IP Library Granted Patent US 11,900,818
Granted Patent B2
US 11,900,818 · App. 16/897,699 · Granted Feb 13, 2024

Time varying loudness prediction system

Inventors: Alireza Rostamzadeh (Foster City, CA); Rohit Goyal (San Francisco, CA); Ryan Cunningham (San Francisco, CA); Jane Yen Hung (San Francisco, CA); Stanley Swaintek (Mill Valley, CA)
Assignee: JOBY AERO, INC.
G08G5/0034G01C21/20G06N5/04G06N20/00G08G5/0047G01W1/10
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,900,818
App. No.
16/897,699
Filed
Jun 10, 2020
Granted
Feb 13, 2024
Kind
B2
Art Unit
3668
USPC
701/4
Abstract

Disclosed are methods and systems for predicting time varying loudness in a geographic region. Training data, including noise information, weather information, and traffic information is collected from a plurality of sensors located in a plurality of geographic regions. The information is collected during multiple time periods. The noise information includes time varying loudness. Static features of the geographic regions are also defined and included in the training data. The static and time varying dynamic features train a model. The model is used predict time varying loudness within a different region and at a time later than times the training data is collected. The predicted loudness levels are utilized, in some aspects, to determine a route for an aircraft.

Claims (94)

1. A system, comprising:

hardware processing circuitry;

one or more hardware memories storing instructions that when executed configure the hardware processing circuitry to perform operations comprising:

receiving measurements of dynamic feature data for a geographic region;

determining static features for the geographic region;

generating a predicted background noise loudness in the geographic region during a defined time period using a model, the model trained on training data including historical measurements of dynamic feature data for a plurality of regions over a plurality of training time periods and static features of the plurality of regions, wherein the geographic region is absent from the plurality of regions, wherein the defined time period occurs after the plurality, of training time periods;

determining, based on the predicted background noise loudness, whether to route an aircraft through the geographic region;

determining a route and one or more operating constraints based on the predicted background noise loudness in the geographic region, the one or more operating constraints indicative of at least one of: a take-off maneuver or a landing maneuver associated with the route;

selecting an aircraft, from among a plurality of different aircrafts, for the route based on the predicted background noise loudness, the one or more operating constraints, and capabilities of the aircraft; and

routing the aircraft through a particular geographic region based on the determined route.

2. The system of claim 1 , wherein the generating of the predicted background noise loudness predicts the background noise loudness at a particular time of day and a particular date within the defined time period, and the historical measurements of the dynamic feature data are correlated with a time of day and a date of the historical measurements.

3. The system of claim 1 , the operations further comprising:

wherein generating the predicted background noise loudness comprises:

predicting a first background noise loudness in a first region during the defined time period based on the model;

predicting a second background noise loudness in a second region during the defined time period based on the model;

determining the first background noise loudness is higher than the second background noise loudness; and

wherein routing the aircraft comprises routing the aircraft through the first region during the defined time period in response to the determination.

4. The system of claim 1 , the operations further comprising:

wherein generating the predicted background noise loudness comprises generating, based on the model and for each of the plurality of regions in a map, a predicted background noise loudness of the respective region;

wherein determining the route comprises:

identifying an origin and destination;

identifying a plurality of routes from the origin to the destination, each of the plurality of routes including at least one of the plurality of regions in the map;

determining a comparison of the predicted background noise loudness of the at least one of the plurality of regions included in a first route of the plurality of routes to the predicted background noise loudness of the at least one of the plurality of regions included in a second route of the plurality of routes; and

selecting the first route or the second route based on the comparison; and

wherein routing the aircraft comprises routing the aircraft over the selected route.

5. The system of claim 4 , the operations further comprising:

aggregating predicted background noise loudness of regions included in the first route; and

aggregating predicted background noise loudness of regions included in the second route, wherein the selection of the first route or the second route is based on the first route aggregating and the second route aggregating.

6. The system of claim 4 , the operations further comprising:

determining a minimum predicted background noise loudness along the selected route;

comparing the minimum predicted background noise loudness to a noise threshold; and

determining an altitude for the aircraft, along the selected route to be above a predefined altitude in response to the minimum predicted background noise loudness being below the noise threshold.

7. The system of claim 1 , wherein the capabilities of the aircraft are indicative of the ability of the aircraft to perform one or more maneuvers for the route and complete the route without violating a noise threshold given the predicted background noise loudness.

8. The system of claim 1 , wherein the take-off maneuver comprises a take-off angle and the landing maneuver comprises a landing angle.

9. A non-transitory computer readable storage medium comprising instructions that when executed configure hardware processing circuitry to perform operations comprising:

receiving measurements of dynamic feature data for a geographic region;

determining static features for the geographic region; and

generating a predicted background noise loudness in the geographic region during a defined time period using a model, the model trained on training data including historical measurements of dynamic feature data for a plurality of regions over a plurality of training time periods and static features of the plurality of regions, wherein the geographic region is absent from the plurality of regions, wherein the defined time period occurs after the plurality of training time periods;

determining, based on the predicted background noise loudness, whether to route an aircraft through the geographic region;

determining a route and one or more operating constraints based on the predicted background noise loudness in the geographic region, the one or more operating constraints indicative of at least one of: a take-off maneuver or a landing maneuver associated with the route;

selecting an aircraft, from among a plurality of different aircrafts, for the route based on the predicted background noise loudness, the one or more operating constraints, and capabilities of the aircraft; and

routing the aircraft through the geographic region based on the determined route.

10. The non-transitory computer readable storage medium of claim 9 , the operations further comprising:

wherein generating the predicted background noise loudness comprises:

predicting a first background noise loudness in a first region during the defined time period based on the model;

predicting a second background noise loudness in a second region during the defined time period based on the model;

determining the first background noise loudness is higher than the second background noise loudness; and

wherein routing the aircraft comprises routing the aircraft through the first region during the defined time period in response to the determination.

11. The non-transitory computer readable storage medium of claim 9 , the operations further comprising:

wherein generating the predicted background noise loudness comprises generating, based on the model and for each of the plurality of regions in a map, a predicted background noise loudness of the respective region;

wherein determining the route comprises:

identifying an origin and destination of an aircraft;

identifying a plurality of routes from the origin to the destination, each of the plurality of routes including at least one of the plurality of regions in the map;

determining a comparison of the predicted background noise loudness of the at least one of the plurality of regions included in a first route of the plurality of routes to the predicted background noise loudness of the at least one of the plurality of regions included in a second route of the plurality of routes; and

selecting the first route or the second route based on the comparison; and

wherein routing the aircraft comprises routing the aircraft over the selected route.

12. The non-transitory computer readable storage medium of claim 11 , the operations further comprising:

aggregating predicted background noise loudness of regions included in the first route; and

aggregating predicted background noise loudness of regions included in the second route, wherein the selection of the first route or the second route is based on the first route aggregating and the second route aggregating.

13. The non-transitory computer readable storage medium of claim 11 , the operations further comprising:

determining a minimum predicted background noise loudness along the selected route;

comparing the minimum predicted background noise loudness to a noise threshold; and

determining an altitude for the aircraft along the selected route to be above a predefined altitude in response to the minimum predicted background noise loudness being below the noise threshold.

14. A method performed by hardware processing circuitry, comprising:

receiving measurements of dynamic feature data for a geographic region;

determining static features for the geographic region; and

generating a predicted background noise loudness in the geographic region during a defined time period using a model, the model trained on training data including historical measurements of dynamic feature data for a plurality of regions over a plurality of training time periods and static features of the plurality of regions, wherein the geographic region is absent from the plurality of regions, wherein the defined time period occurs after the plurality of training time periods;

determining, based on the predicted background noise loudness, whether to route an aircraft through the geographic region;

determining a route and one or more operating constraints based on the predicted background noise loudness in the geographic region, the one or more operating constraints indicative of at least one of: a take-off maneuver or a landing maneuver associated with the route;

selecting an aircraft, from among a plurality of different aircrafts, for the route based on the predicted background noise loudness, the one or more operating constraints, and capabilities of the aircraft; and

routing the aircraft through the geographic region based on the determined route.

15. The method of claim 14 , wherein the generating of the predicted background noise loudness predicts the background noise loudness at a particular time of day and a particular date within the defined time period, and the historical measurements of the dynamic feature data are correlated with a time of day and a date of the historical measurements.

16. The method of claim 14 , further comprising:

wherein generating the predicted background noise loudness comprises:

predicting a first background noise loudness in a first region during the defined time period based on the model;

predicting a second background noise loudness in a second region during the defined time period based on the model;

determining the first background noise loudness is higher than the second background noise loudness; and

wherein routing the aircraft comprises routing the aircraft through the first region during the defined time period in response to the determination.

17. The method of claim 14 , further comprising:

wherein generating the predicted background noise loudness comprises generating, based on the model and for each of the plurality of regions in a map, a predicted background noise loudness of the respective region;

wherein determining the route comprises:

identifying an origin and destination of an aircraft;

identifying a plurality of routes from the origin to the destination, each of the plurality of routes including at least one of the plurality of regions in the map;

determining a comparison of the predicted background noise loudness of the at least one of the plurality of regions included in a first route of the plurality of routes to the predicted background noise loudness of the at least one of the plurality of regions included in a second route of the plurality of routes;

selecting the first route or the second route based on the comparison; and

wherein routing the aircraft comprises routing the aircraft over the selected route.

18. The method of claim 17 , further comprising:

aggregating predicted background noise loudness of regions included in the first route; and

aggregating predicted background noise loudness of regions included in the second route, wherein the selection of the first route or the second route is based on the first route aggregating and the second route aggregating.

19. The method of claim 17 , further comprising:

determining a minimum predicted background noise loudness along the selected route;

comparing the minimum predicted background noise loudness to a noise threshold; and

determining an altitude for the aircraft along the selected route to be above a predefined altitude in response to the minimum predicted background noise loudness being below the noise threshold.

20. The method of claim 14 , wherein the dynamic features are indicative of at least one of: weather, sound levels, or traffic associated with the geographic area; and wherein the static features are indicative of at least one of: elevation, vegetation, topography, or a distance to a road associated with the geographic area.

Assignments (17)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 16, 2026
From: JOBY ELEVATE, INC.
To: JOBY AERO, INC.
Reel/Frame 075428/0529 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 16, 2026
From: UBER TECHNOLOGIES, INC.
To: UBER ELEVATE, INC.
Reel/Frame 075429/0355 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 16, 2026
From: JOBY ELEVATE, INC.
To: JOBY AERO, INC.
Reel/Frame 075429/0431 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 16, 2026
From: UBER TECHNOLOGIES, INC.
To: UBER ELEVATE, INC.
Reel/Frame 075429/0529 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 16, 2026
From: JOBY ELEVATE, INC.
To: JOBY AERO, INC.
Reel/Frame 075429/0561 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 16, 2026
From: UBER TECHNOLOGIES, INC.
To: UBER ELEVATE, INC.
Reel/Frame 075429/0726 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 16, 2026
From: JOBY ELEVATE, INC.
To: JOBY AERO, INC.
Reel/Frame 075430/0030 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 16, 2026
From: UBER TECHNOLOGIES, INC.
To: UBER ELEVATE, INC.
Reel/Frame 075430/0080 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 16, 2026
From: JOBY ELEVATE, INC.
To: JOBY AERO, INC.
Reel/Frame 075430/0172 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 16, 2026
From: JOBY ELEVATE, INC.
To: JOBY AERO, INC.
Reel/Frame 075403/0137 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 16, 2026
From: UBER TECHNOLOGIES, INC.
To: UBER ELEVATE, INC.
Reel/Frame 075409/0386 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 15, 2026
From: UBER TECHNOLOGIES, INC.
To: UBER ELEVATE, INC.
Reel/Frame 075407/0147 →
CORRECTIVE ASSIGNMENT TO CORRECT THE RECEIVING PARTY ADDRESS SHOULD BE #225 INSTEAD OF #255 PREVIOUSLY RECORDED AT REEL: 057652 FRAME: 0016. ASSIGNOR(S) HEREBY CONFIRMS THE ASSIGNMENT. Recorded Apr 19, 2023
From: JOBY ELEVATE, INC.
To: JOBY AERO, INC
Reel/Frame 063375/0776 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 2, 2021
From: JOBY ELEVATE, INC.
To: JOBY AERO, INC.
Reel/Frame 057652/0016 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 16, 2021
From: UBER TECHNOLOGIES, INC.
To: UBER ELEVATE, INC.
Reel/Frame 055310/0555 →
CHANGE OF NAME Recorded Feb 16, 2021
From: UBER ELEVATE, INC.
To: JOBY ELEVATE, INC.
Reel/Frame 055310/0609 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 16, 2020
From: ROSTAMZADEH, ALIREZA; GOYAL, ROHIT; CUNNINGHAM, RYAN; HUNG, JANE YEN; SWAINTEK, STANLEY
To: UBER TECHNOLOGIES, INC.
Reel/Frame 052946/0897 →
Continuity (2)
Provisional Application 62859685 · Jun 10, 2019
Related Publication 20200388166A1 · Dec 10, 2020
Cited By (3)
US 12,192,714 US 12,332,062 US 12,488,695