datasets
收藏资源简介:
本数据集为Modified LIBERO RLDS Datasets,包含四个经过修改的LIBERO数据集,以RLDS(Robot Learning Data Standard)格式存储。这些数据集源自LIBERO机器人学习项目,并针对OpenVLA(一个开源视觉-语言-动作模型)的微调实验进行了专门调整。数据集的具体修改细节和实验设置可参考OpenVLA相关论文的附录E。该数据集主要用于机器人学习领域的视觉-语言-动作模型微调任务。
This dataset is the Modified LIBERO RLDS Datasets, which includes four modified LIBERO datasets stored in the RLDS (Robot Learning Data Standard) format. These datasets originate from the LIBERO robot learning project and have been specifically adapted for fine-tuning experiments with OpenVLA (an open-source vision-language-action model). The specific modification details and experimental setup of the dataset can be referred to in Appendix E of the relevant OpenVLA paper. This dataset is primarily used for fine-tuning vision-language-action models in the field of robot learning.
数据集概述
该数据集为 Modified LIBERO RLDS Datasets,包含四个经过修改的 LIBERO 数据集,以 RLDS 数据格式存储。
用途
数据集用于 OpenVLA 微调实验,具体修改细节请参见 OpenVLA 论文 的附录 E。运行 OpenVLA 在 LIBERO 环境中的操作指南,请参考 OpenVLA GitHub README。
许可
数据集遵循 MIT 许可证(license: mit)。
引用
若使用该数据集,建议引用 OpenVLA 论文:
bibtex @article{kim24openvla, title={OpenVLA: An Open-Source Vision-Language-Action Model}, author={{Moo Jin} Kim and Karl Pertsch and Siddharth Karamcheti and Ted Xiao and Ashwin Balakrishna and Suraj Nair and Rafael Rafailov and Ethan Foster and Grace Lam and Pannag Sanketi and Quan Vuong and Thomas Kollar and Benjamin Burchfiel and Russ Tedrake and Dorsa Sadigh and Sergey Levine and Percy Liang and Chelsea Finn}, journal = {arXiv preprint arXiv:2406.09246}, year={2024} }
此外,引用 LIBERO 时请参考 LIBERO 项目仓库。




