Use What You've Got: Steps Toward Opportunistic Computing

摘要

We define opportunistic computing environments as augmented reality environments that attempt to minimally perturb existing work practices and allow users to opportunistically take advantage of them. In this paper, we present Rasa, an opportunistic computing environment for military command and control that augments the physical objects on a command post map by observing and understanding the users' speech, pen, and touch- based multimodal language. We give a thorough account of Rasa's underlying multiagent framework, recognition, understanding, and multimodal integration components. Finally, we examine three properties of language- generativity, comprehensibility, and compositionality- that render it suitable as an augmentation scheme, and we compare these properties to those of current tagging technologies and approaches.