Automated vehicular damage detection

Patent metadata

Field	Value
Publication number	US-11568687-B2
Application number	US-201916671042-A
Country	US
Kind code	B2
Filing date	Oct 31, 2019
Priority date	Oct 31, 2019
Publication date	Jan 31, 2023
Grant date	Jan 31, 2023

Abstract

Described herein are systems, methods, and non-transitory computer readable media for evaluating vibrational characteristics of a vehicle such as an autonomous vehicle and vibrational characteristics of a road surface in conjunction with one another to identify anomalous vehicle vibrational characteristics that may be indicative of potential damage to the structure of a vehicle. A baseline vibrational signature may be generated for a road segment based on sensor data received from multiple vehicles traversing the road segment. A vibrational signature may also be generated for a particular vehicle being evaluated based on real-time sensor data. If the vibrational signature for the vehicle deviates from the baseline vibrational signature for the road segment by more than a threshold amount, the vehicle may be deemed to be exhibiting anomalous vibrational characteristics indicative of potential vehicular damage. One or more actions in response thereto may then be taken such as automatically halting the vehicle.

First claim

What is claimed is:

1. A computer-implemented method for automated determination of potential vehicular damage, comprising:
receiving real-time sensor data from one or more on-board sensors of a vehicle, the on-board sensors comprising an inertial measurement unit (IMU), the real-time sensor data being indicative of vibrational characteristics of the vehicle during operation;
determining a vibrational signature for the vehicle based at least in part on the real-time sensor data;
determining a baseline vibrational signature based on aggregated vibrational data from vehicles;
determining that the vehicle is currently traversing a second road segment different from a previously traversed first road segment, wherein the baseline vibrational signature comprises a first baseline vibrational signature corresponding to the first road segment;
determining a threshold value indicative of potential vehicular damage based at least in part on the baseline vibrational signature;
determining a second baseline vibrational signature corresponding to the second road segment;
determining, based at least in part on the first baseline vibrational signature, a first metric indicative of an average or cumulative amount of vibration associated with the first road segment;
determining, based at least in part on the second baseline vibrational signature, a second metric indicative of an average or cumulative amount of vibration associated with the second road segment;
determining, based at least in part on a comparison of the first metric and the second metric, that the average or cumulative amount of vibration associated with the second road segment is greater than the average or cumulative amount of vibration associated with the first road segment;
in response to determining that the average or cumulative amount of vibration associated with the second road segment is greater than the average or cumulative amount of vibration associated with the first road segment, increasing the threshold value indicative of the potential vehicular damage;
generating a vibrational anomaly alert responsive, at least in part, to determining that the vibrational signature for the vehicle exceeds the threshold value; and
initiating a response to the vibrational anomaly alert, wherein the response comprises:
determining a location within a predetermined proximity of a current location of the vehicle at which to halt the vehicle and initiating a braking operation to halt the vehicle at the location; or
sending a communication to a remote third-party emergency assistance provider.

2. The computer-implemented method of claim 1 ,
wherein the second baseline vibrational signature is based on map data corresponding to the second road segment.

3. The computer-implemented method of claim 1 , further comprising:
storing the baseline vibrational signature in association with map data corresponding to the road segment.

4. The computer-implemented method of claim 1 , wherein the one or more on-board sensors of the vehicle comprise a microphone.

5. A system for automated determination of potential vehicular damage, comprising:
at least one processor; and
at least one memory storing computer-executable instructions, wherein the at least one processor is configured to access the at least one processor and execute the computer-executable instructions to:
receive real-time sensor data from one or more on-board sensors of a vehicle, the on-board sensors comprising an inertial measurement unit (IMU), the real-time sensor data being indicative of vibrational characteristics of the vehicle during operation;
determine a road segment currently being traversed by the vehicle;
determine a baseline vibrational signature corresponding to the road segment based on aggregated vibrational data from vehicles;
determine a vibrational signature for the vehicle based at least in part on the real-time sensor data;
determine that the vehicle is currently traversing a second road segment different from a previously traversed first road segment, wherein the baseline vibrational signature comprises a first baseline vibrational signature corresponding to the first road segment;
determine a threshold value indicative of potential vehicular damage based at least in part on the baseline vibrational signature;
determine a second baseline vibrational signature corresponding to the second road segment;
determine, based at least in part on the first baseline vibrational signature, a first metric indicative of an average or cumulative amount of vibration associated with the first road segment;
determine, based at least in part on the second baseline vibrational signature, a second metric indicative of an average or cumulative amount of vibration associated with the second road segment;
determine, based at least in part on a comparison of the first metric and the second metric, that the average or cumulative amount of vibration associated with the second road segment is greater than the average or cumulative amount of vibration associated with the first road segment;
in response to determining that the average or cumulative amount of vibration associated with the second road segment is greater than the average or cumulative amount of vibration associated with the first road segment, increase the threshold value indicative of the potential vehicular damage;
generate a vibrational anomaly alert responsive, at least in part, to determining that the vibrational signature for the vehicle exceeds the threshold value; and
initiate a response to the vibrational anomaly alert, wherein the response comprises:
determining a location within a predetermined proximity of a current location of the vehicle at which to halt the vehicle and initiating a braking operation to halt the vehicle at the location; or
sending a communication to a remote third-party emergency assistance provider.

6. The system of claim 5 , wherein the
second baseline vibrational signature is based on map data corresponding to the second road segment.

7. The system of claim 5 , wherein the at least one processor is further configured to execute the computer-executable instructions to:
store the baseline vibrational signature in association with map data corresponding to the road segment.

8. The system of claim 5 , wherein the one or more on-board sensors of the vehicle comprise a microphone.

9. A computer program product for automated determination of potential vehicular damage, the computer program product comprising a non-transitory computer-readable medium readable by a processing circuit, the non-transitory computer-readable medium storing instructions executable by the processing circuit to cause a method to be performed, the method comprising:
receiving real-time sensor data from one or more on-board sensors of a vehicle, the on-board sensors comprising an inertial measurement unit (IMU), the real-time sensor data being indicative of vibrational characteristics of the vehicle during operation;
determining a vibrational signature for the vehicle based at least in part on the real-time sensor data;
determining a baseline vibrational signature based on aggregated vibrational data from vehicles;
determining that the vehicle is currently traversing a second road segment different from a previously traversed first road segment, wherein the baseline vibrational signature comprises a first baseline vibrational signature corresponding to the first road segment;
determining a threshold value indicative of potential vehicular damage based at least in part on the baseline vibrational signature;
determining a second baseline vibrational signature corresponding to the second road segment;
determining, based at least in part on

Assignees

• Pony Ai Inc

Inventors

• Dingli Robert
• Diehl Peter G
• Li chen yue

Classifications

• G07C5/008

  communicating information to a remotely located station (transmission systems for measured values G08C) · CPC title

• G07C5/085

  using electronic data carriers · CPC title

• G07C5/0816 Primary

  Indicating performance data, e.g. occurrence of a malfunction · CPC title

• G07C5/0808

  Diagnosing performance data (testing of vehicles G01M17/00; testing of electrical installation on vehicles G01R31/005) · CPC title

• B60Q9/008

  for anti-collision purposes · CPC title