Tesla, Inc. patent applications on April 17th, 2025
Patent Applications by Tesla, Inc. on April 17th, 2025
Tesla, Inc.: 3 patent applications
Tesla, Inc. has applied for patents in the areas of G06N20/00 (2), B60W30/08 (1), B60W50/14 (1), G06Q40/08 (1), G06N3/08 (1) B60W30/08 (1), G06N3/08 (1), G07C5/0808 (1)
With keywords such as: vehicle, data, pseudonymous, service, processor, driving, network, series, time, and training in patent application abstracts.
Patent Applications by Tesla, Inc.
20250121818. MACHINE LEARNING MODEL FOR PREDICTING DRIVING EVENTS_simplified_abstract_(tesla, inc.)
Inventor(s): Thoralf Gutierrez of Palo Alto CA US for tesla, inc., James Potthast of Palo Alto CA US for tesla, inc., Alex Baranau of Palo Alto CA US for tesla, inc.
IPC Code(s): B60W30/08, B60W50/14, G06N20/00, G06Q40/08
CPC Code(s): B60W30/08
Abstract: a processor retrieves data associated with a set of driving sessions and generates a training dataset by labeling a first subset of data that corresponds to driving sessions that included a first event and labeling a second subset of the data that corresponds to driving sessions that included an indication of an airbag activation. the processor then trains an artificial intelligence model using the training dataset, such that trained artificial intelligence model predicts a score indicative of a likelihood of a new driving session associated with a new driver being associated with at least the first event or an airbag activation. once trained, the processor can augment the score using data retrieved after each driving session. the processor can also notify the driver if the driver's actions has caused their score to increase/decrease and provide an underlying reason.
Inventor(s): Ashok Kumar Elluswamy of Sunnyvale CA US for tesla, inc., Matthew Bauch of San Francisco CA US for tesla, inc., Christopher Payne of San Francisco CA US for tesla, inc., Andrej Karpathy of San Francisco CA US for tesla, inc., Joseph Polin of San Francisco CA US for tesla, inc.
IPC Code(s): G06N3/08, G06F18/28, G06N3/04, G06V20/56, G16Y20/10
CPC Code(s): G06N3/08
Abstract: sensor data, including a group of time series elements, is received. a training data set is determined, including by determining for at least a selected time series element in the group of time series elements a corresponding ground truth. the corresponding ground truth is based on a plurality of time series elements in the group of time series elements. a processor is used to train a machine learning model using the training dataset.
Inventor(s): Thoralf Gutierrez of Palo Alto CA US for tesla, inc., James Potthast of Palo Alto CA US for tesla, inc.
IPC Code(s): G07C5/08, G06N20/00
CPC Code(s): G07C5/0808
Abstract: the present disclosure related to a vehicle prognostication with a management of data communications between individual vehicles and a network service. the network service can facilitate the management of data communications between a selected vehicle and remote service utilizing pseudonymous identifiers. illustratively, a pseudonymous identifier can correspond to at least a semi-unique identifier generated by a vehicle or configure on a vehicle. the generation/configuration of the pseudonymous is implemented in a manner that the network service does not associate any additional identifiers, such as vins, associated with the vehicle, vehicle owner, vehicle user, etc. a network service can receive the vehicle data with a pseudonymous and perform the prognostication of the vehicle. the network service can post vehicle prognostication with directives associated with the pseudonymous identifiers. the vehicle can identify one or more directives by matching the pseudonymous identifiers with the vehicle's pseudonymous identifier.