Google reveals Gemini Robotics 2.0, promising improved dexterity and safety
Summary
Google has introduced Gemini Robotics 2.0, an upgrade to its robotics software that helps robots perform more complex tasks and work together. The new system includes a model that lets robots understand live video and correct mistakes while doing tasks.Key Facts
- Gemini Robotics 2.0 is built on Google’s Gemini AI models and improves robot dexterity and safety.
- The system can analyze changing environments and help robots collaborate on tasks.
- Gemini Robotics ER 2 is a vision language model that processes live video to guide robots step-by-step.
- ER 2 can recognize key moments in tasks, like when a robot should stop pouring liquid, with about 90% accuracy.
- The model allows robots to identify errors and retry just the failed step instead of starting over.
- Robots using this system can work together without getting in each other’s way.
- Gemini Robotics 2 includes models that generate robot actions from instructions, similar to how AI creates text or images.
- Google is testing this technology on different robot hardware, including Boston Dynamics machines.
Read the Full Article
This is a fact-based summary from The Actual News. Click below to read the complete story directly from the original source.
