AI-powered smart glasses for sensing and recognition of human-robot walking environments

The project is to develop an environment recognition system using computer vision and deep learning techniques (i.e., image or video classification of walking environments) and to further develop a functional prototype of an AI-powered glasses. The designed system could achieve high prediction accuracy on real-world visual data and be efficient for onboard real-time inference with embedded devices. The predictions generated by the recognition system can support the development of next-generation environment-adaptive controllers for robotic leg prostheses and exoskeletons, which would turn out to help older adults or individuals with mobility impairments regain mobility and independence through powered locomotor assistance.

Faculty Supervisor:

Alex Mihailidis

Student:

Partner:

University Health Network

Discipline:

Computer science

Sector:

Health and Related Sciences & Technology

University:

University of Toronto

Program: