Learning Soccer Juggling Skills with Layer-wise Mixture-of-Experts

1 code implementation • SIGGRAPH 2022 • Zhaoming Xie, Sebastian Starke, Hung Yu Ling, Michiel Van de Panne

Learning physics-based character controllers that can successfully integrate diverse motor skills using a single policy remains a challenging problem.

Humanoid Control Imitation Learning +1

Learning to Brachiate via Simplified Model Imitation

1 code implementation • 8 May 2022 • Daniele Reda, Hung Yu Ling, Michiel Van de Panne

Key to our method is the use of a simplified model, a point mass with a virtual arm, for which we first learn a policy that can brachiate across handhold sequences with a prescribed order.

Humanoid Control Motion Synthesis +1

Character Controllers Using Motion VAEs

1 code implementation • 26 Mar 2021 • Hung Yu Ling, Fabio Zinno, George Cheng, Michiel Van de Panne

A fundamental problem in computer animation is that of realizing purposeful and realistic human movement given a sufficiently-rich set of motion capture clips.

Continuous Control Motion Synthesis +2

ALLSTEPS: Curriculum-driven Learning of Stepping Stone Skills

1 code implementation • 9 May 2020 • Zhaoming Xie, Hung Yu Ling, Nam Hee Kim, Michiel Van de Panne

Humans are highly adept at walking in environments with foot placement constraints, including stepping-stone scenarios where the footstep locations are fully constrained.

reinforcement-learning Reinforcement Learning (RL)

On Learning Symmetric Locomotion

1 code implementation • Proceedings of ACM SIGGRAPH Motion, Interaction, and Games (MIG 2019) 2019 • Farzad Abdolhosseini, Hung Yu Ling, Zhaoming Xie, Xue Bin Peng, Michiel Van de Panne

We describe, compare, and evaluate four practical methods for encouraging motion symmetry.