日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

教示学習arXiv:1807.06583

教示学習のための解釈可能な潜在空間

Interpretable Latent Spaces for Learning from Demonstration

シェア:XThreadsFacebookLINEはてブBluesky

人間の教示と感覚入力の対応づけを通じて、学習した圧縮潜在表現を人間が解釈できる意味ラベルに整合させる手法を提案し、シミュレーションと実世界の物体データで有効性を示した。

著者: Yordan Hristov, Alex Lascarides, Subramanian Ramamoorthy

分類: cs.CV, cs.RO

原文アブストラクト

Effective human-robot interaction, such as in robot learning from human demonstration, requires the learning agent to be able to ground abstract concepts (such as those contained within instructions) in a corresponding high-dimensional sensory input stream from the world. Models such as deep neural networks, with high capacity through their large parameter spaces, can be used to compress the high-dimensional sensory data to lower dimensional representations. These low-dimensional representations facilitate symbol grounding, but may not guarantee that the representation would be human-interpretable. We propose a method which utilises the grouping of user-defined symbols and their corresponding sensory observations in order to align the learnt compressed latent representation with the semantic notions contained in the abstract labels. We demonstrate this through experiments with both simulated and real-world object data, showing that such alignment can be achieved in a process of physical symbol grounding.

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. 3GXO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
  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

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