Google DeepMind’s optimized AI model runs directly on robots
SMRTR summary
Google DeepMind's new on-device Gemini Robotics AI model enables offline operation with capabilities similar to its flagship version. This compact model allows robots to perform various tasks without specific training, adapting to new situations with minimal demonstrations across different robot types. Google is releasing an SDK for developers to evaluate and fine-tune the model, currently available to trusted testers.
SMRTR provides this summary for quick context. The original article belongs to The Verge.
Read the original article