Applications that have access to user intent and task context can support better, faster decision-making on the part of the user. In this paper, we present AUTOS, an approach to the implementation of individual and team intent inference. AUTOS uses observable contextual clues to infer current operator task state and predict future task state. Guided by the concepts of activity theory, AUTOS task models can be hierarchically organized to infer team intent. To illustrate some of the properties of AUTOS technology, we describe our ongoing work in team intent inference with a prototype system embedded in a demonstration application for a military domain.

Intent inference is an approach to developing intelligent user interfaces in which the intentions of the user are inferred and tracked. An intent-aware application can proactively initiate tasks likely to be useful to the user in the current context, for instance, by collecting available data relevant to a decision the user must make. The utility of intent-inference can be further augmented with the notion of team intent inference, where the activities of each team member as well as those of the team overall can be tracked and coordinated by a system that has access to the corresponding user models. In this paper we present a framework called AUTOS that encapsulates the principles of team-intent inference and introduce an application created within this framework. Implications of our approach for intelligent user interface design are discussed.

This paper reports our preliminary design and implementation towards the development of Kavanah, a system to help users retrieve information and discover knowledge for a medical domain application. The goal of this system is to adaptively react to the dynamic changes in the user's interests and preferences in searching for information within the context of the on-going information retrieval task. The context in which the user seeks information is modeled by an active user interface through analyzing the user's interactions with the system to dynamically construct an ontology of concepts representing the user's information seeking context. We implement the system using Unified Medical Language System knowledge base as a test bed.

Existing target-based and objectives-based ("strategy-to-task") approaches to mission planning do not explicitly address the adversary's decision-making processes. Obviously, the adversary's courses of action (COA) are influenced in a cause-and-effect manner by actions taken by friendly forces. Given the iterative/interleaved nature of actions taken by enemy and friendly forces, mission planning must clearly take adversarial decision making into account especially during concurrent mission planning and execution. Currently, adversarial behaviour with regards to cause-and-effect are difficult to account for within the framework of existing planning approaches. This paper describes a cognitive architecture for computationally modeling, predicting, and explaining adversarial behaviors and COAs and proposes an integrated framework for mission planning. Our framework fits naturally within the Effects-Based Operations (EBO) approach to mission planning.