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.
Similar content being viewed by others
References
Balch T, Arkin RC (1994) Communication in reactive multiagent robotic systems. Auton Robots 1(1):27–52
Baron-Cohen S (1995) Mindblindness. MIT Press, Cambridge
Berlin M, Gray J, Thomaz AL, Breazeal C (2006) Perspective taking: An organizing principle for learning in human-robot interaction. In: AAAI
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
Brooks R, Meltzoff AN (2002) The importance of eyes: How infants interpret adult looking behavior. Dev Psychol 38(6):958–966
Butterfield J, Gerkey BP, Jenkins OC (2008) Multi-robot Markov random fields. In: Auton agents and multi agent syst (AAMAS 2008), Estoril, Portugal
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
Carruthers P, Smith PK (1996) Theories of theories of mind. Cambridge University Press, Cambridge
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
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
Clement F, Koenig M, Harris P (2004) The ontogenesis of trust. Mind Lang 19(4):360–379
Corriveau KH, Meints K, Harris PL (in press) Early tracking of informant accuracy inaccuracy. Br J Dev Psychol
Crick C, Pfeffer A (2003) Loopy belief propagation as a basis for communication in sensor networks. In: Uncertainty in artificial intell (UAI), Acapulco, Mexico
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
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
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
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
Gopnik A, Meltzoff AN (1997) Words, thoughts, and theories. MIT Press, Cambridge
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
Harris PL (2007) Trust. Dev Sci 10:135–138
Harris PL, Koenig MA (2006) Trust in testimony: How children learn about science and religion. Child Dev 77:505–524
Hoffman G, Breazeal C (2007) Cost-based anticipatory action selection for human-robot fluency. IEEE Trans Robot (TROB) 23(5):952–961
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
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
Jung B, Sukhatme GS (2002) Tracking targets using multiple robots: The effect of environment occlusion. Auton Robots 13(3):191–205
Koenig M, Harris PL (2005) Preschoolers mistrust ignorant and inaccurate speakers. Child Dev 76:1261–1277
Koenig MA, Clement F, Harris PL (2004) Trust in testimony: Children’s use of true and false statements. Psychol Sci 15:694–698
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
Marr D (1982) Vision. Holt, New York
Moore C, Corkum V (1998) Infant gaze following based on eye direction. Br J Dev Psychol 16(4):495–503
Parker L (1998) Alliance: an architecture for fault-tolerant multi-robot cooperation. IEEE Trans Robot Autom 14(2):220–240
Paskin M, Guestrin C McFadden J (2005) A robust architecture for distributed inference in sensor networks. In: Information processing in sensor networks (IPSN’05)
Plarre K, Kumar PR (2004) Extended message passing algorithm for inference in loopy Gaussian graphical models. Ad Hoc Netw 2:153–169
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
Scaife M, Bruner JS (1975) The capacity for joint visual attention in the infant. Nature 253:265–266
Scassellati B (2002) Theory of mind for a humanoid robot. Auton Robots 12(1):13–24. DOI http://dxdoiorg/101023/A:1013298507114
Scassellati B, Doniec M, Sun G (2006) Active learning of joint attention. In: IEEE/RSJ int conf humanoid robotics (Humanoids 2006), Genoa, Italy
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
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
Tenenbaum JB, Griffiths TL (2003) Theory-based causal inference. In: Proc of the 14th annu conf the advances in neural information processing syst
Thrun S, Burgard W, Fox D (2005) Probabilistic robotics. MIT Press, Cambridge, ISBN 0-262-20162-3
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
Wellman HM (1990) The child’s theory of mind. MIT Press, Cambridge
Wellman HM, Bartsch K (1988) Young children’s reasoning about beliefs. Cognition 30:239–277
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
Author information
Authors and Affiliations
Corresponding author
Rights 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
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12369-008-0003-1