A method for task planning of a giant remote sensing satellite cluster based on atomic task decomposition

Abstract

This application discloses a method for planning large-scale remote sensing constellation missions based on atomic task decomposition, relating to the field of remote sensing satellite mission planning technology. The method includes: acquiring user-submitted observation tasks and determining the observation mode of the tasks; performing atomic task decomposition to obtain a corresponding set of subtasks; determining constraints and an objective function based on the subtask set; minimizing the objective function to obtain an optimal mission observation scheme; and allocating each subtask to a corresponding remote sensing satellite based on the optimal mission observation scheme to execute the observation task. This application, by refining complex multi-satellite collaborative observation tasks into operable atomic tasks, reduces the complexity of the problem, optimizes the allocation process of satellite resources, achieves efficient integration and execution of dynamic user objectives and autonomous observation objectives, and improves the adaptability and response speed of remote sensing satellites when facing complex observation needs, thereby adapting to rapid changes in user requirements.

Description

Technical Field

[0001] This application relates to the field of mission planning technology for remote sensing satellites, and in particular to a method for planning large-scale remote sensing constellations based on atomic mission decomposition. Background Technology

[0002] With the rapid advancement of remote sensing technology, the observation tasks proposed by users have become increasingly complex and diverse. By calling on multiple satellites in a giant remote sensing constellation to work together, the observation needs of complex tasks such as regional search, multi-angle collaboration, and multi-payload confirmation can be met. In order to effectively utilize the satellite resources of the giant remote sensing constellation, efficient task planning for the giant remote sensing constellation is required.

[0003] Currently, when planning missions for giant remote sensing constellations, considering the simultaneous occurrence of multiple complex targets, it is necessary to comprehensively consider mission priorities, resource allocation, and scheduling strategies. Mathematical programming and intelligent optimization algorithms are typically used to calculate collaborative strategies, generating global static or periodic scheduling schemes to maximize overall resource utilization and mission completion efficiency.

[0004] However, relying solely on mathematical programming and intelligent optimization algorithms to calculate collaborative strategies in related technologies faces significant challenges, including but not limited to: First, centralized architectures suffer from high solution complexity when dealing with massive satellite scales and highly coupled tasks; second, user requests exhibit significant dynamic randomness, making it difficult for existing planning methods to respond quickly; third, the lack of efficient conflict resolution mechanisms means that the insertion of high-priority new tasks often causes severe global disturbances to the original plan, resulting in insufficient dynamic adjustment capabilities; and fourth, existing methods often treat complex tasks as a whole, lacking fine-grained atomic decomposition mechanisms, making it difficult to flexibly adapt to the needs of high-concurrency and high-timeliness applications, thus limiting the overall response timeliness and flexibility of remote sensing services.

[0005] Therefore, there is currently a lack of a method for achieving highly timely and dynamic mission planning based on giant remote sensing constellations. Summary of the Invention

[0006] This application provides a method for planning giant remote sensing constellation missions based on atomic task decomposition, in order to overcome the shortcomings of the aforementioned related technologies. The technical solution is as follows:

[0007] In a first aspect, this application provides a method for planning giant remote sensing constellation missions based on atomic task decomposition, the method comprising:

[0008] Obtain the observation task submitted by the user and determine the observation mode of the observation task;

[0009] Based on the observation mode, the observation task is decomposed into atomic tasks to obtain a corresponding set of subtasks;

[0010] The constraints and objective function are determined by combining the set of subtasks;

[0011] The optimal mission observation scheme is obtained by minimizing the objective function using the simulated annealing method.

[0012] Based on the optimal mission observation scheme, each subtask in the subtask set is assigned to a corresponding remote sensing satellite to perform the observation mission.

[0013] In one alternative embodiment of the first aspect, determining the observation mode for the observation task includes:

[0014] Semantic analysis is performed on the observation task to extract the corresponding observation requirements; the observation requirements include observation area requirements, time range requirements, and payload requirements.

[0015] The observation mode corresponding to the observation task is determined based on the geographical area range corresponding to the observation area requirement, the observation time interval corresponding to the time range requirement, and the load type corresponding to the load requirement.

[0016] In one alternative embodiment of the first aspect, after the corresponding observation requirements are extracted, the method further includes:

[0017] If the geographical area range corresponding to the observation area requirement is less than or equal to a preset geographical area range threshold, and the observation time interval corresponding to the time range requirement is less than or equal to an observation time length threshold, and the load requirement includes at least two load types, then the observation mode of the observation task is determined to be a multimodal collaborative observation mode.

[0018] The atomic task decomposition of the observation task based on the observation mode, resulting in a corresponding set of subtasks, includes:

[0019] The observation task is decomposed into atomic tasks according to the multimodal collaborative observation mode to determine each type of payload corresponding to the payload requirement;

[0020] The observation task is decomposed into multiple subtasks with the same geographical area, the same observation time interval, and different payload types, generating a subtask set containing each subtask.

[0021] In one alternative embodiment of the first aspect, after the corresponding observation requirements are extracted, the method further includes:

[0022] If the geographical area range corresponding to the observation area requirement is greater than the preset geographical area range threshold, and the observation time interval corresponding to the time range requirement is less than or equal to the observation time length threshold, and the load requirement includes a single load type, then the observation mode of the observation task is determined to be the spatial continuous observation mode.

[0023] The atomic task decomposition of the observation task based on the observation mode, resulting in a corresponding set of subtasks, includes:

[0024] The observation task is decomposed into atomic tasks according to the continuous space observation mode, and the geographical area is divided into multiple sub-regions; wherein the area of ​​each sub-region is less than or equal to the area covered by a remote sensing satellite in one pass.

[0025] The observation task is decomposed into sub-tasks that observe multiple sub-regions based on the same payload type within the same observation time interval, and a sub-task set containing each sub-task is generated.

[0026] In one alternative embodiment of the first aspect, after the corresponding observation requirements are extracted, the method further includes:

[0027] If the geographical area range corresponding to the observation area requirement is less than or equal to the preset geographical area range threshold, and the time range requirement includes observation time intervals greater than the observation time length threshold and / or multiple periodic observation time intervals, and the load requirement includes one or more load types, then the observation mode of the observation task is determined to be the time continuous observation mode.

[0028] The atomic task decomposition of the observation task based on the observation mode, resulting in a corresponding set of subtasks, includes:

[0029] The observation task is decomposed into atomic tasks according to the continuous time observation mode, the time range requirement is divided into multiple sub-time intervals, and the load type corresponding to each sub-time interval is determined.

[0030] The observation task is decomposed into sub-tasks that observe the same geographical area within each sub-time interval based on a defined payload type, generating a sub-task set containing each sub-task.

[0031] In one alternative embodiment of the first aspect, after the corresponding observation requirements are extracted, the method further includes:

[0032] If the observation target is determined to be a moving target based on the observation requirements, then the observation mode of the observation task is determined to be a spatiotemporal continuous observation mode.

[0033] The atomic task decomposition of the observation task based on the observation mode, resulting in a corresponding set of subtasks, includes:

[0034] The observation task is decomposed into atomic tasks according to the spatiotemporal continuous observation mode to obtain the motion prior information of the moving target; the motion prior information includes initial position, initial velocity and initial direction;

[0035] Based on the prior motion information, the estimated path of the moving target in various future time periods is predicted, and multiple adjacent prediction regions are obtained by decomposing the estimated path, and the prediction time interval corresponding to each prediction region is determined.

[0036] The observation task is decomposed into sub-tasks based on a determined payload type and in chronological order, which observe moving targets in the corresponding prediction area within each prediction time interval, and a sub-task set containing each sub-task is generated.

[0037] In one alternative to the first aspect, determining the constraints and objective function by combining the set of subtasks includes:

[0038] Based on the time range requirements of each subtask in the subtask set, the observation time window constraint for remote sensing satellite to perform subtasks is constructed; based on the observation area requirements of each subtask, the cloud coverage constraint within the corresponding geographical area is constructed; and based on the payload requirements of each subtask, the satellite payload type constraint is constructed.

[0039] Based on the sum of task priorities, the sum of observation quality, and the observation start time of the sub-task set, an energy function is constructed as the objective function.

[0040] The method of minimizing the objective function based on simulated annealing to obtain the optimal task observation scheme includes:

[0041] Remote sensing satellites for observation tasks are selected from the giant remote sensing constellation to construct a random observation scheme that meets the constraints of the observation time window, the cloud coverage rate, and the satellite payload type.

[0042] At the current annealing temperature, with the random observation scheme as the target observation scheme, a neighborhood observation scheme for the target observation scheme is generated based on the neighborhood function;

[0043] Calculate the difference between the objective functions of the target observation scheme and the domain observation scheme, respectively;

[0044] If the difference is less than 0, then the domain observation scheme is taken as the new target observation scheme;

[0045] Otherwise, the domain observation scheme is used as the new target observation scheme with a preset probability.

[0046] The annealing temperature is updated based on a preset cooling rate;

[0047] If the updated annealing temperature is lower than the temperature threshold, the iteration stops, and the target annealing scheme is output as the optimal task observation scheme.

[0048] Otherwise, proceed to the step of generating the domain observation scheme based on the domain function.

[0049] Secondly, this application also provides a giant remote sensing constellation mission planning device based on atomic mission decomposition, comprising:

[0050] The observation task acquisition module is used to acquire observation tasks submitted by users and to determine the observation mode of the observation tasks.

[0051] The atomic task decomposition module is used to decompose the observation task into atomic tasks based on the observation mode to obtain a corresponding set of subtasks.

[0052] The task planning module is used to determine the constraints and objective function by combining the set of subtasks;

[0053] The task planning module is also used to minimize the objective function based on the simulated annealing method to obtain the optimal task observation scheme;

[0054] The mission planning module is also used to assign each subtask in the subtask set to a corresponding remote sensing satellite based on the optimal mission observation scheme, so as to execute the observation mission.

[0055] Thirdly, this application also 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 method provided by the first aspect of this application or any implementation thereof.

[0056] Fourthly, this application also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method provided by the first aspect of this application or any implementation thereof.

[0057] The beneficial effects of the technical solutions provided in some embodiments of this application include at least the following:

[0058] This application provides a method for planning large-scale remote sensing constellation missions based on atomic task decomposition. By refining complex multi-satellite collaborative observation tasks into operable atomic tasks, it optimizes the allocation process of satellite resources, achieves efficient integration and execution of dynamic user objectives and autonomous observation objectives, and improves the adaptability and response speed of remote sensing satellites in the face of complex observation needs. In this way, complex observation tasks and objectives can be efficiently decomposed, reducing the complexity of the problem and thus adapting to rapid changes in user needs, thereby improving the timeliness of remote sensing services and better meeting the actual application needs of users. Attached Figure Description

[0059] To more clearly illustrate the technical solutions in this application or related technologies, the drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0060] Figure 1 This is a flowchart illustrating a method for planning giant remote sensing constellation missions based on atomic task decomposition, as provided in an embodiment of this application.

[0061] Figure 2 This is a schematic diagram of the structure of a giant remote sensing constellation mission planning device based on atomic task decomposition provided in an embodiment of this application;

[0062] Figure 3 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0063] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0064] The terms "comprising" and "having," and any variations thereof, in the specification, claims, and accompanying drawings of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or modules is not limited to the steps or modules listed, but may optionally include steps or modules not listed, or may optionally include other steps or modules inherent to such process, method, product, or apparatus.

[0065] It should be noted that the terms "first" and "second" used in this application are merely to distinguish similar objects and do not represent a specific ordering of the objects. It is understood that "first" and "second" can be interchanged in a specific order or sequence where permitted. It should be understood that the objects distinguished by "first" and "second" can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in an order other than those described or illustrated herein.

[0066] The present application will now be described in detail with reference to specific embodiments.

[0067] Next, combine Figure 1 This application introduces a method for planning giant remote sensing constellation missions based on atomic task decomposition, as provided in its embodiments. For details, please refer to... Figure 1 , Figure 1 This illustration shows a flowchart of a giant remote sensing constellation mission planning method based on atomic mission decomposition provided in an embodiment of this application. Figure 1 As shown, the method includes the following steps:

[0068] S101, Obtain the observation task submitted by the user and determine the observation mode of the observation task;

[0069] S102, Based on the observation mode, the observation task is decomposed into atomic tasks to obtain a corresponding set of subtasks;

[0070] S103, determine the constraints and objective function based on the set of subtasks;

[0071] S104, Minimize the objective function based on the simulated annealing method to obtain the optimal mission observation scheme;

[0072] S105, based on the optimal mission observation scheme, each sub-task in the sub-task set is assigned to the corresponding remote sensing satellite to perform the observation mission.

[0073] Specifically, in S101, users can submit observation task requests through electronic devices, and set observation targets and input observation requirements through I / O devices. Observation requirements include, but are not limited to, observation area requirements, time range requirements, and payload requirements.

[0074] It should be noted that the observation target can be a point target or a regional target. The point target can be a stationary or moving target, and the observation area can be defined by delineating a certain geographical area centered on the point target.

[0075] Specifically, the observation area requirements can be defined by setting the coordinates of the observation area. For example, the rectangular area enclosed by observation coordinate points 1, 2, 3, and 4 can be set as the observation area. The time range requirements can be set by setting one or more observation time intervals. Payload requirements can be understood as the requirements for the observation characteristics of remote sensing satellites, including but not limited to requirements for parameters such as sensor type (e.g., band, resolution) and satellite attitude (e.g., observation angle).

[0076] In some embodiments, in S101, after obtaining the observation task submitted by the user, semantic analysis can be performed on the observation task to extract the corresponding observation requirements; the observation requirements include observation area requirements, time range requirements, and payload requirements.

[0077] Understandably, semantic analysis can be used to parse the geographic area range corresponding to the observation area requirement, the observation time interval corresponding to the time range requirement, and the load type corresponding to the load requirement. Then, based on the specific content of the parsed geographic area range, observation time interval, and load type, the observation mode corresponding to the observation task can be determined.

[0078] For example, by using a pre-defined mapping table, given the combination of parameters corresponding to each observation mode, the mapping relationship between the observation mode and the observation task can be determined based on the size of the geographical area, the span of the observation time interval, and the number of payload types. Thus, the observation mode to be used can be easily determined based on the mapping relationship between the two.

[0079] In some embodiments, determining the observation mode of the observation task may include the following process:

[0080] If the geographical area corresponding to the observation area requirement is less than or equal to a preset geographical area threshold, and the observation time interval corresponding to the time range requirement is less than or equal to an observation time length threshold, and the payload requirement includes at least two payload types, then the observation mode of the observation task is determined to be a multimodal collaborative observation mode, indicating that the current observation task requires remote sensing satellites equipped with different sensors to perform observation tasks with the same geographical area and the same observation time interval.

[0081] The atomic task decomposition of the observation task based on the observation mode, resulting in a corresponding set of subtasks, includes:

[0082] The observation task is decomposed into atomic tasks according to the multimodal collaborative observation mode to determine each type of payload corresponding to the payload requirement;

[0083] The observation task is decomposed into multiple subtasks with the same geographical area, the same observation time interval, and different payload types, generating a subtask set containing each subtask.

[0084] This can be understood as decomposing the observation task into sub-tasks based on different payload types that observe the same geographical area within the same observation time interval, generating a sub-task set containing each sub-task.

[0085] In some embodiments, determining the observation mode of the observation task may include the following process:

[0086] After extracting the corresponding observation requirements, if the geographical area range corresponding to the observation area requirement is greater than the preset geographical area range threshold, and the observation time interval corresponding to the time range requirement is less than or equal to the observation time length threshold, and the load requirement includes a single load type, then the observation mode of the observation task is determined to be the spatial continuous observation mode.

[0087] The atomic task decomposition of the observation task based on the observation mode, resulting in a corresponding set of subtasks, includes:

[0088] The observation task is decomposed into atomic tasks according to the continuous space observation mode, and the geographical area is divided into multiple sub-regions; wherein the area of ​​each sub-region is less than or equal to the area covered by a remote sensing satellite in one pass.

[0089] The observation task is decomposed into sub-tasks that observe multiple sub-regions based on the same payload type within the same observation time interval, and a sub-task set containing each sub-task is generated.

[0090] In some embodiments, determining the observation mode of the observation task may include the following process:

[0091] After extracting the corresponding observation requirements, if the geographical area range corresponding to the observation area requirement is less than or equal to a preset geographical area range threshold, and the time range requirement includes an observation time interval greater than the observation time length threshold and / or multiple periodic observation time intervals, and the load requirement includes one or more load types, then the observation mode of the observation task is determined to be a time-continuous observation mode.

[0092] Specifically, in the continuous time observation mode, it is necessary to perform continuous observations over a relatively long period of time or periodic observations over multiple time intervals on the observation range. Different load types can be set for each time interval.

[0093] The atomic task decomposition of the observation task based on the observation mode, resulting in a corresponding set of subtasks, includes:

[0094] The observation task is decomposed into atomic tasks according to the continuous time observation mode, the time range requirement is divided into multiple sub-time intervals, and the load type corresponding to each sub-time interval is determined.

[0095] The observation task is decomposed into sub-tasks that observe the same geographical area within each sub-time interval based on a defined payload type, generating a sub-task set containing each sub-task.

[0096] In some embodiments, determining the observation mode of the observation task may include the following process:

[0097] After extracting the corresponding observation requirements, if the observation target is determined to be a moving target based on the observation requirements, then the observation mode of the observation task is determined to be a spatiotemporal continuous observation mode.

[0098] The atomic task decomposition of the observation task based on the observation mode, resulting in a corresponding set of subtasks, includes:

[0099] The observation task is decomposed into atomic tasks according to the spatiotemporal continuous observation mode to obtain the motion prior information of the moving target; the motion prior information includes initial position, initial velocity and initial direction.

[0100] Specifically, a motion prediction model can be constructed based on prior motion information, as follows:

[0101] ;

[0102] Where, pos t Let pos0 be the predicted position at time t, v be the initial velocity, and θ be the initial direction.

[0103] Furthermore, predicting the estimated path of the moving target in various future time periods based on the prior motion information is equivalent to determining the predicted position of the moving target at various future times based on the motion prediction model, thus obtaining the estimated path.

[0104] Then, multiple adjacent prediction regions can be obtained based on the estimated path decomposition, and the prediction time interval corresponding to each prediction region can be determined based on the time interval of the moving target in the corresponding prediction region.

[0105] Therefore, the observation task can be decomposed into sub-tasks that observe moving targets within the corresponding prediction area in chronological order according to a determined payload type within each prediction time interval, generating a sub-task set containing each sub-task, and thus forming a continuous chain of observation sub-tasks, which can be represented in the following form:

[0106] ;

[0107] Where Ti represents the i-th subtask, including the observation time interval [t] start ,t end Predicted position pos ti And payload type Cj, where the subscript j indicates satellite j.

[0108] It should be noted that for the spatiotemporal continuous observation mode of moving targets, observations can be performed sequentially according to the time order of each sub-task. The motion prediction model can be updated in real time based on the changes in the position, velocity, and direction of the moving target observed by the sub-task. The estimated path can be recalculated and decomposed into new sub-tasks based on the updated motion model.

[0109] The step of determining the constraints and objective function by combining the set of subtasks includes:

[0110] Based on the time range requirements of each subtask in the set of subtasks, the observation time window constraints for remote sensing satellites to perform subtasks are constructed; based on the observation area requirements of each subtask, the cloud coverage constraints within the corresponding geographical area are constructed; and based on the payload requirements of each subtask, the satellite payload type constraints are constructed.

[0111] It should be noted that the satellite's observation window refers to the time interval during which the satellite can observe ground targets within a specific period of time.

[0112] Specifically, we can assume an assumed observation scheme for each satellite during observation, exclude assumed observation schemes that do not meet the constraints, and in each assumed observation scheme, assign each subtask in the subtask set to a specific satellite and time window. A satellite can perform observations of one or more subtasks.

[0113] Specifically, the observation time window constraint includes the following constraints:

[0114] ①Time window constraint

[0115] The time window constraint ensures that the geographical area of ​​the sub-task and the corresponding observation time interval must fall within the satellite's observation time window when observation is carried out, thereby ensuring the feasibility of the observation.

[0116] The time window constraint is defined as the requirement that a valid time window must be available when performing an observation task; that is, the set of valid time windows for an observation task cannot be empty. The formula is as follows:

[0117] ;

[0118] in, This indicates that the user submitted a total of Each observation task may include multiple observation targets (each observation target is equivalent to a sub-task). Indicates the first The number of targets in the observation task uploaded this time; Indicates the total number of satellites; Indicates the first The satellite to the first The visible time window of each subtask, that is, for any subtask, there exists a satellite such that the window is not empty.

[0119] It should be noted that users can specify different numbers of observation targets in each observation task they submit, such as uploading 5 targets at point 1 and 3 targets at point 2. This application embodiment does not limit this.

[0120] The effective time window for each satellite to each sub-task can be obtained by using the time window constraints described above, and the assumed observation scheme corresponding to the effective time window is retained.

[0121] ②Observation start time constraint

[0122] Ensure that the assumed observation schemes meet the user-specified time range requirements. Specifically, the task start time for each assumed observation scheme must be earlier than the specified observation start time, and the task end time must be later than the specified observation end time, as shown in the following formula:

[0123] ;

[0124] ;

[0125] in, Indicates the first The satellite to the first The number of valid time windows for each target uploaded in this session; Indicates the first The satellite to the first The first upload of each target The observation start time for each effective time window; Indicates the latest required start time for observation; It indicates that it is the first The satellite to the first The first upload target The observation end time of each effective time window; Indicates the earliest required end time of observation.

[0126] For example, if a user uploads 5 targets for the first time, the effective time window for the j-th satellite to capture images of these targets is 10. That is, the satellite can capture images of the targets within these 10 time windows.

[0127] The above-mentioned observation start time constraint eliminates hypothetical observation schemes where the observation start time and observation end time do not meet the time range requirements.

[0128] ③ Satellite uniqueness constraint

[0129] This ensures that the satellite performs only one subtask observation at a time, avoiding the infeasibility of simultaneously performing multiple subtasks. This constraint requires sorting the start times of all visible time windows for the same satellite and constraining that the end time of the observation in the preceding time window must be later than the start time of the observation in the following time window, as shown in the following formula:

[0130] ;

[0131] in, This represents the start time of observation in the time window preceding the nth time window.

[0132] In this way, hypothetical observation schemes that would result in time conflicts can be eliminated.

[0133] ④ Constraint on the uniqueness of the observation target

[0134] Limiting the number of observations for the same subtask prevents duplicate observations and ensures efficient resource allocation. This constraint is defined as allowing the same subtask to occur only once in the observation scheme, as shown in the following formula:

[0135] ;

[0136] in, Indicates all satellites to the first The total number of valid time windows for each uploaded observation task; and This represents any two distinct time windows; Indicates the first The first observation task uploaded The observation targets corresponding to each time window; Indicates the first The first observation task uploaded The observation target corresponding to each time window.

[0137] Furthermore, based on the observation area requirements of each sub-task, cloud coverage constraints within the corresponding geographical area can be constructed, as shown in the following formula:

[0138] ;

[0139] in, Indicates the first Cloud coverage of each observation target; This indicates the maximum cloud cover that an optical satellite can tolerate for observation purposes.

[0140] In addition, the satellite can be screened based on the type of payload it carries, including but not limited to the type of sensor it carries, the observation band, the resolution, the attitude angle relative to the ground observation target, and the orbital parameters. This application does not limit this.

[0141] In addition to the constraints mentioned above, when formulating a multi-satellite collaborative observation scheme, it is also necessary to consider the satellite's storage capacity and satellite-to-ground transmission capacity to ensure that each satellite in the observation scheme can conduct normal observations of one or more sub-tasks planned for it, and avoid satellite reset due to storage or energy limitations, which would lead to mission observation failure.

[0142] Multiple observation schemes that meet the requirements can be obtained by filtering through the above constraints.

[0143] In some embodiments, the energy function can be constructed as the objective function based on the sum of task priorities, the sum of observation quality, and the observation start time of the set of subtasks, including:

[0144] Calculate the negative value based on the sum of task priorities. The negative value of the sum of observation quality The sum of the total observation start times The energy function is constructed;

[0145] in, Let be the decision variable, representing the th Is the goal determined by the first...? The satellite is planned for observation; specifically, when the first... The first goal is achieved by the... When observing from a satellite, ,otherwise, .

[0146] The combined benefits of maximizing the sum of task priorities, maximizing the sum of observation quality, and minimizing observation start time are achieved by minimizing the energy function, using the following formula:

[0147] ;

[0148] in, Let S be the energy function, and S represent the observation scheme. For the first Task priority of each subtask For the first The satellite observed the first The observation quality of each sub-task For the first The satellite observed the first The start time of observation for each sub-task Additional energy is added based on constraint violations.

[0149] In some embodiments, the sum of task priorities, the sum of observation quality, and the total observation start time in the observation scheme can be calculated based on the following formulas, including:

[0150] In remote sensing satellite observation services, due to the uniqueness constraints of satellite resources and observation targets, time window conflicts may occur during the multi-satellite collaborative optimization scheduling process. Observation schemes that eliminate time window conflicts can be eliminated through a time window priority selection mechanism, specifically including:

[0151] When an observation target has multiple available time windows, the first step should be to examine whether these windows belong to the same satellite.

[0152] If different time windows belong to the same satellite, the earliest start time window is selected first to maximize observation opportunities and acquire data as early as possible. The formula for calculating the minimum sum of observation start times is as follows:

[0153] ;

[0154] In some embodiments, considering that different time windows belong to different satellites, it is necessary to further evaluate the observation quality of each satellite and determine the most suitable time window according to the principle of the earliest start time. The formula for maximizing the sum of observation quality is as follows:

[0155] ;

[0156] The maximum total observation quality can be calculated using the above formula.

[0157] In some embodiments, for situations where time windows may overlap when a single satellite observes multiple targets simultaneously, the selection strategy is based on task priority and observation start time. When multiple observation tasks compete for the same satellite resource, tasks with higher priority should be executed first. The formula for calculating the maximum sum of observation priorities is as follows:

[0158] ;

[0159] The maximum sum of observation priorities can be calculated using the above formula.

[0160] It should be noted that the design of these constraints and objective functions effectively solves the complex scheduling problem among multiple satellites and multiple targets, thereby improving the efficiency of satellite observation services and the utilization of satellite resources. In particular, by introducing restrictions on observation time and cloud coverage, the adaptability of the observation scheme to actual observation conditions is enhanced, ensuring that the acquired remote sensing data meets the user's data quality requirements.

[0161] Further, the execution of step S104, which involves minimizing the objective function based on simulated annealing to obtain the optimal task observation scheme, includes:

[0162] Remote sensing satellites for observation tasks are selected from the giant remote sensing constellation, and a random observation scheme S that conforms to the observation time window constraint, the cloud coverage constraint, and the satellite payload type constraint is constructed.

[0163] At the current annealing temperature Given a cooling rate Using the aforementioned random observation scheme as the target observation scheme, based on the neighborhood function A domain observation scheme for generating the target observation scheme. ′;

[0164] Calculate the difference between the objective functions of the target observation scheme and the domain observation scheme respectively, using the formula:

[0165] ;

[0166] If the difference If it is less than 0, then the domain observation scheme will be... As a new target observation scheme;

[0167] Otherwise, the domain observation scheme is used as the new target observation scheme with a preset probability.

[0168] Specifically, a preset probability can be taken as... / ;

[0169] The annealing temperature is updated based on a preset cooling rate, using the following formula:

[0170] ← ;

[0171] If the updated annealing temperature is lower than the temperature threshold, the iteration stops, and the target annealing scheme is output as the optimal task observation scheme.

[0172] Otherwise, proceed to the step of generating the domain observation scheme based on the domain function.

[0173] By following the steps above, the optimal mission observation scheme can be obtained.

[0174] In this way, the simulated annealing algorithm can be effectively applied to solve complex multi-satellite collaborative observation problems, optimize resource allocation, and ensure comprehensive optimization of observation task priority, observation quality, and observation time.

[0175] The following are device embodiments of this application, which can be used to execute the method embodiments of this application. For details not disclosed in the device embodiments of this application, please refer to the method embodiments of this application.

[0176] Please see below. Figure 2 This is a schematic diagram of a giant remote sensing constellation mission planning device based on atomic task decomposition, provided as an exemplary embodiment of this application. This device can be implemented as all or part of a terminal through software, hardware, or a combination of both, or it can be integrated as an independent module on a server. The giant remote sensing constellation mission planning device based on atomic task decomposition in this embodiment can be applied to a terminal or the cloud. The device includes:

[0177] The observation task acquisition module is used to acquire observation tasks submitted by users and to determine the observation mode of the observation tasks.

[0178] The atomic task decomposition module is used to decompose the observation task into atomic tasks based on the observation mode to obtain a corresponding set of subtasks.

[0179] The task planning module is used to determine the constraints and objective function by combining the set of subtasks;

[0180] The task planning module is also used to minimize the objective function based on the simulated annealing method to obtain the optimal task observation scheme;

[0181] The mission planning module is also used to assign each subtask in the subtask set to a corresponding remote sensing satellite based on the optimal mission observation scheme, so as to execute the observation mission.

[0182] It should be noted that the apparatus provided in the above embodiments is only illustrated by the division of the functional modules described above when executing the giant remote sensing constellation mission planning method based on atomic task decomposition. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the apparatus provided in the above embodiments and the giant remote sensing constellation mission planning method embodiments based on atomic task decomposition belong to the same concept, and the implementation process is detailed in the method embodiments, which will not be repeated here.

[0183] This application also 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 steps of any of the methods described above.

[0184] Please see Figure 3 This is a structural block diagram of an electronic device provided in an embodiment of this application.

[0185] like Figure 3 As shown, the electronic device 300 includes a processor 301 and a memory 302.

[0186] In this embodiment, the processor 301 is the control center of the computer system, and can be a processor of a physical machine or a processor of a virtual machine. The processor 301 may include one or more processing cores, such as a 4-core processor or an 8-core processor. The processor 301 can be implemented using at least one hardware form selected from DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array).

[0187] Processor 301 may also include a main processor and a coprocessor. The main processor is a processor used to process data in the wake-up state, also known as a CPU (Central Processing Unit). The coprocessor is a low-power processor used to process data in the standby state.

[0188] Memory 302 may include one or more computer-readable storage media, which may be non-transitory. Memory 302 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In some embodiments of this application, the non-transitory computer-readable storage media in memory 302 is used to store at least one instruction, which is executed by processor 301 to implement the method in the embodiments of this application.

[0189] In some embodiments, the electronic device 300 further includes a peripheral device interface 303 and at least one peripheral device 304. The processor 301, memory 302, and peripheral device interface 303 can be connected via a bus or signal line. Each peripheral device 304 can be connected to the peripheral device interface 303 via a bus, signal line, or circuit board. Specifically, the peripheral device 304 includes: a display screen, a camera, and audio circuitry. The peripheral device interface 303 can be used to connect at least one I / O (Input / Output) related peripheral device to the processor 301 and memory 302.

[0190] In some embodiments of this application, the processor 301, memory 302, and peripheral device interface 303 are integrated on the same chip or circuit board; in other embodiments of this application, any one or two of the processor 301, memory 302, and peripheral device interface 303 can be implemented on separate chips or circuit boards. This application does not specifically limit the implementation in this regard.

[0191] The electronic device structural block diagram shown in the embodiments of this application does not constitute a limitation on the electronic device 300. The electronic device 300 may include more or fewer components than shown, or combine certain components, or use different component arrangements.

[0192] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the methods in any of the foregoing embodiments. The computer-readable storage medium may include, but is not limited to, any type of disk, including floppy disks, optical disks, DVDs, CD-ROMs, microdrives, as well as magneto-optical disks, ROMs, RAMs, EPROMs, EEPROMs, DRAMs, VRAMs, flash memory devices, magnetic cards or optical cards, nanosystems (including molecular memory ICs), or any type of medium or device suitable for storing instructions and / or data.

[0193] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the parts that contribute to the related technology, can be embodied in the form of software products. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0194] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for planning giant remote sensing constellation missions based on atomic task decomposition, characterized in that, include: Obtain the observation tasks submitted by the user, perform semantic analysis on the observation tasks, and extract the corresponding observation requirements; The observation requirements include observation area requirements, time range requirements, and payload requirements; The observation mode corresponding to the observation task is determined based on the geographical area range corresponding to the observation area requirement, the observation time interval corresponding to the time range requirement, and the load type corresponding to the load requirement. Based on the observation mode, the observation task is decomposed into atomic tasks to obtain a corresponding set of subtasks; The constraints and objective function are determined by combining the set of subtasks; The optimal mission observation scheme is obtained by minimizing the objective function using the simulated annealing method. Based on the optimal mission observation scheme, each subtask in the subtask set is assigned to a corresponding remote sensing satellite to perform the observation mission; After the corresponding observation requirements are extracted, if the observation target is determined to be a moving target based on the observation requirements, then the observation mode of the observation task is determined to be a spatiotemporal continuous observation mode. Based on the observation mode, the observation task is decomposed into atomic tasks to obtain a corresponding set of subtasks, including: The observation task is decomposed into atomic tasks according to the spatiotemporal continuous observation mode to obtain the motion prior information of the moving target; the motion prior information includes initial position, initial velocity and initial direction; Based on the prior motion information, the estimated path of the moving target in various future time periods is predicted, and multiple adjacent prediction regions are obtained by decomposing the estimated path, and the prediction time interval corresponding to each prediction region is determined. The observation task is decomposed into sub-tasks based on a determined payload type and in chronological order, which observe moving targets in the corresponding prediction area within each prediction time interval, and a sub-task set containing each sub-task is generated.

2. The method for planning giant remote sensing constellation missions based on atomic task decomposition according to claim 1, characterized in that, After obtaining the corresponding observation requirements, the method further includes: If the geographical area range corresponding to the observation area requirement is less than or equal to a preset geographical area range threshold, and the observation time interval corresponding to the time range requirement is less than or equal to an observation time length threshold, and the load requirement includes at least two load types, then the observation mode of the observation task is determined to be a multimodal collaborative observation mode. The atomic task decomposition of the observation task based on the observation mode, resulting in a corresponding set of subtasks, includes: The observation task is decomposed into atomic tasks according to the multimodal collaborative observation mode to determine each type of payload corresponding to the payload requirement; The observation task is decomposed into multiple subtasks with the same geographical area, the same observation time interval, and different payload types, generating a subtask set containing each subtask.

3. The method for planning giant remote sensing constellation missions based on atomic task decomposition according to claim 1, characterized in that, After obtaining the corresponding observation requirements, the method further includes: If the geographical area range corresponding to the observation area requirement is greater than the preset geographical area range threshold, and the observation time interval corresponding to the time range requirement is less than or equal to the observation time length threshold, and the load requirement includes a single load type, then the observation mode of the observation task is determined to be the spatial continuous observation mode. The atomic task decomposition of the observation task based on the observation mode, resulting in a corresponding set of subtasks, includes: The observation task is decomposed into atomic tasks according to the continuous space observation mode, and the geographical area is divided into multiple sub-regions; wherein the area of ​​each sub-region is less than or equal to the area covered by a remote sensing satellite in one pass. The observation task is decomposed into sub-tasks that observe multiple sub-regions based on the same payload type within the same observation time interval, and a sub-task set containing each sub-task is generated.

4. The method for planning giant remote sensing constellation missions based on atomic task decomposition according to claim 1, characterized in that, After obtaining the corresponding observation requirements, the method further includes: If the geographical area range corresponding to the observation area requirement is less than or equal to the preset geographical area range threshold, and the time range requirement includes observation time intervals greater than the observation time length threshold and / or multiple periodic observation time intervals, and the load requirement includes one or more load types, then the observation mode of the observation task is determined to be the time continuous observation mode. The atomic task decomposition of the observation task based on the observation mode, resulting in a corresponding set of subtasks, includes: The observation task is decomposed into atomic tasks according to the continuous time observation mode, the time range requirement is divided into multiple sub-time intervals, and the load type corresponding to each sub-time interval is determined. The observation task is decomposed into sub-tasks that observe the same geographical area within each sub-time interval based on a defined payload type, generating a sub-task set containing each sub-task.

5. A method for planning giant remote sensing constellation missions based on atomic task decomposition according to any one of claims 1-4, characterized in that, The step of determining the constraints and objective function by combining the set of subtasks includes: Based on the time range requirements of each subtask in the subtask set, the observation time window constraint for remote sensing satellite to perform subtasks is constructed; based on the observation area requirements of each subtask, the cloud coverage constraint within the corresponding geographical area is constructed; and based on the payload requirements of each subtask, the satellite payload type constraint is constructed. Based on the sum of task priorities, the sum of observation quality, and the observation start time of the sub-task set, an energy function is constructed as the objective function. The method of minimizing the objective function based on simulated annealing to obtain the optimal task observation scheme includes: Remote sensing satellites for observation tasks are selected from the giant remote sensing constellation to construct a random observation scheme that meets the constraints of the observation time window, the cloud coverage rate, and the satellite payload type. At the current annealing temperature, with the random observation scheme as the target observation scheme, a neighborhood observation scheme for the target observation scheme is generated based on the neighborhood function; Calculate the difference between the objective functions of the target observation scheme and the domain observation scheme, respectively; If the difference is less than 0, then the domain observation scheme is taken as the new target observation scheme; Otherwise, the domain observation scheme is used as the new target observation scheme with a preset probability. The annealing temperature is updated based on a preset cooling rate; If the updated annealing temperature is lower than the temperature threshold, the iteration stops, and the target annealing scheme is output as the optimal task observation scheme. Otherwise, proceed to the step of generating the domain observation scheme based on the domain function.

6. An apparatus for planning giant remote sensing constellation missions based on an atomic mission decomposition method according to any one of claims 1-5, characterized in that, The device includes: The observation task acquisition module is used to acquire the observation tasks submitted by the user and to determine the observation mode of the observation tasks. The atomic task decomposition module is used to decompose the observation task into atomic tasks based on the observation mode to obtain a corresponding set of subtasks. The task planning module is used to determine the constraints and objective function by combining the set of subtasks; The task planning module is also used to minimize the objective function based on the simulated annealing method to obtain the optimal task observation scheme; The task planning module is also used to assign each subtask in the subtask set to the corresponding remote sensing satellite based on the optimal task observation scheme, so as to execute the observation task.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the method as described in any one of claims 1 to 5.

8. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 5.

Images