US 2022/0032924 A1Published application

System and method for driver distraction detection and classification

AssigneeMorgan State University

InventorsMansoureh Jeihani, Samira Ahangari, Abdollah Dehzangi, Arsalan Hassan Pour

Life of this patent

Estimating the term…

Loading patent…

Abstract

Systems and methods are disclosed for detecting both the occurrence and type of driver distraction experienced by a driver, determined through evaluation of sensed vehicle conditions or activities, such as steering, braking, lane changing, etc. as detected by one or more sensors on or associated with the vehicle. That detection of the occurrence and type of driver distraction may then be used to initiate another action, including initiating an audible or visual alert to the driver, taking measures to interfere with or stop operation of the device that is causing the distraction, log the occurrence and type of distraction that occurred, and report the occurrence and type of distraction to an outside monitoring computer (such as one associated with a guardian of the driver, an insurer of the vehicle, a law enforcement authority, or the like). To allow such detection, the system and method set forth herein employ machine learning methods to first train a classifier to classify certain driver behaviors (as evidenced by sensed vehicle movements and conditions) as a distraction or non-distraction event, and if a distraction event is detected then to further classify a type of such distraction event, and then to apply the trained classifier to classify the driver's ongoing driving activity.

Claims20

Dependent claims

A system for detecting and classifying a type of driver distraction, comprising:

a driving simulator data capture device configured to acquire simulated driving behavior data profiles associated with a plurality of driving simulations in which a driving simulation operator engages a known driving distraction at a known time or simulated location during the driving simulation;
a distraction classification training device receiving said simulated driving behavior data from the driving simulator data capture device;
a distraction occurrence and type determination device;
and
a computer readable memory in data communication with said distraction classification training device and said distraction occurrence and type determination device;
wherein said distraction classification training device includes a training processor executing computer instructions configured to:
determine at said training processor a classification of each said simulated driving behavior data profiles as one of a driving distraction event or driving non-distraction event;
upon classification of a first simulated driving behavior data profile as a driving distraction event, classify a type of distraction event for said first simulated driving behavior data profile;
and
store said classifications of each said simulated driving behavior data profiles and one or more classifications of types of distraction events in said computer readable memory;
and
wherein said distraction classification training device includes an application processor executing computer instructions configured to:
receive at said distraction classification training device from a remote vehicle sensor system a live driving behavior data profile associated with said remote vehicle sensor system;
compare said live driving behavior data profile to said classifications in said computer readable memory;
determine at said application processor a classification of said live driving behavior data profile as one of a live driving distraction event or a live driving non-distraction event;
and
upon classification of said live driving behavior data profile as a live driving distraction event, classifying a type of distraction event for said live driving behavior data profile.

14 more elements

A method for detecting and classifying a type of driver distraction, comprising:

acquiring simulated driving behavior data profiles from a driving simulator data capture device, wherein each said driving behavior data profile is associated with a driving simulation in which a driving simulation operator engages a known driving distraction at a known time or simulated location during the driving simulation;
receiving at a distraction classification training device said simulated driving behavior data from the driving simulator data capture device;
determining at said distraction classification training device a classification of each said simulated driving behavior data profile as one of a driving distraction event or driving non-distraction event;
upon classification of a first simulated driving behavior data profile as a driving distraction event, classifying at said distraction classification training device a type of distraction event for said first simulated driving behavior data profile;
storing said classifications of each said simulated driving behavior data profiles and one or more classifications of types of distraction events in a computer readable memory in data communication with said distraction classification training device;
receiving at a distraction occurrence and type determination device from a remote vehicle sensor system a live driving behavior data profile associated with said remote vehicle sensor system, wherein said distraction occurrence and type determination device is in data communication with said computer readable memory;
comparing at said distraction occurrence and type determination device said live driving behavior data profile to said classifications in said computer readable memory;
determining at said distraction occurrence and type determination device a classification of said live driving behavior data profile as one of a live driving distraction event or a live driving non-distraction event;
and
upon classification of said live driving behavior data profile as a live driving distraction event, classifying at said distraction occurrence and type determination device a type of distraction event for said live driving behavior data profile.

7 more elements

A non-transitory computer-usable medium for detecting and classifying a type of driver distraction, said computer-usable medium embodying a computer program code, said computer program code comprising computer executable instructions configured for:

acquiring simulated driving behavior data profiles from a driving simulator data capture device, wherein each said driving behavior data profile is associated with a driving simulation in which a driving simulation operator engages a known driving distraction at a known time or simulated location during the driving simulation;
receiving at a distraction classification training device said simulated driving behavior data from the driving simulator data capture device;
determining at said distraction classification training device a classification of each said simulated driving behavior data profile as one of a driving distraction event or driving non-distraction event;
upon classification of a first simulated driving behavior data profile as a driving distraction event, classifying at said distraction classification training device a type of distraction event for said first simulated driving behavior data profile;
storing said classifications of each said simulated driving behavior data profiles and one or more classifications of types of distraction events in a computer readable memory in data communication with said distraction classification training device;
receiving at a distraction occurrence and type determination device from a remote vehicle sensor system a live driving behavior data profile associated with said remote vehicle sensor system, wherein said distraction occurrence and type determination device is in data communication with said computer readable memory;
comparing at said distraction occurrence and type determination device said live driving behavior data profile to said classifications in said computer readable memory;
determining at said distraction occurrence and type determination device a classification of said live driving behavior data profile as one of a live driving distraction event or a live driving non-distraction event;
and
upon classification of said live driving behavior data profile as a live driving distraction event, classifying at said distraction occurrence and type determination device a type of distraction event for said live driving behavior data profile.

7 more elements

Dependencies are inferred from the claim text.

Facts

Application: 17/389,741Filed 30 Jul 2021
Priority: 30 Jul 2020
Published: 3 Feb 2022
Term ends: Not estimatedThe source records don’t support an estimate.

Classification19 codes

B60W 40/09
Related to drivers or passengers: driving style or behaviour
B60W 40/02
Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a…:…
B60W 50/14
Interaction between the driver and the control system: means for informing the driver, warning the driver or prompting a driver intervention
G06F 18/24
Analysing: classification techniques

Family

Application63/058,592Us provisional application · filed 30 Jul 2020
US 12,145,597 B2Related patent
US 2022/0032924 A1This patent

From the US filing history. Foreign family members aren’t listed.

Timeline

Citations

Open elsewhere

Building an agent or pulling many patents? Use the API or MCP server instead of scraping pages. Get an API key