日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

VLAarXiv:2503.02012

事前学習済み埋め込みを行動仕様記述の仕組みとして用いる手法

Pretrained Embeddings as a Behavior Specification Mechanism

シェア:XThreadsFacebookLINEはてブBluesky

知覚モデルを用いるシステムの振る舞いを、理想と観測の埋め込み間の距離で記述する新しい時相論理ETLを提案し、基盤モデル駆動ロボットの計画タスクで有効性を示した。

著者: Parv Kapoor, Abigail Hammer, Ashish Kapoor, Karen Leung, Eunsuk Kang

分類: cs.AI, cs.RO, cs.SE

原文アブストラクト

We propose an approach to formally specifying the behavioral properties of systems that rely on a perception model for interactions with the physical world. The key idea is to introduce embeddings -- mathematical representations of a real-world concept -- as a first-class construct in a specification language, where properties are expressed in terms of distances between a pair of ideal and observed embeddings. To realize this approach, we propose a new type of temporal logic called Embedding Temporal Logic (ETL), and describe how it can be used to express a wider range of properties about AI-enabled systems than previously possible. We demonstrate the applicability of ETL through a preliminary evaluation involving planning tasks in robots that are driven by foundation models; the results are promising, showing that embedding-based specifications can be used to steer a system towards desirable behaviors.

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