RealMirror: A Comprehensive, Open-Source Vision-Language-Action Platform for Embodied AI
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908545445789696 |
|---|---|
| author | Tai, Cong Zheng, Zhaoyu Long, Haixu Wu, Hansheng Xiang, Haodong Long, Zhengbin Xiong, Jun Shi, Rong Zhang, Shizhuang Qiu, Gang Wang, He Li, Ruifeng Huang, Jun Chang, Bin Feng, Shuai Shen, Tao |
| author_facet | Tai, Cong Zheng, Zhaoyu Long, Haixu Wu, Hansheng Xiang, Haodong Long, Zhengbin Xiong, Jun Shi, Rong Zhang, Shizhuang Qiu, Gang Wang, He Li, Ruifeng Huang, Jun Chang, Bin Feng, Shuai Shen, Tao |
| contents | The emerging field of Vision-Language-Action (VLA) for humanoid robots faces several fundamental challenges, including the high cost of data acquisition, the lack of a standardized benchmark, and the significant gap between simulation and the real world. To overcome these obstacles, we propose RealMirror, a comprehensive, open-source embodied AI VLA platform. RealMirror builds an efficient, low-cost data collection, model training, and inference system that enables end-to-end VLA research without requiring a real robot. To facilitate model evolution and fair comparison, we also introduce a dedicated VLA benchmark for humanoid robots, featuring multiple scenarios, extensive trajectories, and various VLA models. Furthermore, by integrating generative models and 3D Gaussian Splatting to reconstruct realistic environments and robot models, we successfully demonstrate zero-shot Sim2Real transfer, where models trained exclusively on simulation data can perform tasks on a real robot seamlessly, without any fine-tuning. In conclusion, with the unification of these critical components, RealMirror provides a robust framework that significantly accelerates the development of VLA models for humanoid robots. Project page: https://terminators2025.github.io/RealMirror.github.io |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_14687 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RealMirror: A Comprehensive, Open-Source Vision-Language-Action Platform for Embodied AI Tai, Cong Zheng, Zhaoyu Long, Haixu Wu, Hansheng Xiang, Haodong Long, Zhengbin Xiong, Jun Shi, Rong Zhang, Shizhuang Qiu, Gang Wang, He Li, Ruifeng Huang, Jun Chang, Bin Feng, Shuai Shen, Tao Robotics The emerging field of Vision-Language-Action (VLA) for humanoid robots faces several fundamental challenges, including the high cost of data acquisition, the lack of a standardized benchmark, and the significant gap between simulation and the real world. To overcome these obstacles, we propose RealMirror, a comprehensive, open-source embodied AI VLA platform. RealMirror builds an efficient, low-cost data collection, model training, and inference system that enables end-to-end VLA research without requiring a real robot. To facilitate model evolution and fair comparison, we also introduce a dedicated VLA benchmark for humanoid robots, featuring multiple scenarios, extensive trajectories, and various VLA models. Furthermore, by integrating generative models and 3D Gaussian Splatting to reconstruct realistic environments and robot models, we successfully demonstrate zero-shot Sim2Real transfer, where models trained exclusively on simulation data can perform tasks on a real robot seamlessly, without any fine-tuning. In conclusion, with the unification of these critical components, RealMirror provides a robust framework that significantly accelerates the development of VLA models for humanoid robots. Project page: https://terminators2025.github.io/RealMirror.github.io |
| title | RealMirror: A Comprehensive, Open-Source Vision-Language-Action Platform for Embodied AI |
| topic | Robotics |
| url | https://arxiv.org/abs/2509.14687 |