CAP6938-02: Special Topics in Plan, Activity, and Intent Recognition

Schedule: Fall 2007, TR 1330-1445
Location: CL1 212
Professor: Dr. Gita Sukthankar

Plan recognition is the process of making inferences about other agents based on observations, prior knowledge, and closed-world assumptions. This synergistic area of AI research combines techniques from human-computer interaction, autonomous and multi-agent systems, natural language understanding, machine learning, and computer vision.

Objectives:

After completing the course, students should: Additionally, students will refine their research, writing, and presentation skills.

Assignments

Outline

  1. Introduction; Robocup Application Domain
  2. Elder-Care Application Domain; Event Hierarchy Circumscription
  3. Event Tracking in SOAR; Plan Recognition for Adversarial Domains
  4. Efficiency Improvements for Symbolic Plan Recognition
  5. Probabilistic Grammars
  6. Graphical Models
  7. Dynamic Bayes Networks (DBNs)
  8. Applications of Hidden Markov Models
  9. Review
  10. Exam Problems; Presentations; Questionnaire
  11. Partial Observable Markov Decision Processes (POMDPs)
  12. Model Learning for POMDPs; Emotion Recognition
  13. Plan Recognition in Spoken Dialogue Corpora; Unsupervised Learning of Object Categories
  14. Human Motion Prediction; Tactical Game Play
  15. Undirected Graphical Models
  16. Learning by Observation
  17. Final Presentations