Steps Towards Satisficing Distributed Dynamic Team Trust

Edmund R Hunt; Chris Baber; Mehdi Sobhani; Sanja Milivojevic; Sagir Yusuf; Mirco Musolesi; Patrick Waterson; Sally Maynard

doi:10.1609/aaaiss.v2i1.27644

Steps Towards Satisficing Distributed Dynamic Team Trust

Edmund R Hunt
, Chris Baber
, Mehdi Sobhani
, Sanja Milivojevic^*
, Sagir Yusuf
, Mirco Musolesi
, Patrick Waterson
, Sally Maynard^*

^*Corresponding author for this work

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

12 Downloads (Pure)

Abstract

Defining and measuring trust in dynamic, multiagent teams is important in a range of contexts, particularly in defense and security domains. Team members should be trusted to work towards agreed goals and in accordance with shared values. In this paper, our concern is with the definition of goals and values such that it is possible to define 'trust' in a way that is interpretable, and hence usable, by both humans and robots. We argue that the outcome of team activity can be considered in terms of 'goal', 'individual/team values', and 'legal principles'. We question whether alignment is possible at the level of 'individual/team values', or only at the 'goal' and 'legal principles' levels. We argue for a set of metrics to define trust in human-robot teams that are interpretable by human or robot team members, and consider an experiment that could demonstrate the notion of 'satisficing trust' over the course of a simulated mission.

Original language	English
Title of host publication	Proceedings of the 2023 AAAI Fall Symposia
Publisher	AAAI Press
Volume	2
ISBN (Electronic)	101577358856, 139781577358855
DOIs	https://doi.org/10.1609/aaaiss.v2i1.27644
Publication status	Published - 22 Jan 2024

Publication series

Name
ISSN (Electronic)	2994-4317

Keywords

cs.AI
cs.HC
cs.RO

Access to Document

10.1609/aaaiss.v2i1.27644Licence: Unspecified

Full-text PDF (author accepted manuscript)
This is the accepted author manuscript (AAM). The final published version (version of record) is available online via The AAAI Press at [URL]. Please refer to any applicable terms of use of the publisher.
Accepted author manuscript, 1.85 MBLicence: CC BY

https://arxiv.org/abs/2309.05378Licence: CC BY

Handle.net

Persistent link

CenSoF: ESRC Centre for Sociodigital Futures
Halford, S. (Principal Investigator), Southerton, D. (Co-Investigator), Manchester, H. (Co-Investigator), Evans, D. M. (Co-Investigator), Watson, D. L. (Co-Investigator), Anderson, B. (Co-Investigator), Cater, K. F. (Co-Investigator), Carver, N. (Co-Investigator), Clarke, P. H. (Co-Investigator), Dermott, E. (Co-Investigator), Facer, K. (Co-Investigator), Hauert, S. (Co-Investigator), Liu, W. (Co-Investigator), McQuillan, D. (Co-Investigator), O'Kane, A. A. (Co-Investigator), Owen, R. (Co-Investigator), Parker, M. (Co-Investigator), Preist, C. W. (Co-Investigator), Schien, D. (Co-Investigator), Sriprakash, A. (Co-Investigator), Milivojevic, S. (Co-Investigator), Hussain, R. (Co-Investigator), Gutierrez Lopez, M. (Researcher), Cheilan, L. (Researcher), Thomas, L. M. (Researcher), Van Isacker, T. (Researcher), Valladares Celis, C. (Researcher), Atkins, E. L. (Student), Knight, E. W. (Student), Pykett, J. (Co-Investigator), Pitts, H. (Co-Investigator), Williamson, B. (Co-Investigator), Lagedamont, M. (Co-Investigator), Dowse, M. (Researcher), Brand, J. F. (Student), James, R. (Student), Okafo, D. (Student), Horsley, N. (Researcher), Jansen, A. H. (Administrator), Stevenson, T. P. (Other ), Hill, J. M. (Manager), Abu-Aisheh, R. (Researcher), Bo, H. (Researcher), Hemming, R. (Researcher), Huang, L. (Researcher), Ward, K. J. (Other ), Ogden, J. (Co-Investigator), Coleman, R. (Co-Investigator), Kleen, N. (Student) & Liu, T. (Student)
1/05/22 → 30/04/28
Project: Research, Parent

Cite this

@inproceedings{0f8576617deb4552983424a0b8a0a1af,

title = "Steps Towards Satisficing Distributed Dynamic Team Trust",

abstract = "Defining and measuring trust in dynamic, multiagent teams is important in a range of contexts, particularly in defense and security domains. Team members should be trusted to work towards agreed goals and in accordance with shared values. In this paper, our concern is with the definition of goals and values such that it is possible to define 'trust' in a way that is interpretable, and hence usable, by both humans and robots. We argue that the outcome of team activity can be considered in terms of 'goal', 'individual/team values', and 'legal principles'. We question whether alignment is possible at the level of 'individual/team values', or only at the 'goal' and 'legal principles' levels. We argue for a set of metrics to define trust in human-robot teams that are interpretable by human or robot team members, and consider an experiment that could demonstrate the notion of 'satisficing trust' over the course of a simulated mission.",

keywords = "cs.AI, cs.HC, cs.RO",

author = "Hunt, \{Edmund R\} and Chris Baber and Mehdi Sobhani and Sanja Milivojevic and Sagir Yusuf and Mirco Musolesi and Patrick Waterson and Sally Maynard",

year = "2024",

month = jan,

day = "22",

doi = "10.1609/aaaiss.v2i1.27644",

language = "English",

volume = "2",

publisher = "AAAI Press",

booktitle = "Proceedings of the 2023 AAAI Fall Symposia",

address = "United States",

}

TY - GEN

T1 - Steps Towards Satisficing Distributed Dynamic Team Trust

AU - Hunt, Edmund R

AU - Baber, Chris

AU - Sobhani, Mehdi

AU - Milivojevic, Sanja

AU - Yusuf, Sagir

AU - Musolesi, Mirco

AU - Waterson, Patrick

AU - Maynard, Sally

PY - 2024/1/22

Y1 - 2024/1/22

N2 - Defining and measuring trust in dynamic, multiagent teams is important in a range of contexts, particularly in defense and security domains. Team members should be trusted to work towards agreed goals and in accordance with shared values. In this paper, our concern is with the definition of goals and values such that it is possible to define 'trust' in a way that is interpretable, and hence usable, by both humans and robots. We argue that the outcome of team activity can be considered in terms of 'goal', 'individual/team values', and 'legal principles'. We question whether alignment is possible at the level of 'individual/team values', or only at the 'goal' and 'legal principles' levels. We argue for a set of metrics to define trust in human-robot teams that are interpretable by human or robot team members, and consider an experiment that could demonstrate the notion of 'satisficing trust' over the course of a simulated mission.

AB - Defining and measuring trust in dynamic, multiagent teams is important in a range of contexts, particularly in defense and security domains. Team members should be trusted to work towards agreed goals and in accordance with shared values. In this paper, our concern is with the definition of goals and values such that it is possible to define 'trust' in a way that is interpretable, and hence usable, by both humans and robots. We argue that the outcome of team activity can be considered in terms of 'goal', 'individual/team values', and 'legal principles'. We question whether alignment is possible at the level of 'individual/team values', or only at the 'goal' and 'legal principles' levels. We argue for a set of metrics to define trust in human-robot teams that are interpretable by human or robot team members, and consider an experiment that could demonstrate the notion of 'satisficing trust' over the course of a simulated mission.

KW - cs.AI

KW - cs.HC

KW - cs.RO

U2 - 10.1609/aaaiss.v2i1.27644

DO - 10.1609/aaaiss.v2i1.27644

M3 - Conference Contribution (Conference Proceeding)

VL - 2

BT - Proceedings of the 2023 AAAI Fall Symposia

PB - AAAI Press

ER -

Steps Towards Satisficing Distributed Dynamic Team Trust

Abstract

Publication series

Keywords

Access to Document

Handle.net

Fingerprint

Projects

CenSoF: ESRC Centre for Sociodigital Futures

Cite this