AgiBot World Colosseo：面向可扩展与智能具身系统的大规模操作平台
机器人学
2025-08-05 v4 计算机视觉与模式识别
机器学习
摘要
我们探索可扩展的机器人数据如何解决泛化机器人操作的现实挑战。我们推出了 AgiBot World，这是一个大规模平台，包含跨越五种部署场景中 217 项任务的超过 100 万条轨迹，与现有数据集相比，我们实现了数据规模的一个数量级提升。在带有真人参与验证的标准化采集流程的加速下，AgiBot World 保证了高质量和多样化的数据分布。它可以从夹爪扩展到灵巧手和视触觉传感器，用于细粒度的技能获取。基于这些数据，我们引入了 Genie Operator-1 (GO-1)，这是一种利用潜在动作表示来最大化数据利用率的新型通用策略，展示了随着数据量增加而可预测的性能扩展。在我们的数据集上预训练的策略在域内和分布外场景中，均比在 Open X-Embodiment 上训练的策略实现了平均 30% 的性能提升。GO-1 在现实世界的灵巧和长时序任务中表现出卓越的能力，在复杂任务上实现了超过 60% 的成功率，并比先前的 RDT 方法高出 32%。通过开源数据集、工具和模型，我们旨在普及对大规模、高质量机器人数据的访问，推进可扩展和通用智能的追求。
引用
@article{arxiv.2503.06669,
title = {AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems},
author = {AgiBot-World-Contributors and Qingwen Bu and Jisong Cai and Li Chen and Xiuqi Cui and Yan Ding and Siyuan Feng and Shenyuan Gao and Xindong He and Xuan Hu and Xu Huang and Shu Jiang and Yuxin Jiang and Cheng Jing and Hongyang Li and Jialu Li and Chiming Liu and Yi Liu and Yuxiang Lu and Jianlan Luo and Ping Luo and Yao Mu and Yuehan Niu and Yixuan Pan and Jiangmiao Pang and Yu Qiao and Guanghui Ren and Cheng Ruan and Jiaqi Shan and Yongjian Shen and Chengshi Shi and Mingkang Shi and Modi Shi and Chonghao Sima and Jianheng Song and Huijie Wang and Wenhao Wang and Dafeng Wei and Chengen Xie and Guo Xu and Junchi Yan and Cunbiao Yang and Lei Yang and Shukai Yang and Maoqing Yao and Jia Zeng and Chi Zhang and Qinglin Zhang and Bin Zhao and Chengyue Zhao and Jiaqi Zhao and Jianchao Zhu},
journal= {arXiv preprint arXiv:2503.06669},
year = {2025}
}
备注
Project website: https://agibot-world.com/. Github repo: https://github.com/OpenDriveLab/AgiBot-World. The author list is ordered alphabetically by surname, with detailed contributions provided in the appendix