IP Library Granted Patent US 12687403
Granted Patent B1
US 12687403 · App. 18/646,449 · Granted Jul 21, 2026

Monitoring of data to predict road conditions

Inventors: Emily Margaret Gray (San Antonio, TX); Daniel Christopher Bitsis, Jr. (San Antonio, TX); Qunying Kou (San Antonio, TX); Robert Wiseman Simpson (Fair Oaks Ranch, TX); Manfred Amann (San Antonio, TX); Donnette Moncrief Brown (San Antonio, TX); Eric David Schroeder (San Antonio, TX); Meredith Beveridge (San Antonio, TX); Michael J. Maciolek (Boerne, TX); Bobby Lawrence Mohs (San Antonio, TX); Brian Francisco Shipley (Plano, TX); Justin Dax Haslam (San Antonio, TX); Ashley Raine Philbrick (San Antonio, TX)
Assignee: United Services Automobile Association (USAA)
G01C21/3664G07C5/008G07C5/085G01S19/39
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 12687403
App. No.
18/646,449
Granted
Jul 21, 2026
Kind
B1
Abstract

The present disclosure relates to monitoring data in and around a vehicle to predict anomalous, e.g., unsafe, road conditions, and using the data to suggest a corrective action to avoid the unsafe road conditions. A computing device receives information indicative of imagery, sound, or vehicle operation via sensors and/or cameras mounted in or near a vehicle. The information may be received via the vehicle itself or via a device. The computing device then determines whether there is an indication of an anomalous road condition. The computing device also receives vehicle operation data extracted from one or more vehicle sensors. The computing device then determines whether there is an indication of unsafe road conditions, and if there is, the computing device may output a notice or alert via a notification system to alert the driver.

Claims (39)

1 . A system for detecting unsafe road conditions, comprising:

a memory storing instructions that, when executed by a processor, are configured to cause the processor to:

receive sound data output by one or more sensors of one or more devices indicative of a change in road condition, wherein the sound data comprises patterns of noises corresponding to the change in the road condition;

receive vehicle telematics data from a vehicle;

analyze the sound data and the vehicle telematics data acquired over time;

identify the change in the road condition based on the analysis;

determine a location of the change in the road condition based at least in part on the sound data and the vehicle telematics data; and

in response to identifying the change in the road condition and the location of the change in the road condition, transmit a notification of the change in the road condition and the location of the change in the road condition to a traffic service, wherein the notification outputs an action to avoid a lane associated with the change in the road condition.

2 . The system of claim 1 , wherein the one or more sensors are within a user device or the vehicle.

3 . The system of claim 1 , wherein the sound data comprises driver noise or driver speech.

4 . The system of claim 1 , wherein the sound data comprises sounds associated with the vehicle.

5 . The system of claim 1 , wherein the vehicle telematics data comprises vehicle location data, vehicle operation data, vehicle sensor data, and vehicle diagnostics data.

6 . The system of claim 1 , wherein the patterns of noises are associated with road hazards, potholes, and construction.

7 . The system of claim 1 , wherein the sound data is captured by one or more audio input sensors.

8 . The system of claim 1 , wherein the road condition comprises construction, pot holes, speed bumps, road defects, guard rail damage, or a combination thereof.

9 . The system of claim 1 , wherein the patterns of noises further comprise frequencies or vibrations.

10 . The system of claim 1 , wherein the patterns of noises comprise a combination of a low frequency humming noise coupled with increasing vibrations indicative of a road repair condition.

11 . A tangible, non-transitory, machine-readable medium, comprising machine-readable instructions that, when executed by one or more processors, cause the one or more processors to:

receive sound data from one or more sensors in a user device located inside of a vehicle, wherein the sound data comprises patterns of noises corresponding to a change in a road condition;

receive vehicle telematics data of the vehicle;

analyze the sound data and the vehicle telematics data acquired over time:

identify the change in road condition based on the analysis;

determine a location of the change in the road condition based at least in part on the sound data and the vehicle telematics data; and

in response to identifying the change in the road condition and the location of the change in the road condition, transmitting a notification of the change in the road condition, wherein the notification outputs an action to avoid a lane associated with the change in the road condition.

12 . The tangible, non-transitory, machine-readable medium of claim 11 , wherein the machine-readable instructions cause the one or more processors to transmit the notification to the user device.

13 . The tangible, non-transitory, machine-readable medium of claim 11 , wherein the machine-readable instructions cause the one or more processors to communicate location information of the road condition to a display of the vehicle.

14 . The tangible, non-transitory, machine-readable medium of claim 11 , wherein the machine-readable instructions cause the one or more processors to transmit the notification to an insurance company or a rental car company.

15 . The tangible, non-transitory, machine-readable medium of claim 11 , wherein the machine-readable instructions cause the one or more processors to suggest alternative driving routes as part of the notification.

16 . The tangible, non-transitory, machine-readable medium of claim 11 , wherein the machine-readable instructions cause the one or more processors to incentivize a driver to not drive the vehicle.

17 . A processor-implemented method for detecting unsafe road conditions, comprising:

receiving, via one or more sensors of one or more devices, sound data indicative of a road condition in or near a vehicle, wherein the sound data comprises patterns of noises corresponding to a change in road condition;

receiving vehicle telematics data from the vehicle:

analyzing the sound data and the vehicle telematics data acquired over time:

identifying the change in the road condition based on the analysis;

determining a location of the identified change in the road condition based at least in part on the sound data and the vehicle telematics data; and

in response to identifying the change in the road condition and the location of the change in the road condition, transmitting a notification of the change in the road condition to a driver operating the vehicle, wherein the notification outputs an action to avoid a lane associated with the change in the road condition.

18 . The method of claim 17 , wherein the sound data comprises sound detected by a user device or sound detected in or around the vehicle.

19 . The method of claim 17 , wherein the sound data comprises audible sounds produced by the driver.

20 . The method of claim 17 , wherein the one or more sensors comprise sound detection sensors, proximity sensors, gyroscopes, biometric sensors, or a combination thereof.