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.
Learning to engage with interactive systems
2020-10-01
Meng , L , Lin , D , Francey , A , Gorbet , R , Beesley , P & Kulić , D 2020 , ' Learning to engage with interactive systems ' , ACM Transactions on Human-Robot Interaction , vol. 10 , no. 1 , 3408876 . https://doi.org/10.1145/3408876
Article (Journal)
Electronic Resource
English
NTIS | 1984
|Learning from Science and Sport - How we, Safety, ``Engage with Rigor''
British Library Conference Proceedings | 2012
|British Library Conference Proceedings | 2006
|Engage or Retreat Differential Game with Two Targets
IEEE | 2019
|