SEMINAR: Improving Robot Network Awareness through Adaptable Fuzzy-based Link Quality Estimation

Mr. Christopher Lowrance, Ph.D. Candidate, CECS Dept., University of Louisville
When Feb 19, 2016
from 03:30 PM to 04:30 PM
Where Duthie Center for Engineering, Room 117
Add event to calendarvCal

The seminar is free and open to the public. A reception and social time begins at 3:00 p.m., Seminar at 3:30 p.m.

Abstract: It is often essential for robots to maintain wireless connectivity with other systems so that commands, sensor data, and other situational awareness information can be exchanged.  Unfortunately, maintaining an appropriate quality connection between these systems can be problematic.  Robot mobility combined with the attenuation and rapid dynamics associated with radio propagation can cause frequent link quality (LQ) issues such as degraded throughput, temporary disconnects, or even link failure.  In order to proactively mitigate such problems, robots must possess the capability, at the application layer, to gauge the quality of their wireless connections.  However, many of the existing approaches to higher-layer link quality (LQ) estimation lack adaptability or the framework necessary to rapidly build and sustain an accurate LQ prediction model.  Our primary contribution is the introduction of a novel technique of blending machine learning with fuzzy logic so that an adaptable, yet intuitive LQ estimator can be formed.  We also introduce a unique active learning framework for quickly constructing and maintaining an LQ prediction model with minimal sampling overhead.

Bio: Christopher Lowrance received his B.S. in electrical engineering from the Virginia Military Institute (VMI) in Lexington, Virginia and his M.S.E.E. from the George Washington University in Washington, D.C.  He is a telecommunication system engineer for the U.S. Army and a former assistant professor in the Electrical Engineering and Computer Science Department at the United States Military Academy in West Point, New York.  Currently, he is a Ph.D. Candidate in the Department of Computer Engineering and Computer Science at the University of Louisville, which is located in Louisville, Kentucky.  His primary research interests include ad hoc networks, fuzzy inference systems, and machine learning with an application emphasis on robotics.