ロボットナビゲータによる自然な説明生成
WHY: Natural Explanations from a Robot Navigator
認知ベースの自律ナビゲーションシステムが、常識・定性推論・学習した空間モデルに基づき、移動中の判断を自然言語でリアルタイムに説明する手法を提案した。
著者: Raj Korpan, Susan L. Epstein, Anoop Aroor, Gil Dekel
分類: cs.AI, cs.CL, cs.HC, cs.RO
原文アブストラクト
Effective collaboration between a robot and a person requires natural communication. When a robot travels with a human companion, the robot should be able to explain its navigation behavior in natural language. This paper explains how a cognitively-based, autonomous robot navigation system produces informative, intuitive explanations for its decisions. Language generation here is based upon the robot's commonsense, its qualitative reasoning, and its learned spatial model. This approach produces natural explanations in real time for a robot as it navigates in a large, complex indoor environment.
