USPTO Patent for Object Classification in Autonomous Systems

ChangeBridge: Patent Grants - AI & Computing (G06N)

Published March 24th, 2026

Detected March 25th, 2026

Summary

The USPTO has granted patent US12586365B2 to NVIDIA Corporation for an object classification system using multilabel and hierarchical classification for autonomous systems. The patent describes methods utilizing neural networks to classify objects based on attributes and class labels, enhancing final classification accuracy.

View original document View source feed page

What changed

USPTO patent grant US12586365B2 has been issued to NVIDIA Corporation for a novel method of object classification in autonomous systems. The patent details the use of neural networks for multilabel and hierarchical classification, enabling systems to identify objects like traffic signs by analyzing multiple attributes and class labels. This technology aims to improve the accuracy and robustness of object recognition in AI-driven applications.

This patent grant represents a new intellectual property development in the field of AI and autonomous systems. While not imposing direct regulatory obligations on other entities, it signifies advancements in technology that may influence future industry standards and competitive landscapes. Companies operating in the autonomous vehicle, robotics, and AI sectors should be aware of this patented technology, particularly concerning its potential impact on their own research, development, and product strategies.

Source document (simplified)

← USPTO Patent Grants

Object classification using multiple labels for autonomous systems and applications

Grant US12586365B2 Kind: B2 Mar 24, 2026

Assignee

NVIDIA Corporation

Inventors

Rui Shen, Sebastian Michael Agethen, Jian xing Zhang

Abstract

In various examples, multilabel hierarchical classification of objects for autonomous systems and applications is described herein. Systems and methods are disclosed that use one or more neural networks to classify objects, such as traffic signs, using multilabel classification and/or hierarchical classification. For instance, a multilabel subnetwork of the neural network(s) may classify an object based at least on one or more attributes associated with the object. As such, the output from the multilabel subnetwork may include at least a classification associated with the object and an attribute classification(s) associated with the object. A hierarchical subnetwork of the neural network(s) may also classify the object using one or more class labels, where a class label indicates another classification and/or a class group associated with the object. The systems and methods may then use the classification, the attribute classification(s), and/or the class label(s) to determine a final classification associated with the object.