Modeling driver style to lower a carbon footprint

Patent metadata

Field	Value
Publication number	US-12561696-B2
Application number	US-202218086627-A
Country	US
Kind code	B2
Filing date	Dec 21, 2022
Priority date	Dec 21, 2022
Publication date	Feb 24, 2026
Grant date	Feb 24, 2026

Abstract

An example operation includes comparing a first set of driving styles for a vehicle to a second set of driving styles for one or more similar vehicles in a geographic area over a period, wherein the first set of driving styles affects a carbon footprint of the vehicle and the second set of driving styles affects another carbon footprint of the one or more similar vehicles; determining a carbon credit when the carbon footprint of the vehicle is lower than the another carbon footprint of the one or more similar vehicles, by a threshold, based on the comparing; and applying the carbon credit to the vehicle.

First claim

What is claimed is:

1 . A method, comprising:
receiving, by a processor of a vehicle, real-time driving data from a sensor of the vehicle; determining a driving style of the vehicle based on at least one of throttle activations, braking patterns, vehicle speed, steering angles, and operating modes included in the real-time driving data; determining, by the processor, a carbon footprint of the vehicle based on execution of a machine learning model on the real-time driving data, where the machine learning model is trained on historical driving data and environmental parameters and is configured to adapt dynamically based on changing driving conditions; determining a change to the driving style of the vehicle to reduce the carbon footprint of the vehicle; modifying at least one of an engine throttle and a braking system of the vehicle to respond less abruptly when activated while the vehicle is travelling based on the determined change to the driving style of the vehicle; determining a modification to an operation of the vehicle based on a predicted reduction of the carbon footprint; and predicting when the carbon footprint will equal a second carbon footprint based on the modification.

2 . The method of claim 1 , comprising:
notifying the vehicle of a difference between the carbon footprint and a second carbon footprint which is greater than a threshold.

3 . The method of claim 1 , comprising:
determining a recommendation for the vehicle, wherein the recommendation comprises a proposed change in an operation of the vehicle; predicting reduction in the carbon footprint based on the recommendation; and providing the recommendation and the predicted reduction to the vehicle.

4 . The method of claim 1 , comprising:
gathering, by the vehicle, a set of user data comprising at least one of: a route traveled, a driving behavior, a vehicle utilization level, a vehicle maintenance status, a weather condition, or a road condition; and providing the set of user data to an artificial intelligence model configured for predicting the carbon footprint of the vehicle based on the set of user data.

5 . The method of claim 1 , wherein the determining the change to the driving style comprises determining a change to an operating mode of an engine of the vehicle that consumes less carbon footprint.

6 . The method of claim 1 , further comprising changing an operating mode of an engine of the vehicle based on the determined change to the driving style of the vehicle.

7 . A system, comprising:
a memory storing instructions; and a processor that, when executing the instructions, is configured to
receive real-time driving data from a sensor of a vehicle;
determine a driving style of the vehicle based on at least one of throttle activations, braking patterns, vehicle speed, steering angles, and operating modes included in the real-time driving data;
determine a carbon footprint of the vehicle based on execution of a machine learning model on the real-time driving data, where the machine learning model is trained on historical driving data and environmental parameters, and is configured to adapt dynamically based on changing driving conditions;
determine a change to the driving style of the vehicle to reduce the carbon footprint of the vehicle;
modify at least one of an engine throttle and a braking system of the vehicle to respond less abruptly when activated while the vehicle is travelling based on the determined change to the driving style of the vehicle;
determining a modification to an operation of the vehicle based on a predicted reduction of the carbon footprint; and
predicting when the carbon footprint will equal a second carbon footprint based on the modification.

8 . The system of claim 7 , wherein the processor is configured to:
notify the vehicle of a difference between the carbon footprint and a second carbon footprint which is greater than a threshold.

9 . The system of claim 7 , wherein the processor is configured to:
determine a recommendation for the vehicle, wherein the recommendation comprises a proposed change in an operation of the vehicle; predict a reduction in the carbon footprint based on the recommendation; and provide the recommendation and the predicted reduction to the vehicle.

10 . The system of claim 7 , wherein the processor is configured to:
gather a set of user data that comprises at least one of: a route traveled, a driver behavior, a vehicle utilization level, a vehicle maintenance status, a weather condition, or a road condition; and provide the set of user data to an artificial intelligence model configured to predict the carbon footprint of the vehicle based on the set of user data.

11 . The system of claim 7 , wherein the processor is configured to determine a change to an operating mode of an engine of the vehicle that consumes less carbon footprint.

12 . A computer-readable storage medium comprising instructions that, when executed by a processor, cause the processor to perform:
receiving real-time driving data from a sensor of a vehicle; determining a driving style of the vehicle based on at least one of throttle activations, braking patterns, vehicle speed, steering angles, and operating modes included in the real-time driving data; determining a carbon footprint of the vehicle based on execution of a machine learning model on the real-time driving data, where the machine learning model is trained on historical driving data and environmental parameters and is configured to adapt dynamically based on changing driving conditions; determining a change to the driving style of the vehicle to reduce the carbon footprint of the vehicle; modifying at least one of an engine throttle and a braking system of the vehicle to respond less abruptly when activated while the vehicle is travelling based on the determined change to the driving style of the vehicle; determining a modification to an operation of the vehicle based on a predicted reduction of the carbon footprint; and predicting when the carbon footprint will equal a second carbon footprint based on the modification.

13 . The computer-readable storage medium of claim 12 , wherein the instructions further cause the processor to perform:
notifying the vehicle of a difference between the carbon footprint and a second carbon footprint which is greater than a threshold.

14 . The computer-readable storage medium of claim 12 , wherein the instructions further cause the processor to perform:
determining a recommendation for the vehicle, wherein the recommendation comprises-a proposed change in an operation of the vehicle; predicting a reduction in the carbon footprint based on the recommendation; and providing the recommendation and the predicted reduction to the vehicle.

15 . The computer-readable storage medium of claim 12 , further comprising instructions for:
gathering a set of user data comprising at least one of: a route traveled, a driving behavior, a vehicle utilization level, a vehicle maintenance status, a weather condition, or a road condition; and providing the set of user data to an artificial intelligence model configured for predicting the carbon footprint of the vehicle based on the set of user data.

Assignees

• Toyota Connected North America Inc

Inventors

• Salako Olarinre
• Prasad Varun
• Holman Daniel Ellis
• Ghanbarnezhad Farzam
• Bargas Danny P
• Mishra Rohit
• Lerman Jennifer C

Classifications

• G07C5/02

  Registering or indicating driving, working, idle, or waiting time only (apparatus forming part of taximeters G07B13/00) · CPC title

• G06Q30/018 Primary

  Certifying business or products · CPC title