/Patent Tracker
DisneyPatent applicationRobots & automationInterest 7/10

Disney patents robot control that learns from human operators

Disney describes a method for training robots to act on their own by learning from human commands. The system uses a specific type of AI model to analyze past movements and operator inputs to predict the next action the robot should take.

Why it mattersThis could help robots in theme parks or studios interact more naturally with guests by mimicking human behavior without constant manual control.

In the filing’s own words

A method of training a diffusion model to enable autonomous interaction between a robotic device and a human includes receiving an operator command for the robotic device and pose data including a history of poses. The method includes applying noise to the operator command and encoding the noisy operator command, pose data, and history of operator commands into input tokens. The method includes inputting the tokens into a transformer encoder of the diffusion model and training the model to perform denoising to generate an autonomous command from the noisy operator command based on the pose data and command history. The method includes generating the autonomous command based on the transformer encoder output and executing the command to cause the robotic device to perform an action during autonomous interaction with the human.

What exactly they claim (claim 1)

1. A method of training a diffusion model to enable autonomous interaction between a robotic device and a human, the method comprising: receiving, via a processing element, an operator command for the robotic device; receiving, via the processing element, pose data including a history of poses; applying, via the processing element, noise to the operator command to generate a noisy operator command; encoding, via the processing element, the noisy operator command, the pose data, and a history operator commands into a plurality of input tokens; inputting, via the processing element, the plurality of input tokens into a transformer encoder of the diffusion model; training, via the processing element, the diffusion model to perform a denoising operation to generate an autonomous command from the noisy operator command based on the pose data and the history of operator commands; generating, via the processing element, the autonomous command based on an output of the transformer encoder; and executing, via the robotic device, the autonomous command to cause the robotic device to perform an action during the autonomous interaction between the robotic device and the human.

Facts

Company
Disney (DISNEY ENTERPRISES, INC.)
Official title
AUTONOMOUS HUMAN-ROBOT INTERACTION VIA DIFFUSION-BASED OPERATOR IMITATION
Publication number
US20260257351A1
Application number
19550668
Filed
Feb 26, 2026
Published
Sep 3, 2026
Inventors
9
Claims
20

Classified under

B25J 9/163 Operations & transportG06N 3/08 Physics & computing
Read the full filing (official PDF) ↗ Open in the Patent Tracker

More from Disney 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.