Landscape of Machine Implemented Ethics

Abstract

This paper surveys the state-of-the-art in machine ethics, that is, considerations of how to implement ethical behaviour in robots, unmanned autonomous vehicles, or software systems. The emphasis is on covering the breadth of ethical theories being considered by implementors, as well as the implementation techniques being used. There is no consensus on which ethical theory is best suited for any particular domain, nor is there any agreement on which technique is best placed to implement a particular theory. Another unresolved problem in these implementations of ethical theories is how to objectively validate the implementations. The paper discusses the dilemmas being used as validating 'whetstones' and whether any alternative validation mechanism exists. Finally, it speculates that an intermediate step of creating domain-specific ethics might be a possible stepping stone towards creating machines that exhibit ethical behaviour.

Moral dilemmas for moral machines

“…Some scenarios include other 'characters', such as criminals, pregnant women, or doctors. 6 vehicles; see, for example, Allen et al [2], Wallach and Allen [102], Pereira and Saptawijaya [84], Pereira and Saptawijaya [83], Berreby et al [15], Danielson [33], Lin [68], Malle et al [73], Saptawijaya and Pereira [89], Saptawijaya and Pereira [90], Bentzen [14], Bhargava and Kim [16], Casey [26], Cointe et al [29], Greene [48], Lindner et al [69], Santoni de Sio [88], Welsh [103], Wintersberger [104], Bjørgen et al [17], Grinbaum [51], Misselhorn [75], Pardo [82], Sommaggio and Marchiori [93], Baum et al [13], Cunneen et al [31], Krylov et al [63], Sans and Casacuberta [87], Wright [105], Agrawal et al [1], Agrawal et al [9], Banks [11], Bauer [12], Etienne [40], Gordon [46], Harris [52], Lindner et al [70], Nallur [77]. And, several more articles that discuss trolley problems without citing Foot; e.g., Bonnefon et al [20], Etzioni and Etzioni [41], Lim and Taeihagh [67], Evans et al…”

Perspectives about artificial moral agents

“…The implementation of human inspired moral behaviors in artificial systems typically follows top-down, bottom-up, or hybrid approaches [23,24,45,72,72,79], but there is no consensus about which implementation is best fit for the endeavor of developing moral machines [53].…”

“…The breadth of different AMA design approaches reported in the literature reveals a lack of consensus among scholars working on the Machine Ethics project and raises questions about whether it is possible to develop an objective validation of AMAs that avoids designer bias and ensures explainability [22,42,53,64].…”

Automation: An Essential Component of Ethical Ai?

“…Although it is important for all three aspects to be ethical, we posit that the ethical problems involved in these three aspects may be solved using different techniques. For instance, the question of ethics inside AI seems more abstract, and current efforts fall short of expectations (Nallur, 2020). On the other hand, ethics of people developing AI and the ethics of deploying AI may be more amenable to being solved using currently available techniques.…”