Potential Game-Based Non-Myopic Sensor Network Planning for Multi-Target Tracking

Cited 5 time in webofscience Cited 0 time in scopus
  • Hit : 108
  • Download : 0
This paper presents a potential game-based method for the non-myopic planning of mobile sensor networks in the context of target tracking. The planning objective is to select the sequence of sensing points over more than one future time step to maximize information about the target states. This multistep lookahead scheme aims to overcome getting trapped at local information maximum when there are gaps in the sensing coverage due to constraints of the sensor platform mobility or limitations in sensing capabilities. However, long-term planning becomes computationally intractable as the length of planning horizon increases. This paper develops a game-theoretic approach to address the computational challenges. The main contributions of this paper are twofold: 1) to formulate a non-myopic planning problem for tracking multiple targets in a potential game, the size of which increases linearly as the number of planning steps and 2) to design a learning algorithm exploiting the joint strategy fictitious play and dynamic programming, which overcomes the gaps in sensing coverage. The numerical examples of multi-target tracking demonstrate that the proposed method gives a better estimation performance than myopic planning and is computationally tractable.
Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Issue Date
2018-12
Language
English
Article Type
Article
Citation

IEEE ACCESS, v.6, pp.79245 - 79257

ISSN
2169-3536
DOI
10.1109/ACCESS.2018.2885027
URI
http://hdl.handle.net/10203/250156
Appears in Collection
AE-Journal Papers(저널논문)
Files in This Item
There are no files associated with this item.
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 5 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0