Geotab

Image data captured at vehicles is transmitted and stored remotely from vehicles. To prevent redundant transmission and storage of image data, a reference metadata database is implemented, where metadata is stored corresponding to image data. Before transmitting image data from a vehicle and storing the image data remotely, metadata corresponding to the image data is evaluated against the reference metadata database to determine whether the image data is already stored remotely from the vehicle. Where the metadata corresponding to the image data is already in the reference metadata database, the image data is not re-transmitted or stored in duplicate. Where the metadata corresponding to the image data is not already in the reference metadata database, the image data is transmitted from the vehicle and stored in the image data database.

Systems and methods for detecting bad installations of telematics devices are provided. The method involves operating at least one processor to: receive image data associated with an installation of a telematics device in a vehicle; extract a portion of the image data containing the telematics device using a first machine learning model trained to detect the telematics device in the image data; determine whether the telematics device was correctly installed using a second machine learning model on the extracted portion of the image data, the second machine learning model trained to classify the telematics device in the extracted portion of the image data based on a position and orientation of at least one fastener attached to the telematics device; and automatically execute at least one action in response to and based on the determination of whether the telematics device was correctly installed.

Systems, methods, models, and training data for models are discussed, for determining vehicle positioning, and in particular identifying tailgating. Simulated training images showing vehicles following other vehicles, under various conditions, are generated using a virtual environment. Models are trained to determine following distance between two vehicles. Trained models are used in detection of tailgating, based on determined distance between two vehicles. Results of tailgating are output to warn a driver, or to provide a report on driver behavior.

Methods by a telematics device and a telematics device for simplifying captured telematics data and providing near real-time data points to a telematics server. Simplifying the data uses an algorithm that prioritizes primary data while providing timely secondary data under various conditions. In some implementations, a data simplification method is applied to partially filled data captured buffers containing secondary data. In some implementations, partially filled data capture buffers are processed if data points of that data type have not been selected for sending or if the data capture buffers are filled over a particular threshold. In some implementations, data points having an estimate error greater than an estimate error threshold are selected for sending to the telematics server.

System relating to a telematic vehicle sharing platform ecosystem and a telematic vehicle share I/O expander to automate sharing and management of a vehicle that is shared by more than one operator.

System, apparatus, device and methods relating to a telematic vehicle sharing platform ecosystem and a telematic vehicle share I/O expander to automate sharing and management of a vehicle that is shared by more than one operator.

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.

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 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.

Systems, methods, devices, and models for identifying preventable idling in vehicles are described. Preventable idling events are identified which are outside of acceptability criteria, such as idling duration. Preventable idling events can be associated with drivers and/or vehicles to provide avenues to curb preventable idling. Fuel consumption and/or carbon emissions for preventable idling events are identified to quantify efficacy of curbing preventable idling. Histograms and concentration maps are generated to identify high-concentration idling events, and take targeted action.