Robust recognition of physical team behaviors using spatio-temporal models

ABSTRACT

This paper presents a framework for robustly recognizing physical team behaviors by exploiting spatio-temporal patterns. Agent team behaviors in athletic and military domains typically exhibit an observable structure characterized by the relative positions of teammates and external landmarks, such as a team of soldiers ambushing an opponent or a soccer player moving to receive a pass. We demonstrate how complex team relationships that are not easily expressed by region-based heuristics can be modeled from data and domain knowledge in a way that is robust to noise and spatial variation. To represent team behaviors in our domain of MOUT (Military Operations in Urban Terrain) planning, we employ two classes of spatial models: 1) team templates that encode static relationships between team members and external landmarks; and 2) spatially-invariant Hidden Markov Models (HMMs) to represent evolving agent team configurations over time. These two classes of models can be combined to improve recognition accuracy, particularly for behaviors that appear similar in static snapshots. We evaluate our modeling techniques on large urban maps and position traces of two-person human teams performing MOUT behaviors in a customized version of Unreal Tournament (a commercially available first-person shooter game).

REFERENCES

• 1: Dana Harry Ballard , Christopher M. Brown, Computer Vision, Prentice Hall Professional Technical Reference, 1982
• 2: B. Best and C. Lebiere. Spatial plans, communication, and teamwork in synthetic MOUT agents. In Proceedings of Behavior Representation in Modeling and Simulation Conference (BRIMS), 2003.
• 3: Richard O. Duda , Peter E. Hart , David G. Stork, Pattern Classification (2nd Edition), Wiley-Interscience, 2000
• 4: Martin A. Fischler , Robert C. Bolles, Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography, Communications of the ACM, v.24 n.6, p.381-395, June 1981 [doi>10.1145/358669.358692]
• 5: Richard Hartley , Andrew Zisserman, Multiple view geometry in computer vision, Cambridge University Press, New York, NY, 2000
• 6: Stephen S. Intille , Aaron F. Bobick, A framework for recognizing multi-agent action from visual evidence, Proceedings of the sixteenth national conference on Artificial intelligence and the eleventh Innovative applications of artificial intelligence conference innovative applications of artificial intelligence, p.518-525, July 18-22, 1999, Orlando, Florida, United States
• 7: M. Jug, J. Pers, B. Dezman, and S. Kovacic. Trajectory based assessment of coordinated human activity. In Proceedings of the International Conference on Computer Vision Systems (ICVS), 2003.
• 8: G. Kaminka and M. Tambe. Robust agent teams via socially attentive monitoring. Journal of Artificial Intelligence Research, 12: pp.105--147, 2000.
• 9: Gal A. Kaminka , Manuela M. Veloso , Steve Schaffer , Chris Sollitto , Rogelio Adobbati , Andrew N. Marshall , Andrew Scholer , Sheila Tejada, GameBots: a flexible test bed for multiagent team research, Communications of the ACM, v.45 n.1, January 2002 [doi>10.1145/502269.502293]
• 10: K. Murphy. The Bayes Net Toolbox for Matlab. Computing Science and Statistics, 33, 2001.
• 11: D. Pearson and J. Laird. Redux: Example-drive diagrammatic tools for rapid knowledge acquisition. In Proceedings of Behavior Representation in Modeling and Simulation Conference (BRIMS), 2004.
• 12: J. Phillips, M. McCloskey, P. McDermott, S. Wiggins, and D. Battaglia. Decision-centered MOUT training for small unit leaders. Technical Report 1776, U.S. Army Research Institute for Behavioral and Social Sciences, 2001.
• 13: L. Rabiner. A tutorial on Hidden Markov models and selected applications in speech recognition. Proceedings of the IEEE, 77, 1989.
• 14: P. Riley and M. Veloso. On behavior classification in adversarial environments. In L. Parker, G. Bekey, and J. Barhen, editors, Distributed Autonomous Robotic Systems 4. Springer-Verlag, 2000.
• 15: Patrick Riley , Manuela M. Veloso, Recognizing Probabilistic Opponent Movement Models, RoboCup 2001: Robot Soccer World Cup V, p.453-458, January 2002
• 16: S. Saria and S. Mahadevan. Probabilistic plan recognition in multiagent systems. In Proceedings of the International Conference on AI and Planning Systems (ICAPS), 2004.
• 17: G. Sukthankar. Thesis proposal: Activity recognition for physically-embodied agent teams. Technical Report CMU-RI-05-44, Robotics Institute, Carnegie Mellon, 2005.
• 18: M. Tambe. Tracking dynamic team activity. In Proceedings of the National Conference on Artificial Intelligence (AAAI), 1996.
• 19: Gang Xu , Zhengyou Zhang, Epipolar Geometry in Stereo, Motion, and Object Recognition: A Unified Approach, Kluwer Academic Publishers, Norwell, MA, 1996

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.5 PATTERN RECOGNITION

Additional Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
        I.2.11 Distributed Artificial Intelligence

General Terms:
Algorithms

Keywords:
HMMs, RANSAC, multi-agent plan recognition