日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

最適化arXiv:2308.04571

ペアワイズなユーザー選好に基づくアルゴリズム最適化

Optimizing Algorithms From Pairwise User Preferences

シェア:XThreadsFacebookLINEはてブBluesky

ユーザーが2つの結果を比較するだけで、高次元のアルゴリズムパラメータを最適化するSortCMAを提案し、深度センサ調整やソーシャルナビゲーションに適用した。

著者: Leonid Keselman, Katherine Shih, Martial Hebert, Aaron Steinfeld

分類: cs.RO, cs.CV, cs.HC

原文アブストラクト

Typical black-box optimization approaches in robotics focus on learning from metric scores. However, that is not always possible, as not all developers have ground truth available. Learning appropriate robot behavior in human-centric contexts often requires querying users, who typically cannot provide precise metric scores. Existing approaches leverage human feedback in an attempt to model an implicit reward function; however, this reward may be difficult or impossible to effectively capture. In this work, we introduce SortCMA to optimize algorithm parameter configurations in high dimensions based on pairwise user preferences. SortCMA efficiently and robustly leverages user input to find parameter sets without directly modeling a reward. We apply this method to tuning a commercial depth sensor without ground truth, and to robot social navigation, which involves highly complex preferences over robot behavior. We show that our method succeeds in optimizing for the user's goals and perform a user study to evaluate social navigation results.

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