日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

マニピュレーションarXiv:2402.07127

見て学ぶ:ロボットマニピュレーションのための動画ベース学習アプローチのレビュー

Learning by Watching: A Review of Video-based Learning Approaches for Robot Manipulation

シェア:XThreadsFacebookLINEはてブBluesky

ロボットのマニピュレーションスキルを、オンライン上の大量の人間動画を視聴することで学習する動画ベース学習の研究をレビューし、その基礎技術、利点、評価指標、課題をまとめたサーベイ。

著者: Chrisantus Eze, Christopher Crick

分類: cs.RO, cs.AI, cs.CV, cs.LG

原文アブストラクト

Robot learning of manipulation skills is hindered by the scarcity of diverse, unbiased datasets. While curated datasets can help, challenges remain in generalizability and real-world transfer. Meanwhile, large-scale "in-the-wild" video datasets have driven progress in computer vision through self-supervised techniques. Translating this to robotics, recent works have explored learning manipulation skills by passively watching abundant videos sourced online. Showing promising results, such video-based learning paradigms provide scalable supervision while reducing dataset bias. This survey reviews foundations such as video feature representation learning techniques, object affordance understanding, 3D hand/body modeling, and large-scale robot resources, as well as emerging techniques for acquiring robot manipulation skills from uncontrolled video demonstrations. We discuss how learning only from observing large-scale human videos can enhance generalization and sample efficiency for robotic manipulation. The survey summarizes video-based learning approaches, analyses their benefits over standard datasets, survey metrics, and benchmarks, and discusses open challenges and future directions in this nascent domain at the intersection of computer vision, natural language processing, and robot learning.

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. 2newmo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
  3. 3NVIDIA、CoRLでGR00T 2とIsaac Lab 3.0を発表新製品・発表
  4. 4GXO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
  5. 5Google DeepMind、ロボット向けAIを発表新製品・発表

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