Developing Autonomous Driving Framework
*bldg. 2 NO.102/ 16:00~
Dr. Moongu Jeon received the B.S. degree in architectural engineering from Korea University, Seoul, South Korea, in 1988, and the M.S. and Ph.D. degrees in computer science and scientific computation from the University of Minnesota, Minneapolis, MN, USA, in 1999 and 2001, respectively. As a post-graduate researcher, he worked on optimal control problems at the University of California at Santa Barbara, Santa Barbara, CA, USA, from 2001 to 2003, and then moved to the National Research Council of Canada, where he worked on the sparse representation of high-dimensional data and the image processing until 2005. In 2005, he joined the GIST, South Korea, where he is currently a full professor at the School of Electrical Engineering and Computer Science. His current research interests are in artificial intelligence/machine learning, computer vision, visual surveillance, and autonomous driving.
Since the invention of the wheel, the human race has dreamed and aimed at automating the wheel. Now we are at this point when humans’ dream and hard work are taking the form of reality. The evolution of electric vehicles, development of state-of-the-art sensors, and advances in artificial intelligence have provided us with the necessary tools to see through the dream of the autonomous vehicle. Since the prototypes are going through experimentation and testing phase, the objective is to attain a sustainable and robust autonomous vehicle. The safety and convenience is the foremost ambition of autonomous vehicle, and we can achieve this can by ameliorating architecture of autonomous vehicles. In this talk, I will give a comprehensive overview to convert an electric car into a self-driving car. We modified The KIA Soul EV to adapt to needs of the self-driving car. We will discuss the hardware aspect involving the installation and integration of the state-of-the-art sensors, and the software aspect in the context of localization, perception, planning and control. The implementation of the state-of-the-art algorithm provides the efficiency in performance and smooth maneuvering of the self-driving car in the constrained environment.