MUMBAI, India, Jan. 9 -- Intellectual Property India has published a patent application (202541133628 A) filed by Indian Institute Of Technology, Chennai, Tamil Nadu, on Dec. 30, 2025, for 'system and method for llm-based autonomous robot task planning and feasibility validation.'
Inventor(s) include Nirav Patel; Bijo Sebastian; Rengaswamy Jayaganthan; Vaidehi Bagaria; and Nikshep Grampurohit.
The application for the patent was published on Jan. 9, under issue no. 02/2026.
According to the abstract released by the Intellectual Property India: "A robot control system and method for autonomous robotic task planning and feasibility validation are disclosed. The system includes at least one processor, at least one memory, and a robot controller communicatively coupled to at least one physical robot having actuators, joints, and sensors. The processor is configured to acquire static robot configuration data from a URDF file and real-time robot state data from ROS topics. Based on the acquired data, the system generates a hardware-agnostic, real-time RCM defining executable robot actions constrained by mechanical, kinematic, payload, and safety limits of the robot. The RCM is provided to a planning module including an LLM, wherein the planning module is restricted to selecting only actions defined in the RCM. Selected actions are validated against the constraints prior to execution, and only validated actions are transmitted to the robot controller for execution."
Disclaimer: Curated by HT Syndication.
