Google Launches On-Device Gemini AI Model for Robots
Google DeepMind Unveils Gemini Robotics On-Device for Offline Robot Control
Google DeepMind just dropped an exciting update in the robotics space—Gemini Robotics On-Device, a new language model that lets robots perform tasks without needing an internet connection. This builds on their earlier Gemini Robotics model (released in March) but with a key upgrade: local processing.
Developers can now fine-tune robot movements using natural language prompts, making it easier to adapt robots for different tasks. Google claims its performance is nearly on par with its cloud-based counterpart and outperforms other on-device models (though they didn’t specify which ones).
Image Credits: Google Real-World Robot Skills: From Laundry to Assembly Lines
In demos, robots running this model successfully:
- Unzipped bags
- Folded clothes
- Adapted to new objects (like assembling parts on an industrial belt)
Originally trained for ALOHA robots, the model was later adapted to work on:
- Franka FR3 (a bi-arm industrial robot)
- Apptronik’s Apollo humanoid
Gemini Robotics SDK: Training Robots with Demonstrations
Google also announced a Gemini Robotics SDK, allowing developers to train robots using 50-100 task demonstrations in the MuJoCo physics simulator. This could speed up robot learning for real-world applications.
The Bigger Picture: AI’s Push into Robotics
Google isn’t alone in this race:
- Nvidia is building foundation models for humanoids
- Hugging Face is working on open models—and actual robots
- RLWRLD (a Korean startup) is developing foundational models for robotics
The future of AI-powered robots is heating up—and it’s happening offline, on-device, and in real time.
Want more tech insights?
Join us at TechCrunch Disrupt in Boston, MA (July 15) for deep dives into AI, robotics, and venture trends. Save $200+ on All Stage passes and connect with leaders from Precursor Ventures, NEA, Index Ventures, and Underscore VC.
Related article
Google rolls out Gemini in Chrome to India
On Wednesday, Google announced it is expanding Gemini integration for Chrome to new regions, including India, Canada, and New Zealand. This rollout allows desktop users to access Gemini via a sidebar, where they can ask Google’s AI chatbot about on-s
YouTube expands AI deepfake detection to politicians, government officials, and journalists
On Tuesday, YouTube announced it is expanding its deepfake detection technology to a select group of government officials, political candidates, and journalists. The tool identifies AI-generated likenesses and lets pilot participants request the remo
YouTube Tests AI-Powered Search Feature with Guided Answers
Many users turn to YouTube when searching for recipes or travel plans, looking for relevant videos. Now, the platform is introducing an AI-powered interactive search tool that delivers step-by-step results, blending text and video content.With the ne
Related Special Topic Recommendations
Comments (3)
0/500
Super cool that robots can now think offline with Gemini! Imagine them zipping around without Wi-Fi, making decisions on the fly. Can’t wait to see this in action at home! 🤖
This is wild! Robots running Gemini AI offline? Google’s pushing the future hard. Can’t wait to see how this shakes up industries, but I’m low-key worried about robots getting too smart too fast. 😅
Google DeepMind Unveils Gemini Robotics On-Device for Offline Robot Control
Google DeepMind just dropped an exciting update in the robotics space—Gemini Robotics On-Device, a new language model that lets robots perform tasks without needing an internet connection. This builds on their earlier Gemini Robotics model (released in March) but with a key upgrade: local processing.
Developers can now fine-tune robot movements using natural language prompts, making it easier to adapt robots for different tasks. Google claims its performance is nearly on par with its cloud-based counterpart and outperforms other on-device models (though they didn’t specify which ones).
Real-World Robot Skills: From Laundry to Assembly Lines
In demos, robots running this model successfully:
- Unzipped bags
- Folded clothes
- Adapted to new objects (like assembling parts on an industrial belt)
Originally trained for ALOHA robots, the model was later adapted to work on:
- Franka FR3 (a bi-arm industrial robot)
- Apptronik’s Apollo humanoid
Gemini Robotics SDK: Training Robots with Demonstrations
Google also announced a Gemini Robotics SDK, allowing developers to train robots using 50-100 task demonstrations in the MuJoCo physics simulator. This could speed up robot learning for real-world applications.
The Bigger Picture: AI’s Push into Robotics
Google isn’t alone in this race:
- Nvidia is building foundation models for humanoids
- Hugging Face is working on open models—and actual robots
- RLWRLD (a Korean startup) is developing foundational models for robotics
The future of AI-powered robots is heating up—and it’s happening offline, on-device, and in real time.
Want more tech insights?
Join us at TechCrunch Disrupt in Boston, MA (July 15) for deep dives into AI, robotics, and venture trends. Save $200+ on All Stage passes and connect with leaders from Precursor Ventures, NEA, Index Ventures, and Underscore VC.
Google rolls out Gemini in Chrome to India
On Wednesday, Google announced it is expanding Gemini integration for Chrome to new regions, including India, Canada, and New Zealand. This rollout allows desktop users to access Gemini via a sidebar, where they can ask Google’s AI chatbot about on-s
YouTube expands AI deepfake detection to politicians, government officials, and journalists
On Tuesday, YouTube announced it is expanding its deepfake detection technology to a select group of government officials, political candidates, and journalists. The tool identifies AI-generated likenesses and lets pilot participants request the remo
YouTube Tests AI-Powered Search Feature with Guided Answers
Many users turn to YouTube when searching for recipes or travel plans, looking for relevant videos. Now, the platform is introducing an AI-powered interactive search tool that delivers step-by-step results, blending text and video content.With the ne
Super cool that robots can now think offline with Gemini! Imagine them zipping around without Wi-Fi, making decisions on the fly. Can’t wait to see this in action at home! 🤖
This is wild! Robots running Gemini AI offline? Google’s pushing the future hard. Can’t wait to see how this shakes up industries, but I’m low-key worried about robots getting too smart too fast. 😅





Home






