IP Library Granted Patent US 12694977
Granted Patent B1
US 12694977 · App. 17/334,038 · Granted Jul 28, 2026

Using sound to determine introduction of contagion(s) within vehicles

Inventors: Nicholas Nakjoo Kim (San Jose, CA); Daniel David Baker (San Francisco, CA)
Assignee: Zoox, Inc.
G16H40/67G06V20/59G16H50/20G16H50/80H04R3/00
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 12694977
App. No.
17/334,038
Granted
Jul 28, 2026
Kind
B1
Abstract

Systems and methods may determine whether contagion(s) are being spread within a vehicle using sound and/or other sensor data. The vehicle may include sensors, such as microphones, cameras, and the like, that continuously or periodically monitor sound and other conditions in an interior of the vehicle and generate sensor data for use in determining whether contagion(s) have been introduced into the vehicle. In the case of sound, audio data generated by the microphones, for example, may represent acoustic characteristic(s) associated with the sound(s) produced by the occupant(s). The introduction of contagion(s) may be used when determining whether to perform action(s) associated with sanitizing the vehicle and/or otherwise reducing a spread of viruses, bacteria, and/or germs among the occupant(s) and/or within the vehicle.

Claims (121)

1 . A vehicle system comprising:

a microphone;

one or more processors; and

one or more non-transitory computer-readable media storing instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:

receiving, from the microphone, first audio data corresponding to a first sound captured in a vehicle;

determining that the first sound was produced by an occupant of the vehicle;

providing, as an input to a machine-learned (ML) model, the first audio data;

receiving, as an output from the ML model, at least one first characteristic associated with the first sound;

receiving, from the microphone, second audio data corresponding to a second sound captured in the vehicle;

determining that the second sound was produced by the occupant of the vehicle;

determining at least one second characteristic associated with the second sound;

determining an identifier associated with the occupant;

determining, based at least in part on the identifier, a profile of the occupant;

determining, based at least in part on the profile, a first threshold associated with contagions being introduced into the vehicle;

comparing the at least one first characteristic to the first threshold;

comparing the at least one second characteristic to a second threshold;

determining, based at least in part on comparing the at least one first characteristic to the first threshold and comparing the at least one second characteristic to the second threshold, that the first sound and the second sound are indicative of a contagion being introduced into the vehicle;

storing, in association with the profile, an indication of the occupant introducing the contagion into the vehicle;

causing the vehicle to autonomously perform a mitigating action to limit a spread of the contagion, the mitigating action being controlling a heating and air conditioning (HVAC) system of the vehicle; and

determining, based at least in part performing the mitigating action, that the vehicle is available to accept ride-share requests.

2 . The vehicle system of claim 1 , wherein:

the at least one first characteristic comprises at least one of:

a duration of the first sound,

a frequency at which the first sound is detected,

a sound pressure level associated with the first sound, or

a number of times the first sound was detected; and

the at least one second characteristic comprises at least one of:

a duration of the second sound,

a frequency at which the second sound is detected,

a sound pressure level associated with the second sound, or

a number of times the second sound was detected.

3 . The vehicle system of claim 1 , wherein the mitigating action further comprises at least one of:

dispersing a cleansing agent within the vehicle;

actuating a window of the vehicle;

causing the vehicle to come to a stop to permit one or more occupants of the vehicle to exit; or

determining that the vehicle is unavailable to be scheduled for additional occupants.

4 . The vehicle system of claim 1 , the operations further comprising determining, based at least in part on the profile, the second threshold, wherein the second threshold is associated with the contagions being introduced into the vehicle.

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

receiving an indication associated with the occupant scheduling the vehicle;

determining the profile associated with the occupant; and

determining, based at least in part on the profile, that the vehicle is limited to being scheduled for the occupant.

6 . A method comprising:

receiving first audio data generated by a microphone of a vehicle;

associating the first audio data with a first sound produced by an occupant of the vehicle;

determining a first characteristic of the first audio data;

determining an identifier associated with the occupant;

determining, based at least in part on the identifier, a threshold associated with contagions being introduced into the vehicle;

comparing the first characteristic to the threshold;

determining, based at least in part on comparing the first characteristic to the threshold, that the first audio data is indicative of a contagion being introduced within the vehicle;

determining a first action to limit a spread of the contagion within the vehicle based at least in part on determining that the first audio data is indicative of the contagion being introduced within the vehicle, the first action including controlling an airflow within the vehicle;

causing, at a first time, performance of the first action;

receiving second audio data generated by the microphone of the vehicle, the second audio data being different than the first audio data;

associating the second audio data with a second sound produced by the occupant of the vehicle;

determining a second characteristic of the second audio data;

determining, based at least in part on the second characteristic, a second action to limit the spread of the contagion within the vehicle, the second action being different than the first action;

causing, at a second time that is after the first time, performance of the second action; and

storing an indication in association with a profile of the occupant, the indication being used to limit ride-share requests of the occupant.

7 . The method of claim 6 , further comprising:

inputting the first sound into a machine learned model trained to classify sounds based on audio data; and

receiving from the machine learned model a classification of the first sound.

8 . The method of claim 6 , further comprising:

providing the first audio data as an input to a machine-learned model; and

generating, as an output from the machine-learned model, a score representing a likelihood of the contagion being introduced into the vehicle.

9 . The method of claim 6 , wherein the first characteristic comprises at least one of:

a frequency at which the occupant produces the first sound;

a duration of the first sound;

a number of times the occupant produces the first sound; or

a sound pressure level associated with the first sound.

10 . The method of claim 6 , wherein the first action or the second action comprises at least one of:

scheduling the vehicle for cleaning;

dispersing a cleansing agent within the vehicle;

exposing an interior of the vehicle to ultraviolet light;

actuating a window of the vehicle;

controlling a heating ventilation and air conditioning (HVAC) system of the vehicle;

prompting additional occupants to exit the vehicle; or

determining that the vehicle is unavailable to be scheduled for additional occupants.

11 . The method of claim 6 , further comprising providing a notification to the occupant of the vehicle, the notification being associated with the first characteristic.

12 . The method of claim 6 , further comprising determining that the first sound was generated by the occupant, and wherein associating the first audio data with the occupant is based at least in part on determining that the first sound was generated by the occupant.

13 . The method of claim 6 , further comprising determining, based at least in part on the identifier, the profile associated with the occupant, and wherein the threshold is stored in association with the profile.

14 . The method of claim 6 , further comprising:

receiving sensor data captured by a sensor of the vehicle, the sensor data representing data other than audio data; and

associating the sensor data with the occupant, and

wherein determining that the contagion was introduced into the vehicle is further based at least in part on the sensor data.

15 . The method of claim 6 , further comprising:

determining that the first characteristic fails to satisfy the threshold; and

based at least in part on determining that the first characteristic fails to satisfy the threshold, at least one of:

causing performance of the first action, or

refraining from causing performance of the second action.

16 . One or more non-transitory computer readable media storing instructions executable by a processor, wherein the instructions, when executed, cause the processor to perform acts comprising:

receiving audio data generated by a microphone of a vehicle;

associating the audio data with a sound produced by an occupant of the vehicle;

determining a characteristic of the audio data;

determining an identifier associated with the occupant;

determining, based at least in part on the identifier, a threshold associated with a contagion being introduced within the vehicle;

comparing the characteristic to the threshold;

determining, based at least in part on comparing the characteristic to the threshold, that the audio data is indicative of the contagion being introduced within the vehicle;

causing the vehicle to perform a first action to limit a spread of the contagion based at least in part on determining that the audio data is indicative of the contagion being introduced within the vehicle, wherein the first action comprises controlling a heating ventilation and air conditioning (HVAC) system of the vehicle;

based at least in part on the contagion being introduced into the vehicle, determining that the vehicle is at least one of:

unavailable for ride-share requests, or

unable to be scheduled for other occupants;

storing an indication in association with a profile of the occupant, the indication being used to limit ride-share requests associated with the occupant;

causing the vehicle to perform a second action associated with cleansing the vehicle of the contagion; and

based at least in part on performing the second action, determining that the vehicle is at least one of:

available for the ride-share requests, or

able to be scheduled for the other occupants.

17 . The one or more non-transitory computer readable media of claim 16 , wherein the first action or the second action further comprises at least one of:

scheduling the vehicle for cleaning;

dispersing a cleansing agent within the vehicle;

exposing an interior of the vehicle to ultraviolet light;

actuating a window of the vehicle; or

prompting additional occupants to exit the vehicle.

18 . The one or more non-transitory computer readable media of claim 16 , wherein the characteristic comprises at least one of:

a frequency at which the occupant produces the sound;

a duration of the sound;

a number of times the occupant produces the sound; or

a sound pressure level associated with the sound.

19 . The one or more non-transitory computer readable media of claim 16 , further comprising:

inputting the sound into a machine learned model trained to classify sounds based on audio data; and

receiving from the machine learned model a classification of the sound.

20 . The one or more non-transitory computer readable media of claim 16 , further comprising receiving sensor data generated by a sensor of the vehicle, and wherein determining the characteristic of the audio data is based at least in part on the sensor data.

21 . The one or more non-transitory computer readable media of claim 16 , the acts further comprising providing, based at least in part on determining the characteristic, a notification to the occupant of the vehicle.