Google DeepMind has introduced Gemini Robotics 2, a new family of AI models designed to give robots full-body control, improved dexterity and the ability to work together.

Unlike earlier versions that focused mainly on upper-body movement, Gemini Robotics 2 can control an entire humanoid. Google says robots can now walk, crouch, stretch, balance and manipulate objects from a single instruction.

In one demonstration, Apptronik’s Apollo 2 was told to place a watering can in a green bin on a bottom shelf. The robot walked to the table, picked up the can, moved to the shelf and bent down to place it in the requested location.

The new system includes three models. Gemini Robotics 2 is the vision-language-action model that converts what a robot sees and hears into physical movements.

Gemini Robotics ER 2 acts as the higher-level reasoning system. It can plan multi-step tasks lasting several minutes, track progress through live video, recover from failed steps, and coordinate different robots working together. It can also use tools such as Google Search. The model is available through the Gemini API and Google AI Studio, while its Enterprise Agent Platform access remains in private preview.

Gemini Robotics On-Device 2 runs locally without requiring an internet connection. DeepMind says it can adapt to a substantially different robot design using fewer than 200 examples and a few hours of training data.

Gemini Robotics 2 can control the five-fingered SharpaWave hand, which has 22 degrees of freedom. Google demonstrated tasks including tying a trash bag, closing a ziplock bag, and handling light bulbs.

However, performance remains uneven. DeepMind reported a 92% success rate for unscrewing a light bulb, compared with 44% for tying a trash bag and 40% for sealing a ziplock bag. Screwing in a bulb succeeded 36% of the time. Google also acknowledged that movement speed and multi-finger dexterity still need significant improvement.

Wired described the release as another step toward what DeepMind calls “physical AGI” — the long-term goal of creating robots capable of handling the wide range of physical tasks humans can perform. DeepMind robotics head Carolina Parada said the company wants to build an intelligence layer that can eventually work across different types of robots.

DeepMind also introduced ASIMOV-Agentic, a new benchmark designed to test whether a robot’s reasoning system can reject unsafe actions, recognize when a task is impossible, and ask a human for assistance when uncertain.

Google says Gemini Robotics ER 2 is its safest robotics model so far. It can detect when a person moves too close, stop the robot, and resume work once the area is clear.

The launch comes as robot hardware itself faces growing geopolitical scrutiny. The US recently moved to block new Chinese-made humanoid and quadruped robot models from entering the market over national security concerns.

Google is working with partners including Apptronik, Boston Dynamics and Agile Robots. For now, Gemini Robotics 2 and On-Device 2 remain limited to early-access partners, while ER 2 is available to developers.

Get the latest tech news, telecom insights, and product launches wherever you prefer.

Add ProPakistani to Preferred Sources and see more of our stories in Google Search and Top Stories.

Technology and Automotive Specialist covering the latest cars, smartphones, AI breakthroughs, and...

Shares