Gemini Robotics ER 2: powering robotics with video understanding, task orchestration, and multi-robot collaboration
Gemini Robotics ER 2 is a high-level brain for robots, enabling real-time spatial reasoning, task planning, and multi-robot collaboration. It improves progress classification and moment-finding accuracy, achieving 57.4% and 91.3% precision, respectively, while offering efficient computation. The model outperforms ER 1.6 in tool orchestration and safety benchmarks, supporting low-level control interfaces and multimodal input for enhanced workflow efficiency.
More from Deepmind Google
Putting sign language AI into users’ hands
Introducing sign-language-to-text (SL2T), our breakthrough model powering new sign language features for Deaf and hard of hearing users.
Gemini Robotics 2 brings whole body intelligence to robots
We’re launching Lyria 3.5 in Google Flow Music, with advances across musicality, lyrics, vocals, and creative control
