Genie Studio 2.0: A One-Stop Platform for Full-Stack Embodied AI Deployment
智元发布Genie Studio 2.0，打通机器人“上岗”最后一公里
On October 23, 2026, Zhim yuan released Genie Studio 2.0, a one-stop platform for full-stack embodied AI deployment, aiming to enable robots to transition from model capabilities to real-world operations. The platform includes three core modules: Flywheel for model iteration, Agent for task orchestration, and Monitor for fleet management, enabling rapid deployment and scalable operations in industrial settings.
Genie Studio 2.0 represents a significant step in bridging the gap between simulated AI models and real-world robotic deployment, offering a comprehensive platform for end-to-end robotic task execution. The tool integrates data collection, model training, simulation testing, and real-world deployment, with demonstrated success in multiple industrial applications.
Source: Chinese robotics — Dataset and collection discovery · Read original article ↗
English translation unavailable. Choose the original article to read it.
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
Reported numbers
Reported success rate
99%
simulation_time
30 minutes
View original evidence
Genie Sim Benchmark评测平台覆盖四个维度、42类任务，支持5分钟接入、30分钟完成评测，仿真结果与真机表现误差小于10%，把大部分风险拦截在真机上线之前。
Open source S19deployment_time
7
View original evidence
平台由三大核心模块组成：Flywheel 具身模型迭代开发平台、Agent 模块化作业编排平台、Monitor 多机舰队运维平台，完整覆盖「采‑训‑测‑推‑编‑管」全生命周期，补齐机器人从模型能力到真实上岗的关键短板，最快 7 天即可完成全新作业场景从 0 到 1 的部署验证。
Open source S8
- paper: not_reported
- code: not_reported
- weights: not_reported
- dataset: not_reported
What remains unknown
Not established in the collected evidence: Environment, Control, Data origin.
Reported performance applies to the described task. It does not establish general autonomy or deployment readiness.
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
在真实项目验证中，智元自研强化学习训练框架实现小时级收敛，相关任务成功率达到99%。
Open source S17
Genie Sim Benchmark评测平台覆盖四个维度、42类任务，支持5分钟接入、30分钟完成评测，仿真结果与真机表现误差小于10%，把大部分风险拦截在真机上线之前。
Open source S19
平台由三大核心模块组成：Flywheel 具身模型迭代开发平台、Agent 模块化作业编排平台、Monitor 多机舰队运维平台，完整覆盖「采‑训‑测‑推‑编‑管」全生命周期，补齐机器人从模型能力到真实上岗的关键短板，最快 7 天即可完成全新作业场景从 0 到 1 的部署验证。
Open source S8
完整闭环分为四步：数据采集→模型训练→仿真模拟大考→真机部署，异常数据回流反哺迭代。
Open source S12
Source：Chinese robotics — Dataset and collection discovery · news.pedaily.cn