Perception and Action Planning for Robots

Departments: Mechanical Engineering and Materials Science
Time: Thursday, April 8, 2021 - 3:30pm - 4:30pm
Type: Seminar Series
Presenter: Prof. Volkan Isler; University of Minnesota, Head of the Samsung AI Center in New York (SAIC-NY)
Room/Office:
Location:

Yale School of Engineering & Applied Science Special Robotics Seminar

Prof. Volkan Isler
University of Minnesota
Head of the Samsung AI Center in New York (SAIC-NY)

“Perception and Action Planning for Robots”

Thursday, April 8 at 3:30pm
Contact department for Zoom instructions

Abstract: Planning algorithms that are aware of both the sensing and actuation limitations of robots are critical for robot operation in dynamic and complex environments. In the first part of my presentation, I will go over our work on developing sensing planning algorithms for mobile robot search and coverage where geometric representations provide the perception-action interface. I will show examples of our work on developing optimization algorithms for the resulting planning problems. I will also present some of our field deployments for environmental monitoring and agricultural applications that allow us to validate these algorithms at the system level. In the second part of my talk, I will go over our recent and ongoing work at SAIC-NY on learning state representations which allow robots to reason about and manipulate household objects in natural settings.

Bio: Volkan Isler is a professor of computer science and engineering at the University of Minnesota. He is currently on leave, serving as the head of Samsung’s newly established AI Center in New York (SAIC-NY). His primary research interest is to develop algorithms and systems that are aware of sensing, planning and communication limitations of robotic systems. 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, as an associate editor for the IEEE Transactions on Robotics, and IEEE Transactions on Automation Science & Engineering. He is also a co-founder of Farm-Vision Technologies — a UMN start up based on his lab’s work on yield mapping for specialty farms.

Host: Aaron Dollar, Professor of Mechanical Engineering & Materials Science and Computer Science