FANUC cobot takes plain-language commands, trained in Isaac Sim before hardware existed
lukas_m_ziegler · x · 2026-09-25
At AMB, a FANUC CRX cobot takes natural-language pick commands: vision-based object recognition plus NVIDIA's GR00T vision-language-action model plans the grasp (Cosmos used for some applications). The team developed against an Isaac Sim digital twin since hardware wasn't available, using the same simulation to prep fine-tuning data — so the robot learned its task before the physical arm existed, decoupling software progress from hardware availability.
More from Embodied
- Smart light fixtures as an always-powered AI sensor platform for the home — K-enthusiast24 · 2026-09-25
- Meta is putting its Muse agent into AI glasses, aiming to make the interface disappear — TansuYegen · 2026-09-25
- Agents turn stock ESP32 kits into anything: why familiar forms guide what to build — genmon · 2026-09-25
- The Gaussian is enough: Toyota study finds non-Gaussian priors don't help fine-tuning LBMs — _krishna_murthy · 2026-09-25
- AR Yu-Gi-Oh built on Snap's Specs glasses uses AI to battle with physical cards — TheZachMueller · 2026-09-25
- Robot learning paper club #5: π0.5 fine-tuned on a real manufacturing task — DominiqueCAPaul · 2026-09-25