Object Recognition Integrating Autonomous and Interactive Methods Based on the Analysis of Human Expressions of Object Attributes and Spatial Relationships

服务机器人需要能够识别位于复杂环境中的对象。虽然最近在这方面取得了一些进展，但自主视觉系统仍然很难识别自然条件下的物体。在本研究中，我们提出了一种交互式目标识别系统。在这个系统中，机器人要求用户口头提供它无法检测到的对象的信息。特别是，它根据情况向用户询问关于对象之间的颜色和空间关系的问题。实验结果证实了该交互系统的有效性和有效性。

Service robots need to be able to recognize objects located in complex environments. Although there has been recent progress in this area, it remains difficult for autonomous vision systems to recognize objects in natural conditions. In this research, we have proposed an interactive object recognition system. In this system, the robot asks the user to verbally provide information about an object that it cannot detect. In particular, it asks the user questions regarding color and spatial relationship between objects depending on the situation. Experimental results confirm the usefulness and efficiency of our interaction system.