Google DeepMind has introduced Gemini Robotics 2, a suite of three AI models designed to give robots intelligent whole-body control, advanced dexterity, and multi-robot collaboration capabilities. The suite includes: Gemini Robotics 2 (a vision-language-action model enabling full humanoid control from feet to fingertips), Gemini Robotics ER 2 (an embodied reasoning model for multi-step task planning and robot teamwork), and Gemini Robotics On-Device 2 (an efficient on-device VLA that can adapt to new robot embodiments in a few hours with under 200 examples). Key advances include controlling Apptronik's Apollo 2 humanoid for whole-body tasks, fine dexterous manipulation with 22-DOF hands, agentic reasoning for multi-minute task sequences, and a new ASIMOV-Agentic safety benchmark. The ER 2 model is available on Google AI Studio and Gemini Enterprise Agent Platform, while VLA models are in early-access partner preview.
