Google DeepMind has launched Gemini Robotics 2, a new suite of AI models designed to give humanoid and other robots greater autonomy through whole-body control, advanced dexterity and multi-robot collaboration.
The system is being demonstrated on Apptronik‘s Apollo 2 humanoid robot, which Google DeepMind says can now perform full-body autonomous movements, including walking, crouching, bending and manipulating objects, while reasoning through complex tasks in real time.
The announcement builds on the companies’ ongoing collaboration. Earlier this month, Apptronik launched Robot Park, a facility where Apollo 2 robots collect data used to train next-generation AI models, including Gemini Robotics 2.
Google DeepMind describes Gemini Robotics 2 as the “intelligence layer” for robots, enabling machines to move beyond pre-programmed tasks and adapt to changing environments. The company says the platform is designed to work across different robot types and can be adapted to new hardware in a matter of hours.
The release comprises three models:
- Gemini Robotics 2, a vision-language-action (VLA) model that converts visual and language inputs into robot movements and can control full humanoid robots as well as dual-arm systems;
- Gemini Robotics ER 2, an embodied reasoning model that plans multi-step tasks, communicates with people and enables multiple robots to work together; and
- Gemini Robotics On-Device 2, an optimized VLA model that runs locally on robotic hardware and can be adapted to new robot embodiments using only a few hours of training data.
Google DeepMind says Gemini Robotics 2 extends its previous work by adding whole-body control. While earlier versions focused primarily on upper-body manipulation, the latest model enables humanoids to coordinate movements from “feet to fingertips”.
In one demonstration, Apollo 2 receives the instruction to “put the watering can into the green bin in the bottom shelf”, before walking across the room, picking up the object and placing it in the correct location.
The company also highlighted improvements in robot dexterity. Gemini Robotics 2 can control Apptronik’s Apollo 2 equipped with five-fingered SharpaWave hands to perform tasks such as tying a trash bag or unscrewing a light bulb.
The model also supports conventional parallel grippers for industrial manipulation tasks including precision insertion and packing.
Another new capability is multi-robot collaboration. Google DeepMind says Gemini Robotics ER 2 allows different robot types to communicate and coordinate on complex workflows that would otherwise require a single machine to perform every task.
The reasoning model is also designed to manage task execution over several minutes, monitoring progress, recovering from failures and adapting to changing situations.
To support industrial deployments where cloud connectivity is limited, Gemini Robotics On-Device 2 runs directly on robot hardware. According to Google DeepMind, the model can be adapted to new dual-arm robot platforms with fewer than 200 training examples collected over just a few hours.
Safety also forms part of the latest release.
Google DeepMind has introduced ASIMOV-Agentic, a benchmark designed to evaluate “agentic safety orchestration and uncertainty resolution”. The benchmark measures a robot’s ability to refuse unsafe actions, determine when a task cannot be completed safely and request human intervention when appropriate.
The company says Gemini Robotics ER 2 also improves human-awareness capabilities, enabling robots to detect nearby people, trigger safety functions and stop safely when someone enters their working area.
Gemini Robotics ER 2 is now available through Google AI Studio and in private preview on the Gemini Enterprise Agent Platform, while Gemini Robotics 2 and Gemini Robotics On-Device 2 are available to selected early-access partners.
