TY - GEN
T1 - Approaches to time-dependent gas distribution modelling
AU - Asadi, Sahar
AU - Lilienthal, Achim
N1 - Publisher Copyright:
© 2015 IEEE.
PY - 2015/11/10
Y1 - 2015/11/10
N2 - Mobile robot olfaction solutions for gas distribution modelling offer a number of advantages, among them au- tonomous monitoring in different environments, mobility to select sampling locations, and ability to cooperate with other systems. However, most data-driven, statistical gas distribution modelling approaches assume that the gas distribution is generated by a time-invariant random process. Such time-invariant approaches cannot model well developing plumes or fundamental changes in the gas distribution. In this paper, we discuss approaches that explicitly consider the measurement time, either by sub-sampling according to a given time-scale or by introducing a recency weight that relates measurement and prediction time. We evaluate the performance of these time-dependent approaches in simulation and in real-world experiments using mobile robots. The results demonstrate that in dynamic scenarios improved gas distribution models can be obtained with time-dependent approaches.
AB - Mobile robot olfaction solutions for gas distribution modelling offer a number of advantages, among them au- tonomous monitoring in different environments, mobility to select sampling locations, and ability to cooperate with other systems. However, most data-driven, statistical gas distribution modelling approaches assume that the gas distribution is generated by a time-invariant random process. Such time-invariant approaches cannot model well developing plumes or fundamental changes in the gas distribution. In this paper, we discuss approaches that explicitly consider the measurement time, either by sub-sampling according to a given time-scale or by introducing a recency weight that relates measurement and prediction time. We evaluate the performance of these time-dependent approaches in simulation and in real-world experiments using mobile robots. The results demonstrate that in dynamic scenarios improved gas distribution models can be obtained with time-dependent approaches.
KW - Dispersion
KW - Kernel
KW - Pollution measurement
KW - Predictive models
KW - Robot sensing systems
KW - Time measurement
KW - Weight measurement
UR - http://www.scopus.com/inward/record.url?scp=84962271801&partnerID=8YFLogxK
U2 - 10.1109/ECMR.2015.7324215
DO - 10.1109/ECMR.2015.7324215
M3 - Conference contribution
AN - SCOPUS:84962271801
T3 - 2015 European Conference on Mobile Robots, ECMR 2015 - Proceedings
BT - 2015 European Conference on Mobile Robots, ECMR 2015 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - European Conference on Mobile Robots, ECMR 2015
Y2 - 2 September 2015 through 4 September 2015
ER -