TY - GEN
T1 - Data-driven distributed state estimation and behavior modeling in sensor networks
AU - Yu, Rui
AU - Yuan, Zhenyuan
AU - Zhu, Minghui
AU - Zhou, Zihan
N1 - Funding Information:
1R. Yu and Z. Zhou are with College of Information Sciences and Technology, Pennsylvania State University, University Park, PA 16802, USA {rzy54, zuz22}@psu.edu 2Z. Yuan and M. Zhu are with School of Electrical Engineering and Computer Science, Pennsylvania State University, University Park, PA 16802, USA {zqy5086, muz16}@psu.edu This work is supported in part by a seed grant from Penn State Institute for Computational and Data Sciences. Z. Yuan and M. Zhu were supported by NSF grants ECCS-1710859 and CNS-1830390.
Publisher Copyright:
© 2020 IEEE.
PY - 2020/10/24
Y1 - 2020/10/24
N2 - Nowadays, the prevalence of sensor networks has enabled tracking of the states of dynamic objects for a wide spectrum of applications from autonomous driving to environmental monitoring and urban planning. However, tracking realworld objects often faces two key challenges: First, due to the limitation of individual sensors, state estimation needs to be solved in a collaborative and distributed manner. Second, the objects' movement behavior model is unknown, and needs to be learned using sensor observations. In this work, for the first time, we formally formulate the problem of simultaneous state estimation and behavior learning in a sensor network. We then propose a simple yet effective solution to this new problem by extending the Gaussian process-based Bayes filters (GPBayesFilters) to an online, distributed setting. The effectiveness of the proposed method is evaluated on tracking objects with unknown movement behaviors using both synthetic data and data collected from a multi-robot platform.
AB - Nowadays, the prevalence of sensor networks has enabled tracking of the states of dynamic objects for a wide spectrum of applications from autonomous driving to environmental monitoring and urban planning. However, tracking realworld objects often faces two key challenges: First, due to the limitation of individual sensors, state estimation needs to be solved in a collaborative and distributed manner. Second, the objects' movement behavior model is unknown, and needs to be learned using sensor observations. In this work, for the first time, we formally formulate the problem of simultaneous state estimation and behavior learning in a sensor network. We then propose a simple yet effective solution to this new problem by extending the Gaussian process-based Bayes filters (GPBayesFilters) to an online, distributed setting. The effectiveness of the proposed method is evaluated on tracking objects with unknown movement behaviors using both synthetic data and data collected from a multi-robot platform.
UR - http://www.scopus.com/inward/record.url?scp=85102411879&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85102411879&partnerID=8YFLogxK
U2 - 10.1109/IROS45743.2020.9340838
DO - 10.1109/IROS45743.2020.9340838
M3 - Conference contribution
AN - SCOPUS:85102411879
T3 - IEEE International Conference on Intelligent Robots and Systems
SP - 8192
EP - 8199
BT - 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2020
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2020
Y2 - 24 October 2020 through 24 January 2021
ER -