Driving abnormality detection

• US 9,925,987 B1
• Filed: 12/11/2015
• Issued: 03/27/2018
• Est. Priority Date: 12/11/2015
• Status: Active Grant

• Current Assignee: Lytx, Inc.
• Original Assignee: Lytx, Inc.
• Inventors: Nguyen, Vincent
• Primary Examiner(s): Haile, Benyam
• Application Number:
  US14/966,325
• Time in Patent Office: 837 Days
• Field of Search: 180271, 340 31, 340439, 340576, 701 1, 701 334
• CPC Class Codes: B60Q 9/00 Arrangement or adaptation of signal devices not provided for in one of main groups B60Q1/00 - B60Q7/00 , e.g. haptic signalling
• CPC Class Codes: B60W 2050/146 Display means
• CPC Class Codes: B60W 2510/0638 Engine speed
• CPC Class Codes: B60W 2520/10 Longitudinal speed
• CPC Class Codes: B60W 2540/10 Accelerator pedal position
• CPC Class Codes: B60W 2540/12 Brake pedal position
• CPC Class Codes: B60W 2540/18 Steering angle
• CPC Class Codes: B60W 2540/21 Voice
• CPC Class Codes: B60W 2540/30 Driving style
• CPC Class Codes: B60W 2554/80 Spatial relation or speed relative to objects
• CPC Class Codes: B60W 2556/45 External transmission of data to or from the vehicle
• CPC Class Codes: B60W 2556/50 of positioning data, e.g. GPS [Global Positioning System] data
• CPC Class Codes: B60W 40/00 Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
• CPC Class Codes: B60W 40/02 related to ambient conditions
• CPC Class Codes: B60W 40/04 Traffic conditions
• CPC Class Codes: B60W 40/06 Road conditions
• CPC Class Codes: B60W 40/08 related to drivers or passengers
• CPC Class Codes: B60W 40/09 Driving style or behaviour
• CPC Class Codes: B60W 50/082 Selecting or switching between different modes of propelling
• CPC Class Codes: B60W 50/085 Changing the parameters of the control units, e.g. changing limit values, working points by control input
• CPC Class Codes: B60W 50/14 : Means for informing the driver, warning the driver or prompting a driver intervention
• CPC Class Codes: G06Q 40/08 : Insurance
• CPC Class Codes: G06V 20/597 : Recognising the driver's state or behaviour, e.g. attention or drowsiness
• CPC Class Codes: G07C 5/008 : communicating information to a remotely located station transmission systems for measured values G08C
• CPC Class Codes: G07C 5/02 : Registering or indicating driving, working, idle, or waiting time only apparatus forming part of taximeters G07B13/00
• CPC Class Codes: G07C 5/0816 : Indicating performance data, e.g. occurrence of a malfunction
• CPC Class Codes: G07C 5/085 : using electronic data carriers
• CPC Class Codes: G08G 1/0112 : from the vehicle, e.g. floating car data [FCD]
• CPC Class Codes: G08G 1/0129 : for creating historical data or processing based on historical data
• CPC Class Codes: G08G 1/163 : involving continuous checking

Abstract

A system for detecting abnormal driver behavior includes an input interface and a processor. The input interface is for receiving a sensor data of a vehicle. The processor is for determining a driving behavior based at least in part on the sensor data of the vehicle; determining whether the driving behavior is abnormal; and, in the event that the driving behavior is abnormal, indicating an abnormal driver behavior.

Claims

1. A system for detecting abnormal driver behavior, comprising:

an input interface for receiving a sensor data of a vehicle; and

a processor for;

determining a driving behavior based at least in part on the sensor data of the vehicle, wherein the sensor data of the vehicle includes at least three or more of the following;

location data, global positioning system (GPS) data, accelerometer data, braking data, turning data, fuel data, or engine revolutions per minute (RPM) data, or proximity data, wherein the determining of the driving behavior comprises;

determining a set of maneuvers, comprising;

determining six or more of the following;

a braking profile, a turning profile, a following profile, a driving speed profile, an acceleration profile, a turn signal profile, a voice profile, a location specific profile, a smile profile, or a frown behavior, wherein the braking profile comprises a brake application rate, a deceleration curve, a brake position, or any combination thereof, wherein the turning profile comprises a steering wheel turning rate, a preferred turning radius, a turning path, or any combination thereof, wherein the following profile comprises an approach rate, a following distance, a minimum following distance, a backoff rate, or any combination thereof, wherein the driving speed profile comprises a city street driving speed, a highway driving speed, a driving speed to speed limit ratio, or any combination thereof, wherein the acceleration profile comprises an acceleration rate coming up to highway speed, an acceleration rate from a stop, an acceleration rate when passing another vehicle, or any combination thereof, wherein the turn signal profile comprises a distance a turn signal is lit before turning on a city street, a time a turn signal is lit before changing lanes on a highway, whether a turn signal is used to signal a highway exit, or any combination thereof, wherein the voice profile comprises a fraction of the time the driver voice is heard, a driver voice volume, a driver voice tone, whether or not certain words are heard from the driver, whether or not profanity is heard from the driver, or any combination thereof, and wherein the location specific profile comprises a driving maneuver that is specific to a particular location;

determining whether the driving behavior is abnormal, comprising;

comparing a previous set of maneuvers with a normal set of maneuvers to obtain a cumulative maneuver abnormality, the normal set of maneuvers relating to previous sensor data for a user, the comparing of the previous set of maneuvers with the normal set of maneuvers comprises;

calculating a first difference between a first previous profile and a first normal profile;

calculating a second difference between a second previous profile and a second normal profile, the previous set of maneuvers including the first previous profile and the second previous profile, the normal set of maneuvers including the first normal profile and the second normal profile, the normal set of maneuvers includes previous sensor data for a user; and

aggregating the first difference and the second difference to obtain the cumulative maneuver abnormality;

comparing the cumulative maneuver abnormality with a threshold to determine whether the driving behavior is abnormal; and

in response to a determination that the driving behavior is abnormal;

indicating an abnormal driver behavior; and

providing coaching for the user associated with the vehicle.

2. The system of claim 1, wherein the processor is further for determining a normal driving behavior based at least in part on the sensor data of the vehicle.

3. The system of claim 2, wherein determining a normal driving behavior comprises clustering data.

4. The system of claim 2, wherein determining a normal driving behavior comprises determining normal maneuvers.

5. The system of claim 4, wherein determining normal maneuvers comprises determining one or more location specific patterns.

6. The system of claim 4, wherein determining normal maneuvers comprises determining the braking profile.

7. The system of claim 6, wherein determining the braking profile comprises determining a hard braking profile.

8. The system of claim 1, wherein a cumulative abnormality comprises a cumulative abnormality over a period of time.

9. The system of claim 1, wherein the determining of the set of maneuvers includes:

determining nine or more of the following;

the braking profile, the turning profile, the following profile, the driving speed profile, the acceleration profile, the turn signal profile, the voice profile, the location specific profile, the smile profile, or the frown behavior.

10. A method for detecting abnormal driver behavior, comprising:

receiving a sensor data of a vehicle, wherein the sensor data of the vehicle includes at least three or more of the following;

location data, global positioning system (GPS) data, accelerometer data, braking data, turning data, fuel data, or engine revolutions per minute (RPM) data, or proximity data, wherein the determining of the driving behavior comprises;

determining a set of maneuvers, comprising;

determining six or more of the following;

a braking profile, a turning profile, a following profile, a driving speed profile, an acceleration profile, a turn signal profile, a voice profile, a location specific profile, a smile profile, or a frown behavior, wherein the braking profile comprises a brake application rate, a deceleration curve, a brake position, or any combination thereof, wherein the turning profile comprises a steering wheel turning rate, a preferred turning radius, a turning path, or any combination thereof, wherein the following profile comprises an approach rate, a following distance, a minimum following distance, a backoff rate, or any combination thereof, wherein the driving speed profile comprises a city street driving speed, a highway driving speed, a driving speed to speed limit ratio, or any combination thereof, wherein the acceleration profile comprises an acceleration rate coming up to highway speed, an acceleration rate from a stop, an acceleration rate when passing another vehicle, or any combination thereof, wherein the turn signal profile comprises a distance a turn signal is lit before turning on a city street, a time a turn signal is lit before changing lanes on a highway, whether a turn signal is used to signal a highway exit, or any combination thereof, wherein the voice profile comprises a fraction of the time the driver voice is heard, a driver voice volume, a driver voice tone, whether or not certain words are heard from the driver, whether or not profanity is heard from the driver, or any combination thereof, and wherein the location specific profile comprises a driving maneuver that is specific to a particular location;

determining, using a processor, a driving behavior based at least in part on the sensor data of the vehicle;

determining whether the driving behavior is abnormal, comprising;

comparing a previous set of maneuvers with a normal set of maneuvers to obtain a cumulative maneuver abnormality, the normal set of maneuvers relating to previous sensor data for a user, the comparing of the previous set of maneuvers with the normal set of maneuvers comprises;

calculating a first difference between a first previous profile and a first normal profile;

calculating a second difference between a second previous profile and a second normal profile, the previous set of maneuvers including the first previous profile and the second previous profile, the normal set of maneuvers including the first normal profile and the second normal profile, the normal set of maneuvers includes previous sensor data for a user; and

aggregating the first difference and the second difference to obtain the cumulative maneuver abnormality;

comparing the cumulative maneuver abnormality with a threshold to determine whether the driving behavior is abnormal; and

in response to a determination that the driving behavior is abnormal;

indicating an abnormal driver behavior; and

providing coaching for the user associated with the vehicle.

11. A computer program product for detecting abnormal driver behavior, the computer program product being embodied in a non-transitory computer readable storage medium and comprising computer instructions for:

receiving a sensor data of a vehicle, wherein the sensor data of the vehicle includes at least three or more of the following;

location data, global positioning system (GPS) data, accelerometer data, braking data, turning data, fuel data, or engine revolutions per minute (RPM) data, or proximity data, wherein the determining of the driving behavior comprises;

determining a set of maneuvers, comprising;

determining six or more of the following;

a braking profile, a turning profile, a following profile, a driving speed profile, an acceleration profile, a turn signal profile, a voice profile, a location specific profile, a smile profile, or a frown behavior, wherein the braking profile comprises a brake application rate, a deceleration curve, a brake position, or any combination thereof, wherein the turning profile comprises a steering wheel turning rate, a preferred turning radius, a turning path, or any combination thereof, wherein the following profile comprises an approach rate, a following distance, a minimum following distance, a backoff rate, or any combination thereof, wherein the driving speed profile comprises a city street driving speed, a highway driving speed, a driving speed to speed limit ratio, or any combination thereof, wherein the acceleration profile comprises an acceleration rate coming up to highway speed, an acceleration rate from a stop, an acceleration rate when passing another vehicle, or any combination thereof, wherein the turn signal profile comprises a distance a turn signal is lit before turning on a city street, a time a turn signal is lit before changing lanes on a highway, whether a turn signal is used to signal a highway exit, or any combination thereof, wherein the voice profile comprises a fraction of the time the driver voice is heard, a driver voice volume, a driver voice tone, whether or not certain words are heard from the driver, whether or not profanity is heard from the driver, or any combination thereof, and wherein the location specific profile comprises a driving maneuver that is specific to a particular location;

determining, using a processor, a driving behavior based at least in part on the sensor data of the vehicle;

determining whether the driving behavior is abnormal, comprising;

comparing a previous set of maneuvers with a normal set of maneuvers to obtain a cumulative maneuver abnormality, the normal set of maneuvers relating to previous sensor data for a user, the comparing of the previous set of maneuvers with the normal set of maneuvers comprises;

calculating a first difference between a first previous profile and a first normal profile;

calculating a second difference between a second previous profile and a second normal profile, the previous set of maneuvers including the first previous profile and the second previous profile, the normal set of maneuvers including the first normal profile and the second normal profile, the normal set of maneuvers includes previous sensor data for a user; and

aggregating the first difference and the second difference to obtain the cumulative maneuver abnormality;

comparing the cumulative maneuver abnormality with a threshold to determine whether the driving behavior is abnormal; and

in response to a determination that the driving behavior is abnormal;

indicating an abnormal driver behavior; and

providing coaching for the user associated with the vehicle.