Improving user specifications for robot behavior through active preference learning: Framework and evaluation

An important challenge in human–robot interaction (HRI) is enabling non-expert users to specify complex tasks for autonomous robots. Recently, active preference learning has been applied in HRI to interactively shape a robot’s behavior. We study a framework where users specify constraints on allowab...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	The International journal of robotics research 2020-05, Vol.39 (6), p.651-667
Hauptverfasser:	Wilde, Nils, Blidaru, Alexandru, Smith, Stephen L, Kulić, Dana
Format:	Artikel
Sprache:	eng
Schlagworte:	Initial specifications Interactive learning Learning Robots Task complexity
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!