Michiel van de Panne
B.A.Sc., University of Calgary (1987); M.A.Sc., University of Toronto (1989); Ph.D., University of Toronto (1994); Assistant Professor, University of Toronto (1993-1998); Associate Professor, University of Toronto (1998-2001); Visiting Professor, University of British Columbia (1999-2001); Motion Playground Inc. (2000-2004 ); Associate Professor, UBC (2001-2008 ); Full Professor, UBC (2008-)
My research interests that span reinforcement learning, control, physics-based simulation of human and animal movement, robotics, computer animation, and computer graphics. How can we develop models of human and animal movement that match their skills and agility in real life? What is the best way to learn new motor skills? How can we develop reinforcement learning and planning methods that transfer well to the real world, as opposed to being limited to simulations?
ALLSTEPS: Curriculum-driven Learning of Stepping Stone Skills.
Zhaoming Xie, Hung Yu Ling, Nam Hee Kim, and Michiel van de Panne.
ACM/EG Symposium on Computer Animation, 2020.
Character Controllers using Motion VAEs.
Hung Yu Ling, Fabio Zinno, George Cheng, Michiel van de Panne
ACM Transactions on Graphics (Proc. SIGGRAPH 2020)
DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills
Xue Bin Peng, Pieter Abbeel, Sergey Levine, Michiel van de Panne
ACM Transactions on Graphics (Proc. SIGGRAPH 2018)
DeepLoco: Dynamic Locomotion Skills Using Hierarchical Deep Reinforcement Learning
Xue Bin Peng, Glen Berseth, KangKang Yin, Michiel van de Panne
ACM Transactions on Graphics (Proc. SIGGRAPH 2017)