Learning to Sit: Synthesizing Human-Chair Interactions via Hierarchical Control

Yu-Wei Chao, Jimei Yang, Weifeng Chen, Jia Deng

Keywords: physics-based motion synthesis, hierarchical reinforcement learning, motion capture data

TL;DR: Synthesizing human motions on interactive tasks using mocap data and hierarchical RL.

Abstract: Recent progress on physics-based character animation has shown impressive breakthroughs on human motion synthesis, through imitating motion capture data via deep reinforcement learning. However, results have mostly been demonstrated on imitating a single distinct motion pattern, and do not generalize to interactive tasks that require flexible motion patterns due to varying human-object spatial configurations. To bridge this gap, we focus on one class of interactive tasks---sitting onto a chair. We propose a hierarchical reinforcement learning framework which relies on a collection of subtask controllers trained to imitate simple, reusable mocap motions, and a meta controller trained to execute the subtasks properly to complete the main task. We experimentally demonstrate the strength of our approach over different single level and hierarchical baselines. We also show that our approach can be applied to motion prediction given an image input. A video highlight can be found at https://youtu.be/XWU3wzz1ip8/.