Systems and methods for detecting turn indicator light signals

Patent metadata

Field	Value
Publication number	US-11951981-B2
Application number	US-202217652965-A
Country	US
Kind code	B2
Filing date	Mar 1, 2022
Priority date	Mar 1, 2022
Publication date	Apr 9, 2024
Grant date	Apr 9, 2024

Abstract

Systems and methods of detecting and validating a turn light indicator in a vehicle include receiving optical perception data from an optical perception system. The optical perception data includes data describing a detected turn indicator light of another vehicle perceived by the optical perception system including a status of the detected turn indicator light. A turn indicator light signal is generated in the form of a time varying waveform based on the status of the detected turn indicator light. A duty cycle and frequency of the turn indicator light signal is obtained. An assessment is made whether the detected turn indicator light is a valid detection by comparing the duty cycle and frequency with predetermined bounds. When the detected turn indicator light is assessed to be a valid detection, then an automated feature of the vehicle is controlled based on the data describing the detected turn indicator light.

First claim

What is claimed is:

1. A method of detecting and validating a turn light indicator in a vehicle, the method comprising:
receiving, via at least one processor, optical perception data from an optical perception system of the vehicle, wherein the optical perception data includes data describing at least one detected turn indicator light of another vehicle perceived by the optical perception system including a status of the at least one detected turn indicator light;
generating, via the at least one processor, a turn indicator light signal in the form of a time varying waveform based on the status of the at least one detected turn indicator light;
obtaining, via the at least one processor, a duty cycle and frequency of the turn indicator light signal;
assessing, via the at least one processor, whether the at least one detected turn indicator light is a valid detection by comparing the duty cycle and frequency with predetermined bounds; and
when the at least one detected turn indicator light is assessed to be a valid detection, then controlling, via the at least one processor, at least one automated feature of the vehicle based on the data describing the at least one detected turn indicator light.

2. The method of claim 1 , wherein when the at least one detected turn indicator light is assessed not to be a valid detection, then the at least one automated feature of the vehicle is controlled without using the data describing at least one detected turn indicator light.

3. The method of claim 1 , wherein the assessing further includes deriving a consistency over time metric for at least one of the duty cycle and the frequency and comparing the consistency over time metric with an expected limit.

4. The method of claim 1 , wherein the predetermined bounds range from 1 to 2 Hertz for the frequency and 30% to 75% ON time for the duty cycle.

5. The method of claim 1 , wherein the optical perception system includes an artificial intelligence engine configured to detect the at least one detected turn indicator light based on image data from one or more cameras of the vehicle.

6. The method of claim 1 , wherein the at least one automated feature of the vehicle includes braking, steering, propulsion and outputting a visual and/or audible warning or alert through a visual and/or audio output device.

7. The method of claim 1 , wherein the time varying waveform comprises a step function.

8. The method of claim 1 , wherein the duty cycle is measured over a first time window and the frequency is measured over a second time window.

9. The method of claim 8 , wherein a length of time of the first time window is the same as a length of time of the second time window.

10. The method of claim 1 , wherein the data describing at least one detected turn indicator light of another vehicle includes location.

11. A vehicle, comprising:
an optical perception system; and
at least one processor in operable communication with the optical perception system, wherein the at least one processor is configured to execute program instructions, wherein the program instructions are configured to cause the at least one processor to:
receive optical perception data from the optical perception system of the vehicle, wherein the optical perception data includes data describing at least one detected turn indicator light of another vehicle perceived by the optical perception system including a status of the at least one detected turn indicator light;
generate a turn indicator light signal in the form of a time varying waveform based on the status of the at least one detected turn indicator light;
obtain a duty cycle and frequency of the turn indicator light signal;
assess whether the at least one detected turn indicator light is a valid detection by comparing the duty cycle and frequency with predetermined bounds; and
when the at least one detected turn indicator light is assessed to be a valid detection, then control at least one automated feature of the vehicle based on the data describing the at least one detected turn indicator light.

12. The vehicle of claim 11 , wherein when the at least one detected turn indicator light is assessed not to be a valid detection, then the at least one automated feature of the vehicle is controlled without using the data describing at least one detected turn indicator light.

13. The vehicle of claim 11 , wherein the program instructions are configured to cause the at least one processor to assess whether the at least one detected turn indicator light is a valid detection further by deriving a consistency over time metric for at least one of the duty cycle and the frequency and comparing the consistency over time metric with an expected limit.

14. The vehicle of claim 11 , wherein the predetermined bounds range from 1 to 2 Hertz for the frequency and 30% to 75% ON time for the duty cycle.

15. The vehicle of claim 11 , wherein the vehicle includes one or more cameras and the optical perception system includes an artificial intelligence engine configured to detect the at least one detected turn indicator light based on image data from the one or more cameras.

16. The vehicle of claim 11 , wherein the at least one automated feature of the vehicle includes braking, steering, propulsion and outputting a visual and/or audible warning or alert through a visual and/or audio output device.

17. The vehicle of claim 11 , wherein the time varying waveform comprises a step function.

18. The vehicle of claim 11 , wherein the duty cycle is measured over a first time window and the frequency is measured over a second time window.

19. The vehicle of claim 18 , wherein a length of time of the first time window is the same as a length of time of the second time window.

20. The vehicle of claim 11 , wherein the data describing at least one detected turn indicator light of another vehicle includes location.

Assignees

• Gm Global Tech Operations Llc
• Gm Global Tech Operations

Inventors

• Kraft Daniel R
• Jakubczak Taylor A
• Grewal Amanpal S
• Khan Darren
• Llewellyn Ben

Classifications

• B60W30/0956 Primary

  the prediction being responsive to traffic or environmental parameters · CPC title

• B60W10/04

  including control of propulsion units · CPC title

• B60W10/18

  including control of braking systems · CPC title

• B60W10/20

  including control of steering systems · CPC title

• B60W50/14

  Means for informing the driver, warning the driver or prompting a driver intervention · CPC title