Distributed Consensus Multi-Distribution Filter for Heavy-Tailed Noise

View Full Paper

Ask AI

Bookmark

The proposed multi-distribution filter improved estimation accuracy by at least 20% in situations with both Gaussian and heavy-tailed distributions.
Simulation results clearly showcased the effectiveness of combining Gaussian and student-t filters for better state estimation.
The method utilizes an information consensus strategy to achieve global estimation through local interactions with neighboring nodes for effective filtering processes for noise distributions in target tracking systems and beyond. It is essential for applications reliant on precise target tracking in environments affected by various types of noise, including outliers.

Discussion

No takes yet. Share an insight, caveat, or question.

Randomized trial demonstrates improved estimation accuracy with a multi-distribution filter, indicating enhanced target tracking performance.

Chang et al. (2024) studied this question.

View Full Paper

Ask AI

Bookmark

Randomized trial demonstrates improved estimation accuracy with a multi-distribution filter, indicating enhanced target tracking performance.