Unverified70% confidenceFactExact time
Google DeepMind's RT series includes RT-1, RT-2, and RT-X: RT-1 trains foundational manipulation capabilities, RT-2 links VLMs with robot actions, and RT-X achieves stronger generalization through cross-platform data sharing.
2
Sources
70%
Confidence
Long-term
Relevance
9/1/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedRT-2是Google DeepMind的Robotics Transformer 2，与OpenVLA等大规模机器人基础模型需要覆盖多样化场景、包含精确空间信息和语义标注的真实世界数据76% similarUnverifiedGoogle DeepMind's RT series models and Meta's projects are both exploring the use of world models to replace or supplement traditional physics simulators73% similarVerifiedGoogle DeepMind's RT-2 was the first to directly use a vision-language model to generate robot action commands.70% similarUnverifiedRepresentative VLA model works include Google DeepMind's RT-2 and Stanford's OpenVLA.70% similarUnverifiedVision-Language-Action (VLA) models are the latest paradigm for embodied intelligence, with representative works including Google DeepMind's RT-2 and Physical Intelligence's π0.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/840652API
curl https://kongchang.com/api/v1/knowledge/claims/840652MCP
get_claim(id=840652)