A Smart Home Testbed for Evaluating XAI with Non-Experts

Kevin McAreavey; Kim Bauters; Weiru Liu

doi:10.5220/0010908100003116

A Smart Home Testbed for Evaluating XAI with Non-Experts

Kevin McAreavey, Kim Bauters, Weiru Liu

Department of Engineering Mathematics

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

116 Downloads (Pure)

Abstract

Smart homes are powered by increasingly advanced AI, yet are controlled by, and affect, non-experts. These non-expert home users are an under-represented stakeholder in the explainable AI (XAI) literature. In this paper we facilitate future XAI research by introducing a family of smart home applications serving as a testbed to evaluate XAI with non-experts. The testbed is a hybrid-AI system spanning several AI disciplines, including machine learning and AI planning. Applications include a smart home battery and smart thermostatic radiator valve (TRV). End-user functionality is representative of leading commercial products and relevant research applications. The testbed is based on a flexible software architecture and web-based user interface, supports a range of AI tools in a modular fashion, and can be easily deployed using inexpensive consumer hardware.

Original language	English
Title of host publication	Proceedings of the 14th International Conference on Agents and Artificial Intelligence (ICAART'22)
Editors	Ana Paula Rocha, Luc Steels, Jaap van den Herik
Pages	773-784
Volume	3
ISBN (Electronic)	978-989-758-547-0
DOIs	https://doi.org/10.5220/0010908100003116
Publication status	Published - 3 Feb 2022
Event	ICAART 2022: 14th International Conference on Agents and Artificial Intelligence - Online Duration: 3 Feb 2022 → 5 Feb 2022 Conference number: 14 https://icaart.scitevents.org/

Conference

Conference	ICAART 2022
Period	3/02/22 → 5/02/22
Internet address	https://icaart.scitevents.org/

Keywords

Explainable AI (XAI)
Explainable Machine Learning
Explainable AI Planning (XAIP)
Smart Homes

Access to Document

10.5220/0010908100003116Licence: Other

Full-text PDF (author’s accepted manuscript)
This is the author accepted manuscript (AAM). The final published version (version of record) is available online via SCITEPRESS at 10.5220/0010908100003116. Please refer to any applicable terms of use of the publisher.
Accepted author manuscript, 718 KB

Handle.net

Persistent link

Cite this

@inproceedings{b441e6336ac744889f846c70839ae2c9,

title = "A Smart Home Testbed for Evaluating XAI with Non-Experts",

abstract = "Smart homes are powered by increasingly advanced AI, yet are controlled by, and affect, non-experts. These non-expert home users are an under-represented stakeholder in the explainable AI (XAI) literature. In this paper we facilitate future XAI research by introducing a family of smart home applications serving as a testbed to evaluate XAI with non-experts. The testbed is a hybrid-AI system spanning several AI disciplines, including machine learning and AI planning. Applications include a smart home battery and smart thermostatic radiator valve (TRV). End-user functionality is representative of leading commercial products and relevant research applications. The testbed is based on a flexible software architecture and web-based user interface, supports a range of AI tools in a modular fashion, and can be easily deployed using inexpensive consumer hardware.",

keywords = "Explainable AI (XAI), Explainable Machine Learning, Explainable AI Planning (XAIP), Smart Homes",

author = "Kevin McAreavey and Kim Bauters and Weiru Liu",

year = "2022",

month = feb,

day = "3",

doi = "10.5220/0010908100003116",

language = "English",

volume = "3",

pages = "773--784",

editor = "Rocha, {Ana Paula} and Luc Steels and {van den Herik}, Jaap",

booktitle = "Proceedings of the 14th International Conference on Agents and Artificial Intelligence (ICAART'22)",

note = "ICAART 2022 : 14th International Conference on Agents and Artificial Intelligence ; Conference date: 03-02-2022 Through 05-02-2022",

url = "https://icaart.scitevents.org/",

}

A Smart Home Testbed for Evaluating XAI with Non-Experts. / McAreavey, Kevin ; Bauters, Kim ; Liu, Weiru.
Proceedings of the 14th International Conference on Agents and Artificial Intelligence (ICAART'22). ed. / Ana Paula Rocha; Luc Steels; Jaap van den Herik. Vol. 3 2022. p. 773-784.

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

TY - GEN

T1 - A Smart Home Testbed for Evaluating XAI with Non-Experts

AU - McAreavey, Kevin

AU - Bauters, Kim

AU - Liu, Weiru

N1 - Conference code: 14

PY - 2022/2/3

Y1 - 2022/2/3

N2 - Smart homes are powered by increasingly advanced AI, yet are controlled by, and affect, non-experts. These non-expert home users are an under-represented stakeholder in the explainable AI (XAI) literature. In this paper we facilitate future XAI research by introducing a family of smart home applications serving as a testbed to evaluate XAI with non-experts. The testbed is a hybrid-AI system spanning several AI disciplines, including machine learning and AI planning. Applications include a smart home battery and smart thermostatic radiator valve (TRV). End-user functionality is representative of leading commercial products and relevant research applications. The testbed is based on a flexible software architecture and web-based user interface, supports a range of AI tools in a modular fashion, and can be easily deployed using inexpensive consumer hardware.

AB - Smart homes are powered by increasingly advanced AI, yet are controlled by, and affect, non-experts. These non-expert home users are an under-represented stakeholder in the explainable AI (XAI) literature. In this paper we facilitate future XAI research by introducing a family of smart home applications serving as a testbed to evaluate XAI with non-experts. The testbed is a hybrid-AI system spanning several AI disciplines, including machine learning and AI planning. Applications include a smart home battery and smart thermostatic radiator valve (TRV). End-user functionality is representative of leading commercial products and relevant research applications. The testbed is based on a flexible software architecture and web-based user interface, supports a range of AI tools in a modular fashion, and can be easily deployed using inexpensive consumer hardware.

KW - Explainable AI (XAI)

KW - Explainable Machine Learning

KW - Explainable AI Planning (XAIP)

KW - Smart Homes

UR - https://www.scitepress.org/PublicationsDetail.aspx?ID=o4V0Ybld090=&t=1

UR - https://www.scitepress.org/ProceedingsDetails.aspx?ID=PKHqtxzij4c=&t=1

U2 - 10.5220/0010908100003116

DO - 10.5220/0010908100003116

M3 - Conference Contribution (Conference Proceeding)

VL - 3

SP - 773

EP - 784

BT - Proceedings of the 14th International Conference on Agents and Artificial Intelligence (ICAART'22)

A2 - Rocha, Ana Paula

A2 - Steels, Luc

A2 - van den Herik, Jaap

T2 - ICAART 2022

Y2 - 3 February 2022 through 5 February 2022

ER -

A Smart Home Testbed for Evaluating XAI with Non-Experts

Abstract

Conference

Keywords

Access to Document

Handle.net

Other files and links

Fingerprint

CHAI: Cyber Hygiene in AI enabled domestic life

Cite this

A Smart Home Testbed for Evaluating XAI with Non-Experts

Abstract

Conference

Keywords

Access to Document

Handle.net

Other files and links

Fingerprint

Projects

CHAI: Cyber Hygiene in AI enabled domestic life

Cite this