TY - GEN
T1 - Modeling human motion patterns for multi-robot planning
AU - Karnad, Nikhil
AU - Isler, Volkan I
PY - 2012/1/1
Y1 - 2012/1/1
N2 - Modeling human motion in complex environments without losing long-range dependencies is difficult due to the large number of combinatorially distinct paths humans may follow. Existing representations avoid this difficulty by limiting the prediction of human motion to a local level. As a result, robot motion planning algorithms that use these representations are reactive in nature, and fail to exploit higher-order dependencies. We present a novel motion model capable of representing the global path behavior of people. Our model compactly encodes higher-order temporal dependencies inherent in human mobility traces on an abstract representation of the environment that lends itself to combinatorial planning. We incorporate uncertainties into the planning process using POMDPs and present a general predictive multi-robot planning algorithm applicable to pedestrian datasets commonly found in the literature. We evaluate our planner by simulating multiple instances of a variant of the visibility-based target-tracking problem inspired by our previous work. We report encouraging results that demonstrate our multi-robot plans exhibit desirable combinatorial structure, e.g. robot re-use.
AB - Modeling human motion in complex environments without losing long-range dependencies is difficult due to the large number of combinatorially distinct paths humans may follow. Existing representations avoid this difficulty by limiting the prediction of human motion to a local level. As a result, robot motion planning algorithms that use these representations are reactive in nature, and fail to exploit higher-order dependencies. We present a novel motion model capable of representing the global path behavior of people. Our model compactly encodes higher-order temporal dependencies inherent in human mobility traces on an abstract representation of the environment that lends itself to combinatorial planning. We incorporate uncertainties into the planning process using POMDPs and present a general predictive multi-robot planning algorithm applicable to pedestrian datasets commonly found in the literature. We evaluate our planner by simulating multiple instances of a variant of the visibility-based target-tracking problem inspired by our previous work. We report encouraging results that demonstrate our multi-robot plans exhibit desirable combinatorial structure, e.g. robot re-use.
UR - http://www.scopus.com/inward/record.url?scp=84864459644&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84864459644&partnerID=8YFLogxK
U2 - 10.1109/ICRA.2012.6225209
DO - 10.1109/ICRA.2012.6225209
M3 - Conference contribution
AN - SCOPUS:84864459644
SN - 9781467314039
T3 - Proceedings - IEEE International Conference on Robotics and Automation
SP - 3161
EP - 3166
BT - 2012 IEEE International Conference on Robotics and Automation, ICRA 2012
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2012 IEEE International Conference on Robotics and Automation, ICRA 2012
Y2 - 14 May 2012 through 18 May 2012
ER -