US Patent Issued to GDM Holding on July 21 for "Training a simulation-to-real model, based on perception losses, to mitigate reality gap in robotics and/or other applications" (California Inventors)

ALEXANDRIA, Va., July 21 -- United States Patent no. 12,688,341, issued on July 21, was assigned to GDM Holding LLC (Mountain View, Calif.).

"Training a simulation-to-real model, based on perception losses, to mitigate reality gap in robotics and/or other applications" was invented by Daniel Ho (Fremont, Calif.), Yunfei Bai (Fremont, Calif.) and Kanishka Rao (Santa Clara, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Implementations disclosed herein relate to mitigating the reality gap through training a simulation-to-real machine learning model ("Sim2Real" model) based on loss(es) generated using already trained perception model(s), such as perception model(s) trained to process an image and generat...