EquAct: An SE(3)-Equivariant Multi-Task Transformer for Open-Loop Robotic Manipulation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhu, Xupeng, Qi, Yu, Zhu, Yizhe, Walters, Robin, Platt, Robert
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912398196080640
author Zhu, Xupeng
Qi, Yu
Zhu, Yizhe
Walters, Robin
Platt, Robert
author_facet Zhu, Xupeng
Qi, Yu
Zhu, Yizhe
Walters, Robin
Platt, Robert
contents Transformer architectures can effectively learn language-conditioned, multi-task 3D open-loop manipulation policies from demonstrations by jointly processing natural language instructions and 3D observations. However, although both the robot policy and language instructions inherently encode rich 3D geometric structures, standard transformers lack built-in guarantees of geometric consistency, often resulting in unpredictable behavior under SE(3) transformations of the scene. In this paper, we leverage SE(3) equivariance as a key structural property shared by both policy and language, and propose EquAct-a novel SE(3)-equivariant multi-task transformer. EquAct is theoretically guaranteed to be SE(3) equivariant and consists of two key components: (1) an efficient SE(3)-equivariant point cloud-based U-net with spherical Fourier features for policy reasoning, and (2) SE(3)-invariant Feature-wise Linear Modulation (iFiLM) layers for language conditioning. To evaluate its spatial generalization ability, we benchmark EquAct on 18 RLBench simulation tasks with both SE(3) and SE(2) scene perturbations, and on 4 physical tasks. EquAct performs state-of-the-art across these simulation and physical tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2505_21351
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle EquAct: An SE(3)-Equivariant Multi-Task Transformer for Open-Loop Robotic Manipulation
Zhu, Xupeng
Qi, Yu
Zhu, Yizhe
Walters, Robin
Platt, Robert
Robotics
Transformer architectures can effectively learn language-conditioned, multi-task 3D open-loop manipulation policies from demonstrations by jointly processing natural language instructions and 3D observations. However, although both the robot policy and language instructions inherently encode rich 3D geometric structures, standard transformers lack built-in guarantees of geometric consistency, often resulting in unpredictable behavior under SE(3) transformations of the scene. In this paper, we leverage SE(3) equivariance as a key structural property shared by both policy and language, and propose EquAct-a novel SE(3)-equivariant multi-task transformer. EquAct is theoretically guaranteed to be SE(3) equivariant and consists of two key components: (1) an efficient SE(3)-equivariant point cloud-based U-net with spherical Fourier features for policy reasoning, and (2) SE(3)-invariant Feature-wise Linear Modulation (iFiLM) layers for language conditioning. To evaluate its spatial generalization ability, we benchmark EquAct on 18 RLBench simulation tasks with both SE(3) and SE(2) scene perturbations, and on 4 physical tasks. EquAct performs state-of-the-art across these simulation and physical tasks.
title EquAct: An SE(3)-Equivariant Multi-Task Transformer for Open-Loop Robotic Manipulation
topic Robotics
url https://arxiv.org/abs/2505.21351