SATELLITE SCHEDULING SYSTEM USING CROWD-SOURCED DATA

• US 20140040282A1
• Filed: 08/02/2013
• Published: 02/06/2014
• Est. Priority Date: 08/03/2012
• Status: Active Grant

• Current Assignee: Planet Labs PBC
• Original Assignee: Skybox Imaging, Inc. (Planet Labs PBC)
• Inventors: Mann, Julian M., Berkenstock, Daniel, Augenstein, Sean
• Granted Patent: US 8,977,619 B2
• Time in Patent Office: Days
• US Class Current: 707/748
• CPC Class Codes: B64G 1/1021 Earth observation satellites
• CPC Class Codes: B64G 1/1085 Swarms and constellations
• CPC Class Codes: B64G 1/242 Orbits and trajectories
• CPC Class Codes: G06F 16/29 Geographical information databases
• CPC Class Codes: G06Q 10/06314 Calendaring for a resource
• CPC Class Codes: Y10S 707/919 Geographic
• CPC Class Codes: Y10S 707/921 Spatial

Abstract

Examples of satellite scheduling systems are provided that use crowd-sourced data to generate image acquisition events for a network of imaging satellites. A crowd-sourcing system may utilize crowd-sourced data (e.g., messages generated by users of social network services) to determine events of interest and geographic locations of such events. Event data may then be used to create or update image acquisition tasks and/or task priorities which are automatically provided to a scheduling system to facilitate timely and responsive acquisition of overhead images of the geographic location of the event. The scheduling system can utilize a directed acyclic graph to increase or maximize a utilization function, which can lead to determination of optimal or near-optimal schedules in a relatively quick and efficient manner.

Claims

1. A method for using crowd-sourced data to automatically schedule an image acquisition event in a constellation of imaging micro-satellites, the method comprising:

accessing crowd-sourced data;

analyzing the crowd-sourced data to determine an event of interest;

determining a geographic location for the event of interest using the crowd-sourced data;

determining a degree of relevance for the event of interest;

creating an image acquisition request, wherein the image acquisition request comprises (1) the determined geographic location of the event of interest and (2) a task priority based at least in part on the determined degree of relevance for the event of interest; and

automatically providing via a machine-to-machine interface the image acquisition request to a scheduling system associated with the constellation of imaging micro-satellites, the scheduling system operable to generate an image acquisition task associated with the determined geographic location for at least one imaging micro-satellite in the constellation of imaging micro-satellites,

wherein the method is performed under control of a crowd-sourcing system comprising computing hardware.

2. The method of claim 1, wherein analyzing the crowd-sourced data to determine an event of interest comprises:

generating a list of terms from textual data within the crowd-sourced data;

determining a frequency of use within the crowd-sourced data for each term in the list of terms;

comparing the frequency of use for each term in the list of terms to a baseline frequency of use; and

identifying an event of interest when an event-related term in the list of terms has a frequency that exceeds an interest threshold over the baseline frequency of use.

3. The method of claim 2, wherein the interest threshold is at least 110% of the baseline frequency of use.

4. The method of claim 1, wherein analyzing the crowd-sourced data to determine an event of interest comprises:

searching for a list of keywords in the crowd-sourced data;

determining a frequency of use of each of the keywords in the list of keywords in the crowd-sourced data;

identifying an event of interest when the frequency of use of an event-related keyword exceeds a baseline threshold.

5. The method of claim 1, wherein determining the geographic location of the event of interest using the crowd-sourced data comprises identifying statistically significant anomalies in geographic tagging trends.

6. The method of claim 1, wherein determining a degree of relevance for the event of interest comprises using sentiment analysis to assess a relative importance of the event of interest.

7. The method of claim 1, wherein the method is performed in near real-time to generate the image acquisition request.

8. The method of claim 1, wherein the crowd-sourced data is accessed and analyzed on a periodic basis automatically without intervening input from a user.

9. The method of claim 1, wherein the event of interest is an environmental disaster, a political revolution, a social uprising, or an event having a sociocultural impact on a community.

10. The method of claim 1, wherein the scheduling system utilizes a directed acyclic graph to generate the image acquisition task.

11. A system for using crowd-sourced data to automatically generate an image acquisition request for a satellite scheduling system, the system comprising:

a computing device;

a network input/output device configured to retrieve over a network crowd-sourced data from one or more data sources;

a crowd-sourced data analysis module configured to use the computing device to;

analyze the crowd-sourced data to determine an event of interest;

determine a geographic location for the event of interest using the crowd-sourced data; and

create an image acquisition request comprising the determined geographic location of the event of interest and a task priority; and

a machine-to-machine interface configured to automatically provide the image acquisition request to the satellite scheduling system.

12. The system of claim 11, wherein the crowd-sourced data analysis module is configured to determine the geographic location by identifying statistically significant anomalies in geographic tagging trends.

13. The system of claim 11, wherein the crowd-sourced data analysis module is configured to the degree of relevance by using sentiment analysis to assess a relative importance of the event of interest.

14. The system of claim 11, wherein the image acquisition request is created in near real-time.

15. The system of claim 11, wherein the crowd-sourced data is accessed and analyzed on a periodic basis automatically without intervening input from a user.

16. A system for scheduling events for imaging satellites, the system comprising:

non-transitory data storage configured to store crowd-sourced data related to events; and

a physical computing system in communication with the non-transitory data storage, the physical computing system configured to;

analyze the crowd-sourced data for trends indicating one or more socially significant events;

determine a geographic location for each of the socially significant events;

determine a degree of relevance for each of the socially significant events;

create an image acquisition task, wherein the image acquisition task comprises at least (1) the determined geographic location corresponding to one or more of the socially significant events and (2) a task priority based at least in part on the determined degree of relevance for the one or more socially significant events; and

provide the image acquisition task to a scheduling system associated with the imaging satellites, the scheduling system operable to generate for the imaging satellites a schedule of tasks which includes at least the image acquisition task.

17. The system of claim 16, further comprising a machine-to-machine interface configured to communicate the image acquisition task to the scheduling system.

18. The system of claim 16, wherein the scheduling system is configured to use a directed acyclic graph to produce the schedule of tasks.

19. The system of claim 18, wherein at least one task is such that all acceptable paths through the directed acyclic graph pass through the task.

20. The system of claim 18, wherein the scheduling system generates the schedule of tasks subject to pair-wise constraints and cumulative constraints.

21. The system of claim 20, wherein the cumulative constraints include one of a data capacity limitation, a power requirement, or a thermal value.

22. The system of claim 20, wherein the pair-wise constraints include a slewing rate of one of the imaging satellites.

23. The system of claim 16, wherein the physical computing system is configured to create the image acquisition task in near real-time.

24. The system of claim 16, wherein the crowd-sourced data is analyzed on a periodic basis automatically without intervening input from a user.

25. A method for generating an image acquisition request, the method performed under control of a crowd-sourcing system comprising computing hardware including one or more physical processors, the method comprising:

analyzing crowd-sourced data to determine a location of an event of interest;

ranking the event of interest;

creating an image acquisition request comprising the determined location and the ranking of the event of interest; and

providing via a machine-to-machine interface the image acquisition request to a scheduling system,

wherein the event of interest is determined and the image acquisition request is provided to the scheduling system without intervening input from a user.

26. The method of claim 25, wherein the event of interest is a political event, a social event, an environmental event, an astronomical event, or a sociocultural event having an impact on a community.

27. The method of claim 25, wherein the crowd-sourced data comprises at least data generated by one or more users of a social network, data generated by one or more users of a web service, data published in a web blog, or data published on an online news website.