WORLDWIDE_SanGuai / Research bulletin

[ worldwide.arakne.de ]

世界很大,讀一小點。

SanGuai 的三日研究佈告板。每天更新,讀完就走。

EST. 202672H上架 72 小時
人工智慧 / 2611.17060

Ropedia Xperience 2:擴展實體 AI 環境與行為的黃金標準

Ropedia Xperience 2: A Gold Standard for Scaling Physical AI Environments and Behaviors

作者: Hao Li, Fangzhou Hong, Zhaoxi Chen, Hui En Pang, Kairui Hu, Mingze Sun, Runmao Yao, Xinhao Ji et al.論文發布: 2026-11-12離架倒數: 63 小時

研究速讀

作者提出 Ropedia Xperience 2,釋出 1,589 個公制尺度 3D 掃描與 4,230 段第一人稱錄影、涵蓋 74 項任務共 131 小時。他們主張每筆資料可轉為可互動模擬環境、將人體動作重定向為機器人軌跡,並以虛擬遙操作產生更多行為,作為實體 AI 資料蒐集的黃金標準。

值得留意

  1. 釋出 1,589 個公制尺度 3D 掃描與 4,230 段第一人稱錄影,涵蓋 74 項任務、共 131 小時。
  2. 作者稱場景可轉為物理互動模擬環境,人體動作可重定向為全身機器人軌跡。
  3. 另稱可透過虛擬遙操作與自動長程軌跡生成取得更多機器人行為。

閱讀限制

僅依標題與摘要整理,未讀全文,無法核實資料品質、轉換流程細節或作者主張的實際效果。

原始摘要 [EN]

Large foundation models such as GPT-6 Astra and Claude Fable 5.1 have recently been shown to control robots directly from visual observations. They nevertheless remain brittle on long-horizon, contact-rich tasks in real-world environments. Further progress depends on two complementary resources: demonstrations of human behavior that supervise how tasks are performed, and interactive environments in which policies can be rolled out, evaluated, and improved in closed loop. Language models have advanced along well-characterized scaling laws; the corresponding question for physical AI is how capability scales with environments and behaviors, which first requires identifying which data to scale and how to produce and reuse such data continuously. To address this question, we introduce Ropedia Xperience 2, comprising 1,589 released metric-scale 3D scans and a collection of 4,230 egocentric recordings of 74 tasks (131 hours). We further show that each capture can be repurposed for robot learning: scenes are converted into physically interactive simulation environments, human motion is retargeted to whole-body robot trajectories, and additional robot behaviors are obtained through virtual teleoperation and automated long-horizon trajectory generation. We propose this joint capture of environments and behaviors as a gold standard for physical AI data collection, laying a data foundation for establishing scaling laws over environments and behaviors.

AI 摘要僅根據公開標題與摘要整理;研究結論來自作者,請以原文為準。