Maryam Kamgarpour

CIS – “Get to know your neighbors” Seminar Series

“Learning for safety and coordination in uncertain dynamical systems”
Prof. Maryam Kamgarpour, Tenure Track Assistant Professor, Systems Control And Multiagent Optimization Research and Head of Sycamore Lab

Monday, June 20, 2022 3:15 – 4:15pm | Hybrid

 Learning algorithms for sequential decision-making under uncertainty have been successful in challenging tasks such as games (chess, Atari) or online recommendation systems. Meanwhile, their applications to safety-critical systems such as human robot interactions remain limited. I will discuss my group’s work on addressing two challenges towards enabling learning systems for real-world dynamical system applications: safe learning and multi-agent learning. I will illustrate our theory and algorithms with applications arising in robotics and autonomous driving.

Maryam Kamgarpour holds a Doctor of Philosophy in Engineering from the University of California, Berkeley and a Bachelor of Applied Science from University of Waterloo, Canada. Her research is on safe decision-making and control under uncertainty, game theory and mechanism design, mixed integer and stochastic optimization and control. Her theoretical research is motivated by control challenges arising in intelligent transportation networks, robotics, power grid systems and healthcare. She is the recipient of NASA High Potential Individual Award, NASA Excellence in Publication Award, and the European Union (ERC) Starting Grant.