Google launches Gemini Robotics 2.5 VLA model with 96% pick-pack success
ZoubinGhahrama1 · x · 2026-11-11
Google DeepMind announced Gemini Robotics 2.5, its most capable vision-language-action model, expanding both the breadth of skills robots can learn and how fast they master them. It handles delicate tasks like using tongs and tying bows; tested with Apptronik and Mercedes-Benz, it achieved a 96% success rate for Apollo 2 humanoid pick-and-pack of automotive parts, and adds new real-time hazard and people avoidance safety features plus an open-source release.
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