Prior to joining the University, McFall lived abroad for more than 10 years. His international experiences began with a study abroad for his entire undergraduate senior year at the Luleå University of Technology in Sweden, 50 miles south of the Arctic Circle. After graduating with his B.S. in Mechanical Engineering from Virginia Tech, his international travels continued during masters studies at MIT with an appointment at the Japan Atomic Energy Research Institute in Japan. His work there involved heat transfer in the superconducting magnet systems for the International Thermonuclear Experimental Reactor project.
Such positive international experiences led to a research fellow position at Dalarna University in Sweden after graduation from MIT with his M.S. in Mechanical Engineering. His research shifted to artificial intelligence and image/signal processing where he was involved in developing an automated winter road condition sensor using artificial neural networks to classify road condition using image and sound input data. The research fellow position at Dalarna University quickly led to a permanent faculty position in the Department of Computer Engineering and Informatics.
To help advance his career in academia, he left Dalarna University to pursue a Ph.D. in Mechanical Engineering at Georgia Tech’s European campus in Metz, France. He continued working in artificial intelligence by developing an alternative method for solving boundary value problems using artificial neural networks.
His current research focuses on autonomous vehicles, directing numerous student teams to develop sensor systems and actuation control for self-driving cars.
Industry Expertise (2)
Areas of Expertise (11)
Modular Mechatronics Component Laboratory to Support Research and Education (professional)
Awarded by Kennesaw State University Office of the Vice President for Research Pilot/Seed Grant
VEX Robotics Kits for MTRE 1000 (professional)
Awarded by Kennesaw State University Southern Polytechnic College of Engineering and Engineering Technology
KSU Strategic Internationalization Grant (professional)
Awarded by the Division of Global Affairs, Kennesaw State University
SPSU Technology Fee Grant (professional)
Awarded by University Information Technology Services
SPSU Area A Mini-Grant (professional)
Awarded by Academic Affairs
The Georgia Institute of Technology: Ph.D., Mechanical Engineering 2006
The Massachusetts Institute of Technology: M.S., Mechanical Engineering 1997
Virginia Polytechnic Institute and State University: B.S., Mechanical Engineering 1995
Media Appearances (2)
Are Atlanta Roadways Ready For An Autonomous Future? A High View To Where We’re Headed
Many of us have a certain vision of how autonomous vehicles, a smart, driverless vehicle, will look like. Whether you have your favorite sci-fi movie or the Jetsons in your mind, the technology is quickly evolving past our imagination and into the real world.
After approving regulations this past February, California is now allowing autonomous vehicles to operate on public roads without a back-up human inside ready to jump in just in case something goes awry.
“The pace of this technology is quite dramatic,” says Dr. Kevin McFall, associate professor and interim chair of mechatronics engineering in KSU’s Southern Polytechnic College of Engineering and Engineering Technology. “Ten years ago, traditional cruise control was the closest it came. For several years now, backup cameras augmented with the vehicle’s path, automatic obstacle detection and braking, parking assist, etc. have become standard equipment on even non-luxury vehicles.”
“Today, fully autonomous passenger and freight vehicles are being tested in real driving conditions,” says Dr. McFall, who has been studying autonomous vehicles for the past four years. “And GM has announced the manufacture of cars without steering wheels planned to be produced next year in 2019.”
The Tradeoffs of Imbuing Self-Driving Cars with Human Morality
"I think the discussion about instinct and morality is partially driven by the visceral reaction that humans may not be driving their cars in the future," Dr. Kevin McFall, Assistant Professor in the Mechatronics Engineering Department at Kennesaw State University told Motherboard. "I imagine similar concerns surfaced when the horse was replaced with automobiles. Certainly something was lost back then without the bond to a living vehicle. But looking back I don't think anyone would second-guess that transition. To this day we still ride horses for entertainment. Perhaps some day will only drive cars for entertainment as well."
Event Appearances (6)
A Mobile Telepresence Robot: A Case Study for Assessment of a Capstone Design Course
123rd ASEE Annual Conference New Orleans, LA
Artificial Intelligence and Autonomous Vehicles
6th International Congress of Innovation and Technology nstituto Technolólogico de Soledad Atlántico, Barranquilla, Colombia
Using Visual Lane Detection to Control Steering in a Self-Driving Vehicle
EAI International Conference on Social Innovation and Community Aspects of Smart Cities Bratislava, Slovakia
Visual Lane Detection Algorithm Using the Perspective Transform
ASME Early Career Technical Conference Birmingham, AL
An Artificial Neural Network Approach for the Mass Balance of a Reactor in Steady State
SIAM Conference on Dynamical System Snowbird, UT
Comparison of the Length Factor Artificial Neural Network and Finite Element Methods for Solving Boundary Value Problems
ASME Early Career Technical Conference Atlanta, GA
Research Grants (2)
Achieving increased photovoltaic panel energy collection with cell-strings that track the sun
Environmental Protection Agency (P3 Awards Phase I)
Most photovoltaic panels are mounted on the ground or roofs at a fixed angle of tilt, resulting in sub-optimal energy collection as these panels do not always face the sun directly. Various tracking system designs increase energy collection by 29% to 40%, but generally require significant investments in materials and equipment. This project’s objective is to design a fixed-tilt photovoltaic module that utilizes the innovative concept of enclosing groups of cells that will track the sun. Such a module should substantially improve upon the amount of energy collected over a similarly-sized conventional fixed-tilt solar panel, while avoiding the costly complications associated with existing tracking panels.
Hub Development Mini-grant
BEST Robotics Inc.
Privately funded mini-grant
Recent Papers (6)
An effective lane detection algorithm employing the Hough transform and inverse perspective mapping to estimate distances in real space is utilized to send steering control commands to a self-driving vehicle. The vehicle is capable of autonomously traversing long stretches of straight road in a wide variety of conditions with the same set of algorithm design parameters. Better performance is hampered by slowly updating inputs to the steering control system.
This paper presents a methodology to estimate the stress-strain relationship of an unbound aggregate base using linear viscoelastic theory.
In this paper, software effort estimation models using Artificial Neural Network (ANN) ensembles and regression analysis are developed based on data collected from 163 software development projects. The main emphasis of the paper is in developing an effective experimental design to achieve superior effort estimation results.
Students develop a sense of community through this assignment by discussing personally relevant topics via the shared experience enabled by the social media tools Twitter and Paper.
The length factor artificial neural network (ANN) method for solving coupled systems of partial differential equations (DEs) is unique among ANN methods in that the approximate solution exactly satisfies boundary conditions (BCs) on arbitrary geometries regardless of the ANN output.Besides removing the BC constraint from the optimization process, this property allows the method to accurately solve problems with discontinuous BCs despite the continuous nature of ANNs. An automated design parameter selection process is developed to choose a single ANN from an ensemble comprising numerous combinations of design parameters and random starting weights and biases. The selection is made completely independently of the human designer by comparing the magnitude and uniformity of each approximate solution's error in satisfying the DE(s). The automated selection process successfully chooses a solution with error on the same order of magnitude as the best solution in the ensemble. The resulting approximations provide low error solutions for the three different thermal-fluid science example problems explored, including the Navier–Stokes equations.
A method for solving boundary value problems (BVPs) is introduced using artificial neural networks (ANNs) for irregular domain boundaries with mixed Dirichlet/Neumann boundary conditions (BCs). The approximate ANN solution automatically satisfies BCs at all stages of training, including before training commences. This method is simpler than other ANN methods for solving BVPs due to its unconstrained nature and because automatic satisfaction of Dirichlet BCs provides a good starting approximate solution for significant portions of the domain. Automatic satisfaction of BCs is accomplished by the introduction of an innovative length factor. Several examples of BVP solution are presented for both linear and nonlinear differential equations in two and three dimensions. Error norms in the approximate solution on the order of 10-4 to 10-5 are reported for all example problems.