Gemini Robotics 2.5 hits the factory floor: 96% success sorting parts on Mercedes-Benz lines
CyberRobooo · x · 2026-11-11
Google DeepMind unveiled Gemini Robotics 2.5, its most capable vision-language-action (VLA) model, with three key advances:
- Dexterity: robots handle far more tasks, from everyday tools to delicate flexible objects, tested across 200+ distinct tasks.
- Reliability: in a real POC on Mercedes-Benz production lines, Apptronik's Apollo 2 humanoid picked automotive brackets from bulk bins and sequenced them into trays, hitting 96% success after a few weeks of post-training with almost no lab-to-line drop.
- Safety: improved physical safety steerability plus a new benchmark for robotics-specific adversarial jailbreaks.
Rolling out to robot partners, aided by Gemini 4 Argon for research acceleration.
More from Embodied
- NVIDIA's VLA driving model hits 20 decisions/s on Jetson Thor after Embedl optimization — No-Dragonfly6246 · 2026-11-13
- UC Berkeley's ATLAS drives humanoid robots from a single human video, no VLA or task-specific training — ChongZzZhang · 2026-11-13
- Roboticist: You Can't Do Robotics Without NVIDIA's Stack; Jensen's Long Bets Are Underrated — tianyin_xu · 2026-11-13
- US humanoids span pilots, early commercial expansions and production ramps amid FCC import limits — ingliguori · 2026-11-13
- Invictus Robotics unveils Aeras, a force-controlled aerial manipulation drone for industrial work — lukas_m_ziegler · 2026-11-13
- Zero-HLM: 45 sim demos become 4,800, humanoid zero-shot sim2real hits 69% vs 23% baseline — 机器之心 · 2026-11-13