Vehicle wheel impact detection

Patent metadata

Field	Value
Publication number	US-10916074-B2
Application number	US-201816036328-A
Country	US
Kind code	B2
Filing date	Jul 16, 2018
Priority date	Jul 16, 2018
Publication date	Feb 9, 2021
Grant date	Feb 9, 2021

Abstract

Data describing operation of a vehicle is provided to a deep neural network. A vehicle wheel impact event is determined based on output of the deep neural network. Alternatively or additionally, it is possible to determine the wheel impact event based on output of a threshold based algorithm that compares vehicle acceleration and the velocity to one or more thresholds.

First claim

What is claimed is:

1. A computer comprising a processor and a memory, the memory storing instructions executable by the processor to:
provide a first set of vehicle data to a deep neural network;
provide a second set of vehicle data to a threshold based algorithm that compares vehicle acceleration and velocity to one or more thresholds;
perform a comparison of a first impact severity level output from the deep neural network to a second impact severity level output by the threshold based algorithm; and
determine a vehicle wheel impact event based at least in part on the comparison of the first impact severity level output from the deep neural network and the second impact severity level output by the threshold based algorithm.

2. The computer of claim 1 , the instructions further including instructions to determine that the first impact severity level and the second impact severity level differ, and to then determine the vehicle wheel impact event based on the second impact severity level.

3. The computer of claim 1 , wherein each of the first set of data and the second set of data include at least one of velocity, yaw rate, roll rate, total acceleration, vertical acceleration, lateral acceleration, longitudinal acceleration, a wheel speed, a brake torque, an accelerator pedal position, a steering angle, and an ignition status.

4. The computer of claim 1 , the instructions further including instructions to actuate a vehicle component based on the wheel impact event.

5. The computer of claim 1 , wherein the wheel impact event includes one or more of an impact severity, a predicted impact cause, and an identification of an impacted wheel.

6. The computer of claim 5 , wherein the impact severity is selected from a plurality of impact severity levels.

7. A method, comprising:
providing a first set of vehicle data to a deep neural network;
providing a second set of vehicle data to a threshold based algorithm that compares vehicle acceleration and velocity to one or more thresholds;
performing a comparison of a first impact severity level output from the deep neural network to a second impact severity level output by the threshold based algorithm; and
determining a vehicle wheel impact event based at least in part on the comparison of the first impact severity level output from the deep neural network and the second impact severity level output by the threshold based algorithm.

8. The method of claim 7 , further comprising comparing a first impact severity level output from the deep neural network to a second impact severity level output by the threshold based algorithm.

9. The method of claim 7 , wherein the first set of vehicle data includes at least one of velocity, yaw rate, roll rate, total acceleration, vertical acceleration, lateral acceleration, longitudinal acceleration, a wheel speed, a brake torque, an accelerator pedal position, a steering angle, and an ignition status.

10. The method of claim 7 , further comprising actuating a vehicle component based on the wheel impact event.

11. The method of claim 7 , wherein the wheel impact event includes one or more of an impact severity, a predicted impact cause, and an identification of an impacted wheel.

12. The method of claim 11 , wherein the impact severity is selected from a plurality of impact severity levels.

13. The method of claim 8 , further comprising determining that the first impact severity level and the second impact severity level differ, and then determining the vehicle wheel impact event based on the second impact severity level.

Assignees

• Ford Global Tech Llc

Inventors

• Panigrahi Smruti Ranjan
• Luo Dawei
• Lu Jianbo
• Wang Dexin

Classifications

• G06N3/0499

  Feedforward networks · CPC title

• G06N3/09

  Supervised learning · CPC title

• G06N3/02

  Neural networks · CPC title

• G01L5/0052

  measuring forces due to impact (G01L5/0061, G01L5/14 take precedence; impact testing of structures G01M7/08; impact testing of material G01N3/00) · CPC title

• B60W30/09 Primary

  Taking automatic action to avoid collision, e.g. braking and steering · CPC title