Learning to engage with interactive systems

Lingheng Meng, Daiwei Lin, Adam Francey, Rob Gorbet, Philip Beesley, Dana Kulić

Research output: Contribution to journalArticleResearchpeer-review

Abstract

Physical agents that can autonomously generate engaging, life-like behavior will lead to more responsive and user-friendly robots and other autonomous systems. Although many advances have been made for one-to-one interactions in well-controlled settings, physical agents should be capable of interacting with humans in natural settings, including group interaction. To generate engaging behaviors, the autonomous system must first be able to estimate its human partners' engagement level. In this article, we propose an approach for estimating engagement during group interaction by simultaneously taking into account active and passive interaction, and use the measure as the reward signal within a reinforcement learning framework to learn engaging interactive behaviors. The proposed approach is implemented in an interactive sculptural system in a museum setting. We compare the learning system to a baseline using pre-scripted interactive behaviors. Analysis based on sensory data and survey data shows that adaptable behaviors within an expert-designed action space can achieve higher engagement and likeability.

Original languageEnglish
Article number3408876
Number of pages29
JournalACM Transactions on Human-Robot Interaction
Volume10
Issue number1
DOIs
Publication statusPublished - Oct 2020

Keywords

  • adaptive system
  • engagement
  • group interaction
  • human-robot interaction
  • interactive system
  • Living architecture
  • natural setting interaction
  • open-world interaction
  • reinforcement learning
  • robotic arts
  • robotic sculpture
  • social robot
  • voluntary engagement

Cite this