Humanoids 2010 Workshop: Humanoid Robots Learning from Human Interaction

Tuesday December 7th • Nashville, TN

Overview

This full-day workshop will bring together researchers working on interactive robot learning for humanoid robots.

Program

Click to access to the schedule for the workshop.

Motivation and Objectives

Empowering everyday users with the ability to customize robot behavior is vital for broadening the use of robots in human environments. Interactive policy learning methods, in which the robot obtains some or all of its training data through interaction with a human, have gained widespread interest in recent years due to their accessibility to non-expert users. Endowing machines with human-like learning capabilities has an advantage of utilizing the natural human teaching abilities and allows users to teach robots as they would teach other humans. Furthermore, people have been shown to exhibit implicit expectations from the humanoid robots in interactive robot learning setups.

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:
  • Imitation learning
  • Learning from demonstration
  • Developmental psychology
  • Teachable agents
  • Cognitive models
  • Human-robot interaction
  • Unimodal and multi-modal media for efficient human-humanoid interaction
  • Correspondence problem in human-humanoid learning scenarios
  • Caregiver modeling
  • Adaptive systems
  • Transfer learning
  • Sliding autonomy
  • Learning performance evaluation