Exploiting a sensed environment to improve human-agent communication

Published in Proceedings of the fourth international joint conference on Autonomous …, 2005, 2005

Recommended citation: Shana Watters, Tim Miller, Praveen Balachandran, William Schuler, and Richard Voyles. 2005. Exploiting a sensed environment to improve human-agent communication. In Proceedings of the fourth international joint conference on Autonomous …, 2005. https://dl.acm.org/doi/pdf/10.1145/1082473.1082481

Abstract:

This paper describes an implemented robotic agent architecture in which the environment, as sensed by the agent, is used to guide the recognition of spoken and gestural directives given by a human user. The agent recognizes these directives using a probabilistic language model that conditions probability estimates for possible directives on visually-, proprioceptively-, or otherwise-sensed properties of entities in its environment, and updates these probabilities when these properties change. The result is an agent that can discriminate against mis-recognized directives that do not ‘make sense’ in its representation of the current state of the world.