Grounding language in perception for scene conceptualization in autonomous robots

In order to behave autonomously, it is desirable for robots to have the ability to use human supervision and learn from different input sources (perception, gestures, verbal and textual descriptions etc). In many machine learning tasks, the supervision is directed specifically towards machines and hence is straight forward clearly annotated examples. But this is not always very practical and recently it was found that the most preferred interface to robots is natural language. Also the supervision might only be available in a rather indirect form, which may be vague and incomplete. This is frequently the case when humans teach other humans since they may assume a particular context and existing world knowledge. We explore this idea here in the setting of conceptualizing objects and scene layouts. Initially the robot undergoes training from a human in recognizing some objects in the world and armed with this acquired knowledge it sets out in the world to explore and learn more higher level concepts like static scene layouts and environment activities. Here it has to exploit its learned knowledge and ground language into perception to use inputs from different sources that might have overlapping as well as novel information. When exploring, we assume that the robot is given visual input, without explicit type labels for objects, and also that it has access to more or less generic linguistic descriptions of scene layout. Thus our task here is to learn the spatial structure of a scene layout and simultaneously visual object models it was not trained on. In this paper, we present a cognitive architecture and learning framework for robot learning through natural human supervision and using multiple input sources by grounding language in perception.