Unverified50% confidenceFactExact time
Google's SayCan project, proposed in 2022, uses LLM knowledge as a value function to guide robot behavior, with action selection determined by multiplying LLM scores by the success probability of skill modules.
1
Sources
50%
Confidence
Long-term
Relevance
9/1/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedGoogle于2022年发布SayCan，让语言模型仅负责生成可行动作序列，具体执行交由预训练底层技能策略完成74% similarUnverifiedSayCan由Google DeepMind于2022年提出，将语言模型与机器人动作库结合72% similarUnverified将大语言模型接入机器人的典型范式包括Google的SayCan（用LLM分解任务后调用底层运动原语）和RT-2（端到端生成控制指令）68% similarVerified思维链（Chain-of-Thought）提示技术由Google Research于2022年提出68% similarUnverifiedIn a 2022 study, Google Research systematically summarized the concept of emergent capabilities, finding that abilities such as chain-of-thought reasoning and few-shot learning are absent in small models but suddenly emerge after the parameter count crosses a critical threshold.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/840653API
curl https://kongchang.com/api/v1/knowledge/claims/840653MCP
get_claim(id=840653)