ActionFlow: Equivariant, Accurate, and Efficient Policies with Spatially Symmetric Flow Matching

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Funk, Niklas, Urain, Julen, Carvalho, Joao, Prasad, Vignesh, Chalvatzaki, Georgia, Peters, Jan
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910593238171648
author Funk, Niklas
Urain, Julen
Carvalho, Joao
Prasad, Vignesh
Chalvatzaki, Georgia
Peters, Jan
author_facet Funk, Niklas
Urain, Julen
Carvalho, Joao
Prasad, Vignesh
Chalvatzaki, Georgia
Peters, Jan
contents Spatial understanding is a critical aspect of most robotic tasks, particularly when generalization is important. Despite the impressive results of deep generative models in complex manipulation tasks, the absence of a representation that encodes intricate spatial relationships between observations and actions often limits spatial generalization, necessitating large amounts of demonstrations. To tackle this problem, we introduce a novel policy class, ActionFlow. ActionFlow integrates spatial symmetry inductive biases while generating expressive action sequences. On the representation level, ActionFlow introduces an SE(3) Invariant Transformer architecture, which enables informed spatial reasoning based on the relative SE(3) poses between observations and actions. For action generation, ActionFlow leverages Flow Matching, a state-of-the-art deep generative model known for generating high-quality samples with fast inference - an essential property for feedback control. In combination, ActionFlow policies exhibit strong spatial and locality biases and SE(3)-equivariant action generation. Our experiments demonstrate the effectiveness of ActionFlow and its two main components on several simulated and real-world robotic manipulation tasks and confirm that we can obtain equivariant, accurate, and efficient policies with spatially symmetric flow matching. Project website: https://flowbasedpolicies.github.io/
format Preprint
id arxiv_https___arxiv_org_abs_2409_04576
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ActionFlow: Equivariant, Accurate, and Efficient Policies with Spatially Symmetric Flow Matching
Funk, Niklas
Urain, Julen
Carvalho, Joao
Prasad, Vignesh
Chalvatzaki, Georgia
Peters, Jan
Robotics
Artificial Intelligence
Spatial understanding is a critical aspect of most robotic tasks, particularly when generalization is important. Despite the impressive results of deep generative models in complex manipulation tasks, the absence of a representation that encodes intricate spatial relationships between observations and actions often limits spatial generalization, necessitating large amounts of demonstrations. To tackle this problem, we introduce a novel policy class, ActionFlow. ActionFlow integrates spatial symmetry inductive biases while generating expressive action sequences. On the representation level, ActionFlow introduces an SE(3) Invariant Transformer architecture, which enables informed spatial reasoning based on the relative SE(3) poses between observations and actions. For action generation, ActionFlow leverages Flow Matching, a state-of-the-art deep generative model known for generating high-quality samples with fast inference - an essential property for feedback control. In combination, ActionFlow policies exhibit strong spatial and locality biases and SE(3)-equivariant action generation. Our experiments demonstrate the effectiveness of ActionFlow and its two main components on several simulated and real-world robotic manipulation tasks and confirm that we can obtain equivariant, accurate, and efficient policies with spatially symmetric flow matching. Project website: https://flowbasedpolicies.github.io/
title ActionFlow: Equivariant, Accurate, and Efficient Policies with Spatially Symmetric Flow Matching
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2409.04576