Wendell Wallach

Artificial Morality: Top-down, Bottom-up, and Hybrid Approaches

A principal goal of the discipline of artificial morality is to design artificial agents to act as if they are moral agents. Intermediate goals of artificial morality are directed at building into AI systems sensitivity to the values, ethics, and legality of activities. The development of an effective foundation for the field of artificial morality involves exploring the technological and philosophical issues involved in making computers into explicit moral reasoners. The goal of this paper is to discuss strategies for implementing artificial morality and the differing criteria for success that are appropriate to different strategies.

A Conceptual and Computational Model of Moral Decision Making in Human and Artificial Agents

Recently, there has been a resurgence of interest in general, comprehensive models of human cognition. Such models aim to explain higher-order cognitive faculties, such as deliberation and planning. Given a computational representation, the validity of these models can be tested in computer simulations such as software agents or embodied robots. The push to implement computational models of this kind has created the field of artificial general intelligence (AGI). Moral decision making is arguably one of the most challenging tasks for computational approaches to higher-order cognition. The need for increasingly autonomous artificial agents to factor moral considerations into their choices and actions has given rise to another new field of inquiry variously known as Machine Morality, Machine Ethics, Roboethics, or Friendly AI. In this study, we discuss how LIDA, an AGI model of human cognition, can be adapted to model both affective and rational features of moral decision making. Using the LIDA model, we will demonstrate how moral decisions can be made in many domains using the same mechanisms that enable general decision making. Comprehensive models of human cognition typically aim for compatibility with recent research in the cognitive and neural sciences. Global workspace theory, proposed by the neuropsychologist Bernard Baars (1988), is a highly regarded model of human cognition that is currently being computationally instantiated in several software implementations. LIDA (Franklin, Baars, Ramamurthy, & Ventura, 2005) is one such computational implementation. LIDA is both a set of computational tools and an underlying model of human cognition, which provides mechanisms that are capable of explaining how an agents selection of its next action arises from bottom-up collection of sensory data and top-down processes for making sense of its current situation. We will describe how the LIDA model helps integrate emotions into the human decision-making process, and we will elucidate a process whereby an agent can work through an ethical problem to reach a solution that takes account of ethically relevant factors.

Machine morality: bottom-up and top-down approaches for modelling human moral faculties

The implementation of moral decision making abilities in artificial intelligence (AI) is a natural and necessary extension to the social mechanisms of autonomous software agents and robots. Engineers exploring design strategies for systems sensitive to moral considerations in their choices and actions will need to determine what role ethical theory should play in defining control architectures for such systems. The architectures for morally intelligent agents fall within two broad approaches: the top-down imposition of ethical theories, and the bottom-up building of systems that aim at goals or standards which may or may not be specified in explicitly theoretical terms. In this paper we wish to provide some direction for continued research by outlining the value and limitations inherent in each of these approaches.

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.

CONSCIOUSNESS AND ETHICS: ARTIFICIALLY CONSCIOUS MORAL AGENTS

What roles or functions does consciousness fulfill in the making of moral decisions? Will artificial agents capable of making appropriate decisions in morally charged situations require machine consciousness? Should the capacity to make moral decisions be considered an attribute essential for being designated a fully conscious agent? Research on the prospects for developing machines capable of making moral decisions and research on machine consciousness have developed as independent fields of inquiry. Yet there is significant overlap. Both fields are likely to progress through the instantiation of systems with artificial general intelligence (AGI). Certainly special classes of moral decision making will require attributes of consciousness such as being able to empathize with the pain and suffering of others. But in this article we will propose that consciousness also plays a functional role in making most if not all moral decisions. Work by the authors of this article with LIDA, a computational and conceptual model of human cognition, will help illustrate how consciousness can be understood to serve a very broad role in the making of all decisions including moral decisions.

Framing robot arms control

The development of autonomous, robotic weaponry is progressing rapidly. Many observers agree that banning the initiation of lethal activity by autonomous weapons is a worthy goal. Some disagree with this goal, on the grounds that robots may equal and exceed the ethical conduct of human soldiers on the battlefield. Those who seek arms-control agreements limiting the use of military robots face practical difficulties. One such difficulty concerns defining the notion of an autonomous action by a robot. Another challenge concerns how to verify and monitor the capabilities of rapidly changing technologies. In this article we describe concepts from our previous work about autonomy and ethics for robots and apply them to military robots and robot arms control. We conclude with a proposal for a first step toward limiting the deployment of autonomous weapons capable of initiating lethal force.

Implementing moral decision making faculties in computers and robots

The challenge of designing computer systems and robots with the ability to make moral judgments is stepping out of science fiction and moving into the laboratory. Engineers and scholars, anticipating practical necessities, are writing articles, participating in conference workshops, and initiating a few experiments directed at substantiating rudimentary moral reasoning in hardware and software. The subject has been designated by several names, including machine ethics, machine morality, artificial morality, or computational morality. Most references to the challenge elucidate one facet or another of what is a very rich topic. This paper will offer a brief overview of the many dimensions of this new field of inquiry.

From Robots to Techno Sapiens: Ethics, Law and Public Policy in the Development of Robotics and Neurotechnologies

The specific ethical and legal challenges posed by robotics must be considered within the context of the broader societal impact of emerging technologies. The public is generally fascinated by new technologies, and perceives technology as an engine of both promise and productivity. But there is also considerable disquiet as to whether we are surrendering the future to a juggernaut of change that will decimate cherished values and institutions. This disquiet is evident in the worldwide prohibition on human cloning, restrictions upon the sale of genetically modified foods in the EU, controversy regarding research using embryonic stem cells in the US, and international regulations prohibiting athletes from using human growth hormones and drugs that enhance performance. Technological innovation offers countless rewards, but also poses dangers that are difficult to predict. How will humanity navigate the promise and perils of the bio-tech, info-tech and nanotech revolution? The various fields (genomics, synthetic biology, nanotechnology, information technology and robotics, regenerative medicine, and neuroscience) that are contributing to this revolution overlap and converge. The overlap and convergence of research in neuroscience and artificial intelligence will be given particular attention in this article. Computational neuroscience has become an important tool for revealing information processing properties of various structures within the nervous system. Computer simulations provide laboratories for testing various theories about mental activity. Findings in neuroscience inform strategies for developing discrete cognitive capabilities in AI. The computational theory of mind drives hypotheses regarding the likelihood of reproducing human intelligence artificially. In turn, critics of the contention that mental activity can

Toward a ban on lethal autonomous weapons: surmounting the obstacles

A 10-point plan toward fashioning a proposal to ban some---if not all---lethal autonomous weapons.

Why machine ethics

“A robot may not injure a human being, or through inaction, allow a human to come to harm.” – Isaac Asimovs First Law of Robotics T he first book report i ever gave, to mrs. slatins first grade class in Lake, Mississippi, in 1961, was on a slim volume entitled You Will Go to the Moon . I have spent the intervening years thinking about the future. The four decades that have passed have witnessed advances in science and physical technology that would be incredible to a child of any other era. I did see my countryman Neil Armstrong step out onto the moon. The processing power of the computers that controlled the early launches can be had today in a five-dollar calculator. The genetic code has been broken and the messages are being read – and in some cases, rewritten. Jet travel, then a perquisite of the rich, is available to all. That young boy that I was spent time on other things besides science fiction. My father was a minister, and we talked (or in many cases, I was lectured and questioned!) about good and evil, right and wrong, and what our duties were to others and to ourselves. In the same four decades, progress in the realm of ethics has been modest. Almost all of it has been in the expansion of inclusiveness, broadening the definition of who deserves the same consideration one always gave neighbors. I experienced some of this first hand as a schoolchild in 1960s Mississippi.