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. For a supplementary video link, see this https URL . |
Year | Venue | Field |
---|---|---|
2018 | international conference on learning representations | Control theory,Computer science,Motor control,Motor controller,Human–computer interaction,RGB color model,Artificial intelligence,Proprioception,Perception,Machine learning,Visual perception |
DocType | Volume | Citations |
Journal | abs/1811.09656 | 6 |
PageRank | References | Authors |
0.41 | 30 | 8 |
Name | Order | Citations | PageRank |
---|---|---|---|
Josh S. Merel | 1 | 143 | 11.34 |
Arun Ahuja | 2 | 72 | 7.45 |
Vu Pham | 3 | 15 | 2.28 |
Saran Tunyasuvunakool | 4 | 10 | 2.14 |
Siqi Liu | 5 | 55 | 4.94 |
Dhruva Tirumala Bukkapatnam | 6 | 6 | 0.41 |
Nicolas Heess | 7 | 1762 | 94.77 |
Greg Wayne | 8 | 592 | 31.86 |