Google Introduces Gemini Robotics On-Device AI Model, Can Adapt to Different Types of Robots

Developed by Google DeepMind, the Gemini Robotics On-Device model follows the company’s server-based robotics model.

Written by Akash Dutta, Edited by Siddharth Suvarna | Updated: 25 June 2025 15:42 IST

Highlights

Gemini Robotics On-Device is a VLA model
It works with ALOHA, Franka FR3, and Apollo humanoid robots
Google says the model can learn new tasks with 50-100 demonstrations

Google Introduces Gemini Robotics On-Device AI Model, Can Adapt to Different Types of Robots

Google says the model outperforms other on-device alternatives on out-of-distribution tasks

Photo Credit: Google

Google DeepMind released a new Gemini Robotics artificial intelligence (AI) model on Tuesday that can run entirely on a local device. Dubbed Gemini Robotics On-Device, it is a voice-language-action (VLA) model that can make robots perform a wide range of tasks in real-world environments. The Mountain View-based tech giant said that since the AI model functions without the need to be connected with a data network, it is more useful for applications that are latency sensitive. Currently, the model is available to those who have signed up for its trusted tester programme.

Google's New Robotics Model Runs Entirely On-Device

In a blog post, Carolina Parada, a Senior Director and Head of Robotics at Google DeepMind, announced the release of Gemini Robotics On-Device. The new VLA model can be accessed via a Gemini Robotics software development kit (SDK) after signing up for its tester programme. The model can also be tested on the company's MuJoCo physics simulator.

Since it is a proprietary model, details about its architecture and training methods are not known. However, Google has highlighted its capabilities. The VLA model is designed for bi-arm robots and has minimal computational requirements. Despite that, the model allows for experimentation, and the company claims that it can adapt to new tasks with just 50 to 100 demonstrations.

Google DeepMind’s Gemini Robotics AI Models That Can Control Robots

Gemini Robotics On-Device also adheres to natural language instructions and can perform complex tasks such as unzipping bags or folding clothes. Based on internal testing, the tech giant claims that the AI model “exhibits strong generalisation performance while running entirely locally.” Additionally, it is also said to outperform other on-device models on “more challenging out-of-distribution tasks and complex multi-step instructions.”

Notably, Google highlighted that while the AI model was trained for ALOHA robots, researchers were also able to adapt it to Franka FR3 and Apptronik's Apollo humanoid robots. All of these are bi-arm robots, which is the only configuration that is compatible with Gemini Robotics On-Device.

The AI model was able to adhere to instructions and perform general tasks on all the different robots. Additionally, it could also handle previously unseen objects and scenarios, and even execute industrial belt assembly tasks that require a high level of precision and dexterity, the company claimed.

For the latest tech news and reviews, follow Gadgets 360 on X, Facebook, WhatsApp, Threads and Google News. For the latest videos on gadgets and tech, subscribe to our YouTube channel. If you want to know everything about top influencers, follow our in-house Who'sThat360 on Instagram and YouTube.