CN116187529A - Remote sensing satellite intelligent task management and control method based on intention understanding - Google Patents
Remote sensing satellite intelligent task management and control method based on intention understanding Download PDFInfo
- Publication number
- CN116187529A CN116187529A CN202211691004.XA CN202211691004A CN116187529A CN 116187529 A CN116187529 A CN 116187529A CN 202211691004 A CN202211691004 A CN 202211691004A CN 116187529 A CN116187529 A CN 116187529A
- Authority
- CN
- China
- Prior art keywords
- task
- intention
- remote sensing
- satellite
- resource
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06316—Sequencing of tasks or work
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Artificial Intelligence (AREA)
- Educational Administration (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention discloses an intelligent task management and control method of a remote sensing satellite based on intention understanding, which comprises the following steps: constructing an on-board domain knowledge system facing remote sensing application, and supporting on-board intelligent task decision based on intention understanding, namely realizing the intention understanding of the remote sensing task expressed by natural language under the support of the on-board domain knowledge system; by combining an on-board domain knowledge system, the remote sensing task intention of the natural language description of the ground surface is automatically decomposed into a programmable task list through a task list completion technology based on template matching understanding and machine learning and a task template matching technology.
Description
Technical Field
The invention relates to an intelligent task management and control for remote sensing satellites, which is based on an artificial intelligence technology.
Background
With the continuous development of aerospace technology and the increase of the number of in-orbit remote sensing satellites, the remote sensing satellites become indispensable information acquisition means in the applications of rescue and relief, resource environment census, ship navigation and the like, and particularly the emergency rescue requirements of rescue and relief and the like have extremely high timeliness. The current remote sensing satellite task adopts a task operation mode facing to instructions under foundation management and control, and the method mainly comprises the following steps:
1) A user puts forward a requirement or a request for earth observation;
2) The satellite management and control system collects the observation requirements set by a user according to a certain period, and then comprehensively considers task attributes (such as observation positions, spatial resolution and the like) of the observation requirements and the use constraints (such as maximum observation duration, side swing angle constraints and the like) of the satellites in the system to carry out satellite task planning and formulate a corresponding observation task plan;
3) And making a control instruction according to the observation task plan, uploading a satellite, executing and acquiring observation data by the satellite according to the instruction, downloading the observation data to the ground, processing the observation data and sending the observation data to a user.
It can be seen that the satellite management and control task is complex, and the pressure of measurement and control equipment personnel is high.
Along with the continuous increase of remote sensing satellites and remote sensing tasks, the limitation and the deficiency of the task operation mode facing the instruction in the rapid acquisition of the remote sensing information are gradually revealed.
1) However, with the increasing number of satellites and the demands of users, and the unpredictability of the demands of the satellite manager for users and the real-time nature and uncertainty of the demands of the users, the pressure faced by ground stations handling a large number of observation tasks increases dramatically if all satellite mission plans are formulated and uploaded by the ground stations.
2) The traditional ground planning and instruction uploading modes have the problems of poor timeliness, manpower consumption, low resource utilization rate, possibility of losing information in the transmission process and the like.
3) Due to the complexity of user demands, uncertainty and timeliness of observation targets, uncertainty of satellite resources, uncontrollability of external factors and the like, the problem of dynamic task planning based on intelligent remote sensing is very complex, and the conventional static ground planning has great defects in aspects of timeliness, robustness, fault tolerance, flexibility and the like.
Disclosure of Invention
The technical solution of the invention is as follows: the intelligent remote sensing satellite intelligent task management and control method based on the emergency remote sensing task intention understanding and autonomous task planning is provided, supports autonomous management and control oriented to macroscopic intention, has sufficient autonomy and degree of freedom in a ground authorization range, can autonomously decide to produce tasks and autonomously plan to execute tasks on orbit according to the general remote sensing task intention, improves autonomy of the remote sensing tasks, and can well meet application requirements of high-dynamic and high-aging disaster reduction remote sensing and the like.
The technical scheme of the invention is as follows: an intelligent task management and control method of a remote sensing satellite based on intention understanding comprises the following steps:
constructing an on-board domain knowledge system facing remote sensing application, and supporting on-board intelligent task decision based on intention understanding, namely realizing the intention understanding of the remote sensing task expressed by natural language under the support of the on-board domain knowledge system;
by combining an on-board domain knowledge system, the remote sensing task intention of the natural language description of the ground surface is automatically decomposed into a programmable task list through a task list completion technology based on template matching understanding and machine learning and a task template matching technology.
The construction of the remote sensing application-oriented on-board domain knowledge system supports on-board intelligent task decisions based on intention understanding, and comprises the following steps: and determining the domain of the knowledge system of the satellite domain by combining the knowledge background and the application requirement of the satellite remote sensing task domain, wherein the domain of the knowledge system of the satellite domain comprises a target library, a resource library, an understanding rule library and an intention template library.
The target library is used for combing the main target entity of the remote sensing application aiming at the knowledge service requirement of the main remote sensing object in the rescue and relief disaster and resource environment general investigation remote sensing application, and the class concept and the class attribute of the target entity are defined as follows:
the class concept is specifically: disaster frequent areas, resource census areas, provinces, cities, airports and ports;
the class attribute is specifically: the attributes of the disaster frequent regions comprise region names, geographic coordinate ranges, earth surface types and frequent disaster types, the attributes of the resource census regions comprise region names, geographic coordinate ranges and resource types, the attributes of the provinces comprise provinces names and geographic coordinates, the attributes of the cities comprise city names and geographic coordinate ranges, the airport attributes comprise airport names, airport categories, occupied areas and geographic coordinate ranges, and the port attributes comprise port names, port categories, occupied areas and geographic coordinate ranges.
The resource library is used for combing main resource entities of remote sensing applications according to knowledge service requirements of main satellite resources in the remote sensing applications for rescue and relief of disaster and resource environment, and class concepts and class attributes of the resource entities are defined as follows:
the class concept is specifically: remote sensing of satellite and satellite load;
the class attribute is specifically: the remote sensing satellite attributes comprise satellite names, semi-long axes, eccentricities, orbital inclinations, near-place amplitude angles, right ascent and intersection points and true near-point angles, and the satellite load attributes comprise load types, detection spectrum ranges, signal frequency bands, resolutions, breadth, view angles, incident angle ranges, working modes, roll pitching maneuver ranges and positioning accuracy.
The understanding rule base is used for combing a rule set facing task intention understanding of remote sensing tasks aiming at knowledge service requirements of task intention understanding in rescue and relief work and resource environment general investigation remote sensing applications, and the rule defines a mapping relation between remote sensing task intention types and intention templates, wherein the remote sensing task intention types are determined by combining business requirements of the rescue and relief work and resource environment general investigation remote sensing applications, and the method comprises resource environment general investigation, resource environment detailed investigation, continuous observation of heavy point areas such as disasters, abnormal condition early warning, rescue target search discovery, rescue target identification verification, abnormal target tracking monitoring and post-disaster condition assessment.
The intention template library is used for combing a template set facing the intention decomposition of a remote sensing task according to the knowledge service requirement of the task intention decomposition in the remote sensing application of rescue and relief and resource environment census, wherein the intention template comprises all element parameters serving the intention decomposition, including target elements, resource elements and task elements, the target elements comprise observation targets and are entities in the target library, the resource elements comprise appointed load types, and the task elements comprise task priorities, time domain requirements in the tasks and airspace requirements in the tasks.
Setting two intention templates according to the attribute of the intention, wherein the two intention templates comprise a single-resource intention template and a multi-resource intention template; the single resource intention template specifically comprises the following steps: when the task priority is medium or low, considering the resource constraint condition and the idle window, only one satellite resource is needed: an optical satellite or SAR satellite, optimizing and allocating to realize economic acquisition of target information; when task priority is high, multiple satellite resources are needed: and the optical satellite and the SAR satellite cooperatively realize the real-time acquisition of the target information.
The remote sensing task intention of the natural language description of the ground surface is automatically decomposed into a programmable task list by combining the on-board domain knowledge system through a task list completion technology based on template matching understanding and machine learning and a task template matching technology, and the remote sensing task intention comprises the following steps:
receiving remote sensing task intention information of natural language description uploaded on the ground;
extracting an observation target and task intention type keywords from remote sensing task intention information by using a natural language word segmentation processing technology;
matching intention types through keyword information, intelligently selecting the most suitable intention template according to the intention types to match and expand, and preliminarily outputting structured intention information;
according to the corresponding intention template in the intention template library, applying rule fusion and machine learning algorithm to instantiate important parameters of the intention, wherein the important parameters comprise an observation target, task priority, task effective time period, observation period, duration, spatial resolution and imaging quality requirements, and a programmable task set of an optical satellite or SAR satellite is obtained and directly used as input of autonomous task planning.
Compared with the prior art, the invention has the advantages that:
1) Based on intelligent design and autonomous technology, the command operation control program of the remote sensing satellite can be simplified, the task response time is shortened, the optimal human-computer interface between space facility user and the intelligent remote sensing satellite system is realized, ground station staff is liberated from the complicated satellite operation control task, and more energy is focused on the global command decision of emergency tasks such as emergency disaster relief and the like.
2) The intelligent remote sensing satellite system is endowed with more autonomy, can be responsible for specific task details, realizes the control from 'many-to-one', 'one-to-one' instruction remote control to 'one-control-multiple' task control, and then reaches the 'autonomous action' of the satellite, fully utilizes the respective advantages of people and the satellite, and achieves optimization, synergy and complementation.
Therefore, the intelligent task management and control method for the remote sensing satellite based on intent understanding is an innovative satellite operation and control system which is provided for reducing the high dependence of the remote sensing satellite system on ground task management and control and improving the autonomy and flexibility of the on-orbit task execution of the remote sensing satellite system, so that the remote sensing satellite can provide more efficient, autonomous and intelligent service in emergency application.
Drawings
FIG. 1 is a flow chart of knowledge representation and ontology modeling of an on-board knowledge system for remote sensing tasks;
fig. 2 is a flow chart for remote sensing satellite intelligent task decision control based on intent understanding.
Detailed Description
The intelligent remote sensing satellite takes an on-board knowledge system facing the remote sensing task as a knowledge data basis, directly receives remote sensing task intention information of a ground user, carries out understanding to form knowledge information, can further carry out knowledge analysis and understanding to generate decision information, and further generates an executable task list, so that the remote sensing satellite has efficient, autonomous and intelligent task decision-making and executing capabilities.
(1) And constructing an on-board domain knowledge system facing remote sensing application, and supporting on-board intelligent task decision based on intention understanding. The specific steps are shown in figure 1.
1) The knowledge system category of the satellite field is determined by combining the knowledge background and the application requirement of the satellite remote sensing task field, and the knowledge system category mainly comprises a target library, a resource library, an understanding rule library and an intention template library.
2) The target library in step 1) is used for combing main target entities of remote sensing application according to knowledge service requirements of main remote sensing objects in rescue and relief work and resource environment general investigation remote sensing application, and class concepts and class attributes of the main target entities are defined as follows:
the class concept is specifically: disaster frequent areas, resource census areas, provinces, cities, airports and ports;
the class attribute is specifically: the attributes of the disaster frequent regions comprise region names, geographic coordinate ranges, earth surface types and frequent disaster types, the attributes of the resource census regions comprise region names, geographic coordinate ranges and resource types, the attributes of the provinces comprise provinces names and geographic coordinates, the attributes of the cities comprise city names and geographic coordinate ranges, the airport attributes comprise airport names, airport categories, occupied areas and geographic coordinate ranges, and the port attributes comprise port names, port categories, occupied areas and geographic coordinate ranges.
2) The resource library in step 1) is used for combing main resource entities of remote sensing applications according to knowledge service requirements of main satellite resources in rescue and relief work and general investigation of resource environment, and class concepts and class attributes of the main resource entities are defined as follows:
the class concept is specifically: remote sensing of satellite and satellite load;
the class attribute is specifically: the remote sensing satellite attributes comprise satellite names, semi-long axes, eccentricities, orbital inclinations, near-place amplitude angles, right ascent and intersection points and true near-point angles, and the satellite load attributes comprise load types, detection spectrum ranges, signal frequency bands, resolutions, breadth, view angles, incident angle ranges, working modes, roll pitching maneuver ranges and positioning accuracy.
3) The understanding rule base is described in step 1), and a rule set facing the understanding of the intention of a remote sensing task is combed according to the knowledge service requirement of the intention of the task in the remote sensing application of rescue and relief work and resource environment census, wherein the rule defines the mapping relation between the intention type of the remote sensing task and the intention template, and the intention type of the remote sensing task is determined by combining the service requirement of the rescue and relief work and the resource environment census remote sensing application, and the rule set comprises continuous observation of heavy point areas such as resource environment census, resource environment detailed investigation, disasters, abnormal condition early warning, rescue target search discovery, rescue target identification verification, abnormal target tracking monitoring and post-disaster condition assessment.
4) The intention template library in step 1) is used for combing a template set facing the intention decomposition of a remote sensing task according to the knowledge service requirement of the task intention decomposition in the remote sensing application of rescue and relief work and resource environment census, wherein the intention template comprises all element parameters serving the intention decomposition and comprises target elements, resource elements and task elements, the target elements comprise observation targets, the entity in the target library in step 2), the resource elements comprise appointed load types, and the task elements comprise task priorities, time domain requirements (effective time deadlines, observation periods and duration) in the tasks and airspace requirements (spatial resolution and imaging quality) in the tasks.
5) Two intention templates are set according to the attribute of the intention, including a single-resource intention template and a multi-resource intention template. The single resource intention template specifically comprises the following steps: when the task priority is medium or low, considering the resource constraint condition and the idle window, only one satellite resource is needed: an optical satellite or SAR satellite, optimizing and allocating to realize economic acquisition of target information; when task priority is high, multiple satellite resources are needed: and the optical satellite and the SAR satellite cooperatively realize the real-time acquisition of the target information.
(2) The remote sensing satellite intelligent task decision based on intention understanding refers to realizing the intention understanding of the remote sensing task expressed by natural language under the support of the knowledge system of the field on the satellite as described in the step (1). By combining an on-board domain knowledge system, the remote sensing task intention of the natural language description of the ground surface is automatically decomposed into a programmable task list through a task list completion technology based on template matching understanding and machine learning and a task template matching technology. The specific flow is shown in fig. 2.
1) Receiving remote sensing task intention information of natural language description uploaded on the ground;
2) Extracting an observation target and task intention type keywords from remote sensing task intention information by using a natural language word segmentation processing technology;
3) Matching intention types through keyword information, intelligently selecting the most suitable intention template according to the intention types to match and expand, and preliminarily outputting structured intention information;
4) According to the corresponding intention template in the intention template library, rule fusion and machine learning algorithms are applied to instantiate important parameters of the intention, wherein the important parameters comprise an observation target, task priority, task effective time period, observation period, duration, spatial resolution and imaging quality requirements, and a programmable task set of an optical satellite or SAR satellite is obtained and can be directly used as input of autonomous task planning.
What is not described in detail in the present specification is a well known technology to those skilled in the art.
Claims (8)
1. The remote sensing satellite intelligent task management and control method based on intention understanding is characterized by comprising the following steps of:
constructing an on-board domain knowledge system facing remote sensing application, and supporting on-board intelligent task decision based on intention understanding, namely realizing the intention understanding of the remote sensing task expressed by natural language under the support of the on-board domain knowledge system;
by combining an on-board domain knowledge system, the remote sensing task intention of the natural language description of the ground surface is automatically decomposed into a programmable task list through a task list completion technology based on template matching understanding and machine learning and a task template matching technology.
2. The method for controlling intelligent tasks of remote sensing satellites based on intention understanding according to claim 1, wherein the constructing an on-board domain knowledge system facing remote sensing applications, supporting on-board intelligent task decisions based on intention understanding, comprises: and determining the domain of the knowledge system of the satellite domain by combining the knowledge background and the application requirement of the satellite remote sensing task domain, wherein the domain of the knowledge system of the satellite domain comprises a target library, a resource library, an understanding rule library and an intention template library.
3. The remote sensing satellite intelligent task management and control method based on intention understanding according to claim 2, wherein the target library is used for combing main target entities of remote sensing applications aiming at knowledge service requirements of main remote sensing objects in rescue and relief work and resource environment census remote sensing applications, and class concepts and class attributes of the target entities are defined as follows:
the class concept is specifically: disaster frequent areas, resource census areas, provinces, cities, airports and ports;
the class attribute is specifically: the attributes of the disaster frequent regions comprise region names, geographic coordinate ranges, earth surface types and frequent disaster types, the attributes of the resource census regions comprise region names, geographic coordinate ranges and resource types, the attributes of the provinces comprise provinces names and geographic coordinates, the attributes of the cities comprise city names and geographic coordinate ranges, the airport attributes comprise airport names, airport categories, occupied areas and geographic coordinate ranges, and the port attributes comprise port names, port categories, occupied areas and geographic coordinate ranges.
4. The remote sensing satellite intelligent task management and control method based on intention understanding according to claim 2, wherein the resource library is used for combing main resource entities of remote sensing applications aiming at knowledge service requirements of main satellite resources in rescue and relief work and resource environment census remote sensing applications, and class concepts and class attributes of the resource entities are defined as follows:
the class concept is specifically: remote sensing of satellite and satellite load;
the class attribute is specifically: the remote sensing satellite attributes comprise satellite names, semi-long axes, eccentricities, orbital inclinations, near-place amplitude angles, right ascent and intersection points and true near-point angles, and the satellite load attributes comprise load types, detection spectrum ranges, signal frequency bands, resolutions, breadth, view angles, incident angle ranges, working modes, roll pitching maneuver ranges and positioning accuracy.
5. The remote sensing satellite intelligent task management and control method based on intention understanding according to claim 2, wherein the understanding rule base is used for combing a rule set facing task intention understanding of remote sensing tasks according to knowledge service requirements of task intention understanding in rescue and relief work and resource environment general investigation remote sensing applications, and rules define a mapping relation between remote sensing task intention types and intention templates, wherein the remote sensing task intention types are combined with service requirements of rescue and relief work and resource environment general investigation remote sensing applications, and the method comprises resource environment general investigation, resource environment detailed investigation, continuous observation of heavy areas such as disasters, abnormal condition early warning, rescue target search discovery, rescue target identification verification, abnormal target tracking monitoring and post-disaster condition assessment.
6. The remote sensing satellite intelligent task management and control method based on intention understanding according to claim 2, wherein the intention template library is used for combing a template set facing the intention decomposition of a remote sensing task according to knowledge service requirements of the intention decomposition of the task in rescue and relief and resource environment census remote sensing applications, the intention template comprises all element parameters serving the intention decomposition, including target elements, resource elements and task elements, wherein the target elements comprise observation targets and are entities in the target library, the resource elements comprise appointed load types, and the task elements comprise task priorities, time domain requirements in the task and space domain requirements in the task.
7. The remote sensing satellite intelligent task management and control method based on intention understanding according to claim 6, wherein two intention templates are set according to the attribute of intention itself, including a single resource intention template and a multi-resource intention template; the single resource intention template specifically comprises the following steps: when the task priority is medium or low, considering the resource constraint condition and the idle window, only one satellite resource is needed: an optical satellite or SAR satellite, optimizing and allocating to realize economic acquisition of target information; when task priority is high, multiple satellite resources are needed: and the optical satellite and the SAR satellite cooperatively realize the real-time acquisition of the target information.
8. The remote sensing satellite intelligent task management and control method based on intention understanding according to claim 2, wherein the remote sensing task intention of the natural language description of the ground is automatically decomposed into a programmable task list by combining an on-board domain knowledge system through a task list completion technology based on template matching understanding and machine learning and a task template matching technology, and the method comprises the following steps:
receiving remote sensing task intention information of natural language description uploaded on the ground;
extracting an observation target and task intention type keywords from remote sensing task intention information by using a natural language word segmentation processing technology;
matching intention types through keyword information, intelligently selecting the most suitable intention template according to the intention types to match and expand, and preliminarily outputting structured intention information;
according to the corresponding intention template in the intention template library, applying rule fusion and machine learning algorithm to instantiate important parameters of the intention, wherein the important parameters comprise an observation target, task priority, task effective time period, observation period, duration, spatial resolution and imaging quality requirements, and a programmable task set of an optical satellite or SAR satellite is obtained and directly used as input of autonomous task planning.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211691004.XA CN116187529A (en) | 2022-12-27 | 2022-12-27 | Remote sensing satellite intelligent task management and control method based on intention understanding |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211691004.XA CN116187529A (en) | 2022-12-27 | 2022-12-27 | Remote sensing satellite intelligent task management and control method based on intention understanding |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116187529A true CN116187529A (en) | 2023-05-30 |
Family
ID=86435597
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211691004.XA Pending CN116187529A (en) | 2022-12-27 | 2022-12-27 | Remote sensing satellite intelligent task management and control method based on intention understanding |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116187529A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116432993A (en) * | 2023-06-15 | 2023-07-14 | 南京北斗创新应用科技研究院有限公司 | Space-earth integrated observation resource collaborative scheduling method and system |
| CN118245933A (en) * | 2024-05-20 | 2024-06-25 | 中国科学院空天信息创新研究院 | Optical remote sensing data segmentation method, device, equipment and medium |
-
2022
- 2022-12-27 CN CN202211691004.XA patent/CN116187529A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116432993A (en) * | 2023-06-15 | 2023-07-14 | 南京北斗创新应用科技研究院有限公司 | Space-earth integrated observation resource collaborative scheduling method and system |
| CN116432993B (en) * | 2023-06-15 | 2023-11-03 | 南京北斗创新应用科技研究院有限公司 | Space-earth integrated observation resource collaborative scheduling method and system |
| CN118245933A (en) * | 2024-05-20 | 2024-06-25 | 中国科学院空天信息创新研究院 | Optical remote sensing data segmentation method, device, equipment and medium |
| CN118245933B (en) * | 2024-05-20 | 2024-08-13 | 中国科学院空天信息创新研究院 | Optical remote sensing data segmentation method, device, equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116187529A (en) | Remote sensing satellite intelligent task management and control method based on intention understanding | |
| CN108229685B (en) | Air-ground integrated unmanned intelligent decision-making method | |
| WO2019127945A1 (en) | Structured neural network-based imaging task schedulability prediction method | |
| CN102780523A (en) | Multi-satellite cooperative observation business scheduling method | |
| CN113283666B (en) | Heuristic intelligent task reasoning and decision-making method for satellite group | |
| CN107506892A (en) | It is a kind of towards the ground integrated Intelligent control system of quiet rail Optical remote satellite star | |
| US20220035367A1 (en) | Coordination of remote vehicles using automation level assignments | |
| CN102436531A (en) | Hyperspectral data simulation and application platform based on distribution assembly | |
| Guo et al. | Study on landscape architecture model design based on big data intelligence | |
| Williams | Collaborative multi-robot multi-human teams in search and rescue. | |
| Thangavel et al. | Artificial intelligence for trusted autonomous satellite operations | |
| Zheng et al. | Robustness of the planning algorithm for ocean observation tasks | |
| CN114580208A (en) | On-satellite autonomous task generation method and system for ocean moving target | |
| CN112180987B (en) | Collaborative operation method, collaborative operation system, collaborative operation device, collaborative operation computer equipment and collaborative operation storage medium | |
| Martin | Satellite image collection optimization | |
| US11812331B2 (en) | Method and apparatus for map query and electronic device | |
| Zhang et al. | Satellite group autonomous operation mechanism and planning algorithm for marine target surveillance | |
| Niu et al. | Multi-satellite observation scheduling for large area disaster emergency response | |
| CN115097753A (en) | Teleoperation method and device for lunar surface inspection device, storage medium and processor | |
| Antonov et al. | A method for controlling groups of unmanned aerial vehicles in a virtual environment using haptic gloves | |
| Li et al. | Research on intelligent monitoring system of hydraulic engineering based on digital twin | |
| He et al. | Auto mission planning system design for imaging satellites and its applications in environmental field | |
| Meng et al. | Architecture and key technologies for the mission planning system of space sensor network | |
| CN115562334B (en) | Unmanned plane cluster task cooperation method and system oriented to multi-source disaster situation data fusion | |
| Chen et al. | A Collaborative Search and Rescue Method for Maritime Multi-Unmanned Platforms Based on MDLS Algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |