MUMBAI, India, May 29 -- Intellectual Property India has published a patent application (202641064555 A) filed by Vellore Institute Of Technology, Vellore, Tamil Nadu, on May 21, for 'reinforcement learning-based autonomous motorized walking assist device with adaptive navigation and multimodal feedback architecture.'
Inventor(s) include Arun Pandian J; and Vijaykrishnan P.
The application for the patent was published on May 29, under issue no. 22/2026.
According to the abstract released by the Intellectual Property India: "The invention relates to an autonomous motorized walking assist device for visually impaired, elderly, and physically challenged users. The device comprises a walking stick assembly integrated with a motorized multi-wheel base, servo-actuated distance sensing unit, motion sensing unit, and an embedded control unit executing a reinforcement learning-based adaptive control framework. The system performs sensor fusion to generate environmental state representations and dynamically controls motor speed, direction, and torque, including terrain-responsive torque adjustment. A multimodal feedback system provides context-aware haptic and auditory alerts. The device further includes a fail-safe mechanism for safety. The invention enables adaptive navigation, improved stability, reduced collision risk, and reduced user effort."
Disclaimer: Curated by HT Syndication.
