AgiBot World Colosseo: A Large-Scale Manipulation Platform for Scalable and Intelligent Embodied Systems
By AgiBot-World-Contributors, Qingwen Bu, Jisong Cai, Li Chen, X. Cui, Yan Ding, Siyuan Feng, Shenyuan Gao, Xindong He, Xu Huang and 41 more. IEEE/RJS International Conference on Intelligent RObots and Systems, 2025
409 citations recorded by the source corpus.
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.
Subfields: Artificial Intelligence, Control and Systems Engineering, Social Psychology
View Paper: https://www.semanticscholar.org/paper/9d60da11b2af826310882f1a81e0b125c0600a00
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
In Control and Systems Engineering
Citations in the corpus
- GR00T N1: An Open Foundation Model for Generalist Humanoid Robots (2025, neutral): “2025) is a large-scale dataset of trajectories from 100 robots.”
- π0.5: a Vision-Language-Action Model with Open-World Generalization (2025, neutral): “…robot manipulation policies from narrow, single-task datasets to diverse datasets that span many scenes and tasks [17, 25, 80, 63, 41, 6, 30, 67, 1] allows the resulting policies to not only solve a wider range of tasks out of the box, but also improves their ability to generalize to new scenes…”
- UniVLA: Learning to Act Anywhere with Task-centric Latent Actions (2025, positive): “Empowered by the emergence of large-scale robotic datasets [78, 63, 38, 1], robot policies based on vision-language-action models (VLA) have made encouraging strides recently [10, 28, 39].”
- RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation (2025, positive): “AgiBot World [4] provides over one million human-verified trajectories spanning 217 tasks in diverse deployment scenarios, RoboMIND [39] contributes 107 K teleoperated episodes (including annotated failures) across 479 tasks and four robot platforms, Open X-Embodiment [31] consolidates more than…”