Maneuver prediction based on audio data

• US 10,102,760 B1
• Filed: 08/23/2017
• Issued: 10/16/2018
• Est. Priority Date: 08/23/2017
• Status: Active Grant

• Current Assignee: Honeywell International Inc.
• Original Assignee: Honeywell International Inc.
• Inventors: Foltan, Stanislav, Sosovicka, Robert, Josth Adamova, Eva
• Primary Examiner(s): Nguyen, Hung T
• Application Number:
  US15/684,435
• Time in Patent Office: 419 Days
• Field of Search: 340945, 340961, 340963, 340984, 701 36, 701 45, 701301
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G08G 5/0008 with other aircraft
• CPC Class Codes: G08G 5/0021 located in the aircraft
• 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
• CPC Class Codes: G10L 15/02 Feature extraction for speech recognition; Selection of recognition unit
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 2015/225 Feedback of the input speech
• CPC Class Codes: G10L 2015/228 of application context
• CPC Class Codes: G10L 25/51 for comparison or discrimination
• CPC Class Codes: H04R 2499/13 Acoustic transducers and sound field adaptation in vehicles
• CPC Class Codes: H04R 29/00 Monitoring arrangements; Testing arrangements for hearing aids H04R25/30; detection of loudspeaker connection H04R5/04; sound-field adaptation dependent on speaker detection H04S7/308

Abstract

This disclosure is directed to a system includes a receiver configured to receive audio data from a vehicle. In some examples, the system includes processing circuitry configured to determine an expected maneuver for the vehicle based on the audio data. In some examples, the processing circuitry is further configured to determine whether to output an alert based on the expected maneuver determined from the audio data.

Claims

1. A collision awareness system comprising:

a receiver configured to receive audio data from a vehicle; and

processing circuitry configured to;

determine an expected maneuver for the vehicle based on the audio data;

calculate a current collision prediction based on the expected maneuver;

compare the current collision prediction to a previous collision prediction; and

determine whether to output an alert in response to comparing the current collision prediction to the previous collision prediction.

2. The collision awareness system of claim 1, further comprising a non-transitory memory device configured to store a set of stored features, wherein the processing circuitry is configured to determine the expected maneuver by at least:

applying a speech-recognition module to the audio data;

determining one or more features of the audio data in response to applying the speech-recognition module to the audio data; and

comparing the one or more features of the audio data to the set of stored features.

3. The collision awareness system of claim 2, wherein the processing circuitry is configured to determine the expected maneuver by at least selecting a stored feature from the set of stored features in response to comparing the one or more features of the audio data to the set of stored features.

4. The collision awareness system of claim 3,

wherein the non-transitory memory device is further configured to store a set of stored maneuvers,

wherein each stored feature from the set of stored features is associated with a respective recorded maneuver from the set of stored maneuvers, and

wherein the processing circuitry is configured to determine the expected maneuver by at least determining the respective stored maneuver that is associated with the selected stored feature.

5. The collision awareness system of claim 1, wherein:

the vehicle is another vehicle;

the receiver includes a radio receiver configured to receive radio signals including the audio data from the other vehicle;

the system is configured to be installed on an ownship vehicle; and

the processing circuitry is configured to determine whether to output the alert by at least determining whether the other vehicle is likely to collide with the ownship vehicle while performing the expected maneuver.

6. The collision awareness system of claim 1, wherein:

the vehicle is an ownship vehicle on which the system is installed;

the receiver includes a microphone configured to receive the audio data from the ownship vehicle; and

the processing circuitry is configured to determine whether to output the alert by at least determining whether the ownship vehicle is likely to collide with an object.

7. The collision awareness system of claim 1, wherein the processing circuitry is configured to determine whether to output the alert in response to comparing the current collision prediction to the previous collision prediction by at least:

determining that the current collision prediction indicates that no collision will occur;

determining that the current collision prediction contradicts the previous collision prediction; and

suppressing the alert from the previous collision prediction in response to determining that the current collision prediction contradicts the previous collision prediction.

8. The collision awareness system of claim 1, wherein the receiver includes a radio receiver configured to receive radio signals including the audio data from the vehicle, the collision awareness system further comprising a surveillance receiver configured to receive surveillance broadcasts from the vehicle, wherein the processing circuitry is further configured to determine the previous collision prediction based on the surveillance broadcasts received by the surveillance receiver from the vehicle.

9. The collision awareness system of claim 1, wherein the processing circuitry is configured to determine the previous collision prediction based on surveillance signals received from the vehicle.

10. A collision awareness method executed by processing circuitry for:

receiving audio data from a vehicle;

determining an expected maneuver for the vehicle based on the audio data;

calculate a current collision prediction based on the expected maneuver;

compare the current collision prediction to a previous collision prediction; and

determining whether to output an alert in response to comparing the current collision prediction to the previous collision prediction.

11. The collision awareness method of claim 10, wherein determining the expected maneuver comprises:

applying a speech-recognition module to the audio data;

determining one or more features of the audio data in response to applying the speech-recognition module to the audio data; and

comparing the one or more features of the audio data to a set of stored features.

12. The collision awareness method of claim 11, wherein determining the expected maneuver comprises selecting a stored feature from the set of stored features in response to comparing the one or more features of the audio data to the set of stored features.

13. The collision awareness method of claim 12, wherein determining the expected maneuver further comprises determining a respective stored maneuver from a set of stored maneuvers that is associated with the selected stored feature, wherein each stored feature from the set of stored features is associated with a respective recorded maneuver from the set of stored maneuvers.

14. The collision awareness method of claim 10, wherein determining whether to output the alert in response to comparing the current collision prediction to the previous collision prediction further comprises:

determining that the current collision prediction indicates that no collision will occur;

determining that the current collision prediction contradicts the previous collision prediction; and

suppressing the alert from the previous collision prediction in response to determining that the current collision prediction contradicts the previous collision prediction.

15. The collision awareness method of claim 10, wherein determining whether to output the alert in response to comparing the current collision prediction to the previous collision prediction further comprises:

determining that the current collision prediction indicates that no collision will occur;

determining that the current collision prediction confirms the previous collision prediction; and

outputting the alert in response to determining that the current collision prediction confirms the previous collision prediction.

16. The collision awareness method of claim 10, wherein determining whether to output the alert in response to comparing the current collision prediction to the previous collision prediction further comprises:

determining that the current collision prediction indicates that a collision will occur;

determining that the current collision prediction contradicts the previous collision prediction; and

outputting the alert in response to determining that the current collision prediction contradicts the previous collision prediction.

17. The collision awareness method of claim 10, wherein determining whether to output the alert in response to comparing the current collision prediction to the previous collision prediction further comprises:

determining that the current collision prediction indicates that a collision will occur;

determining that the current collision prediction confirms the previous collision prediction; and

outputting the alert in response to determining that the current collision prediction confirms the previous collision prediction.

18. The collision awareness method of claim 10, further comprising determining the previous collision prediction based on surveillance signals received from the vehicle.

19. A collision awareness system comprising:

a receiver configured to receive audio data from a vehicle;

a non-transitory memory device configured to store a set of stored features; and

processing circuitry configured to;

apply a speech-recognition module to the audio data;

determine one or more features of the audio data in response to applying the speech-recognition module to the audio data;

determine an expected maneuver for the vehicle based on the audio data in least in part by comparing the one or more features of the audio data to the set of stored features; and

determine whether to output an alert based on the expected maneuver determined from the audio data.

20. The collision awareness system of claim 19, wherein the processing circuitry is configured to determine the expected maneuver by at least selecting a stored feature from the set of stored features in response to comparing the one or more features of the audio data to the set of stored features.