Google DeepMind Launches Gemini Robotics 2.5 With 96% Success on Mercedes Lines
bousmalis · x · 2026-11-11
Google DeepMind introduced Gemini Robotics 2.5, its most capable vision-language-action model to date, built on Gemini 4 Argon and validated across 200+ distinct tasks.
Three key advances
- Dexterity: robots handle significantly more tasks, from everyday tools to delicate, flexible objects
- Reliability: in a real-world proof-of-concept on Mercedes-Benz production lines, the model helped Apptronik's Apollo 2 humanoid pick and pack automotive parts with a 96% success rate
- Safety: improved physical safety steerability plus a new benchmark for robotics-specific adversarial jailbreaks
The model is rolling out to partners, with four live demos shown at CoRL.
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