Data driven airplane intent inferencing

• US 9,691,286 B2
• Filed: 04/22/2015
• Issued: 06/27/2017
• Est. Priority Date: 04/22/2015
• Status: Active Grant

• Current Assignee: The Boeing Co.
• Original Assignee: The Boeing Co.
• Inventors: Safa-Bakhsh, Robab, Parks, Paul C., Bahrami, Ali, Yuan, Jun
• Primary Examiner(s): Hilgendorf, Dale W
• Application Number:
  US14/692,894
• Publication Number:
  US 20160314692A1
• Time in Patent Office: 797 Days
• CPC Class Codes: G01C 23/00 Combined instruments indicating more than one navigational value, e.g. for aircraft; Combined measuring devices for measuring two or more variables of movement, e.g. distance, speed or acceleration
• CPC Class Codes: G01C 23/005 Flight directors indicating arrangements specially adapted for rotary gyroscopes G01C19/32
• CPC Class Codes: G08G 5/0013 with a ground station
• CPC Class Codes: G08G 5/0017 Arrangements for implementing traffic-related aircraft activities, e.g. arrangements for generating, displaying, acquiring or managing traffic information head-up displays G02B27/01; ground or aircraft-carrier-deck-installations B64F
• CPC Class Codes: G08G 5/0021 located in the aircraft
• CPC Class Codes: G08G 5/0026 located on the ground
• CPC Class Codes: G08G 5/0043 Traffic management of multiple aircrafts from the ground G08G5/003 takes precedence; data processing specially designed for resource management, e.g. scheduling or allocating time, human or machine resources G06Q10/06
• CPC Class Codes: G08G 5/0052 for cruising combined instruments indicating more than one navigational value G01C23/00
• CPC Class Codes: G08G 5/0082 for monitoring traffic from a ground station radar or analogous systems specially adapted for traffic control G01S13/91
• CPC Class Codes: G08G 5/04 Anti-collision systems
• CPC Class Codes: G08G 5/045 Navigation or guidance aids, e.g. determination of anti-collision manoeuvers radar or analogous systems specially adapted for anti-collision between aircraft G01S13/933

Abstract

Method, system and computer program product for providing a predicted vehicle track and for providing alerts when two predicted vehicle tracks are closer than a threshold amount. A vehicle intent prediction model is generated based on past instance of tracks for a vehicle operation, known vehicle intent data for the past instances, and contextual factors, such as weather, airline operator, air vehicle type or configuration, day of the week, etc. for the past instances. The vehicle intent prediction model can be generated using one or more machine learning algorithms. A future vehicle trajectory for a current vehicle operation can be output by the vehicle intent prediction model using the current track and existing contextual factors for the current vehicle operation. In the event that two vehicles following their respective predicted vehicle future trajectories would be closer than a threshold distance, an alert can be provided.

Claims

1. A computer-implemented method for vehicle intent prediction, the method comprising:

accessing, using a computer processor, vehicle intent prediction models for different vehicle operations, wherein the vehicle intent prediction models are based on past instances of vehicle tracks for the vehicle operations and known vehicle intent data for the past instances, wherein the known vehicle intent data comprises at least one of aircraft flight control surface positions, engine power setting, aircraft flight mode, flight management computer (FMC) control inputs, and pilot control inputs;

for a current operation of a first of the different vehicle operations, predicting in real time a first vehicle intent, based on current vehicle track data for the first vehicle operation and the accessed vehicle intent prediction model for the first vehicle operation;

predicting a first future vehicle trajectory based on the predicted first vehicle intent; and

displaying the predicted first future vehicle trajectory on a computer display.

2. The computer-implemented method of claim 1, wherein the vehicle intent prediction models for different vehicle operations are further based on at least one contextual factor, and wherein the predicted first vehicle intent is based on the current vehicle track data for the first vehicle operation, at least one current contextual factor applicable to the current first vehicle operation, and the accessed vehicle intent prediction model for the first vehicle operation.

3. The computer-implemented method of claim 1, further comprising:

for a current operation of a second of the different vehicle operations, predicting a second vehicle intent, based on current vehicle track data for the second vehicle operation and the accessed vehicle intent prediction model for the second vehicle operation;

predicting a second future vehicle trajectory based on the predicted second vehicle intent; and

upon determining that the predicted first future vehicle trajectory and the predicted second future vehicle trajectory are closer than a threshold limit, generating an alert.

4. The computer-implemented method of claim 3, wherein the threshold limit is user configurable.

5. The computer-implemented method of claim 3, wherein the vehicle intent prediction models for different vehicle operations are further based on at least one contextual factor;

wherein the predicted first vehicle intent is based on the current vehicle track data for the first vehicle operation, at least one current contextual factor applicable to the first vehicle operation, and the accessed vehicle intent prediction model for the first vehicle operation; and

wherein the predicted second vehicle intent is based on the current vehicle track data for the second vehicle operation, at least one current contextual factor applicable to the second vehicle operation, and the accessed vehicle intent prediction model for the first vehicle operation.

6. The computer-implemented method of claim 1, further comprising generating the vehicle intent prediction models for the different vehicle operations, wherein the vehicle operations are flights of commercial aircraft, and wherein the known vehicle intent includes at least one of:

aircraft flight control surface positions;

engine power setting;

aircraft flight mode;

flight management computer (FMC) control inputs; and

pilot control inputs.

7. The computer-implemented method of claim 1, further comprising generating the vehicle intent prediction models for the different vehicle operations, wherein generating vehicle intent prediction models comprises performing a multilayer perceptron and resilient propagation analysis of the past instances of vehicle tracks and the known vehicle intent data.

8. The computer-implemented method of claim 1, further comprising receiving actual vehicle intent data;

and

upon the received actual vehicle intent data differing from the predicted vehicle intent, generating an alert.

9. A computer program product for predicting vehicle intent, the computer program product comprising:

a computer-readable storage medium having computer-readable program code embodied therewith, the computer-readable program code executable by one or more computer processors to;

access vehicle intent prediction models for different vehicle operations, wherein the vehicle intent prediction models are based on past instances of vehicle tracks for the vehicle operations and known vehicle intent data for the past instances, wherein the known vehicle intent data comprises at least one of aircraft flight control surface positions, engine power setting, aircraft flight mode, flight management computer (FMC) control inputs, and pilot control inputs;

for a current operation of a first of the different vehicle operations, predict in real time a first vehicle intent, based on current vehicle track data for the first vehicle operation and the accessed vehicle intent prediction model for the first vehicle operation;

predict a first future vehicle trajectory based on the predicted first vehicle intent; and

output for display the predicted first future vehicle trajectory on a computer display.

10. The computer program product of claim 9, wherein the vehicle intent prediction models for different vehicle operations are further based on at least one contextual factor, and wherein the predicted first vehicle intent is based on the current vehicle track data for the first vehicle operation, at least one current contextual factor applicable to the current first vehicle operation, and the accessed vehicle intent prediction model for the first vehicle operation.

11. The computer program product of claim 9, wherein the computer-readable program code is further executable to:

for a current operation of a second of the different vehicle operations, predict a second vehicle intent, based on current vehicle track data for the second vehicle operation and the accessed vehicle intent prediction model for the second vehicle operation;

predict a second future vehicle trajectory based on the predicted second vehicle intent; and

upon determining that the predicted first future vehicle trajectory and the predicted second future vehicle trajectory are closer than a threshold limit, generate an alert.

12. The computer program product of claim 11, wherein the threshold limit is user configurable.

13. The computer program product of claim 11, wherein the vehicle intent prediction models for different vehicle operations are further based on at least one contextual factor;

wherein the predicted first vehicle intent is based on the current vehicle track data for the first vehicle operation, at least one current contextual factor applicable to the first vehicle operation, and the accessed vehicle intent prediction model for the first vehicle operation; and

wherein the predicted second vehicle intent is based on the current vehicle track data for the second vehicle operation, at least one current contextual factor applicable to the second vehicle operation, and the accessed vehicle intent prediction model for the first vehicle operation.

14. The computer program product of claim 9, wherein the computer-readable program code is further executable to generate the vehicle intent prediction models for the different vehicle operations, wherein the vehicle operations are flights of commercial aircraft, and wherein the known vehicle intent includes at least one of:

aircraft flight control surface positions;

engine power setting;

aircraft flight mode;

flight management computer (FMC) control inputs; and

pilot control inputs.

15. The computer program product of claim 9, wherein the computer-readable program code is further executable to generate the vehicle intent prediction models for the different vehicle operations, wherein the vehicle intent prediction models are generated by performing a multilayer perceptron and resilient propagation analysis of the past instances of vehicle tracks and the known vehicle intent data.

16. The computer program product of claim 9, wherein the computer-readable program code is further executable to receive actual vehicle intent data;

and

upon the received actual intent data differing from the predicted vehicle intent, generating an alert.

17. A system, comprising:

memory storing past instances of vehicle tracks for various vehicle operations and known vehicle intent data for the past instances; and

a processor configured to;

access vehicle intent prediction models for different vehicle operations, wherein the vehicle intent prediction models are based on the past instances of vehicle tracks for the vehicle operations and the known vehicle intent data for the past instances, wherein the known vehicle intent data comprises at least one of aircraft flight control surface positions, engine power setting, aircraft flight mode, flight management computer (FMC) control inputs, and pilot control inputs;

for a current operation of a first of the different vehicle operations, predict in real time a first vehicle intent, based on current vehicle track data for the first vehicle operation and the accessed vehicle intent prediction model for the first vehicle operation;

predict a first future vehicle trajectory based on the predicted first vehicle intent; and

output for display the predicted first future vehicle trajectory on a computer display.

18. The system of claim 17, wherein the vehicle intent prediction models for different vehicle operations are further based on at least one contextual factor, and wherein the predicted first vehicle intent is based on the current vehicle track data for the first vehicle operation, at least one current contextual factor applicable to the current first vehicle operation, and the accessed vehicle intent prediction model for the first vehicle operation.

19. The system of claim 17, wherein the processor is further configured to:

for a current operation of a second of the different vehicle operations, predict a second vehicle intent, based on current vehicle track data for the second vehicle operation and the accessed vehicle intent prediction model for the second vehicle operation;

predict a second future vehicle trajectory based on the predicted second vehicle intent; and

upon determining that the predicted first future vehicle trajectory and the predicted second future vehicle trajectory are closer than a threshold limit, generate an alert.

20. The system of claim 17, wherein the processor is further configured to receive actual vehicle intent data;

and

upon the received actual vehicle intent data differing from the predicted vehicle intent, generating an alert.

21. The system of claim 17, wherein the processor is further configured to generate the vehicle track intent models for the different vehicle operations, wherein the vehicle track intent models are generated by performing a multilayer perceptron and resilient propagation analysis of the past instances of vehicle tracks and the known vehicle intent data.