International Workshop on Computational Machine Ethics

Held in conjunction with KR 2021
November 5, Online event


Machine ethics is a subfield of AI ethics concerned with implementing moral and ethical behaviours in cognitive machines. The successful deployment of cognitive machines or robots in human society will require them to be adequately equipped with the moral and ethical competence to prevent physical, emotional or psychological harm they could cause by otherwise being oblivious to ethics and morality and to maximise the benefits they can provide to society. In recent years various approaches have been developed including logic-based formulations, reinforcement learning methods and hybrid models. While learning-based methods provide higher flexibility and adaptability, logic-based formulation enables better explainability, which is an important requirement in ethics. Nevertheless, compared to the extensive discussion in the press regarding the dangers of AI and rapid development of frameworks for regulating the ethical use of AI, there is surprisingly little literature on computational approaches to ensure ethical consideration in AI applications particularly machine ethics. In particular, how to represent ethical principles and reason about the best course of action for real-life scenarios in a generalisable way largely remains an open question. There is thus much needed research in knowledge representation and reasoning for this important area and a workshop in KR will provide the best venue to facilitate knowledge exchange and in-depth discussion.


The 1st International Workshop on Computational Machine Ethics (CME 2021) aims to provide a forum for researchers from academia and industry to exchange ideas and techniques in the area of machine ethics, to promote widespread awareness of machine ethics in the KR community as well as identifying new research directions in the area. Besides regular research papers, we also welcome vision papers, demonstration papers and papers showcasing industry applications.

Topics of interest include but are not limited to:
  • Explicit ethical agents
  • Logic-based approaches to machine ethics
  • Knowledge representation of ethical principles
  • Commonsense reasoning and its application to machine ethics
  • Machine learning-based approaches to machine ethics
  • Integration of symbolic and sub-symbolic models
  • Computational modelling of morality and ethics
  • Natural language processing for descriptive ethics
  • Formal verification of machine ethics
  • Development of machine ethics in cognitive robot programs
  • Explainability of ethical reasoning

Organising Committee

Program Committee

Important Dates

The workshop will be fully online.

  • Paper submission: 2 July 2021 extended to 23 July 2021
  • Paper notification: 6 August 2021 27 August 2021
  • Workshop date and time: 5 November 2021, 08:00-12:00 (CET time)
  • Registration: Registration is free but mandatory for attending KR2021 and the workshop. Click this link to register on the KR2021 website by Oct 15.


We welcome and encourage the submission of original, previously unpublished research and also have a recently published research track, similarly to the main conference of KR 2021. Submissions should be 3-6 pages (including figures, references, etc.) and formatted according to the KR 2021 style files. Papers can be submitted via EasyChair:

The workshop proceedings will be submitted to for online publication.

Invited Speakers

Workshop Programs

08:00-08:15    Opening 
08:15-09:15 Invited Talk 1 Speaker: Toby Walsh, UNSW, Australia Title: All the AI ethical principles you need to know (and perhaps implement) Abstract: There is a lot of discussion in many different fora about AI and Ethics. Companies, governments, and many other bodies have put forwards plethora of different ethical principles to deal with the new challenges that AI brings. I will attempt to identify what new issues AI brings to the table, as well as where AI requires us to address otherwise old issues. I will cover topics from driverless cars to predictive policing. Biography: Toby Walsh is an ARC Laureate Fellow and Scientia Professor of AI at UNSW and CSIRO Data61, and adjunct professor at QUT. He is a strong advocate for limits to ensure AI is used to improve our lives, having spoken at the UN, and to heads of state, parliamentary bodies, company boards and many other bodies on this topic. He is a Fellow of the Australia Academy of Science, and was named on the international "Who's Who in AI" list of influencers. He has authored two books on AI for a general audience, the most recent entitled "2062: The World that AI Made". His third book, "Machines Behaving Badly: the morality of AI" is out in Easter 2022.
09:15-10:15 Invited Talk 2 Speaker: Louise Dennis, University of Manchester, UK Title: Explicitly ethical agent reasoning [slides] Abstract: This talk will survey our work on the implementation of computational ethical reasoning using approaches from Symbolic Artificial Intelligence. In particular we will focus on work where an agent that can perform ethical reasoning interacts with some larger system in order to modify the system behaviour in line with an explicit ethical theory drawn from philosophy. We will look at a range of implementation options (including the philosophical theories chosen and the ways an ethical agent interacts with the rest of the system) and discuss how these relate to important topics such as stakeholder involvement and verification. Biography: Louise Dennis is a senior lecturer at the University of Manchester where she is part of the Autonomy and Verification group. Her expertise is in the development and verification of autonomous systems with interests in rational agent programming languages, and architectures for autonomous systems, with a particular emphasis on ethical machine reasoning, explainability and creating verifiable systems. Her work on machine ethics has involved the implementation of a number of ethical theories for decision-making and the formal verification of those implementations. Louise is currently co-investigator on two UKRI Hubs for Robotics for a Safer World: Future AI and Robotics for Space (FAIR-SPACE) and Robotics and AI for Nuclear (RAIN) and on the Trustworthy Autonomous Systems programme node on Verifiability. She is a member of the IEEE Standards working group for Transparency for Autonomous Systems (P7001).
10:15-10:30 Coffee Break
10:30-11:30 Paper Presentations 10:30-10:45 Louise Dennis and Cristina Perea del Olmo A defeasible logic implementation of ethical reasoning [paper] 10:45-11:00 Gauvain Bourgne, Camilo Sarmiento and Jean-Gabriel Ganascia ACE modular framework for computational ethics: dealing with multiple actions, concurrency and omission [paper] 11:00-11:15 Rajitha Ramanayake and Vivek Nallur A computational architecture for a pro-social rule bending agent [paper] 11:15-11:30 Ken Satoh, Jean-Gabriel Ganascia, Gauvain Bourgne and Adrian Paschke Overview of RECOMP project [paper]
11:30-11:55 Panel Discussion
11:55-12:00 Closing
*All times are CET.