Disney patents AI to predict robot movements using digital twins
Disney has been granted a patent for a system that uses a neural network to improve digital simulations of robots. The technology compares real sensor data from a robot with its digital model to train the AI to accurately predict the robot's position, motion, or electrical state. Once trained, the system can apply these predictions to other robots with different mechanical parts.
In the filing’s own words
Systems and methods for training a neural network to predict states of a robotics device are disclosed. Robotics data is received for a robotics device, including indications of a set of components, a digital simulation of the robotics device, and measurement data received from a sensor associated with the robotics device. The set of components includes an actuator and a structural element. A training dataset is generated using the received robotics data. Generating the training dataset includes comparing the measurement data with simulated measurement data based on the digital simulation. A neural network is trained using the generated training dataset to modify the digital simulation of the robotics device to predict a state of the robotics device, such as a position, motion, electrical quantity, or other. When trained, the neural network is applied to predict states of the robotics device or a different robotics device.
What exactly they claim (claim 1)
1. A computer-implemented method of training a neural network to predict states of a robotics device, the method comprising: receiving robotics data for at least one robotics device, wherein the robotics data includes indications of a set of components comprising at least one actuator and at least one structural element, a digital simulation of the at least one robotics device, and measurement data received from at least one sensor associated with the at least one robotics device; generating, using the received robotics data, a training dataset, wherein generating the training dataset includes comparing the measurement data with simulated measurement data based on the digital simulation; training, using the generated training dataset, a neural network to modify the digital simulation of the at least one robotics device to predict a state of the at least one robotics device; modifying the digital simulation of the at least one robotics device using the trained neural network; and applying the trained neural network to a different robotics device to predict a future state of the different robotics device, wherein the different robotics device includes a different set of components comprising, in part, different mechanical components.
Facts
- Company
- Disney (DISNEY ENTERPRISES, INC.)
- Official title
- Simulation of robotics devices using a neural network systems and methods
- Patent number
- US12789365B2
- Application number
- 18232239
- Filed
- Aug 9, 2023
- Granted
- Nov 10, 2026
- Inventors
- 5
- Claims
- 18
Classified under
B25J 9/161 Operations & transportB25J 9/1605 Operations & transportB25J 9/163 Operations & transportB25J 9/1653 Operations & transportB25J 9/1664 Operations & transportMore from Disney in Robots & automation
- Disney patents robot control that uses AI to stop shaking Nov 3, 2026
- Disney patents suit frame that moves like a real muscle Nov 10, 2026
- Disney patents robot control that learns from human operators Sep 3, 2026
- Disney patents motion system for physical characters Nov 5, 2026
- Disney patents method to predict how objects fly off moving rides Oct 20, 2026
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.
