The Role of Domain Randomization in Training Diffusion Policies for Whole-Body Humanoid Control

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kaidanov, Oleg, Al-Hafez, Firas, Suvari, Yusuf, Belousov, Boris, Peters, Jan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909376144474112
author Kaidanov, Oleg
Al-Hafez, Firas
Suvari, Yusuf
Belousov, Boris
Peters, Jan
author_facet Kaidanov, Oleg
Al-Hafez, Firas
Suvari, Yusuf
Belousov, Boris
Peters, Jan
contents Humanoids have the potential to be the ideal embodiment in environments designed for humans. Thanks to the structural similarity to the human body, they benefit from rich sources of demonstration data, e.g., collected via teleoperation, motion capture, or even using videos of humans performing tasks. However, distilling a policy from demonstrations is still a challenging problem. While Diffusion Policies (DPs) have shown impressive results in robotic manipulation, their applicability to locomotion and humanoid control remains underexplored. In this paper, we investigate how dataset diversity and size affect the performance of DPs for humanoid whole-body control. In a simulated IsaacGym environment, we generate synthetic demonstrations by training Adversarial Motion Prior (AMP) agents under various Domain Randomization (DR) conditions, and we compare DPs fitted to datasets of different size and diversity. Our findings show that, although DPs can achieve stable walking behavior, successful training of locomotion policies requires significantly larger and more diverse datasets compared to manipulation tasks, even in simple scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2411_01349
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle The Role of Domain Randomization in Training Diffusion Policies for Whole-Body Humanoid Control
Kaidanov, Oleg
Al-Hafez, Firas
Suvari, Yusuf
Belousov, Boris
Peters, Jan
Robotics
Machine Learning
Humanoids have the potential to be the ideal embodiment in environments designed for humans. Thanks to the structural similarity to the human body, they benefit from rich sources of demonstration data, e.g., collected via teleoperation, motion capture, or even using videos of humans performing tasks. However, distilling a policy from demonstrations is still a challenging problem. While Diffusion Policies (DPs) have shown impressive results in robotic manipulation, their applicability to locomotion and humanoid control remains underexplored. In this paper, we investigate how dataset diversity and size affect the performance of DPs for humanoid whole-body control. In a simulated IsaacGym environment, we generate synthetic demonstrations by training Adversarial Motion Prior (AMP) agents under various Domain Randomization (DR) conditions, and we compare DPs fitted to datasets of different size and diversity. Our findings show that, although DPs can achieve stable walking behavior, successful training of locomotion policies requires significantly larger and more diverse datasets compared to manipulation tasks, even in simple scenarios.
title The Role of Domain Randomization in Training Diffusion Policies for Whole-Body Humanoid Control
topic Robotics
Machine Learning
url https://arxiv.org/abs/2411.01349