実環境向けの曖昧さのない空間参照表現の生成学習
Learning to Generate Unambiguous Spatial Referring Expressions for Real-World Environments
深層学習で物体間の空間関係を推定し、自然で曖昧さのない参照表現を生成する2段階手法を提案し、類似物体が多い環境でも従来法より正確で好まれる表現を生成できることを示した。
著者: Fethiye Irmak Doğan, Sinan Kalkan, Iolanda Leite
分類: cs.RO, cs.CV
原文アブストラクト
Referring to objects in a natural and unambiguous manner is crucial for effective human-robot interaction. Previous research on learning-based referring expressions has focused primarily on comprehension tasks, while generating referring expressions is still mostly limited to rule-based methods. In this work, we propose a two-stage approach that relies on deep learning for estimating spatial relations to describe an object naturally and unambiguously with a referring expression. We compare our method to the state of the art algorithm in ambiguous environments (e.g., environments that include very similar objects with similar relationships). We show that our method generates referring expressions that people find to be more accurate ($\sim$30% better) and would prefer to use ($\sim$32% more often).
