Abstract: A method of training Machine Learning (ML) models for aligning inertial data captured by inertial sensors located in dynamic vehicles, comprising receiving inertial data recorded in a plurality of trips of vehicles using inertial sensors placed in the vehicles in one or more predefined orientations with respect to the vehicles, segmenting each of the trips to trip segments, creating labeled training samples each comprising a time-series vector comprising inertial data samples recorded during a time window of a respective trip segment and associated with a label reflecting the predefined orientation of the inertial sensors, training one or more ML models using the labeled training samples to estimate orientation of inertial sensors with respect to vehicles, and outputting the trained ML model(s) for estimating orientation of inertial sensors placed in vehicles with respect to the vehicles for aligning their captured inertial data with respect to the vehicles.

Abstract: A system and method for estimating a velocity of a vehicle, including obtaining readings of at least one inertial sensor that is attached to the vehicle, calculating a time difference between a time when an irregularity is sensed in a first location of the vehicle and a time when the irregularity is sensed in a second location of the vehicle, and calculating the velocity of the vehicle based on the time difference.

Abstract: A system and method for estimating a velocity of a vehicle, including obtaining readings of at least one inertial sensor that is attached to the vehicle, calculating a time difference between a time when an irregularity is sensed in a first location of the vehicle and a time when the irregularity is sensed in a second location of the vehicle, and calculating the velocity of the vehicle based on the time difference.

Abstract: A system and method for providing localization, including, during a training phase: obtaining a training dataset of accelerations, angular velocities, and known locations over time of vehicles moving in a defined area; and training a machine learning model to provide location estimation in the defined area based on the accelerations and angular velocities using the training dataset; and during runtime phase: obtaining runtime accelerations and angular velocities overtime of a vehicle moving in the defined area; and using the trained model to obtain current location of the vehicle based on the runtime acceleration and angular velocities.

Abstract: A system and method for estimating a velocity of a vehicle, including obtaining readings of at least one inertial sensor that is attached to the vehicle, calculating a time difference between a time when an irregularity is sensed in a first location of the vehicle and a time when the irregularity is sensed in a second location of the vehicle, and calculating the velocity of the vehicle based on the time difference.

Abstract: A method of tracking ground vehicles based on Inertial Measurement Unit (IMU) data, comprising accumulating motion data captured by IMU(s) deployed in a vehicle, the motion data captured periodically in a plurality of time points starting from a known initial location of the vehicle comprises at least acceleration and angular velocity, computing, based on the motion data, a measured heading angle time-series of the vehicle expressing a movement direction of the vehicle over time, analyzing map data of an area of the known initial location to identify candidate routes, simulating, based on the map data, a simulated heading angle time-series for each candidate route expressing a simulated movement direction along the respective candidate route over time, ranking the candidate routes based on match between each simulated heading angle time-series and the measured heading angle time-series, and estimating a location of the vehicle based on the ranking.

Abstract: A system and method for providing localization, including, during a training phase: obtaining a training dataset of accelerations, angular velocities, and known locations over time of vehicles moving in a defined area; and training a machine learning model to provide location estimation in the defined area based on the accelerations and angular velocities using the training dataset; and during runtime phase: obtaining runtime accelerations and angular velocities overtime of a vehicle moving in the defined area; and using the trained model to obtain current location of the vehicle based on the runtime acceleration and angular velocities.

Abstract: A system and method for estimating a location of a vehicle, including, using a processor: measuring, via an inertial sensor attached to a vehicle, at least one of an acceleration or angular velocity of the vehicle; determining, via the processor, in the at least one of the acceleration or the angular velocity a signal signature based on a pattern recognition algorithm, wherein the signal signature is associated with a particular mark located at a particular location; determining, via the processor, that the vehicle is located at the particular location based on the predetermined association between the particular mark and the particular location; and providing, via the processor, the particular location to a human user or to a computerized application.

Abstract: A system and method for providing localization, including, during a training phase: obtaining a training dataset of accelerations, angular velocities, and known locations over time of vehicles moving in a defined area; and training a machine learning model to provide location estimation in the defined area based on the accelerations and angular velocities using the training dataset; and during runtime phase: obtaining runtime accelerations and angular velocities over time of a vehicle moving in the defined area; and using the trained model to obtain current location of the vehicle based on the runtime acceleration and angular velocities.

Abstract: A system and method for providing localization, including, during a training phase: obtaining a training dataset of accelerations, angular velocities, and known locations over time of vehicles moving in a defined area; and training a machine learning model to provide location estimation in the defined area based on the accelerations and angular velocities using the training dataset; and during runtime phase: obtaining runtime accelerations and angular velocities over time of a vehicle moving in the defined area; and using the trained model to obtain current location of the vehicle based on the runtime acceleration and angular velocities.