OpenHelix: A Short Survey, Empirical Analysis, and Open-Source Dual-System VLA Model for Robotic Manipulation

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Cui, Can, Ding, Pengxiang, Song, Wenxuan, Bai, Shuanghao, Tong, Xinyang, Ge, Zirui, Suo, Runze, Zhou, Wanqi, Liu, Yang, Jia, Bofang, Zhao, Han, Huang, Siteng, Wang, Donglin
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913823902924800
author Cui, Can
Ding, Pengxiang
Song, Wenxuan
Bai, Shuanghao
Tong, Xinyang
Ge, Zirui
Suo, Runze
Zhou, Wanqi
Liu, Yang
Jia, Bofang
Zhao, Han
Huang, Siteng
Wang, Donglin
author_facet Cui, Can
Ding, Pengxiang
Song, Wenxuan
Bai, Shuanghao
Tong, Xinyang
Ge, Zirui
Suo, Runze
Zhou, Wanqi
Liu, Yang
Jia, Bofang
Zhao, Han
Huang, Siteng
Wang, Donglin
contents Dual-system VLA (Vision-Language-Action) architectures have become a hot topic in embodied intelligence research, but there is a lack of sufficient open-source work for further performance analysis and optimization. To address this problem, this paper will summarize and compare the structural designs of existing dual-system architectures, and conduct systematic empirical evaluations on the core design elements of existing dual-system architectures. Ultimately, it will provide a low-cost open-source model for further exploration. Of course, this project will continue to update with more experimental conclusions and open-source models with improved performance for everyone to choose from. Project page: https://openhelix-robot.github.io/.
format Preprint
id arxiv_https___arxiv_org_abs_2505_03912
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle OpenHelix: A Short Survey, Empirical Analysis, and Open-Source Dual-System VLA Model for Robotic Manipulation
Cui, Can
Ding, Pengxiang
Song, Wenxuan
Bai, Shuanghao
Tong, Xinyang
Ge, Zirui
Suo, Runze
Zhou, Wanqi
Liu, Yang
Jia, Bofang
Zhao, Han
Huang, Siteng
Wang, Donglin
Robotics
Computer Vision and Pattern Recognition
Dual-system VLA (Vision-Language-Action) architectures have become a hot topic in embodied intelligence research, but there is a lack of sufficient open-source work for further performance analysis and optimization. To address this problem, this paper will summarize and compare the structural designs of existing dual-system architectures, and conduct systematic empirical evaluations on the core design elements of existing dual-system architectures. Ultimately, it will provide a low-cost open-source model for further exploration. Of course, this project will continue to update with more experimental conclusions and open-source models with improved performance for everyone to choose from. Project page: https://openhelix-robot.github.io/.
title OpenHelix: A Short Survey, Empirical Analysis, and Open-Source Dual-System VLA Model for Robotic Manipulation
topic Robotics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.03912