Gemini Robotics 2.5 accelerates real-world general dexterity

Summary

Google DeepMind introduced Gemini Robotics 2.5, a vision-language-action model that increases the range of skills robots can learn and the speed of learning them. Tested across more than 200 tasks, it reached a 96% success rate in a proof-of-concept with Apptronik's Apollo 2 humanoid on Mercedes-Benz production lines, and it is rolling out to robotics partners.

Topics

• Robotics and embodied AI

Related items

• InfoWe don’t understand whether GDM intentionally trains on CoTSame vendor · Redwood Research Blog
• Infollm-gemini 0.36Same vendor · Simon Willison's Weblog
• InfoGoogle Widens Gemini 4 Carbon Access After AI Agents Verify Signal CodeSame vendor · SecurityWeek
• InfoGemini 4 Carbon is now availableSame vendor · DeepMind Safety Research
• InfoGoogle releases Gemini 4 Carbon with agent ‘swarm’ featureSame vendor · The Verge (AI)