MUMBAI, India, Feb. 6 -- Intellectual Property India has published a patent application (202641000645 A) filed by Manipal Academy Of Higher Education, Manipal, Karnataka, on Jan. 3, for 'a system and method for predictive and adaptive control of a humanoid platform.'
Inventor(s) include Subhradip Mukherjee; Natansh N; and Rituraj Bhattacharjee.
The application for the patent was published on Feb. 6, under issue no. 06/2026.
According to the abstract released by the Intellectual Property India: "The present invention provides a Predictive Adaptive Humanoid Control System designed to enable highly stable, responsive, and intelligent locomotion and interaction in humanoid platforms. The system integrates multi-modal sensor data, including proximity, joint-position, pressure, visual, auditory, and gesture inputs, to generate a synchronized real-time state estimate of the humanoid. A model-predictive control module computes future locomotion trajectories, while a heuristic path-optimization engine determines efficient navigation paths, even in dynamic or obstacle-filled environments. The system further employs adaptive state-updating logic to maintain balance, minimize path deviation, and ensure smooth joint actuation. Experimental results demonstrate 0% overshoot, 1.8-second settling time, improved path accuracy, and fast perceptual responses including gesture, speech, and face recognition. Overall, the invention delivers a computationally efficient, real-time control framework that significantly enhances the stability, adaptability, and autonomy of humanoid robotic platforms."
Disclaimer: Curated by HT Syndication.
