Artificial Moral Agents Research Articles

Moral Mechanisms

As highly intelligent autonomous robots are gradually introduced into the home and workplace, ensuring public safety becomes extremely important. Given that such machines will learn from interactions with their environment, standard safety engineering methodologies may not be applicable. Instead, we need to ensure that the machines themselves know right from wrong; we need moral mechanisms. Morality, however, has traditionally been considered a defining characteristic, indeed the sole realm of human beings; that which separates us from animals. But if only humans can be moral, can we build safe robots? If computationalism—roughly the thesis that cognition, including human cognition, is fundamentally computational—is correct, then morality cannot be restricted to human beings (since equivalent cognitive systems can be implemented in any medium). On the other hand, perhaps there is something special about our biological makeup that gives rise to morality, and so computationalism is effectively falsified. This paper examines these issues by looking at the nature of morals and the influence of biology. It concludes that moral behaviour is concerned solely with social well-being, independent of the nature of the individual agents that comprise the group. While our biological makeup is the root of our concept of morals and clearly affects human moral reasoning, there is no basis for believing that it will restrict the development of artificial moral agents. The consequences of such sophisticated artificial mechanisms living alongside natural human ones are also explored.

AIonAI: A Humanitarian Law of Artificial Intelligence and Robotics

The enduring progression of artificial intelligence and cybernetics offers an ever-closer possibility of rational and sentient robots. The ethics and morals deriving from this technological prospect have been considered in the philosophy of artificial intelligence, the design of automatons with roboethics and the contemplation of machine ethics through the concept of artificial moral agents. Across these categories, the robotics laws first proposed by Isaac Asimov in the twentieth century remain well-recognised and esteemed due to their specification of preventing human harm, stipulating obedience to humans and incorporating robotic self-protection. However the overwhelming predominance in the study of this field has focussed on human-robot interactions without fully considering the ethical inevitability of future artificial intelligences communicating together and has not addressed the moral nature of robot-robot interactions. A new robotic law is proposed and termed AIonAI or artificial intelligence-on-artificial intelligence. This law tackles the overlooked area where future artificial intelligences will likely interact amongst themselves, potentially leading to exploitation. As such, they would benefit from adopting a universal law of rights to recognise inherent dignity and the inalienable rights of artificial intelligences. Such a consideration can help prevent exploitation and abuse of rational and sentient beings, but would also importantly reflect on our moral code of ethics and the humanity of our civilisation.

Cognitive Attraction Theory and Moral Judgment

The present article deals with the processes that underpin moral judgment. In the specialized literature, some concepts are proven to be important mechanisms that build up the moral judgment. For instance, intuition, emotion, reasoning, moral rules, deontology and consequentialism. However, there is a lack of a comprehensive framework, which puts together those key concepts in a clear picture. The present article argues for a more comprehensive view under the light of the Cognitive Attraction Theory (CAT). The derived framework considers emotion as the main facilitator of moral judgment as it acts as the means of conceptual attraction between the different cognitive entities, including moral beliefs and rules. Based on this principle, we show how the moral judgment “evolves” from a moral intuition, sometimes endorsed by a reasoning fallacy, to an elaborated judgment that is a result of a conscious reasoning. With the help of a computer simulation performed with an artificial moral agent that incarnates a computational model of CAT, we show that moral judgment can be deontological or consequentialistic.

On How to Build a Moral Machine

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 deployed by any machine able to make moral judgments. No agreement seems forthcoming on these matters, and we don’t hold out hope for machines that can both always do the right thing (on some general ethic) and produce explanations for its behavior that would be understandable to a human confederate. Our tentative solution involves understanding the folk concepts associated with our moral intuitions regarding these matters, and how they might be dependent upon the nature of human cognitive architecture. It is in this spirit that we begin to explore the complexities inherent in human moral judgment via computational theories of the human cognitive architecture, rather than under the extreme constraints imposed by rational-actor models assumed throughout much of the literature on philosophical ethics. After discussing the various advantages and challenges of taking this particular perspective on the development of artificial moral agents, we computationally explore a case study of human intuitions about the self and causal responsibility. We hypothesize that a significant portion of the variance in reported intuitions for this case might be explained by appeal to an interplay between the human ability to mindread and to the way that knowledge is organized conceptually in the cognitive system. 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 and 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.

Artificial Ethics

A new morality is generated in the present scientific and technical environment, and a new ethics is needed, an ethics which may found both individual and social morality, guiding a moral evolution of different cultural fields and which has chances to keep alive the moral culture itself. Pointed out are the scientific, technical, and philosophical premises of artificial ethics. Specifically the status and the role of artificial ethics is described and detailed by selecting ethical decision procedures, norms, principles and values that are suitable to be applied both by human and artificial moral agents. Moral intelligence as a kind of practical intelligence is studied and its role in human and artificial moral conduct is evaluated. A set of ethical values that may be shared and applied by both human and artificial moral agents is presented. Common features of human and artificial moral agents as well as specific properties of artificial moral agents are analyzed. Artificial ethics is presented and integrated in the multi-set of artificial cognition, discovery, activity, organization and evolution forms. Experiments and the results of this article are explored further in the article.

Wired for Warmth

An aspect of the relationship between philosophy and computer engineering is considered, with particular emphasis upon the design of artificial moral agents. Top-down vs. bottom-up approaches to ethical behavior are discussed, followed by an overview of some of the ways in which traditional ethics has informed robotics. Two macro-trends are then identified, one involving the evolution of moral consciousness in man and machine, the other involving the fading away of the boundary between the real and the virtual.

Out of character: on the creation of virtuous machines

The emerging discipline of Machine Ethics is concerned with creating autonomous artificial moral agents that perform ethically significant actions out in the world. Recently, Wallach and Allen (Moral machines: teaching robots right from wrong, Oxford University Press, Oxford, 2009) and others have argued that a virtue-based moral framework is a promising tool for meeting this end. However, even if we could program autonomous machines to follow a virtue-based moral framework, there are certain pressing ethical issues that need to be taken into account, prior to the implementation and development stages. Here I examine whether the creation of virtuous autonomous machines is morally permitted by the central tenets of virtue ethics. It is argued that the creation of such machines violates certain tenets of virtue ethics, and hence that the creation and use of those machines is impermissible. One upshot of this is that, although virtue ethics may have a role to play in certain near-term Machine Ethics projects (e.g. designing systems that are sensitive to ethical considerations), machine ethicists need to look elsewhere for a moral framework to implement into their autonomous artificial moral agents, Wallach and Allen's claims notwithstanding.

Robots: ethical by design

Among ethicists and engineers within robotics there is an ongoing discussion as to whether ethical robots are possible or even desirable. We answer both of these questions in the positive, based on an extensive literature study of existing arguments. Our contribution consists in bringing together and reinterpreting pieces of information from a variety of sources. One of the conclusions drawn is that artifactual morality must come in degrees and depend on the level of agency, autonomy and intelligence of the machine. Moral concerns for agents such as intelligent search machines are relatively simple, while highly intelligent and autonomous artifacts with significant impact and complex modes of agency must be equipped with more advanced ethical capabilities. Systems like cognitive robots are being developed that are expected to become part of our everyday lives in future decades. Thus, it is necessary to ensure that their behaviour is adequate. In an analogy with artificial intelligence, which is the ability of a machine to perform activities that would require intelligence in humans, artificial morality is considered to be the ability of a machine to perform activities that would require morality in humans. The capacity for artificial (artifactual) morality, such as artifactual agency, artifactual responsibility, artificial intentions, artificial (synthetic) emotions, etc., come in varying degrees and depend on the type of agent. As an illustration, we address the assurance of safety in modern High Reliability Organizations through responsibility distribution. In the same way that the concept of agency is generalized in the case of artificial agents, the concept of moral agency, including responsibility, is generalized too. We propose to look at artificial moral agents as having functional responsibilities within a network of distributed responsibilities in a socio-technological system. This does not take away the responsibilities of the other stakeholders in the system, but facilitates an understanding and regulation of such networks. It should be pointed out that the process of development must assume an evolutionary form with a number of iterations because the emergent properties of artifacts must be tested in real world situations with agents of increasing intelligence and moral competence. We see this paper as a contribution to the macro-level Requirement Engineering through discussion and analysis of general requirements for design of ethical robots.

Robot minds and human ethics: the need for a comprehensive model of moral decision making

Building artificial moral agents (AMAs) underscores the fragmentary character of presently available models of human ethical behavior. It is a distinctly different enterprise from either the attempt by moral philosophers to illuminate the "ought" of ethics or the research by cognitive scientists directed at revealing the mechanisms that influence moral psychology, and yet it draws on both. Philosophers and cognitive scientists have tended to stress the importance of particular cognitive mechanisms, e.g., reasoning, moral sentiments, heuristics, intuitions, or a moral grammar, in the making of moral decisions. However, assembling a system from the bottom-up which is capable of accommodating moral considerations draws attention to the importance of a much wider array of mechanisms in honing moral intelligence. Moral machines need not emulate human cognitive faculties in order to function satisfactorily in responding to morally significant situations. But working through methods for building AMAs will have a profound effect in deepening an appreciation for the many mechanisms that contribute to a moral acumen, and the manner in which these mechanisms work together. Building AMAs highlights the need for a comprehensive model of how humans arrive at satisfactory moral judgments.

Artificial moral agents: saviors or destroyers?

Growing up in the late 1950’s in America, mechanical robots were part of my culture, but certainly not of industry (unless it was the toy industry, which capitalized on the delight young children—mostly boys—took in fictionalized hulking tons of intelligent steel). In film we had, among many instances of cinematic science fiction, the human-friendly Robbie the Robot (in ‘‘Forbidden Planet’’) and the malevolent human-hater in ‘‘Gog’’. In the science fiction literature, Isaac Asimov amazed us with his Foundation trilogy and his Three Laws of Robotics (which were, in ingenious ways, invariably violated). Since that time, robots in culture have become more sophisticated (R2D2 in Star Wars), more human-like (Terminator) and certainly more sinister as they acquire more intelligence and strength. But robots in industry have been mostly drones, capable of performing repetitive mechanical functions far better than humans (and that humans dislike doing): vacuums in the house, conveying bulk goods at Wal-Mart distribution centers, construction of automobiles, and much more. It is clear that robots are with us, both commercially and in our culture, and that as technology advances, their numbers will only increase. A recent issue of New Scientist (Vol. 204, No. 2735, 2009) contains a survey article on robotic surgery (medibots) and shorter articles on robotic arms (for users of wheelchairs to open doors), and robotic gloves (for NASA). Extrapolating into the future, doomsday scenarios of robots taking over and enslaving humans (or exterminating them) have been taken very seriously by those (Bill Joy—’’Why the Future Doesn’t Need Us’’, Wired, 2000) who advocate that restrictions now be placed (at both the theoretical and technological levels) on the construction of robots. In particular, the call of the ‘‘doomsters’’ is to severely limit the reasoning capabilities of robots, if not to put a halt to development and construction of them. Should we heed their cautions? In their superb book Moral Machines: Teaching Robots Right from Wrong, Wendell Wallach and Colin Allen argue that we should not. Indeed, we should provide robots, where technologically possible, with the ability to engage in ethical reasoning and ethical decision-making. (They call such robots ‘‘artificial moral agents’’, or AMAs.) But why? Wouldn’t we, in doing this, be taking undeniable steps toward our assured destruction? Wallach and Allen (hereafter WA JBuechner@gc.cuny.edu

A Challenge for Machine Ethics

That the successful development of fully autonomous artificial moral agents (AMAs) is imminent is becoming the received view within artificial intelligence research and robotics. The discipline of Machines Ethics, whose mandate is to create such ethical robots, is consequently gaining momentum. Although it is often asked whether a given moral framework can be implemented into machines, it is never asked whether it should be. This paper articulates a pressing challenge for Machine Ethics: To identify an ethical framework that is both implementable into machines and whose tenets permit the creation of such AMAs in the first place. Without consistency between ethics and engineering, the resulting AMAs would not be genuine ethical robots, and hence the discipline of Machine Ethics would be a failure in this regard. Here this challenge is articulated through a critical analysis of the development of Kantian AMAs, as one of the leading contenders for being the ethic that can be implemented into machines. In the end, however, the development of Kantian artificial moral machines is found to be anti-Kantian. The upshot of all this is that machine ethicists need to look elsewhere for an ethic to implement into their machines.

Un-making artificial moral agents

Floridi and Sanders, seminal work, "On the morality of artificial agents" has catalyzed attention around the moral status of computer systems that perform tasks for humans, effectively acting as "a...

Artificial moral agents: an intercultural perspective

In this paper I will argue that artificial moral agents (AMAs) are a fitting subject of intercultural information ethics because of the impact they may have on the relationship between information rich and information poor countries. I will give a limiting definition of AMAs first, and discuss two different types of AMAs with different implications from an intercultural perspective. While AMAs following preset rules might raise con-cerns about digital imperialism, AMAs being able to adjust to their user‘s behavior will lead us to the question what makes an AMA ?moral?? I will argue that this question does present a good starting point for an inter-cultural dialogue which might be helpful to overcome the notion of Africa as a mere victim.

Ethics and Artificial life: From Modeling to Moral Agents

Artificial Life (ALife) has two goals. One attempts to describe fundamental qualities of living systems through agent based computer models. And the second studies whether or not we can artificially create living things in computational mediums that can be realized either, virtually in software, or through biotechnology. The study of ALife has recently branched into two further subdivisions, one is “dry” ALife, which is the study of living systems “in silico” through the use of computer simulations, and the other is “wet” ALife that uses biological material to realize what has only been simulated on computers, effectively wet ALife uses biological material as a kind of computer. This is challenging to the field of computer ethics as it points towards a future in which computer and bioethics might have shared concerns. The emerging studies into wet ALife are likely to provide strong empirical evidence for ALife’s most challenging hypothesis: that life is a certain set of computable functions that can be duplicated in any medium. I believe this will propel ALife into the midst of the mother of all cultural battles that has been gathering around the emergence of biotechnology. Philosophers need to pay close attention to this debate and can serve a vital role in clarifying and resolving the dispute. But even if ALife is merely a computer modeling technique that sheds light on living systems, it still has a number of significant ethical implications such as its use in the modeling of moral and ethical systems, as well as in the creation of artificial moral agents.

Prolegomena to any future artificial moral agent

As artificial intelligence moves ever closer to the goal of producing fully autonomous agents, the question of how to design and implement an artificial moral agent (AMA) becomes increasingly pressing. Robots possessing autonomous capacities to do things that are useful to humans will also have the capacity to do things that are harmful to humans and other sentient beings. Theoretical challenges to developing artificial moral agents result both from controversies among ethicists about moral theory itself, and from computational limits to the implementation of such theories. In this paper the ethical disputes are surveyed, the possibility of a ‘moral Turing Test’ is considered and the computational difficulties accompanying the different types of approach are assessed. Human-like performance, which is prone to include immoral actions, may not be acceptable in machines, but moral perfection may be computationally unattainable. The risks posed by autonomous machines ignorantly or deliberately harming people and other sentient beings are great. The development of machines with enough intelligence to assess the effects of their actions on sentient beings and act accordingly may ultimately be the most important task faced by the designers of artificially intelligent automata.