February 13, 2019
This talk is open to MIE faculty and graduate students. Registration is not required.
Nowadays, the complexity in the design of robotic systems increases enormously due to the fact that human beings desire a higher level of intelligence and autonomy. Additionally, it is important that the developed systems must be capable of autonomously adapting to the variations in the operating environment while maintaining the overall objective to accomplish tasks even in highly uncertain and unstructured environments. Such robotic systems must display the ability to learn from experience, adapt themselves to the changing environment and seamlessly integrate information to-and-from humans.
In this talk, Erkan Kayacan will develop learning and adaptation capabilities for field robots operating in increasingly unstructured, uncertain and changing environments, and over long periods of time to facilitate reliable, long-term robot applications in the real environment. Dr. Kayacan will discuss five examples for the key enablers of this technology: (i) Robust and accurate navigation and control under leafy canopies where GPS is ineffective with LIDARs and vision fused with Learning-based Nonlinear Model Predictive Control (NMPC) in agricultural fields, (ii) Computationally efficient solution methods for NMPC and Nonlinear Moving Horizon Estimation methods, (iii) Low-cost onboard phenotyping through deep-learning enabled machine vision, and (iv) Multi-objective control for the string stability of self-driving cars and (v) Learning-based control for reconfigurable autonomous vessels.
Erkan Kayacan received the B.Sc. and M.Sc. degrees in mechanical engineering from Istanbul Technical University, Turkey, in 2008 and 2010, respectively. In December 2014, he received the Ph.D. degree at University of Leuven (KU Leuven), Belgium. During his PhD, he held a visitor PhD scholar position at Boston University, USA. After his Ph.D., he became a Postdoctoral Researcher with Delft Center for Systems and Control, Delft University of Technology, The Netherlands and Distributed Autonomous Systems Laboratory, University of Illinois at Urbana-Champaign, Urbana, IL, USA. He is currently a Postdoctoral Associate with Computer Science & Artificial Intelligence Laboratory and Senseable City Laboratory, Massachusetts Institute of Technology, Boston, MA, USA.
His research interests center around real-time optimization-based control and estimation methods, nonlinear control, and machine learning, with special emphasis on foundational theory and experimental realization on robotic and autonomous systems.
Dr. Kayacan is a recipient of the Best Systems Paper Award at Robotics: Science and Systems (RSS) in 2018.