A Risk-Based Sensor Management using Random Finite Sets and POMDP

Marcos Eduardo Gomes Borges (1) , Dominique Maltese (2) , Philippe Vanheeghe (1) , Emmanuel Duflos (1)

1 CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189
2 SAFRAN Electronics & Defense

In this paper, we consider the problem of scheduling an agile sensor to perform an optimal control action in the case of the multi-target tracking scenario. Our purpose is to present a random finite set (RFS) approach to the multi- target sensor management problem formulated in the Partially Observed Markov Decision Process (POMDP) framework. The reward function associated with each sensor control (action) is computed via the Expected Risk Reduction between the multi- target predicted and updated densities. The proposed algorithm is implemented via the Probability Hypothesis Density filter (PHD). Numerical studies demonstrate the performance of this particular approach to a radar beam-pointing problem where targets need to be prioritized.

Mots clés: Multi-Object Tracking; Target tracking; Sensor Management; Expected Risk Reduction; Random Finite Sets; Partially Observed Markov Decision Process POMDP; Probability Hypothesis Density filter; PHD filter

Domaines: Traitement du signal et de l'image [eess.SP]; Statistiques [math.ST]; Probabilités [math.PR]; Optimisation et contrôle [math.OC]; Théorie de l'information et codage [math.IT]

Marcos Eduardo Gomes Borges, Dominique Maltese, Philippe Vanheeghe, Emmanuel Duflos. A Risk-Based Sensor Management using Random Finite Sets and POMDP. 20th International Conference on Information Fusion (FUSION), Jul 2017, Xi'an, China. pp.1-9, ⟨10.23919/ICIF.2017.8009843⟩. ⟨hal-02411689⟩