The French National Research Agency Projects for science

Voir cette page en français

ANR funded project

Contenus numériques et interactions (CONTINT)
Edition 2013


ETHICAA


ETHICs and Autonomous Agents

Ethics and Autonomous Agents
Machines and software acting on behalf of humans (i.e. agents) get more autonomy and are increasingly less under the control of human operators or users. As already discussed in the literature, the question of an ethical regulation and control of autonomous agents is raised. The objective of the ETHICAA project is to define what should be an autonomous entity that could manage ethical conflicts, considering both the individual agent and the multi-agent levels.

Main issues
Most of the contributions so far have dealt with recommendations, advices or hard-wired ethical principles. However major challenges still hold. First, ethical theories are themselves difficult to implement with operational ethical principles. Second, operational ethical principles are difficult to implement due to automatic situation assessment limits. General rules fail to assess a situation and contextual evaluation should be used for each particular situation. Third, from a philosophical point-of-view, there are numerous ethical principals and none of them is better than the others making difficult to choose the one to implement. Finally, as far as applications are concerned, ICT systems are more and more open and decentralized, and involve autonomous artificial agents interacting with other agents, human operators or users. In this context, managing the ethical conflicts between the agents is a major issue.

That is why novel and original methods are needed to address contextual ethical decision-making for such collective systems.

Methods
The ethical conflicts are characterized by the fact that there is no « good » way to solve them, and when a decision must be made it should be an informed decision based on an assessment of the arguments and values at stake. Broadly speaking, three important components have to be considered to define a conflict management framework dealing with ethical conflicts in agent systems: (1) definition of an ethical reasoning framework including the representation of several ethical principles and situation assessment; (2) definition of ethical conflicts detection methods that can tackle situations where agents reason individually or collectively; (3) definition of multiple ethical decision-making models to manage ethical conflicts in smartly combining different ethical principles into a multi-point-of-view ethical decision-making framework.

As ethics is an individual notion shaped on culture, context and personal experiences, ethical decision-making only makes sense in a given application. The ETHICAA project proposes to instanciate its framework on two applicative domains: robotics and privacy management. These two domains have been chosen for their impact on society in terms of trust, acceptance and ethics. In the robotic domain, the ETHICAA framework will be used to manage ethical conflicts arising in the cooperation between one artificial agent and one human operator in the context of the joint operation of an UAV (Unmanned Air Vehicle). In the case of privacy management, ethical conflicts may arise between multiple artificial agents and human users, and we will consider a social network where ethical autonomous agents control and manage the privacy policies of the accounts owned by humans.

Results

s, the ETHICAA project aims at
proposing conflict management modes based on the assess-
ment of the arguments and values at stake for agent systems
featuring ethical behaviours. In this paper, we present vari-
ous practical case studies of ethical conflicts and highlight
what their main system and decision features are. This gath-
ering of requirements is a first step towards the definition
of the conflict management framework envisionned in the
project.

Outlook

The results targeted by the ETHICAA project are (i) formal representation of ethical principles, values and conflicts, as well as (ii) automatic reasoning models to handle these ethical representations, (iii) all being validated on real world scenarios. Consequently the outcome of ETHICAA is composed of a framework and recommendations to design ethical systems of artificial agents, i.e. able to execute ethical regulation modes depending of the context and ethical conflicts involving other agents or humans.

Scientific outputs and patents

The project ETHICAA produced two articles in 2014. The first one is entitled «Towards a Framework to Deal with Ethical Conflicts in Autonomous Agents and Multi-Agent Systems« and was presented at the 12th International Conference on Computational Ethics and Philosophical Enquiry (CPCE). The second one is entitled «Can a drone be brave?« and was presented at the 82nd Congress of the Francophone Association for Knowledge.

Partners

Ardans Ardans SAS

ARMINES - FAYOL ARMINES - Institut Henri Fayol de l'Ecole des Mines de Saint-Etienne

GREYC Groupe de Recherche en Informatique, Image, Automatique et Instrumentation de Caen

IMT Institut Mines Télécom

LIP6 Laboratoire d'Informatique de Paris 6

Onera Onera

ANR grant: 993 788 euros
Beginning and duration: janvier 2014 - 48 mois

Submission abstract

Machines and software acting on behalf of humans (i.e. agents) get more autonomy and are increasingly less under the control of human operators or users. Therefore especially when machines interact with humans, we need to ensure that they do not harm them or threaten their autonomy. Consequently the question of an ethical regulation and control of such autonomous agents is raised and has been discussed in the literature, stressing the need of ethical standards.

The objective of the ETHICAA project is to define what should be an autonomous entity that could manage ethical conflicts, considering both the individual agent and the multi-agent levels. The ethical conflicts that will be considered are those occurring 1) inside one agent, 2) between one agent and the ethical principles and values of the system it belongs to, 3) between one agent and a human operator or user, 4) between several agents including or not human beings. Ethical conflicts are characterized by the fact that there is no « good » way to solve them. Nevertheless when a decision must be made it should be an informed decision based on an assessment of the arguments and values at stake. The models, methods and tools developed within the project will contribute to define the ETHICAA framework for the definition and management of agent systems featuring ethical behaviours.

ETHICAA proposes to base the achievement of this objective on two applicative domains: robotics and privacy management. These two domains have been chosen for their impact on society in terms of trust, acceptance and ethics. In the robotic domain, the ETHICAA framework will be used to manage ethical conflicts arising in the cooperation between one artificial agent and one human operator in the context of the joint operation of a UAV (Unmanned Air Vehicle). In the case of privacy management, ethical conflicts may arise between multiple artificial agents and human users inside a social network where ethical autonomous agents control and manage the privacy policies of the accounts owned by humans.

The results targeted by the ETHICAA project are (i) formal representation of ethical principles, values and conflicts, as well as (ii) automatic reasoning models to handle these ethical representations, (iii) all being validated on real world scenarios. Consequently the outcome of ETHICAA is composed of a framework and recommendations to design ethical systems of artificial agents, i.e. able to execute ethical regulation modes depending of the context and ethical conflicts involving other agents or humans.

 

ANR Programme: Contenus numériques et interactions (CONTINT) 2013

Project ID: ANR-13-CORD-0006

Project coordinator:
Monsieur Gregory BONNET (Groupe de Recherche en Informatique, Image, Automatique et Instrumentation de Caen)

Project web site: http://ethicaa.org/

 

Back to the previous page

 

The project coordinator is the author of this abstract and is therefore responsible for the content of the summary. The ANR disclaims all responsibility in connection with its content.