US Patent Issued to GOOGLE on Dec. 16 for "Mitigating reality gap through training a simulation-to-real model using a vision-based robot task model" (California Inventors)

ALEXANDRIA, Va., Dec. 16 -- United States Patent no. 12,498,677, issued on Dec. 16, was assigned to GOOGLE LLC (Mountain View, Calif.).

"Mitigating reality gap through training a simulation-to-real model using a vision-based robot task model" was invented by Kanishka Rao (Santa Clara, Calif.), Chris Harris (Los Altos, Calif.), Julian Ibarz (Mountain View, Calif.), Alexander Irpan (Palo Alto, Calif.), Seyed Mohammad Khansari Zadeh (San Carlos, Calif.) and Sergey Levine (Berkeley, 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) using a vision-based robot ta...