Active Robot Learning for Temporal Task Models

With the goal of having robots learn new skills after deployment, we propose an active learning framework for modelling user preferences about task execution. The proposed approach interactively gathers information by asking questions expressed in natural language. We study the validity and the lear...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2018 13th ACM/IEEE International Conference on Human-Robot Interaction (HRI) S. 123 - 131
Hauptverfasser: Racca, Mattia, Kyrki, Ville
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: New York, NY, USA ACM 26.02.2018
Schriftenreihe:ACM Conferences
Schlagworte:
Computer systems organization > Embedded and cyber-physical systems > Robotics > External interfaces for robotics
Computing methodologies > Machine learning > Learning settings > Active learning settings
Human-centered computing > Human computer interaction (HCI) > Interaction paradigms > Natural language interfaces
Human-centered computing > Interaction design
Human-robot interaction
Interactive machine learning
Natural languages
Robot learning
Task analysis
Usability
human-robot interaction
interactive machine learning
ISBN:9781450349536, 1450349536
ISSN:2167-2148
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:With the goal of having robots learn new skills after deployment, we propose an active learning framework for modelling user preferences about task execution. The proposed approach interactively gathers information by asking questions expressed in natural language. We study the validity and the learning performance of the proposed approach and two of its variants compared to a passive learning strategy. We further investigate the human-robot-interaction nature of the framework conducting a usability study with 18 subjects. The results show that active strategies are applicable for learning preferences in temporal tasks from non-expert users. Furthermore, the results provide insights in the interaction design of active learning robots.
ISBN:9781450349536
1450349536
ISSN:2167-2148
DOI:10.1145/3171221.3171241