News
GEN-1 Foundation Model Boosts Robot Reliability and Speed
Generalist introduced GEN-1, a multimodal robot learning model that controls robot actions in real time. It is trained on over 500,000 hours of physical interaction data,
VLA
News
Universal Robots and Scale AI Bring AI Model Training Onto The Factory Floor
Universal Robots introduced a system that captures synchronized data from robots in production environments, rather than in separate lab setups. Built with Scale AI, it is designed for customers
News
Figure Releases Helix 02, a Full-Body Foundation Model for Humanoid Control
Figure has released Helix 02, a major upgrade to its foundation model that brings full-body autonomy to its existing humanoid platform. Building on the previous Helix model which controlled the upper body from vision inputs, Helix 02 now integrates lower body
News
Microsoft Unveils Rho-alpha to Bridge Language, Vision, and Touch in Robotics
Microsoft has introduced Rho-alpha, a vision-language-action model that lets robots follow spoken or written instructions like “Insert the plug” or “Turn the knob to position 5.” It combines visual input with a sense of touch to guide actions
News
LG’s CLOiD Robot Tackles Housework with Vision-Led Physical AI
LG Electronics has unveiled CLOiD, its home robot that aims to help with daily chores. Announced at CES, the humanoid robot moves autonomously through kitchens, laundry rooms, and living spaces, using its arms and hands to carry out routine household tasks.
News
mimic-video Uses Pretrained Video Models to Improve Robot Learning Efficiency by 10x
mimic-video is a new robot control system from teams at mimic robotics, Microsoft Zurich, ETH Zurich, ETH AI Center, and UC Berkeley. The team says that the new model helps robots learn faster and with less training data.