Geotab Incorporated

Robert Spencer Hockin

Willem Petersen

Xiaohui Yu

Meghan Frances Fotak

Paul Philip Ciolek

Robert Bradley

Paul Stobbe

Harjot Singh Parmar

Amish Vijay Patel

James David Johnston

Weinan Sun

Matthew Konski

Daniel Alec Sheen

Michael Angelo David Santorelli

Yongkyun Shin

Farzan Farhangian

Michael Pirruccio

Jialin Zhu

Jonathan Bean

Patrick Wojcik

Andrew James Murfin

Joseph James Deppong

Stephan Edelman

Jailin Zhu

James Johnston

Michael Santorelli

Described herein are examples of a computerized method that comprises: in response to obtaining information regarding a potential collision between a vehicle and an object, obtaining data describing the vehicle for a time period extending before and after a time of the potential collision. The method may determine a likelihood that the potential collision is a non-collision event based on the data describing the vehicle by performing one or more assessments. The assessments may include telematics monitor assessment, driver behavior assessment, road surface feature assessment, trip correlation assessment, and/or context assessment. In response to determining that the likelihood indicates that the potential collision is not a non-collision event, the method may trigger one or more actions responding to the potential collision.

Methods for characterizing a vehicle collision

Methods for reversing determination for a vehicle asset are provided. The methods include capturing by a telematics device coupled to the vehicle acceleration data from a three-axis accelerometer, determining by an edge reversing-determination machine learning mode, a machine-learning-determined reversing indication for the vehicle asset. The edge reversing-determination machine-learning model being updated based on a centralized reversing-determination machine-learning model trained using a vehicle-provided reversing indication.

Systems and methods for vehicle reversing detection using edge machine learning

A method and a system for impact detection in a stationary vehicle are provided. The method includes putting a telematics device into a sleep mode and performing a first micro wakeup. In response to determining that a first value read from a sensor during the micro wakeup is greater than a noise threshold, increasing a frequency of the micro wakeups and a sampling rate of the sensor. The method also includes reading a second value from the sensor during a second wakeup, performing a regular wakeup, and sending the first and second values during the regular wakeup.

Device for low-power acceleration detection in a telematics device

Devices and methods for detecting an end of trip by an asset tracker are described. An end of trip may be detected using a Global Navigation Satellite System (GNSS) module or an Inertial Measurement Unit (IMU), such as a three-axis accelerometer. In some implementations, the asset tracker uses the IMU for end of trip detection. In other implementations, the asset tracker uses the IMU for impact detection while using the GNSS module for end of trip detection.

Devices and methods for trip detection in an asset tracker

A method of activating an asset tracker from an ultra-low power shipping mode to a motion detection mode. The method includes detecting an activation trigger activity including double-tapping on the housing of the asset tracker, mid-air gestures comprising orientation changes, touch sensing, optical sensing, and loss of proximity with a proximity object in the packaging of the asset container.

Devices and methods for activating an asset tracker

Methods, systems, and devices for data capture instructions for asset tracking are provided. An example method for capturing data involves obtaining raw data from a data source onboard an asset and monitoring the raw data for satisfaction of a simplified data capture trigger. When the simplified data capture trigger is satisfied, a dataset simplification algorithm is performed on the raw data to generate a simplified set of raw data, and the simplified set of raw data is logged. The method further involves monitoring the raw data for satisfaction of a rich data capture trigger. When the rich data capture trigger is satisfied, an unsimplified block of raw data is identified and logged for rich data analysis. The data is transmitted to a server. The unsimplified block of raw data contains raw data that is additional to the raw data contained in the simplified set of raw data.

Data capture instructions for asset tracking

A method and a device for low-power acceleration detection in a stationary vehicle are provided. The method includes putting a telematics device into a sleep mode, performing a plurality of micro wakeups during which a plurality of accelerometer readings are captured. The method further includes sending the plurality of accelerometer readings over a network interface to a telematics server. The telematics device which carries out the method has a controller, memory, and network interface. An accident impact profile may be recorded during the micro wakeups and sent during a regular wakeup duration for analysis by the telematics server.

Low-power acceleration detection in a telematics device

Described herein are various techniques, including systems and non-transitory instructions, that, in response to obtaining information regarding a potential collision between a vehicle and an object, obtain data describing the vehicle for a time period extending before and after a time of the potential collision. The system may determine a likelihood that the potential collision is a non-collision event based on the data describing the vehicle by performing one or more assessments. The assessments may include telematics monitor assessment, driver behavior assessment, road surface feature assessment, trip correlation assessment, and/or context assessment. In response to determining that the likelihood indicates that the potential collision is not a non-collision event, the system may trigger one or more actions responding to the potential collision.

Systems for characterizing a vehicle collision

Method and system for impact detection in a stationary vehicle

Methods for reversing determination for a vehicle asset are provided. The methods include capturing by a telematics device coupled to the vehicle acceleration data from a three-axis accelerometer, determining by a reversing-determination machine learning mode, a machine-learning-determined reversing indication for the vehicle asset. The reversing-determination machine-learning model being trained by a vehicle reversing indication comprising a vehicle speed and a reverse gear indication.

Systems and methods for vehicle reversing detection using machine learning

Methods, systems, and devices for data capture trigger configuration for asset tracking are provided. Another example method capturing raw data involves obtaining a rich data capture trigger that defines when a controller of an asset tracking device onboard an asset is to identify and log an unsimplified block of raw data in raw data on the asset tracking device for rich data analysis, transmitting data capture instructions to the asset tracking device that contains the rich data capture trigger, and receiving the simplified set of raw data and the unsimplified block of raw data from the asset tracking device.

Data capture trigger configuration for asset tracking

A method and a system for impact detection in a stationary vehicle are provided. The method includes putting a telematics device into a sleep mode, performing at least one micro wakeup, determining at least one value from at least one sensor during the micro wakeup. The method also includes storing the at least one value, returning to sleep mode, and waking up from the sleep mode. The method further includes sending the at least one value over a network interface to a telematics server. The telematics device which carries out the method has a controller, memory, and network interface. An accident impact profile may be recorded during the micro wakeups and sent during a wakeup duration for analysis by the telematics server.

Devices and systems for determining an alternator condition in a motor vehicle are provided. The method includes performing a plurality of micro wakeups to capture voltage values during a cranking event, determining the maximum cranking voltage and its timestamp, detecting an ignition signal, determining the maximum device voltage and its timestamp, and determining a potential alternator undercharging condition if a duration between the maximum cranking voltage timestamp and the maximum device voltage timestamp is greater than an undercharging indicator duration threshold. Advantageously, an alternator may be repaired or replaced before it fails thus averting having the motor vehicles inoperable.

Growing community of inventors

Milton, Canada

Robert Spencer Hockin