Optimal federated fusion of multiple maneuvering targets based on multi-Bernoulli filters

• The proposed federated fusion algorithm combines multiple JMGM-MB filters in a hierarchical structure, achieving optimal fusion tracking of multiple maneuvering targets. • A master filter on the fusion node identifies the origins of state estimates and supplements missed detections, improving robustness and estimation accuracy. • The optimal fusion of IMM filters is rigorously derived using a covariance upper-bounding technique that eliminates correlations among filters. • Simulation results demonstrate that the proposed algorithm outperforms existing centralized and distributed fusion algorithms in linear and heterogeneous scenarios.