Identifying Physical Team Behaviors from Spatial Relationships

Gita Sukthankar and Katia Sycara
Conference Paper, Proceedings of 2005 Conference on Behavior Representation in Modeling and Simulation (BRIMS), May, 2005

View Publication

Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.


An important part of classifying MOUT (Military Operations in Urban Terrain) team behaviors is recognizing subtle spatial relationships between physical entities: opponents waiting in ambush, teammates organizing around a rendez-vous point, and potentially dangerous cul-de-sacs. In this paper, we present a RANSAC (Random Sampling and Consensus) based algorithm for identifying spatial relationships of MOUT entities based on a model library; possible configurations are scored based on a similarity function that incorporates information on entity type matching, transform validity, spatial proximity, and preservation of visibility constraints. Configurations can include both static entities (doors, buildings, hazards) and dynamic ones (opponents, teammates, and civilians). The output from our algorithm is used as a state feature for our behavior recognition system to recognize team behaviors from sequences of state transitions. We demonstrate that our algorithm is robust to spatial variations, generalizes across scenarios, and can be executed in real-time.

author = {Gita Sukthankar and Katia Sycara},
title = {Identifying Physical Team Behaviors from Spatial Relationships},
booktitle = {Proceedings of 2005 Conference on Behavior Representation in Modeling and Simulation (BRIMS)},
year = {2005},
month = {May},
keywords = {spatial reasoning, plan recognition, MOUT},
} 2017-09-13T10:43:27-04:00