Expired50% confidenceFactExact time
DeepMind launched the Auto-RT project, combining large language models with the robot control model RT-2, using the LLM as a task planning layer to decompose natural language instructions into low-level action sequences.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/8/2026
First Seen
Valid until: 10/6/2026(expired)
Sources
A Beginner's Guide to AI Agents: How Large Models Are Driving a New Computing Revolution
bilibiliAgent教程7/2/2026
Related Claims
VerifiedGoogle DeepMind的RT-2首次将视觉-语言模型直接用于生成机器人动作指令84% similarUnverifiedDeepMind developed the VLA (Vision-Language-Action model) system, which treats the robot's physical actions on equal footing with visual tokens and language tokens.74% similarUnverified现代大语言模型（LLM）属于深度学习的范畴72% similarUnverifiedDeepMind's RT series models and Stanford's Mobile ALOHA project represent cutting-edge practices in the direction of embodied intelligence.72% similarUnverifiedDeepMind layered a Gemini model on top of its VLA, allowing users to issue instructions directly in natural language so the robot can carry on a conversation while working.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/282613API
curl https://kongchang.com/api/v1/knowledge/claims/282613MCP
get_claim(id=282613)