Grounded Situation Models for Robots: Bridging Language, Perception, and Action

摘要

Our long-term objective is to develop robots that engage in natural language-mediated cooperative tasks with humans. To support this goal, we are developing an amodal representation called a grounded situation model (GSM), as well as a modular architecture in which the GSM resides in a centrally located module. We present an implemented system that allows of a range of conversational and assistive behavior by a manipulator robot. The robot updates beliefs about its physical environment and body, based on a mixture of linguistic, visual and proprioceptive evidence. It can answer basic questions about the present or past and also perform actions through verbal interaction. Most importantly, a novel contribution of our approach is the robot’s ability for seamless integration of both languageand sensor-derived information about the situation: For example, the system can acquire parts of situations either by seeing them or by “imagining ” them through descriptions given by the user: “There is a red ball at the left”. These situations can later be used to create mental imagery, thus enabling bidirectional translation between perception and language. This work constitutes a step towards robots that use situated natural language grounded in perception and action. Robots, Language and Modularity As robots grow in ability and complexity, natural language is likely to assume an increasingly central role in humanrobot interaction. Our current work is part of a larger effort to develop conversational interfaces for interactive robots