Teaching Human Teachers to Teach Robot Learners

Research output: Chapter in Book/Report/Conference proceedingConference paperpeer-review

11 Citations (Scopus)
513 Downloads (Pure)

Abstract

Using Programming by Demonstration to teach robot learners generalisable skills relies on having effective human teachers. This paper aims to address two problems commonly observed in demonstration data sets that arise due to poor teaching strategies; undemonstrated states and ambiguous demonstrations. Overcoming these issues through the use of visual feedback and simple heuristic rules is investigated as a potential way of training novice users to more effectively teach robot learners to generalise a task. The proposed method intends to offer the user a more transparent understanding of the robot learner’s model state during the teaching phase, to create a more interactive and robust teaching process. Results from a single-factor, three-phase repeated measures study with n = 30 participants, comparing the proposed feedback and heuristic rules set against an unguided condition, show a statistically significant (F(2, 58) = 8.0289, p = 0.00084) improvement of user teaching efficiency of approximately 180% when using the proposed feedback visualisation.
Original languageEnglish
Title of host publicationInternational Conference on Robotics and Automation (ICRA)
PublisherIEEE
Number of pages7
Publication statusPublished - 21 May 2018

Keywords

  • Robotics
  • Human Robot Interaction
  • Programming by Demonstration
  • Learning from demonstration
  • Teaching
  • Training
  • Visualisation
  • Visualization
  • Machine Learning
  • Gaussian Mixture Model

Fingerprint

Dive into the research topics of 'Teaching Human Teachers to Teach Robot Learners'. Together they form a unique fingerprint.

Cite this