The Role of Blackboard-Based Reasoning and Visual Analytics in RESIN's Predictive Analysis

Abstract

Knowledge gathering and investigative tasks in open environments can be very complex because the problem-solving context is constantly evolving, and the data may be incomplete, unreliable and/or conflicting. This paper significantly extends our previous work on a mixed-initiative agent by making it capable of assisting humans in foraging task analysis using AI blackboard-based reasoning, visualizations and a mix-initiative user interface. The agent is equipped with the ability to adapt its processing to available resources, deadlines and its current problem-solving context.