2016 Poster Sessions : Artificial Intelligence & Physical Simulation

Student Name : Michael Bao, Matthew Cong, Jenny Jin
Advisor : Ron Fedkiw
Research Areas: Graphics/HCI
We are currently exploring a new paradigm wherein traditional AI and learning schemes are not used to train the typical phenotypical models, but instead are used to train and control an underlying reduced manifold system that in turn drives a physics based simulation in order to achieve the desired result. For example, consider the problem of determining body shapes for humans. Instead of using traditional learning approaches to train skin shapes based on joint parameters, we instead use the AI to train an underlying anatomical model that in turn drives the shape of the overlaid skin vertices. This closed loop interplay with the physical simulation reduces the size and scope of the learning problem to not only make it tractable, but also to impose physical constraints reducing it to a sub-manifold that alleviates some issues with the uncanny valley such as volume preservation. (This is just one example of how embedding physical simulation into learning enables better tractability for a large variety of problems.)

Michael Bao
Michael Bao is currently a second year Ph.D. candidate at Stanford University under the advisement of Professor Ronald Fedkiw. His current research interests are computer graphics and physically-based simulation and animation for use in visual effects and video games. He graduated from the University of California, Berkeley in May 2014 with a Bachelor of Science in Electrical Engineering and Computer Sciences. He has also worked with Professor Adrien Treuille and Professor Rhiju Das on EteRNA as well as EteRNA's collaboration with NOVA to allow students around the country to synthesize RNA. Additionally, he was the Lead Programmer on Chivalry: Medieval Warfare which has gone on to sell more than two million copies.

Jenny Jin
Jenny Jin is currently a second year PhD candidate in Professor Ron Fedkiw's group at Stanford University in the Computer Science Department. Her main interests are in computer graphics and physically-based simulations. She is also interested in computer vision, and would like to explore opportunities to do interdisciplinary research in these two fields. Prior to Stanford, Jenny studied Physics at Princeton University.

Matthew Cong
Matthew Cong is currently a fifth-year Ph.D. candidate in the Department of Computer Science at Stanford University advised by Professor Ron Fedkiw. He is fortunate to be supported by a National Defense Science and Engineering Graduate Fellowship. He is also currently consulting at Industrial Light & Magic.

Ronald Fedkiw
Fedkiw received his Ph.D. in Mathematics from UCLA in 1996 and did postdoctoral studies both at UCLA in Mathematics and at Caltech in Aeronautics before joining the Stanford Computer Science Department. He was awarded an Academy Award from The Academy of Motion Picture Arts and Sciences (twice: 2008 and 2015), the National Academy of Science Award for Initiatives in Research, a Packard Foundation Fellowship, a Presidential Early Career Award for Scientists and Engineers (PECASE), a Sloan Research Fellowship, the ACM Siggraph Significant New Researcher Award, an Office of Naval Research Young Investigator Program Award (ONR YIP), the Okawa Foundation Research Grant, the Robert Bosch Faculty Scholarship, the Robert N. Noyce Family Faculty Scholarship, two distinguished teaching awards, etc. Currently he is on the editorial board of the Journal of Computational Physics, and he participates in the reviewing process of a number of journals and funding agencies. He has published over 110 research papers in computational physics, computer graphics and vision, as well as a book on level set methods - and is listed on ISIHighlyCited. Since joining Stanford, he has graduated 29 Ph.D. students. For the past 15 years, he has been a consultant with Industrial Light + Magic. He received screen credits for his work on "Terminator 3: Rise of the Machines", "Star Wars: Episode III - Revenge of the Sith", "Poseidon" and "Evan Almighty".