Detection of driving actions that mitigate risk

Patent metadata

Field	Value
Publication number	US-12468269-B2
Application number	US-202217728053-A
Country	US
Kind code	B2
Filing date	Apr 25, 2022
Priority date	Oct 12, 2017
Publication date	Nov 11, 2025
Grant date	Nov 11, 2025

Abstract

Systems and methods are provided for detecting a driving action that mitigates risk.

First claim

What is claimed is:

1 . A computer-implemented method comprising:
determining, using a camera coupled to a first vehicle, a position of a second vehicle; determining that the second vehicle is about to enter a lane in which the first vehicle is traveling and that the first vehicle is driving faster than the second vehicle, causing a predicted risk based on a following distance that is shorter than a threshold distance; determining that a driver of the first vehicle performs a defensive driving action that is:
responsive to the predicted risk;
initiated prior to the driver being presented with any form of message regarding the predicted risk; and
at least as safe as a typical driver in a same defensive driving scenario; and
generating an alert notification based on the determination that the driver performed the defensive driving action, wherein the alert notification comprises an identification of the predicted risk based on the following distance that is shorter than the threshold distance and an identification of the defensive driving action that mitigated the predicted risk.

2 . The computer implemented method of claim 1 , further comprising:
assessing an updated risk after the driver of the first vehicle performed the defensive driving action; and comparing the updated risk after the driver of the first vehicle performed the defensive driving action with the predicted risk had the driver not performed the defensive driving action.

3 . The computer-implemented method of claim 1 , wherein the defensive driving action includes slowing down the first vehicle or moving the first vehicle to a different lane.

4 . The computer-implemented method of claim 1 , wherein the defensive driving action includes slowing down the first vehicle within a time period leading up to or just after the second vehicle moved into the lane in which the first vehicle is traveling.

5 . The computer-implemented method of claim 4 , further comprising:
determining that the distance between the first vehicle and the second vehicle has increased in the time period.

6 . The computer-implemented method of claim 1 , further comprising:
determining that a following distance between the first vehicle and the second vehicle will be below a predetermined threshold if the second vehicle enters the lane in which the first vehicle is traveling.

7 . The computer-implemented method of claim 1 , further comprising:
transmitting data to a remote device, wherein the data includes an inference that the driver performed the defensive driving action that mitigated risk.

8 . The computer-implemented method of claim 7 , wherein the data includes video data from the camera.

9 . The computer-implemented method of claim 8 , further comprising:
training an autonomous vehicle driving system with the video data.

10 . The computer-implemented method of claim 1 , wherein the second vehicle is about to enter the lane in which the first vehicle is traveling from a merging lane of a highway.

11 . A system comprising:
at least one memory unit; and at least one processor coupled to the at least one memory unit, in which the at least one processor is configured to:
determine, using a camera coupled to a first vehicle, a position of a second vehicle;
determine that the second vehicle is about to enter a lane in which the first vehicle is traveling and that the first vehicle is driving faster than the second vehicle, causing a predicted risk based on a following distance that is shorter than a threshold distance;
determine whether a driver of the first vehicle performs a defensive driving action that is:
responsive to the predicted risk;
initiated prior to the driver being presented with any form of message regarding the predicted risk; and
at least as safe as a typical driver in a same defensive driving scenario; and

generate an alert notification based on the determination that the driver performed the defensive driving action, wherein the alert notification comprises an identification of the predicted risk based on the following distance that is shorter than the threshold distance and an identification of the defensive driving action that mitigated the predicted risk.

12 . The system of claim 11 , wherein the at least one processor is further configured to:
assess an updated risk after the driver of the first vehicle performed the defensive driving action; and compare the updated risk after the driver of the first vehicle performed the defensive driving action with the predicted risk had the driver not performed the defensive driving action.

13 . The system of claim 11 , wherein the defensive driving action includes slowing down the first vehicle or moving the first vehicle to a different lane.

14 . The system of claim 11 , wherein the at least one processor is further configured to:
transmitting data to a remote device, wherein the data includes an inference that the driver performed the defensive driving action that mitigated risk.

15 . The system of claim 14 , wherein the data includes video data from the camera, and wherein the at least one processor is further configured to:
train an autonomous vehicle driving system with the video data.

16 . A machine-readable storage medium having computer-executable instructions stored thereon that, when executed by one or more processors, cause the one or more processors to perform operations comprising:
determining, using a camera coupled to a first vehicle, a position of a second vehicle; determining that the second vehicle is about to enter a lane in which the first vehicle is traveling and that the first vehicle is driving faster than the second vehicle, causing a predicted risk based on a following distance that is shorter than a threshold distance; determining whether a driver of the first vehicle performs a defensive driving action that is:
responsive to the predicted risk;
initiated prior to the driver being presented with any form of message regarding the predicted risk; and
at least as safe as a typical driver in a same defensive driving scenario; and
generating an alert notification based on the determination that the driver performed the defensive driving action, wherein the alert notification comprises an identification of the predicted risk based on the following distance that is shorter than the threshold distance and an identification of the defensive driving action that mitigated the predicted risk.

17 . The machine-readable storage medium of claim 16 , wherein the operations further comprise:
assessing an updated risk after the driver of the first vehicle performed the defensive driving action; and comparing the updated risk after the driver of the first vehicle performed the defensive driving action with the predicted risk had the driver not performed the defensive driving action.

18 . The machine-readable storage medium of claim 16 , wherein the defensive driving action includes slowing down the first vehicle or moving the first vehicle to a different lane.

19 . The machine-readable storage medium of claim 16 , wherein the operations further comprise:
transmitting data to a remote device, wherein the data includes an inference that the driver performed the defensive driving action that mitigated risk.

20 . The machine-readable storage medium of claim 19 , wherein the data includes video data from the camera, and wherein the operations further comprise:
training an autonomous vehicle driving system with the video data.

Assignees

• Netradyne Inc

Inventors

• Campos Michael
• Anubhav
• Annapureddy Venkata Sreekanta Reddy
• Gupta Vikram
• Rahman Hisham
• Aenugu Sneha
• Bakliwal Priyam
• Thomas Alexander
• Kahn Adam David
• Julian David Jonathan
• Pandya Sandeep
• Agrawal Avneesh

Classifications

• G06V20/588

  Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road · CPC title

• G06V20/58

  Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads · CPC title

• B60R11/04

  Mounting of cameras operative during drive; Arrangement of controls thereof relative to the vehicle · CPC title

• G08G1/04

  using optical or ultrasonic detectors · CPC title

• G08G1/166

  for active traffic, e.g. moving vehicles, pedestrians, bikes · CPC title