System and method to operate a drone

Patent metadata

Field	Value
Publication number	US-10545512-B2
Application number	US-201916386465-A
Country	US
Kind code	B2
Filing date	Apr 17, 2019
Priority date	Dec 8, 2015
Publication date	Jan 28, 2020
Grant date	Jan 28, 2020

Abstract

A method for controlling a drone includes receiving a request for information about a spatial location, generating data requests, configuring a flight plan and controlling one or more drones to fly over the spatial location to obtain data types based on the data requests, and extracting and analyzing data to answer the request. The method can include extracting data points from the data types, obtaining labels from a user for one or more of the data points, predicting labels for unlabeled data points from a learning algorithm using the labels obtained from the user, determining the predicted labels are true labels for the unlabeled data points and combining the extracted data, the user labeled data points and the true labeled data points to answer the request for information. The learning algorithm may be active learning using a support vector machine.

First claim

What is claimed is:

1. A computer implemented method for controlling one or more drones to respond to a request for information, comprising;
receiving a request for information about a spatial location;
generating a plurality of data requests corresponding to data necessary to answer the request;
configuring a first flight plan for one or more drones over the spatial location to obtain data from sensors based on the plurality of data requests;
controlling one or more drones to fly over the spatial location according to the configured flight plan to obtain the sensor data from the spatial location based on the plurality of data requests;
analyzing the obtained sensor data to determine whether the request for information can be answered with a degree of confidence equal to or above a threshold;
in a case in which the request for information can be answered with a degree of confidence equal to or above the threshold, analyzing the sensor data to provide an answer to the request for information; and
in a case in which the request for information can be answered with a degree of confidence below the threshold, generating at least one additional data request necessary to answer the request, configuring a second flight plan for one or more drones over the spatial location to obtain data from sensors based on the at least one additional data requests, controlling one or more drones to fly over the spatial location according to the configured flight plan to obtain the sensor data from the spatial location based on the at least one additional data requests, and analyzing the obtained sensor data to provide an answer to the request for information.

2. The computer implemented method of claim 1 , wherein the generating at least one additional data request necessary to answer the request is automatically generated by an active learning system.

3. The computer implemented method of claim 2 , wherein the configuring a flight plan for one or more drones over the spatial location to obtain data from sensors based on the at least one additional data requests is automatically configured by active learning.

4. The computer implemented method of claim 3 , wherein the active learning is provided by a support vector machine.

5. The computer implemented method of claim 3 , wherein the active learning is provided by semi-supervised machine learning.

6. The computer implemented method of claim 5 , wherein the semi-supervised machine learning includes interactively querying a user to obtain additional data requests.

7. The computer implemented method of claim 1 , further comprising:
receiving a natural language question relating to the spatial location;
receiving a plurality of requests for information relating to answering the natural language question;
searching sensor data obtainable by the at least one drone responsive to the plurality of requests for information;
analyzing the obtainable sensor data to determine whether the natural language question can be answered with a degree of confidence equal to or above a threshold;
in a case in which the natural language question can be answered with a degree of confidence equal to or above the threshold, configuring the first flight plan for one or more drones over the spatial location to obtain data from the sensors based on the plurality of data requests; and
in a case in which the natural language question can be answered with a degree of confidence below the threshold, generating at least one additional data request relating to answering the natural language question, and configuring a third flight plan for one or more drones over the spatial location to obtain data from sensors based on the plurality of data requests and the at least one additional data requests.

8. A non-transitory article of manufacture tangibly embodying computer readable instructions, which when implemented, cause a computer to perform the steps of a method for controlling one or more drones to respond to a request for information, comprising;
receiving a request for information about a spatial location;
generating a plurality of data requests corresponding to data necessary to answer the request;
configuring a first flight plan for one or more drones over the spatial location to obtain data from sensors based on the plurality of data requests;
controlling one or more drones to fly over the spatial location according to the configured flight plan to obtain the sensor data from the spatial location based on the plurality of data requests;
analyzing the obtained sensor data to determine whether the request for information can be answered with a degree of confidence equal to or above a threshold;
in a case in which the request for information can be answered with a degree of confidence equal to or above the threshold, analyzing the sensor data to provide an answer to the request for information; and
in a case in which the request for information can be answered with a degree of confidence below the threshold, generating at least one additional data request necessary to answer the request, configuring a second flight plan for one or more drones over the spatial location to obtain data from sensors based on the at least one additional data requests, controlling one or more drones to fly over the spatial location according to the configured flight plan to obtain the sensor data from the spatial location based on the at least one additional data requests, and analyzing the obtained sensor data to provide an answer to the request for information.

9. The non-transitory article of manufacture of claim 8 , wherein the generating at least one additional data request necessary to answer the request is automatically generated by an active learning system.

10. The non-transitory article of manufacture of claim 9 , wherein the configuring a flight plan for one or more drones over the spatial location to obtain data from sensors based on the at least one additional data requests is automatically configured by active learning.

11. The non-transitory article of manufacture of claim 10 , wherein the active learning is provided by a support vector machine.

12. The non-transitory article of manufacture of claim 10 , wherein the active learning is provided by semi-supervised machine learning.

13. The non-transitory article of manufacture of claim 12 , wherein the semi-supervised machine learning includes interactively querying a user to obtain additional data requests.

14. The non-transitory article of manufacture of claim 8 , further comprising:
receiving a natural language question relating to the spatial location;
receiving a plurality of requests for information relating to answering the natural language question;
searching sensor data obtainable by the at least one drone responsive to the plurality of requests for information;
analyzing the obtainable sensor data to determine whether the natural language question can be answered with a degree of confidence equal to or above a threshold;
in a case in which the natural language question can be answered with a degree of confidence equal to or above the threshold, configuring the first flight plan for one or more drones over the spatial location to obtain data from the sensors based on the plurality of data requests; and
in a case in which the natural language question can be answered with a degree of confidence below the threshold, generating at least one additional data request relating to answering the natural language question, and configuring a third flight plan for one or more drones over the spatial location to obtain data from sensors based on the plurality of data requests and the

Assignees

• IBM

Inventors

• Boland Gregory F
• Kozloski James R
• Ma Yu
• Manweiler Justin G
• Siemonsen Kevin E
• Topkara Umut
• Vogt Katherine
• Weisz Justin D

Classifications

• B64U2201/104

  using satellite radio beacon positioning systems, e.g. GPS · CPC title

• G06N7/01

  Probabilistic graphical models, e.g. probabilistic networks · CPC title

• G06N20/00

  Machine learning · CPC title

• G06F40/205

  Parsing · CPC title

• G05D1/104 Primary

  involving a plurality of aircrafts, e.g. formation flying (traffic control systems for aircraft G08G5/00) · CPC title