The goal of the HERA (Hybrid Ethical Reasoning Agents) project is to provide novel, theoretically well-founded and practically usable machine ethics tools for implementation in physical and virtual moral agents such as (social) robots and software bots. The research approach is to use advances in formal logic and modelling as a bridge between artificial intelligence and recent work in analytical ethics and political philosophy .
Collaborators
Martin Mose Bentzen, Technical University of Denmark
Felix Lindner, Albert-Ludwigs-University of Freiburg
Levels of Modeling in the HERA Project
| Ethical Principles | Cases | Judgment | |
|---|---|---|---|
| Natural Language and Natural Reasoning | Sometimes explicitly adhered to, often implicitly | Described in philosophical literature, by professionals, in novels etc. | Based on intuitions, emotions, informed by principles |
| Logical Formalization | Logical models of principles from ethical literature | Logical models of cases | Judgment reached via model of logical reasoning |
| Software Implementation | Algorithmic models of principles based on logical reasoning | Formal representations of cases | AI Reasoning methods |