Commercial and general aircraft avoidance using acoustic pattern recognition

• US 9,685,089 B2
• Filed: 12/12/2014
• Issued: 06/20/2017
• Est. Priority Date: 12/12/2014
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Paczan, Nathan Michael, Buchmueller, Daniel
• Primary Examiner(s): Kan, Yuri
• Application Number:
  US14/569,183
• Publication Number:
  US 20160247405A1
• Time in Patent Office: 921 Days
• CPC Class Codes: G01S 15/02 using reflection of acoustic waves G01S15/66 takes precedence
• CPC Class Codes: G01S 5/18 using ultrasonic, sonic, or infrasonic waves
• CPC Class Codes: G05D 1/106 Change initiated in response to external conditions, e.g. avoidance of elevated terrain or of no-fly zones
• CPC Class Codes: G08G 5/0013 with a ground station
• CPC Class Codes: G08G 5/0039 Modification of a flight plan
• CPC Class Codes: G08G 5/0069 specially adapted for an unmanned aircraft
• CPC Class Codes: G08G 5/0078 for monitoring traffic from the aircraft radar or analogous systems specially adapted for traffic control G01S13/91
• 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: G10K 11/34 using electrical steering of transducer arrays, e.g. beam steering constructional aspects B06B1/0607, B06B1/085
• CPC Class Codes: H04L 67/1074 for supporting data block transmission mechanisms file transfer H04L67/06

Abstract

This disclosure is directed to a detection and avoidance apparatus for an unmanned aerial vehicle (“UAV”) and systems, devices, and techniques pertaining to automated object detection and avoidance during UAV flight. The system may detect objects within the UAV'"'"'s airspace through acoustic, visual, infrared, multispectral, hyperspectral, or object detectable signal emitted or reflected from an object. The system may identify the source of the object detectable signal by comparing features of the received signal with known sources signals in a database. The features may include, for example, an acoustic signature emitted or reflected by the objet. Furthermore, a trajectory envelope for the object may be determined based on characteristic performance parameters for the object such as cursing speed, maneuverability, etc. The UAV may determine an optimized flight plan based on the trajectory envelopes of detected objects within the UAV'"'"'s air-space.

Claims

1. A method, comprising:

generating acoustic signals, by one or more acoustic sensors of an unmanned aerial vehicle (UAV), from acoustic waves generated by propulsion of a flying object;

determining one or more characteristic features of the acoustic signals;

identifying the flying object based at least in part on a comparison of the one or more characteristic features to a database of known acoustic signals;

associating performance parameters with the flying object using a database that includes performance parameters for at least one of a plurality of flying objects or class of flying objects;

determining a location and an airspeed associated with the flying object based at least in part on the acoustic signals;

determining a trajectory envelope for the flying object based at least in part on the location, the airspeed and the associated performance parameters; and

updating a flight plan for the UAV based at least in part on the trajectory envelope of the flying object, wherein the updated flight plan does not interact with the trajectory envelope of the flying object.

2. The method of claim 1, further comprising processing the acoustic signals using a beamformer to create beamformed acoustic signals prior to determining the location and the airspeed associated with the flying object, and wherein the determining the trajectory envelope for the flying object is performed using the beamformed acoustic signals.

3. The method of claim 1, wherein the identifying the flying object includes determining a class of the flying object, and wherein the associated performance parameters are for the class of flying objects.

4. The method of claim 1, wherein the trajectory envelope is based at least in part on one of a rate of climb, a rate of decent, or a maneuverability parameter associated with the flying object.

5. The method of claim 1, wherein the one or more characteristic features of the acoustic signals form a signal fingerprint in the form of a spectrogram over time, and wherein the one or more characteristic features are determined by a signal-to-noise ratio of the acoustic signals meeting or exceeding a threshold value.

6. An unmanned aerial vehicle (UAV), comprising:

one or more processors;

memory to store computer-readable instructions;

one or more audio sensors coupled to the unmanned aerial vehicle (UAV), the one or more audio sensors to generate audio signals from sound received from an object within an airspace at least partially surrounding the UAV; and

a flight management component stored within the memory that, when executed, causes the one or more processors to;

receive the audio signals associated with the object;

determine, based at least in part on an analysis of the audio signals, an identity of the object associated with audio signals;

determine performance parameters for the object based at least in part on the identity of the object; and

determine a trajectory envelope for the object based at least in part on the performance parameters.

7. The UAV of claim 6, wherein the flight management component is further configured to determine a location and airspeed associated with the object.

8. The UAV of claim 7, wherein the flight management component is further configured to process to the audio signals using a beamformer to generate beamformed audio signals, and wherein the location and the airspeed of the object is determined based at least in part on the beamformed audio signals.

9. The UAV of claim 6, wherein the flight management component is further configured to locate the object within a zone of a plurality of zones defined around the UAV.

10. The UAV of claim 6, further comprising a communication component to create a peer-to-peer network with one or more nearby UAVs, the communication component configured to exchange at least one of the audio signals, the identity of the object, or the trajectory envelope of the object with the one or more nearby UAVs.

11. The UAV of claim 10, where the flight management component is further configured to determine a location and airspeed associated with the object based at least in part on information exchanged from at least one of the one or more nearby UAVs using triangulation.

12. The UAV of claim 6, wherein the performance parameters are stored in a database and include at least a rate of climb, a rate of decent, and a maneuverability parameter associated with each of various objects.

13. The UAV of claim 6, wherein the identity of the object is a model of an aircraft, and wherein the performance parameters are associated with the model of the aircraft.

14. An object detection and avoidance system comprising:

one or more processors; and

memory storing computer-executable instructions that, when executed, cause the one or more processors to perform acts comprising;

generating audio signals from sound captured from an object;

identifying the object based at least in part on one or more characteristic features of the audio signals;

determining performance parameters for the object based at least in part on the identifying of the object; and

determining a trajectory envelope of the object based at least in part on the performance parameters.

15. The object detection and avoidance system of claim 14, wherein the acts further comprise updating a flight plan for an unmanned aerial vehicle (UAV) based at least in part on a probability of interaction between the UAV and the trajectory envelope of the object.

16. The object detection and avoidance system of claim 14, wherein identifying the object includes matching the one or more characteristic features of the audio signals with signal features stored in a database that associates individual signal features with respective objects or groups of objects.

17. The object detection and avoidance system of claim 14, further comprising determining an airspeed of the object based at least in part on changes in the audio signals over a defined period of time.

18. The object detection and avoidance system of claim 17, wherein the trajectory envelope is formed using a scalable volume that is scaled based in least in part on the airspeed and performance parameters of the object.

19. The object detection and avoidance system of claim 14, wherein the acts further comprise:

receiving at least some audio signals from one or more nearby UAVs;

or

transmitting at least some of the generated audio signals to one or more nearby UAVs.

20. The object detection and avoidance system of claim 14, further comprising a multispectral sensor to capture specific wavelengths of electromagnetic energy reflected or emitted by the object and indicative of unique materials associated with the object, and further comprising identifying the object based at least in part on the specific wavelengths of electromagnetic energy reflected or emitted by the object.