Archive: Developing Smart Cyber-Physical Systems Using Robot Learning - Ashis Banerjee (UW)
Traditional engineering systems, including those in the manufacturing, logistics, and transportation sectors, are transforming into cyber-physical systems (CPS), where several computational and physical resources are being intrinsically connected to each other to provide new capabilities. However, the impact of such capabilities on meaningful performance metrics, such as productivity and safety, is determined by how smartly we use the available resources. In this talk, we will discuss some recent foundational advances in robot learning to achieve smart use of CPS resources. Specifically, we will cover how a) spatio-temporal convolutional neural networks enable visual perception of workers' ergonomic risks during warehouse object manipulation; b); deep reinforcement learning adapts driving patterns of (semi)- autonomous cars based on their owners' preferences; and, c) a combination of deep segmentation and reinforcement learning facilitates formation of patterns using micro-robots. We will conclude by outlining promising future research directions.
Speaker Bio:
Ashis G. Banerjee is an Assistant Professor of Industrial & Systems Engineering and Mechanical Engineering at the University of Washington, Seattle. Prior to his current appointment, he was a Research Scientist at General Electric Global Research. Before that, he was a Postdoctoral Associate at the Massachusetts Institute of Technology. He obtained his Ph.D. and M.S. in Mechanical Engineering from the University of Maryland, College Park, and B.Tech. in Manufacturing Science and Engineering from the Indian Institute of Technology, Kharagpur. Dr. Banerjee has received several honors including the 2019 Amazon Research Award, the 2012 Most Cited Paper Award from the Computer-Aided Design journal, and the 2009 Best Dissertation Award from the Department of Mechanical Engineering at the University of Maryland. He has published nearly fifty articles in peer- reviewed journals and conference proceedings, and is an Associate Editor of the Journal of Micro-Bio Robotics and IEEE Robotics and Automation Letters. His research interests include digital manufacturing, predictive and prescriptive analytics, and autonomous robotics.
This talk was recorded on May 12, 2020 as part of the University of Washington Mechanical Engineering Graduate Seminar (ME 520). Learn more at me.uw.edu