Gemini Robotics 2.5 ships with 96% pick-and-pack success on Mercedes lines
emmanuelvivier · x · 2026-11-12
Google DeepMind unveiled Gemini Robotics 2.5, its most capable vision-language-action model, tested across 200+ tasks. Key gains: broader dexterity (everyday tools, delicate and flexible objects); reliability — Apptronik's Apollo 2 humanoid hit a 96% success rate picking and packing automotive parts in a real Mercedes-Benz production-line proof of concept; and safety, with improved physical steerability plus a new benchmark for robotics-specific adversarial jailbreaks. Rolling out to partners to move robots into unstructured real-world environments.
More from Embodied
- AMD runs MolmoAct2 robot policy locally on a Ryzen AI Max+ 395 mini PC — DJiafei · 2026-11-12
- World Labs and AMD enter robotics, Li Fei-Fei appears at CoRL — breadli428 · 2026-11-12
- SimEX: agents learn manipulation skills in imperfect simulation and transfer them to real robots — chris_j_paxton · 2026-11-12
- Feather Robotics' $33,000 semi-humanoid tried hands-on: 15 lb payload per arm — chris_j_paxton · 2026-11-12
- Lie bracket visualized: how second-order residue lets wheeled robots move without sliding — burny_tech · 2026-11-12
- UCLA's TriMI: a $800 tri-modal robotic hand interface for demos, teleop and execution — chris_j_paxton · 2026-11-12