Gemini Robotics 2 brings whole body intelligence to robots
Quick Answer
Gemini Robotics 2 by Google DeepMind introduces whole-body intelligence in robots, enabling advanced dexterity and multi-robot collaboration.
Quick Take
The models, including Gemini Robotics ER 2 and On-Device 2, allow for intelligent control and quick adaptation to new robotic bodies, enhancing task execution in complex environments.
Key Points
- Gemini Robotics 2 enables robots to perform complex tasks with whole-body control.
- The ER 2 model allows robots to communicate and plan multi-step tasks.
- On-Device 2 achieves fast adaptation to new robot embodiments in hours.
- Robots can now execute longer task sequences involving hundreds of decisions.
- Multi-robot collaboration enhances efficiency in complex workflows.
Source Excerpt
From feet to fingertips — we are teaching robots intelligent whole-body control, fine dexterity, and teamwork to complete a broad range of complex tasks.
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from Google DeepMind
See more →
Introducing Gemma 4 12B: a unified, encoder-free
Google DeepMind has introduced Gemma 4 12B, a unified, encoder-free multimodal model designed to enhance performance across various tasks. This model aims to streamline processes in AI applications by eliminating the need for traditional encoders, potentially improving efficiency and reducing costs for developers and researchers in the field.
