日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

認知ロボティクスarXiv:2002.04021

物体分解型認知プログラムによる高速概念推論モデル

A Model of Fast Concept Inference with Object-Factorized Cognitive Programs

シェア:XThreadsFacebookLINEはてブBluesky

ロボットが少数の画像から概念を素早く推論できるよう、物体分解とサブゴール化のヒューリスティクスを取り入れて探索を高速化し、精度と説明可能性を向上させた。

著者: Daniel P. Sawyer, Miguel Lázaro-Gredilla, Dileep George

分類: cs.AI, cs.RO

原文アブストラクト

The ability of humans to quickly identify general concepts from a handful of images has proven difficult to emulate with robots. Recently, a computer architecture was developed that allows robots to mimic some aspects of this human ability by modeling concepts as cognitive programs using an instruction set of primitive cognitive functions. This allowed a robot to emulate human imagination by simulating candidate programs in a world model before generalizing to the physical world. However, this model used a naive search algorithm that required 30 minutes to discover a single concept, and became intractable for programs with more than 20 instructions. To circumvent this bottleneck, we present an algorithm that emulates the human cognitive heuristics of object factorization and sub-goaling, allowing human-level inference speed, improving accuracy, and making the output more explainable.

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