AAAI FSS 2012: Robots Learning Interactively from Human Teachers (RLIHT)

November 2-4 • Arlington, VA


This symposium will bring together researchers working on interactive robot learning, with a focus on interactions where the human intentionally changes a robot’s knowledge or behavior.

    Motivation and Objectives

To harness the full capabilities of robots, we should enable human end-users to customize their robots' behaviors and teach them new ones. Furthermore, it should be intuitive for these users to do so --- as simple as teaching other humans. Due to its accessibility to non-expert users, interactive learning is a promising method to achieve this goal and has attracted widespread attention in recent years. However, many challenges remain to make these methods applicable to robots.

The goal of this symposium is to increase awareness and interest in interactive learning methods and foster interdisciplinary collaboration by bringing together a diverse collection of researchers to discuss and exchange ideas on the current and potential future research directions.

    List of Topics

Research in interactive learning encompasses many topics, and we solicit a broad range of contributions in an effort to foster collaboration between different research areas. Topics of interest include, but are not limited to:

  1. Imitation learning

  2. Learning from demonstration

  3. Developmental psychology

  4. Teachable agents

  5. Cognitive models

  6. Human-robot interaction

  7. Long-term learning through interaction

  8. Unimodal and multi-modal media for efficient human-humanoid interaction

  9. Caregiver modeling

  10. Adaptive systems

  11. Transfer learning

  12. Sliding autonomy

  13. Evaluation of learning systems