Skip to main content
SpringerLink
Log in

Modeling Aspects of Theory of Mind with Markov Random Fields

  • Original Paper
  • Published:
International Journal of Social Robotics Aims and scope Submit manuscript

Abstract

We propose Markov random fields (MRFs) as a probabilistic mathematical model for incorporating the internal states of other agents, both human and robotic, into robot decision making. By using estimates of Theory of Mind (ToM), the mental states of other agents can be incorporated into decision making through statistical inference, allowing robots to balance their own goals and internal objectives with those of other collaborating agents. The MRF model is well-suited to domains in which the joint probability over latent (action) and observed (perceived) variables can be factored into pairwise interactions between these variables. Specifically, these interactions occur through functions that evaluate “local evidence” between an observed and latent variable and “compatibility” between a pair of latent variables. We will describe how experimental findings from the ToM literature can be explained using MRF models, and then show how this framework can be applied to a social robotics task. We will also describe how to use belief propagation on a multi-robot MRF as a novel approach to multi-robot coordination, with parallels to human collaboration strategies.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Balch T, Arkin RC (1994) Communication in reactive multiagent robotic systems. Auton Robots 1(1):27–52

    Article  Google Scholar 

  2. Baron-Cohen S (1995) Mindblindness. MIT Press, Cambridge

    Google Scholar 

  3. Berlin M, Gray J, Thomaz AL, Breazeal C (2006) Perspective taking: An organizing principle for learning in human-robot interaction. In: AAAI

  4. Breazeal C, Brooks A, Gray J, Hoffman G, Kidd C, Lee H, Lieberman J, Lockerd A, Chilongo D (2004) Tutelage and collaboration for humanoid robots. Int J Humanoid Robot 1(2):315–348

    Article  Google Scholar 

  5. Brooks R, Meltzoff AN (2002) The importance of eyes: How infants interpret adult looking behavior. Dev Psychol 38(6):958–966

    Article  Google Scholar 

  6. Butterfield J, Gerkey BP, Jenkins OC (2008) Multi-robot Markov random fields. In: Auton agents and multi agent syst (AAMAS 2008), Estoril, Portugal

  7. Butterworth G (1991) The ontogeny and phylogeny of joint visual attention. In: Whiten A (ed) Natural theories of mind: Evolution, development and simulation of everyday mindreading. Basil Blackwell, Cambridge, pp 223–232

    Google Scholar 

  8. Carruthers P, Smith PK (1996) Theories of theories of mind. Cambridge University Press, Cambridge

    Google Scholar 

  9. Cassimatis NL (2003) A framework for answering queries using multiple representation and inference techniques. In: Proc of the 10th int workshop on knowledge representation meets databases

  10. Charman T (2000) Theory of mind and early diagnosis of autism. In: Baron-Cohen S, Tager-Flusberg H, Cohen DJ (eds) Understanding other minds: perspectives from developmental cognitive neuroscience. Oxford University Press, London, pp 422–441

    Google Scholar 

  11. Clement F, Koenig M, Harris P (2004) The ontogenesis of trust. Mind Lang 19(4):360–379

    Google Scholar 

  12. Corriveau KH, Meints K, Harris PL (in press) Early tracking of informant accuracy inaccuracy. Br J Dev Psychol

  13. Crick C, Pfeffer A (2003) Loopy belief propagation as a basis for communication in sensor networks. In: Uncertainty in artificial intell (UAI), Acapulco, Mexico

  14. Dias M, Stentz A (2002) Opportunistic optimization for market-based multirobot control. In: Proc of the 2002 int conf on intell robots and syst, vol 3, pp 2714–2720

  15. Gerkey BP, Matarić MJ (2004) A formal analysis and taxonomy of task allocation in multi-robot systems. Int J Robot Res 23(9):939–954

    Article  Google Scholar 

  16. Gerkey BP, Vaughan RT, Howard A (2003) The player/stage project: tools for multi-robot and distributed sensor systems. In: Proc of the intl conf on advanced robotics (ICAR), Coimbra, Portugal, pp 317–323

  17. Goodman ND, Baker CL, Bonawitz EB, Mansinghka VK, Gopnik A, Wellman H, Schulz LE, Tenenbaum JB (2006) Intuitive theories of mind: a rational approach to false belief. In: Proc of the 28th annu conf of the cogn sci soc, Vancouver, Canada

  18. Gopnik A, Meltzoff AN (1997) Words, thoughts, and theories. MIT Press, Cambridge

    Google Scholar 

  19. Gopnik A, Glymour C, Sobel DM, Schulzand LE, Kushnir T, Danks D (2004) A theory of causal learning in children: causal maps and Bayes nets. Psychol Rev 111:3–32

    Article  Google Scholar 

  20. Harris PL (2007) Trust. Dev Sci 10:135–138

    Article  Google Scholar 

  21. Harris PL, Koenig MA (2006) Trust in testimony: How children learn about science and religion. Child Dev 77:505–524

    Article  Google Scholar 

  22. Hoffman G, Breazeal C (2007) Cost-based anticipatory action selection for human-robot fluency. IEEE Trans Robot (TROB) 23(5):952–961

    Article  Google Scholar 

  23. Ihler AT, Fisher III JW, Moses RL, Willsky AS (2005) Nonparametric belief propagation for self-calibration in sensor networks. IEEE J Sel Areas Commun 23(4):809–819

    Article  Google Scholar 

  24. Johnson S, Slaughter V, Carey S (1998) Whose gaze would infants follow? the elicitation of gaze following in 12-month-olds. Dev Sci 1:233–238

    Article  Google Scholar 

  25. Jung B, Sukhatme GS (2002) Tracking targets using multiple robots: The effect of environment occlusion. Auton Robots 13(3):191–205

    Article  MATH  Google Scholar 

  26. Koenig M, Harris PL (2005) Preschoolers mistrust ignorant and inaccurate speakers. Child Dev 76:1261–1277

    Article  Google Scholar 

  27. Koenig MA, Clement F, Harris PL (2004) Trust in testimony: Children’s use of true and false statements. Psychol Sci 15:694–698

    Article  Google Scholar 

  28. Leslie AM (1994) ToMM, ToBy, and agency: core architecture and domain specificity. In: Hirschfeld L, Gelman S (eds) Mapping the mind: domain specificity in cognition and culture. Cambridge University Press, Cambridge, pp 119–148

    Google Scholar 

  29. Marr D (1982) Vision. Holt, New York

    Google Scholar 

  30. Moore C, Corkum V (1998) Infant gaze following based on eye direction. Br J Dev Psychol 16(4):495–503

    Google Scholar 

  31. Parker L (1998) Alliance: an architecture for fault-tolerant multi-robot cooperation. IEEE Trans Robot Autom 14(2):220–240

    Article  Google Scholar 

  32. Paskin M, Guestrin C McFadden J (2005) A robust architecture for distributed inference in sensor networks. In: Information processing in sensor networks (IPSN’05)

  33. Plarre K, Kumar PR (2004) Extended message passing algorithm for inference in loopy Gaussian graphical models. Ad Hoc Netw 2:153–169

    Article  Google Scholar 

  34. Sabbagh M, Baldwin D (2001) Learning words from knowledgeable versus ignorant speakers: links between preschoolers’ theory of mind and semantic development. Child Dev 72(4):1054–1070

    Article  Google Scholar 

  35. Scaife M, Bruner JS (1975) The capacity for joint visual attention in the infant. Nature 253:265–266

    Article  Google Scholar 

  36. Scassellati B (2002) Theory of mind for a humanoid robot. Auton Robots 12(1):13–24. DOI http://dxdoiorg/101023/A:1013298507114

    Article  MATH  Google Scholar 

  37. Scassellati B, Doniec M, Sun G (2006) Active learning of joint attention. In: IEEE/RSJ int conf humanoid robotics (Humanoids 2006), Genoa, Italy

  38. Schwertfeger J, Jenkins O (2007) Multi-robot belief propagation for distributed robot allocation. In: Proc of the IEEE intl conf on dev and learning, London, England

  39. Sobel DM (in press) Integrating top-down and bottom-up approaches to causal learning. In: Johnson S (ed) A neo-constructivist approach to early development, Oxford, New York

  40. Tenenbaum JB, Griffiths TL (2003) Theory-based causal inference. In: Proc of the 14th annu conf the advances in neural information processing syst

  41. Thrun S, Burgard W, Fox D (2005) Probabilistic robotics. MIT Press, Cambridge, ISBN 0-262-20162-3

    MATH  Google Scholar 

  42. Trafton JG, Cassimatis NL, Bugajska MD, Brock DP, Mintz FE, Schultz AC (2005) Enabling effective human-robot interaction using perspective-taking in robots. IEEE Trans Syst Man Cybern Part A Syst Humans 35(4):460–470

    Article  Google Scholar 

  43. Wellman HM (1990) The child’s theory of mind. MIT Press, Cambridge

    Google Scholar 

  44. Wellman HM, Bartsch K (1988) Young children’s reasoning about beliefs. Cognition 30:239–277

    Article  Google Scholar 

  45. Yedidia JS, Freeman WT, Weiss Y (2001) Exploring artificial intelligence in the new millennium. Morgan Kaufmann, San Mateo, Chap Understanding belief propagation and its generalizations

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Computer Science, Brown University, Providence, RI, 02912-1910, USA

    Jesse Butterfield, Odest Chadwicke Jenkins & Jonas Schwertfeger

  2. Department of Cognitive and Linguistic Sciences, Brown University, Providence, RI, 02912, USA

    David M. Sobel

Authors
  1. Jesse Butterfield
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Odest Chadwicke Jenkins
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. David M. Sobel
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jonas Schwertfeger
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Jesse Butterfield.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Butterfield, J., Jenkins, O.C., Sobel, D.M. et al. Modeling Aspects of Theory of Mind with Markov Random Fields. Int J of Soc Robotics 1, 41–51 (2009). https://doi.org/10.1007/s12369-008-0003-1

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12369-008-0003-1

Keywords

Search

Navigation