US Patent Issued to TATA CONSULTANCY SERVICES on Aug. 19 for "Method and system for reinforcement learning and dual channel action embedding based robotic navigation" (Indian Inventors)

ALEXANDRIA, Va., Aug. 20 -- United States Patent no. 12,393,195, issued on Aug. 19, was assigned to TATA CONSULTANCY SERVICES Ltd. (Mumbai, India).

"Method and system for reinforcement learning and dual channel action embedding based robotic navigation" was invented by Harshad Khadilkar (Thane West, India), Hardik Bharat Meisheri (Thane West, India), Omkar Dilip Shelke (Thane West, India), Durgesh Kalwar (Thane West, India) and Pranavi Pathakota (Hyderabad, India).

According to the abstract* released by the U.S. Patent & Trademark Office: "The present disclosure provides a Reinforcement Learning (RL) based architecture to efficiently learn action embeddings in low dimensional space. In conventional methods, the embeddings are learnt with ...