세미나/포럼
[세미나/포럼] [2023.12.08(금)] AI Convergence Network & Artificial Intelligence Colloquium 개최 안내
- 세미나/포럼
- 교내
- 김성민
- 2023-12-05
< AI Convergence Network & Artificial Intelligence Colloquium > ▶ When : 2023년 12월 8일(금), 오후 3시 ▶ Where : 팔달관 407호 ▶ Speaker : Prof. Steve Ko(Simon Fraser University, Canada) ▶ Title : Offloading Visual SLAM Tasks to a GPU ▶ Abstract : Visual SLAM (Simultaneous Localization and Mapping) has become an important class of algorithms used in many applications such as robot navigation and augmented reality. It provides a mechanism for a mobile agent to process visual input, build a map of the surroundings, and understand where the agent is and how the agent is moving. However, visual SLAM algorithms are known to be resource-intensive and require powerful machines to run, making it difficult to run on an everyday device. To improve this status quo, we are working on offloading expensive SLAM tasks to a GPU. We are comprehensively examining various components within SLAM and asking the question of how to divide the work between the CPU and the GPU in the most efficient way. This talk will describe our effort. ▶ Bio : Steve Ko is an Associate Professor in the School of Computing Science at Simon Fraser University. His current research interest is improving the reliability and security of mobile systems by developing techniques at the intersection of mobile systems and software engineering. He received a B.S. degree in Mathematics from Yonsei University, an MS in Computer Science and Engineering from Seoul National University, and a PhD in Computer Science from the University of Illinois at Urbana-Champaign. He worked as a postdoc in the Department of Computer Science at Princeton University. Until 2020, He was with the Department of Computer Science and Engineering at the University at Buffalo, The State University of New York as an Associate Professor. ▶ Host : 소프트웨어학과 고영배 교수(youngko@ajou.ac.kr)