Knowledge Representation for Culturally Competent Personal Robots: Requirements, Design Principles, Implementation, and Assessment

Abstract

Culture, intended as the set of beliefs, values, ideas, language, norms and customs which compose a person’s life, is an essential element to know by any robot for personal assistance. Culture, intended as that person’s background, can be an invaluable source of information to drive and speed up the process of discovering and adapting to the person’s habits, preferences and needs. This article discusses the requirements posed by cultural competence on the knowledge management system of a robot. We propose a framework for cultural knowledge representation that relies on (i) a three-layer ontology for storing concepts of relevance, culture-specific information and statistics, person-specific information and preferences; (ii) an algorithm for the acquisition of person-specific knowledge, which uses culture-specific knowledge to drive the search; (iii) a Bayesian Network for speeding up the adaptation to the person by propagating the effects of acquiring one specific information onto interconnected concepts. We have conducted a preliminary evaluation of the framework involving 159 Italian and German volunteers and considering 122 among habits, attitudes and social norms.

This is a preview of subscription content, log in to check access.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18
Fig. 19
Fig. 20
Fig. 21

Notes

  1. 1.

    This rationale is at the core of the H2020 project CARESSES (http://caressesrobot.org/), which aims at the development of culturally competent robots for elderly care. One of the key research areas of CARESSES is denoted as Transcultural Robotic Nursing [5], which is, ideally, the bridge between culturally competent human caregivers and culturally competent robot caregivers.

  2. 2.

    The current corpus of Guidelines for Culturally Competent Robot Behaviours, together with a set of scenarios grounding them in daily life situations, is freely available at: http://caressesrobot.org/en/2018/03/08/caresses-scenarios-and-guidelines-available/.

  3. 3.

    For example using user-friendly tools such as Protégé: https://protege.stanford.edu/.

  4. 4.

    http://www.w3.org/TR/owl-time/

  5. 5.

    http://www.bbc.co.uk/ontologies.

  6. 6.

    We prefer the term “instance” to the OWL-2 term “individual” because the latter is commonly used as a synonym of “person”, which might lead to confusion in this article.

  7. 7.

    We introduce the term likeliness for two reasons: (i) to highlight the fact that it is not necessarily the result of statistical analyses, but it can also be provided by experts on the basis of qualitative assessment; (ii) to provide a unique name for the a posteriori probability (see Definition 1), the conditional probability (see Definition 2) and the evidence (see Definition 3), which our algorithms for the Assessment & Adaptation (see Sect. 3.4) use concurrently.

  8. 8.

    https://en.wikipedia.org/wiki/Breakfast#Italy.

  9. 9.

    As usual, only object and data properties that are relevant for the discussion are shown.

  10. 10.

    \(T_{\mathtt {C}}\) is built from \(A_{\mathtt {C}}\) using OWL-2 APIs. In principle, building \(T_{\mathtt {C}}\) as a separate structure is not required, since the tree–like structure of \(A_{\mathtt {C}}\) can be directly explored using OWL-2 APIs. From this perspective, Algorithm 1 shall be interpreted as providing information about how \(A_{\mathtt {C}}\) is explored by Algorithms 2 and 3.

  11. 11.

    In the current implementation, we use the API to create belief networks provided by Netica. See: https://www.norsys.com/netica.html.

  12. 12.

    On the opposite, two nodes with a common predecessor are conditionally independent given that their predecessor is known, i.e., \(\mathsf {P(HAM\_EATING... | PENTECOST..., GEN)}= \mathsf {P(HAM\_EATING... | GEN)}\).

  13. 13.

    German version: https://tinyurl.com/ybvr4xeo;

    Italian version: https://tinyurl.com/y8b3zuub.

References

  1. 1.

    Agarwal P, Verma R, Mallik A (2016) Ontology based disease diagnosis system with probabilistic inference. In: 1st India international conference on information processing (IICIP), IEEE, pp 1–5

  2. 2.

    Andrist S, Ziadee M, Boukaram H, Mutlu B, Sakr M (2015) Effects of culture on the credibility of robot speech: A comparison between english and arabic. In: HRI, pp 157–164

  3. 3.

    Baader F, Calvanese D, McGuinness D, Nardi D, Patel-Schneider P (2003) The description logic handbook: theory, implementations and applications. Cambridge University Press, New York

    Google Scholar 

  4. 4.

    Bateman CM (2007) Game writing: Narrative skills for videogames. Charles River Media Independence

  5. 5.

    Bruno B, Chong NY, Kamide H, Kanoria S, Lee J, Lim Y, Pandey AK, Papadopoulos C, Papadopoulos I, Pecora F, Saffiotti A, Sgorbissa A (2017a) Paving the way for culturally competent robots: a position paper. In: RO-MAN 2017, pp 430–435

  6. 6.

    Bruno B, Mastrogiovanni F, Pecora F, Sgorbissa A, Saffiotti A (2017b) A framework for culture-aware robots based on fuzzy logic. In: IEEE international conference on fuzzy systems (FUZZ-IEEE), IEEE, pp 1–6

  7. 7.

    Carvalho RN, Laskey KB, Costa PC (2017) Pr-owl-a language for defining probabilistic ontologies. Int J Approx Reason 91:56–79

    MathSciNet  Article  MATH  Google Scholar 

  8. 8.

    Conti D, Di Nuovo S, Buono S, Di Nuovo A (2017) Robots in education and care of children with developmental disabilities: a study on acceptance by experienced and future professionals. Int J Soc Robot 9(1):51–62

    Article  Google Scholar 

  9. 9.

    Dautenhahn K, Woods S, Kaouri C, Walters ML, Koay KL, Werry I (2005) What is a robot companion-friend, assistant or butler? In: IEEE/RSJ international conference on intelligent robots and systems (IROS 2005) IEEE, pp 1192–1197

  10. 10.

    Ding Z, Peng Y (2004) A probabilistic extension to ontology language owl. In: Proceedings of the 37th annual Hawaii international conference on system sciences, IEEE, p 10

  11. 11.

    Eresha G, Häring M, Endrass B, André E, Obaid M (2013) Investigating the influence of culture on proxemic behaviors for humanoid robots. In: RO-MAN 2013, pp 430–435

  12. 12.

    Evers V, Maldonado H, Brodecki T, Hinds P (2008) Relational vs. group self-construal: untangling the role of national culture in HRI. In: HRI 2008, pp 255–262

  13. 13.

    Flandorfer P (2012) Population ageing and socially assistive robots for elderly persons: the importance of sociodemographic factors for user acceptance. Int J Popul Res 2012:13. https://doi.org/10.1155/2012/829835

    Google Scholar 

  14. 14.

    Guarino N, et al (1998) Formal ontology and information systems. In: Proceedings of FOIS, pp 81–97

  15. 15.

    Hall ET (1976) Beyond culture. Anchor, Norwell

    Google Scholar 

  16. 16.

    Hofstede G, Hofstede GJ, Minkov M (1991) Cultures and organizations: software of the mind, vol 2. McGraw-Hill, New York city

    Google Scholar 

  17. 17.

    IEEE Standards Association (2018) 1872.1-robot task representation. http://standards.ieee.org/develop/project/1872.1.html. Accessed 18 Jan 2019

  18. 18.

    Joosse MP, Poppe RW, Lohse M, Evers V (2014) Cultural differences in how an engagement-seeking robot should approach a group of people. In: CABS 2014, pp 121–130

  19. 19.

    Köckemann U (2016) Constraint-based methods for human-aware planning. Ph.D. thesis, Örebro university

  20. 20.

    Lugrin B, Frommel J, André E (2015) Modeling and evaluating a bayesian network of culture-dependent behaviors. In: Culture computing 2015, pp 33–40

  21. 21.

    Marios Vasiliou R, Christiana Kouta R, Vasilios Raftopoulos R (2013) The use of the cultural competence assessment tool (ccatool) in community nurses: the pilot study and test-retest reliability. Int J Caring Sci 6(1):44

    Google Scholar 

  22. 22.

    Menicatti R, Bruno B, Sgorbissa A (2017) Modelling the influence of cultural information on vision-based human home activity recognition. In: 2017 14th international conference on ubiquitous robots and ambient intelligence (URAI), pp 32–38

  23. 23.

    Niles I, Pease A (2001) Towards a standard upper ontology. In: Proceedings of the international conference on formal ontology in information systems, ACM, pp 2–9

  24. 24.

    Nomura T, Suzuki T, Kanda T, Han J, Shin N, Burke J, Kato K (2008) What people assume about humanoid and animal-type robots: cross-cultural analysis between japan, korea, and the united states. Int J Humanoid Robot 5(01):25–46

    Article  Google Scholar 

  25. 25.

    Papadopoulos I (2006a) The papadopoulos, tilki and taylor model of developing cultural competence. Transcultural health and social care: development of culturally competent practitioners, pp 7–24

  26. 26.

    Papadopoulos I (2006b) Transcultural health and social care: development of culturally competent practitioners. Elsevier, Amsterdam

    Google Scholar 

  27. 27.

    Patompak P, Jeong S, Nilkhamhang I, Chong NY (2017) Learning social relations for culture aware interaction. In: 2017 14th international conference on ubiquitous robots and ambient intelligence (URAI), pp 26–31

  28. 28.

    Rehm M, Bee N, Endrass B, Wissner M, André E (2007) Too close for comfort?: adapting to the user’s cultural background. In: HCM 2007, pp 85–94

  29. 29.

    Robinson H, MacDonald B, Broadbent E (2014) The role of healthcare robots for older people at home: a review. Int J Socl Robot 6(4):575–591

    Article  Google Scholar 

  30. 30.

    Ryan JO, Mateas M, Wardrip-Fruin N (2016) A lightweight videogame dialogue manager. In: DiGRA/FDG

  31. 31.

    Torta E, Cuijpers RH, Juola JF, van der Pol D (2011) Design of robust robotic proxemic behaviour. In: ICSR 2011, pp 21–30

  32. 32.

    Trovato G, Zecca M, Do M, Terlemez Ö, Kuramochi M, Waibel A, Asfour T, Takanishi A (2015) A novel greeting selection system for a culture-adaptive humanoid robot. Int J Adv Robot Syst 12:34

    Article  Google Scholar 

  33. 33.

    W3C Owl Working Group and others (2009) OWL 2 web ontology language document overview

  34. 34.

    Wang L, Rau PLP, Evers V, Robinson BK, Hinds P (2010) When in rome: the role of culture & context in adherence to robot recommendations. In: HRI 2010, pp 359–366

Download references

Acknowledgements

We are grateful to reviewer 3 whose insightful and constructive comments have greatly improved the quality of the article, guided us in our research, and inspired us in our service as reviewers.

Funding

This work has been supported by the European Commission Horizon2020 Research and Innovation Programme under Grant Agreement No. 737858 (CARESSES).

Author information

Affiliations

Authors

Corresponding author

Correspondence to Barbara Bruno.

Ethics declarations

Conflict of Interest

The authors declare that they have no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Bruno, B., Recchiuto, C.T., Papadopoulos, I. et al. Knowledge Representation for Culturally Competent Personal Robots: Requirements, Design Principles, Implementation, and Assessment. Int J of Soc Robotics 11, 515–538 (2019). https://doi.org/10.1007/s12369-019-00519-w

Download citation

Keywords

  • Culture-aware robotics
  • Companion robot
  • Knowledge representation