Message Passing-based Cooperative Localization with embedded Particle Flow

Cooperative localization is an enabling technology for the IoT that will introduce innovative services for modern convenience and public safety. Particle-based belief propagation (BP) is a state-of-the-art method for cooperative localization. However, in large and dense cooperative localization networks, particle-based BP suffers from particle degeneracy. In this paper, we propose a new method that combines particle-based BP and particle flow (PF) and can avoid this detrimental effect. To perform operations on the graph effectively, particles are moved towards regions of high likelihood based on the solution of a partial differential equation. We show that the proposed PF-BP algorithm can significantly outperform conventional particle-based BP in accuracy and runtime.