Motivations and Risks of Machine Ethics

被引:26
作者
Cave, Stephen [1 ]
Nyrup, Rune [1 ]
Vold, Karina [2 ]
Weller, Adrian [1 ]
机构
[1] Univ Cambridge, Leverhulme Ctr Future Intelligence, Cambridge CB2 1SB, England
[2] Univ Cambridge, Fac Philosophy, Leverhulrne Ctr Future Intelligence, Cambridge CB2 1SB, England
基金
英国工程与自然科学研究理事会;
关键词
Ethical alignment; ethical reasoning; machine agency; machine ethics; CONSCIOUSNESS; AGENCY; ROBOT;
D O I
10.1109/JPROC.2018.2865996
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
This paper surveys reasons for and against pursuing the field of machine ethics, understood as research aiming to build "ethical machines." We clarify the nature of this goal, why it is worth pursuing, and the risks involved in its pursuit. First, we survey and clarify some of the philosophical issues surrounding the concept of an "ethical machine" and the aims of machine ethics. Second, we argue that while there are good prima facie reasons for pursuing machine ethics, including the potential to improve the ethical alignment of both humans and machines, there are also potential risks that must be considered. Third, we survey these potential risks and point to where research should be devoted to clarifying and managing potential risks. We conclude by making some recommendations about the questions that future work could address.
引用
收藏
页码:562 / 574
页数:13
相关论文
共 73 条
[1]   Prolegomena to any future artificial moral agent [J].
Allen, C ;
Varner, G ;
Zinser, J .
JOURNAL OF EXPERIMENTAL & THEORETICAL ARTIFICIAL INTELLIGENCE, 2000, 12 (03) :251-261
[2]   Artificial morality: Top-down, bottom-up, and hybrid approaches [J].
Allen C. ;
Smit I. ;
Wallach W. .
Ethics and Information Technology, 2005, 7 (3) :149-155
[3]  
Allen C., 2009, Moral Machines: Teaching Robots Right from Wrong
[4]   Why machine ethics? [J].
Allen, Colin ;
Wallach, Wendell ;
Smit, Iva .
IEEE INTELLIGENT SYSTEMS, 2006, 21 (04) :12-17
[5]  
Andersen M.M.., 2004, GREEN POL INT POL IN, P1
[6]   An approach to computing ethics [J].
Anderson, Michael ;
Anderson, Susan Leigh ;
Armen, Chris .
IEEE INTELLIGENT SYSTEMS, 2006, 21 (04) :56-63
[7]   Machine ethics [J].
Anderson, Michael ;
Anderson, Susan Leigh .
IEEE INTELLIGENT SYSTEMS, 2006, 21 (04) :10-11
[8]   ROBOT BE GOOD [J].
Anderson, Michael ;
Anderson, Susan Leigh .
SCIENTIFIC AMERICAN, 2010, 303 (04) :72-77
[9]  
Anderson S. L., 2011, Machine Ethics, P524
[10]  
Anderson SL., 2011, MACHINE ETHICS, P21, DOI DOI 10.1017/CBO9780511978036.004