Robust recognition of physical team behaviors using spatio-temporal models Export

@inproceedings{citeulike:3353139, 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).}, address = {New York, NY, USA}, author = {Sukthankar, Gita and Sycara, Katia}, booktitle = {AAMAS '06: Proceedings of the fifth international joint conference on Autonomous agents and multiagent systems}, citeulike-article-id = {3353139}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1160633.1160746}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/1160633.1160746}, doi = {10.1145/1160633.1160746}, isbn = {1-59593-303-4}, keywords = {behavioral-models, behaviors, spatio-temporal}, location = {Hakodate, Japan}, pages = {638--645}, posted-at = {2009-08-01 17:50:23}, priority = {2}, publisher = {ACM}, title = {Robust recognition of physical team behaviors using spatio-temporal models}, url = {http://dx.doi.org/10.1145/1160633.1160746}, year = {2006} }

TY - CONF ID - citeulike:3353139 L3 - citeulike-article-id:3353139 N2 - 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). CY - Hakodate, Japan SN - 1-59593-303-4 AD - New York, NY, USA EP - 645 TI - Robust recognition of physical team behaviors using spatio-temporal models PB - ACM T2 - AAMAS '06: Proceedings of the fifth international joint conference on Autonomous agents and multiagent systems SP - 638 KW - behavioral-models KW - behaviors KW - spatio-temporal AU - Sukthankar, Gita AU - Sycara, Katia PY - 2006/// UR - http://dx.doi.org/10.1145/1160633.1160746 ER -