Autonomous Generation of Robust and Focused Explanations for Robot Policies

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussaConference contributionScientificvertaisarvioitu

24 Lataukset (Pure)

Abstrakti

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.

AlkuperäiskieliEnglanti
OtsikkoProceedings of the 28th IEEE International Conference on Robot and Human Interactive Communication, RO-MAN 2019
KustantajaIEEE
Sivumäärä8
ISBN (elektroninen)9781728126227
DOI - pysyväislinkit
TilaJulkaistu - 1 lokakuuta 2019
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisuussa
TapahtumaIEEE International Symposium on Robot and Human Interactive Communication - New Delhi, Intia
Kesto: 14 lokakuuta 201918 lokakuuta 2019
Konferenssinumero: 28

Conference

ConferenceIEEE International Symposium on Robot and Human Interactive Communication
LyhennettäRO-MAN
MaaIntia
KaupunkiNew Delhi
Ajanjakso14/10/201918/10/2019

Sormenjälki Sukella tutkimusaiheisiin 'Autonomous Generation of Robust and Focused Explanations for Robot Policies'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

  • Projektit

    ROSE: Robotit ja hyvinvointipalvelujen tulevaisuus

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

    01/01/201830/06/2021

    Projekti: Academy of Finland: Strategic research funding

    Siteeraa tätä

    Struckmeier, O., Racca, M., & Kyrki, V. (2019). Autonomous Generation of Robust and Focused Explanations for Robot Policies. teoksessa 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