RiEMann: Near Real-Time SE(3)-Equivariant Robot Manipulation without Point Cloud Segmentation

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Gao, Chongkai, Xue, Zhengrong, Deng, Shuying, Liang, Tianhai, Yang, Siqi, Shao, Lin, Xu, Huazhe
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866916421109284864
author Gao, Chongkai
Xue, Zhengrong
Deng, Shuying
Liang, Tianhai
Yang, Siqi
Shao, Lin
Xu, Huazhe
author_facet Gao, Chongkai
Xue, Zhengrong
Deng, Shuying
Liang, Tianhai
Yang, Siqi
Shao, Lin
Xu, Huazhe
contents We present RiEMann, an end-to-end near Real-time SE(3)-Equivariant Robot Manipulation imitation learning framework from scene point cloud input. Compared to previous methods that rely on descriptor field matching, RiEMann directly predicts the target poses of objects for manipulation without any object segmentation. RiEMann learns a manipulation task from scratch with 5 to 10 demonstrations, generalizes to unseen SE(3) transformations and instances of target objects, resists visual interference of distracting objects, and follows the near real-time pose change of the target object. The scalable action space of RiEMann facilitates the addition of custom equivariant actions such as the direction of turning the faucet, which makes articulated object manipulation possible for RiEMann. In simulation and real-world 6-DOF robot manipulation experiments, we test RiEMann on 5 categories of manipulation tasks with a total of 25 variants and show that RiEMann outperforms baselines in both task success rates and SE(3) geodesic distance errors on predicted poses (reduced by 68.6%), and achieves a 5.4 frames per second (FPS) network inference speed. Code and video results are available at https://riemann-web.github.io/.
format Preprint
id arxiv_https___arxiv_org_abs_2403_19460
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle RiEMann: Near Real-Time SE(3)-Equivariant Robot Manipulation without Point Cloud Segmentation
Gao, Chongkai
Xue, Zhengrong
Deng, Shuying
Liang, Tianhai
Yang, Siqi
Shao, Lin
Xu, Huazhe
Robotics
Artificial Intelligence
We present RiEMann, an end-to-end near Real-time SE(3)-Equivariant Robot Manipulation imitation learning framework from scene point cloud input. Compared to previous methods that rely on descriptor field matching, RiEMann directly predicts the target poses of objects for manipulation without any object segmentation. RiEMann learns a manipulation task from scratch with 5 to 10 demonstrations, generalizes to unseen SE(3) transformations and instances of target objects, resists visual interference of distracting objects, and follows the near real-time pose change of the target object. The scalable action space of RiEMann facilitates the addition of custom equivariant actions such as the direction of turning the faucet, which makes articulated object manipulation possible for RiEMann. In simulation and real-world 6-DOF robot manipulation experiments, we test RiEMann on 5 categories of manipulation tasks with a total of 25 variants and show that RiEMann outperforms baselines in both task success rates and SE(3) geodesic distance errors on predicted poses (reduced by 68.6%), and achieves a 5.4 frames per second (FPS) network inference speed. Code and video results are available at https://riemann-web.github.io/.
title RiEMann: Near Real-Time SE(3)-Equivariant Robot Manipulation without Point Cloud Segmentation
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2403.19460