OpenHelix：机器人操作领域的简要综述、实证分析及开源双系统VLA模型

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

May 6, 2025

作者: Can Cui, Pengxiang Ding, Wenxuan Song, Shuanghao Bai, Xinyang Tong, Zirui Ge, Runze Suo, Wanqi Zhou, Yang Liu, Bofang Jia, Han Zhao, Siteng Huang, Donglin Wang

cs.AI

摘要

双系统VLA（视觉-语言-动作）架构已成为具身智能研究的热点，但现有开源工作尚不足以支持进一步的性能分析与优化。针对这一问题，本文将对现有双系统架构的结构设计进行总结与比较，并对这些架构的核心设计要素开展系统性实证评估。最终，我们将提供一个低成本的开放源代码模型，以供深入探索。当然，该项目将持续更新，带来更多实验结论及性能更优的开源模型，供大家选用。项目主页：https://openhelix-robot.github.io/。

English

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/.