US Patent Issued to Mitsubishi Electric Research Laboratories on Nov. 25 for "System and method for controlling a robotic manipulator based on hierarchical reinforcement learning of control policies" (Massachusetts, Pennsylvania Inventors)

ALEXANDRIA, Va., Nov. 25 -- United States Patent no. 12,479,090, issued on Nov. 25, was assigned to Mitsubishi Electric Research Laboratories Inc. (Cambridge, Mass.).

"System and method for controlling a robotic manipulator based on hierarchical reinforcement learning of control policies" was invented by Devesh Jha (Cambridge, Mass.), Shivam Vats (Pittsburg, Pa.) and Diego Romeres (Cambridge, Mass.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A feedback controller for controlling a robotic manipulator to perform a task is provided. The feedback controller comprises a memory configured to store a hierarchical reinforcement learning (HRL) neural network including (i) nominal control policy, and (ii) recovery...