Techniques for plan recognition

Knowing a user's plans and goals can significantly improve the effectivenes s of an interactive system. However, recognizing such goals and the user's intended plan for achieving them is not an easy task. Although much researc h has dealt with representing the knowledge necessary for plan inference an d developing strategies that hypothesize the user's evolving plans, a numbe r of serious problems still impede the use of plan recognition in large-sca le, real-world applications. This paper describes the various approaches th at have been taken to plan inference, along with techniques for dealing wit h ambiguity, robustness, and representation of requisite domain knowledge, and discusses areas for further research.