Google's Gemini Robotics 2.5 hits 96% pick-and-pack success on Mercedes-Benz lines
ZoubinGhahrama1 · x · 2026-11-11
Google DeepMind unveiled Gemini Robotics 2.5, its most capable vision-language-action model yet, expanding both the breadth of robot skills and how fast robots acquire them.
- Trained with Gemini 4 Argon: robots practice thousands of times in simulation and even review replays of their own mistakes to fix technique, adding hundreds of dexterous tasks in just months.
- Tested across 200+ distinct tasks, from everyday tools to delicate, flexible objects.
- In a real-world proof of concept on Mercedes-Benz production lines, Apptronik's Apollo 2 humanoid picked and packed auto parts with a 96% success rate.
- Improved physical-safety steerability plus a new benchmark for robotics-specific adversarial jailbreaks.
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