日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

ナビゲーションarXiv:2206.08500

ナビゲーションエージェントは環境について何を学習するのか?

What do navigation agents learn about their environment?

シェア:XThreadsFacebookLINEはてブBluesky

視覚ナビゲーションエージェントの内部表現を解析する解釈システムiSEEを提案し、障害物回避や目標可視性、進捗などの情報が動的に符号化されていることを明らかにした。

著者: Kshitij Dwivedi, Gemma Roig, Aniruddha Kembhavi, Roozbeh Mottaghi

分類: cs.CV, cs.LG, cs.RO

原文アブストラクト

Today's state of the art visual navigation agents typically consist of large deep learning models trained end to end. Such models offer little to no interpretability about the learned skills or the actions of the agent taken in response to its environment. While past works have explored interpreting deep learning models, little attention has been devoted to interpreting embodied AI systems, which often involve reasoning about the structure of the environment, target characteristics and the outcome of one's actions. In this paper, we introduce the Interpretability System for Embodied agEnts (iSEE) for Point Goal and Object Goal navigation agents. We use iSEE to probe the dynamic representations produced by these agents for the presence of information about the agent as well as the environment. We demonstrate interesting insights about navigation agents using iSEE, including the ability to encode reachable locations (to avoid obstacles), visibility of the target, progress from the initial spawn location as well as the dramatic effect on the behaviors of agents when we mask out critical individual neurons. The code is available at: https://github.com/allenai/iSEE

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

MINISFORUM(ミニPC)

MINISFORUM(ミニPC)の公式広告バナーMINISFORUM公式ストアを見る ↗
PR本紙発行元 EmplifAI