Vulnerable road user's adversarial behavior opportunity and capability

Patent metadata

Field	Value
Publication number	US-12420839-B2
Application number	US-202318319026-A
Country	US
Kind code	B2
Filing date	May 17, 2023
Priority date	May 17, 2023
Publication date	Sep 23, 2025
Grant date	Sep 23, 2025

Abstract

A system for determining opportunity and capability for identified adversarial behavior within an autonomous vehicle, comprising a pedestrian detection system, a vehicle controller and an adversarial intent algorithm adapted to determine a risk level of adversarial behavior from at least one pedestrian within proximity of the autonomous vehicle, and, when the adversarial intent algorithm determines that there is a risk of adversarial behavior, to determine a risk level of the adversarial behavior based on opportunity and capability.

First claim

What is claimed is:

1. A method of determining opportunity and capability for identified adversarial behavior within an autonomous vehicle, comprising:
determining, with a pedestrian detection system, a vehicle controller and an adversarial intent algorithm, a risk level of adversarial behavior from at least one pedestrian within proximity of the autonomous vehicle based on contextual information including at least one of: a time of day, historical data related to how safe a location where the autonomous vehicle is located is, how crowded a cross-walk is, weather conditions and how well the location where the autonomous vehicle is located is illuminated;
when the adversarial intent algorithm determines that there is a risk of adversarial behavior, determining the risk level of the adversarial behavior based on opportunity and capability; and
generating visual and auditory warning cues for the at least one pedestrian, generating reports with information related to the adversarial behavior and sending the reports with the information related to the adversarial behavior to remotely located police and emergency service providers, based on the risk level of the adversarial behavior.

2. The method of claim 1 , wherein the determining a risk level of the adversarial behavior based on opportunity and capability includes initiating, with the vehicle controller, an opportunity algorithm adapted to determine one of: a positive opportunity of adversarial behavior and a negative opportunity of adversarial behavior.

3. The method of claim 2 , wherein the initiating, with the vehicle controller, the opportunity algorithm includes determining one of the positive opportunity of adversarial behavior and the negative opportunity of adversarial behavior based on the contextual information.

4. The method of claim 2 , wherein, if the opportunity algorithm indicates a negative opportunity of adversarial behavior, the method includes determining, with the vehicle controller, a low risk of adversarial behavior and continuing to run, with the vehicle controller, the opportunity algorithm.

5. The method of claim 4 , wherein, if the opportunity algorithm indicates a positive opportunity of adversarial behavior, the method includes initiating, with the vehicle controller, a capability algorithm adapted to determine one of: a positive capability of adversarial behavior and a negative capability of adversarial behavior.

6. The method of claim 5 , wherein, the initiating, with the vehicle controller, the capability algorithm further includes initiating a threatening object detection algorithm.

7. The method of claim 6 , wherein, if the capability algorithm indicates a negative capability of adversarial behavior, the method includes determining, with the vehicle controller, a low risk of adversarial behavior and continuing to run, with the vehicle controller, the capability algorithm.

8. The method of claim 7 , wherein, if the opportunity algorithm indicates a positive opportunity of adversarial behavior, and, if the capability algorithm indicates a positive capability of adversarial behavior, the method includes determining, with the vehicle controller, a high risk of adversarial behavior.

9. The method of claim 8 , wherein, the determining, with the vehicle controller, a low risk of adversarial behavior further includes generating, with the vehicle controller, the visual and auditory warning cues for the pedestrian.

10. The method of claim 9 , wherein, the determining, with the vehicle controller, a high risk of adversarial behavior further includes the generating, with the vehicle controller, reports with information related to the adversarial behavior and sending the reports with the information related to the adversarial behavior to remotely located entities.

11. A system for determining opportunity and capability for identified adversarial behavior within an autonomous vehicle, comprising a pedestrian detection system, a vehicle controller and an adversarial intent algorithm adapted to determine a risk level of adversarial behavior from at least one pedestrian within proximity of the autonomous vehicle based on contextual information including at least one of: a time of day, historical data related to how safe a location where the autonomous vehicle is located is, how crowded a cross-walk is, weather conditions and how well the location where the autonomous vehicle is located is illuminated, and, when the adversarial intent algorithm determines that there is a risk of adversarial behavior, to determine the risk level of the adversarial behavior based on opportunity and capability, and generate visual and auditory warning cues for the at least one pedestrian, generate reports with information related to the adversarial behavior and send the reports with the information related to the adversarial behavior to remotely located police and emergency service providers, based on the risk level of the adversarial behavior.

12. The system of claim 11 , wherein when determining a risk level of the adversarial behavior based on opportunity and capability, the vehicle controller is further adapted to initiate an opportunity algorithm adapted to determine one of: a positive opportunity of adversarial behavior and a negative opportunity of adversarial behavior.

13. The system of claim 12 , wherein when initiating the opportunity algorithm, the vehicle controller is further adapted to determine one of the positive opportunity of adversarial behavior and the negative opportunity of adversarial behavior based on a time of day, historical data related to how safe a location where the autonomous vehicle is located is, and how well the location where the autonomous vehicle is located is illuminated.

14. The system of claim 12 , wherein, if the opportunity algorithm indicates a negative opportunity of adversarial behavior, the vehicle controller is further adapted to determine a low risk of adversarial behavior and to continue running the opportunity algorithm.

15. The system of claim 14 , wherein, if the opportunity algorithm indicates a positive opportunity of adversarial behavior, the vehicle controller is further adapted to initiate a capability algorithm adapted to determine one of: a positive capability of adversarial behavior and a negative capability of adversarial behavior.

16. The system of claim 15 , wherein, when initiating the capability algorithm, the vehicle controller is further adapted to initiate a threatening object detection algorithm.

17. The system of claim 16 , wherein, if the capability algorithm indicates a negative capability of adversarial behavior, the vehicle controller is further adapted to determine a low risk of adversarial behavior and to continue running the capability algorithm.

18. The system of claim 17 , wherein, if the opportunity algorithm indicates a positive opportunity of adversarial behavior, and, if the capability algorithm indicates a positive capability of adversarial behavior, the vehicle controller is adapted to determine a high risk of adversarial behavior.

19. The system of claim 18 , wherein, when the vehicle controller determines a low risk of adversarial behavior, the vehicle controller is further adapted to cause the autonomous vehicle to generate visual and auditory warning cues for the pedestrian, and, when the vehicle controller determines a high risk of adversarial behavior, the vehicle controller is further adapted to generate reports with information related to the adversarial behavior and send the reports with the information related to the adve

Assignees

• Gm Global Tech Operations Llc

Inventors

• Khamis Alaa M
• Tong Wei
• Mudalige Upali P

Classifications

• B60W2420/403

  Image sensing, e.g. optical camera · CPC title

• G06V20/64

  Three-dimensional [3D] objects · CPC title

• B60W2554/4046

  Behavior, e.g. aggressive or erratic · CPC title

• B60W2554/4029

  Pedestrians · CPC title

• B60W2556/45

  External transmission of data to or from the vehicle · CPC title