Multi-Task Sensor Resource Balancing Using Lagrangian Relaxation and Policy Rollout

M.I. Schöpe, Hans Driessen, Alexander Yarovoy

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

15 Downloads (Pure)

Abstract

The sensor resource management problem in a multi-object tracking scenario is considered. In order to solve it, a dynamic budget balancing algorithm is proposed which models the different sensor tasks as partially observable Markov decision processes. Those are being solved by applying a combination of Lagrangian relaxation and policy rollout. The algorithm converges to a solution which is close to the optimal steady-state solution. This is shown through simulations of a two-dimensional tracking scenario. Moreover, it is demonstrated how the algorithm allocates the sensor time budgets dynamically to a changing environment and takes predictions of the future situation into account.
Original languageEnglish
Title of host publication2020 23rd International Conference on Information Fusion (FUSION)
Subtitle of host publicationProceedings
PublisherIEEE
Pages1-8
Number of pages8
ISBN (Electronic)978-0-578-64709-8
DOIs
Publication statusPublished - 2020
Event23rd International Conference on Information Fusion (FUSION 2020) - Virtual, South Africa
Duration: 6 Jul 20209 Jul 2020
https://www.fusion2020.org/

Conference

Conference23rd International Conference on Information Fusion (FUSION 2020)
Abbreviated titleFUSION
CountrySouth Africa
CityVirtual
Period6/07/209/07/20
Internet address

Keywords

  • Lagrangian Relaxation
  • Partially Observable Markov Decision Process
  • Policy Rollout
  • Sensor Resource Management

Fingerprint Dive into the research topics of 'Multi-Task Sensor Resource Balancing Using Lagrangian Relaxation and Policy Rollout'. Together they form a unique fingerprint.

Cite this