ABSTRACT: This paper, the third in a series, provides representational and design recommendations for the implementation of an ethical control and reasoning system potentially suitable for constraining lethal actions in an autonomous robotic system so that they fall within the bounds prescribed by the Laws of War and Rules of Engagement. It is based upon extensions to existing deliberative/reactive autonomous robotic architectures, and includes recommendations for (1) post facto suppression of unethical behavior, (2) behavioral design that incorporates ethical constraints from the onset, (3) the use of affective functions as an adaptive component in the event of unethical action, and (4) a mechanism in support of identifying and advising operators regarding the ultimate responsibility for the deployment of such a system. 1.

Abstract. This paper shows how moral decisions can be drawn computationally by using prospective logic programs. These are employed to model moral dilemmas, as they are able to prospectively look ahead at the consequences of hypothetical moral judgments. With this knowledge of consequences, moral rules are then used to decide the appropriate moral judgments. The whole moral reasoning is achieved via a priori constraints and a posteriori preferences on abductive stable models, two features available in prospective logic programming. In this work we model various moral dilemmas taken from the classic trolley problem and employ the principle of double effect as the moral rule. Our experiments show that preferred moral decisions, i.e. those following the principle of double effect, are successfully delivered. 1

Abstract not found

What is the nature of moral behavior? According to the study of bounded rationality, it results not from character traits or rational deliberation alone, but from the interplay between mind and environment. In this view, moral behavior is based on pragmatic social heuristics rather than moral rules or maximization principles. These social heuristics are not good or bad per se, but solely in relation to the environments in which they are used. This has methodological implications for the study of morality: Behavior needs to be studied in social groups as well as in isolation, in natural environments as well as in labs. It also has implications for moral policy: Only by accepting the fact that behavior is a function of both mind and environmental structures can realistic prescriptive means of achieving moral goals be developed.

Abstract. This paper shows how moral decisions can be drawn computationally by using ACORDA, a working implementation of prospective logic programming. ACORDA is employed to model moral dilemmas, as they are able to prospectively look ahead at the consequences of hypothetical moral judgments. With this knowledge of consequences, moral rules are then used to decide the appropriate moral judgments. The whole moral reasoning is achieved via a priori constraints and a posteriori preferences on abductive stable models, two features available in ACORDA. 1

Damage to the prefrontal cortex increases utilitarian moral judgements

Analogies are often theoretically useful. Important principles of electricity are suggested by an analogy between water current flowing through a pipe and electrical current “flowing” through a wire. A basic theory of sound is suggested by an analogy between waves caused by a stone being dropped into a still lake and “sound waves ” caused by a disturbance in air. At the very least, analogies suggest questions and shape the direction of research; at most, analogies may be crucial to explaining and understanding natural phenomena (Holyoak and Thagard 1995). Of course, principles suggested by such analogies need to be confirmed by relevant evidence. Even where analogies are fruitful, they are only partial. Sound waves and electricity are not wet; electricity does not spill out when a wire is cut. In this chapter we consider what is suggested by taking seriously an analogy between language and morality. Recently there have been a number of striking claims made about such a linguistic analogy – claims that if true, have profound implications for longstanding debates in moral philosophy about the innateness of moral capacities, and the existence of moral universals. (For example, the title of Hauser (2006) is Moral minds: how nature designed a universal sense of right and wrong.) We will indicate what support pursuit of the linguistic analogy might

Abstract—This paper presents the motivation, basis and a prototype implementation of an ethical adaptor capable of using a moral affective function, guilt, as a basis for altering a robot’s ongoing behavior. While the research is illustrated in the context of the battlefield, the methods described are believed generalizable to other domains such as eldercare and are potentially extensible to a broader class of moral emotions, including compassion and empathy. I I.

In the field of moral psychology, a number of theoretical proposals that were at one time regarded as unconnected at best—and, at worst, contradictory—are showing signs of reconciliation. At the core of this emerging consensus is a recognition that moral judgment is the product of interaction and competition between distinct psychological

Economists have a well-developed theory of value but the theory of why people hold the values they do is rudimentary at best. In spite of the fact that it is common to argue that values are important, most work on values is normative and the positive theory of values is relatively under- developed. In this paper we propose a simple yet general way to think about values – they are about how one trades-off one own’s utility against that of others – and argue that we can draw on the large literature on pro-social behavior for hypotheses on how people will choose values. Then, using data from the UK’s Citizenship Survey we show how models of self-interest, fairness, reciprocity and identity, can explain many of the patterns that we observe in the data across a wide variety of values.