Chris Paxton· @chris_j_paxton · X·· 4 hours agoEditorial score65
Large models are changing assumptions about how intelligence for robotics will work
Summary
Chris Paxton discusses how large models are transforming the approach to robotic intelligence, with Gemini 4 Argon enabling real-world physical learning by autonomously generating simulation code from human demonstrations, leading to successful real-world performance on a humanoid robot.
Source: Chris Paxton — X Robotics · Read original article ↗
Article text · Original source · English
Large models really are changing a lot of the assumptions about how intelligence for robotics is going to work
In robotics, Gemini 4 Argon is speeding up real-world physical learning. We let Argon watch a video of a human playing cornhole. It mapped the environment, calculated whole-body joint movements, and autonomously built the simulation code to practice. When transferred to Apptronik’s Apollo humanoid, the robot sank seven straight shots in a real-world trial.View the quoted post on X
Source：Chris Paxton · x.com