Situation-Specific Intention Recognition for Human-Robot Cooperation

Recognizing human intentions is part of the decision process in many technical devices. In order to achieve natural interaction, the required estimation quality and the used computation time need to be balanced. This becomes challenging, if the number of sensors is high and measurement systems are complex. In this paper, a model predictive approach to this problem based on online switching of small, situation-specific Dynamic Bayesian Networks is proposed. The contributions are an efficient modeling and inference of situations and a greedy model predictive switching algorithm maximizing the mutual information of predicted situations. The achievable accuracy and computational savings are demonstrated for a household scenario by using an extended range telepresence system.

[1]  R. Goldman,et al.  Partial Observability and Probabilistic Plan/Goal Recognition , 2005 .

[2]  Henry A. Kautz.  A formal theory of plan recognition , 1987 .

[3]  Henry A. Kautz,et al.  Reasoning about plans , 1991, Morgan Kaufmann series in representation and reasoning.

[4]  Henry Kautz,et al.  Chapter 2 – A Formal Theory of Plan Recognition and its Implementation , 1991 .

[5]  Nir Friedman,et al.  Probabilistic Graphical Models - Principles and Techniques , 2009 .

[6]  O. C. Schrempf,et al.  Evaluation of hybrid Bayesian networks using analytical density representations , 2005 .

[7]  Uwe D. Hanebeck,et al.  Intention recognition for partial-order plans using Dynamic Bayesian Networks , 2009, 2009 12th International Conference on Information Fusion.

[8]  Hung Hai Bui,et al.  A General Model for Online Probabilistic Plan Recognition , 2003, IJCAI.

[9]  Avi Pfeffer,et al.  Object-Oriented Bayesian Networks , 1997, UAI.

[10]  Jeff A. Bilmes,et al.  Dynamic Bayesian Multinets , 2000, UAI.

[11]  Uwe D. Hanebeck,et al.  Motion compression applied to guidance of a mobile teleoperator , 2005, 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[12]  Kathryn B. Laskey,et al.  Network Fragments: Representing Knowledge for Constructing Probabilistic Models , 1997, UAI.

[13]  Karim A. Tahboub,et al.  Journal of Intelligent and Robotic Systems (2005) DOI: 10.1007/s10846-005-9018-0 Intelligent Human–Machine Interaction Based on Dynamic Bayesian Networks Probabilistic Intention Recognition , 2004 .

[14]  Heinz Wörn,et al.  A novel approach to proactive human-robot cooperation , 2005, ROMAN 2005. IEEE International Workshop on Robot and Human Interactive Communication, 2005..

[15]  Stuart J. Russell,et al.  Dynamic bayesian networks: representation, inference and learning , 2002 .

[16]  Qiang Ji,et al.  Efficient Sensor Selection for Active Information Fusion , 2010, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[17]  Jason L. Williams,et al.  Information theoretic sensor management , 2007 .

[18]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

[19]  Michael P. Wellman,et al.  Probabilistic State-Dependent Grammars for Plan Recognition , 2000, UAI.

[20]  N. S. Sridharan,et al.  The Plan Recognition Problem: An Intersection of Psychology and Artificial Intelligence , 1978, Artif. Intell..