Detection of distracted drivers

Patent metadata

Field	Value
Publication number	US-12365335-B2
Application number	US-202218055116-A
Country	US
Kind code	B2
Filing date	Nov 14, 2022
Priority date	Nov 14, 2022
Publication date	Jul 22, 2025
Grant date	Jul 22, 2025

Abstract

A system for detecting hazards for a vehicle includes a vehicle sensor for determining information about an environment surrounding the vehicle and a global navigation satellite system (GNSS). The system also includes a controller in electrical communication with the vehicle sensor and the GNSS. The controller is programmed to perform a plurality of measurements. The controller is further programmed to determine a plurality of classification scores of the first remote vehicle based at least in part on the plurality of measurements of the first remote vehicle and to determine an overall hazard score of the first remote vehicle based at least in part on the plurality of classification scores of the first remote vehicle. The controller is further programmed to take an action based at least in part on the overall hazard score of the first remote vehicle.

First claim

What is claimed is:

1. A system for detecting hazards for a vehicle, the system comprising:
a vehicle sensor for determining information about an environment surrounding the vehicle;
a global navigation satellite system (GNSS) for determining a geographical location, heading, and orientation of the vehicle;
a controller in electrical communication with the vehicle sensor and the GNSS, wherein the controller is programmed to:
perform a plurality of measurements of a first remote vehicle using the vehicle sensor to determine a position, heading, and velocity of the first remote vehicle;
determine a plurality of classification scores of the first remote vehicle based at least in part on the plurality of measurements of the first remote vehicle, wherein to determine the plurality of classification scores, the controller is further programmed to:
determine a plurality of position and speed violation classification scores of the first remote vehicle using a first machine learning classifier model;
determine a plurality of mutual interaction violation classification scores of the first remote vehicle using a second machine learning classifier model;
determine an anomaly detection score of the first remote vehicle using a machine learning anomaly detection model;
determine a plurality of traffic rule violation classification scores of the first remote vehicle using a third machine learning classifier model; and
determine a plurality of visual hazard classification scores of the first remote vehicle using a fourth machine learning classifier model;

determine an overall hazard score of the first remote vehicle based at least in part on the plurality of classification scores of the first remote vehicle, wherein the overall hazard score of the first remote vehicle is a weighted exponential moving average of the plurality of position and speed violation classification scores, the plurality of mutual interaction violation classification scores, the anomaly detection score, the plurality of traffic rule violation classification scores, and the plurality of visual hazard classification scores; and
control the vehicle using an automated routing system to guide the vehicle away from the first remote vehicle in response to determining that the overall hazard score of the first remote vehicle is above a predetermined overall hazard score threshold.

2. The system of claim 1 , wherein to determine the plurality of classification scores of the first remote vehicle, the controller is further programmed to:
determine an acceptable speed range of the first remote vehicle; and
determine a speeding classification score of the first remote vehicle based at least in part on the plurality of measurements of the first remote vehicle,
wherein to determine the speeding classification score, the controller is further programmed to compare a velocity of the first remote vehicle to the acceptable speed range of the first remote vehicle.

3. The system of claim 2 , wherein to determine the acceptable speed range of the first remote vehicle, the controller is further programmed to:
determine a plurality of road characteristics of a roadway upon which the first remote vehicle is traveling using at least one of: the vehicle sensor and the GNSS,
wherein the plurality of road characteristics includes at least one of: a road type, an effective road width, and a road speed limit;

determine a plurality of road conditions of the roadway upon which the first remote vehicle is traveling using at least one of: the vehicle sensor and the GNSS,
wherein the plurality of road conditions includes at least one of: a road weather condition, a road moisture condition, and a road lighting condition;

determine a plurality of road hazard statuses of the roadway upon which the first remote vehicle is traveling using the vehicle sensor,
wherein the plurality of road hazard statuses includes at least one of: a pedestrian presence status, a bicyclist presence status, and a congestion hazard status; and

calculate the acceptable speed range of the first remote vehicle using a machine learning regression model,
wherein the machine learning regression model has been trained to output the acceptable speed range of the first remote vehicle based on the plurality of road characteristics, the plurality of road conditions, and the plurality of road hazard statuses of the roadway upon which the first remote vehicle is traveling.

4. The system of claim 1 , wherein to determine the plurality of position and speed violation classification scores of the first remote vehicle, the controller is further programmed to:
retrieve a location of lane edges of a roadway upon which the first remote vehicle is traveling using at least one of: the GNSS and the vehicle sensor; and
determine the plurality of position and speed violation classification scores of the first remote vehicle using the first machine learning classifier model,
wherein the plurality of position and speed violation classification scores includes a lane keeping failure classification score, an excessive turn speed classification score, and an excessive speed change classification score, and
wherein the first machine learning classifier model has been trained to output the plurality of position and speed violation classification scores based on the plurality of measurements of the first remote vehicle and the location of lane edges.

5. The system of claim 1 , wherein to determine the plurality of mutual interaction violation classification scores of the first remote vehicle, the controller is further programmed to:
determine a distance between the first remote vehicle and a second remote vehicle using the vehicle sensor;
compare the distance between the first remote vehicle and the second remote vehicle to a predetermined distance threshold;
perform a plurality of measurements of the second remote vehicle using the vehicle sensor to determine a position, heading, and velocity of a second remote vehicle in response to determining that the distance between the first remote vehicle and the second remote vehicle is less than or equal to the predetermined distance threshold; and
determine the plurality of mutual interaction violation classification scores of the first remote vehicle using the second machine learning classifier model,
wherein the plurality of mutual interaction violation classification scores includes a tailgating classification score, a dangerous passing classification score, and a road rage classification score, and
wherein the second machine learning classifier model has been trained to output the plurality of mutual interaction violation classification scores based on the plurality of measurements of the first remote vehicle and the plurality of measurements of the second remote vehicle.

6. The system of claim 1 , wherein to determine the anomaly detection score of the first remote vehicle, the controller is further programmed to:
determine the anomaly detection score of the first remote vehicle using the machine learning anomaly detection model,
wherein the machine learning anomaly detection model has been trained to detect anomalies based on at least one of: the plurality of measurements of the first remote vehicle and geographic data from the GNSS.

7. The system of claim 1 , wherein to determine the plurality of traffic rule violation classification scores of the first remote vehicle, the controller is further programmed to:
retrieve information about road signs in an environment surrounding the first remote vehicle using at least one of: the GNSS and the vehicle sensor;
retrieve information about traffic signals in the environment surrounding the first remote vehicle using at least one of: the GNSS and the vehicle sensor;
d

Assignees

• Gm Global Tech Operations Llc

Inventors

• Esna Ashari Esfahani Alireza
• Mudalige Upali P

Classifications

• B60W2554/4042

  Longitudinal speed · CPC title

• B60W2554/4044

  Direction of movement, e.g. backwards · CPC title

• B60W2554/4049

  Relationship among other objects, e.g. converging dynamic objects · CPC title

• B60W2555/60

  Traffic rules, e.g. speed limits or right of way · CPC title

• B60W2554/4046

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