Search

CN-121998374-A - Self-intelligent driven constellation task planning method, device, equipment, medium and observation constellation

CN121998374ACN 121998374 ACN121998374 ACN 121998374ACN-121998374-A

Abstract

The application relates to the technical field of constellation task planning, and discloses a constellation task planning method with intelligent driving, which is used for responding to constellation task instructions, carrying out capability matching on remote sensing satellites to obtain candidate satellites, sending resource evaluation requests to the candidate satellites, obtaining satellite resource evaluation information of the candidate satellites, carrying out observation action planning to obtain an observation action list, sending the observation action list to a working satellite, executing the observation task, sending adjustment evaluation requests to the candidate satellites if the resource limitation condition exists in the execution process of the observation task, and carrying out 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 advantages that unified sensing and observation action planning are carried out on a plurality of remote sensing satellites based on satellite resource evaluation information, a complete autonomous decision-making closed loop is constructed on the satellites, the self intelligence of constellation level is realized, and the autonomy and the intelligence level of observation constellation are improved.

Inventors

  • LI CHAO
  • YAO KELU

Assignees

  • 之江实验室

Dates

Publication Date
20260508
Application Date
20260225

Claims (15)

  1. 1. The method is characterized by being applied to an observation constellation comprising a plurality of remote sensing satellites, and comprises the following steps of: Responding to a constellation task instruction indicating an observation task, performing capability matching on the remote sensing satellite to obtain candidate satellites capable of executing the observation task, and sending a resource evaluation request to the candidate satellites; Acquiring satellite resource evaluation information fed back by the candidate satellite based on the resource evaluation request, and planning observation actions of the candidate satellite according to the satellite resource evaluation information to obtain an observation action list of the observation constellation, wherein the observation action list corresponds to a working satellite for actually executing a task; transmitting the observation action list to the working satellite to instruct the working satellite to execute the observation task; If the resource limitation exists in the execution process of the observation task, sending an adjustment evaluation request to the candidate satellite, and carrying out action re-planning on the candidate satellite according to task adjustment evaluation information fed back by the candidate satellite based on the adjustment evaluation request so as to adjust the observation action list.
  2. 2. The method according to claim 1, wherein said planning the observation actions of the candidate satellites according to the satellite resource evaluation information to obtain an observation action list of the observation constellation comprises: Updating a satellite situation map of the observation constellation according to the satellite resource evaluation information to obtain a real-time situation map of the observation constellation; And performing task planning according to the real-time situation map and an observation task list to obtain the observation action list, wherein the observation task list corresponds to the constellation task instruction and is obtained by performing instruction analysis according to the constellation task instruction.
  3. 3. The method according to claim 2, wherein performing task planning according to the real-time situation map and the observation task list to obtain the observation action list includes: extracting candidate information according to the real-time situation map to obtain candidate state information of the candidate satellite; extracting task elements according to the observation task list to obtain task condition information of the observation task; And synthesizing a task planning prompt according to the candidate state information and the task condition information, sending the task planning prompt to a task planning large model, and carrying out task planning through the task planning large model so as to output the observation action list.
  4. 4. The method of claim 1, wherein said performing a capability match on said remote sensing satellite results in candidate satellites capable of performing said observation task, comprising: performing instruction analysis on the constellation task instruction to obtain an observation task list corresponding to the constellation task instruction; And performing capacity matching on the remote sensing satellite according to the observation task list and the constellation capacity map of the observation constellation to obtain the candidate satellite, wherein the constellation capacity map represents the remote sensing observation capacity of the remote sensing satellite.
  5. 5. The method of claim 4, wherein said parsing the constellation task instructions to obtain an observation task list corresponding to the constellation task instructions comprises: Carrying out semantic analysis on the constellation task instruction to obtain task intention and task elements about the observation task; inquiring geographic information based on the task elements to acquire geographic information about the observation task; And carrying out task planning on the observation task according to the task intention, the task elements and the geographic information to obtain the observation task list.
  6. 6. The method of claim 1, wherein determining whether a resource-constrained condition exists during execution of the observation task is performed by: Performing progress evaluation on the observation task according to the execution result of the observation task to obtain a progress evaluation result; Performing real-time state monitoring on the working satellite to perform state evaluation on the working satellite to obtain a state evaluation result; sending an intermediate evaluation request to the working satellite, and acquiring intermediate resource evaluation information fed back by the working satellite based on the intermediate evaluation request; And carrying out task continuous evaluation on the working satellite according to the progress evaluation result, the state evaluation result and the intermediate resource evaluation information to obtain a continuous evaluation result, and judging that the resource limitation exists in the execution process of the observation task under the condition that the continuous evaluation result does not meet the task continuous condition.
  7. 7. The method according to claim 6, wherein the performing the progress evaluation on the observation task according to the execution result of the observation task to obtain the progress evaluation result includes: after the observation constellation executes the observation task for a preset time, acquiring a task execution result of the working satellite in the preset time; Performing quality evaluation on the task execution result to obtain an execution quality evaluation result; And carrying out completion degree evaluation on the observation action list according to the execution quality evaluation result and the preset time to obtain the progress evaluation result.
  8. 8. The method of claim 6, wherein performing task continuation assessment on the working satellite according to the progress assessment result, the status assessment result and the intermediate resource assessment information to obtain a continuation assessment result comprises: comparing the state evaluation result with a safety state threshold value of the working satellite to obtain a state safety result of the working satellite; Under the condition that the state safety result indicates that the working satellite is in a healthy execution state, carrying out resource feasibility analysis on the working satellite according to the progress evaluation result and the intermediate resource evaluation information to obtain a resource feasibility result of the working satellite; And carrying out multidimensional evaluation on the working satellite according to the progress evaluation result and the resource feasibility result to obtain the continuous evaluation result.
  9. 9. The utility model provides a constellation task planning device that utensil intelligence was driven, its characterized in that is applied to the observation constellation that includes a plurality of remote sensing satellites, and the device includes: The instruction response matching module is used for responding to a constellation task instruction indicating an observation task, carrying out capability matching on the remote sensing satellite to obtain a candidate satellite capable of executing the observation task, and sending a resource evaluation request to the candidate satellite; The observation action planning module is used for acquiring satellite resource evaluation information fed back by the candidate satellite based on the resource evaluation request, and carrying out observation action planning on the candidate satellite according to the satellite resource evaluation information to obtain an observation action list of the observation constellation, wherein the observation action list corresponds to a working satellite for actually executing a task; The observation task execution module is used for sending the observation action list to the working satellite so as to instruct the working satellite to execute the observation task; And the observation action re-planning module is used for carrying out action re-planning, sending an adjustment evaluation request to the candidate satellite if the resource limitation exists in the execution process of the observation task, and carrying out action re-planning on the candidate satellite according to task adjustment evaluation information fed back by the candidate satellite based on the adjustment evaluation request so as to adjust the observation action list.
  10. 10. The apparatus of claim 9, wherein the observation action planning module comprises: the situation updating unit is used for updating the satellite situation map of the observation constellation according to the satellite resource evaluation information to obtain a real-time situation map of the observation constellation; And the task planning unit is used for carrying out task planning according to 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 carrying out instruction analysis according to the constellation task instruction.
  11. 11. The apparatus of claim 9, wherein the instruction response matching module comprises: the instruction analysis unit is used for carrying out instruction analysis on the constellation task instruction to obtain an observation task list corresponding to the constellation task instruction; And the capability matching unit is used for carrying out capability matching on the remote sensing satellite according to the observation task list and the constellation capability map of the observation constellation to obtain the candidate satellite, wherein the constellation capability map represents the remote sensing observation capability of the remote sensing satellite.
  12. 12. The apparatus of claim 9, wherein the observation action re-planning module comprises: The task progress evaluation unit is used for performing progress evaluation on the observation task according to the execution result of the observation task to obtain a progress evaluation result; the satellite state evaluation unit is used for carrying out real-time state monitoring on the working satellite so as to carry out state evaluation on the working satellite and obtain a state evaluation result; The satellite resource evaluation unit is used for sending an intermediate evaluation request to the working satellite and acquiring intermediate resource evaluation information fed back by the working satellite based on the intermediate evaluation request; And the task continuation evaluation unit is used for carrying out task continuation evaluation on the working satellite according to the progress evaluation result, the state evaluation result and the intermediate resource evaluation information to obtain a continuation evaluation result, and judging that the resource limitation condition exists in the execution process of the observation task under the condition that the continuation evaluation result does not meet the task continuation condition.
  13. 13. A computer device, comprising: A memory and a processor in communication with each other, the memory having stored therein computer instructions which, upon execution, cause the processor to perform the method of any of claims 1 to 8.
  14. 14. A computer readable storage medium having stored thereon computer instructions for causing a computer to perform the method of any one of claims 1 to 8.
  15. 15. An observation constellation characterized in that mission planning is performed by the method of any one of claims 1 to 8.

Description

Self-intelligent driven constellation task planning method, device, equipment, medium and observation constellation Technical Field The application relates to the technical field of constellation task planning, in particular to a method, a device, equipment, a medium and an observation constellation for constellation task planning with intelligent driving. Background For an observation constellation comprising a plurality of remote sensing satellites, when an observation task of a ground surface area is executed, a ground center is required to conduct action planning of the remote sensing satellites according to the observation task, and a planning result is conducted through communication interaction between the remote sensing satellites and the ground center so as to instruct the corresponding remote sensing satellites to execute the observation task according to the action planning result. In actual situations, on the one hand, communication interaction between the ground center and the remote sensing satellite must be performed within a specific window period, and the remote sensing satellite cannot receive the action planning result sent by the ground center within a time period beyond the window period, so that an observation task cannot be executed. On the other hand, the remote sensing satellite depends on the ground center to conduct motion planning, and the ground center cannot timely acquire information such as real-time state and resource information of the remote sensing satellite, so that the ground center cannot adjust motion planning results, and the remote sensing satellite cannot completely execute observation tasks. In the related art, the level of intellectualization of an observation constellation in performing an observation task is still to be improved. Disclosure of Invention The application provides a constellation task planning method, device, equipment, medium and observation constellation with intelligent driving, which are used for carrying out unified perception and observation action planning on a plurality of remote sensing satellites based on satellite resource evaluation information and carrying out multi-satellite action re-planning according to execution progress conditions, thereby constructing a complete autonomous decision-making closed loop on the satellite, realizing the intelligent with constellation level and improving the autonomy and intelligent level of the observation constellation. In order to achieve the above purpose, the main technical scheme adopted by the application comprises the following steps: in a first aspect, an embodiment of the present application provides a method for self-intelligent driven constellation task planning, which is applied to an observation constellation including a plurality of remote sensing satellites, where the method includes: Responding to a constellation task instruction indicating an observation task, performing capability matching on the remote sensing satellite to obtain candidate satellites capable of executing the observation task, and sending a resource evaluation request to the candidate satellites; Acquiring satellite resource evaluation information fed back by the candidate satellite based on the resource evaluation request, and planning observation actions of the candidate satellite according to the satellite resource evaluation information to obtain an observation action list of the observation constellation, wherein the observation action list corresponds to a working satellite for actually executing a task; transmitting the observation action list to the working satellite to instruct the working satellite to execute the observation task; If the resource limitation exists in the execution process of the observation task, sending an adjustment evaluation request to the candidate satellite, and carrying out action re-planning on the candidate satellite according to task adjustment evaluation information fed back by the candidate satellite based on the adjustment evaluation request so as to adjust the observation action list. The constellation task planning method with the intelligent driving body, provided by the embodiment of the application, is used for responding to a constellation task instruction indicating an observation task, determining candidate satellites capable of executing the observation task from the observation constellation, sending a resource evaluation request to the candidate satellites, carrying out observation action planning on the candidate satellites according to satellite resource evaluation information fed back by each candidate satellite after obtaining the satellite resource evaluation information, obtaining an observation action list to indicate corresponding working satellites to execute the observation task, and obtaining resource evaluation results of all the candidate satellites as a basis for action re-planning in the execution process of the observation task if any working satell