Home > Research > Publications & Outputs > What Do You Want From Me?

Research

Associated organisational units

Links

Text available via DOI:

View graph of relations

What Do You Want From Me?: Adapting Systems to the Uncertainty of Human Preferences

Research output: Contribution to conference - Without ISBN/ISSN › Conference paper › peer-review

Published

Standard

What Do You Want From Me? Adapting Systems to the Uncertainty of Human Preferences. / Gavidia-Calderon, Carlos; Bennaceur, Amel; Kordoni, Anastasia et al.
2022. Paper presented at New Ideas and Emerging Results (ICSE-NIER’22), United States.

Research output: Contribution to conference - Without ISBN/ISSN › Conference paper › peer-review

Harvard

Gavidia-Calderon, C, Bennaceur, A, Kordoni, A, Levine, M & Nuseibeh, B 2022, 'What Do You Want From Me? Adapting Systems to the Uncertainty of Human Preferences', Paper presented at New Ideas and Emerging Results (ICSE-NIER’22), United States, 21/05/22 - 29/05/22. https://doi.org/10.1145/3510455.3512791, https://doi.org/10.1109/icse-nier55298.2022.9793539

APA

Gavidia-Calderon, C., Bennaceur, A., Kordoni, A., Levine, M., & Nuseibeh, B. (2022). What Do You Want From Me? Adapting Systems to the Uncertainty of Human Preferences. Paper presented at New Ideas and Emerging Results (ICSE-NIER’22), United States. https://doi.org/10.1145/3510455.3512791, https://doi.org/10.1109/icse-nier55298.2022.9793539

Vancouver

Gavidia-Calderon C, Bennaceur A, Kordoni A, Levine M, Nuseibeh B. What Do You Want From Me? Adapting Systems to the Uncertainty of Human Preferences. 2022. Paper presented at New Ideas and Emerging Results (ICSE-NIER’22), United States. doi: 10.1145/3510455.3512791, 10.1109/icse-nier55298.2022.9793539

Author

Gavidia-Calderon, Carlos ; Bennaceur, Amel ; Kordoni, Anastasia et al. / What Do You Want From Me? Adapting Systems to the Uncertainty of Human Preferences. Paper presented at New Ideas and Emerging Results (ICSE-NIER’22), United States.

Bibtex

@conference{270775d19ac647ed91768f9adaa6563e,
title = "What Do You Want From Me?: Adapting Systems to the Uncertainty of Human Preferences",
abstract = "Autonomous systems, like drones and self-driving cars, are becoming part of our daily lives. Multiple people interact with them, each with their own expectations regarding system behaviour. To adapt system behaviour to human preferences, we propose and explore a game-theoretic approach. In our architecture, autonomous systems use sensor data to build game-theoretic models of their interaction with humans. In these models, we represent human preferences with types and a probability distribution over them. Game-theoretic analysis then outputs a strategy, that determines how the system should act to maximise utility, given its beliefs over human types. We showcase our approach in a search-and-rescue (SAR) scenario, with a robot in charge of locating victims. According to social psychology, depending on their identity some people are keen to help others, while some prioritise their personal safety. These social identities define what a person favours, so we can map them directly to game-theoretic types. We show that our approach enables a SAR robot to take advantage of human collaboration, outperforming non-adaptive configurations in average number of successful evacuations.",
author = "Carlos Gavidia-Calderon and Amel Bennaceur and Anastasia Kordoni and Mark Levine and Bashar Nuseibeh",
year = "2022",
month = may,
day = "13",
doi = "10.1145/3510455.3512791",
language = "English",
note = "New Ideas and Emerging Results (ICSE-NIER{\textquoteright}22) ; Conference date: 21-05-2022 Through 29-05-2022",

}

RIS

TY - CONF

T1 - What Do You Want From Me?

T2 - New Ideas and Emerging Results (ICSE-NIER’22)

AU - Gavidia-Calderon, Carlos

AU - Bennaceur, Amel

AU - Kordoni, Anastasia

AU - Levine, Mark

AU - Nuseibeh, Bashar

PY - 2022/5/13

Y1 - 2022/5/13

N2 - Autonomous systems, like drones and self-driving cars, are becoming part of our daily lives. Multiple people interact with them, each with their own expectations regarding system behaviour. To adapt system behaviour to human preferences, we propose and explore a game-theoretic approach. In our architecture, autonomous systems use sensor data to build game-theoretic models of their interaction with humans. In these models, we represent human preferences with types and a probability distribution over them. Game-theoretic analysis then outputs a strategy, that determines how the system should act to maximise utility, given its beliefs over human types. We showcase our approach in a search-and-rescue (SAR) scenario, with a robot in charge of locating victims. According to social psychology, depending on their identity some people are keen to help others, while some prioritise their personal safety. These social identities define what a person favours, so we can map them directly to game-theoretic types. We show that our approach enables a SAR robot to take advantage of human collaboration, outperforming non-adaptive configurations in average number of successful evacuations.

AB - Autonomous systems, like drones and self-driving cars, are becoming part of our daily lives. Multiple people interact with them, each with their own expectations regarding system behaviour. To adapt system behaviour to human preferences, we propose and explore a game-theoretic approach. In our architecture, autonomous systems use sensor data to build game-theoretic models of their interaction with humans. In these models, we represent human preferences with types and a probability distribution over them. Game-theoretic analysis then outputs a strategy, that determines how the system should act to maximise utility, given its beliefs over human types. We showcase our approach in a search-and-rescue (SAR) scenario, with a robot in charge of locating victims. According to social psychology, depending on their identity some people are keen to help others, while some prioritise their personal safety. These social identities define what a person favours, so we can map them directly to game-theoretic types. We show that our approach enables a SAR robot to take advantage of human collaboration, outperforming non-adaptive configurations in average number of successful evacuations.

U2 - 10.1145/3510455.3512791

DO - 10.1145/3510455.3512791

M3 - Conference paper

Y2 - 21 May 2022 through 29 May 2022

ER -