Technology ❯ Robotics ❯ Machine Learning

Vision-Language Models

Primitive-Centric Framework Tactile Feedback Action Generation Spatial Reasoning Benchmarking Action Prediction Robotic Manipulation Zero-Shot Learning Vision-Language-Action Models Semantic Assembly Representation Corruption Restoration Gemini Robotics 1.5 DySL-VLA Framework Training and Scaling

DeepMind Unveils Gemini Robotics‑ER 1.5 and Gemini Robotics 1.5 to Let Robots Plan Tasks and Use the Web

Developers get the reasoning model via the Gemini API, with the control model restricted to trusted partners pending further safety testing.