For astronauts At the node Execute the task Previous accumulated energy, For nodes arrive Mobile energy consumption, To complete the task The required energy For astronauts At the node Execute the task Previous accumulated energy, For astronauts At the node Execute the task The accumulated energy before, For astronauts At the node Execute the task Previous accumulated energy, Subscript for task With task index The weight values ​​between them For the set of immediate preceding relation tuples , indicating the task subscript Must be in the task index At least after completion Execute after the time. To complete the task Required time For a sufficiently large constant, For astronauts At the node Execute the task If it is 1, then it is 1; otherwise it is 0. A set of optional tasks. For astronauts At the node Execute the task Previous cumulative time, For must be in the stage Completed task set For astronauts At the node Execute the task Previous cumulative time, For astronauts During the period Execute the task If it is 1, then it is 1; otherwise it is 0. For nodes The time to move to 0 For time period The time limit, It is a set that includes both the required task set and the optional task set. For astronauts At the node Execute the task Previous accumulated energy, To complete the task The required energy For nodes Mobile energy consumption down to 0 For time period The upper limit of energy.

[0042] It should be noted that, as shown above, formulas (1)-(9) constitute the core mixed-integer programming model. The objective function of formula (1) maximizes the total benefit obtained by all astronauts in completing their tasks at each node; formulas (2) and (4) ensure that the arrival flow at each node is consistent with the departure flow, thereby ensuring that each astronaut... The journey forms a single connected loop; Formula (3) restricts the in-degree of the landing point on the first day to zero, Formula (5) restricts the out-degree of the landing point on the last day to zero; Formula (6) ensures that each node is visited at most once; Formulas (7) and (8) respectively ensure that each path starts from the landing point and ends at the landing point, completing the closed loop; Formula (9) prevents the occurrence of invalid sub-loops of a single node.

[0043] Equations (10)-(17) describe the time- and energy-related constraints. Equation (10) initializes the accumulated time and accumulated energy to zero each time it departs from the landing point; Equations (11) and (14) utilize large... Linearization, updating on selected arcs and Formulas (12)-(15) respectively guarantee each time period The total time and total energy do not exceed their upper limit; Formulas (13) and (16) force the cumulative time and cumulative energy at the end of each stage to remain non-decreasing in the time dimension; Formula (17) prohibits the occurrence of an earlier period after a later period.

[0044] Formulas (18) and (19) introduce the precedence relation for generalization. Formula (18) requires that for each If the task and If all are selected, then the task The start time must be at least during the task Finish Only after that can it be started; Formula (19) is an optional coupling constraint, which is used to force the successor and successor tasks to be performed by the same astronaut or to omit them at the same time when needed.

[0045] Formulas (20) and (21) respectively implement the set of mandatory tasks. A task must have at least one access to the set of optional tasks. A task can only be accessed once.

[0046] Formulas (22)-(23) ensure that all selected tasks During its designated time period Execute internally.

[0047] Formulas (24)-(27) are the safety return constraints. When the task... During the period When the astronauts are scheduled to return to the landing site, they must retain sufficient time and energy to ensure timely return.

[0048] Finally, formulas (28) and (29) enforce the duality and nonnegativity of all decision variables.

[0049] In step S103, the mixed integer programming model is input into a preset mathematical solver to find the final task execution scheme.

[0050] In some embodiments, a mixed-integer programming model is input into a preset mathematical solver to find a final task execution scheme, including: Input the mixed-integer programming model into the preset mathematical solver, and use the unit utility maximization task insertion algorithm to find the final task execution scheme; or Input the mixed-integer programming model into the preset mathematical solver, and use the execution-first-return algorithm to find the final task execution solution; or The mixed-integer programming model is input into a preset mathematical solver, and the adaptive fusion strategy is used to dynamically coordinate the unit utility maximization task insertion algorithm and the execution priority return algorithm to find the final task execution scheme.

[0051] In some embodiments, a mixed-integer programming model is input into a preset mathematical solver, and a unit utility maximization task insertion algorithm is used to find the final task execution scheme, including: Determine if all tasks are currently incomplete. If none are, generate a blank task execution plan. Otherwise, obtain the current task completion status to generate a current task execution plan for completed tasks. Iterate through all candidate locations for any task in the mandatory task set, attempting to insert the current task into all possible positions in the current task execution plan. Check if the current position satisfies the constraint parameters. If it does, calculate the unit utility obtained by inserting the current task, executed at all candidate locations, into all possible positions, and select the maximum unit utility. Based on the maximum unit utility, insert the current task, executed at a certain candidate location, into a possible position in the current task execution plan to obtain a new task execution plan, and remove the current task from the mandatory task set. Otherwise, skip the current task. The aforementioned process is executed iteratively until the set of required tasks is empty or no new tasks can be inserted. The algorithm checks if the set of required tasks is empty. If it is not empty, it indicates that no feasible solution was found. Otherwise, it iterates through all candidate locations for any task in the set of optional tasks, attempting to insert the current task into all possible positions in the current task execution plan. It then checks if the current position satisfies the constraint parameters. If it does, it calculates the unit utility obtained by inserting the current task, which is executed at all candidate locations, into all possible positions, and selects the maximum unit utility. Based on the maximum unit utility, it inserts the current task, which is executed at a certain candidate location, into a possible position in the current task execution plan to obtain a new task execution plan. The current task is then removed from the set of optional tasks. Otherwise, the current task is skipped. The aforementioned process is repeated iteratively until the set of selectable tasks is empty or no new tasks can be inserted, in order to obtain the final task execution plan.

[0052] In some embodiments, a mixed-integer programming model is input into a preset mathematical solver, and an execution-first-return algorithm is used to find the final task execution scheme, including: Determine if all tasks are currently incomplete. If none are, generate a blank task execution plan. Otherwise, obtain the current task completion status to generate a current task execution plan for completed tasks. At the end of all unfinished stages in the current task execution plan, insert a task that directly returns to the landing point to obtain a new task execution plan; Check whether the new task execution plan meets the constraint parameters. If it does not, indicate that no feasible solution was found. Otherwise, use the new task execution plan as the final task execution plan.

[0053] In some embodiments, a mixed-integer programming model is input into a preset mathematical solver, and an adaptive fusion strategy is used to dynamically coordinate the unit utility maximization task insertion algorithm and the execution priority return algorithm to find the final task execution scheme, including: The mixed integer programming model is input into a preset mathematical solver, and an adaptive fusion strategy is used to dynamically coordinate the unit utility maximization task insertion algorithm and the execution priority return algorithm to solve multiple feasible task execution schemes. Multiple feasible task execution plans are evaluated and weighted in a multidimensional manner to determine the final task execution plan.

[0054] In actual implementation, such as Figure 3 As shown, in order to balance solution quality and efficiency, this embodiment of the invention integrates multiple algorithms into the solution module of a multi-scenario, multi-stage task planning platform. Through a scenario-adaptive fusion strategy, it dynamically adjusts the solver time allocation and algorithm priority in different scenarios, and performs multi-dimensional evaluation and weighted sorting on the solutions produced by multiple algorithms to extract the optimal solution or recommend the optimal candidate solution according to the scenario preset priority. This achieves automatic generation of optimal or near-optimal task planning solutions, ensuring response speed or solution quality, and supporting users to make local adjustments to the solution.

[0055] Specifically, the mixed integer programming model is input into a mathematical solver (such as Gurobi, CPLEX, COPT, etc.) using JAVA, Python, or command line, and preset parameters such as the maximum solution time and expected upper and lower bounds are set. The mathematical solver is called in parallel or in time-sharing to find the optimal solution. Each time a feasible solution is found, the current feasible solution is recorded and converted into the current task execution plan.

[0056] Furthermore, in order to find the optimal solution more quickly, this embodiment of the invention proposes to use a unit utility maximization task insertion algorithm to find the final task execution scheme, the specific process of which is as follows: Step 1: Determine if all tasks are currently incomplete. If none are, generate a blank task execution plan. If the first attempt is a direct round trip to the landing point, otherwise a task execution plan consisting of completed tasks will be generated based on the current task completion status. Step 2, for the set of required tasks Tasks in All alternative locations Iterate, attempting to insert it into all possible positions in the current solution. In the process, it sequentially checks whether the location satisfies the preceding relationship constraints, safe return requirements, specified task execution phase requirements, and daily time and energy limit constraints. If not, the task is skipped; if satisfied, the calculation is performed at the location. Tasks to be performed Insert at position The unit utility obtained ,in This represents the weighting ratio between time and energy. Step 3, find the The largest value So at the location Tasks to be performed Insert at the position of the current scheme Location, and from the set of required tasks. Remove task .

[0057] Step four, repeat steps two and three until the set of required tasks is reached. Empty or unable to insert new tasks; Step 5, for the set of optional tasks Perform steps two through four in a similar manner; Step 6, if a set of tasks is required If the value is not empty, a message will be displayed indicating that no feasible solution was found; otherwise, the current solution will be returned.

[0058] Furthermore, in order to find the optimal solution more quickly, this embodiment of the invention proposes to use an execution-first return algorithm to find the final task execution scheme, the specific process of which is as follows: Step 1: Determine if all tasks are currently incomplete. If none are, generate a blank task execution plan. If the first attempt is a direct round trip to the landing point, otherwise a task execution plan consisting of completed tasks will be generated based on the current task completion status. Step 2: At the end of all unfinished stages in the current plan, insert a task that directly returns to the landing point to obtain a new task execution plan; Step 3: Check whether the new task execution plan meets the time and energy upper limit constraints. If it does not meet the constraints, indicate that no feasible solution was found; otherwise, use the new task execution plan as the final task execution plan.

[0059] Furthermore, to find the optimal solution more quickly, this embodiment of the invention proposes to use an adaptive fusion strategy to dynamically coordinate the unit utility maximization task insertion algorithm and the execution priority return algorithm to find the final task execution scheme. The specific process is as follows: Based on the current scenario requirements, computing power limitations, and available time, the invocation of two algorithms is dynamically coordinated. This is illustrated using three scenarios: normal planning, sudden adjustment, and emergency return. In the normal planning scenario, computing power limitations are relatively weak and available time is ample, allowing all algorithms to run in parallel. Before reaching the available time limit, the task execution plans given by each method are continuously compared, and the solution with higher overall utility is recommended. In the sudden adjustment scenario, computing power limitations are relatively strong and available time is short. Only the task insertion algorithm that maximizes unit utility and the priority return algorithm can be invoked. Before reaching the available time limit, the task execution plans given by each method are continuously compared, and the solution with higher overall utility is recommended. In the emergency return scenario, computing power limitations are the strongest and available time is the shortest. Only the priority return algorithm can be invoked, and the recommended task execution plan is given.

[0060] The following detailed description of the multi-scenario, multi-stage mission planning method for manned lunar activities proposed in this invention will be provided through a specific embodiment.

[0061] This embodiment evaluates the performance of the mathematical solver (Gurobi 12.0.1, with default cutting plane and preprocessing) for mixed integer programming models, the task insertion algorithm for maximizing unit utility (implemented in pure Python 3.12 single-threaded mode, α=0.75), and the priority return algorithm on an experimental platform configured with a 3.8 GHz 8-core AMD 5800X CPU, 32GB of memory, and Windows 11 operating system. Evaluation metrics include total utility, runtime, and resource utilization.

[0062] In a typical three-day manned lunar mission example, the mathematical solver ultimately yielded a total utility of 114, a runtime of 40232 s, a total time utilization rate of 97.9%, and a total energy utilization rate of 74.1%. The unit utility maximization task insertion algorithm ultimately yielded a total utility of 115.5, a runtime of 38 s, a total time utilization rate of 93.7%, and a total energy utilization rate of 70.0%. The priority return algorithm ultimately yielded a total utility of 0, a runtime of less than 1 s, and a total time utilization rate of 0% and a total energy utilization rate of 0%.

[0063] The results show that the three algorithms each have their own focus in terms of computing power requirements, running time, and resource utilization, and their combined use can help adapt to complex needs in multiple scenarios. Among them, the unit utility maximization task insertion algorithm reduces the running time by about three orders of magnitude while maintaining or exceeding the benefits, and is also more efficient in terms of resource consumption, providing efficient and reliable algorithmic support for mission planning of manned lunar activities.

[0064] In summary, the multi-scenario, multi-stage mission planning method for manned lunar activities proposed in this embodiment of the invention addresses various scenarios such as normal planning optimization, emergency plan adjustment, and emergency situation return. It employs mathematical models and algorithms to plan a multi-stage mission planning scheme in one go, and possesses compatibility with other software and hardware platforms. Specifically, the constructed hybrid integer programming model can express and handle multiple round trips to landing sites, multiple alternative point sampling, mandatory and optional task processing, maximum detection distance requirements, precedence constraints, and adherence to safe return constraints within a single mathematical model. It utilizes a fusion-based solution algorithm, including mathematical solvers, unit utility maximization task insertion algorithms, and priority return algorithms, and automatically integrates multiple solution algorithms according to scenario requirements to obtain the best manned lunar activity mission planning scheme. Furthermore, it can be equipped with supporting software and hardware interfaces, software environments, and hardware carriers to support the implementation of the above models and algorithms, thus ensuring compatibility with other software and hardware platforms.

[0065] Next, referring to the accompanying drawings, a multi-scenario, multi-stage mission planning device for manned lunar activities proposed according to an embodiment of the present invention is described.

[0066] Figure 4 This is a block diagram of a multi-scenario, multi-stage mission planning device for manned lunar activities provided in an embodiment of the present invention.

[0067] like Figure 4 As shown, the multi-scenario, multi-stage mission planning device 40 for manned lunar activities includes: a construction module 401, a preprocessing module 402, and a search module 403.

[0068] The module 401 is used to construct a task pool from multiple planned tasks for manned lunar activities and to set the corresponding constraint parameters for the task pool. The preprocessing module 402 is used to preprocess the task pool and constraint parameters to construct a mixed-integer programming model. The search module 403 is used to input the mixed-integer programming model into a preset mathematical solver to find the final task execution scheme.

[0069] In some embodiments, the preprocessing module 402 includes: The splitting unit is used to split a single landing point in the task pool into multiple virtual landing points, and to number the starting landing point of each virtual landing point to obtain a set of virtual locations; An introduction unit is used to introduce a virtual task for each virtual landing point and to number each virtual task to obtain a set of virtual tasks; The first numbering unit is used to renumber the nodes of the original multiple real task geographical locations in the task pool to obtain a set of real locations. The second numbering unit is used to renumber all the real tasks to be planned in the task pool to obtain the set of real tasks. The building unit is used to construct a mixed-integer programming model based on the set of virtual locations, the set of virtual tasks, the set of real locations, the set of real tasks, and constraint parameters.

[0070] In some embodiments, the searching module 403 includes: The first solving unit is used to input the mixed-integer programming model into a preset mathematical solver and use the unit utility maximization task insertion algorithm to find the final task execution scheme; or The second solving unit is used to input the mixed-integer programming model into a preset mathematical solver and use an execution-first-return algorithm to find the final task execution scheme; or The third solving unit is used to input the mixed integer programming model into the preset mathematical solver and use an adaptive fusion strategy to dynamically coordinate the unit utility maximization task insertion algorithm and the execution priority return algorithm to find the final task execution scheme.

[0071] In some embodiments, the first solving unit includes: Determine if all tasks are currently incomplete. If none are, generate a blank task execution plan. Otherwise, obtain the current task completion status to generate a current task execution plan for completed tasks. Iterate through all candidate locations for any task in the mandatory task set, attempting to insert the current task into all possible positions in the current task execution plan. Check if the current position satisfies the constraint parameters. If it does, calculate the unit utility obtained by inserting the current task, executed at all candidate locations, into all possible positions, and select the maximum unit utility. Based on the maximum unit utility, insert the current task, executed at a certain candidate location, into a possible position in the current task execution plan to obtain a new task execution plan, and remove the current task from the mandatory task set. Otherwise, skip the current task. The aforementioned process is executed iteratively until the set of required tasks is empty or no new tasks can be inserted. The algorithm checks if the set of required tasks is empty. If it is not empty, it indicates that no feasible solution was found. Otherwise, it iterates through all candidate locations for any task in the set of optional tasks, attempting to insert the current task into all possible positions in the current task execution plan. It then checks if the current position satisfies the constraint parameters. If it does, it calculates the unit utility obtained by inserting the current task, which is executed at all candidate locations, into all possible positions, and selects the maximum unit utility. Based on the maximum unit utility, it inserts the current task, which is executed at a certain candidate location, into a possible position in the current task execution plan to obtain a new task execution plan. The current task is then removed from the set of optional tasks. Otherwise, the current task is skipped. The aforementioned process is repeated iteratively until the set of selectable tasks is empty or no new tasks can be inserted, in order to obtain the final task execution plan.

[0072] In some embodiments, the second solving unit includes: Determine if all tasks are currently incomplete. If none are, generate a blank task execution plan. Otherwise, obtain the current task completion status to generate a current task execution plan for completed tasks. At the end of all unfinished stages in the current task execution plan, insert a task that directly returns to the landing point to obtain a new task execution plan; Check whether the new task execution plan meets the constraint parameters. If it does not, indicate that no feasible solution was found. Otherwise, use the new task execution plan as the final task execution plan.

[0073] In some embodiments, the third solving unit includes: The mixed integer programming model is input into a preset mathematical solver, and an adaptive fusion strategy is used to dynamically coordinate the unit utility maximization task insertion algorithm and the execution priority return algorithm to solve multiple feasible task execution schemes. Multiple feasible task execution plans are evaluated and weighted in a multidimensional manner to determine the final task execution plan.

[0074] It should be noted that the foregoing explanation of the multi-scenario, multi-stage mission planning method embodiment for manned lunar activities also applies to the multi-scenario, multi-stage mission planning device for manned lunar activities in this embodiment, and will not be repeated here.

[0075] The multi-scenario, multi-stage mission planning device for manned lunar activities proposed in this embodiment of the invention addresses various scenarios such as normal planning optimization, emergency scheme adjustment, and emergency situation return. It employs mathematical models and algorithms to plan a multi-stage mission planning scheme in one go, and possesses compatibility with other software and hardware platforms. Specifically, the hybrid integer programming model can express and handle multiple round trips to landing sites, multiple alternative point sampling, mandatory and optional task processing, maximum detection distance requirements, precedence constraints, and adherence to safe return constraints within a single mathematical model. It utilizes a fusion-based solution algorithm, including mathematical solvers, unit utility maximization task insertion algorithms, and priority return algorithms, and automatically integrates multiple solution algorithms according to scenario requirements to obtain the best manned lunar activity mission planning scheme. Furthermore, it can be equipped with supporting software and hardware interfaces, software environments, and hardware carriers to support the implementation of the aforementioned models and algorithms, thus ensuring compatibility with other software and hardware platforms.

[0076] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.

[0077] The electronic device may include: a memory 501, a processor 502, and a computer program stored on the memory 501 and capable of running on the processor 502.

[0078] When the processor 502 executes the program, it implements the multi-scenario, multi-stage mission planning method for manned lunar activities provided in the above embodiments.

[0079] Furthermore, electronic devices also include: Communication interface 503 is used for communication between memory 501 and processor 502.

[0080] The memory 501 is used to store computer programs that can run on the processor 502.

[0081] Memory 501 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0082] If the memory 501, processor 502, and communication interface 503 are implemented independently, then the communication interface 503, memory 501, and processor 502 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, Figure 5 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0083] Optionally, in a specific implementation, if the memory 501, processor 502, and communication interface 503 are integrated on a single chip, then the memory 501, processor 502, and communication interface 503 can communicate with each other through an internal interface.

[0084] Processor 502 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention.

[0085] This invention also provides a computer program product, which, when executed by a processor, implements the above-described multi-scenario, multi-stage mission planning method for manned lunar activities.

[0086] This invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described multi-scenario, multi-stage mission planning method for manned lunar surface activities.

[0087] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0088] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this invention, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0089] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of preferred embodiments of the invention includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which embodiments of the invention pertain.

[0090] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0091] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0092] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0093] Furthermore, the functional units in the various embodiments of the present invention can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0094] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

Claims

1. A multi-scenario, multi-stage mission planning method for manned lunar activities, characterized in that, Includes the following steps: Multiple unplanned tasks for manned lunar activities are constructed into a task pool, and the constraint parameters corresponding to the task pool are set. The task pool and the constraint parameters are preprocessed to construct a mixed integer programming model; The mixed integer programming model is input into a preset mathematical solver to find the final task execution scheme.

2. The multi-scenario, multi-stage mission planning method for manned lunar activities according to claim 1, characterized in that, The preprocessing of the task pool and the constraint parameters to construct a mixed-integer programming model includes: The single landing point in the task pool is split into multiple virtual landing points, and the starting landing point of each virtual landing point is numbered to obtain a set of virtual locations; A virtual task is introduced for each virtual landing point, and each virtual task is numbered to obtain a set of virtual tasks; The nodes of the original multiple real task geographical locations in the task pool are renumbered to obtain a set of real locations; All real tasks to be planned in the task pool are renumbered to obtain a set of real tasks; The mixed-integer programming model is constructed based on the set of virtual locations, the set of virtual tasks, the set of real locations, the set of real tasks, and the constraint parameters.

3. The multi-scenario, multi-stage mission planning method for manned lunar activities according to claim 1, characterized in that, The step of inputting the mixed-integer programming model into a preset mathematical solver to find the final task execution scheme includes: The mixed-integer programming model is input into the preset mathematical solver, and the final task execution scheme is found using the unit utility maximization task insertion algorithm; or The mixed-integer programming model is input into the preset mathematical solver, and the execution-first-return algorithm is used to find the final task execution scheme; or The mixed integer programming model is input into the preset mathematical solver, and the unit utility maximization task insertion algorithm and the execution priority return algorithm are dynamically coordinated using an adaptive fusion strategy to find the final task execution scheme.

4. The multi-scenario, multi-stage mission planning method for manned lunar activities according to claim 3, characterized in that, The step of inputting the mixed-integer programming model into the preset mathematical solver and using the unit utility maximization task insertion algorithm to find the final task execution scheme includes: Determine if all tasks are currently incomplete. If none are, generate a blank task execution plan. Otherwise, obtain the current task completion status to generate a current task execution plan for completed tasks. Iterate through all candidate locations for any task in the mandatory task set, attempting to insert the current task into all possible positions in the current task execution plan, and sequentially determine whether the current position satisfies the constraint parameters. If it does, calculate the unit utility obtained by inserting the current task executed in all candidate locations into all possible positions, select the maximum unit utility, and insert the current task executed in a certain candidate location into a certain possible position in the current task execution plan based on the maximum unit utility to obtain a new task execution plan. Remove the current task from the mandatory task set; otherwise, skip the current task. The aforementioned process is executed iteratively until the set of required tasks is empty or no new tasks can be inserted. Determine if the set of mandatory tasks is empty. If the set of mandatory tasks is not empty, indicate that no feasible solution was found. Otherwise, iterate through all candidate locations for any task in the set of optional tasks, attempting to insert the current task into all possible positions in the current task execution plan. Sequentially determine if the current position satisfies the constraint parameters. If satisfied, calculate the unit utility obtained by inserting the current task executed at all candidate locations into all possible positions, select the maximum unit utility, and insert the current task executed at a certain candidate location into a possible position in the current task execution plan based on the maximum unit utility to obtain a new task execution plan. Remove the current task from the set of optional tasks. Otherwise, skip the current task. The aforementioned process is executed iteratively until the set of optional tasks is empty or no new tasks can be inserted, in order to obtain the final task execution plan.

5. The multi-scenario, multi-stage mission planning method for manned lunar activities according to claim 3, characterized in that, The step of inputting the mixed-integer programming model into the preset mathematical solver and using the execution-first-return algorithm to find the final task execution scheme includes: Determine if all tasks are currently incomplete. If none are, generate a blank task execution plan. Otherwise, obtain the current task completion status to generate a current task execution plan for completed tasks. At the end of all unfinished stages in the current task execution plan, insert a task that directly returns to the landing point to obtain a new task execution plan; Check whether the new task execution plan satisfies the constraint parameters. If it does not, indicate that no feasible solution was found. Otherwise, use the new task execution plan as the final task execution plan.

6. The multi-scenario, multi-stage mission planning method for manned lunar activities according to claim 3, characterized in that, The step of inputting the mixed-integer programming model into the preset mathematical solver and using an adaptive fusion strategy to dynamically coordinate the unit utility maximization task insertion algorithm and the execution priority return algorithm to find the final task execution scheme includes: The mixed integer programming model is input into the preset mathematical solver, and the unit utility maximization task insertion algorithm and the execution priority return algorithm are dynamically coordinated by the adaptive fusion strategy to solve multiple feasible task execution schemes. The multiple feasible task execution schemes are evaluated and weighted in a multidimensional manner to determine the final task execution scheme.

7. A multi-scenario, multi-stage mission planning device for manned lunar activities, characterized in that, include: The construction module is used to build a task pool from multiple unplanned tasks for manned lunar activities and to set the constraint parameters corresponding to the task pool. A preprocessing module is used to preprocess the task pool and the constraint parameters to construct a mixed integer programming model; The search module is used to input the mixed integer programming model into a preset mathematical solver to find the final task execution scheme.

8. An electronic device, characterized in that, include: The memory, the processor, and the computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the multi-scenario, multi-stage mission planning method for manned lunar activities as described in any one of claims 1-6.

9. A computer program product, characterized in that, When the computer program / instruction is executed by the processor, it implements the multi-scenario, multi-stage mission planning method for manned lunar activities as described in any one of claims 1-6.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the multi-scenario, multi-stage mission planning method for manned lunar activities as described in any one of claims 1-6.

Images