A naukri.com initiative
TechCrunch
3w
267
Image Credit: TechCrunch
Google rolls out new Gemini model that can run on robots locally
- Google DeepMind released a new language model called Gemini Robotics On-Device that can run tasks locally on robots without an internet connection.
- Gemini Robotics On-Device can control a robot's movements and be fine-tuned using natural language prompts.
- The model performs well in benchmarks compared to cloud-based models and outperforms other on-device models.
- Google demoed the model with robots performing tasks like unzipping bags and folding clothes.
- Gemini Robotics On-Device was trained on ALOHA robots and later adapted for use on other robots like the bi-arm Franka FR3 and Apollo humanoid robots.
- The bi-arm Franka FR3 robot successfully handled new scenarios and tasks it hadn't encountered before.
- Google is also releasing a Gemini Robotics SDK for developers to train robots on new tasks using the MuJoCo physics simulator.
- Nvidia, Hugging Face, and Mirae Asset-backed Korean startup RLWRLD are also working on AI models and platforms for robotics.
- Nvidia is building a platform for humanoids, Hugging Face is developing open models for robotics and working on robots, and RLWRLD is creating foundational models for robots.
Read Full Article
16 Likes
For uninterrupted reading, download the app