U-M Industrial and Operations Engineering (IOE) assistant professor, Jessie Yang, together with associate professor, Carol Menassa and Professor Vineet Kamat of Civil and Environmental Engineering (CEE), has received MCubed funding to create an entirely new end-to-end mobility system for individuals with vision impairments.
The project, led by Menassa of CEE and James Weiland from the School of Medicine, aims to develop a smart mobility system that features assisted navigation, autonomous maneuvering and real-time data integration technologies.
The research team’s approach will integrate visual slam, occupancy grid mapping and feature maps from point clouds along with deep learning to develop the navigation and maneuvering system. This system will rely on sensors placed on the individual and in the surrounding environment, and results from the research will lead to recommendations for both.
To inform the likelihood of the new technology being applied in a real-world setting, working prototypes will be created and evaluated for usefulness and usability, two factors predictive of technology adoption. The prototypes will include a multi-modal interface to provide non-visual orientation and directional cues to the user.
“The success of the proposed assistive technology relies on a good human-machine interface to convey information and to guide the visually impaired,” said Yang. “No matter how accurately the device navigates, if it can’t communicate this information effectively to the user, it won’t be widely adopted. To this end, we will develop and test novel human-machine interface designs to enhance user experience.”
“No matter how accurately the device navigates, if it can't communicate this information effectively to the user, it won't be widely adopted."Jessie Yang. Assistant Professor, U-M Industrial & Operations Engineering
Due to cross-department and other U-M collaboration, including Robin Brewer from the School of Information, researchers for this project can draw on combined expertise in building structures, machine learning, human visual systems, and user experience design.
Mcubed stimulates innovative research and scholarship by distributing real-time seed funding to multi-unit, faculty-led teams. Through this revolutionary research funding program, faculty from at least two different campus units can form a collaborative trio, or “cube.”