Google DeepMind has released two new robotics-focused AI models. The first, Gemini Robotics ER 2, is described as a step change in video understanding, tool orchestration, and multi-robot collaboration. It is designed to help robots reason, collaborate, and solve real-world tasks.
The second, Gemini Robotics 2, focuses on whole-body intelligence. According to the source, it brings whole-body intelligence to robots, which is a different focus from ER 2's emphasis on video understanding and teamwork.
The two releases are not directly compared in the source material, but they appear complementary: ER 2 strengthens high-level reasoning and multi-robot coordination, while Robotics 2 targets the physical control side of robot behavior. Both are part of Google DeepMind's broader push to make robots more capable in real-world settings.