Unverified50% confidenceBenchmarkExact time
The research team deployed the policy on a real Stretch 3 robot, achieving a 63.9% success rate on a subset of 12 tasks, compared to a simulation success rate of 66.7% on those same tasks.
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
Unverified该项目中roboreg负责机器人位姿估计，OpTaS负责实时求解带约束的导纳任务63% similarUnverifiedPolicy answers the question of what action a robot should take in order to complete a given task.62% similarUnverifiedAgent team tasks have three states: Pending, In Progress, and Completed.61% similarUnverifiedThe core research methodology was to have three agents each execute on a unified task set, recording the type, frequency, and sequence of each tool call to form comparable behavioral profiles.59% similarUnverifiedThe bipedal balancing robot was trained entirely on 100% synthetic data and successfully achieved policy transfer from a simulated environment to the real physical world.58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1002348API
curl https://kongchang.com/api/v1/knowledge/claims/1002348MCP
get_claim(id=1002348)