Machine Ethics

Developing and Deploying
Principles and Practices Ensuring
Ethical Behavior of Autonomous Systems

Placeholder Picture

Consensus

Establish cases where there is general agreement as to the ethically preferable action

Placeholder Picture

Abstraction

Determine ethically relevant features and corresponding duties from consensus cases

Placeholder Picture

Integration

Synthesize principle from cases that balances duties when they are in conflict

Placeholder Picture

Deployment

Instantiate principle in system to determine and defend ethically preferable actions

Projects

Computational Ethics

2022- / Trends in Cognitive Sciences

Incorporating Public Opinion in Policy Decisions

2020- / Artificial Intelligence

Explanation in a Value-Driven Agent

2018- / AI and Ethics

GenEth

2012-14 / AAAI, Paladyn

Machine Ethics

2009-11 / Cambridge University Press

MedEthEx

2006 / IAAI

Special Issue on Machine Ethics

2006 / IEEE Intelligent Systems

AAAI Symposium on Machine Ethics

2005 / AAAI Technical Report

Jeremy

2004 / AAAI Workshop

People

Michael Anderson

University of Hartford

Susan Leigh Anderson

University of Connecticut

Vincent Berenz

Max Planck Institute
for Intelligent Systems

Beishui Liao

Zhejiang University
Institute of Logic and Cognition

Leon van der Torre

University of Luxembourg

Edmond Awad

University of Exeter

Machine Ethics

www.machineethics.com

Placeholder PicturePlaceholder PicturePlaceholder Picture