/Patent Tracker
NvidiaPatent applicationRobots & automationInterest 6/10

Nvidia patents method to create new robot training videos from existing footage

Nvidia describes a system that takes videos of a robot performing a task and uses them to create new videos showing the robot doing the same task in different ways. This process generates additional data to help train robotic devices to handle various scenarios.

Why it mattersThis technique could help robots learn more efficiently by expanding their training data without needing to film every possible variation manually.

In the filing’s own words

Apparatuses, systems, and techniques to generate data to train a robotic device to perform tasks. In at least one embodiment, one or more first videos of a robotic device performing a task is used to generate one or more second videos of the robotic device performing the task differently than depicted in the one or more first videos.

What exactly they claim (claim 1)

1. A processor comprising: one or more circuits to use one or more first videos of a robotic device performing a task to generate one or more second videos of the robotic device performing the task differently than depicted in the one or more first videos.

Facts

Company
Nvidia (NVIDIA Corporation)
Official title
DATA GENERATION OF ROBOTIC DEVICES PERFORMING TASKS
Publication number
US20260264239A1
Application number
19436169
Filed
Dec 30, 2025
Published
Sep 10, 2026
Inventors
8
Claims
20

Classified under

B25J 9/1664 Operations & transportB25J 9/161 Operations & transportB25J 9/1612 Operations & transportB25J 9/163 Operations & transportB25J 9/1671 Operations & transportB25J 9/1689 Operations & transport

More from Nvidia in Robots & automation

Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.