Sakana AI's Smart Cellular Bricks, featured in Scientific American, self-identify shape with no central brain
SakanaAILabs · x · 2026-09-17
Sakana AI announced its Smart Cellular Bricks research has been accepted by Nature Communications and featured in the latest Scientific American.
The system uses hundreds of simple cubic bricks, each running identical small Neural Cellular Automata and communicating only with physically connected neighbors. No brick knows its position or the overall shape, yet the collective converges on the correct global shape class and locates missing or damaged modules.
The work shows decentralized collective-intelligence principles hold up under noisy communication and module failures in physical hardware, including recognizing shape variations not seen in training — a first step toward taking collective intelligence beyond software.
Related event: Sakana AI's Smart Cellular Bricks Published in Nature Communications(2 posts)→
More from Embodied
- Drone-captured 400-ft guyed tower rebuilt as 3DGS via Metashape and LichtFeld Studio — janusch_patas · 2026-11-02
- Physical AI's real story: a 4-layer map of 15 companies behind humanoid robots — pdamodaran · 2026-11-02
- Autonomous's Harness Pro uses an ESP32-P4, not a mini PC, to monitor AI coding agents — dee_hw · 2026-11-02
- KAIST's QCP lets robot policies control execution quality in real time — kaist-ai · 2026-11-02
- ANYbotics begins customer deliveries of ANYmal X, first legged robot certified for explosive atmospheres — lukas_m_ziegler · 2026-11-02
- InSpatio opens China's first embodied simulation data center targeting 1M hours/month — 智东西 · 2026-11-02