To Örebro University

oru.seÖrebro University Publications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Reinforcement Learning Approaches in Social Robotics
Örebro University, School of Science and Technology.ORCID iD: 0000-0001-6168-0706
Örebro University, School of Science and Technology.ORCID iD: 0000-0002-3122-693X
2021 (English)In: Sensors, E-ISSN 1424-8220, Vol. 21, no 4, article id 1292Article, review/survey (Refereed) Published
Abstract [en]

This article surveys reinforcement learning approaches in social robotics. Reinforcement learning is a framework for decision-making problems in which an agent interacts through trial-and-error with its environment to discover an optimal behavior. Since interaction is a key component in both reinforcement learning and social robotics, it can be a well-suited approach for real-world interactions with physically embodied social robots. The scope of the paper is focused particularly on studies that include social physical robots and real-world human-robot interactions with users. We present a thorough analysis of reinforcement learning approaches in social robotics. In addition to a survey, we categorize existent reinforcement learning approaches based on the used method and the design of the reward mechanisms. Moreover, since communication capability is a prominent feature of social robots, we discuss and group the papers based on the communication medium used for reward formulation. Considering the importance of designing the reward function, we also provide a categorization of the papers based on the nature of the reward. This categorization includes three major themes: interactive reinforcement learning, intrinsically motivated methods, and task performance-driven methods. The benefits and challenges of reinforcement learning in social robotics, evaluation methods of the papers regarding whether or not they use subjective and algorithmic measures, a discussion in the view of real-world reinforcement learning challenges and proposed solutions, the points that remain to be explored, including the approaches that have thus far received less attention is also given in the paper. Thus, this paper aims to become a starting point for researchers interested in using and applying reinforcement learning methods in this particular research field.

Place, publisher, year, edition, pages
MDPI, 2021. Vol. 21, no 4, article id 1292
Keywords [en]
Human-robot interaction, physical embodiment, reinforcement learning, reward design, social robotics
National Category
Robotics
Identifiers
URN: urn:nbn:se:oru:diva-90245DOI: 10.3390/s21041292ISI: 000624663200001PubMedID: 33670257Scopus ID: 2-s2.0-85100651693OAI: oai:DiVA.org:oru-90245DiVA, id: diva2:1535235
Funder
EU, Horizon 2020, 721619Available from: 2021-03-08 Created: 2021-03-08 Last updated: 2024-01-16Bibliographically approved
In thesis
1. Perceived Safety in Social Human-Robot Interaction
Open this publication in new window or tab >>Perceived Safety in Social Human-Robot Interaction
2022 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

This compilation thesis contributes to a deeper understanding of perceived safety in human-robot interaction (HRI) with a particular focus on social robots. The current understanding of safety in HRI is mostly limited to physical safety, whereas perceived safety has often been neglected and underestimated. However, safe HRI requires a conceptualization of safety that goes beyond physical safety covering also perceived safety of the users. Within this context, this thesis provides a comprehensive analysis of perceived safety in HRI with social robots, considering a diverse set of human-related and robot-related factors.

Two particular challenges for providing perceived safety in HRI are 1) understanding and evaluating human safety perception through direct and indirect measures, and 2) utilizing the measured level of perceived safety for adapting the robot behaviors. The primary contribution of this dissertation is in addressing the first challenge. The thesis investigates perceived safety in HRI by alternating between conducting user studies, literature review, and testing the findings from the literature within user studies.

In this thesis, six main factors influencing perceived safety in HRI are lifted: the context of robot use, the user’s comfort, experience and familiarity with robots, trust, sense of control over the interaction, and transparent and predictable robot behaviors. These factors could provide a common understanding of perceived safety and bridge the theoretical gap in the literature. Moreover, this thesis proposes an experimental paradigm to observe and quantify perceived safety using objective and subjective measures. This contributes to bridging the methodological gap in the literature.

The six factors are reviewed in HRI literature, and the robot features that affect these factors are organized in a taxonomy. Although this taxonomy focuses on social robots, the identified characteristics are relevant to other types of robots and autonomous systems. In addition to the taxonomy, the thesis provides a set of guidelines for providing perceived safety in social HRI. As a secondary contribution, the thesis presents an overview of reinforcement learning applications in social robotics as a suitable learning mechanism for adapting the robots’ behaviors to mitigate psychological harm.

Place, publisher, year, edition, pages
Örebro: Örebro University, 2022. p. 77
Series
Örebro Studies in Technology, ISSN 1650-8580 ; 94
National Category
Computer Sciences
Identifiers
urn:nbn:se:oru:diva-98102 (URN)9789175294322 (ISBN)
Public defence
2022-04-28, Örebro universitet, Långhuset, Hörsal L2, Fakultetsgatan 1, Örebro, 13:15 (English)
Opponent
Supervisors
Available from: 2022-03-17 Created: 2022-03-17 Last updated: 2022-05-04Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textPubMedScopus

Authority records

Akalin, NezihaLoutfi, Amy

Search in DiVA

By author/editor
Akalin, NezihaLoutfi, Amy
By organisation
School of Science and Technology
In the same journal
Sensors
Robotics

Search outside of DiVA

GoogleGoogle Scholar

doi
pubmed
urn-nbn

Altmetric score

doi
pubmed
urn-nbn
Total: 154 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf