Why Not Explain? Effects of Explanations on Human Perceptions of Autonomous Driving

Daniel Omeiza; Konrad Kollnig; Helena Web; Marina Jirotka; Lars Kunze

doi:10.1109/ARSO51874.2021.9542835

Why Not Explain? Effects of Explanations on Human Perceptions of Autonomous Driving

Daniel Omeiza^*, Konrad Kollnig, Helena Web, Marina Jirotka, Lars Kunze

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceeding › Academic › peer-review

42 Downloads (Pure)

Abstract

Autonomous vehicles (AVs) have the potential to change the way we commute, travel, and transport our goods. The deployment of AVs in society, however, requires that people understand, accept, and trust them. Intelligible explanations can help different AV stakeholders to assess AVs' behaviours, and in turn, increase their confidence and foster trust. In a user study (N = 101), we examined different explanation types (based on investigatory queries) provided by an AV and their effect on people using the trust determinant factors. Our quantitative and qualitative analysis shows that explanations with causal attributions improved task performance and understanding when assessing driving events but did not directly improve perceived trust. This underlines the potential need for additional measures and research to enhance trust in AVs.

Original language	English
Title of host publication	2021 IEEE International Conference on Advanced Robotics and Its Social Impacts, ARSO 2021
Publisher	IEEE Computer Society
Pages	194-199
Number of pages	6
ISBN (Electronic)	9781665449533
DOIs	https://doi.org/10.1109/ARSO51874.2021.9542835
Publication status	Published - 8 Jul 2021
Externally published	Yes
Event	2021 IEEE International Conference on Advanced Robotics and Its Social Impacts, ARSO 2021 - Virtual, Japan Duration: 8 Jul 2021 → 10 Jul 2021 https://ieee-arso2021.org/

Publication series

Series	Proceedings of IEEE Workshop on Advanced Robotics and its Social Impacts, ARSO
Volume	2021-July
ISSN	2162-7568

Conference

Conference	2021 IEEE International Conference on Advanced Robotics and Its Social Impacts, ARSO 2021
Country/Territory	Japan
Period	8/07/21 → 10/07/21
Internet address	https://ieee-arso2021.org/

Access to Document

10.1109/ARSO51874.2021.9542835

Full TextFinal published version, 363 KBLicence: Taverne

Cite this

Omeiza, Daniel ; Kollnig, Konrad ; Web, Helena et al. / Why Not Explain? Effects of Explanations on Human Perceptions of Autonomous Driving. 2021 IEEE International Conference on Advanced Robotics and Its Social Impacts, ARSO 2021. IEEE Computer Society, 2021. pp. 194-199 (Proceedings of IEEE Workshop on Advanced Robotics and its Social Impacts, ARSO, Vol. 2021-July).

@inproceedings{65df55610ccf48239e702edf93dd395d,

title = "Why Not Explain? Effects of Explanations on Human Perceptions of Autonomous Driving",

abstract = "Autonomous vehicles (AVs) have the potential to change the way we commute, travel, and transport our goods. The deployment of AVs in society, however, requires that people understand, accept, and trust them. Intelligible explanations can help different AV stakeholders to assess AVs' behaviours, and in turn, increase their confidence and foster trust. In a user study (N = 101), we examined different explanation types (based on investigatory queries) provided by an AV and their effect on people using the trust determinant factors. Our quantitative and qualitative analysis shows that explanations with causal attributions improved task performance and understanding when assessing driving events but did not directly improve perceived trust. This underlines the potential need for additional measures and research to enhance trust in AVs.",

author = "Daniel Omeiza and Konrad Kollnig and Helena Web and Marina Jirotka and Lars Kunze",

note = "Funding Information: This work was supported by the UK{\textquoteright}s Engineering and Physical Sciences Research Council (EPSRC) through project RoboTIPS: Developing Responsible Robots for the Digital Economy, grant reference EP/S005099/1. It was also supported by the Assuring Autonomy International Programme (Demonstrator project: Sense-Assess-eXplain (SAX)), a partnership between Lloyd{\textquoteright}s Register Foundation and the University of York. Publisher Copyright: {\textcopyright} 2021 IEEE.; 2021 IEEE International Conference on Advanced Robotics and Its Social Impacts, ARSO 2021 ; Conference date: 08-07-2021 Through 10-07-2021",

year = "2021",

month = jul,

day = "8",

doi = "10.1109/ARSO51874.2021.9542835",

language = "English",

series = "Proceedings of IEEE Workshop on Advanced Robotics and its Social Impacts, ARSO",

publisher = "IEEE Computer Society",

pages = "194--199",

booktitle = "2021 IEEE International Conference on Advanced Robotics and Its Social Impacts, ARSO 2021",

address = "United States",

url = "https://ieee-arso2021.org/",

}

Omeiza, D, Kollnig, K, Web, H, Jirotka, M & Kunze, L 2021, Why Not Explain? Effects of Explanations on Human Perceptions of Autonomous Driving. in 2021 IEEE International Conference on Advanced Robotics and Its Social Impacts, ARSO 2021. IEEE Computer Society, Proceedings of IEEE Workshop on Advanced Robotics and its Social Impacts, ARSO, vol. 2021-July, pp. 194-199, 2021 IEEE International Conference on Advanced Robotics and Its Social Impacts, ARSO 2021, Japan, 8/07/21. https://doi.org/10.1109/ARSO51874.2021.9542835

Why Not Explain? Effects of Explanations on Human Perceptions of Autonomous Driving. / Omeiza, Daniel; Kollnig, Konrad; Web, Helena et al.
2021 IEEE International Conference on Advanced Robotics and Its Social Impacts, ARSO 2021. IEEE Computer Society, 2021. p. 194-199 (Proceedings of IEEE Workshop on Advanced Robotics and its Social Impacts, ARSO, Vol. 2021-July).

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceeding › Academic › peer-review

TY - GEN

T1 - Why Not Explain? Effects of Explanations on Human Perceptions of Autonomous Driving

AU - Omeiza, Daniel

AU - Kollnig, Konrad

AU - Web, Helena

AU - Jirotka, Marina

AU - Kunze, Lars

N1 - Funding Information: This work was supported by the UK’s Engineering and Physical Sciences Research Council (EPSRC) through project RoboTIPS: Developing Responsible Robots for the Digital Economy, grant reference EP/S005099/1. It was also supported by the Assuring Autonomy International Programme (Demonstrator project: Sense-Assess-eXplain (SAX)), a partnership between Lloyd’s Register Foundation and the University of York. Publisher Copyright: © 2021 IEEE.

PY - 2021/7/8

Y1 - 2021/7/8

N2 - Autonomous vehicles (AVs) have the potential to change the way we commute, travel, and transport our goods. The deployment of AVs in society, however, requires that people understand, accept, and trust them. Intelligible explanations can help different AV stakeholders to assess AVs' behaviours, and in turn, increase their confidence and foster trust. In a user study (N = 101), we examined different explanation types (based on investigatory queries) provided by an AV and their effect on people using the trust determinant factors. Our quantitative and qualitative analysis shows that explanations with causal attributions improved task performance and understanding when assessing driving events but did not directly improve perceived trust. This underlines the potential need for additional measures and research to enhance trust in AVs.

AB - Autonomous vehicles (AVs) have the potential to change the way we commute, travel, and transport our goods. The deployment of AVs in society, however, requires that people understand, accept, and trust them. Intelligible explanations can help different AV stakeholders to assess AVs' behaviours, and in turn, increase their confidence and foster trust. In a user study (N = 101), we examined different explanation types (based on investigatory queries) provided by an AV and their effect on people using the trust determinant factors. Our quantitative and qualitative analysis shows that explanations with causal attributions improved task performance and understanding when assessing driving events but did not directly improve perceived trust. This underlines the potential need for additional measures and research to enhance trust in AVs.

UR - http://www.scopus.com/inward/record.url?scp=85116434999&partnerID=8YFLogxK

U2 - 10.1109/ARSO51874.2021.9542835

DO - 10.1109/ARSO51874.2021.9542835

M3 - Conference article in proceeding

AN - SCOPUS:85116434999

T3 - Proceedings of IEEE Workshop on Advanced Robotics and its Social Impacts, ARSO

SP - 194

EP - 199

BT - 2021 IEEE International Conference on Advanced Robotics and Its Social Impacts, ARSO 2021

PB - IEEE Computer Society

T2 - 2021 IEEE International Conference on Advanced Robotics and Its Social Impacts, ARSO 2021

Y2 - 8 July 2021 through 10 July 2021

ER -

Omeiza D, Kollnig K, Web H, Jirotka M, Kunze L. Why Not Explain? Effects of Explanations on Human Perceptions of Autonomous Driving. In 2021 IEEE International Conference on Advanced Robotics and Its Social Impacts, ARSO 2021. IEEE Computer Society. 2021. p. 194-199. (Proceedings of IEEE Workshop on Advanced Robotics and its Social Impacts, ARSO, Vol. 2021-July). doi: 10.1109/ARSO51874.2021.9542835

Why Not Explain? Effects of Explanations on Human Perceptions of Autonomous Driving

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this