意味的制約下での未知部品を用いた新規構造の組み立て学習
Learning to Assemble Novel Structures with Unfamiliar Parts under Semantic Constraints
訓練時には存在しなかった意味的制約（どの部品タイプや特徴が有効な構造を作るか）を、対話とデモンストレーションから学習し、新しい構造を組み立てるニューロシンボリックアーキテクチャを提案した。
著者: Jonghyuk Park, Alex Lascarides, Subramanian Ramamoorthy
分類: cs.AI
原文アブストラクト
This paper describes a neurosymbolic architecture for learning to assemble novel structures using evidence from embodied conversations and task demonstrations. We focus on scenarios where an agent encounters, after deployment, semantic constraints on structures--in other words, constraints as to which part types and features make valid structures--that were not available during training, and where it is initially unaware of the relevant structure and component part concepts. The agent must acquire and exploit such knowledge through user interactions while attempting assembly. We study this setting in a simulated toy truck assembly domain, learning from symbolic evidence encoded in natural language and from dense visual observations. Our experiments show that communicating semantic constraints through natural language (e.g., "dump trucks have a dumper") yields more data-efficient online adaptation than relying only on task demonstrations and/or only naming the parts through natural language.