Living with Agents: From Human-Agent Teamwork to Cognitive Prostheses

Abstract

Tomorrow’s world will be filled with agents embedded everywhere in the places and things around us. Providing a pervasive web of sensors and effectors, teams of such agents will function as cognitive prostheses-computational systems that leverage and extend human intellectual, perceptual, and collaborative capacities, just as the steam shovel was a sort of muscular prosthesis or the eyeglass a sort of visual prosthesis. While these heterogeneous cooperating entities may operate at different levels of sophistication and with dynamically varying degrees of autonomy, they will require some common means of representing and appropriately participating in joint tasks. Just as important, developers of such systems will need tools and methodologies to assure that such systems will work together reliably, naturally, and effectively, even when they are designed independently. In this talk I will describe some of the principles and applications that are important to the design and implementation of effective human-agent systems.