Task planning method, device and equipment for constellation with intelligent driving, medium and observation constellation

Abstract

The invention relates to the technical field of constellation task planning, and discloses a constellation task planning method with intelligent driving, and the method comprises the steps: carrying out the capability matching of a remote sensing satellite in response to a constellation task instruction, obtaining a candidate satellite, and sending a resource evaluation request to the candidate satellite; acquiring satellite resource evaluation information of the candidate satellites, and performing observation action planning to obtain an observation action list; an observation action list is sent to the working satellite, and an observation task is executed; and if a resource limitation condition exists in the execution process of the observation task, sending an adjustment evaluation request to the candidate satellites, and performing action re-planning on the candidate satellites according to task adjustment evaluation information fed back by the candidate satellites so as to adjust the observation action list. The method has the beneficial effects that unified perception and observation action planning are carried out on a plurality of remote sensing satellites based on satellite resource evaluation information, a complete autonomous decision closed loop is constructed on the satellites, constellation-level self intelligence is realized, and the autonomy and intelligent level of observation constellations is improved.

Description

Technical Field

[0001] This application relates to the field of constellation mission planning technology, and in particular to a constellation mission planning method, apparatus, device, medium and observation constellation driven by embodied intelligence. Background Technology

[0002] For observation constellations comprising multiple remote sensing satellites, when performing observation tasks over surface areas, a ground center needs to plan the satellites' actions based on the observation mission. The action planning results are then uploaded via communication between the remote sensing satellites and the ground center, instructing the corresponding satellites to execute the observation tasks accordingly. However, in reality, communication between the ground center and the remote sensing satellites must occur within a specific window period. Outside this window, the satellites cannot receive the action planning results from the ground center, thus preventing them from executing the observation tasks. Furthermore, since the remote sensing satellites rely on the ground center for action planning, and the ground center cannot obtain real-time status and resource information about the satellites in a timely manner, it cannot adjust the action planning results, causing the satellites to be unable to complete their observation tasks.

[0003] In related technologies, the level of intelligence of observation constellations in performing observation tasks still needs to be improved. Summary of the Invention

[0004] This application provides a constellation mission planning method, apparatus, device, medium, and observation constellation driven by embodied intelligence. Based on satellite resource assessment information, it performs unified perception and observation action planning for multiple remote sensing satellites, and replans multi-satellite actions according to the execution progress, thereby constructing a complete autonomous decision-making closed loop on the satellite, realizing constellation-level embodied intelligence, and improving the autonomy and intelligence level of the observation constellation.

[0005] To achieve the above objectives, the main technical solutions adopted in this application include: In a first aspect, embodiments of this application provide an embodied intelligence-driven constellation mission planning method, applied to an observation constellation comprising multiple remote sensing satellites; the method includes: In response to the constellation mission command indicating the observation mission, the remote sensing satellites are matched for capabilities to obtain candidate satellites capable of performing the observation mission, and a resource assessment request is sent to the candidate satellites. Obtain satellite resource assessment information from the candidate satellites based on the resource assessment request, and plan observation actions for the candidate satellites according to the satellite resource assessment information to obtain the observation action list of the observation constellation; wherein, the observation action list corresponds to operational satellites that actually perform tasks; The list of observation actions is sent to the working satellite to instruct the working satellite to perform the observation tasks; If resource constraints exist during the execution of the observation mission, an adjustment evaluation request is sent to the candidate satellite, and the action replanning is performed on the candidate satellite based on the mission adjustment evaluation information fed back by the candidate satellite based on the adjustment evaluation request, so as to adjust the list of observation actions.

[0006] The constellation mission planning method driven by embodied intelligence proposed in this application responds to a constellation mission command instructing an observation mission. It identifies candidate satellites capable of performing the mission from the observation constellation and sends resource assessment requests to these satellites. After receiving satellite resource assessment information from each candidate satellite, it plans observation actions for the candidate satellites based on this information, generating an observation action list to instruct the corresponding operational satellites to perform the observation mission. If any operational satellite experiences resource constraints during the execution of the observation mission, it obtains the resource assessment results of all candidate satellites and uses this as a basis for action replanning, thereby adjusting the observation action list. Compared with related technologies, this application achieves constellation-level embodied intelligence. By sending resource assessment requests to remote sensing satellites and receiving feedback satellite resource assessment information, it autonomously perceives the internal state and external environment of the observation constellation. Based on this autonomous perception, it makes autonomous reasoning decisions and generates an observation action list to instruct the remote sensing satellites to autonomously execute the observation mission. This constructs a complete autonomous decision-making closed loop on-board, reducing the observation constellation's dependence on ground command and human intervention, and improving the autonomy and intelligence level of the observation constellation during the execution of observation missions.

[0007] Optionally, the step of planning observation actions for the candidate satellites based on the satellite resource assessment information to obtain the observation action list for the observation constellation includes: The satellite situation map of the observation constellation is updated based on the satellite resource assessment information to obtain the real-time situation map of the observation constellation; Based on the real-time situation map and the observation task list, task planning is performed to obtain the observation action list; wherein, the observation task list corresponds to the constellation task instructions and is obtained by parsing the constellation task instructions.

[0008] Optionally, the step of performing task planning based on the real-time situation map and the observation task list to obtain the observation action list includes: Candidate information is extracted based on the real-time situation map to obtain the candidate status information of the candidate satellites; Based on the observation task list, task elements are extracted to obtain the task condition information of the observation task; Based on the candidate state information and the task condition information, a task planning prompt is synthesized, and the task planning prompt is sent to the task planning model. The task planning is then performed through the task planning model to output the list of observation actions.

[0009] Optionally, the capability matching of the remote sensing satellite to obtain candidate satellites capable of performing the observation task includes: The constellation mission instructions are parsed to obtain a list of observation tasks corresponding to the constellation mission instructions; Based on the observation task list and the constellation capability map of the observation constellation, the remote sensing satellites are matched to obtain the candidate satellites; wherein, the constellation capability map represents the remote sensing observation capabilities of the remote sensing satellites.

[0010] Optionally, the step of parsing the constellation mission instructions to obtain a list of observation tasks corresponding to the constellation mission instructions includes: Semantic parsing of the constellation mission instructions yields the mission intent and mission elements of the observation mission. Geographic information is queried based on the task elements to obtain geographic information about the observation task; Based on the task intent, the task elements, and the geographic information, the observation task is planned to obtain the observation task list.

[0011] Optionally, the presence of resource constraints during the execution of the observation task can be determined using the following methods: Based on the execution results of the observation task, the progress of the observation task is evaluated, and the progress evaluation results are obtained. The working satellite is monitored in real time to assess its status and obtain the assessment results. Send an intermediate evaluation request to the working satellite and obtain intermediate resource evaluation information fed back by the working satellite based on the intermediate evaluation request; Based on the progress assessment results, the status assessment results, and the intermediate resource assessment information, a mission continuation assessment is performed on the working satellite to obtain a continuation assessment result; if the continuation assessment result does not meet the mission continuation conditions, it is determined that there are resource constraints during the execution of the observation mission.

[0012] Optionally, the step of evaluating the progress of the observation task based on its execution results to obtain a progress evaluation result includes: After the observation constellation has completed the observation task for a preset time, the task execution results of the working satellite during the preset time are obtained; The execution results of the task are evaluated to obtain the execution quality evaluation results; The completion rate of the observed action list is evaluated based on the execution quality assessment results and the preset time to obtain the progress assessment results.

[0013] Optionally, the step of performing a mission continuation assessment on the working satellite based on the progress assessment result, the status assessment result, and the intermediate resource assessment information to obtain a continuation assessment result includes: The status assessment result is compared with the safety status threshold of the working satellite to obtain the status safety result of the working satellite; If the status safety result indicates that the working satellite is in a healthy operating state, a resource feasibility analysis is performed on the working satellite based on the progress assessment result and the intermediate resource assessment information to obtain the resource feasibility result of the working satellite; The working satellite is evaluated in multiple dimensions based on the progress assessment results and the resource feasibility results to obtain the continuation assessment results.

[0014] Secondly, embodiments of this application provide an intelligently driven constellation mission planning device, applied to an observation constellation including multiple remote sensing satellites; the device includes: The instruction response matching module is used to perform capability matching on the remote sensing satellites in response to the constellation mission instruction indicating the observation mission, obtain candidate satellites that can perform the observation mission, and send resource assessment requests to the candidate satellites. The observation action planning module is used to obtain satellite resource assessment information fed back by the candidate satellite based on the resource assessment request, and to plan the observation actions of the candidate satellite according to the satellite resource assessment information to obtain the observation action list of the observation constellation; wherein, the observation action list corresponds to the working satellites that actually perform the tasks; The observation task execution module is used to send the observation action list to the working satellite to instruct the working satellite to perform the observation task; The observation action replanning module is used to replan actions. If there are resource constraints during the execution of the observation task, it sends an adjustment evaluation request to the candidate satellite and replans the actions of the candidate satellite based on the task adjustment evaluation information fed back by the candidate satellite based on the adjustment evaluation request, so as to adjust the list of observation actions.

[0015] Optionally, the observation action planning module includes: The situation update unit is used to update the satellite situation map of the observation constellation based on the satellite resource assessment information to obtain the real-time situation map of the observation constellation. The task planning unit is used to plan tasks based on the real-time situation map and the observation task list to obtain the observation action list; wherein, the observation task list corresponds to the constellation task instruction and is obtained by parsing the constellation task instruction.

[0016] Optionally, the instruction response matching module includes: The instruction parsing unit is used to parse the constellation mission instructions to obtain a list of observation tasks corresponding to the constellation mission instructions. A capability matching unit is used to perform capability matching on the remote sensing satellites according to the observation task list and the constellation capability map of the observation constellation to obtain the candidate satellites; wherein, the constellation capability map represents the remote sensing observation capabilities of the remote sensing satellites.

[0017] Thirdly, embodiments of this application provide a computer device, including: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the method described in any of the above embodiments.

[0018] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer instructions, which are used to cause a computer to perform the method described in any one of the above embodiments.

[0019] Fifthly, embodiments of this application provide a computer program product, including computer instructions, which are used to cause a computer to perform the method described in any of the above embodiments. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the specific embodiments of this application or the prior art, the drawings used in the description of the specific embodiments or the prior art 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 from these drawings without creative effort.

[0021] Figure 1 A flowchart illustrating the steps of the constellation mission planning method driven by embodied intelligence provided in an embodiment of this application; Figure 2 This is a schematic diagram illustrating the interaction between the constellation control system and the remote sensing satellite in an embodiment of this application; Figure 3 This is a flowchart illustrating the steps of the observation action planning in the embodiments of this application; Figure 4 This is a flowchart illustrating the steps of task planning in an embodiment of this application; Figure 5 This is a schematic diagram of the interaction process of the task planning model in the embodiments of this application; Figure 6 This is a flowchart illustrating the capability matching steps in an embodiment of this application; Figure 7 This is a diagram illustrating the steps of instruction parsing in an embodiment of this application; Figure 8 This is a flowchart illustrating the instruction parsing process for constellation mission instructions in this embodiment of the application. Figure 9 This is a diagram illustrating the steps involved in determining whether a resource-constrained situation exists in an embodiment of this application. Figure 10 This is a flowchart illustrating the steps of progress assessment in an embodiment of this application; Figure 11 This is a flowchart illustrating the steps of task continuation evaluation in an embodiment of this application; Figure 12 A block diagram of an embodied intelligence-driven constellation mission planning device provided in an embodiment of this application; Figure 13 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments 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.

[0023] For observation constellations comprising multiple remote sensing satellites, when performing observation tasks over surface areas, a ground center needs to plan the satellites' actions based on the observation mission. The action planning results are then uploaded via communication between the remote sensing satellites and the ground center, instructing the corresponding satellites to execute the observation tasks accordingly. However, in practice, communication between the ground center and the remote sensing satellites must occur within a specific window period. Outside this window, the satellites cannot receive the action planning results from the ground center, thus preventing them from executing the observation tasks. Furthermore, since the remote sensing satellites rely on the ground center for action planning, and the ground center cannot obtain real-time status and resource information about the satellites in a timely manner, it cannot adjust the action planning results, causing the satellites to be unable to complete the observation tasks. In related technologies, the level of intelligence in observation constellations during mission execution still needs improvement.

[0024] To address the aforementioned issues, this application provides an embodied intelligence-driven constellation mission planning method, apparatus, device, medium, and observation constellation. Responding to constellation mission instructions, it performs capability matching on remote sensing satellites to obtain candidate satellites and sends resource assessment requests to these candidate satellites. It then acquires satellite resource assessment information for the candidate satellites, plans observation actions for them, and obtains a list of observation actions. The observation action list is sent to the operational satellites to instruct them to perform observation tasks. If resource constraints exist during the execution of observation tasks, an adjustment assessment request is sent to the candidate satellites, and based on the task adjustment assessment information fed back by the candidate satellites, the actions of the candidate satellites are replanned to adjust the observation action list.

[0025] The constellation mission planning method driven by embodied intelligence provided in this application, in response to a constellation mission instruction indicating an observation mission, identifies candidate satellites capable of performing the observation mission from the observation constellation and sends resource assessment requests to the candidate satellites; after receiving satellite resource assessment information from each candidate satellite, it plans observation actions for the candidate satellites based on the satellite resource assessment information to obtain an observation action list, which instructs the corresponding working satellites to perform the observation mission; if any working satellite is resource-constrained during the execution of the observation mission, it obtains the resource assessment results of all candidate satellites as a basis for action replanning, thereby adjusting the observation action list.

[0026] Compared with related technologies, this application achieves constellation-level embodied intelligence. By sending resource assessment requests to remote sensing satellites and receiving feedback satellite resource assessment information, it autonomously perceives the internal state and external environment of the observation constellation. Based on this autonomous perception, it makes autonomous reasoning decisions and generates a list of observation actions to instruct the remote sensing satellites to autonomously execute observation tasks. This constructs a complete autonomous decision-making closed loop on the satellite, reduces the observation constellation's dependence on ground command and human intervention, and improves the autonomy and intelligence level of the observation constellation in the execution of observation tasks.

[0027] According to an embodiment of this application, an embodiment of a constellation mission planning method driven by embodied intelligence is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0028] Reference Figure 1 As shown, this embodiment provides a constellation mission planning method driven by embodied intelligence, applied to an observation constellation including multiple remote sensing satellites; the method includes: S100. In response to the constellation mission command indicating the observation mission, perform capability matching on the remote sensing satellites to obtain candidate satellites capable of performing the observation mission, and send resource assessment requests to the candidate satellites.

[0029] S200. Obtain satellite resource assessment information from candidate satellites based on resource assessment requests, and plan observation actions for candidate satellites according to the satellite resource assessment information to obtain an observation action list for the observation constellation; wherein, the observation action list corresponds to working satellites that actually perform tasks.

[0030] S300. Sends a list of observation actions to the working satellite to instruct it to perform observation tasks.

[0031] S400. If resource constraints exist during the execution of the observation mission, an adjustment assessment request is sent to the candidate satellites, and the actions of the candidate satellites are replanned based on the mission adjustment assessment information fed back by the candidate satellites based on the adjustment assessment request, so as to adjust the list of observation actions.

[0032] Among them, resource-constrained situations refer to situations where, during the execution of an observation mission, the satellite resources of the working satellite are insufficient to support it in completing the pre-planned observation actions, and the working satellite is unable to complete the observation mission.

[0033] Specifically, the constellation task planning method provided in this embodiment can be implemented through a constellation control system. (Refer to...) Figure 2 As shown, the constellation control system may include a command parsing and capability matching module, a resource assessment and action planning module, an action sending and execution instruction module, and an adjustment assessment and action replanning module connected in sequence. The command parsing and capability matching module is used to receive constellation mission instructions that indicate observation tasks, and to perform capability matching on remote sensing satellites according to the constellation mission instructions to obtain candidate satellites that can perform observation tasks, forming a candidate satellite list.

[0034] The command parsing and capability matching module sends the candidate satellite list to the resource assessment and action planning module. The resource assessment and action planning module, based on the received candidate satellite list, sends resource assessment requests to each candidate satellite and receives satellite resource assessment information from each candidate satellite based on the resource assessment requests. After receiving the satellite resource assessment information, the resource assessment and action planning module also plans observation actions for the candidate satellites based on the satellite resource assessment information, obtaining a list of observation actions for the observation constellation.

[0035] The resource assessment and action planning module sends the observation action list to the action sending and execution instruction module. The action sending and execution instruction module is used to send the observation action list to the working satellites according to the actual tasks to be performed in the observation action list, so as to instruct each working satellite to perform the observation tasks.

[0036] During the execution of the observation mission, each working satellite monitors its own progress in real time. If any working satellite encounters resource constraints, it sends an adjustment assessment request to the remote sensing satellites via the adjustment assessment and action replanning module, and obtains the mission adjustment assessment information fed back by each remote sensing satellite based on the request. After receiving the mission adjustment assessment information, the adjustment assessment and action replanning module performs action replanning on the remote sensing satellites, thereby adjusting the original observation action list or generating a new observation action list. The adjustment assessment and action replanning module sends the adjusted observation action list to the action transmission and execution instruction module, which instructs the adjusted working satellites to execute the observation mission.

[0037] Furthermore, in the instruction parsing and capability matching module, a constellation mission instruction indicating the observation task is received. This constellation mission instruction can be an instruction sent by a user at the ground center, containing task elements such as the observation target, observation mode, and requirements for processing the observation results. The instruction parsing and capability matching module performs intent parsing on the received constellation mission instruction to identify the user's observation intent and obtain the task elements of the observation task. In some embodiments, the constellation mission instruction can be in natural language or structured text form.

[0038] After obtaining the task elements of the observation mission, the required observation capabilities for performing the mission are determined based on these elements. Capability matching is then performed among all remote sensing satellites based on these requirements to identify candidate satellites capable of performing the mission. Capability matching methods may include, but are not limited to, constellation capability map matching, constraint condition judgment, knowledge base retrieval, and model optimality search. For example, when constraint condition judgment is used as the capability matching method, the observation capability requirements can be transformed into constraints. Based on these constraints, a step-by-step binary screening is performed on all remote sensing satellites to select those that meet the constraints as candidate satellites.

[0039] Furthermore, in the resource assessment and action planning module, the module receives the candidate satellite list sent by the instruction parsing and capability matching module, and sends resource assessment requests to each candidate satellite in the list. This instructs the candidate satellites to perform resource assessments based on these requests, and they also send their respective satellite resource assessment information, including status data such as satellite energy and thermal control data, to the resource assessment and action planning module. Upon receiving the satellite resource assessment information from the candidate satellites, the resource assessment and action planning module plans observation actions for the candidate satellites based on this information, resulting in an observation action list. It is understood that the observation action list contains the observation actions required to perform the observation tasks and their corresponding working satellites. Each observation action has a corresponding action time, and there is a temporal relationship between the various observation actions. The working satellites can be one or more remote sensing satellites from the candidate satellites.

[0040] Furthermore, in the action sending and execution instruction module, the observation action list sent by the resource assessment and action planning module is received, and the observation action list is distributed to the corresponding working satellites via inter-satellite communication. After receiving the observation action list, the working satellite performs action parsing to determine the observation actions it needs to perform, and adds the observation actions to the task manager. In some embodiments, the distribution process of the observation action list can be inter-satellite collaborative distribution, including: the resource assessment and action planning module sends the observation action list to the nearest first remote sensing satellite; the first remote sensing satellite parses its own observation actions from the observation action list and adds them to the task manager, and then sends other observation actions in the observation action list to the adjacent second remote sensing satellite via inter-satellite communication; similarly, after adding its own observation actions to the task manager, the second remote sensing satellite sends other observation actions to the adjacent third remote sensing satellite via inter-satellite communication; the above process of task parsing, adding, and sending is repeated until all working satellites have obtained the observation actions they need to perform.

[0041] After each working satellite acquires its required observation actions, it executes these actions according to the planned sequence and time, acquiring observation image data of the observed targets. During the execution of these actions, the task manager monitors the progress of each working satellite in real time to determine if any resource constraints exist. If any working satellite experiences resource constraints, it reports this information to the adjustment assessment and action replanning module, triggering a resource reassessment and action replanning to adjust the observation action list. The task manager can also monitor the task execution status of each working satellite in real time to determine if it is within a safe range. If any working satellite's task execution status deviates from the safe range, this information is reported to the adjustment assessment and action replanning module, triggering a resource reassessment and action replanning to adjust the observation action list.

[0042] Furthermore, in the adjustment assessment and action replanning module, when resource constraints are detected, an adjustment assessment request is sent to candidate satellites. This instructs the candidate satellites to conduct resource assessments based on the request and send their respective task adjustment assessment information to the adjustment assessment and action replanning module. It should be noted that the candidate satellites sending the adjustment assessment request can be all candidate satellites except those with resource constraints, or all operational satellites among the candidate satellites. When the request is sent to all operational satellites among the candidate satellites, it indicates that the resource constraints on the constrained satellites are relatively low, and the observation mission can continue to be performed with reduced observation requirements. In this case, the impact of resource constraints can be eliminated by simplifying or downgrading the observation actions of the constrained satellites, or by distributing tasks among the operational satellites. When the request is sent to all candidate satellites other than the constrained satellites, it indicates that the resource constraints on the constrained satellites are relatively high, and the constrained satellites cannot continue to perform the observation mission. In this case, the observation actions need to be replanned based on the resource information of all candidate satellites other than the constrained satellites to eliminate the impact of the resource constraints on the observation mission execution process.

[0043] After receiving mission adjustment assessment information from each candidate satellite, the adjustment assessment and action replanning module replans the actions of the candidate satellites based on the mission adjustment assessment information to adjust the observation action list, resulting in an adjusted observation action list. It is understood that the action replanning method can be the same as the observation action planning method. In some embodiments, if any working satellite completes its observation action ahead of schedule, an adjustment assessment request can be sent to candidate satellites other than that working satellite to replan actions based on the feedback mission adjustment assessment information. This allows for the allocation of resources from that working satellite to other working satellites, achieving effective allocation of satellite resources and improving the execution efficiency of the observation mission.

[0044] The constellation mission planning method driven by embodied intelligence provided in this embodiment responds to a constellation mission instruction that indicates an observation mission, identifies candidate satellites capable of performing the observation mission from the observation constellation, and sends resource assessment requests to the candidate satellites; after receiving satellite resource assessment information from each candidate satellite, it plans observation actions for the candidate satellites based on the satellite resource assessment information to obtain an observation action list, which instructs the corresponding working satellites to perform the observation mission; if any working satellite is resource-constrained during the execution of the observation mission, it obtains the resource assessment results of all candidate satellites as a basis for action replanning, thereby adjusting the observation action list.

[0045] Compared with related technologies, this application achieves constellation-level embodied intelligence. By sending resource assessment requests to remote sensing satellites and receiving feedback satellite resource assessment information, it autonomously perceives the internal state and external environment of the observation constellation. Based on this autonomous perception, it makes autonomous reasoning decisions and generates a list of observation actions to instruct the remote sensing satellites to autonomously execute observation tasks. This constructs a complete autonomous decision-making closed loop on the satellite, reduces the observation constellation's dependence on ground command and human intervention, and improves the autonomy and intelligence level of the observation constellation in the execution of observation tasks.

[0046] Reference Figure 3 As shown, in one embodiment of this application, observation actions are planned for candidate satellites based on satellite resource assessment information to obtain a list of observation actions for the observation constellation, including: S210. Update the satellite situation map of the observation constellation based on satellite resource assessment information to obtain the real-time situation map of the observation constellation.

[0047] S220. Based on the real-time situation map and the observation task list, perform task planning to obtain the observation action list; wherein, the observation task list corresponds to the constellation task instructions and is obtained by parsing the instructions based on the constellation task instructions.

[0048] The satellite resource assessment information may include the status information of candidate satellites, including but not limited to their position, attitude, and energy status. The satellite situation map of the observation constellation can represent the cluster capability of the constellation and the current status of each remote sensing satellite, including status data of each satellite, meteorological conditions at the target observation point, and mission progress, providing data support for observation action planning. In some embodiments, the satellite situation map may adopt a hierarchical dynamic map structure, including a bottom layer, a middle layer, and an upper layer. The bottom layer records the status data of each remote sensing satellite; the middle layer describes the relative relationships between the satellites, including but not limited to their relative positional relationships, communication visibility, and mission coordination; and the upper layer records the mission execution status and observation information of each satellite.

[0049] The observation task list corresponds to the constellation task instructions, representing the observation intent required for each task. It can be obtained by parsing the constellation task instructions. When the constellation task instructions are in natural language form, natural language processing is performed on them to identify the task elements within the instructions. Based on these identified elements, a standardized structured text format is constructed, resulting in the observation task list. The natural language processing methods may include, but are not limited to, word segmentation, syntactic analysis, and semantic extraction.

[0050] Specifically, at the current moment, based on the acquired satellite resource assessment information, the corresponding information in the satellite situation map is updated in real time to obtain the real-time situation map of the observation constellation at the current moment. In some embodiments, the real-time update process of the satellite situation map may include: updating the data of the lower layer of the real-time situation map based on the satellite resource assessment information; performing dynamic correlation calculations among remote sensing satellites according to the updated lower layer real-time situation map to update the data of the middle layer; and updating the data of the upper layer according to information such as whether each remote sensing satellite is currently in mission execution status and mission execution progress.

[0051] Further, based on the real-time situation map and the observation task list, task planning is performed on candidate satellites to obtain a list of observation actions for the candidate satellites. In some embodiments, the action planning process may include: obtaining task information of the observation tasks based on the observation task list, including task gain, task loss, and task constraints; using a heuristic genetic algorithm, quantifying the task information as an optimization objective, and representing the task constraints of the observation tasks and the satellite resource assessment information of the candidate satellites as constraints, thereby constructing a multi-objective optimization model for the observation tasks. A global iterative search is performed through the multi-objective optimization model to determine the observation actions that each candidate satellite needs to perform, generating a list of observation actions. The task gain of the observation task can be the positive value that performing the observation task can generate for the constellation control system or the user issuing the constellation task command, including but not limited to the urgency and importance of the observation task, and the image quality of the observation results. The task loss of the observation task can be the cost incurred by the constellation control system by performing the observation task, including but not limited to the side-swing energy consumption and image capture energy consumption of the remote sensing satellite due to performing the observation task. The task constraints of an observation mission can be the restrictions that must be met when performing the observation mission, including but not limited to the solar angle, the side swing angle and side swing velocity of the remote sensing satellite, and the cloud thickness in the target area.

[0052] It is understood that this embodiment updates the satellite situation map based on the acquired satellite resource assessment information, enabling the observation constellation, as an embodied intelligent agent, to grasp the real-time status of each remote sensing satellite. Thus, the observation constellation can plan actions based on the real-time status of the remote sensing satellites, realizing the autonomous perception and intelligent decision-making of the observation constellation and improving the intelligence level of the observation constellation.

[0053] Reference Figure 4 As shown in one embodiment of this application, task planning is performed based on the real-time situation map and the observation task list to obtain an observation action list, including: S222. Extract candidate information based on the real-time situation map to obtain candidate status information of candidate satellites.

[0054] S224. Extract task elements from the observation task list to obtain the task condition information of the observation tasks.

[0055] S226. Synthesize task planning prompts based on candidate state information and task condition information, send the task planning prompts to the task planning big model, and perform task planning through the task planning big model to output a list of observation actions.

[0056] Specifically, based on the candidate satellite list, the status data of the candidate satellites and the relative relationships between each candidate satellite are extracted from the real-time situation map, and the extracted information is structured to obtain the candidate status information of each candidate satellite.

[0057] Furthermore, the observation task list corresponds to the constellation task instructions, representing the observation intent required by the observation task. Information is extracted from the task elements of the observation task based on the observation task list to obtain the observation intent and task condition information.

[0058] Furthermore, prompts are synthesized based on candidate state information and task condition information to obtain a complete task planning prompt that represents the basis for task planning. It is understood that the prompt synthesis method can include text merging and structured template filling, among others. For example, structured template filling can include: performing template matching based on the task condition information of the observed task to obtain a prompt template; and filling the corresponding information from the candidate state information and task condition information into the corresponding positions of the prompt template to obtain the task planning prompt.

[0059] Furthermore, the mission planning prompts are sent to the mission planning big model, which then performs mission planning for the candidate satellites and outputs a list of observation actions. It is understood that the mission planning big model can be a large language model pre-trained based on relevant external knowledge in the remote sensing observation field. It can perform temporal planning reasoning for each candidate satellite based on candidate state information and mission condition information to generate a list of observation actions. In some embodiments, the mission planning process may include: selecting suitable operational satellites from the candidate satellites to perform the observation mission; for any operational satellite, planning the power-on and power-off commands for each payload on that operational satellite, and planning the execution commands for each payload to perform the observation mission during the power-on process, the evaluation commands for the execution results after completion of the execution commands, and the transmission commands for feeding back the execution results to the user, thus obtaining a list of observation actions.

[0060] In some embodiments, the process of task planning using a large task planning model can be referred to Figure 5As shown, users at the ground control center send constellation mission commands to the constellation control system based on their observation needs. Upon receiving the commands, the system generates a list of observation missions, including mission condition information. A retrieval system within the system searches the constellation capability map based on the mission commands to obtain a list of candidate satellites. Based on this list, it searches the real-time situation map to obtain the candidate status information for each satellite. A mission planning prompt is synthesized from the mission condition information and candidate status information and input into the large-scale mission planning model. The model then plans the missions for the candidate satellites and outputs a list of observation actions. This list can be sent to the individual operational satellites or fed back to the user for review and adjustment.

[0061] Reference Figure 6 As shown, in one embodiment of this application, capability matching is performed on remote sensing satellites to obtain candidate satellites capable of performing observation tasks, including: S110. Parse the constellation mission instructions to obtain a list of observation tasks corresponding to the constellation mission instructions.

[0062] S120. Based on the observation task list and the constellation capability map of the observation constellation, perform capability matching on the remote sensing satellites to obtain candidate satellites; wherein, the constellation capability map represents the remote sensing observation capabilities of the remote sensing satellites.

[0063] Specifically, the constellation task instructions are parsed to identify the task elements in the constellation task instructions, and a standardized structured text form is constructed based on the identified task elements to obtain the observation task list.

[0064] Furthermore, the observation constellation corresponds to a constellation capability graph, which represents the remote sensing observation capabilities of each remote sensing satellite in the constellation, as well as the relationship between mission execution capabilities and resource consumption. For example, the constellation capability graph can be in the form of a graph structure, containing nodes such as satellite nodes, capability nodes, execution nodes, and cost nodes corresponding to each remote sensing satellite. The nodes are connected by edges, representing the capability relationships of each remote sensing satellite.

[0065] Understandably, the constellation capability map encompasses satellite capability information related to observation missions, indicating how each remote sensing satellite can perform observation missions. It provides a basis for the observation capability for mission planning, thereby enabling intelligent decision-making at the observation constellation level and improving the intelligence level of the observation constellation.

[0066] Reference Figure 7 As shown, in one embodiment of this application, the constellation mission instructions are parsed to obtain a list of observation tasks corresponding to the constellation mission instructions, including: S112. Perform semantic parsing on the constellation mission instructions to obtain the mission intent and mission elements of the observation mission.

[0067] S114. Based on task elements, perform geographic information queries to obtain geographic information about the observation task.

[0068] S116. Based on the mission intent, mission elements, and geographic information, perform mission planning for the observation missions to obtain a list of observation missions.

[0069] Specifically, the constellation task instructions are obtained in natural language form, natural language processing is performed on the constellation task instructions, and intent parsing is performed on the natural language processing results of the constellation task instructions to identify the observation intent of the constellation task instructions and obtain the task intent and task elements of the observation task.

[0070] In some embodiments, semantic parsing of constellation task instructions can be performed by an intent-parsing agent. This intent-parsing agent can be a large language model-based agent, including a context adjustment unit and an intent parsing unit. The context adjustment unit includes an in-memory database or cache database to store context information from multi-turn dialogues with the user, supporting dynamic updates and expiration handling to ensure the agent understands the user's true needs. The intent parsing unit, by combining external domain knowledge and context information, performs in-depth analysis and understanding of the constellation task instructions to determine the task elements of the observation task. It is understood that the intent-parsing agent can adopt an extensible design, supporting the dynamic loading of new tools and application interfaces, and achieving functional expansion through the integration of multi-functional tools to adapt to the actual needs of different scenarios.

[0071] Furthermore, task elements can include the observation target, observation mode, and requirements for processing observation results. For the target area where the observation target is located, a third-party geographic information interface can be called to query geographic information and determine the geographic information of the target area. It is understood that geographic information can include data such as the target area's name, region type, latitude and longitude, and altitude.

[0072] Furthermore, based on the mission intent, mission elements, and geographic information, the observation mission is planned to divide it into multiple sub-tasks, resulting in an observation mission list. (Refer to...) Figure 8As shown, in some embodiments, constellation task instructions can be task requests made by users to the observed constellation, including natural language instructions, routine monitoring inputs, and process information feedback. For example, natural language instructions could be in the form of "detect traffic congestion in Hangzhou," routine monitoring inputs could be requests made to the observed constellation in the event of an abnormal disaster on the Earth's surface, and process information feedback could be updates to the dynamic information of the observed target. After receiving the constellation task instructions, the intent parsing agent analyzes the observation type based on the task elements of the constellation task instructions, and fills the observation type and other task elements into the task template to generate sub-tasks.

[0073] Reference Figure 9 As shown in this embodiment of the application, the following method is used to determine whether there is a resource constraint during the execution of the observation task: S410. Based on the results of the observation task execution, conduct a progress assessment of the observation task and obtain the progress assessment results.

[0074] S420. Conduct real-time status monitoring of the operational satellite to assess its status and obtain the status assessment results.

[0075] S430. Send an intermediate evaluation request to the working satellite and obtain intermediate resource evaluation information fed back by the working satellite based on the intermediate evaluation request.

[0076] S440. Based on the progress assessment results, status assessment results, and intermediate resource assessment information, conduct a mission continuation assessment for the working satellite to obtain the continuation assessment results; if the continuation assessment results do not meet the mission continuation conditions, it is determined that there are resource constraints during the execution of the observation mission.

[0077] Specifically, during the execution of an observation mission, for any given working satellite, the execution result of that satellite for the current observation mission is acquired, and mission progress is tracked based on the execution result to achieve lifecycle management of the observation mission and obtain a progress evaluation result. In some embodiments, the progress evaluation result may include indicators such as time progress, mission progress, and quality progress. Time progress can be obtained by comparing the current time taken with the planned time, indicating whether there is a time lag in the execution of the observation mission. Mission progress can be obtained by comparing the execution result of the observation mission with the total workload, indicating the completion status of the observation mission. Quality progress can be obtained by performing a quality evaluation based on the execution result of the observation mission, indicating whether the current execution result meets the quality standards of the observation mission.

[0078] Furthermore, by using the status sensing payloads on each operational satellite, the satellite's status is monitored in real time to obtain status assessment results, determining whether the operational satellite and its payload are operating within normal ranges. It is understandable that real-time status monitoring can determine the operational satellite's status boundaries, thereby providing early warnings of potential malfunctions, reducing satellite lifespan loss, and ensuring the satellite's survivability.

[0079] Furthermore, an intermediate assessment request is sent to the operational satellite, enabling it to assess its own resource status, generate intermediate resource assessment information, and feed it back to the constellation control system. Understandably, this intermediate resource assessment information indicates the operational satellite's resource consumption during observation mission execution, helping to determine if excessive resource consumption is occurring and ensuring the satellite's energy health.

[0080] Furthermore, based on a preset time period, progress assessment results, status assessment results, and intermediate resource assessment information are acquired periodically. The obtained information is then used to conduct mission continuation assessments for the working satellites, yielding continuation assessment results for each satellite. If the continuation assessment results meet the mission continuation conditions, it indicates that the corresponding working satellite can continue performing its observation mission and achieve optimal mission benefits. If the continuation assessment results do not meet the mission continuation conditions, it indicates that the corresponding working satellite is experiencing resource constraints and cannot continue performing its observation mission. In this case, it is necessary to re-plan the observation action list for that working satellite or all working satellites, generating a new observation action list to ensure that the observation mission can be fully executed.

[0081] Reference Figure 10 As shown, in one embodiment of this application, the progress of the observation task is evaluated based on the execution result of the observation task, and the progress evaluation result is obtained, including: S412. After the observation constellation has completed its observation mission for the preset time, acquire the mission execution results of the working satellites within the preset time.

[0082] S414. Conduct a quality assessment of the task execution results to obtain the execution quality assessment results.

[0083] S416. Based on the execution quality assessment results and the preset time, evaluate the completion rate of the observation action list to obtain the progress assessment results.

[0084] Specifically, the progress of the observation mission is periodically evaluated based on a preset time. After the preset time has elapsed, the mission execution results of each working satellite are acquired within that time period. It can be understood that the mission execution results can be raw remote sensing data for the observed target. After obtaining the raw remote sensing data, it is unpacked to separate image data, auxiliary data, and telemetry data. Based on the attitude parameters of each working satellite, the image data undergoes geometric correction, and atmospheric correction is performed based on meteorological data of the target area, resulting in corrected image data, which serves as the mission execution result.

[0085] Furthermore, a quality assessment is performed on the task execution results to obtain the execution quality assessment results of the observation task within a preset time period. In some embodiments, the quality assessment may include image quality assessment, image occlusion assessment, and recognition confidence assessment, wherein image quality assessment may evaluate the image resolution of the task execution results to determine the image acquisition quality of the working satellite. Image occlusion assessment may evaluate the cloud occlusion level in the task execution results to determine the degree of remote sensing acquisition of the target area by the working satellite. Recognition confidence assessment may perform target recognition based on the task execution results to obtain the recognition confidence of the observed target, thereby determining the recognition capability of the task execution results for the observed target.

[0086] Furthermore, based on the execution quality assessment results and the preset time, the completion rate of the observation action list is assessed to obtain a progress assessment result, which is used to determine whether the working satellite is performing the observation tasks according to the preset execution rate of the observation action list. In some embodiments, the completion rate assessment may be calculated by comparing the number of sub-tasks completed with the preset time to determine the degree of completion of the sub-tasks and obtain a progress assessment result.

[0087] Reference Figure 11 As shown, in one embodiment of this application, a mission continuation assessment is performed on the working satellite based on the progress assessment results, status assessment results, and intermediate resource assessment information to obtain the continuation assessment results, including: S442. Compare the status assessment results with the safety status threshold of the operational satellite to obtain the status safety result of the operational satellite.

[0088] S444. If the status safety result indicates that the working satellite is in a healthy operating state, a resource feasibility analysis is performed on the working satellite based on the progress assessment results and intermediate resource assessment information to obtain the resource feasibility result of the working satellite.

[0089] S446. Conduct a multi-dimensional assessment of the working satellite based on the progress assessment results and resource feasibility results to obtain the continuation assessment results.

[0090] Specifically, the status assessment results include multiple status indicators for the operational satellites, each corresponding to a normal range defined by a safety status threshold. For any operational satellite, the status assessment result is compared to the safety status threshold. Whether the status assessment result deviates from the normal range determines whether the operational satellite is in a healthy operational state. It is understood that if the status assessment result deviates from the normal range, it indicates that the operational satellite is not in a healthy operational state. In this case, the subsequent resource feasibility analysis process is skipped, and it is determined that the operational satellite cannot continue to perform its observation mission.

[0091] Furthermore, if the status assessment result is within the normal range, it indicates that any working satellite is in a healthy operational state. At this point, a resource feasibility analysis is performed on any working satellite based on the progress assessment result and intermediate resource assessment information to determine whether the satellite resources of any working satellite are sufficient to support it in completing the pre-planned observation actions, and whether the working satellite will experience resource depletion after completing the observation actions, thereby obtaining the resource feasibility result of any working satellite.

[0092] Furthermore, environmental status data of the target area is acquired through remote sensing satellites. The progress assessment results, resource feasibility results, and environmental status data are fused together to analyze whether any given satellite is suitable to continue its observation mission, thus obtaining a continuation assessment result for that satellite. The environmental status data may include meteorological conditions in the target area and dynamic information about the observed targets, used to determine whether the environmental status of the target area is suitable for observation.

[0093] In some embodiments, information fusion may involve separately assigning scores to the progress assessment results, resource feasibility results, and environmental status data, and then performing a weighted fusion calculation based on the assessment results to obtain a continuation assessment result. If the continuation assessment result exceeds a preset continuation threshold, it is determined that the continuation assessment result meets the mission continuation conditions, indicating that any working satellite can continue to perform the observation mission and obtain the optimal mission benefits. If the continuation assessment result does not exceed the preset continuation threshold, it is determined that the continuation assessment result does not meet the mission continuation conditions, indicating that any working satellite cannot continue to perform the observation mission and needs to adjust the current observation action list through action replanning to ensure that the observation mission can be fully executed.

[0094] Accordingly, please refer to Figure 12 This application provides an intelligently driven constellation mission planning device for use in observation constellations comprising multiple remote sensing satellites; the device includes: The instruction response matching module 1210 is used to perform capability matching on remote sensing satellites in response to constellation mission instructions indicating observation tasks, obtain candidate satellites that can perform observation tasks, and send resource assessment requests to the candidate satellites.

[0095] The observation action planning module 1220 is used to obtain satellite resource assessment information based on the resource assessment request feedback from candidate satellites, and to plan observation actions for candidate satellites according to the satellite resource assessment information to obtain an observation action list for the observation constellation; wherein, the observation action list corresponds to the working satellites that actually perform the tasks.

[0096] The observation task execution module 1230 is used to send a list of observation actions to the working satellite to instruct the working satellite to perform observation tasks.

[0097] The observation action replanning module 1240 is used to replan actions. If there are resource constraints during the execution of the observation task, it sends an adjustment evaluation request to the candidate satellites and replans the actions of the candidate satellites based on the task adjustment evaluation information fed back by the candidate satellites based on the adjustment evaluation request, so as to adjust the list of observation actions.

[0098] In some alternative implementations, the observation action planning module 1220 includes: The situation update unit is used to update the satellite situation map of the observation constellation based on satellite resource assessment information, so as to obtain the real-time situation map of the observation constellation.

[0099] The task planning unit is used to plan tasks based on the real-time situation map and the observation task list to obtain the observation action list; the observation task list corresponds to the constellation task instructions and is obtained by parsing the constellation task instructions.

[0100] In some alternative implementations, the task planning unit includes: The situation matching and retrieval subunit is used to extract candidate information based on the real-time situation map to obtain the candidate status information of candidate satellites.

[0101] The task element extraction subunit is used to extract task elements from the observation task list to obtain the task condition information of the observation tasks.

[0102] The model task planning subunit is used to synthesize task planning prompts based on candidate state information and task condition information, send the task planning prompts to the task planning big model, and perform task planning through the task planning big model to output a list of observation actions.

[0103] In some alternative implementations, the instruction response matching module includes: The instruction parsing unit is used to parse the constellation mission instructions and obtain a list of observation tasks corresponding to the constellation mission instructions.

[0104] The capability matching unit is used to perform capability matching of remote sensing satellites based on the observation task list and the constellation capability map of the observation constellation to obtain candidate satellites; wherein, the constellation capability map represents the remote sensing observation capabilities of the remote sensing satellites.

[0105] In some optional implementations, the instruction parsing unit includes: The instruction semantic parsing subunit is used to perform semantic parsing on constellation mission instructions to obtain the mission intent and mission elements of the observation mission.

[0106] The geographic information query subunit is used to query geographic information based on task elements and obtain geographic information about the observation task.

[0107] The observation task planning subunit is used to plan observation tasks based on task intent, task elements, and geographic information, and obtain an observation task list.

[0108] In some alternative implementations, the observation action replanning module 1240 includes: The task progress assessment unit is used to assess the progress of the observation task based on the execution results of the observation task, and obtain the progress assessment results.

[0109] The satellite status assessment unit is used to monitor the status of the operational satellite in real time, to assess the status of the operational satellite, and to obtain the status assessment results.

[0110] The satellite resource assessment unit is used to send intermediate assessment requests to the working satellite and obtain intermediate resource assessment information fed back by the working satellite based on the intermediate assessment requests.

[0111] The mission continuation assessment unit is used to conduct mission continuation assessments of the working satellite based on progress assessment results, status assessment results, and intermediate resource assessment information, and obtain continuation assessment results. If the continuation assessment results do not meet the mission continuation conditions, it is determined that there are resource constraints during the execution of the observation mission.

[0112] In some optional implementations, the task progress evaluation unit includes: The execution result acquisition subunit is used to acquire the task execution results of the working satellites within the preset time after the observation constellation has completed its observation tasks.

[0113] The execution quality assessment subunit is used to assess the quality of task execution results and obtain execution quality assessment results.

[0114] The task completion assessment subunit is used to assess the completion of the observation action list based on the execution quality assessment results and the preset time, and obtain the progress assessment results.

[0115] In some optional implementations, the task continuation evaluation unit includes: The state safety comparison subunit is used to compare the state assessment results with the safety state threshold of the operational satellite to obtain the state safety result of the operational satellite.

[0116] The resource feasibility analysis subunit is used to perform a resource feasibility analysis on the working satellite based on the progress assessment results and intermediate resource assessment information, when the status safety result indicates that the working satellite is in a healthy operating state, to obtain the resource feasibility result of the working satellite.

[0117] The evaluation result acquisition subunit is used to perform a multi-dimensional evaluation of the working satellite based on the progress evaluation result and the resource feasibility result, and obtain the continuation evaluation result.

[0118] Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0119] In this embodiment, the constellation mission planning device driven by embodied intelligence is presented in the form of a functional unit. Here, a unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0120] Please see Figure 13 , Figure 13 This is a schematic diagram of a computer device according to an embodiment of this application. As shown in the figure, the computer device includes one or more processors 10, a memory 20, and interfaces for connecting the various components, including high-speed interfaces and low-speed interfaces. The various components communicate with each other using different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on an external input / output device (such as a display device coupled to the interface). In some alternative embodiments, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 13 Take a processor 10 as an example.

[0121] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.

[0122] The memory 20 stores instructions executable by at least one processor 10 to cause the at least one processor 10 to perform the method shown in the above embodiments.

[0123] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0124] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0125] The computer device also includes a communication interface 30 for communicating with other devices or communication networks.

[0126] This application also provides a computer-readable storage medium. The methods described in this application can be implemented in hardware or firmware, or implemented as recordable on a storage medium, or implemented as computer code downloaded over a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and subsequently stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the methods shown in the above embodiments are implemented.

[0127] This application provides a computer program product including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the method of any embodiment of this application.

[0128] Although embodiments of this application have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of this application, and all such modifications and variations fall within the scope defined by the appended claims.

[0129] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0130] For ease of description, the above devices are described separately by function as various units. Of course, in implementing this application, the functions of each unit can be implemented in one or more software and / or hardware.

[0131] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0132] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1A device that provides the functions specified in one or more boxes.

[0133] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0134] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0135] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0136] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0137] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

[0138] Although embodiments of this application have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of this application, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A constellation mission planning method driven by embodied intelligence, characterized in that, Applied to an observation constellation comprising multiple remote sensing satellites; the method includes: In response to the constellation mission command indicating the observation mission, the remote sensing satellites are matched for capabilities to obtain candidate satellites capable of performing the observation mission, and a resource assessment request is sent to the candidate satellites. Obtain satellite resource assessment information from the candidate satellites based on the resource assessment request, and plan observation actions for the candidate satellites according to the satellite resource assessment information to obtain the observation action list of the observation constellation; wherein, the observation action list corresponds to operational satellites that actually perform tasks; The list of observation actions is sent to the working satellite to instruct the working satellite to perform the observation tasks; If resource constraints exist during the execution of the observation mission, an adjustment evaluation request is sent to the candidate satellite, and the action replanning is performed on the candidate satellite based on the mission adjustment evaluation information fed back by the candidate satellite based on the adjustment evaluation request, so as to adjust the list of observation actions.

2. The method according to claim 1, characterized in that, The step of planning observation actions for the candidate satellites based on the satellite resource assessment information to obtain the observation action list for the observation constellation includes: The satellite situation map of the observation constellation is updated based on the satellite resource assessment information to obtain the real-time situation map of the observation constellation; Based on the real-time situation map and the observation task list, task planning is performed to obtain the observation action list; wherein, the observation task list corresponds to the constellation task instructions and is obtained by parsing the constellation task instructions.

3. The method according to claim 2, characterized in that, The step of planning tasks based on the real-time situation map and the observation task list to obtain the observation action list includes: Candidate information is extracted based on the real-time situation map to obtain the candidate status information of the candidate satellites; Based on the observation task list, task elements are extracted to obtain the task condition information of the observation task; Based on the candidate state information and the task condition information, a task planning prompt is synthesized, and the task planning prompt is sent to the task planning model. The task planning is then performed through the task planning model to output the list of observation actions.

4. The method according to claim 1, characterized in that, The capability matching of the remote sensing satellites to obtain candidate satellites capable of performing the observation mission includes: The constellation mission instructions are parsed to obtain a list of observation tasks corresponding to the constellation mission instructions; Based on the observation task list and the constellation capability map of the observation constellation, the remote sensing satellites are matched to obtain the candidate satellites; wherein, the constellation capability map represents the remote sensing observation capabilities of the remote sensing satellites.

5. The method according to claim 4, characterized in that, The step of parsing the constellation mission instructions to obtain a list of observation tasks corresponding to the constellation mission instructions includes: Semantic parsing of the constellation mission instructions yields the mission intent and mission elements of the observation mission. Geographic information is queried based on the task elements to obtain geographic information about the observation task; Based on the task intent, the task elements, and the geographic information, the observation task is planned to obtain the observation task list.

6. The method according to claim 1, characterized in that, The following methods are used to determine whether there are resource constraints during the execution of the observation task: Based on the execution results of the observation task, the progress of the observation task is evaluated, and the progress evaluation results are obtained. The working satellite is monitored in real time to assess its status and obtain the assessment results. Send an intermediate evaluation request to the working satellite and obtain intermediate resource evaluation information fed back by the working satellite based on the intermediate evaluation request; Based on the progress assessment results, the status assessment results, and the intermediate resource assessment information, a mission continuation assessment is performed on the working satellite to obtain a continuation assessment result; if the continuation assessment result does not meet the mission continuation conditions, it is determined that there are resource constraints during the execution of the observation mission.

7. The method according to claim 6, characterized in that, The step of evaluating the progress of the observation task based on its execution results, and obtaining the progress evaluation results, includes: After the observation constellation has completed the observation task for a preset time, the task execution results of the working satellite during the preset time are obtained; The execution results of the task are evaluated to obtain the execution quality evaluation results; The completion rate of the observed action list is evaluated based on the execution quality assessment results and the preset time to obtain the progress assessment results.

8. The method according to claim 6, characterized in that, The step of performing a mission continuation assessment on the working satellite based on the progress assessment results, the status assessment results, and the intermediate resource assessment information, to obtain continuation assessment results, includes: The status assessment result is compared with the safety status threshold of the working satellite to obtain the status safety result of the working satellite; If the status safety result indicates that the working satellite is in a healthy operating state, a resource feasibility analysis is performed on the working satellite based on the progress assessment result and the intermediate resource assessment information to obtain the resource feasibility result of the working satellite; The working satellite is evaluated in multiple dimensions based on the progress assessment results and the resource feasibility results to obtain the continuation assessment results.

9. A constellation mission planning device driven by embodied intelligence, characterized in that, Applied to an observation constellation comprising multiple remote sensing satellites; the device includes: The instruction response matching module is used to perform capability matching on the remote sensing satellites in response to the constellation mission instruction indicating the observation mission, obtain candidate satellites that can perform the observation mission, and send resource assessment requests to the candidate satellites. The observation action planning module is used to obtain satellite resource assessment information fed back by the candidate satellite based on the resource assessment request, and to plan the observation actions of the candidate satellite according to the satellite resource assessment information to obtain the observation action list of the observation constellation; wherein, the observation action list corresponds to the working satellites that actually perform the tasks; The observation task execution module is used to send the observation action list to the working satellite to instruct the working satellite to perform the observation task; The observation action replanning module is used to replan actions. If there are resource constraints during the execution of the observation task, it sends an adjustment evaluation request to the candidate satellite and replans the actions of the candidate satellite based on the task adjustment evaluation information fed back by the candidate satellite based on the adjustment evaluation request, so as to adjust the list of observation actions.

10. The apparatus according to claim 9, characterized in that, The observation action planning module includes: The situation update unit is used to update the satellite situation map of the observation constellation based on the satellite resource assessment information to obtain the real-time situation map of the observation constellation. The task planning unit is used to plan tasks based on the real-time situation map and the observation task list to obtain the observation action list; wherein, the observation task list corresponds to the constellation task instruction and is obtained by parsing the constellation task instruction.

11. The apparatus according to claim 9, characterized in that, The instruction response matching module includes: The instruction parsing unit is used to parse the constellation mission instructions to obtain a list of observation tasks corresponding to the constellation mission instructions. A capability matching unit is used to perform capability matching on the remote sensing satellites according to the observation task list and the constellation capability map of the observation constellation to obtain the candidate satellites; wherein, the constellation capability map represents the remote sensing observation capabilities of the remote sensing satellites.

12. The apparatus according to claim 9, characterized in that, The observation action replanning module includes: The task progress evaluation unit is used to evaluate the progress of the observation task based on the execution result of the observation task, and obtain the progress evaluation result. The satellite status assessment unit is used to monitor the status of the working satellite in real time, so as to assess the status of the working satellite and obtain the status assessment result. The satellite resource assessment unit is used to send an intermediate assessment request to the working satellite and obtain intermediate resource assessment information fed back by the working satellite based on the intermediate assessment request. The mission continuation assessment unit is used to conduct a mission continuation assessment of the working satellite based on the progress assessment result, the status assessment result, and the intermediate resource assessment information, and obtain a continuation assessment result; if the continuation assessment result does not meet the mission continuation conditions, it is determined that there are resource constraints during the execution of the observation mission.

13. A computer device, characterized in that, include: A memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, the processor executing the computer instructions to perform the method of any one of claims 1 to 8.

14. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing a computer to perform the method of any one of claims 1 to 8.

15. An observation constellation, characterized in that, Task planning is performed using the method described in any one of claims 1 to 8.

Images