ABSTRACT
Human behavior is frequently guided by social and moral norms, and no human community can exist without norms. Robots that enter human societies must therefore behave in norm-conforming ways as well. However, currently there is no solid cognitive or computational model available of how human norms are represented, activated, and learned. We provide a conceptual and psychological analysis of key properties of human norms and identify the demands these properties put on any artificial agent that incorporates norms-demands on the format of norm representations, their structured organization, and their learning algorithms.
- Aarts, H. and Dijksterhuis, A. 2003. The silence of the library: Environment, situational norm, and social behavior. Journal of Personality and Social Psychology. 84, 1 (Jan. 2003), 18--28.Google ScholarCross Ref
- Abel, D. et al. 2016. Reinforcement learning as a framework for ethical decision making. AAAI Workshop: AI, Ethics, and Society, volume WS-16-02 of 13th AAAI Workshops (2016).Google Scholar
- Allen, C. et al. 2005. Artificial morality: Top-down, bottom-up, and hybrid approaches. Ethics and Information Technology. 7, 3 (Sep. 2005), 149--155. Google ScholarDigital Library
- Anderson, M. et al. 2018. A value-driven eldercare robot: Virtual and physical instantiations of a case-supported principle-based behavior paradigm. Proceedings of the IEEE. (2018), 1--Google Scholar
- Arai, S. and Suzuki, K. 2014. Encouragement of right social norms by inverse reinforcement learning. Journal of Information Processing. 22, 2 (2014), 299--306.Google ScholarCross Ref
- Arnold, T. et al. 2017. Value alignment or misalignment -- What will keep systems accountable? The Workshops of the Thirty-First AAAI Conference on Artificial Intelligence: Technical Reports, WS-17-02: AI, Ethics, and Society. The AAAI Press. 81--88.Google Scholar
- Bello, P. et al. 2018. An attention-driven computational model of human causal reasoning. Proceedings of the 40th Annual Meeting of the Cognitive Science Society (Austin, TX, 2018), 1353--1358.Google Scholar
- Bendor, J. and Swistak, P. 2001. The evolution of norms. American Journal of Sociology. 106, 6 (2001), 1493--1545.Google ScholarCross Ref
- Bicchieri, C. 2006. The grammar of society: The nature and dynamics of social norms. Cambridge University Press.Google Scholar
- Brauer, M. and Chaurand, N. 2010. Descriptive norms, prescriptive norms, and social control: An intercultural comparison of people's reactions to uncivil behaviors. European Journal of Social Psychology. 40, 3 (Apr. 2010), 490--499.Google Scholar
- Brennan, G. et al. 2013. Explaining norms. Oxford University Press.Google Scholar
- Bringsjord, S. et al. 2006. Toward a general logicist methodology for engineering ethically correct robots. Intelligent Systems, IEEE. 21, 4 (2006), 38--44. Google ScholarDigital Library
- Chisholm, R.M. 1963. Contrary-to-duty imperatives and deontic logic. Analysis. 24, 2 (1963), 33--36.Google ScholarCross Ref
- Cialdini, R.B. et al. 1990. A focus theory of normative conduct: Recycling the concept of norms to reduce littering in public places. Journal of Personality and Social Psychology. 58, 6 (1990), 1015--1026.Google ScholarCross Ref
- Gasparini, L. et al. 2018. Severity-sensitive norm-governed multi-agent planning. Autonomous Agents and Multi-Agent Systems. 32, 1 (Jan. 2018), 26--58. Google ScholarDigital Library
- Gibbs, J.P. 1965. Norms: The problem of definition and classification. American Journal of Sociology. 70, 5 (1965), 586--594.Google ScholarCross Ref
- Hechter, M. and Opp, K.-D. 2001. Social Norms. Russell Sage Foundation.Google Scholar
- Henrich, J. 2009. The evolution of costly displays, cooperation and religion: Credibility enhancing displays and their implications for cultural evolution. Evolution and Human Behavior. 30, 4 (Jul. 2009), 244--260.Google ScholarCross Ref
- Kasenberg, D. and Scheutz, M. 2017. Interpretable apprenticeship learning with temporal logic specifications. Proceedings of the 56th IEEE Conference on Decision and Control (CDC 2017). IEEE Press. 4914--4921.Google Scholar
- Kasenberg, D. and Scheutz, M. 2018. Norm conflict resolution in stochastic domains. Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence (2018).Google Scholar
- Kim, J. et al. 2018. Not-So-CLEVR: learning same--different relations strains feed-forward neural networks. Interface Focus. 8, 4 (2018).Google Scholar
- Kollingbaum, M.J. et al. 2008. Managing conflict resolution in norm-regulated environments. Engineering Societies in the Agents World VIII. A. Artikis et al., eds. Springer Berlin Heidelberg. 55--71. Google ScholarDigital Library
- Li, J. et al. 2015. Reinforcement learning of normative monitoring intensities. Proceedings of the International Workshop on Coordination, Organisation, Institutions and Norms in Multi-Agent Systems (2015). Google ScholarDigital Library
- Mack, A. ed. 2018. Changing social norms. Social Research: An International Quarterly. 85, 1 (2018), 1--271.Google Scholar
- Mahmoud, M.A. et al. 2014. A review of norms and normative multiagent systems. The Scientific World Journal. 2014, (2014), 1--Google Scholar
- Malle, B.F. 2018. From binary deontics to deontic continua: The nature of human (and robot) norm systems.Google Scholar
- Malle, B.F. et al. 2017. Networks of social and moral norms in human and robot agents. A World with Robots: International Conference on Robot Ethics: ICRE 2015. M.I. Aldinhas Ferreira et al., eds. Springer International Publishing. 3--17.Google Scholar
- Milgram, S. et al. 1969. Note on the drawing power of crowds of different size. Journal of Personality and Social Psychology. 13, 2 (Oct. 1969), 79--82.Google ScholarCross Ref
- Nickles, M. 2007. Towards a logic of graded normativity and norm adherence. Normative Multi-agent Systems: Dagstuhl Seminar Proceedings (Dagstuhl, Germany, 2007).Google Scholar
- Nyga, D. and Beetz, M. 2012. Everything robots always wanted to know about housework (but were afraid to ask). 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems. IEEE Press. 243--250.Google Scholar
- Parsons, T. 1951. The social system. Free Press.Google Scholar
- Pereira, L.M. and Saptawijaya, A. 2007. Modelling morality with prospective logic. Progress in Artificial Intelligence. J. Neves et al., eds. Springer Berlin Heidelberg. 99--111. Google ScholarDigital Library
- Prentice, D.A. and Miller, D.T. 1996. Pluralistic ignorance and the perpetuation of social norms by unwitting actors. Advances in Experimental Social Psychology. M.P. Zanna, ed. Academic Press. 161--209.Google Scholar
- Rakoczy, H. et al. 2008. The sources of normativity: Young children's awareness of the normative structure of games. Developmental Psychology. 44, 3 (May 2008), 875--88Google Scholar
- Russell, S. et al. 2016. Research priorities for robust and beneficial artificial intelligence. arXiv preprint arXiv:1602.03506. (2016).Google Scholar
- Savarimuthu, B.T.R. et al. 2013. Identifying prohibition norms in agent societies. Artificial Intelligence and Law. 21, 1 (2013), 1--46. Google ScholarDigital Library
- Schelling, T.C. 1960. The strategy of conflict. Harvard University Press.Google Scholar
- Scheutz, M. et al. 2017. Spoken instruction-based one-shot object and action learning in a cognitive robotic architecture. Proceedings of the 16th Conference on Autonomous Agents and MultiAgent Systems. International Foundation for Autonomous Agents and Multiagent Systems. 1378--1386. Google ScholarDigital Library
- Serramia, M. et al. 2018. Moral values in norm decision making. Proceedings of the 17th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2018) (Richland, SC, 2018), 1294--1302. Google ScholarDigital Library
- Shams, Z. et al. 2017. Practical reasoning with norms for autonomous software agents. Engineering Applications of Artificial Intelligence. 65, (Oct. 2017), 388--39Google Scholar
- Steyvers, M. and Tenenbaum, J.B. 2005. The large-scale structure of semantic networks: statistical analyses and a model of semantic growth. Cognitive Science. 29, 1 (Jan. 2005), 41--7Google ScholarCross Ref
- Telesford, Q.K. et al. 2011. The ubiquity of small-world networks. Brain Connectivity. 1, 5 (Dec. 2011), 367--37Google ScholarCross Ref
- Ullman, S. 1984. Visual routines. Cognition. 18, 1--3 (Dec. 1984), 97--159.Google ScholarCross Ref
- Ullmann-Margalit, E. 1977. The emergence of norms. Clarendon Press.Google Scholar
- Wilson, D.S. 2002. Darwin's cathedral: Evolution, religion, and the nature of society. University of Chicago Press.Google Scholar
- Wright, J.C. and Bartsch, K. 2008. Portraits of early moral sensibility in two children's everyday conversations. Merrill-Palmer Quarterly. 54, 1 (Mar. 2008), 56--85.Google ScholarCross Ref
- Yuan, L. et al. 2016. Are categorical spatial relations encoded by shifting visual attention between objects? PLOS ONE. 11, 10 (2016), 1--22.Google ScholarCross Ref
Index Terms
- Requirements for an Artificial Agent with Norm Competence
Recommendations
The seven troubles with norm-compliant robots
AbstractMany researchers from robotics, machine ethics, and adjacent fields seem to assume that norms represent good behavior that social robots should learn to benefit their users and society. We would like to complicate this view and present seven key ...
Agent-directed Runtime Norm Synthesis
AAMAS '23: Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent SystemsTo maintain fitness-for-purpose, the set of norms governing a MAS will typically need to evolve to reflect the changing needs of both participants and the environment. We put forward a conceptual framework to address this problem comprising dynamic ...
Norm Emergence in Multiagent Systems: A Viewpoint Paper
AAMAS '20: Proceedings of the 19th International Conference on Autonomous Agents and MultiAgent SystemsThe literature on norm emergence and normative MAS considers norms from two perspectives, namely: prescriptive norms using deontic concepts, and emergent norms that capture preference behaviour. We find that both perspectives lend themselves naturally ...
Comments