US-12623682-B2 - Method and system for driver alerts based on sensor data and contextual information

US12623682B2US 12623682 B2US12623682 B2US 12623682B2US-12623682-B2

Abstract

A method including receiving, from sensor(s) of a mobile device in a driven vehicle, current speed of the vehicle, current travel direction of the vehicle, and current location of the vehicle with respect to a road network. The method including receiving contextual data indicating a plurality of triggering conditions located along road segment(s) present in the road network. The method including identifying a road segment of interest based on the current location and current travel direction of the vehicle. The method including identifying a triggering condition in a vicinity of the road segment of interest. The method including generating an alert related to the triggering condition, wherein generating the alert includes: determining an alert modality for the alert and a set of alert characteristics for the alert modality. The method including outputting the alert with the alert modality and set of alert characteristics to the user using the mobile device.

Inventors

Arash Hadapanah
Hari Balakrishnan
Rafi Finegold
Samuel Madden
Robert S. Kobetis
Brian Sachetta
Sanujit Sahoo
Gábor Tyukász

Assignees

Cambridge Mobile Telematics Inc.

Dates

Publication Date: 20260512
Application Date: 20240410

Claims (20)

1 . A method comprising: receiving, from one or more sensors of a mobile device present in a vehicle during a drive, a current speed of the vehicle, a current travel direction of the vehicle, and a current location of the vehicle with respect to a road network; receiving contextual data, wherein the contextual data indicates a plurality of triggering conditions located along one or more road segments present in the road network; identifying, from the one or more road segments, a road segment of interest based on the current location of the vehicle and the current travel direction of the vehicle; identifying, from the plurality of triggering conditions, a triggering condition in a vicinity of the road segment of interest; generating an alert for a user related to the triggering condition, wherein generating the alert for the user related to the triggering condition includes: determining an alert modality for the alert; and determining a set of alert characteristics for the alert modality; receiving, from the one or more sensors of the mobile device before outputting the alert, first information representing driving behavior of the user; outputting the alert with the alert modality and the set of alert characteristics to the user using the mobile device; receiving, from the one or more sensors of the mobile device after outputting the alert, second information representing driving behavior of the user; generating, after outputting the alert, a second alert for the user related to a second triggering condition, wherein generating the alert for the user related to the second triggering condition includes at least one of: determining a second alert modality for the alert based on the first information representing driving behavior of the user and the second information representing driving behavior of the user; or determining a second set of alert characteristics for the second alert modality based on the first information representing driving behavior of the user and the second information representing driving behavior of the user; and outputting the second alert with at least one of the second alert modality or the second set of alert characteristics to the user using the mobile device.
2 . The method of claim 1 , wherein determining the alert modality comprises: displaying a set of alert modalities to the user of the mobile device; receiving a selection of one of the set of alert modalities; and storing the alert modality in a memory.
3 . The method of claim 1 , wherein determining the set of alert characteristics comprises: displaying a plurality of alert characteristics to the user; receiving a selection of one or more of the plurality of alert characteristics; and storing the one or more of the plurality of alert characteristics as the set of alert characteristics in a memory.
4 . The method of claim 1 , wherein the alert modality corresponds to at least one of an acoustic, visual, vibration, or haptic alert.
5 . The method of claim 1 wherein the set of alert characteristics includes at least one of alert volume, tone of voice, strength of haptic motion, alert duration, or alert delivery time.
6 . The method of claim 1 , wherein the alert comprises positive feedback.
7 . The method of claim 1 , further comprising: wherein generating the alert for the user related to the second triggering condition includes: determining the second alert modality for the alert; and determining a third set of alert characteristics for the second alert modality; and outputting the second alert with the second alert modality and the third set of alert characteristics to the user using the mobile device.
8 . The method of claim 1 , further comprising: wherein generating the alert for the user related to the second triggering condition includes: determining a third alert modality for the alert; and determining the second set of alert characteristics; and outputting the second alert with the third alert modality and the second set of alert characteristics to the user using the mobile device.
9 . The method of claim 1 , wherein at least one of (i) the alert modality or (ii) the set of alert characteristics are determined based on risk evaluation of the user.
10 . The method of claim 1 , wherein at least one of (i) the alert modality or (ii) the set of alert characteristics are determined based on the triggering condition.
11 . The method of claim 1 , wherein the contextual data includes information related to at least one of road type, map data, weather conditions, real-time or historical traffic conditions, time-of-day, or accident statistics.
12 . The method of claim 1 , wherein the method is performed by an application running on the mobile device, wherein the application is not foregrounded by the user or has not been launched by the user.
13 . A system comprising: a vehicle; a mobile device present in the vehicle and including one or more sensors, the mobile device including: one or more memories configured to store computer-executable instructions; and one or more processors configured to access the one or more memories and execute the computer-executable instructions to at least: receive, from the one or more sensors of the mobile device present in the vehicle during a drive, a current speed of the vehicle, a current travel direction of the vehicle, and a current location of the vehicle with respect to a road network; receive contextual data, wherein the contextual data indicates a plurality of triggering conditions located along one or more road segments present in the road network; identify, from the one or more road segments, a road segment of interest based on the current location of the vehicle and the current travel direction of the vehicle; identify, from the plurality of triggering conditions, a first triggering condition in a vicinity of the road segment of interest; generate an alert for a user related to the first triggering condition, wherein generating the alert for the user related to the first triggering condition includes: determine an alert modality for the alert; and determine a set of alert characteristics for the alert modality; receive, from the one or more sensors of the mobile device before outputting the alert, first information representing driving behavior of the user; output the alert with the alert modality and the set of alert characteristics to the user using the mobile device; receive, from the one or more sensors of the mobile device after outputting the alert, second information representing driving behavior of the user; generate, after outputting the alert, a second alert for the user related to a second triggering condition, wherein generating the alert for the user related to the second triggering condition includes at least one of: determine a second alert modality for the alert based on the first information representing driving behavior of the user and the second information representing driving behavior of the user; or determine a second set of alert characteristics for the second alert modality based on the first information representing driving behavior of the user and the second information representing driving behavior of the user; and output the second alert with at least one of the second alert modality or the second set of alert characteristics to the user using the mobile device.
14 . The system of claim 13 , wherein determining the alert modality comprises: displaying a set of alert modalities to the user of the mobile device; receiving a selection of one of the set of alert modalities; and storing the alert modality in a memory.
15 . The system of claim 13 , wherein at least one of (i) the alert modality or (ii) the set of alert characteristics are determined based on risk evaluation of the user.
16 . The system of claim 13 , wherein at least one of (i) the alert modality or (ii) the set of alert characteristics are determined based on the first triggering condition.
17 . One or more non-transitory computer-readable storage media storing instructions that, upon execution by one or more processors of a system, cause the system to perform operations comprising: receiving, from one or more sensors of a mobile device present in a vehicle during a drive, a current speed of the vehicle, a current travel direction of the vehicle, and a current location of the vehicle with respect to a road network; receiving contextual data, wherein the contextual data indicates a plurality of triggering conditions located along one or more road segments present in the road network; identifying, from the one or more road segments, a road segment of interest based on the current location of the vehicle and the current travel direction of the vehicle; identifying, from the plurality of triggering conditions, a first triggering condition in a vicinity of the road segment of interest; generating an alert for a user related to the first triggering condition, wherein generating the alert for the user related to the first triggering condition includes: determining an alert modality for the alert; and determining a set of alert characteristics for the alert modality; receiving, from the one or more sensors of the mobile device before outputting the alert, first information representing driving behavior of the user; outputting the alert with the alert modality and the set of alert characteristics to the user using the mobile device; receiving, from the one or more sensors of the mobile device after outputting the alert, second information representing driving behavior of the user; generating, after outputting the alert, a second alert for the user related to a second triggering condition, wherein generating the alert for the user related to the second triggering condition includes at least one of: determining a second alert modality for the alert based on the first information representing driving behavior of the user and the second information representing driving behavior of the user; or determining a second set of alert characteristics for the second alert modality based on the first information representing driving behavior of the user and the second information representing driving behavior of the user; and outputting the second alert with at least one of the second alert modality or the second set of alert characteristics to the user using the mobile device.
18 . The one or more non-transitory computer-readable storage media of claim 17 , wherein determining the set of alert characteristics comprises: displaying a plurality of alert characteristics to the user; receiving a selection of one or more of the plurality of alert characteristics; and storing the one or more of the plurality of alert characteristics as the set of alert characteristics in a memory.
19 . The one or more non-transitory computer-readable storage media of claim 17 , wherein at least one of (i) the alert modality or (ii) the set of alert characteristics are determined based on risk evaluation of the user.
20 . The one or more non-transitory computer-readable storage media of claim 17 , wherein at least one of (i) the alert modality or (ii) the set of alert characteristics are determined based on the first triggering condition.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS This application is a continuation of U.S. patent application Ser. No. 17/862,943, filed Jul. 12, 2022, entitled “Method And System For Driver Alerts Based On Sensor Data And Contextual Information,” the disclosure of which is hereby incorporated by reference in its entirety for all purposes. BACKGROUND OF THE INVENTION Mobile devices, including smartphones, have been utilized in vehicles to measure driving performance of drivers by collecting and processing data from the device's location sensor, accelerometer, gyroscope, and more. Typical factors measured include hard braking, rapid acceleration, hard cornering or turning, speeding, and phone distraction. Despite the progress made in relation to collecting data related to drivers and their driving behavior, there is a need in the art for improved systems and methods related to detecting and alerting drivers of certain driving behaviors in real-time while driving. SUMMARY OF THE INVENTION Embodiments of the present invention generally relate to methods and systems for providing real-time alerts for drivers. In particular embodiments, reactive, real-time alerts that inform drivers of events that have happened, for example, within a short time after the event, as well as proactive, real-time alerts that inform drivers of an event that could happen in the near future unless the driver takes corrective action, are provided. Accordingly, embodiments of the present invention provide methods to alert drivers of risky driving behaviors in real-time, while they are driving, to provide timely feedback that could improve their driving habits and reduce their risk of causing crashes. The use of the methods and systems described herein can reduce the number of vehicle accidents and increase driving safety. Globally, driving results in 1.35 million deaths and 50 million injuries every year, with loss costs estimated at 1.8 trillion dollars. The vast majority of these incidents are caused by driver error due to a variety of factors including inattentiveness, distraction, poor anticipation, excessive speeding, recklessness, drunk driving, fatigue, a lack of awareness of the environment, and other unforeseen surprises. Many vehicles today come equipped with warning systems that warn drivers moments before a potential crash so they can take evasive action, or in some cases take evasive actions automatically (e.g., automated braking). Although helpful, these systems are not a panacea and crash rates have continued to rise in many countries. For example, in the US, road fatalities increased by 7.2% in 2020 over 2019 despite the COVID-19 pandemic significantly reducing the amount of overall driving, and the first 9 months of 2021 saw a 12% increase in fatalities over the same time period in 2020. Pedestrian and bicyclist injuries and fatalities have also been on the rise in the US since 2009. A variety of incentive programs using insurance discounts and rewards for safe driving have been proposed and deployed to improve driving quality and reduce crash rates. These programs offer incentives and feedback on a daily, weekly, or longer time-frame, relying on drivers to react by improving their driving behavior to earn benefits. A complementary approach to these two prior approaches—immediate warning of an impending crash on the one hand and non-real-time incentivization on the other—is to provide real-time feedback during a drive when instances of poor (or good) driving behaviors are observed. Accordingly, embodiments of the present invention utilize this complementary approach to provide feedback via mobile devices such as smartphones and in-vehicle Internet of Things (IoT) devices to improve driving behavior. An example of an IoT device is the DriveWell Tag provided by the current assignee. As described more fully herein, embodiments of the present invention collect sensor data from mobile devices (e.g., smartphones and IoT devices), process the sensor data in real-time during a drive, possibly augmenting this data with contextual data about the environment in which the vehicle is operating (e.g., the type of road, traffic conditions, weather, and the like) to determine if the driver or vehicle is operating in a way that indicates a higher driving risk. If so, the system can alert the driver in real-time using acoustic, visual, vibration, or other modes of alerts to notify the driver that their actions may increase their risk of experiencing a crash. By alerting drivers of risky actions in real time, drivers will be more likely to make corrections to their behavior and reduce the risk of a crash by becoming aware of problematic behaviors and changing their habits. Real-time alerts can lower crash rates, benefiting drivers, others on the road, insurers, and society. In addition to improvements in driver safety, improvements in fuel economy can be achieved using embodiments of the present invention. Embodiments of the present invention prov