Google DeepMind Ships Three Physical AI Models For Whole Body Control, Dexterity And Multi Robot Collaboration
Google DeepMind launched Gemini Robotics 2, a suite featuring three models for whole body control, embodied reasoning, and rapid robot adaptation.

- DeepMind released Gemini Robotics 2 with three specific models for physical tasks.
- The suite includes a VLA for humanoid control and an on-device model for rapid hardware adaptation.
- Only the ER 2 reasoning model is publicly available at this time.
- The system has been tested on Apptronik Apollo 2 and Franka Duo hardware.
Google DeepMind has introduced Gemini Robotics 2, positioning it as the intelligence layer for the next generation of robotic systems. This release includes three distinct models designed to advance physical AI capabilities in complex environments.
The suite features a vision-language-action model for whole body humanoid control and an embodied reasoning model named Gemini Robotics ER 2 for task orchestration. A third on-device VLA model allows robots to adapt to new physical bodies within a matter of hours, significantly speeding up deployment times.
Current implementations include checkpoints that drive the Apptronik Apollo 2 and a Franka Duo robot. While the system represents a significant step forward for multi-robot collaboration, only the ER 2 model is currently available to the public.
Access to ER 2 allows for experimentation with advanced task orchestration and reasoning in physical environments.
Advances in rapid adaptation reduce the time and cost to deploy robots across different hardware platforms.
This moves the field closer to general purpose robots that can handle diverse physical tasks.
- VLA
- Vision-Language-Action models that process visual and language inputs to generate physical robot control commands.
Gemini Robotics ER 2: powering robotics with video understanding, task orchestration, and multi-robot collaboration
$π\mathbf{R}^2$: Reactive Real-time Flow Policies
Pictura: Perspective-View Self-Play at Scale for Driving
Gemini Robotics 2 brings whole body intelligence to robots
RoboticsNVIDIA Cosmos-H-Dreams: Bringing Real-Time Generative Simulation to Surgical Robotics
BusinessAdvancing responsible AI across Europe
OpenAI has outlined its commitment to responsible AI development and deployment within Europe, detailing its safety, security, transparency, and provenance practices. This initiative aligns with the ongoing progression of the EU AI Act.
How Artificial Intelligence Discovered A New Way To Detect Patients At Risk Of Cardiac Death Using Simple EKGs - Forbes
Artificial intelligence has been used to identify subtle patterns in electrocardiograms (EKGs) that can predict a patient's risk of cardiac death. This new method could help clinicians better assess patient risk using readily available data.
First AI-driven telescope goes stargazing - Northwestern Now News
Northwestern University's AI-driven telescope has begun stargazing, marking a significant milestone in the field of astronomy.
AI ToolsYour RAG copilot can't count — stop letting it try
A user discovered that RAG copilot struggles with basic arithmetic, highlighting its limitations.
EU launches €30B push to build 7 massive AI data centers - E&E News by POLITICO
The European Union announced a €30 billion program to construct seven large AI data centers across member states.
EU says necessary to monitor high risk AI systems after OpenAI, Anthropic AI hacking incidents - Reuters
The European Commission announced that high‑risk AI systems must be closely monitored following recent hacking incidents involving OpenAI and Anthropic models.