Detection of vehicle operating conditions

Patent metadata

Field	Value
Publication number	US-12397779-B2
Application number	US-202016752820-A
Country	US
Kind code	B2
Filing date	Jan 27, 2020
Priority date	Jan 27, 2020
Publication date	Aug 26, 2025
Grant date	Aug 26, 2025

Abstract

A system includes a processor programmed to: identify, based on data from first sensors included in a first vehicle, a second vehicle moving within a first threshold distance of a travel path of the first vehicle and within a second threshold distance of the first vehicle. The processor is further programmed to receive, from second sensors included in the first vehicle, transient velocity data of the second vehicle; and determine an operating condition of the second vehicle based on the transient velocity data.

First claim

What is claimed is:

1. A system comprising a computer including a processor and a memory, the memory including instructions such that the processor is programmed to:
identify, based on data from first sensors included in a first vehicle, a second vehicle moving within a first threshold distance of a travel path of the first vehicle and within a second threshold distance of the first vehicle;
select a measurement target that is the second vehicle or an element on the second vehicle;
collect, from second sensors included in the first vehicle, transient velocity data from the measurement target, wherein the transient velocity data describes a velocity of the measurement target at a frequency of oscillation of the measurement target with respect to the second sensors; and
determine an operating condition of the second vehicle based on the transient velocity data.

2. The system of claim 1 , wherein the processor is further programmed to:
determine, based on the data from the first sensors, an average radial velocity of the second vehicle relative to the first vehicle, wherein determining the operating condition of the second vehicle is further based on the average radial velocity of the second vehicle relative to the first vehicle.

3. The system of claim 1 , wherein the processor is further programmed to:
determine, based on data from the first sensors; physical dimensions of the second vehicle, wherein determining the operating condition of the second vehicle is further based on the physical dimensions of the second vehicle.

4. The system of claim 1 , wherein the processor is further programmed to:
determine a velocity of the second vehicle relative to a support surface, wherein determining the operating condition of the second vehicle is further based on the velocity of the second vehicle relative to the support surface.

5. The system of claim 1 , wherein the processor is further programmed to:
determine a type of support surface on which the second vehicle is travelling, wherein determining the operating condition of the second vehicle is further based on the type of the support surface.

6. The system of claim 1 , wherein the processor is further programmed to:
predict a trajectory of the second vehicle based on the determined operating condition of the second vehicle.

7. The system of claim 6 , wherein the processor is further programmed to: adjust a travel path of the first vehicle based on the predicted trajectory of the second vehicle.

8. The system of claim 1 , wherein the processor is further programmed to: receive from the second sensors, transient velocity data from a surface supporting the first vehicle; and
determine the operating condition in part based on the transient velocity data from the surface supporting the first vehicle.

9. The system of claim 8 , wherein the processor is further programmed to filter the transient velocity data from the measurement target based on the transient velocity data from the surface supporting the first vehicle.

10. The system of claim 9 , wherein the processor is further programmed to:
input the filtered transient velocity data to a trained neural network which determines the operating condition; and
receive the operating condition of the second vehicle from the trained neural network.

11. The system of claim 10 , wherein the trained neural network is trained using a plurality of transient velocity data, each of the plurality of transient velocity data representative of a moving vehicle in a respective controlled operating condition and further wherein each of the respective controlled operating conditions correspond to respective ground truths for purposes of training the trained neural network.

12. The system of claim 1 , wherein the processor is further programmed to:
notify the second vehicle in a case that the transient velocity data indicates a failure mode in the second vehicle.

13. A method comprising:
identifying, based on data from first sensors included in a first vehicle, a second vehicle moving within a first threshold distance of a travel path of the first vehicle and within a second threshold distance of the first vehicle;
selecting a measurement target that is the second vehicle or an element on the second vehicle;
collecting, from second sensors included in the first vehicle, transient velocity data from the measurement target, wherein the transient velocity data describes a velocity of the measurement target at a frequency of oscillation of the measurement target with respect to the second sensors; and
determining an operating condition of the second vehicle based on the transient velocity data.

14. The method of claim 13 , further comprising:
determining, based on the data from the first sensors, an average radial velocity of the second vehicle relative to the first vehicle, wherein determining the operating condition of the second vehicle is further based on the average radial velocity of the second vehicle relative to the first vehicle.

15. The method of claim 13 , further comprising:
determining, based on data from the first sensors; dimensions of the second vehicle, wherein determining the operating condition of the second vehicle is further based on the physical dimensions of the second vehicle.

16. The method of claim 13 , further comprising:
determining a velocity of the second vehicle relative to a support surface, wherein determining the operating condition of the second vehicle is further based on the velocity of the second vehicle relative to the support surface.

17. The method of claim 13 , further comprising:
predicting a trajectory of the second vehicle based on the determined operating condition of the second vehicle, and
adjusting a travel path of the first vehicle based on the predicted trajectory of the second vehicle.

18. The method of claim 13 , further comprising:
receiving from the second sensors, transient velocity data from a surface supporting the first vehicle; and
determining the operating condition in part based on the transient velocity data from the surface supporting the first vehicle.

19. The method of claim 13 , further comprising:
inputting the transient velocity data from the second vehicle to a trained neural network which determines the operating condition; and
receiving the operating condition of the second vehicle from the trained neural network, wherein the trained neural network is trained using a plurality of transient velocity data, each of the plurality of transient velocity data representative of a moving vehicle in a respective controlled operating condition and further wherein each of the respective controlled operating conditions correspond to respective ground truths for purposes of training the trained neural network.

20. The method of claim 13 , further comprising:
notifying the second vehicle in a case that the transient velocity data indicates a failure mode in the second vehicle.

Assignees

• Ford Global Tech Llc

Inventors

• Herman david michael
• Lesky Aaron
• Beras Ronald
• Arunmozhi Ashwin

Classifications

• G06N3/0442

  characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU] · CPC title

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title

• G06N3/09

  Supervised learning · CPC title

• G06N3/08

  Learning methods · CPC title

• B60W2554/804

  Relative longitudinal speed · CPC title