(SIGGRAPH 2016) Terrain-Adaptive Locomotion Skills Using Deep Reinforcement Learning Michiel van de Panne 2016-05-03 | SIGGRAPH 2016 video for the related paper. The full paper can be found at http://www.cs.ubc.ca/~van/papers/2016-TOG-deepRL/index.html
Learning to Steer (ICRA 2005) Michiel van de Panne 2021-09-28 | "Learning to Steer on Winding Tracks Using Semi-Parametric Control Policies.", ICRA 2005: International Conference on Robotics and AutomationKen Alton, Michiel van de Panne. University of British Columbia.cs.ubc.ca/~van/papers/2005-icra-steering.pdf
Learning to Steer and Back-up Michiel van de Panne 2021-09-28 | Ken Alton and Michiel van de Panne"Learning to Steer on Winding Tracks Using Semi-Parametric Control Policies.", ICRA 2005, cs.ubc.ca/~van/papers/2005-icra-steering.pdf
Flexible Motion Optimization with Modulated Assistive Forces Michiel van de Panne 2021-09-06 | Video supplementary material for:"Flexible Motion Optimization with Modulated Assistive Forces"Nam Hee Kim, Hung Yu Ling, Zhaoming Xie and Michiel van de PanneSymposium on Computer Animation, 2021cs.ubc.ca/~van/papers/2021-SCA-modassist/index.html
Interactive Control for Physically-based Animation (SIGGRAPH 2000 paper) Michiel van de Panne 2020-11-14 | Video that demonstrates some of the results the SIGGRAPH 2000 paper:J. F. Laszlo, M. van de Panne, and E. Fiume. Interactive Control For Physically-Based Animation. Proceedings of ACM SIGGRAPH 2000, p. 201-208.
Learning to Locomote: Understanding How Environment Design Matters for Deep Reinforcement Learning Michiel van de Panne 2020-10-17 | Video to accompany MIG 2020 paper
SCA 2020: ALLSTEPS Curriculum-driven Learning of Stepping Stone Skills (full talk) Michiel van de Panne 2020-09-28 | Full talk for the paper "ALLSTEPS: Curriculum-driven Learning of Stepping Stone Skills", ACM/EG Symposium on Computer Animation (SCA 2020). Project page: cs.ubc.ca/~van/papers/2020-allsteps/index.htmlSpecial thanks to STORROR Pro Parkour Team (storror.com) and Jesse Chui (songsforcinema.com)
SCA 2020: ALLSTEPS Curriculum-driven Learning of Stepping Stone Skills (3 minute overview) Michiel van de Panne 2020-09-28 | A short overview of the paper "ALLSTEPS: Curriculum-driven Learning of Stepping Stone Skills", ACM/EG Symposium on Computer Animation (SCA 2020). Project page: cs.ubc.ca/~van/papers/2020-allsteps/index.htmlSpecial thanks to STORROR Pro Parkour Team (storror.com), Jesse Chui (songsforcinema.com), and the Proclaimers (excerpts from "I'm Gonna Be (500 miles) the.proclaimers.co.uk/).
[SIGGRAPH 2020] Character Controllers using Motion VAEs Michiel van de Panne 2020-06-26 | Video for the related SIGGRAPH 2020 paperA fundamental problem in computer animation is that of realizing purposeful and realistic human movement given a sufficiently-rich set of motion capture clips. We learn data-driven generative models of human movement using autoregressive conditional variational autoencoders, or Motion VAEs. The latent variables of the learned autoencoder define the action space for the movement and thereby govern its evolution over time. Planning or control algorithms can then use this action space to generate desired motions. In particular, we use deep reinforcement learning to learn controllers that achieve goal-directed movements. We demonstrate the effectiveness of the approach on multiple tasks. We further evaluate system-design choices and describe the current limitations of Motion VAEs.
ALLSTEPS: Curriculum-driven Learning of Stepping Stone skills Michiel van de Panne 2020-05-11 | This video accompanies the paper of the same title.Curriculum-driven deep reinforcement learning is used to learn control policies for physics-based characters, enabling them to walk across stepping stone sequences and variable terrain. The control policy perceives the upcoming two desired stepping locations.
Synthesis of Constrained Walking Skills (2008 SIGGRAPH ASIA) Michiel van de Panne 2019-10-21 | Video supplementary materials for the 2008 SIGGRAPH ASIA papercs.ubc.ca/~van/papers/2008-TOG-constrainedWalking/index.html
Feedback Control for Cassie with Deep Reinforcement Learning Michiel van de Panne 2018-03-19 | video to accompany paper: arxiv.org/abs/1803.05580
Progressive Reinforcement Learning with Distillation for Multi-Skilled Motion Control Michiel van de Panne 2018-03-04 | video accompanying ICLR 2018 paper:cs.ubc.ca/~van/papers/2018-ICLR-distill/2018-ICLR-distill.pdf
Motion Doodles (SIGGRAPH 2004) Michiel van de Panne 2018-03-04 | "Motion Doodles: An Interface for Sketching Character Motion"SIGGRAPH 2004. cs.ubc.ca/~van/papers/2004-siggraph-motiondoodles.pdf
2005 sbim sketch3d Michiel van de Panne 2018-03-04 | video accompanything paper: "Sketch-based Modeling of Parameterized Objects", 2nd Eurographics Workshop on Sketch-Based Interfaces and Modeling, 2005. cs.ubc.ca/~van/papers/2005-sbim-sketch3d.pdf
SIGGRAPH 2017 DeepLoco (supplemental video) Michiel van de Panne 2017-04-28 | Supplemental video accompanying the SIGGRAPH 2017 paper:"DeepLoco: Dynamic Locomotion Skills Using Hierarchical Deep Reinforcement Learning".Project page: http://www.cs.ubc.ca/~van/papers/2017-TOG-deepLoco/index.html
SIGGRAPH 2017: DeepLoco paper (main video) Michiel van de Panne 2017-04-28 | Main video accompanying the SIGGRAPH 2017 paper:"DeepLoco: Dynamic Locomotion Skills Using Hierarchical Deep Reinforcement Learning".Project page: http://www.cs.ubc.ca/~van/papers/2017-TOG-deepLoco/index.html
[SIGGRAPH 2017] DeepLoco: Highlights Michiel van de Panne 2017-04-28 | Highlights video for the SIGGRAPH 2017 paper.Project page: http://www.cs.ubc.ca/~van/papers/2017-TOG-deepLoco/index.htmlMusic provided by NoCopyrightSoundsAlan Walker - Fade: youtube.com/watch?v=bM7SZ5SBzyYAlan Walker: www.youtube.com/user/DjWalkzz
Learning Locomotion Skills using DeepRL: Does the Choice of Action Space Matter? Michiel van de Panne 2016-11-01 | This video accompanies the ICLR 2017 paper submission:arxiv.org/abs/1611.01055"Learning Locomotion Skills Using DeepRL: Does the Choice of Action Space Matter"?It compares the use of torques, muscle activations, joint target angles, and joint target velocities for control of physics-based locomotion.
Task-based Locomotion (SIGGRAPH 2016) Michiel van de Panne 2016-05-04 | SIGGRAPH 2016 video for the related paper, see: http://www.cs.ubc.ca/~van/papers/2016-TOG-taskBasedLocomotion/index.html
Guided Learning of Control Graphs for Physics-Based Characters (supplemental video) Michiel van de Panne 2016-05-04 | Supplemental video, illustrating the motions with a more detailed character model.
Guided Learning of Control Graphs for Physics-based Characters (SIGGRAPH 2016) Michiel van de Panne 2016-05-04 | SIGGRAPH 2016 video for the related paper. The full paper can be found at http://www.cs.ubc.ca/~van/papers/2016-TOG-controlGraphs/index.html
Terrain-Adaptive Locomotion Using Deep Reinforcement Learning (SIGGRAPH 2016), supplemental video Michiel van de Panne 2016-05-03 | Second video associated with the SIGGRAPH 2016 paper. For the paper, see the project page at: http://www.cs.ubc.ca/~van/papers/2016-TOG-deepRL/index.html
Learning Reduced-Order Feedback Policies for Motion Skills Michiel van de Panne 2015-06-25 | Video that accompanies the paper "Learning Reduced-Order Feedback Policies for Motion Skills", Symposium on Computer Animation 2015.
Dynamic Terrain Traversal Skills Using Reinforcement Learning (Part 2) Michiel van de Panne 2015-05-05 | Part 2 of video that accompanies the SIGGRAPH 2015 paper:http://www.cs.ubc.ca/~van/papers/2015-TOG-terrainRL/index.html
Dynamic Terrain Traversal Skills Using Reinforcement Learning (part 1) Michiel van de Panne 2015-05-05 | Part 1 of the video that accompanies the SIGGRAPH 2015 paper:http://www.cs.ubc.ca/~van/papers/2015-TOG-terrainRL/index.html
Dynamic Animation Synthesis with Free-Form Deformations Michiel van de Panne 2013-09-04 | Dynamic Animation Synthesis with Free-Form Deformations
