University of Hertfordshire

From the same journal

Outline of a sensory-motor perspective on intrinsically moral agents

Research output: Contribution to journalArticlepeer-review

Standard

Outline of a sensory-motor perspective on intrinsically moral agents. / Balkenius, Christian; Canamero, Lola; Parmanets, Philip; Johansson, Birger; Butz, Martin; Olsson, Andreas.

In: Adaptive Behavior, Vol. 24, No. 5, 03.11.2016, p. 306-319.

Research output: Contribution to journalArticlepeer-review

Harvard

Balkenius, C, Canamero, L, Parmanets, P, Johansson, B, Butz, M & Olsson, A 2016, 'Outline of a sensory-motor perspective on intrinsically moral agents', Adaptive Behavior, vol. 24, no. 5, pp. 306-319. https://doi.org/10.1177/1059712316667203

APA

Balkenius, C., Canamero, L., Parmanets, P., Johansson, B., Butz, M., & Olsson, A. (2016). Outline of a sensory-motor perspective on intrinsically moral agents. Adaptive Behavior, 24(5), 306-319. https://doi.org/10.1177/1059712316667203

Vancouver

Balkenius C, Canamero L, Parmanets P, Johansson B, Butz M, Olsson A. Outline of a sensory-motor perspective on intrinsically moral agents. Adaptive Behavior. 2016 Nov 3;24(5):306-319. https://doi.org/10.1177/1059712316667203

Author

Balkenius, Christian ; Canamero, Lola ; Parmanets, Philip ; Johansson, Birger ; Butz, Martin ; Olsson, Andreas. / Outline of a sensory-motor perspective on intrinsically moral agents. In: Adaptive Behavior. 2016 ; Vol. 24, No. 5. pp. 306-319.

Bibtex

@article{23cb1bf4729c4ed68f9ff4838154f020,
title = "Outline of a sensory-motor perspective on intrinsically moral agents",
abstract = "We propose that moral behaviour of artificial agents could (and should) be intrinsically grounded in their own sensory-motor experiences. Such an ability depends critically on seven types of competencies. First, intrinsic morality should be grounded in the internal values of the robot arising from its physiology and embodiment. Second, the moral principles of robots should develop through their interactions with the environment and with other agents. Third, we claim that the dynamics of moral (or social) emotions closely follows that of other non-social emotions used in valuation and decision making. Fourth, we explain how moral emotions can be learned from the observation of others. Fifth, we argue that to assess social interaction, a robot should be able to learn about and understand responsibility and causation. Sixth, we explain how mechanisms that can learn the consequences of actions are necessary for a robot to make moral decisions. Seventh, we describe how the moral evaluation mechanisms outlined can be extended to situations where a robot should understand the goals of others. Finally, we argue that these competencies lay the foundation for robots that can feel guilt, shame and pride, that have compassion and that know how to assign responsibility and blame.",
keywords = "autonomous robots, embodied emotions, sensory-motor grouonding, embodied interaction, empathy, intrinsic morality",
author = "Christian Balkenius and Lola Canamero and Philip Parmanets and Birger Johansson and Martin Butz and Andreas Olsson",
note = "This is the accepted version of the following article: Christian Balkenius, Lola Ca{\~n}amero, Philip P{\"a}rnamets, Birger Johansson, Martin V Butz, and Andreas Olson, {\textquoteleft}Outline of a sensory-motor perspective on intrinsically moral agents{\textquoteright}, Adaptive Behaviour, Vol 24(5): 306-319, October 2016, which has been published in final form at DOI: https://doi.org/10.1177/1059712316667203 Published by SAGE {\textcopyright}The Author(s) 2016 ",
year = "2016",
month = nov,
day = "3",
doi = "10.1177/1059712316667203",
language = "English",
volume = "24",
pages = "306--319",
journal = "Adaptive Behavior",
issn = "1059-7123",
publisher = "SAGE Publications Ltd",
number = "5",

}

RIS

TY - JOUR

T1 - Outline of a sensory-motor perspective on intrinsically moral agents

AU - Balkenius, Christian

AU - Canamero, Lola

AU - Parmanets, Philip

AU - Johansson, Birger

AU - Butz, Martin

AU - Olsson, Andreas

N1 - This is the accepted version of the following article: Christian Balkenius, Lola Cañamero, Philip Pärnamets, Birger Johansson, Martin V Butz, and Andreas Olson, ‘Outline of a sensory-motor perspective on intrinsically moral agents’, Adaptive Behaviour, Vol 24(5): 306-319, October 2016, which has been published in final form at DOI: https://doi.org/10.1177/1059712316667203 Published by SAGE ©The Author(s) 2016

PY - 2016/11/3

Y1 - 2016/11/3

N2 - We propose that moral behaviour of artificial agents could (and should) be intrinsically grounded in their own sensory-motor experiences. Such an ability depends critically on seven types of competencies. First, intrinsic morality should be grounded in the internal values of the robot arising from its physiology and embodiment. Second, the moral principles of robots should develop through their interactions with the environment and with other agents. Third, we claim that the dynamics of moral (or social) emotions closely follows that of other non-social emotions used in valuation and decision making. Fourth, we explain how moral emotions can be learned from the observation of others. Fifth, we argue that to assess social interaction, a robot should be able to learn about and understand responsibility and causation. Sixth, we explain how mechanisms that can learn the consequences of actions are necessary for a robot to make moral decisions. Seventh, we describe how the moral evaluation mechanisms outlined can be extended to situations where a robot should understand the goals of others. Finally, we argue that these competencies lay the foundation for robots that can feel guilt, shame and pride, that have compassion and that know how to assign responsibility and blame.

AB - We propose that moral behaviour of artificial agents could (and should) be intrinsically grounded in their own sensory-motor experiences. Such an ability depends critically on seven types of competencies. First, intrinsic morality should be grounded in the internal values of the robot arising from its physiology and embodiment. Second, the moral principles of robots should develop through their interactions with the environment and with other agents. Third, we claim that the dynamics of moral (or social) emotions closely follows that of other non-social emotions used in valuation and decision making. Fourth, we explain how moral emotions can be learned from the observation of others. Fifth, we argue that to assess social interaction, a robot should be able to learn about and understand responsibility and causation. Sixth, we explain how mechanisms that can learn the consequences of actions are necessary for a robot to make moral decisions. Seventh, we describe how the moral evaluation mechanisms outlined can be extended to situations where a robot should understand the goals of others. Finally, we argue that these competencies lay the foundation for robots that can feel guilt, shame and pride, that have compassion and that know how to assign responsibility and blame.

KW - autonomous robots

KW - embodied emotions

KW - sensory-motor grouonding

KW - embodied interaction

KW - empathy

KW - intrinsic morality

UR - http://adb.sagepub.com/content/24/5/306.abstract

U2 - 10.1177/1059712316667203

DO - 10.1177/1059712316667203

M3 - Article

VL - 24

SP - 306

EP - 319

JO - Adaptive Behavior

JF - Adaptive Behavior

SN - 1059-7123

IS - 5

ER -