Machine Morality: From Harm-Avoidance
to Human-Robot Cooperation
Ismael T. Freire
1,2,3(B) , Dina Urikh
1,2,3 , Xerxes D. Arsiwalla
1,2,3 ,
and Paul F. M. J. Verschure
1,3,4
1 Institute for BioEngineering of Catalonia (IBEC), Barcelona, Spain
ismaeltito.freire@gmail.com
2 Universitat Pompeu Fabra (UPF), Barcelona, Spain
3 Barcelona Institue of Science and Technology (BIST), Barcelona, Spain
4 Catalan Institute for Research and Advanced Studies (ICREA), Barcelona, Spain
Abstract. We present a new computational framework for modeling
moral decision-making in artificial agents based on the notion of ‘Machine
Morality as Cooperation’. This framework integrates recent advances
from cross-disciplinary moral decision-making literature into a single
architecture. We build upon previous work outlining cognitive elements
that an artificial agent would need for exhibiting latent morality, and
we extend it by providing a computational realization of the cognitive
architecture of such an agent. Our work has implications for cognitive
and social robotics. Recent studies in human neuroimaging have pointed
to three different decision-making processes, Pavlovian, model-free and
model-based, that are defined by distinct neural substrates in the brain.
Here, we describe how computational models of these three cognitive processes can be implemented in a single cognitive architecture by using the
distributed and hierarchical organization proposed by the DAC theoretical framework. Moreover, we propose that a pro-social drive to cooperate
exists at the Pavlovian level that can also bias the rest of the decision
system, thus extending current state-of-the-art descriptive models based
on harm-aversion.
Keywords: Morality · Moral decision-making · Computational
models · Cognitive architectures · Cognitive robotics · Human-robot
interaction
1 Introduction
Ever since the ancient Greeks, thinkers across the world have struggled to identify
fundamental features that let human beings create complex social structures
within and between groups. Today theories coming from a wide range of fields
(from evolutionary anthropology to social cognitive neuroscience) are aiming
to explain social cooperation that leads to emergence of such phenomena as
altruism or moral conduct.
c
Springer Nature Switzerland AG 2020
V. Vouloutsi et al. (Eds.): Living Machines 2020, LNAI 12413, pp. 116–127, 2020.
https://doi.org/10.1007/978-3-030-64313-3_13
to Human-Robot Cooperation
Ismael T. Freire
1,2,3(B) , Dina Urikh
1,2,3 , Xerxes D. Arsiwalla
1,2,3 ,
and Paul F. M. J. Verschure
1,3,4
1 Institute for BioEngineering of Catalonia (IBEC), Barcelona, Spain
ismaeltito.freire@gmail.com
2 Universitat Pompeu Fabra (UPF), Barcelona, Spain
3 Barcelona Institue of Science and Technology (BIST), Barcelona, Spain
4 Catalan Institute for Research and Advanced Studies (ICREA), Barcelona, Spain
Abstract. We present a new computational framework for modeling
moral decision-making in artificial agents based on the notion of ‘Machine
Morality as Cooperation’. This framework integrates recent advances
from cross-disciplinary moral decision-making literature into a single
architecture. We build upon previous work outlining cognitive elements
that an artificial agent would need for exhibiting latent morality, and
we extend it by providing a computational realization of the cognitive
architecture of such an agent. Our work has implications for cognitive
and social robotics. Recent studies in human neuroimaging have pointed
to three different decision-making processes, Pavlovian, model-free and
model-based, that are defined by distinct neural substrates in the brain.
Here, we describe how computational models of these three cognitive processes can be implemented in a single cognitive architecture by using the
distributed and hierarchical organization proposed by the DAC theoretical framework. Moreover, we propose that a pro-social drive to cooperate
exists at the Pavlovian level that can also bias the rest of the decision
system, thus extending current state-of-the-art descriptive models based
on harm-aversion.
Keywords: Morality · Moral decision-making · Computational
models · Cognitive architectures · Cognitive robotics · Human-robot
interaction
1 Introduction
Ever since the ancient Greeks, thinkers across the world have struggled to identify
fundamental features that let human beings create complex social structures
within and between groups. Today theories coming from a wide range of fields
(from evolutionary anthropology to social cognitive neuroscience) are aiming
to explain social cooperation that leads to emergence of such phenomena as
altruism or moral conduct.
c
Springer Nature Switzerland AG 2020
V. Vouloutsi et al. (Eds.): Living Machines 2020, LNAI 12413, pp. 116–127, 2020.
https://doi.org/10.1007/978-3-030-64313-3_13