Eyes for the Blind: A Multi-Agent Assistant for the Visually Impaired

This project aims to develop a multi-agent AI framework that assists visually impaired individuals with navigating both indoor and outdoor environments, such as locating a room, identifying obstacles, or safely crossing a road. The system will use specialized agents for tasks including speech recognition, text-to-speech communication, environmental perception, and decision-making. By responding to spoken questions, describing the surrounding environment, and providing informed navigation recommendations, the system could give visually impaired users greater independence and access to information that would otherwise be difficult or impossible to have without assistance.

Intern: Shriyadita De

Mentor: Harun Gopal (AMDS/A5B)