Learning to Engage with Interactive Systems

A Field Study on Deep Reinforcement Learning in a Public Museum

Datos Bibliográficos

ID22190876
AutoresLingheng Meng (0000-0001-9419-5774, University of Waterloo), Daiwei Lin (University of Waterloo), Adam Francey (University of Waterloo), Rob Gorbet (0000-0003-2799-3922, University of Waterloo), Philip Beesley (0000-0002-4747-9472, University of Waterloo), Dana Kulić (0000-0002-4169-2141, Monash University)
Año2021
Volumen10
Número1
Páginas1-29
Fecha de publicación2021-03-31
Open AccessSí
TipoARTICLE
RevistaACM Transactions on Human-Robot Interaction (JOURNAL)
Identificadores de la revistaISSN: 2573-9522 • E-ISSN: 2573-9522
EditorialAssociation for Computing Machinery (ACM) (PUBLISHER)
DOI10.1145/3408876
OpenAlexW3096659177
IdiomaEN
Citas recibidas1
Referencias citadas55

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

Human–computer interaction · Interactive Learning · Multimedia · Physical space · Reinforcement learning · Robot · Computer Science · Human Pose and Action Recognition · Robot Manipulation and Learning · Social Robot Interaction and HRI · Artificial Intelligence

Herramientas

Abrir DOIOpen Access