Hierarchical Visuomotor Control of Humanoids
Josh Merel, Arun Ahuja, Vu Pham, Saran Tunyasuvunakool, Siqi Liu, Dhruva Tirumala, Nicolas Heess, Greg Wayne
Abstract
We aim to build complex humanoid agents that integrate perception, motor control, and memory. In this work, we partly factor this problem into low-level motor control from proprioception and high-level coordination of the low-level skills informed by vision. We develop an architecture capable of surprisingly flexible, task-directed motor control of a relatively high-DoF humanoid body by combining pre-training of low-level motor controllers with a high-level, task-focused controller that switches among low-level sub-policies. The resulting system is able to control a physically-simulated humanoid body to solve tasks that require coupling visual perception from an unstabilized egocentric RGB camera during locomotion in the environment. Supplementary video link: https://youtu.be/fBoir7PNxPk
BibTeX
@inproceedings{
merel2018hierarchical,
title={Hierarchical Visuomotor Control of Humanoids},
author={Josh Merel and Arun Ahuja and Vu Pham and Saran Tunyasuvunakool and Siqi Liu and Dhruva Tirumala and Nicolas Heess and Greg Wayne},
booktitle={International Conference on Learning Representations},
year={2019},
url={https://openreview.net/forum?id=BJfYvo09Y7},
}