Exponential Natural Particle Filter
This addresses computational inefficiencies in particle filtering for applications like robotics or tracking, though it appears incremental as it builds on existing particle filter methods.
The paper tackles particle filter problems like loss of diversity and high computational cost by introducing the Exponential Natural Particle Filter (xNPF), which uses natural gradient learning to improve state transition probability, resulting in convergence much closer to true target states compared to other state-of-the-art filters.
Particle Filter algorithm (PF) suffers from some problems such as the loss of particle diversity, the need for large number of particles, and the costly selection of the importance density functions. In this paper, a novel Exponential Natural Particle Filter (xNPF) is introduced to solve the above problems. In this approach, a state transitional probability with the use of natural gradient learning is proposed which balances exploration and exploitation more robustly. The results show that xNPF converges much closer to the true target states than the other state of the art particle filter.