AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912517879496704 |
|---|---|
| author | AgiBot-World-Contributors Bu, Qingwen Cai, Jisong Chen, Li Cui, Xiuqi Ding, Yan Feng, Siyuan Gao, Shenyuan He, Xindong Hu, Xuan Huang, Xu Jiang, Shu Jiang, Yuxin Jing, Cheng Li, Hongyang Li, Jialu Liu, Chiming Liu, Yi Lu, Yuxiang Luo, Jianlan Luo, Ping Mu, Yao Niu, Yuehan Pan, Yixuan Pang, Jiangmiao Qiao, Yu Ren, Guanghui Ruan, Cheng Shan, Jiaqi Shen, Yongjian Shi, Chengshi Shi, Mingkang Shi, Modi Sima, Chonghao Song, Jianheng Wang, Huijie Wang, Wenhao Wei, Dafeng Xie, Chengen Xu, Guo Yan, Junchi Yang, Cunbiao Yang, Lei Yang, Shukai Yao, Maoqing Zeng, Jia Zhang, Chi Zhang, Qinglin Zhao, Bin Zhao, Chengyue Zhao, Jiaqi Zhu, Jianchao |
| author_facet | AgiBot-World-Contributors Bu, Qingwen Cai, Jisong Chen, Li Cui, Xiuqi Ding, Yan Feng, Siyuan Gao, Shenyuan He, Xindong Hu, Xuan Huang, Xu Jiang, Shu Jiang, Yuxin Jing, Cheng Li, Hongyang Li, Jialu Liu, Chiming Liu, Yi Lu, Yuxiang Luo, Jianlan Luo, Ping Mu, Yao Niu, Yuehan Pan, Yixuan Pang, Jiangmiao Qiao, Yu Ren, Guanghui Ruan, Cheng Shan, Jiaqi Shen, Yongjian Shi, Chengshi Shi, Mingkang Shi, Modi Sima, Chonghao Song, Jianheng Wang, Huijie Wang, Wenhao Wei, Dafeng Xie, Chengen Xu, Guo Yan, Junchi Yang, Cunbiao Yang, Lei Yang, Shukai Yao, Maoqing Zeng, Jia Zhang, Chi Zhang, Qinglin Zhao, Bin Zhao, Chengyue Zhao, Jiaqi Zhu, Jianchao |
| contents | We explore how scalable robot data can address real-world challenges for generalized robotic manipulation. Introducing AgiBot World, a large-scale platform comprising over 1 million trajectories across 217 tasks in five deployment scenarios, we achieve an order-of-magnitude increase in data scale compared to existing datasets. Accelerated by a standardized collection pipeline with human-in-the-loop verification, AgiBot World guarantees high-quality and diverse data distribution. It is extensible from grippers to dexterous hands and visuo-tactile sensors for fine-grained skill acquisition. Building on top of data, we introduce Genie Operator-1 (GO-1), a novel generalist policy that leverages latent action representations to maximize data utilization, demonstrating predictable performance scaling with increased data volume. Policies pre-trained on our dataset achieve an average performance improvement of 30% over those trained on Open X-Embodiment, both in in-domain and out-of-distribution scenarios. GO-1 exhibits exceptional capability in real-world dexterous and long-horizon tasks, achieving over 60% success rate on complex tasks and outperforming prior RDT approach by 32%. By open-sourcing the dataset, tools, and models, we aim to democratize access to large-scale, high-quality robot data, advancing the pursuit of scalable and general-purpose intelligence. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_06669 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems AgiBot-World-Contributors Bu, Qingwen Cai, Jisong Chen, Li Cui, Xiuqi Ding, Yan Feng, Siyuan Gao, Shenyuan He, Xindong Hu, Xuan Huang, Xu Jiang, Shu Jiang, Yuxin Jing, Cheng Li, Hongyang Li, Jialu Liu, Chiming Liu, Yi Lu, Yuxiang Luo, Jianlan Luo, Ping Mu, Yao Niu, Yuehan Pan, Yixuan Pang, Jiangmiao Qiao, Yu Ren, Guanghui Ruan, Cheng Shan, Jiaqi Shen, Yongjian Shi, Chengshi Shi, Mingkang Shi, Modi Sima, Chonghao Song, Jianheng Wang, Huijie Wang, Wenhao Wei, Dafeng Xie, Chengen Xu, Guo Yan, Junchi Yang, Cunbiao Yang, Lei Yang, Shukai Yao, Maoqing Zeng, Jia Zhang, Chi Zhang, Qinglin Zhao, Bin Zhao, Chengyue Zhao, Jiaqi Zhu, Jianchao Robotics Computer Vision and Pattern Recognition Machine Learning We explore how scalable robot data can address real-world challenges for generalized robotic manipulation. Introducing AgiBot World, a large-scale platform comprising over 1 million trajectories across 217 tasks in five deployment scenarios, we achieve an order-of-magnitude increase in data scale compared to existing datasets. Accelerated by a standardized collection pipeline with human-in-the-loop verification, AgiBot World guarantees high-quality and diverse data distribution. It is extensible from grippers to dexterous hands and visuo-tactile sensors for fine-grained skill acquisition. Building on top of data, we introduce Genie Operator-1 (GO-1), a novel generalist policy that leverages latent action representations to maximize data utilization, demonstrating predictable performance scaling with increased data volume. Policies pre-trained on our dataset achieve an average performance improvement of 30% over those trained on Open X-Embodiment, both in in-domain and out-of-distribution scenarios. GO-1 exhibits exceptional capability in real-world dexterous and long-horizon tasks, achieving over 60% success rate on complex tasks and outperforming prior RDT approach by 32%. By open-sourcing the dataset, tools, and models, we aim to democratize access to large-scale, high-quality robot data, advancing the pursuit of scalable and general-purpose intelligence. |
| title | AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems |
| topic | Robotics Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2503.06669 |