Unverified50% confidenceFactExact time
Action chunking was first proposed in the field of robot imitation learning, with the representative work being ACT (Action Chunking with Transformers)
1
Sources
50%
Confidence
Long-term
Relevance
10/14/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe developer is developing a complete motion simulation for a self-built robot, with the goal of loading the trained model onto a 3D-printed robot.69% similarUnverifiedACT uses a Transformer architecture to process visual and proprioceptive inputs, and originally achieved excellent results on dexterous manipulation tasks with robotic arms.69% similarUnverifiedACT（Action Chunking with Transformers）由斯坦福大学Mobile ALOHA团队提出，使用Transformer架构一次性预测未来一段时间内的动作块69% similarUnverifiedThe core method of ChunkAct is to introduce action chunking into agentic robotics, where a single LLM call at online execution time initiates an entire chunk of chained primitives, returning control to the planner only upon failure66% similarUnverified行为克隆（Behavior Cloning）通过让人类操控机器人完成任务并记录轨迹数据，使机器人策略网络直接从专家演示中学习65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1028140API
curl https://kongchang.com/api/v1/knowledge/claims/1028140MCP
get_claim(id=1028140)