The UMD-PRG (PRG stands for Perception and Robotics Group) hails from the University of Maryland.
Hailing from one of the nation's premier public research universities, the UMD-PRG team brings to bear a diverse mix of skills and expertise spanning the breadth of the field of AI. Advised by the renowned computer vision and motor specialist, professor Yiannis Aloimonos, the team hopes to leverage their experience working in similar domains (such as the EPIC-KITCHENS dataset) along with a spate of fresh fearless ideas to create a SimBot that is intelligent, capable, stable, and user-friendly. In particular, they believe that their compositional model of robot action will give them a leg up in the competition.
David S. — Team leader
David is a PhD student in Computer Science at the University of Maryland, College Park, and will be serving as Team Leader for the UMD-PRG team. His research spans such topics as commonsense reasoning, attention mechanisms, knowledge representation, and logic. In this competition, he hopes to merge traditional techniques with cutting-edge ML tools to allow the SimBot to have a more robust, flexible, and interpretable model of the world around it.
Eadom is a PhD student in the department of Computer Science at the University of Maryland College Park, advised by Yiannis Aloimonos and Cornelia Fermuller. His research interests include computer vision, knowledge representation and reinforcement learning. His recent work has focused on developing structured representations of video for downstream applications in AI and robotics, and his past work involves working in robot grasping and manipulation, where he was team leader of Team GMU-BGU in the Amazon Robotics Challenge. In this competition, he aims to apply his recent research on learning and representing complex actions.
Chinmaya is a PhD candidate in Electrical and Computer Engineering at the University of Maryland College Park. He is advised by Prof Yiannis Aloimonos and Dr. Cornelia Fermuller. His Ph.D. thesis is on revisiting symbolic understanding for action understanding. His research areas include graph neural networks, Zero-shot learning, symbolic-AI, the intersection between language and vision and has several publications and a patent in this field. Prior to this, he graduated with a B.Tech In Electrical and Electronic Engineering from the National Institute of Technology Karnataka, Surathkal, India.
John is a PhD student in the Department of Computer Science at the University of Maryland, College Park. He is advised by Prof. Yiannis Aloimonos and Prof. Bill Regli. His research primarily focuses on language-guided object manipulation for robotics.
Michael is a PhD candidate in the department of Computer Science at the University of Maryland College Park, advised by Yiannis Aloimonos and Cornelia Fermuller. His background encompasses symbolic Artificial Intelligence, including cognitive architectures, Computer Vision, action understanding, and methods integrating AI and CV.
Smit is an undergraduate student at the University of Maryland who is currently pursuing his bachelor’s degree in computer science. He channels his love for learning and exploring through his research interests, which include computer vision. He also a part of the Capital One machine learning research stream in the UMD FIRE program.
Yiannis Aloimonos — Faculty advisor
Yiannis Aloimonos leads the Perception and Robotics Group at the University of Maryland. His research is devoted to the principles governing the design and analysis of real-time systems that possess perceptual capabilities, for the purpose of both explaining animal vision and designing seeing machines.