Google DeepMind's New Robot AI Can Now Control a Full Body, From Feet to Fingertips
Gemini Robotics 2 gives humanoid robots whole-body movement and five-fingered hand control. Here is what the upgrade actually means, and how close these machines are to working alongside people.
Key points
- Google DeepMind released Gemini Robotics 2 on Thursday, upgrading its robot AI to control a humanoid's full body rather than just the upper half.
- The model now drives five-fingered robot hands precise enough to tie a trash bag, seal a zip-lock bag, or unscrew a lightbulb.
- A companion model, Gemini Robotics ER 2, lets robots of different designs work together on shared tasks.
- Google says the safety system can now detect nearby humans and bring a robot to a stop if someone gets too close.
- An on-device version runs without an internet connection and can adapt to robots with very different body shapes.
Until now, Google DeepMind's robot AI told a humanoid machine what to do with its arms and hands. The rest of the body was largely on its own.
Gemini Robotics 2 changes that. Announced Thursday, the new model handles the whole machine, from how it plants its feet to how it curls its fingers. Google calls this "whole-body coordination," and in plain terms it means a robot can now crouch, walk, reach low, and grip an object all in one coordinated sequence.
What can the robots actually do now?
More than before, but not everything yet. Demo videos show Apptronik's Apollo 2 robot bending down to pick up a watering can and scanning a shelf to find a specific item.
The hand work is the detail worth paying attention to. Earlier versions of the model controlled simpler gripper-style hands. Gemini Robotics 2 supports full five-fingered hands, which opens up tasks that require a pinching or twisting motion: sealing a zip-lock bag, knotting a trash bag, removing a light bulb from its socket. These are the kinds of small manual tasks that have historically defeated robots.
Google is honest that speed is still a weak point. The company says its robots "have more to advance in movement speed," which is a polite way of saying they are still slow by human standards.
What is the ER model, and why does it matter?
Gemini Robotics ER 2 is the "reasoning" layer, a vision-language model that lets robots read their surroundings, follow spoken or written instructions, and carry out multi-step tasks over a longer stretch of time.
The practical upgrade here is task awareness. The previous version could get confused about where one job ended and another began. The new version, according to Google, "now understands when tasks begin and end." That sounds small. For a warehouse or kitchen setting, it is actually significant.
ER 2 also enables different robot types to collaborate. One video, first reported by The Verge AI, shows Apollo 2 directing a separate two-armed robot to sort tools into a bin. Two machines, different designs, one shared job.
Should people working near robots be worried?
Google says Gemini Robotics ER 2 is its safest robotics model yet. The system can detect when a person gets too close and stop the robot before contact occurs.
That is a baseline safety feature, not a complete answer to workplace safety questions. But it is a meaningful step, especially as these machines start moving their whole bodies in shared spaces.
The on-device model, which runs locally without any internet connection, can now adapt faster when installed in a robot with a different body shape or sensor setup. That makes it easier for manufacturers to drop the software into new hardware without starting from scratch.
One honest takeaway: if your job involves repetitive manual tasks in a structured environment, these robots are getting more capable every few months. They are not replacing skilled tradespeople tomorrow, but watching how quickly the hand-dexterity gap is closing is worth your attention.
