新闻
Gemini Robotics ER 2: powering robotics with video understanding, task orchestration, and multi-robot collaboration
Google DeepMind · 发布于 · 阅读约3分钟
30秒读懂
- 发生了什么
- Google launched Gemini Robotics ER 2, a model that acts as a high-level brain for robots, enabling real-time task planning, video understanding, and multi-robot collaboration.
- 为何重要
- Robotics engineers building physical AI agents should care, especially those integrating vision-language-action models or coordinating multiple robots in shared spaces.
- 注意
- The model requires integration with lower-level control systems and APIs. Real-world performance beyond the demonstrated demos remains to be validated at scale.
收听本摘要
- gemini
The Agent Architect
每周一个模式、一个权衡、一个生产事故案例。为构建智能体系统的人准备的每周简报。
每周一封邮件,一键退订。您的地址仅用于发送简报。