Geotab Inc.

Disclosed herein are systems and methods for determining vehicle downtime. In one embodiment, such a method comprises operating at least one processor to: receive telematics data originating from a plurality of telematics devices installed in a plurality of vehicles; identify, using the telematics data, an unpowered trip completed by at least one vehicle of the plurality of vehicles; identify each unpowered trip completed by the at least one vehicle that is a tow trip; identify, for each vehicle that completed a tow trip, a first powered trip completed prior to the tow trip and a second powered trip completed after the tow trip; and determine, for each vehicle that completed a tow trip, a vehicle downtime based at least in part on a time difference between an end time of the first powered trip and an start time of the second powered trip.

The present disclosure relates to systems and methods for identifying commercial domiciles. An example of one such method includes operating at least one processor to: receive telematics data originating from a plurality of telematics devices installed in a plurality of vehicles; identify, using the telematics data, a vehicle stop zone, each vehicle stop zone comprising a vehicle stop cluster; and identify the vehicle stop zone as a commercial domicile by applying to the vehicle stop cluster of the vehicle stop zone at least one machine learning model trained to classify vehicle stop zones based on one or more vehicle stop features thereof.

Systems and methods for detecting rolling stops are discussed. A stop sign is first identified in image data at vehicle devices. The image data of the strop sign and movement data for a speed of the vehicle are sent to a management device. The management device can verify presence of the stop sign, and determine whether the vehicle made a complete stop at the stop sign based on the movement data, a threshold speed, and a stop time threshold.

Disclosed herein are systems and methods for determining an expansion factor for estimating vehicle traffic. One example method comprises operating at least one processor to: receive telematics data originating from a plurality of telematics devices installed in a plurality of vehicles, map data and census data related to an area within which the vehicles operate; determine, using the telematics data and the map data, an initial estimated vehicle traffic volume for a road segment along which the vehicles operate based on an amount of the vehicles that operate therealong; generate a total estimated vehicle traffic volume for each of the road segments by inputting into a machine learning model the initial estimated vehicle traffic volume and the census data; and determine the expansion factor for the road segments based at least in part on a ratio of the initial estimated vehicle traffic volume to the total estimated vehicle traffic volume.

The present systems, devices, and methods relate to managing shared vehicle access. Authorization policies are stored at a network device, and are provided to vehicle devices. Authorization policies each include an authentication scheme, a list of permitted vehicle operations, and a list of requirements to perform vehicle operations. In this way, whether even if a user is authenticated to access a vehicle, vehicle access is controlled based one whether the user is permitted to perform vehicle operations, and whether requirements are met to perform vehicle operations. This provides a flexible and robust vehicle access system. Authorization Policies are distributed to vehicle device in an Access Configuration, which can be updated.

Disclosed are systems and methods for assessing driving risk in the field of vehicle telematics. The disclosed technology addresses the challenge of evaluating risk from raw, irregularly sampled telematics time series. The system comprises at least one data storage for telematics data and at least one processor operable to determine velocity vectors, longitudinal acceleration, and lateral acceleration from geospatial data, identify trip subintervals with non-zero speed events, and detect anomalous trip events using a stochastic model, such as a continuous-time hidden Markov model. The processor flags events exceeding a threshold as anomalous. A trip risk score is calculated based on the proportion of anomalous events. Principal uses include insurance premium adjustment, fleet management, and driver coaching. The disclosed technology further encompasses processes and non-transitory computer-readable media for implementing these functionalities.

Disclosed herein are systems and methods for determining a likelihood of a vehicle tow. An example of one such method involves operating at least one processor to: receive telematics data originating from a plurality of telematics devices installed in a plurality of vehicles; identify, using the telematics data, a diagnostic trouble code (DTC) cycle experienced by one or more of the plurality of vehicles, the DTC cycle corresponding to a reporting of a DTC during a plurality of vehicle ignition cycles; determine, for each vehicle that experienced the DTC cycle, whether a tow event occurred; determine, for each vehicle for which the tow event occurred, a vehicle downtime associated with the tow event; determine whether a termination of the DTC cycle is associated with the tow event based at least in part on when the reporting of the DTC terminates relative to the vehicle downtime; and determine the likelihood of a vehicle tow for the DTC based at least in part on a number of vehicles for which the termination of the DTC cycle is associated with the tow event.

Disclosed herein are systems and methods for predicting collision risk associated with a roadway intersection. The methods may comprise operating at least one processor to: receive map data and telematics data originating from telematics devices installed in a plurality of vehicles; identify, using the map data, one or more roadway intersections; determine, using the telematics data and/or map data, for each of the one or more roadway intersections, one or more roadway intersection metrics thereof; determine a hazard rating for each roadway of each roadway intersection; and generate a collision probability for each roadway intersection by inputting into a machine learning model the one or more roadway intersection metrics and the hazard rating of each roadway thereof, the collision probability representing a risk of collision for a vehicle traversing the intersection.

Systems, methods, devices, and models determining fuel level in vehicles are described. Raw fuel sensor data tends to be noisy and of low quality. Herein, operational data is collected, which is used to determine times when motion of the vehicle is stable. Raw fuel sensor data for these times is collected in a data subset, which is used to determine fuel level. Quality fuel sensor data is thus obtained. Fuel data can be combined over different time periods to provide a prompt initial fuel level, and an intermittent fuel level during a trip.

A single-path dual-band GNSS front-end system for asset tracking and telematics devices is provided. The system configures a GNSS antenna, a SAW filter, a low-noise amplifier (LNA), and a SAW diplexer to process both L1 and L5 signals, thereby reducing the number of required components, lowering power consumption, and minimizing PCB space while enhancing signal reliability in urban environments. The GNSS front-end system is part of a GNSS subsystem used in asset trackers and telematics devices. A method for processing dual-band GNSS signals in a single-path front-end system is also claimed, including receiving, filtering, amplifying, and separating L1 and L5 signals.