Disambiguation of indicated objects by comparing the appearance of multiple objects

-Development of a multi-tasking robot for human life support (3)-

Abstract

In object detection using verbal instructions, ambiguous instructions may fail to identify objects. In this study, we developed an interactive object detection system that disambiguates instructions by obtaining the most useful appearance features for identifying the target object through dialogue, based on the results of appearance comparisons of multiple detected objects. Through experiments on the detection of commodities, we have confirmed that the proposed method can detect the indicated object even with fewer questions.