An Engineer's Foray into Topological Learning: Addressing Challenges in Mobile Robot Perception and Mapping

Lecture / Panel
For NYU Community

Ashis Banerjee


Ashis G. Banerjee
University of Washington


"An Engineer's Foray into Topological Learning: Addressing Challenges in Mobile Robot Perception and Mapping"


Topological learning (TL), referring to a synergy of computational topology and machine learning, has recently emerged as an effective pattern recognition framework for noisy, high-dimensional problems. The recognition happens by first identifying the topological structures that encode the shape and connectedness information among the observations (sample), and then characterizing the structures based on their relative persistence over a wide range of spatial and/or temporal scales. In this talk, I discuss successful demonstrations of TL for challenging mobile robot perception and mapping problems in unseen environments. Our novel adaptation of TL recognizes occluded objects and anomalies significantly more accurately than other state-of-the-art shape or learning-based methods without requiring real-world training samples. I conclude by pointing out future research directions for active multi-robot coordination.

About Speaker 

Ashis G. Banerjee is an Associate Professor of Industrial & Systems Engineering and Mechanical Engineering at the University of Washington (UW). Prior to joining UW, he was a Research Scientist at GE Global Research and a Postdoctoral Associate at MIT. He obtained his Ph.D. and M.S. in Mechanical Engineering from the University of Maryland (UMD), College Park, and B.Tech. in Manufacturing Science and Engineering from IIT Kharagpur. Dr. Banerjee has authored sixty peer-reviewed publications on a broad range of research topics spanning AI-enabled autonomous robotics, machine learning-driven decision making, and smart manufacturing. His research has been well supported by a large number of organizations, including the DOE, MxD, NAVSEA, ONR, WA State, Amazon Robotics, Boeing, and PACCAR. He has received several honors including the 2019 Amazon Research Award, 2012 Most Cited Paper Award from the Computer-Aided Design journal, and 2009 Best Mechanical Engineering Dissertation Award at UMD. He serves as a Senior Editor of the IEEE Robotics and Automation Letters, and an Associate Editor of the ASME Journal of Mechanisms and Robotics and the Springer Journal of Micro-Bio Robotics.