日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

模倣学習arXiv:2409.06615

実行ミスマッチ下でのワンショット模倣学習

One-Shot Imitation under Mismatched Execution

シェア:XThreadsFacebookLINEはてブBluesky

人間とロボットの軌道を系列レベルの最適輸送コストで自動対応付けし、ペアデータなしで長期タスクの模倣を可能にするRHyMEを提案した。

著者: Kushal Kedia, Prithwish Dan, Angela Chao, Maximus Adrian Pace, Sanjiban Choudhury

分類: cs.RO, cs.AI, cs.LG

原文アブストラクト

Human demonstrations as prompts are a powerful way to program robots to do long-horizon manipulation tasks. However, translating these demonstrations into robot-executable actions presents significant challenges due to execution mismatches in movement styles and physical capabilities. Existing methods for human-robot translation either depend on paired data, which is infeasible to scale, or rely heavily on frame-level visual similarities that often break down in practice. To address these challenges, we propose RHyME, a novel framework that automatically pairs human and robot trajectories using sequence-level optimal transport cost functions. Given long-horizon robot demonstrations, RHyME synthesizes semantically equivalent human videos by retrieving and composing short-horizon human clips. This approach facilitates effective policy training without the need for paired data. RHyME successfully imitates a range of cross-embodiment demonstrators, both in simulation and with a real human hand, achieving over 50% increase in task success compared to previous methods. We release our code and datasets at https://portal-cornell.github.io/rhyme/.

関連論文

  1. 1Boston Dynamics、車輪付きAtlasの研究試作機を紹介研究・技術
  2. 2GXOとApptronik、Apolloの物流現場試験を拡大 最大1,000台の展開を構想量産・展開
  3. 3newmoとKDDIが資本業務提携 2028年に堺市で自動運転タクシー商用化目指す提携・買収
  4. 4NVIDIA、CoRLでGR00T 2とIsaac Lab 3.0を発表新製品・発表
  5. 5UC BerkeleyとNVIDIAの研究者、AIエージェントでロボット制御コードを仮想環境で改善研究・技術

PR・アフィリエイト広告

FRONTIER(GPU搭載BTOパソコン)

FRONTIER(GPU搭載BTOパソコン)の公式広告バナーFRONTIERでGPU搭載PCを見る ↗
PR本紙発行元 EmplifAI