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:2108.01034

物体押し出し方策学習のための効率的な画像間変換HourGlassベースアーキテクチャ

An Efficient Image-to-Image Translation HourGlass-based Architecture for Object Pushing Policy Learning

シェア:XThreadsFacebookLINEはてブBluesky

物体押し出し方策の学習を画像間変換問題として捉え、HourGlass型ネットワークとDQNを組み合わせることで、未知のダイナミクスを持つ物体の押し出しタスクをより速く高精度に学習できることを示した論文。

著者: Marco Ewerton, Angel Martínez-González, Jean-Marc Odobez

分類: cs.RO, cs.AI, cs.LG

原文アブストラクト

Humans effortlessly solve pushing tasks in everyday life but unlocking these capabilities remains a challenge in robotics because physics models of these tasks are often inaccurate or unattainable. State-of-the-art data-driven approaches learn to compensate for these inaccuracies or replace the approximated physics models altogether. Nevertheless, approaches like Deep Q-Networks (DQNs) suffer from local optima in large state-action spaces. Furthermore, they rely on well-chosen deep learning architectures and learning paradigms. In this paper, we propose to frame the learning of pushing policies (where to push and how) by DQNs as an image-to-image translation problem and exploit an Hourglass-based architecture. We present an architecture combining a predictor of which pushes lead to changes in the environment with a state-action value predictor dedicated to the pushing task. Moreover, we investigate positional information encoding to learn position-dependent policy behaviors. We demonstrate in simulation experiments with a UR5 robot arm that our overall architecture helps the DQN learn faster and achieve higher performance in a pushing task involving objects with unknown dynamics.

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

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