Autonomous Generation of Robust and Focused Explanations for Robot Policies

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

26 Downloads (Pure)

Abstract

Transparency of robot behaviors increases efficiency and quality of interactions with humans. To increase transparency of robot policies, we propose a method for generating robust and focused explanations that express why a robot chose a particular action. The proposed method examines the policy based on the state space in which an action was chosen and describes it in natural language. The method can generate focused explanations by leaving out irrelevant state dimensions, and avoid explanations that are sensitive to small perturbations or have ambiguous natural language concepts. Furthermore, the method is agnostic to the policy representation and only requires the policy to be evaluated at different samples of the state space. We conducted a user study with 18 participants to investigate the usability of the proposed method compared to a comprehensive method that generates explanations using all dimensions. We observed how focused explanations helped the subjects more reliably detect the irrelevant dimensions of the explained system and how preferences regarding explanation styles and their expected characteristics greatly differ among the participants.

Original languageEnglish
Title of host publicationProceedings of the 28th IEEE International Conference on Robot and Human Interactive Communication, RO-MAN 2019
PublisherIEEE
Number of pages8
ISBN (Electronic)9781728126227
DOIs
Publication statusPublished - 1 Oct 2019
MoE publication typeA4 Article in a conference publication
EventIEEE International Symposium on Robot and Human Interactive Communication - New Delhi, India
Duration: 14 Oct 201918 Oct 2019
Conference number: 28

Conference

ConferenceIEEE International Symposium on Robot and Human Interactive Communication
Abbreviated titleRO-MAN
CountryIndia
CityNew Delhi
Period14/10/201918/10/2019

Keywords

  • Human-robot interaction
  • Mobile robots
  • Natural language processing
  • State-space methods

Fingerprint Dive into the research topics of 'Autonomous Generation of Robust and Focused Explanations for Robot Policies'. Together they form a unique fingerprint.

  • Projects

    ROSE: Robots and the Future of Welfare Services

    Lundell, J., Brander, T., Kyrki, V., Racca, M. & Verdoja, F.

    01/01/201831/12/2021

    Project: Academy of Finland: Strategic research funding

    Cite this

    Struckmeier, O., Racca, M., & Kyrki, V. (2019). Autonomous Generation of Robust and Focused Explanations for Robot Policies. In Proceedings of the 28th IEEE International Conference on Robot and Human Interactive Communication, RO-MAN 2019 [8956323] IEEE. https://doi.org/10.1109/RO-MAN46459.2019.8956323