theaicatalog
Google ยท Hardware

Google DeepMind's Gemini Robotics 2.5 improves robot dexterity and speed

Google DeepMind introduced Gemini Robotics 2.5, which it calls its most capable vision-language-action model to date. The company says the model achieves a 30% to 100% higher success rate than previous baselines, depending on the task, while completing tasks 20% to 30% faster. In a proof-of-concept with Apptronik and Mercedes-Benz on automotive production lines, Apollo 2 humanoid robots sorted parts into kits with a 96% success rate. Gemini Robotics 2.5 is rolling out to robotics partners.