Shanghai, China--(Newsfile Corp. - March 10, 2025) - Today, AgiBot launches Genie Operator-1 (GO-1), an innovative generalist embodied foundation model which redefines how robots see, understand, and act in the real world. GO-1 introduces the novel Vision-Language-Latent-Action (ViLLA) framework, combining a Vision-Language Model (VLM) and Mixture of Experts (MoE). The VLM utilizes internet-scale heterogeneous data to establish a solid foundation for scene and object understanding. The MoE consists of two key components: the Latent Planner, which learns from cross-embodiment and human operation data to develop general action understanding, and the Action Expert, which uses over a million real robot demonstrations to achieve high-frequency and dexterous manipulation.
These components work in synergy, providing GO-1's unique capabilities：
- Learning from Human Videos
- Few-shot Generalization
- Cross-Embodiment Adaptation
- Continuous Self-Evolution
Paper: https://agibot-world.com/blog/agibot_go1.pdf
AgiBot GO-1 is driving the shift from rigid, task-specific automation to versatile, generalist robotics, unlocking new possibilities across industries-from manufacturing and logistics to services and home automation.
Cannot view this video? Visit:
https://www.youtube.com/watch?v=9dvygD4G93c
Contact:
William Peng, media@zhiyuan-robot.com
To view the source version of this press release, please visit https://www.newsfilecorp.com/release/243954
