T1: A Glimpse at the Future of Agent
Technology
Jeffrey M. Bradshaw
Institute for Human and Machine Cognition, Pensacola, FL USA
In this
tutorial, I will discuss the reasons why agent technologies are playing an increasingly
important role in software and hardware systems. In particular, I will review
the claimed advantages of capabilities such as communication, control, adaptivity,
and mobility in agent-based systems over their counterparts in traditional computing.
I will discuss accommodations being made by developers of next-generation Internet
and computational grid services in anticipation of the wide proliferation of
agent technologies, including DAML/OWL, semantic web and semantic grid services,
and policy services. I will review a variety of military applications of agent
technology, including agent-based services to assure robustness and survivability
from information warfare attacks, modeling of complex organizational structures
and policies in coalition operations, and agents for dynamic sensor tasking
and customized information retrieval. I will discuss the central role of teamwork
and adjustable autonomy in human-agent interaction and illustrate with examples
such as NASA's Personal Satellite Assistant (PSA) and mobile robots for planetary
surface exploration. Taking this approach one step further I will describe efforts
to develop a general approach to the design of cognitive prostheses, where human-agent
teaming could be so natural and transparent that robotic and software agents
could appear to function as direct extensions of human cognitive, kinetic, and
sensory capabilities.
The tutorial will be useful for agent researchers as well as practitioners who would like to get a sense of the most current trends and technologies. No special knowledge is required for successful completion of the tutorial.
T2: Adaptive Web-Based
Systems: Technologies and Examples
Web-based application systems, as well as other complex hypermedia systems with a large variety of users, suffer from an inability to satisfy heterogeneous needs. A Web course presents the same static explanation of a concept to students with widely differing knowledge of the subject. A Web bookstore offers the same selection of bestsellers to customers with different reading preferences. A Web museum offers the same "guided tour" and the same narration to visitors with very different goals and interests. A remedy for the negative effects of the traditional "one-size-fits-all" approach is to enhance a system's ability to adapt its own behaviour to the goals, tasks, interests, and other features of individual users. Starting in the 1990s, many research teams began to investigate ways of modelling features of the users of hypermedia systems. This has led to a number of interesting adaptation techniques and adaptive systems.
The goal of the tutorial is to present a comprehensive introduction into adaptive Web-based systems for "Web-oriented" audience. It will cover the following issues: a brief review of adaptive Web-based systems, a detailed description of several efficient but easy-to-implement adaptation techniques, and a brief review of several experimental studies of Web-based adaptive systems.
The tutorial
will be useful for researchers in the area of advanced Web-based systems as
well as for practitioners who can benefit from making their Web-based systems
adaptive. No special knowledge is required for successful completion of the
tutorial, however a 10 hour experience of work with the Web is desirable.