Departmental Seminar

Abstract:

State-of-the-art machine learning systems are primarily based on supervised methods. This “top-down” approach to intelligence has led to tremendous successes in natural language processing, and computer vision. At the moment, a significant focus in robotics research is on extending these successes to the design and deployment of intelligent robots. 

In this talk, I will first give an overview of robot systems we have built over the years, including: ground, surface, and aerial robot teams for environmental and agricultural data gathering; autonomous robots for picking fruit, mowing and weeding pastures and corn fields; and robots for tidying and cleaning our homes. I will then make the case for “bottom-up” approaches needed to enable long-term operation in unstructured environments, and present results from our recent work on building reactive systems that can robustly operate in such settings.

Biography: 

Volkan Isler is a professor of computer science at the University of Texas at Austin. Previously, he was head of Samsung’s AI Center in New York City and a professor at the University of Minnesota. He is primarily interested in coupling perception and planning in robotics. He has worked on fundamental algorithmic problems in this domain (pursuit-evasion and sensor planning), and developed field systems for environmental sensing, agricultural and home automation. He is the recipient of the NSF CAREER award, UMN McKnight Land-grant Professorship, and the Institute on the Environment Resident Fellowship. He has served as a member of the IEEE RAS Conference Editorial Board, chair of IEEE TC on Networked Robots and as an associate editor for both the IEEE Transactions on Robotics, and IEEE Transactions on Automation Science & Engineering. He is co-founder of Farm-Vision Technologies — a start-up based on his lab’s work on yield mapping for specialty farms.