日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

物体認識arXiv:2006.09306

物体とのインタラクションを通じて物体を学ぶ

Learning About Objects by Learning to Interact with Them

シェア:XThreadsFacebookLINEはてブBluesky

乳児の遊びによる学習に着想を得て、物理シミュレーション環境内でエージェントが自ら物体と相互作用し、外部教師なしで物体の発見や形状・相対質量を学習する枠組みを提案した。

著者: Martin Lohmann, Jordi Salvador, Aniruddha Kembhavi, Roozbeh Mottaghi

分類: cs.CV, cs.LG, cs.RO, eess.IV

原文アブストラクト

Much of the remarkable progress in computer vision has been focused around fully supervised learning mechanisms relying on highly curated datasets for a variety of tasks. In contrast, humans often learn about their world with little to no external supervision. Taking inspiration from infants learning from their environment through play and interaction, we present a computational framework to discover objects and learn their physical properties along this paradigm of Learning from Interaction. Our agent, when placed within the near photo-realistic and physics-enabled AI2-THOR environment, interacts with its world and learns about objects, their geometric extents and relative masses, without any external guidance. Our experiments reveal that this agent learns efficiently and effectively; not just for objects it has interacted with before, but also for novel instances from seen categories as well as novel object categories.

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. 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

OZ GAMING(GPU搭載BTOゲーミングPC)

OZ GAMING(GPU搭載BTOゲーミングPC)の公式広告バナーOZ GAMINGで完成品PCを見る ↗
PR本紙発行元 EmplifAI