Ph.D. Dissertation Defense: Rowland O'Flaherty

Title: A Control Theoretic Perspective on Learning in Robotics

Rowland O'Flaherty
Robotics Ph.D. Candidate
School of Electrical and Computer Engineering
College of Engineering
Georgia Institute of Technology

Date: December 7, 2015 (Monday)
Time: 3:00 PM - 5:00 PM
Location: TSRB 530

Committee:
Dr. Magnus Egerstedt (Advisor), School of Electrical and Computer
Engineering, Georgia Tech
Dr. Ayanna Howard, School of Electrical and Computer Engineering, Georgia
Tech
Dr. Patricio Vela, School of Electrical and Computer Engineering, Georgia
Tech
Dr. Jonathan Rogers, School of Mechanical Engineering, Georgia Tech
Dr. Charles Isbell, School of Interactive Computing, Georgia Tech

Abstract:

For robotic systems to continue to move towards ubiquity, robots need to be
more autonomous. More autonomy dictates that robots need to be able to make
better decisions. Control theory and machine learning are fields of
robotics that focus on the decision making process. However, each of these
fields implements decision making at different levels of abstraction and at
different time scales. Control theory defines low-level decisions at high
rates, while machine learning defines high-level decision at low rates. The
objective of this research is to integrate tools from both machine leaning
and control theory to solve higher dimensional, complex problems, and to
optimize the decision making process.

Throughout this research, multiple algorithms were created that use
concepts from both control theory and machine learning, which provide new
tools for robots to make better decisions. One algorithm enables a robot to
learn how to optimally explore an unknown space, and autonomously decide
when to explore for new information or exploit its current information.
Another algorithm enables a robot to learn how to locomote with complex
dynamics. These algorithms are evaluated both in simulation and on real
robots. The results and analysis of these experiments are presented, which
demonstrate the utility of the algorithms introduced in this work.
Additionally, a new notion of "learnability'' is introduced to define and
determine when a given dynamical system has the ability to gain knowledge
to optimize a given objective function.

Tags: