Multi-Sensor Control for Multi-Object Bayes Filters

Abstract

Sensor management in multi-object stochastic systems is a theoretically and computationally challenging problem. This paper presents a novel approach to the multi-target multi-sensor control problem within the partially observed Markov decision process (POMDP) framework. We model the multi-object state as a labeled multi-Bernoulli random finite set (RFS), and use the labeled multi-Bernoulli filter in conjunction with minimizing a task-driven control objective function: posterior expected error of cardinality and state (PEECS). A major contribution is a guided search for multi-dimensional optimization in the multi-sensor control command space, using coordinate descent method. In conjunction with the Generalized Covariance Intersection method for multi-sensor fusion, a fast multi-sensor algorithm is achieved. Numerical studies are presented in several scenarios where numerous controllable (mobile) sensors track multiple moving targets with different levels of observability. The results show that our method works significantly faster than the approach taken by a state of art method, with similar tracking errors.

arXiv comment21 pages, 8 figures

References in corpus (9)

• Labeled Random Finite Sets and the Bayes Multi-Target Tracking Filter
• Generalized Labeled Multi-Bernoulli Approximation of Multi-Object Densities
• Distributed Fusion with Multi-Bernoulli Filter based on Generalized Covariance Intersection
• Sensor management for multi-target tracking via Multi-Bernoulli filtering
• The Cauchy-Schwarz divergence for Poisson point processes
• Consensus Labeled Random Finite Set Filtering for Distributed Multi-Object Tracking
• The Marginalized $\delta$-GLMB Filter
• On the Finite Time Convergence of Cyclic Coordinate Descent Methods
• Sensor Control for Multi-Object Tracking Using Labeled Multi-Bernoulli Filter

Cited by in corpus (5)

• Online UAV Path Planning for Joint Detection and Tracking of Multiple Radio-tagged Objects
• Linear Complexity Gibbs Sampling for Generalized Labeled Multi-Bernoulli Filtering
• An Overview of Multi-Object Estimation via Labeled Random Finite Set
• Multi-Objective Multi-Agent Planning for Discovering and Tracking Multiple Mobile Objects
• The Role of Bounded Fields-of-View and Negative Information in Finite Set Statistics (FISST)