Related Experiment Video
Updated: Nov 18, 2025
10:16
A Protocol for Real-time 3D Single Particle Tracking
Published on: January 3, 2018
15.1K
Dynamic Indoor Localization Using Maximum Likelihood Particle Filtering
Wenxu Wang1, Damián Marelli1,2, Minyue Fu1,3
1School of Automation, Guangdong University of Technology, Guangzhou 510006, China.
Sensors (Basel, Switzerland)
|February 10, 2021
Summary
This study introduces a novel Maximum Likelihood Particle Filter (MLPF) to improve WiFi-based indoor localization. MLPF significantly reduces the number of particles needed for accurate dynamic localization, making algorithms more efficient.
Area of Science:
- Robotics
- Wireless Communication
- Signal Processing
Background:
- Particle filtering is a common method for WiFi-based indoor dynamic localization.
- Classical particle filtering requires a large number of particles for accuracy in real environments.
- This leads to computational inefficiency due to wasted particles.
Purpose of the Study:
- To propose a novel particle filtering method, the Maximum Likelihood Particle Filter (MLPF).
- To address the inefficiency of classical particle filtering in WiFi-based indoor localization.
- To reduce the number of particles required for accurate localization.
Main Methods:
- Developed the Maximum Likelihood Particle Filter (MLPF).
- Integrated particle prediction and update steps into a single, efficient step.
- Ensured all particles are utilized effectively.
Main Results:
- MLPF drastically reduces the number of particles needed.
- Achieved numerically feasible algorithms with high accuracy.
- Experimental results using real data validate the claims.
Conclusions:
- The Maximum Likelihood Particle Filter (MLPF) offers a significant improvement over classical methods.
- MLPF provides a more efficient and accurate solution for WiFi-based indoor dynamic localization.
- This method enhances the practicality of particle filtering for real-world applications.
