Offline Adaptation of Quadruped Locomotion using Diffusion Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: O'Mahoney, Reece, Mitchell, Alexander L., Yu, Wanming, Posner, Ingmar, Havoutis, Ioannis
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909635183640576
author O'Mahoney, Reece
Mitchell, Alexander L.
Yu, Wanming
Posner, Ingmar
Havoutis, Ioannis
author_facet O'Mahoney, Reece
Mitchell, Alexander L.
Yu, Wanming
Posner, Ingmar
Havoutis, Ioannis
contents We present a diffusion-based approach to quadrupedal locomotion that simultaneously addresses the limitations of learning and interpolating between multiple skills and of (modes) offline adapting to new locomotion behaviours after training. This is the first framework to apply classifier-free guided diffusion to quadruped locomotion and demonstrate its efficacy by extracting goal-conditioned behaviour from an originally unlabelled dataset. We show that these capabilities are compatible with a multi-skill policy and can be applied with little modification and minimal compute overhead, i.e., running entirely on the robots onboard CPU. We verify the validity of our approach with hardware experiments on the ANYmal quadruped platform.
format Preprint
id arxiv_https___arxiv_org_abs_2411_08832
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Offline Adaptation of Quadruped Locomotion using Diffusion Models
O'Mahoney, Reece
Mitchell, Alexander L.
Yu, Wanming
Posner, Ingmar
Havoutis, Ioannis
Robotics
Artificial Intelligence
Machine Learning
We present a diffusion-based approach to quadrupedal locomotion that simultaneously addresses the limitations of learning and interpolating between multiple skills and of (modes) offline adapting to new locomotion behaviours after training. This is the first framework to apply classifier-free guided diffusion to quadruped locomotion and demonstrate its efficacy by extracting goal-conditioned behaviour from an originally unlabelled dataset. We show that these capabilities are compatible with a multi-skill policy and can be applied with little modification and minimal compute overhead, i.e., running entirely on the robots onboard CPU. We verify the validity of our approach with hardware experiments on the ANYmal quadruped platform.
title Offline Adaptation of Quadruped Locomotion using Diffusion Models
topic Robotics
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2411.08832