Paul Bremner Paul2.Bremner@uwe.ac.uk
Associate Professor in Human Robotics Interactions
On proactive, transparent and verifiable ethical reasoning for robots
Bremner, Paul; Dennis, Louise A.; Fisher, Michael; Winfield, Alan F.
Authors
Louise A. Dennis
Michael Fisher
Alan Winfield Alan.Winfield@uwe.ac.uk
Professor in Robotics
Abstract
Previous work on ethical machine reasoning has largely been theoretical, and where such systems have been implemented it has in general been only initial proofs of principle. Here we address the question of desirable attributes for such systems to improve their real world utility, and how controllers with these attributes might be implemented. We propose that ethically-critical machine reasoning should be proactive, transparent and verifiable. We describe an architecture where the ethical reasoning is handled by a separate layer, augmenting a typical layered control architecture, ethically moderating the robot actions. It makes use of a simulation-based internal model, and supports proactive, transparent and verifiable ethical reasoning. To do so the reasoning component of the ethical layer uses our Python based Beliefs, Desires, Intentions (BDI) implementation. The declarative logic structure of BDI facilitates both transparency, through logging of the reasoning cycle, and formal verification methods. To prove the principles of our approach we use a case study implementation to experimentally demonstrate its operation. Importantly, it is the first such robot controller where the ethical machine reasoning has been formally verified.
Citation
Bremner, P., Dennis, L. A., Fisher, M., & Winfield, A. F. (2019). On proactive, transparent and verifiable ethical reasoning for robots. Proceedings of the IEEE, 107(3), 541-561. https://doi.org/10.1109/JPROC.2019.2898267
Journal Article Type | Article |
---|---|
Acceptance Date | Jan 24, 2019 |
Online Publication Date | Feb 21, 2019 |
Publication Date | Mar 1, 2019 |
Deposit Date | Feb 15, 2019 |
Publicly Available Date | Feb 15, 2019 |
Journal | Proceedings of the IEEE |
Print ISSN | 0018-9219 |
Publisher | Institute of Electrical and Electronics Engineers |
Peer Reviewed | Peer Reviewed |
Volume | 107 |
Issue | 3 |
Pages | 541-561 |
DOI | https://doi.org/10.1109/JPROC.2019.2898267 |
Keywords | Machine ethics; Transparency; Verifiability; Ethical robot; Intelligent robots; Robots; Formal verification; Ethics; Predictive models; Safety; Software architecture; Machine learning; Social implications of technology; Design methodology |
Public URL | https://uwe-repository.worktribe.com/output/851952 |
Publisher URL | https://doi.org/10.1109/JPROC.2019.2898267 |
Additional Information | Additional Information : © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. |
Files
Bremner_etal_PIEEE_final.pdf
(3.5 Mb)
PDF
Bremner_etal_supplementary_materials.pdf
(113 Kb)
PDF
You might also like
A two teraflop swarm
(2018)
Journal Article
Experiments in artificial theory of mind: From safety to story-telling
(2018)
Journal Article
Feature and performance comparison of the V-REP, Gazebo and ARGoS robot simulators
(2018)
Journal Article
Mapping Intelligence: Requirements and Possibilities
(2018)
Book Chapter
Negative updating combined with opinion pooling in the best-of-n problem in swarm robotics
(2018)
Journal Article