Predicting Takeover Quality in Conditionally Automated Vehicles Using Machine Learning and Genetic Algorithms

de Salis, Emmanuel; Meteier, Quentin; Capallera, Marine; Angelini, Leonardo; Andreas, Sonderegger; Abou Khaled, Omar; Mugellini, Elena; Widmer, Marino; Carrino, Stefano (2021). Predicting Takeover Quality in Conditionally Automated Vehicles Using Machine Learning and Genetic Algorithms In: Russo, Dario; Ahram, Tareq; Karwowski, Waldemar; Di Bucchianico, Giuseppe; Taiar, Redh (eds.) Intelligent Human Systems Integration 2021. Proceedings of the 4th International Conference on Intelligent Human Systems Integration (IHSI 2021): Integrating People and Intelligent Systems. February 22-24, 2021, Palermo, Italy. Advances in Intelligent Systems and Computing: Vol. 1322 (pp. 84-89). Cham: Springer 10.1007/978-3-030-68017-6_13

[img]
Preview
Text
de_Salis_Emmanuel_IHSI2021.pdf - Accepted Version
Available under License Publisher holds Copyright.

Download (256kB) | Preview

Takeover requests in conditionally automated vehicles are a critical point in time that can lead to accidents, and as such should be transmitted with care. Currently, several studies have shown the impact of using different modalities for different psychophysiological states, but no model exists to predict the takeover quality depending on the psychophysiological state of the driver and takeover request modalities. In this paper, we propose a ma-chine learning model able to predict the maximum steering wheel angle and the reaction time of the driver, two takeover quality metrics. Our model is able to achieve a gain of 42.26% on the reaction time and 8.92% on the maximum steering wheel angle compared to our baseline. This was achieved using up to 150 seconds of psychophysiological data prior to the takeover. Impacts of using such a model to choose takeover modalities instead of using standard takeover requests should be investigated.

Item Type:

Book Section (Book Chapter)

Division/Institute:

Business School > Institute for New Work
Business School > Institute for New Work > New Forms of Work and Organisation
Business School

Name:

de Salis, Emmanuel;
Meteier, Quentin;
Capallera, Marine;
Angelini, Leonardo;
Andreas, Sonderegger0000-0003-0054-0544;
Abou Khaled, Omar;
Mugellini, Elena;
Widmer, Marino;
Carrino, Stefano;
Russo, Dario;
Ahram, Tareq;
Karwowski, Waldemar;
Di Bucchianico, Giuseppe and
Taiar, Redh

Subjects:

B Philosophy. Psychology. Religion > BF Psychology
H Social Sciences > HE Transportation and Communications
Q Science > QA Mathematics > QA75 Electronic computers. Computer science

ISBN:

978-3-030-68016-9

Series:

Advances in Intelligent Systems and Computing

Publisher:

Springer

Funders:

[UNSPECIFIED] Haslerstiftung

Language:

English

Submitter:

Andreas Sonderegger

Date Deposited:

16 Feb 2021 15:25

Last Modified:

01 Mar 2022 02:30

Publisher DOI:

10.1007/978-3-030-68017-6_13

Uncontrolled Keywords:

Human Machine Interaction · Machine Learning · Conditionally Automated Vehicles · Genetic Algorithms · Artificial Intelligence · Takeover Request

ARBOR DOI:

10.24451/arbor.14346

URI:

https://arbor.bfh.ch/id/eprint/14346

Actions (login required)

View Item View Item
Provide Feedback