Programming Machine Ethics

Cham: Springer Verlag. Edited by Ari Saptawijaya (2016)
  Copy   BIBTEX

Abstract

Source: "This book addresses the fundamentals of machine ethics. It discusses abilities required for ethical machine reasoning and the programming features that enable them. It connects ethics, psychological ethical processes, and machine implemented procedures. From a technical point of view, the book uses logic programming and evolutionary game theory to model and link the individual and collective moral realms. It also reports on the results of experiments performed using several model implementations. Opening specific and promising inroads into the terra incognita of machine ethics, the authors define here new tools and describe a variety of program-tested moral applications and implemented systems. In addition, they provide alternative readings paths, allowing readers to best focus on their specific interests and to explore the concepts at different levels of detail. Mainly written for researchers in cognitive science, artificial intelligence, robotics, philosophy of technology and engineering of ethics, the book will also be of general interest to other academics, undergraduates in search of research topics, science journalists as well as science and society forums, legislators and military organizations concerned with machine ethics."

Links

PhilArchive



    Upload a copy of this work     Papers currently archived: 91,219

External links

Setup an account with your affiliations in order to access resources via your University's proxy server

Through your library

Chapters

Conclusions and Further Work

This book discusses the two realms of machine ethics, a field that is now becoming a pressing concern and receiving wide attention due to its growing importance. It makes a number of original inroads that exhibit a proof of possibility to systematically represent and reason about a variety of issues... see more

Bridging Two Realms of Machine Ethics

Bridging capabilities between the two realms, to wit, the individual and collective, helps understand the emergent ethical behavior of agents in groups, and implements them not just in simulations, but in the world of future robots and their swarms. On the basis of preceding chapters, this chapter c... see more

Turing, Functionalism, and Emergence

This chapter addresses the relevance of the ground breaking work of Alan Turing to justify our functionalism stance regarding the modeling of morality. Turing first defined the algorithmic limits of computability, via an effective well-specified mechanism, and showed the generality of his definition... see more

Tabling in Abduction and Updating

In the individual realm part of this book, we are addressing the interplay amongst appropriate LP features to represent moral facets and to reason about them. One such interplay is between LP abduction and updating, both supported with tabling mechanisms. In this chapter, we propose novel approaches... see more

Representing Morality in Logic Programming

This chapter provides necessary background of Logic Programming used throughout this book, including semantics of Logic Programs . The subsequent part of this chapter briefly overview considered LP reasoning features: abduction, preferences, probabilistic LP, updating, LP counterfactuals, and tablin... see more

Modeling Morality Using Logic Programming

This chapter aims at realizing our conception about representing diverse moral facets in Logic Programming, by modeling several issues pertaining to those moral facets, using the three systems discussed in Chap. 7. The applicability of these systems corresponds with their relevance to the moral issu... see more

The Individual Realm of Machine Ethics: A Survey

In this chapter, a survey of research in machine ethics is presented, providing the context and the motivation for our investigations. The survey concerns the individual realm of machine ethics, whereas the background to other realm, the collective one, is broached in Chap. 9, namely Sects. 9.1 and ... see more

Counterfactuals in Logic Programming

Counterfactuals capture the process of reasoning about a past event that did not occur, namely what would have happened had this event occurred; or, vice-versa, to reason about an event that did occur but what if it had not. In this chapter, we innovatively make use of LP abduction and updating in a... see more

Logic Programming Systems Affording Morality Experiments

In this chapter, we discuss how considered Logic Programming-based reasoning features are synthesized in three different systems: Acorda, Probabilistic EPA, and Qualm. Whereas the development of Qualm is a contribution of this book, Acorda and Probabilistic EPA are two existing systems that have bee... see more

Significant Moral Facets Amenable to Logic Programming

This chapter reports on our literature study in moral philosophy and psychology for choosing conceptual viewpoints close to LP-based reasoning. These viewpoints fall into three moral facets tackled in this book. First, we study moral permissibility, taking into account the Doctrines of Double Effect... see more

Modeling Collective Morality via Evolutionary Game Theory

This chapter addresses the collective realm computationally, using Evolutionary Game Theory in populations of individuals, to report on norms and morality emergence. These populations, to start with, are not equipped with much cognitive capability, and simply act from a predetermined set of actions.... see more

Similar books and articles

A challenge for machine ethics.Ryan Tonkens - 2009 - Minds and Machines 19 (3):421-438.
Out of character: on the creation of virtuous machines. [REVIEW]Ryan Tonkens - 2012 - Ethics and Information Technology 14 (2):137-149.
Modelling ethical rules of lying with answer set programming.Jean-Gabriel Ganascia - 2007 - Ethics and Information Technology 9 (1):39-47.

Analytics

Added to PP
2016-08-28

Downloads
18 (#785,610)

6 months
5 (#544,079)

Historical graph of downloads
How can I increase my downloads?

Author's Profile

References found in this work

No references found.

Add more references