Moral Machines: Teaching Robots Right from Wrong

By Wendell Wallach, C. Allen. 2008

1,024 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Cognitive Neuroscience, Safety Research

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Cognitive Neuroscience

In Safety Research

Citations in the corpus

Research Priorities for Robust and Beneficial Artificial Intelligence (2015, background): “For example, Wallach and Allen (2008) argue that a signiﬁcant consideration is the computational expense of diﬀerent behavioral standards (or ethical theories): if a standard cannot be applied eﬃciently enough to guide behavior in safety-critical situations, then cheaper approximations may be…”
Ethical principles in machine learning and artificial intelligence: cases from the field and possible ways forward (2020, background): “Furthermore, the way decisions enacted could back ﬁ re in complex contexts to which the algorithms had no extrapolative power, is an unpredictable issue one has to deal with (Wallach and Allen, 2008; Yurtsever et al., 2020).”
Legal, regulatory, and ethical frameworks for development of standards in artificial intelligence (AI) and autonomous robotic surgery (2019, background): “Such decisions could be informed by what Wallach and Allen (2009) 55 call “ top ‐ down, ” ie, theory ‐ driven, approaches to ethical decision making, or they could be shaped by “ bottom ‐ up, ” or data ‐ driven processes that have been trained to emulate human decision makers.”
Robot rights? Towards a social-relational justification of moral consideration (2010, background): “…Robotics’ testify (Asimov 1942), or that we should build ‘moral machines’ that do not only follow ‘top-down’ laws given to them by humans but that also have the capacity to develop into moral machines ‘bottom up’, that is, by moral learning emerging from their intelligence (Wallach & Allen 2008).”
Interpretable Multi-Objective Reinforcement Learning through Policy Orchestration (2018, background): “These topics have gained popularity among a broad community including philosophers (Wallach and Allen 2008) and non-proﬁts (Russell, Dewey, and Tegmark 2015).”
Towards an Ethical Robot: Internal Models, Consequences and Ethical Action Selection (2014, background): “For instance, in their book Moral Machines, Wendell and Allen [16] write " If multipurpose machines are to be trusted, operating untethered from their designers or owners and programmed to respond flexibly in real or virtual world environments, there must be confidence that their behaviour satisfies”
Artificial Intelligence and Responsible Innovation (2013, background): “(Wallach and Allen 2010); not being designed primarily to kill, being designed with safety in mind, and being transparent with respect to the non-human nature of the artifact (Parry et al.”
Six Human-Centered Artificial Intelligence Grand Challenges (2023, methodology): “For the actual programming of moral capacities into AI systems, two approaches are mainly considered: a top-down and a bottom-up approach (Wallach & Allen, 2008).”
The social dilemma of autonomous vehicles (2015, background): “algorithms that control AVs will need to embed moral principles guiding their decisions in situations of unavoidable harm (10).”
Against the moral Turing test: accountable design and the moral reasoning of autonomous systems (2016, background): “Allen and Wallach have broached this concept (coining the acronym MTT for moral Turing test), rightly noting some difficult problems an MTT would have to resolve in order to be viable (Allen et al. 2006; Wallach and Allen 2008).”
Correcting Robot Plans with Natural Language Feedback (2022, methodology): “This problem of misalignment or a difference in the cost in the mind of the human C H and the robot C R is referred to as the value alignment problem [42].”
Granny and the robots: ethical issues in robot care for the elderly (2012, background): “Similar sensitive customisation of monitoring robots, using a value sensitive design approach, may well turn out to be the best way of garnering the advantages afforded by robots, without reducing the quality of life of the elderly (see Forlizzi et al. 2004 for a related approach).”
Scruples: A Corpus of Community Ethical Judgments on 32, 000 Real-Life Anecdotes (2020, background): “Principally, efforts divide into top-down and bottom-up approaches (Wallach and Allen 2009).”
Blame It on the Self-Driving Car: How Autonomous Vehicles Can Alter Consumer Morality (2020, background): “For behavioral science scholars, the pertinent issue is about the moral competence that AVs should have rather than the technical issue of how it could be implemented (see Conitzer et al. 2017; Wallach and Allen 2008; and Wallach et al. 2010, for a discussion on some of the implementation issues).”
Incorporating Ethics into Artificial Intelligence (2017, background): “(Wallach and Allen 2009: 3) That is, the same question asked about driverless cars stands for many other autonomous machines, including weapons that choose their own targets; robotic surgeons; robots that provide child, elder, and health care; as well as quite a few others.”