"Resilient and Risk-Aware Multi-Robot Coordination In Adversarial Settings"

Location: LTS Auditorium, 8080 Greenmead Drive

Speaker:
Pratap Tokekar
Assistant Professor, Department of Computer Science and UMIACS

Abstract:
Current multi-robot systems are "brittle" since the failure of a single robot can bring the whole team down. Attacks that incapacitate robots or compromise their sensors are becoming increasingly realistic. There is a need for multi-robot decision-making algorithms that are secure and resilient to such attacks.

In this talk, I will present my group's recent work on developing multi-robot coordination algorithms that are resilient to adversarial attacks. We will use the theory of submodular optimization and leverage results from stock markets to design algorithms that are risk-aware and resilient. I will present applications of these results in target tracking, environmental monitoring, and emergency response scenarios.

Speaker Bio:
Pratap Tokekar is an assistant professor in the Department of Computer Science at the University of Maryland.

Previously, he was a postdoctoral researcher at the GRASP lab of University of Pennsylvania. Between 2015 and 2019, Tokekar was an assistant professor at the Department of Electrical and Computer Engineering at Virginia Tech.

He received his doctorate in computer science from the University of Minnesota in 2014 and a bachelor of technology degree in Electronics and Telecommunication from College of Engineering Pune, India in 2008.

Tokekar is a recipient of the NSF CISE Research Initiation Initiative award and an associate editor for the IEEE Robotics & Automation Letters and IEEE Transactions on Automation Science & Engineering.