Different XAI for different HRI
Copyright © 2017, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved. Artificial Intelligence (AI) has become more widespread in critical decision making at all levels of robotics, along with demands that the agent also explain to us humans why they do wha...
| Main Author: | |
|---|---|
| Format: | Conference Paper |
| Published: |
2017
|
| Online Access: | http://hdl.handle.net/20.500.11937/67997 |
| _version_ | 1848761714460327936 |
|---|---|
| author | Sheh, Raymond |
| author_facet | Sheh, Raymond |
| author_sort | Sheh, Raymond |
| building | Curtin Institutional Repository |
| collection | Online Access |
| description | Copyright © 2017, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved. Artificial Intelligence (AI) has become more widespread in critical decision making at all levels of robotics, along with demands that the agent also explain to us humans why they do what they do. This has driven renewed interest in Explainable Artificial Intelligence (XAI). Much work exists on the Human-Robot Interaction (HRI) challenges of creating and presenting explanations to different human users in different applications but matching these up with AI and Machine Learning (ML) techniques that can provide the underlying explanatory information can still be a challenge. In this short paper, we present a categorisation of explanations that communicate the XAI requirements of various users and applications, and the XAI capabilities of various underlying AI and ML techniques. |
| first_indexed | 2025-11-14T10:36:04Z |
| format | Conference Paper |
| id | curtin-20.500.11937-67997 |
| institution | Curtin University Malaysia |
| institution_category | Local University |
| last_indexed | 2025-11-14T10:36:04Z |
| publishDate | 2017 |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | curtin-20.500.11937-679972018-05-18T08:00:27Z Different XAI for different HRI Sheh, Raymond Copyright © 2017, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved. Artificial Intelligence (AI) has become more widespread in critical decision making at all levels of robotics, along with demands that the agent also explain to us humans why they do what they do. This has driven renewed interest in Explainable Artificial Intelligence (XAI). Much work exists on the Human-Robot Interaction (HRI) challenges of creating and presenting explanations to different human users in different applications but matching these up with AI and Machine Learning (ML) techniques that can provide the underlying explanatory information can still be a challenge. In this short paper, we present a categorisation of explanations that communicate the XAI requirements of various users and applications, and the XAI capabilities of various underlying AI and ML techniques. 2017 Conference Paper http://hdl.handle.net/20.500.11937/67997 restricted |
| spellingShingle | Sheh, Raymond Different XAI for different HRI |
| title | Different XAI for different HRI |
| title_full | Different XAI for different HRI |
| title_fullStr | Different XAI for different HRI |
| title_full_unstemmed | Different XAI for different HRI |
| title_short | Different XAI for different HRI |
| title_sort | different xai for different hri |
| url | http://hdl.handle.net/20.500.11937/67997 |