Fundamentals of a new Markup Language: MOML
Certain autonomous agents have to act morally to be socially acceptable. Because morality is not universal, we cannot impose a single set of morality rules for all agents and need to allow individuals to transfer their moral preferences to autonomous agents under their control. This thesis proposes a new XML-based markup language which helps transfer moral attitudes to autonomous systems.
Giller, Simon, 2020
Art der Arbeit Bachelor Thesis
Auftraggebende FHNW School of Business
Betreuende Dozierende Pustulka, Elzbieta
Keywords Machine Ethics, Morality Markup Language, MOML, Autonomous systems
Views: 48 - Downloads: 1
Our society is currently witnessing an increase in the use of autonomous systems. These systems are becoming ever more part of our daily lives. Even in closed or semi-open world scenarios, they come into situations where they must make moral decisions. There currently is no standardised way of defining the morality settings of autonomous agents. Therefore, the goal of this thesis is to propose a new morality markup language (MOML) encoding moral attitudes in a human- and machine-understandable form.
We present a literature review in the areas of machine ethics and markup languages which shaped the proposed morality markup language (MOML). To overcome the most substantial problem of varying moral concepts, MOML uses the idea of the morality menu. The menu lets humans define moral rules and transfer them to an autonomous system to create a proxy morality. Analysing MOML excerpts allowed us to develop an XML schema which we then tested in a test scenario.
The outcome is an XML based morality markup language for autonomous agents. Future projects can use this language or extend it. Using the schema, anyone can write MOML documents and validate them. Finally, we discuss new opportunities, applications and concerns related to the use of MOML. Future work could develop a controlled vocabulary or an ontology defining terms and commands for MOML.
Studiengang: Business Information Technology (Bachelor)
Vertraulichkeit: öffentlich