Accessibility Lunch Seminar - Eshed Ohn-Bar

— 1:00pm

Speaker:
ESHED OHN-BAR , Assistant Professor, Department of Electrical and Computer Engineering, Boston University
https://eshed1.github.io/

Adaptive Accessibility Systems

Despite decades of progress in AI, making AI systems usable and helpful in real-world situations remains challenging. This gap becomes especially clear when designing systems for people with disabilities, whose diverse needs and behaviors often confound existing models and remain a (suboptimal) afterthought. In this talk, I will describe our efforts to build adaptive AI systems that safely and efficiently assist individuals with visual impairments in complex navigation tasks. 

At the core of our approach are AI models that can leverage diverse supervision and realistic interactions to learn multimodal models for how people perceive the environment, respond to instructions, and dynamically move through 3D spaces. Beyond addressing fundamental questions in interactive AI, e.g., for effectively modeling diverse data, the research will pave the way toward a foundational framework for building scalable systems that can seamlessly adapt to varying users, environments, and applications—whether in transportation, healthcare, and education. 

— 

Eshed Ohn-Bar is an Assistant Professor in the Department of Electrical and Computer Engineering at Boston University (BU). His research lies at the intersection of machine intelligence, computer vision, and interactive systems, with the goal of developing scalable AI frameworks that enhance quality of life—from self-driving vehicles to wearable technologies for individuals with disabilities. His collaborations with colleagues have been recognized with numerous awards, including the BU College of Engineering Early Career Excellence in Research Award, best PhD dissertation award from the IEEE Intelligent Transportation Systems Society, and best paper awards (the CVPR AMFG Workshop, Web for All Conference, and finalist at ICPR). His team was also a semifinalist in the 2022 DoT Inclusive Design Challenge. Prior to joining BU, he was a Humboldt Fellow at the Max Planck Institute and a Postdoctoral Researcher at Carnegie Mellon University. Eshed received a BS degree in Mathematics from UC Los Angeles in 2010, MEd from UC Los Angeles in 2011, and the PhD degree in Electrical Engineering from UC San Diego in 2017. 

Zoom Participation.  See announcement.

Event Website:
https://cmubiglab.github.io/lunch/

Add event to Google
Add event to iCal