The University of Southampton
University of Southampton Institutional Repository

Task-oriented accountability in autonomous systems

Task-oriented accountability in autonomous systems
Task-oriented accountability in autonomous systems
In Artificial Intelligence (AI) systems, a key problem is to determine the group of agents that are accountable for delivering a task and, in case of failure, the extent to which each group member is partially accountable.

In this context, accountability is understood as being responsible for failing to deliver a task that a team was allocated and able to fulfil. This is, on one hand, about agents’ accountability as collaborative teams and, on the other hand, their individual degree of accountability in a team. Developing verifiable methods to address this problem is key for designing trustworthy autonomous systems and ensuring their safe and effective integration with other operational systems in society. Using degrees of accountability, one can trace back a failure to AI components and prioritise how to invest resources on fixing faulty components.

In this talk, we report on a line of research on the application of formal methods and modal logics for reasoning about accountability in multiagent systems and focus on answering “Who is accountable for an unfulfilled task in multiagent teams: when, why, and to what extent?”. In addition, we elaborate on open problems, link to ensuring safety in application domains such as Connected and Autonomous Vehicles (CAVs), and highlight the potentials of formal accountability reasoning in design and development of trustworthy AI systems.
Accountability, Responsibility Reasoning, Artificial Intelligence, Multiagent Systems
Yazdanpanah, Vahid
28f82058-5e51-4f56-be14-191ab5767d56
Stein, Sebastian
cb2325e7-5e63-475e-8a69-9db2dfbdb00b
Gerding, Enrico
d9e92ee5-1a8c-4467-a689-8363e7743362
Jennings, Nicholas R.
569702cf-15b9-4a7f-8e38-d2d5f08cf365
Yazdanpanah, Vahid
28f82058-5e51-4f56-be14-191ab5767d56
Stein, Sebastian
cb2325e7-5e63-475e-8a69-9db2dfbdb00b
Gerding, Enrico
d9e92ee5-1a8c-4467-a689-8363e7743362
Jennings, Nicholas R.
569702cf-15b9-4a7f-8e38-d2d5f08cf365

Yazdanpanah, Vahid, Stein, Sebastian, Gerding, Enrico and Jennings, Nicholas R. (2021) Task-oriented accountability in autonomous systems. The UKRI Trustworthy Autonomous Systems Programme: All Hands Meeting, Virtual, Southampton, United Kingdom. 14 - 16 Sep 2021.

Record type: Conference or Workshop Item (Other)

Abstract

In Artificial Intelligence (AI) systems, a key problem is to determine the group of agents that are accountable for delivering a task and, in case of failure, the extent to which each group member is partially accountable.

In this context, accountability is understood as being responsible for failing to deliver a task that a team was allocated and able to fulfil. This is, on one hand, about agents’ accountability as collaborative teams and, on the other hand, their individual degree of accountability in a team. Developing verifiable methods to address this problem is key for designing trustworthy autonomous systems and ensuring their safe and effective integration with other operational systems in society. Using degrees of accountability, one can trace back a failure to AI components and prioritise how to invest resources on fixing faulty components.

In this talk, we report on a line of research on the application of formal methods and modal logics for reasoning about accountability in multiagent systems and focus on answering “Who is accountable for an unfulfilled task in multiagent teams: when, why, and to what extent?”. In addition, we elaborate on open problems, link to ensuring safety in application domains such as Connected and Autonomous Vehicles (CAVs), and highlight the potentials of formal accountability reasoning in design and development of trustworthy AI systems.

Text
Task-Oriented Accountability in Autonomous Systems_TAS_AHM2021 - Accepted Manuscript
Download (4kB)

More information

Published date: 14 September 2021
Venue - Dates: The UKRI Trustworthy Autonomous Systems Programme: All Hands Meeting, Virtual, Southampton, United Kingdom, 2021-09-14 - 2021-09-16
Keywords: Accountability, Responsibility Reasoning, Artificial Intelligence, Multiagent Systems

Identifiers

Local EPrints ID: 451210
URI: http://eprints.soton.ac.uk/id/eprint/451210
PURE UUID: 73e32bdf-2aa7-41d9-94ae-c0a35a3e1be8
ORCID for Vahid Yazdanpanah: ORCID iD orcid.org/0000-0002-4468-6193
ORCID for Sebastian Stein: ORCID iD orcid.org/0000-0003-2858-8857
ORCID for Enrico Gerding: ORCID iD orcid.org/0000-0001-7200-552X

Catalogue record

Date deposited: 14 Sep 2021 16:35
Last modified: 16 Sep 2021 11:14

Export record

Contributors

Author: Vahid Yazdanpanah ORCID iD
Author: Sebastian Stein ORCID iD
Author: Enrico Gerding ORCID iD
Author: Nicholas R. Jennings

University divisions

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×