Berkeley's S1 robot shows self-correction: realigns a misattached wheel on its own

thisdudelikesAI · x · 2026-09-10

Berkeley professor Deepak Pathak demoed his S1 robot's error recovery: when a wheel attached via video prompt didn't align properly during deployment, S1 noticed and realigned it itself. Pathak explains that S1 watches the prompt, understands the goal, and improvises to achieve it — "you learn a lot more about AI when it screws up a task."

Related event: Skild's S1 Robot Fixes Its Own Mistakes in Wheel-Mounting Demo(2 posts)→

Original post →

More from Embodied

Embodied channel →