Understanding Essay

13477 Words Nov 21st, 2014 54 Pages
On How to Build a Moral Machine
Paul Bello PAUL . BELLO @ NAVY. MIL Human & Bioengineered Systems Division - Code 341, Office of Naval Research, 875 N. Randolph St., Arlington, VA 22203 USA Selmer Bringsjord SELMER @ RPI . EDU Depts. of Cognitive Science, Computer Science & the Lally School of Management, Rensselaer Polytechnic Institute, Troy, NY 12180 USA

Herein we make a plea to machine ethicists for the inclusion of constraints on their theories consistent with empirical data on human moral cognition. As philosophers, we clearly lack widely accepted solutions to issues regarding the existence of free will, the nature of persons and firm conditions on moral agency/patienthood; all of which are indispensable concepts to be
…show more content…
In the present paper, we build on a pre-existing computational model of mindreading (Bello et al., 2007) by adding constraints related to psychological distance (Trope & Liberman, 2010), a well-established psychological theory of conceptual organization. Our initial results suggest that studies of folk concepts involved in moral intuitions lead us to an enriched understanding of cognitive architecture and a more systematic method for interpreting the data generated by such studies.

1. Introduction and Plan for the Paper
This article makes a two-pronged argument for the further influence of psychological findings on the development of machine ethics. The first part of our argument presented throughout section 2 lays out the case against adopting traditional ethical theory as a foundation upon which to build moral machines. We address a number of issues pertaining to the apparent naturalization of ethics 1

that our particular approach to developing moral machines seems to entail. The second part of our argument, laid out in section 3, centers on a commitment to doing machine ethics via computational cognitive architectures. Computational cognitive architectures are comprised of data structures and algorithms that purport to be constrained by our best psychological theories of perception, mental representation and inferential powers. In particular, we argue that the capacity for moral machines to mindread, that is

Related Documents