Adaptive Tuning of the Unscented Kalman Filter using Particle Swarm Optimization for Inertial-GPS Sensor Fusion Systems

TL;DR

This paper presents a PSO-based adaptive tuning method for the UKF in IMU-GPS fusion, significantly improving vehicle localization accuracy and stability in real-time scenarios.

Contribution

It introduces a novel PSO-based framework for automatic UKF parameter tuning, enhancing accuracy and robustness over manual methods in vehicle localization.

Findings

82.14% accuracy improvement over manual tuning

Reduced IMU drift by up to 21,606.59 meters

Maintained update times below 10 ms for real-time performance

Abstract

Accurate vehicle positioning requires effective IMU-GPS fusion, yet prior methods-EKF, UKF, ML, GA, and DE-suffer from nonlinearity, instability, or high computational cost. This study introduces a PSO-based adaptive tuning framework for optimizing UKF parameters ({\alpha}, \b{eta}, \k{appa}, Q, R), evaluated in CARLA 0.9.14 using a Tesla Model 3 under diverse maneuvers and environmental conditions. Within defined parameter bounds, convergence stabilized within 15 generations, achieving an 82.14% accuracy improvement over manual tuning and reducing IMU drift by up to 21,606.59m. Multi-trial statistical validation confirmed consistent gains with low confidence intervals. With update times remaining below the 10 ms real-time threshold, the PSO-tuned UKF demonstrates practical localization performance for dynamic, GPS-challenged conditions.