Pothole and road condition classication using human driven telemetry

Patent metadata

Field	Value
Publication number	US-12420803-B2
Application number	US-202318313244-A
Country	US
Kind code	B2
Filing date	May 5, 2023
Priority date	May 5, 2023
Publication date	Sep 23, 2025
Grant date	Sep 23, 2025

Abstract

Methods and systems are provided for road condition classification that include one or more sensors configured to obtain sensor data pertaining to operation of a vehicle along a roadway by a human; and one or more processors that are coupled to the one or more sensors and that are configured to at least facilitate analyzing the sensor data as to one or more threshold values pertaining to the operation of the vehicle; and identifying one or more conditions of the roadway, based on the analyzing of the sensor data. Further, learned input is provided to the vehicle control system to operate with lane position behavior similar to a human driven vehicle.

First claim

What is claimed is:

1. A method comprising:
obtaining sensor data pertaining to operation of a vehicle along a roadway by a human, from one or more sensors of the vehicle, the sensor data pertaining to a position of one or more shocks of a suspension system of the vehicle;
analyzing the sensor data, via one or more processors, as to one or more threshold values pertaining to the operation of the vehicle, the step of analyzing the sensor data comprises determining, via the one or more processors, whether:
a difference between the position of the one or more shocks and a default position of the one or more shocks is greater than a first predetermined threshold; and
the difference between the position of the one or more shocks and the default position of the one or more shocks is less than a second predetermined threshold;

identifying one or more conditions of the roadway, via the one or more processors, based on the analyzing of the sensor data, the step of identifying the one or more conditions comprises identifying the one or more conditions of the roadway based on whether:
the difference is greater than the first predetermined threshold; and
the difference is less than the second predetermined threshold;

classifying, via the one or more processors, the one or more conditions as comprising:
a pothole of the roadway, when the difference is greater than the first predetermined threshold; and
a bump of the roadway, when the difference is less than the second predetermined threshold;

identifying, via the processor using the sensor, a current lane position of the vehicle relative to a center of a lane in which the vehicle is travelling;
automatically moving the vehicle, in accordance with instructions provided by the one or more processors, in order to avoid the pothole, the bump, or both; and
updating a map database of the roadway stored in a computer memory, in accordance with instructions provided by the one or more processors, to include the pothole, the bump, or both, in addition to an optimal lane position of the lane of the roadway for maneuvering around the pothole, the bump, or both.

2. The method of claim 1 , further comprising:
utilizing the updated map database for subsequent autonomous control of the vehicle, one or more other vehicles, or both, in accordance with instructions provided by the one or more processors, including for using the optimal position of the lane of the roadway for maneuvering around the pothole, the bump, or both.

3. The method of claim 2 , wherein the step of utilizing the updated map database comprises automatically controlling steering of the vehicle, the one or more other vehicles, or both, in accordance with the instructions provided by the one or more processors, in order to avoid the one or more conditions of the roadway, including for using the optimal position of the lane of the roadway for maneuvering around the pothole, the bump, or both.

4. The method of claim 2 , wherein the step of utilizing the updated map database comprises automatically controlling the suspension system of the vehicle, the one or more other vehicles, or both, in accordance with the instructions provided by the one or more processors, in order to mitigate effects from the one or more conditions of the roadway, including for using the optimal position of the lane of the roadway for maneuvering around the pothole, the bump, or both.

5. The method of claim 1 , wherein:
the step of obtaining the sensor data further comprises obtaining the sensor data pertaining to lateral control by the human of the vehicle along the roadway, from the one or more sensors of the vehicle while the vehicle is operated by the human; and
the step of identifying the one or more conditions further comprises identifying the one or more conditions of the roadway on which the vehicle is travelling, based on the analyzing of the sensor data pertaining to the lateral control by the human of the vehicle along the roadway.

6. The method of claim 1 , wherein:
the sensor data further pertains to the current lane position of the vehicle inside the lane of the roadway;
the step of analyzing the sensor data further comprises determining, via the one or more processors, whether a difference between the current lane position of the vehicle and the center of the lane is greater than a predetermined threshold; and
the step of identifying the one or more conditions further comprises identifying the one or more conditions of the roadway based on whether the difference is greater than the predetermined threshold.

7. The method of claim 6 , wherein the predetermined is equal to approximately 0.2 inch.

8. The method of claim 1 , wherein:
the sensor data further pertains to an angular position of a steering wheel of the vehicle;
the step of analyzing the sensor data further comprises determining, via the one or more processors, whether a difference between the angular position of the steering wheel and a default angular position of the steering wheel is greater than a predetermined threshold; and
the step of identifying the one or more conditions further comprises identifying the one or more conditions of the roadway based on whether the difference is greater than the predetermined threshold.

9. The method of claim 1 , wherein:
the sensor data further pertains to an angular acceleration of a steering wheel of the vehicle;
the step of analyzing the sensor data further comprises determining, via the one or more processors, whether a difference between the angular acceleration of the steering wheel and a default angular acceleration of the steering wheel is greater than a predetermined threshold; and
the step of identifying the one or more conditions further comprises identifying the one or more conditions of the roadway based on whether the difference is greater than the predetermined threshold.

10. The method of claim 1 , wherein the step of updating the map database comprises updating the map database of the roadway stored in the computer memory, in accordance with instructions provided by the one or more processors, to include both a plurality of potholes and a plurality of bumps, in addition to an optimal lane position of the lane of the roadway for maneuvering around the potholes and the bumps based on the identifying and the classification of both the plurality of potholes and the plurality of bumps on the roadway via the one or more processors using the sensor data.

11. The method of claim 1 , wherein the updated computer database is used via the one or more processors of a fleet vehicles, including for automatically positioning each vehicle of the fleet in the optimal lane position of the lane of the roadway for maneuvering around the potholes and the bumps based on the identifying and the classification of both the plurality of potholes and the plurality of bumps on the roadway via the one or more processors using the sensor data.

12. A system comprising:
one or more sensors configured to obtain sensor data pertaining to operation of a vehicle along a roadway by a human, the sensor data pertaining to a position of one or more shocks of a suspension system of the vehicle;
a computer memory configured to store a map database for the roadway; and
one or more processors that are coupled to the one or more sensors and that are configured to at least facilitate:
analyzing the sensor data as to one or more threshold values pertaining to the operation of the vehicle, including by determining:
a difference between the position of the one or more shocks and a default position of the one or more shocks is greater than a first predetermined threshold; and
the difference between the p

Assignees

• Gm Global Tech Operations Llc

Inventors

• Hart Nathaniel W
• Wright Adam L
• Craig David A

Classifications

• B60W10/22

  including control of suspension systems · CPC title

• B60W2552/35

  Road bumpiness, e.g. potholes · CPC title

• B60W2540/18

  Steering angle · CPC title

• G06V20/588 Primary

  Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road · CPC title

• B60W2556/40

  High definition maps · CPC title