US Patent Issued to GOOGLE on June 17 for "Mitigating reality gap through feature-level domain adaptation in training of vision-based robot action model" (California Inventors)

ALEXANDRIA, Va., June 19 -- United States Patent no. 12,333,787, issued on June 17, was assigned to GOOGLE LLC (Mountain View, Calif.).

"Mitigating reality gap through feature-level domain adaptation in training of vision-based robot action model" was invented by Mohi Khansari (San Carlos, Calif.), Daniel Ho (Fremont, Calif.), Eric Jang (Cupertino, Calif.) and Yu Qing Du (Berkeley, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Implementations disclosed herein relate to mitigating the reality gap through feature-level domain adaptation in training of a vision-based robotic action machine learning (ML) model. Implementations mitigate the reality gap through utilization of embedding consistency losses a...