The Glass Infrastructure: Using Common Sense to Create a Dynamic, Place-Based Social Information System

Most organizations have a wealth of knowledge about themselves available online, but little for a visitor to interact with on-site. At the MIT Media Lab, we have designed and deployed a novel intelligent signage system, the Glass Infrastructure (GI) that enables small groups of users to physically interact with this data and to discover the latent connections between people, projects, and ideas. The displays are built on an adaptive, unsupervised model of the organization developed using dimensionality reduction and common sense knowledge which automatically classifies and organizes the information. The GI is currently in daily use at the lab. We discuss the AI models development, the integration of AI into an HCI interface, and the use of the GI during the labs peak visitor periods. We show that the GI is used repeatedly by lab visitors and provides a window into the workings of the organization. There is an evident trend toward adding interactivity and computing to the physical spaces in which we work, live and travel. In part this may be due to the ease with which places can now be networked, and in part by the decreasing cost of installed equipment. This is evident in signage, instrumentation of transportation systems, digital cameras, and portable applications that connect to these devices. Many of them expose information about the environment to individuals, either directly or by means of a mobile device. We are building the Glass Infrastructure (GI) – a new type of visitor information kiosk for spaces rich in interesting artifacts, such as stores, museums, and research laboratories. Our approach preserves key aspects of exploring collections of artifacts in physical space, such as object permanence and social engagement, while also giving users access to alternative spatial organizations of those artifacts. In the particular context of our research lab – where physical space is structured around organizational groupings of researchers – we wanted to let visitors simultaneously explore research in a thematicaly-organized space, to help them discover work related to their interests across research groups. Kiosks are context dependent, so the information on displayed at each Copyright c 2011, Association for the Advancement of Artificial