Verbal explanations by collaborating robot teams
In this article, we present work on collaborating robot teams that use verbal explanations of their actions and intentions in order to be more understandable to the human. For this, we introduce a mechanism that determines what information the robots should verbalize in accordance with Grice’s maxim...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
De Gruyter
2020-11-01
|
Series: | Paladyn: Journal of Behavioral Robotics |
Subjects: | |
Online Access: | https://doi.org/10.1515/pjbr-2021-0001 |
id |
doaj-f7f3509a94504aea951b6f330418e014 |
---|---|
record_format |
Article |
spelling |
doaj-f7f3509a94504aea951b6f330418e0142021-10-03T07:42:42ZengDe GruyterPaladyn: Journal of Behavioral Robotics2081-48362020-11-01121475710.1515/pjbr-2021-0001pjbr-2021-0001Verbal explanations by collaborating robot teamsSingh Avinash Kumar0Baranwal Neha1Richter Kai-Florian2Hellström Thomas3Bensch Suna4Department of Computing Science, Umeå University, SwedenDepartment of Computing Science, Umeå University, SwedenDepartment of Computing Science, Umeå University, SwedenDepartment of Computing Science, Umeå University, SwedenDepartment of Computing Science, Umeå University, SwedenIn this article, we present work on collaborating robot teams that use verbal explanations of their actions and intentions in order to be more understandable to the human. For this, we introduce a mechanism that determines what information the robots should verbalize in accordance with Grice’s maxim of quantity, i.e., convey as much information as is required and no more or less. Our setup is a robot team collaborating to achieve a common goal while explaining in natural language what they are currently doing and what they intend to do. The proposed approach is implemented on three Pepper robots moving objects on a table. It is evaluated by human subjects answering a range of questions about the robots’ explanations, which are generated using either our proposed approach or two further approaches implemented for evaluation purposes. Overall, we find that our proposed approach leads to the most understanding of what the robots are doing. In addition, we further propose a method for incorporating policies driving the distribution of tasks among the robots, which may further support understandability.https://doi.org/10.1515/pjbr-2021-0001understandable robotsrobot teamsexplainable aihuman-robot interactionnatural language generationgrice’s maxim of quantityinformativeness |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Singh Avinash Kumar Baranwal Neha Richter Kai-Florian Hellström Thomas Bensch Suna |
spellingShingle |
Singh Avinash Kumar Baranwal Neha Richter Kai-Florian Hellström Thomas Bensch Suna Verbal explanations by collaborating robot teams Paladyn: Journal of Behavioral Robotics understandable robots robot teams explainable ai human-robot interaction natural language generation grice’s maxim of quantity informativeness |
author_facet |
Singh Avinash Kumar Baranwal Neha Richter Kai-Florian Hellström Thomas Bensch Suna |
author_sort |
Singh Avinash Kumar |
title |
Verbal explanations by collaborating robot teams |
title_short |
Verbal explanations by collaborating robot teams |
title_full |
Verbal explanations by collaborating robot teams |
title_fullStr |
Verbal explanations by collaborating robot teams |
title_full_unstemmed |
Verbal explanations by collaborating robot teams |
title_sort |
verbal explanations by collaborating robot teams |
publisher |
De Gruyter |
series |
Paladyn: Journal of Behavioral Robotics |
issn |
2081-4836 |
publishDate |
2020-11-01 |
description |
In this article, we present work on collaborating robot teams that use verbal explanations of their actions and intentions in order to be more understandable to the human. For this, we introduce a mechanism that determines what information the robots should verbalize in accordance with Grice’s maxim of quantity, i.e., convey as much information as is required and no more or less. Our setup is a robot team collaborating to achieve a common goal while explaining in natural language what they are currently doing and what they intend to do. The proposed approach is implemented on three Pepper robots moving objects on a table. It is evaluated by human subjects answering a range of questions about the robots’ explanations, which are generated using either our proposed approach or two further approaches implemented for evaluation purposes. Overall, we find that our proposed approach leads to the most understanding of what the robots are doing. In addition, we further propose a method for incorporating policies driving the distribution of tasks among the robots, which may further support understandability. |
topic |
understandable robots robot teams explainable ai human-robot interaction natural language generation grice’s maxim of quantity informativeness |
url |
https://doi.org/10.1515/pjbr-2021-0001 |
work_keys_str_mv |
AT singhavinashkumar verbalexplanationsbycollaboratingrobotteams AT baranwalneha verbalexplanationsbycollaboratingrobotteams AT richterkaiflorian verbalexplanationsbycollaboratingrobotteams AT hellstromthomas verbalexplanationsbycollaboratingrobotteams AT benschsuna verbalexplanationsbycollaboratingrobotteams |
_version_ |
1716845850398818304 |