Michael Anderson

University of Hartford · Computer Science

The newly emerging field of machine ethics (Anderson and Anderson 2006) is concerned with adding an ethical dimension to machines. Unlike computer ethics—which has traditionally focused on ethical issues surrounding humans’ use of machines—machine ethics is concerned with ensuring that the behavior of machines toward human users, and perhaps other...

In this paper, a case-supported principle-based behavior paradigm is proposed to help ensure ethical behavior of autonomous machines. We argue that ethically significant behavior of autonomous systems should be guided by explicit ethical principles determined through a consensus of ethicists. Such a consensus is likely to emerge in many areas in wh...

We argue that ethically significant behavior of autonomous systems should be guided by explicit ethical principles determined through a consensus of ethicists. Such a consensus is likely to emerge in many areas in which intelligent autonomous systems are apt to be deployed and for the actions they are liable to undertake, as we are more likely to a...

We propose a framework for incorporating public opinion into policy making in situations where values are in conflict. This framework advocates creating vignettes representing value choices, eliciting the public's opinion on these choices, and using machine learning to extract principles that can serve as succinct statements of the policies implied...

As part of a larger Machine Ethics Project, we are developing an ethical advisor that provides guidance to health care workers faced with ethical dilemmas. MedEthEx is an implementation of Beauchamp’s and Childress’ Principles of Biomedical Ethics that harnesses machine learning techniques to abstract decision principles from cases in a particular...

Robotics researchers have been focusing on developing autonomous and human-like intelligent robots that are able to plan, navigate, manipulate objects, and interact with humans in both static and dynamic environments. These capabilities, however, are usually developed for direct interactions with people in controlled environments, and evaluated pri...

Technological advances are enabling roles for machines that present novel ethical challenges. The study of 'AI ethics' has emerged to confront these challenges, and connects perspectives from philosophy, computer science, law, and economics. Less represented in these interdisciplinary efforts is the perspective of cognitive science. We propose a fr...

At the turn of the 21st century, Susan Leigh Anderson and Michael Anderson conceived and introduced the Machine Ethics research program, that aimed to highlight the requirements under which autonomous artificial intelligence (AI) systems could demonstrate ethical behavior guided by moral values, and at the same time to show that these values, as we...

Since it is of critical importance that autonomous systems, whether software or hardware, that interact with human beings (and perhaps other sentient beings as well) behave in an ethical manner, we consider six possible approaches to effecting this. We argue that the first five approaches are unsatisfactory and defend the last approach, the approac...

Ethical and explainable artificial intelligence is an interdisciplinary research area involving computer science, philosophy, logic, and social sciences, etc. For an ethical autonomous system, the ability to justify and explain its decision-making is a crucial aspect of transparency and trustworthiness. This paper takes a Value-Driven Agent (VDA) a...

OSX distribution of GenEth as described in GenEth: A general ethical dilemma analyzer (Paladyn, 2018). Video demonstration available at https://www.youtube.com/watch?v=w-VI_Yr3KzQ&t=3s.

The field of machine ethics is concerned with the question of how to embed ethical behaviors, or a means to determine ethical behaviors, into artificial intelligence (AI) systems. The goal is to produce artificial moral agents (AMAs) that are either implicitly ethical (designed to avoid unethical consequences) or explicitly ethical (designed to beh...

Should an artificial intelligence (AI) program that appears to have a better success rate than human pathologists be used to replace or augment humans in detecting cancer cells? We argue that some concerns—the “black-box” problem (ie, the unknowability of how output is derived from input) and automation bias (overreliance on clinical decision suppo...

For an autonomous system, the ability to justify and explain its decision making is crucial to improve its transparency and trustworthiness. This paper proposes an argumentation-based approach to represent, justify and explain the decision making of a value driven agent (VDA). By using a newly defined formal language, some implicit knowledge of a V...

This document’s purpose is to provide input into the advisory processes that determine European support for both research into Responsible AI; and how innovation using AI that takes into account issues of responsibility can be supported. “Responsible AI” is an umbrella term for investigations into legal, ethical and moral standpoints of autonomous...

We have implemented a simulation of a robot functioning in the domain of eldercarewhose behavior is completely determined by an ethical principle. Using a subset of the perceptions and duties that will be required of such a robot, this simulation demonstrates selection of ethically preferable actions in real time using a case-supported principle-ba...

This chapter discusses ethics involved with the use of artificial intelligent technologies in behavioral and mental health care. A foundational overview of medical ethics and current ethical codes and guidelines that pertain to the use of technology is provided. Emerging ethical issues are then discussed along with specific recommendations to addre...

To feel comfortable allowing healthcare robots to interact with human beings, we must ensure that they act in an ethically responsible manner, following an acceptable ethical principle(s). Giving robots ethical principles to guide their behavior results in their being ethical agents; yet we argue that it is the human designers, not the robots, who...

A paradigm of case-supported principle-based behavior (CPB) is proposed to help ensure ethical behavior of autonomous machines. We argue that ethically significant behavior of autonomous systems should be guided by explicit ethical principles determined through a consensus of ethicists. Such a consensus is likely to emerge in many areas in which au...

We assert that ethical decision-making is, to a degree, computable. Some claim that no actions can be said to be ethically correct because all value judgments are relative either to societies or individuals. We maintain, however, along with most ethicists, that there is agreement on the ethically relevant features in many particular cases of ethica...

Purpose – This paper aims to propose a paradigm of case-supported principle-based behavior (CPB) to help ensure ethical behavior of autonomous machines. The requirements, methods, implementation and evaluation components of the CPB paradigm are detailed. Design/methodology/approach – The authors argue that ethically significant behavior of autonom...

We contend that ethically significant behavior of autonomous systems should be guided by explicit ethical principles determined through a consensus of ethicists. To provide assistance in developing these ethical principles, we have developed GenEth, a general ethical dilemma analyzer that, through a dialog with ethicists, codifies ethical principle...

We contend that ethically significant behavior of autonomous systems should be guided by explicit ethical principles determined through a consensus of ethicists. To provide assistance in developing these ethical principles, we have developed GenEth, a general ethical dilemma analyzer that, through a dialog with ethicists, codifies ethical principle...

A paradigm of case-supported principle-based behavior is proposed to help ensure ethical behavior of intelligent autonomous machines. The requirements, methods, implementation, and tests of this paradigm are detailed.

We contend that all behavior of autonomous systems should be guided by explicit ethical principles determined through a consensus of ethicists. Such principles ensure the ethical behavior of complex and dynamic systems and further serve as a basis for justification of their actions as well as a control abstraction for managing unanticipated behavio...

Having discovered a decision principle for a well-known prima facie duty theory in biomedical ethics to resolve particular cases of a common type of ethical dilemma, we developed three applications: a medical ethics advisor system, a medication reminder system and an instantiation of this system in a Nao robot. We are now developing a general, auto...

The new field of machine ethics is concerned with giving machines ethical principles, or a procedure for discovering a way to resolve the ethical dilemmas they might encounter, enabling them to function in an ethically responsible manner through their own ethical decision making. Developing ethics for machines, in contrast to developing ethics for...

In our early work on attempting to develop ethics for a machine, we first established that it is possible to create a program that can compute the ethically correct action when faced with a moral dilemma using a well-known ethical theory (Anderson et al. 2006). The theory we chose, Hedonistic Act Utilitarianism, was ideally suited to the task becau...

Autonomous machines will soon play a big role in our lives. It's time they learned how to behave ethically

To advance the understanding of different diagrammatic reasoning architectures that reason directly with images, we examine the relationship between Anderson’s Inter-Diagrammatic Reasoning (IDR) architecture and Furnas’ BITPICT architecture using the technique of cross-implementation. Implementing substantial functionality of each in the other, and...

We have combined a bottom-up casuistry approach with a top-down implementation of an ethical theory to develop a system that uses machine-learning to abstract relationships between prima facie ethical duties from cases of particular types of ethical dilemmas where ethicists are in agreement as to the correct action. This system has discovered a nov...

Building on our previous achievements in machine ethics (Anderson et al. 2006a-b, 2007, 2008), we are developing and implementing a general interactive approach to analyzing ethical dilemmas with the goal to apply it toward the end of codifying the ethical principles that will help resolve ethical dilemmas that intelligent systems will encounter in...

This paper is a summary and evaluation of work presented at the AAAI 2005 Fall Symposium on Machine Ethics that brought together participants from the fields of Computer Science and Philosophy to the end of clarifying the nature of this newly emerging field and discussing different approaches one could take towards realizing the ultimate goal of cr...

We consider the consequences for human beings of attempting to create ethical robots, a goal of the new field of AI that has been called Machine Ethics. We argue that the concerns that have been raised are either unfounded, or can be minimized, and that many benefits for human beings can come from this research. In particular, working on machine et...

To make ethics computable, we've adopted an approach to ethics that involves considering multiple prima facie duties in deciding how one should act in an ethical dilemma. We believe this approach is more likely to capture the complexities of ethical decision making than a single, absolute-duty ethical theory. However, it requires a decision procedu...

Machine ethics is concerned with how machines behave toward human users and other machines. It aims to create a machine that's guided by an acceptable ethical principle or set of principles in the decisions it makes about possible courses of action it could take. As ethics experts continue to progress toward consensus concerning the right way to be...

As part of a larger Machine Ethics Project, we are developing an ethical advisor that provides guidance to health care workers faced with ethical dilemmas. MedEthEx is an implementation of Beauchamp's and Childress' Principles of Biomedical Ethics that harnesses machine learning techniques to abstract decision principles from cases in a particular...

Machine ethics, in contrast to computer ethics, is concerned with the behavior of machines towards human users and other machines. It involves adding an ethical dimension to machines. Our increasing reliance on machine intelligence that effects change in the world can be dangerous without some restraint. We explore the implementation of two action-...

We contend that the ethical ramifications of machine behavior, as well as recent and potential developments in machine autonomy, necessitate adding an ethical dimension to at least some machines. We lay the theoretical foundation for machine ethics by discussing the rationale for, the feasibilty of, and the benefits of adding an ethical dimension t...

Of the set of behaviors that will be required of an autonomous artificially intelligent agent, a somewhat neglected member has been the ability to deal with diagrammatic information. We describe a theoretical and computational foundation for machine processing of certain forms of diagrammatic information and show its usefulness in enabling a system...

Diagrams are essential in most fields of human activity. There is substantial interest in diagrams and their use in many academic disciplines for the potential benefits they may confer on a wide range of tasks. Are we now in a position to claim that we have a science of diagrams- that is, a science which takes the nature of diagrams and their use a...

The fields of sketch understanding and diagrammatic reasoning share some goals and motivations. We propose that both fields can benefit from a research agenda that addresses these common goals, leveraging techniques from one field to address questions in the other. We present the diaSketch as an example of such synergy.

We show how Diagrammatic SQL, a query language that can be used to query information represented as diagrams, can be combined with SQL to permit queries on combinations of diagrammatic and symbolic data producing both diagrammatic and symbolic responses.

Knowledge discovery from diagrammatic data can be facilitated by a language that permits queries on such data. Such a language (Diagrammatic SQL) is being developed to expedite the development of an autonomous artificially intelligent agent with a capacity to deal with diagrammatic information. This language is described and examples of how it can...

Knowledge discovery from diagrammatic data can be facilitated by a language that permits queries on such data. Such a language (Diagrammatic SQL) is being developed to expedite the development of an autonomous artificial intelligent agent with a capacity to deal with diagrammatic information. This language is described and examples of how it can be...

Smart graphics can be beneficial beyond the level of the user interface. A synergistic combination of artificial intelligence methods and image processing techniques can be useful in permitting intelligent interaction with graphical representations at the processing level as well. An example of such a combination is explored in the context of a dia...

We advocate the development of an agent capable of processing diagrammatic information directly in all its forms. In the same way that we will require intelligent agents to be conversant with natural language, we will expect them to be fluent with diagrammatic information and its processing. We present a methodology to this end, detail a diagrammat...

The theory of inter-diagrammatic reasoning is extended to include the use of color values in diagrams. The syntax of this more general theory, its subsumption of the original theory, and the ramifications of this extension are presented. An example application of this extension in the domain of DNA sequence assembly is described.

Although research in diagrammatic reasoning is as old as research in artificial intelligence itself, it has only recently aroused from a long dormancy induced by a bias toward symbolic computing. This resurgence of interest has been almost exclusively slanted towards the investigation of how a computer might be coaxed into generating information fr...

We believe that many problem domains that lend themselves to a case-based reasoning solution can benefit from a diagrammatic implementation and propose a diagrammatic case-based solution to what we term the n-queens best solution problem where the best solution is defined as that which solves the problem moving the fewest queens. A working system,...

Endowing a computer with an ability to reason with diagrams could be of great benefit in terms of both human-computer interaction and computational efficiency through explicit representation. To date, research in diagrammatic reasoning has dealt with intra-diagrammatic reasoning (reasoning with a single diagram) almost to the exclusion of inter-dia...

Endowing a computer with an ability to reason with diagrams could be of great benefit. To date, research in diagrammatic reasoning has dealt with intra-diagrammatic reasoning (reasoning within a single diagram) almost to the exclusion of interdiagrammatic reasoning (reasoning with related groups of diagrams). We postulate a number of general inter-...

The design of a system capable of handling ad hoc user responses to system-initiated questions is considered. An approach called the expectation-driven response understanding paradigm was developed. In this paradigm, it is assumed that each system-generated question is accompanied by an expectation of what the user should respond. The system attemp...

As part of a larger Machine Ethics Project, we are developing an ethical advisor that provides guidance to health care workers faced with ethical dilemmas. MedEthEx is an implementation of Beauchamp's and Childress' Principles of Biomedical Ethics that harnesses machine learning techniques to abstract decision principles from cases in a particular...

Entertainment has always involved fictional characters in artificial settings. Effective use of artificial worlds and characters demands that the agents and worlds be believable and understandable. We examine the world and characters in the Road Runner cartoons, and show how the world, while not realistic, is internally consis-tent. We argue that t...

A diagram sequence can be defined as a meta-diagram composed of a number of subdiagrams arranged in an order that incorporates some manner of forward moving time. Humans possess a highly developed ability to reason with diagram sequences. Endowing a computer with such an ability could be of great benefit in terms of both human-computer interaction...

Typescript (photocopy). Thesis (M.S.)--University of Connecticut, 1990. Includes bibliographical references.