You're invited to attend the talk

"Smart Mechanics for Intelligent Machines"

by

Prof. Anirban Mazumdar

Assistant Professor
Woodruff School of Mechanical Engineering
Georgia Institute of Technology

Thursday, September 19
3 - 4 PM
Guggenheim 442

About the Talk: 
Mobile robots have the potential to revolutionize a range of important aerial, terrestrial, and aquatic missions.  While great advances have been made in autonomy and intelligent algorithms, the connection between physical form and intelligent behavior remains relatively unexplored.  The design of intelligent systems has often considered the “brains” and “muscles” as separate components that are developed independently of each other.  This can result in unreliable performance or conservative behaviors that fall far short of natural organisms.

Our team at Georgia Tech seeks to create autonomous systems with physical properties that are tailored to maximize the performance of intelligent algorithms.  Specifically, we are exploring how optimized geometry, adaptable shape, controllable impedance, and reflexive behaviors can inform new control and autonomy methods.  We call our approach “smart mechanics.”  These principles can be incorporated into existing physical systems as peripheral modifications or used to generate “clean-sheet” designs.  As a result, new levels of maneuverability, energy efficiency, and performance can be achieved. In this talk, I will discuss some of our recent work on underwater maneuverability, legged and multimodal locomotion, and aerial manipulation.

About the Speaker: 
Anirban Mazumdar is an Assistant Professor at the George W. Woodruff School of Mechanical Engineering at the Georgia Institute of Technology.  His research examines the connection between intelligent algorithms and physical behaviors.  He received his B.S., M.S., and Ph.D. degrees in Mechanical Engineering from the Massachusetts Institute of Technology in 2007, 2009, and 2013 respectively.  Prior to joining Georgia Tech, he was a Postdoctoral Appointee in the High Consequence Automation and Robotics group at Sandia National Laboratories in Albuquerque, NM.

Dr. Mazumdar’s research examines principles for enhanced agility, versatility, and energy efficiency of mobile systems.  In particular, Dr. Mazumdar is interested in how electromechanical design, advanced feedback control, and intelligent behavior can be explored together in order to achieve superior performance.  An overarching theme of Dr. Mazumdar’s work is the idea of dynamic configurability: the capability of a mobile system to change its hardware configurations or software algorithms.  This ability can enable mobile systems to maximize their performance even in heterogeneous or dynamic environments.