Nature Machine Intelligence: Cybernetics and interoception framework for embodied AI agents
AnnaCiaunica · x · 2026-09-25
A Nature Machine Intelligence editorial highlights new work combining biological interoception with cybernetics, reinforcement learning, and neuroscience to build autonomous, adaptive embodied AI agents. Building on Norbert Wiener's 1940s cybernetics, the framework has agents continuously monitor internal states—like living organisms regulating temperature or glucose—and adapt their actions accordingly, closing the feedback loop needed for genuine embodied autonomy.
More from Embodied
- AMD and Perplexity team up to bring Perplexity Portable Computer to Ryzen AI Halo — AnushElangovan · 2026-09-25
- Google Glass founder: glasses that block eye contact will never go mainstream — Scobleizer · 2026-09-25
- 19 Unitree Humanoids Dance With 120 Performers Before 10,000+ in Shanghai's Record Live Show — rohanpaul_ai · 2026-09-25
- Rob LeClerc: AI Fear Will Spike Once Humanoid Robots Get Truly Capable — robleclerc · 2026-09-25
- LeWAM: Lightweight World Action Model Hits 92.28% Success on RoboTwin 2.0 — udmrzn · 2026-09-25
- Blind Stargardt patient reads a letter again after PRIMA implant in Science clinical trial — lukaszkaiser · 2026-09-25