Active airborne noise abatement

Patent metadata

Field	Value
Publication number	US-9959860-B2
Application number	US-201715725633-A
Country	US
Kind code	B2
Filing date	Oct 5, 2017
Priority date	Sep 18, 2015
Publication date	May 1, 2018
Grant date	May 1, 2018

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 method comprising:
capturing, by at least one sensor of a first unmanned aerial vehicle, information regarding a first noise emitted by at least one component of the first unmanned aerial vehicle at a first time, wherein the information regarding the first noise is captured while the first unmanned aerial vehicle travels on a first course at a first speed and at a first altitude over at least a first location, and wherein the information regarding the first noise comprises the first course, the first speed, the first altitude and the first location;
determining, based at least in part on the information regarding the first noise, at least a first sound pressure level of the first noise and a first frequency of the first noise;
selecting, by at least one computer processor, a second sound pressure level of a second noise and a second frequency of the second noise based at least in part on:
the first sound pressure level of the first noise;
the first frequency of the first noise, wherein the second frequency of the second noise is approximately one hundred eighty degrees out of phase with the first frequency of the first noise; and
at least one of:
the first course;
the first speed;
the first altitude; or
the first location;

determining, by at least one sensor of a second unmanned aerial vehicle, that the second unmanned aerial vehicle is traveling at one or more of:
on the first course;
at the first speed;
at the first altitude; or
over at least the first location; and

in response to determining that the second unmanned aerial vehicle is traveling at the one or more of on the first course, at the first speed, at the first altitude or over at least the first location,
causing the second unmanned aerial vehicle to emit the second noise at the second sound pressure level and at the second frequency.

2. The method of claim 1 , wherein the at least one computer processor is associated with at least one server,
wherein the at least one server is either ground-based or airborne, and
wherein selecting the sound pressure level of the second sound and the second frequency of the second sound comprises:
transmitting at least some of the information regarding the first sound by the first aerial vehicle to the at least one server over at least one communications network; and
receiving the at least some of the information regarding the first sound by the at least one server;
transmitting information regarding the second sound to the second aerial vehicle over the at least one computer network, wherein the information regarding the second sound associates the second sound with at least one of the first course, the first speed, the first altitude or the first location; and
receiving the information regarding the second sound by the second aerial vehicle.

3. The method of claim 2 , wherein the at least one server is configured to operate at least one machine learning system trained to identify at least one anti-noise to be emitted by an aerial vehicle based at least in part on a noise emitted by the aerial vehicle and at least one of a course, a speed, an altitude or a location, and
wherein selecting the second sound pressure level of the second noise and the second frequency of the second noise further comprises:
providing the at least some of the information regarding the first noise by the first aerial vehicle as an input to the machine learning system; and
receiving an output from the machine learning system,

wherein the second sound pressure level and the second frequency are selected based at least in part on the output.

4. The method of claim 1 , wherein the at least one computer processor is provided aboard the first aerial vehicle, and
wherein selecting the sound pressure level of the second sound and the second frequency of the second sound comprises:
transmitting at least some of the information regarding the second sound to the second aerial vehicle over the at least one computer network, wherein the information regarding the second sound associates the second sound with at least one of the first course, the first speed, the first altitude or the first location; and
receiving the information regarding the second sound by the second aerial vehicle.

5. An unmanned aerial vehicle (UAV) comprising:
a frame;
at least one motor mounted to the frame, wherein the at least one motor is rotatably coupled to at least one propeller;
a first sensor;
a transceiver;
a sound emitting device mounted to at least one of the frame or the at least one motor; 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:
determine, by the first sensor, information regarding at least one of a course, a speed, an altitude or a position of the UAV during an operation of the UAV;
provide at least some of the information regarding the at least one of the course, the speed, the altitude or the position of the UAV during the operation of the UAV as a first input to at least one machine learning system operated by the one or more computer processors;
determine an output from the at least one machine learning system based at least in part on the first input;
determine, based at least in part on the output, information regarding at least a first sound based at least in part on the output, wherein the information regarding the first sound comprises at least a first sound pressure level of the first sound and at least a first frequency of the first sound; and
emitting at least the first sound by the sound emitting device during the operation of the UAV.

6. The UAV of claim 5 , wherein the UAV further comprises a second sensor, and
wherein the one or more computer processors are further configured to at least:
capture, by the second sensor, information regarding at least a second sound emitted by at least one component of the UAV during the operation of the UAV, wherein the information regarding the second sound comprises at least a second sound pressure level of the second sound and at least a second frequency of the second sound; and
provide at least some of the information regarding at least the second sound emitted by the at least one component of the UAV during the operation of the UAV as a second input to the at least one machine learning system operated by the one or more computer processors,
wherein the output is determined based at least in part on the first input and the second input.

7. The UAV of claim 6 , wherein the one or more computer processors are configured to at least:
transmit, by the transceiver over a communications network, at least some of the information regarding at least the first sound to at least one server, wherein the information regarding at least the first sound comprises:
the first sound pressure level;
the first frequency;
the second sound pressure level;
the second frequency; and
the at least one of the course, the speed, the altitude or the position.

8. The UAV of claim 5 , wherein the UAV further comprises a second sensor, and
wherein the one or more computer processors are further configured to at least:
capture, by the second sensor, information regarding a first plurality of sounds emitted by components of the UAV during the operation of the UAV;
provide at least some of the information regarding the first plurality of the sounds emitted by the components of the UAV during the operation of the UAV as a second input to the at least one machine learning system operated by the one or more computer processors, wherein the output is determined based at least in part on the first input and the second input;
determine, based at least in part on the output, informat

Assignees

• Amazon Tech Inc

Inventors

• Beckman Brian C
• Kimchi Gur

Classifications

• B64C2220/00

  Active noise reduction systems · CPC title

• G10K11/17853

  of the filter · CPC title

• G10K2210/3038

  Neural networks · CPC title

• G10K2210/1281

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

• G05D19/02

  characterised by the use of electric means · CPC title