Gemini Robotics 2.5 Enhances Dexterity and Safety in Real-World Tasks

DeepMind has unveiled Gemini Robotics 2.5, its most advanced vision-language-action (VLA) model to date, designed to significantly enhance the dexterity, reliability, and safety of robots in real-world environments. The model enables robots to learn and perform a broader range of tasks more quickly, marking a step toward widespread industrial and everyday applications. Gemini Robotics 2.5 was tested across over 200 distinct tasks, including complex activities such as using tongs to serve food, tying bows on gift boxes, and pipetting liquids. These tasks required advanced tool use, manipulation of deformable objects, and handling delicate materials. The model achieved a 30% to 100% higher success rate compared to previous baselines and completed tasks 20% to 30% faster.

BeCrypto News shows a short excerpt and links to the publisher. The full report belongs to Blockchain.News.