Active airborne noise abatement

Patent metadata

Field	Value
Publication number	US-9786265-B2
Application number	US-201615237446-A
Country	US
Kind code	B2
Filing date	Aug 15, 2016
Priority date	Sep 18, 2015
Publication date	Oct 10, 2017
Grant date	Oct 10, 2017

Abstract

Noises that are to be emitted by an aerial vehicle during operations may be predicted using one or more machine learning systems, algorithms or techniques. Anti-noises having equal or similar intensities and equal but out-of-phase frequencies may be identified and generated based on the predicted noises, thereby reducing or eliminating the net effect of the noises. The machine learning systems, algorithms or techniques used to predict such noises may be trained using emitted sound pressure levels observed during prior operations of aerial vehicles, as well as environmental conditions, operational characteristics of the aerial vehicles or locations of the aerial vehicles during such prior operations. Anti-noises may be identified and generated based on an overall sound profile of the aerial vehicle, or on individual sounds emitted by the aerial vehicle by discrete sources.

First claim

What is claimed is:

1. An unmanned aerial vehicle (UAV) comprising:
a frame;
a Global Positioning System (GPS) sensor associated with the frame;
at least one acoustic device mounted to the frame;
a plurality of motors mounted to the frame;
a plurality of propellers, wherein each of the plurality of propellers is coupled to one of the plurality of motors;
a sound emitting device mounted to at least one of the frame or one of the plurality of motors; and
a computing device having a memory and one or more computer processors,
wherein the one or more computer processors are configured to at least:
capture data regarding a sound using the at least one acoustic device;
determine a sound pressure level of the sound and a frequency of the sound based at least in part on the data;
determine, by the GPS sensor, a position of the UAV;
determine at least one environmental condition associated with the position;
determine at least one operating characteristic of at least one of the plurality of motors or at least one of the plurality of propellers associated with the position;
determine a sound pressure level of an anti-noise and a frequency of the anti-noise based at least in part on the sound pressure level of the sound, the frequency of the sound, and at least one of:
the position,
the at least one environmental condition, or
the at least one operating characteristic; and

emit the anti-noise from the sound emitting device of the UAV.

2. The UAV of claim 1 , wherein the at least one acoustic device comprises at least one of:
a microphone;
a piezoelectric sensor; or
a vibration sensor.

3. A method to operate a first aerial vehicle comprising a first sound emitting device mounted thereto, wherein the method comprises:
predicting, by at least one computer processor prior to a first time, at least one of:
a first anticipated position of the first aerial vehicle at the first time;
a first anticipated environmental condition at the first anticipated position or at the first time;
a first anticipated operating characteristic of the first aerial vehicle at the first anticipated position or at the first time;

predicting, by the at least one computer processor, a first sound to be emitted by at least one component of the first aerial vehicle at the first time, wherein the first sound is predicted based at least in part on the at least one of the first anticipated position, the first anticipated environmental condition or the first anticipated operating characteristic;
determining, by the at least one computer processor, a second sound based at least in part on the first sound, wherein a second sound pressure level of the second sound is not greater than a first sound pressure level of the first sound, and wherein a second frequency of the second sound is substantially equal in magnitude and of reverse polarity with respect to a first frequency of the first sound; and
causing, by the at least one computer processor, the second sound to be emitted by the first sound emitting device at the first time.

4. The method of claim 3 , wherein the second sound is caused to be emitted by the first sound emitting device at the first time.

5. The method of claim 4 , wherein the first aerial vehicle further comprises a Global Positioning System (GPS) sensor, and
wherein the method further comprises:
determining, by the GPS sensor, that the first aerial vehicle is at the first anticipated position at the first time,
wherein the second sound is caused to be emitted by the first sound emitting device in response to determining that the first aerial vehicle is at the first anticipated position at the first time.

6. The method of claim 3 , wherein the at least one component of the first aerial vehicle is at least one of a frame of the first aerial vehicle, a motor mounted to the frame, or a propeller rotatably coupled to the motor.

7. The method of claim 3 , wherein predicting the first sound to be emitted by the at least one component of the first aerial vehicle at the first time further comprises:
providing, by the at least one computer processor, first information regarding the first anticipated position, the first anticipated environmental condition and the first anticipated operating characteristic to at least one machine learning system as an input; and
receiving, from the at least one machine learning system, second information regarding the first sound as an output, wherein the second information regarding the first sound comprises the first sound pressure level and the first frequency.

8. The method of claim 7 , wherein determining the second sound further comprises:
providing first information regarding the first sound to at least one machine learning system as an input, wherein the information regarding the first sound comprises at least one of a first sound pressure level of the first sound or a first frequency of the first sound; and
receiving, from the at least one machine learning system, second information regarding the second sound as an output, wherein the second information regarding the second sound comprises a second sound pressure level and a second frequency,
wherein the second sound is caused to be emitted by the first sound emitting device at the second sound pressure level or at the second frequency.

9. The method of claim 7 , wherein the at least one machine learning system is configured to perform at least one of:
an artificial neural network;
a conditional random field;
a cosine similarity analysis;
a factorization method;
a K-means clustering analysis;
a latent Dirichlet allocation;
a latent semantic analysis;
a log likelihood similarity analysis;
a nearest neighbor analysis;
a support vector machine; or
a topic model analysis.

10. The method of claim 3 , wherein predicting the at least one of the first anticipated position of the first aerial vehicle at the first time, the first anticipated environmental condition at the first anticipated position or at the first time, or the first anticipated operating characteristic of the first aerial vehicle at the first anticipated position or at the first time comprises:
determining that a second aerial vehicle was at the first anticipated position at a second time, wherein the second time preceded the first time; and
determining information regarding at least one of a second environmental condition or a second operating characteristic observed by the second aerial vehicle at the first anticipated position at the second time,
wherein the first sound to be emitted by the at least one component of the first aerial vehicle at the first time is predicted based at least in part on the information regarding the at least one of the second environmental condition or the second operating characteristic.

11. The method of claim 10 , wherein the first sound to be emitted by the at least one component of the first aerial vehicle at the first time is predicted by at least one computer processor provided on the second aerial vehicle.

12. The method of claim 3 , wherein predicting the at least one of the first anticipated position of the first aerial vehicle at the first time, the first anticipated environmental condition at the first anticipated position or at the first time, or the first anticipated operating characteristic of the first aerial vehicle at the first anticipated position or at the first time comprises:
generating a transit plan for the first aerial vehicle, wherein the transit plan comprises information regarding a plurality of anticipated positions of the aerial vehicle, and wherein the first anticipated position is one of the plurality of anticipated positions,
whe

Assignees

• Amazon Tech Inc

Inventors

• Beckman Brian C
• Kimchi Gur

Classifications

• G10K2210/1281

  Aircraft, e.g. spacecraft, airplane or helicopter · CPC title

• G10K11/17873

  using a reference signal without an error signal, e.g. pure feedforward · CPC title

• G06N20/00

  Machine learning · CPC title

• G05D27/02

  characterised by the use of electric means · CPC title

• G10K2210/3045

  Multiple acoustic inputs, single acoustic output · CPC title