日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

進化ロボティクスarXiv:2206.14916

生物と機械の進化の隔たり:混合微生物群集とロボットの対比

The Hiatus Between Organism and Machine Evolution: Contrasting Mixed Microbial Communities with Robots

シェア:XThreadsFacebookLINEはてブBluesky

混合微生物群集の進化におけるアフォーダンスの役割を論じ、自然進化が可能性空間を開放的に拡張するのに対し、人工進化はアルゴリズムの枠組みに制限されることを対比し、実験設定を提案する。

著者: Andrea Roli, Stuart A. Kauffman

分類: q-bio.PE, cs.AI, cs.RO

原文アブストラクト

Mixed microbial communities, usually composed of various bacterial and fungal species, are fundamental in a plethora of environments, from soil to human gut and skin. Their evolution is a paradigmatic example of intertwined dynamics, where not just the relations among species plays a role, but also the opportunities -- and possible harms -- that each species presents to the others. These opportunities are in fact \textit{affordances}, which can be seized by heritable variation and selection. In this paper, starting from a systemic viewpoint of mixed microbial communities, we focus on the pivotal role of affordances in evolution and we contrast it to the artificial evolution of programs and robots. We maintain that the two realms are neatly separated, in that natural evolution proceeds by extending the space of its possibilities in a completely open way, while the latter is inherently limited by the algorithmic framework it is defined. This discrepancy characterises also an envisioned setting in which robots evolve in the physical world. We present arguments supporting our claim and we propose an experimental setting for assessing our statements. Rather than just discussing the limitations of the artificial evolution of machines, the aim of this contribution is to emphasize the tremendous potential of the evolution of the biosphere, beautifully represented by the evolution of communities of microbes.

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