Systems and methods for virtual artificial intelligence development and testing
Inventors
Schweet, Richard Raymond • Ruggiero, Bendenetto Christopher • Hartshorn, Kyle Robert • Sweeney, Gregory Ryan • Cypher, Kyle Dean • Scharf, Melissa Yenni • Meyer, Emily Ann • Lisy, Alec Brenders • Jarrett, Jeremy David • Fye, Matthew David
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-11372474-B2
Publication Date
2022-06-28
Expiration Date
Abstract
Systems and methods are provided to create training data, validate, deploy and test artificial intelligence (AI) systems in a virtual development environment, incorporating virtual spaces, objects, machinery, devices, subsystems, and actual human action and behavior.
Core Innovation
The invention provides a computer implemented method that provisions, through a virtual reality interface of a virtual reality device worn by each human actor, a virtual environment that is a digital twin virtual environment of a real-world physical environment. The virtual environment includes at least one virtual sensor modeled to generate a virtual output corresponding to an output of a real-world sensor, and the method supports provisioning for a first human actor and simultaneously for a second human actor.
The method tracks real-time physical motion of the first and second human actors within a studio and presents to each human actor at least a portion of a humanoid avatar replicating the real-time physical motion of the other actor within the digital twin virtual environment. Real-time information is collected from the digital twin virtual environment with an artificial intelligence computing system based on the tracking of the real-time physical motion of the first and second human actors within the studio and the virtual output of the virtual sensor.
The artificial intelligence computing system is used at the real-world physical environment that comprises the real-world sensor. Prior to use of the artificial intelligence computing system at the real-world physical environment, the method tests the artificial intelligence computing system based on the tracking of the real-time physical motion of the first and second human actors within the studio.
Claims Coverage
The partial content includes one independent claim. It defines four inventive features: multi-actor VR provisioning of a digital twin virtual environment, real-time studio motion tracking with humanoid avatar replication, AI collection of real-time information from the digital twin based on motion and virtual sensor output, and pre-deployment AI testing before real-world use.
Provisioning a digital twin virtual environment via VR interfaces for multiple human actors
Provisioning, by a virtual environment computer system, a virtual environment to a first human actor through a first virtual reality interface of a first virtual reality device worn by the first human actor and simultaneously to a second human actor through a second virtual reality interface of a second virtual reality device worn by the second human actor, wherein the virtual environment is a digital twin virtual environment of a real-world physical environment and comprises a virtual sensor modeled to generate a virtual output corresponding to an output of a real-world sensor.
Real-time studio motion tracking and humanoid avatar replication for each actor
Tracking real-time physical motion of the first and second human actors within the studio and presenting to each human actor at least a portion of humanoid avatars replicating the real-time physical motion of the other actor within the digital twin virtual environment.
AI collection of real-time information from the digital twin based on tracked motion and virtual sensor output
Collecting real-time information from the digital twin virtual environment with an artificial intelligence computing system, wherein the real-time information is based on the tracking of the real-time physical motion of the first and second human actors within the studio and the virtual output of the virtual sensor, and wherein the artificial intelligence computing system is for use at the real-world physical environment that comprises the real-world sensor.
Pre-deployment AI testing based on tracked real-time motion in the studio digital twin
Prior to use of the artificial intelligence computing system at the real-world physical environment, testing the artificial intelligence computing system based on the tracking of the real-time physical motion of the first and second human actors within the studio.
The inventive concept combines digital twin VR provisioning, studio-based motion tracking with humanoid avatar replication, AI collection of real-time information from motion and virtual sensor output, and testing before real-world deployment.
Stated Advantages
Documented Applications
No documented applications found
Interested in licensing this patent?