US Patent Issued to GOOGLE on Aug. 11 for "Deep reinforcement learning-based techniques for end to end robot navigation" (California Inventors)

ALEXANDRIA, Va., Aug. 12 -- United States Patent no. 12,704,841, issued on Aug. 11, was assigned to GOOGLE LLC (Mountain View, Calif.).

"Deep reinforcement learning-based techniques for end to end robot navigation" was invented by Aleksandra Faust (Palo Alto, Calif.), Hao-tien Chiang (Mountain View, Calif.), Anthony Francis (Mountain View, Calif.) and Marek Fiser (Mountain View, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Using reinforcement learning to train a policy network that can be utilized, for example, by a robot in performing robot navigation and/or other robotic tasks. Various implementations relate to techniques for automatically learning a reward function for training of a policy networ...