from    
to    
search  

 


Numerical Modeling of Plasmas in Fluid and Kinetic Regimes
Interpretable Quantum Advantage in Neural Sequence Learning
The Awesome Power of Biochemistry in Neuroscience
清华大学材料科学与工程研究院《材料科学论坛》:基于三维微纳结构的仿生光电与传感器...
报告题目:
Bring AI into the Physical World – Exploring Robotic Cooking
 报告人:
孙宇
University of South Florida 副教授
报告时间:
2018-07-04 10:00
报告地点:
信息楼(FIT)1-515会议室
主办单位:
信息学院
  简介:

讲演摘要

Computers have tremendous learning capability and have demonstrated superior intelligence in many domains. This talk will describe our research effort to bring computer intelligence into the physical world so that robots could perform physically interactive manipulation tasks.
Our approach first gives robots the ability to learn manipulation skills by “watching” online instructional videos. After “watching” over 200 instructional videos, a functional object-oriented network (FOON) is constructed to represent the observed manipulation skills. Using the network, robots can take a high-level task command such as “I want BBQ Ribs for dinner,” decipher the task goal, seek the correct objects to operate on, and then generate and execute a sequence of manipulation motions that can deal with physical interactions in a new condition. The interactive manipulation motions are learned from human demonstration using deep Recurrent Neural Networks. To best facilitate manipulation motions in the physical world, we also developed new grasping strategies for robots to hold objects with a firm grasp to withstand the disturbance during physical interactions.
 
演讲者简介
 
Dr. Yu Sun is an Associate Professor and the Associate Chair of Graduate Affairs in the Department of Computer Science and Engineering at the University of South Florida. He founded the IEEE RAS Technical Committee on Robotic Hands, Grasping, and Co-Chair the IEEE-RAS Member Service Committee and the IEEE-RAS Competition Committee. He is an Associate Editor of the IEEE Transactions on Robotics.
 
Dr. Yu Sun received his Ph.D. degree in Computer Science from the University of Utah in 2007, and his B.S. and M.S. degrees in Electrical Engineering from Dalian University of Technology in 1997 and 2000 respectively. He was a Postdoctoral Associate in the School of Computing at the University of Utah from May 2008 to May 2009 and a Postdoctoral Associate at Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA from Dec. 2007 to May 2008.
 
His research interests include intelligent systems, robotics, cyber-physical systems, computer vision, deep learning, virtual reality, and medical applications. He has edited two book, published about 80 technical papers and book chapters, and holds nine US patents and four provisional patents. He has served as a panelist and reviewer for U.S. National Science Foundation and French National Research Agency. His research works have been reported on the Discovery Science Channel, Bay News 9, Fox News, Univision (Spanish), and other medias.
今日相关信息
Generation, transport and detection o...
全球变化科学紫荆论坛(第257期): The...
 
同类别相关信息
Recent progress and prospects on bu...
"AI For Good" Isn't Good ...
AIR学术工作坊第5期|智能新药研发学术...
电磁成像方法与应用技术
Single-Protein Electronics
学术活动