Automatic labeling of data for vehicle machine learning models

ChangeBridge: Patent Grants - AI & Computing (G06N)

Published April 7th, 2026

Detected April 7th, 2026

Summary

USPTO granted patent US12596939B2 to inventors including Harsh Bhupendra Bhate and others, covering an automatic data labeling system for vehicle-based machine learning models. The system receives data identification and labeling parameters via a configuration file, creates publication topics on the vehicle, and appends labels to data using metadata for model training purposes.

View original document View source feed page

What changed

USPTO granted patent US12596939B2 for a system that automatically labels data for vehicle machine learning applications. The system receives data identification via a configuration file associated with an ML model stored by a vehicle, defines labeling parameters through the same configuration file, creates topics for data publication on the vehicle containing both gathered data and metadata, and appends labels to data using the metadata in accordance with configuration file definitions.

This patent affects manufacturers developing autonomous or semi-autonomous vehicle systems that use machine learning models. Automotive manufacturers and technology companies working on vehicle data labeling systems should consider potential licensing implications or design around this IP when developing similar systems for ML model training data.

What to do next

Monitor for updates

Source document (simplified)

← USPTO Patent Grants

Automatic labeling of data by an entity gathering the data

Grant US12596939B2 Kind: B2 Apr 07, 2026

Inventors

Harsh Bhupendra Bhate, Vyacheslav Zavadsky, Ziwei Zeng, Senthil Kumar Natarajan, Uttara Thakre, Panduranga Chary Kondoju, Aishwarya Vaibhav Kadam

Abstract

A system receives identification of data to be gathered, via a request configured based on a configuration file associated with a machine learning model stored by a vehicle. The system receives identification of how the data is to be labeled, defined by the configuration file and create one or more topics for publication of the data, onboard the vehicle, the publication including both the gathered data and any meta-data usable to label the data in accordance with the definitions in the configuration file. Also, the system subscribes to the topics to receive the published data and the metadata and appends labels to the data, using the metadata, to label the data in accordance with the definitions for labeling in the configuration file. The system saves the labeled data in vehicle memory as data associated with the model.