Verified65% confidenceFactExact time
RT-2 first demonstrated the feasibility of the VLA architecture by discretizing robot actions into tokens and having the vision-language model directly output action sequences.
3
Sources
65%
Confidence
Long-term
Relevance
8/29/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedVLA directly connects pre-trained vision-language models with robot action policies, enabling robots to process natural language instructions, camera images, and low-level motion control in a unified manner.78% similarVerifiedThe current mainstream technical approach to embodied intelligence is the Vision-Language-Action model (VLA), which takes camera images and language instructions as joint inputs and directly outputs joint control signals for robotic arms.75% similarUnverifiedGoogle's RT-2 uses a pretrained vision-language model (such as PaLI) as the backbone to jointly encode image observations and natural language instructions, and generates discretized action tokens at the output end.73% similarUnverifiedRT-2 (Robotics Transformer 2) directly uses a vision-language model to generate robot control instructions end-to-end.69% similarPartially VerifiedLLaVA用一个简单的线性层连接视觉编码器和语言模型，证明了视觉指令微调的有效性67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/821177API
curl https://kongchang.com/api/v1/knowledge/claims/821177MCP
get_claim(id=821177)