Gemini Robotics 2 brings whole body intelligence to robots
From feet to fingertips — we are teaching robots intelligent whole-body control, fine dexterity, and teamwork to complete a broad range of complex tasks
Key points
- We demonstrated how Gemini's multimodal understanding could drive real-world action with Gemini Robotics.
- Today, we are introducing Gemini Robotics 2 - the intelligence layer powering the next generation of truly adaptable robots.
- Gemini Robotics 2 enables robots to reason through every movement, unlocking a broad range of tasks.
- Gemini Robotics 2: Our most advanced vision-language-action model (VLA) that converts vision and language input into motor control, enabling a robot to take action.
Sources (1)
- [1]Gemini Robotics 2 brings whole body intelligence to robotsGoogle DeepMind Blog · Jul 28, 01:21 PM
From feet to fingertips — we are teaching robots intelligent whole-body control, fine dexterity, and teamwork to complete a broad range of complex tasks
We demonstrated how Gemini's multimodal understanding could drive real-world action with Gemini Robotics.
Extractive summary: sentences quoted from the sources.
Before this
- Jul 21, 2026Introducing Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber
- Jul 17, 2026Introducing Gemini 3.5 Flash Cyber
- Jun 30, 2026Start building with Nano Banana 2 Lite and Gemini Omni Flash
- Jun 24, 2026Introducing computer use in Gemini 3.5 Flash
- Jun 10, 2026DiffusionGemma: 4x faster text generation
- Jun 9, 2026Introducing Gemma 4 12B: a unified, encoder-free multimodal model