Gemini Robotics 2
Gemini Robotics 2 is a family of three robotics models announced by Google DeepMind on July 30, 2026: a vision-language-action (VLA) model of the same name, an embodied reasoning model called Gemini Robotics…
Robotics
Explore robots, the companies building them, and the methods used to sense, learn, and act.
Explore articles
Browse subtopics: Multimodal AI
Articles that also belong to these categories. Counts cover all of Robotics.
All articles (489)Humanoid Robots (234)AI Companies (76)Embodied AI (62)AI Hardware (44)Robotics Companies (40)AI Models (31)Robot Hardware (30)Open Source AI (28)Chinese AI (27)Artificial Intelligence (21)NVIDIA (19)Autonomous Vehicles (18)Reinforcement Learning (17)Computer Vision (14)Machine Learning (12)People (9)Developer Tools (8)Healthcare AI (8)AI Tools & Products (7)Multimodal AI (7)Physical AI (7)World Models (7)Google DeepMind (6)AI History (5)Data & Datasets (5)AI Agents (4)AI Infrastructure (4)AI Safety (4)Algorithms (4)Deep Learning (4)Enterprise AI (4)AI Benchmarks (3)AI Events (3)Companies (3)Generative AI (3)AI Policy & Regulation (2)Defense AI (2)Research Organizations (2)Sensors (2)Statistics (2)Training & Optimization (2)AI Ethics (1)Conversational AI (1)Diffusion Models (1)Google (1)Hardware (1)Large Language Models (1)Mathematics (1)Meta AI (1)OpenAI (1)Transformer Models (1)Universities (1)Venture Capital (1)
Showing 1-7 of 7 articles
Generalist GEN-1
GEN-1 is an embodied robot foundation model and control system developed by Generalist AI.
Generalist GEN-1.5
Generalist GEN-1.5 is a proprietary robot foundation model announced by Generalist AI on August 19, 2026.
Robostral Navigate
Robostral Navigate is an 8-billion-parameter vision language model developed by Mistral AI for instruction-following robot navigation.
SmolVLA
SmolVLA (Small Vision-Language-Action) is a compact, open-source vision-language-action model (VLA) for robotics developed by Hugging Face and released in June 2025.
T-Rex: Tactile-Reactive Dexterous Manipulation
T-Rex: Tactile-Reactive Dexterous Manipulation is a 2026 robot learning research system for contact-rich, bimanual manipulation.
Vision-language-action model
A vision-language-action model (VLA model, or VLA) is a machine-learning model for robotics that uses visual observations and a natural-language instruction to generate actions a robot can execute.