Google DeepMind Launches Gemini Robotics 2 for Whole-Body Control
Google DeepMind's new Gemini Robotics 2 models let humanoid robots coordinate full-body movement, plan multi-step tasks and work together, shown on Apptronik's Apollo 2.
Read more →Vision-Language-Action Models
Vision-language-action (VLA) models are AI systems that combine visual perception, language understanding, and motor control in a single model, letting a robot interpret a scene, follow an instruction, and act on it directly. This hub covers VLA research, releases, and the labs and robots built on the approach.
Combine with:
What Is a Vision-Language-Action (VLA) Model — and Why It Matters
A vision-language-action (VLA) model turns a camera feed and a plain instruction directly into a robot's movements, replacing separate perception and control systems with one model.
Read more →