Autonomous Generation of Robust and Focused Explanations for Robot Policies

Loading...
Thumbnail Image
Journal Title
Journal ISSN
Volume Title
Conference article in proceedings
Date
2019-10-01
Major/Subject
Mcode
Degree programme
Language
en
Pages
8
Series
Proceedings of the 28th IEEE International Conference on Robot and Human Interactive Communication, RO-MAN 2019
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.
Description
Keywords
Human-robot interaction, Mobile robots, Natural language processing, State-space methods
Other note
Citation
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 , IEEE International Symposium on Robot and Human Interactive Communication , New Delhi , India , 14/10/2019 . https://doi.org/10.1109/RO-MAN46459.2019.8956323