Thu, May 24, 2018 @ 02:00 PM - 03:00 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Mohamadreza Ahmadi, University of Texas at Austin
Talk Title: Addressing Challenges in Autonomy: Lessons from Information and Control Theories
Series: Joint CSC@USC/CommNetS-MHI Seminar Series
Abstract: We live in the prolific age of artificial intelligence and machine learning. These automation technologies underlie real systems (e.g. robots, and self-driving vehicles), and virtual systems (e.g. financial, and inventory management). The problem is many of these autonomous systems have become so intricate and black-box that we hit a complexity roadblock. For example, it can be difficult to tell why a classifier or a recommendation engine based on machine learning works. Moreover, when the algorithms work, how can we quantify their limitations, safety, privacy and performance with guarantees. In this talk, I borrow notions from control and information theories to address two challenges in autonomy. The first one is motivated by the Mars 2020 project and is concerned with navigation of an autonomous agent in an uncertain environment (modeled by a Markov decision process) subject to communication and sensing limitations (in terms of transfer entropy), and high-level mission specification (characterized by linear temporal logic formulae). The second one is concerned with belief verification in autonomous systems (represented by a partially observable Markov decision process) with applications in privacy verification of autonomous systems (e.g. a robot) operating on shared infrastructure, and machine teaching.
Biography: Mohamadreza Ahmadi joined the Institute for Computational Engineering and Sciences (ICES) at the University of Texas at Austin as a postdoctoral scholar in fall 2016, where he is currently a Research Associate. He received his DPhil (Ph.D.) in Engineering (Aeronautics) from the University of Oxford in fall 2016 as a Clarendon Scholar. From fall 2014 to spring 2016, he was a lecturer in engineering at Worcester College, University of Oxford. His current research is on applying tools from control theory to design autonomous systems with privacy, safety, and performance guarantees.
Host: Mihailo Jovanovic, email@example.com
Audiences: Everyone Is Invited
Contact: Gerrielyn Ramos