Learning to Generate Unambiguous Spatial Referring Expressions for Real-World Environments
Learning to Generate Unambiguous Spatial Referring Expressions for Real-World Environments
复制标题
学习为现实世界环境生成明确的空间引用表达式
DOI：
10.1109/iros40897.2019.8968510
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Iolanda Leite
中科院分区：
文献类型：
--
作者：
Fethiye Irmak Dogan;Sinan Kalkan;Iolanda Leite
以自然和明确的方式引用对象对于有效的人机交互至关重要。以往的研究主要集中在基于学习的指称表达的理解任务，而生成指称表达仍然主要限于基于规则的方法。在这项工作中，我们提出了一种两阶段的方法，该方法依赖于深度学习来估计空间关系，以自然和明确地用引用表达式描述对象。我们将我们的方法与模糊环境中的最新算法（例如，包括具有相似关系的非常相似的对象的环境）。我们表明，我们的方法生成的引用表达式，人们发现更准确（约30%更好），更喜欢使用（约32%更频繁）。
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 (~30% better) and would prefer to use (~32% more often).