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

2025-10-14

2025 4th International Conference on Smart Cities, Automation & Intelligent Computing Systems (ICON-SONICS)

AI Summary

This study addresses the limitations of conventional IMU-GPS fusion methods, which often struggle with nonlinear dynamics, stability, or computational efficiency, thereby failing to meet the demands of high-precision vehicle localization. To overcome these challenges, this work proposes an adaptive parameter-tuning framework based on particle swarm optimization (PSO), which, for the first time, enables joint optimization of multiple parameters (α, β, κ, Q, R) in the unscented Kalman filter (UKF). Evaluated across diverse driving scenarios in the CARLA simulation platform using a Tesla Model 3 vehicle model, the proposed approach achieves an 82.14% improvement in localization accuracy over manual tuning, reduces maximum IMU drift by 21,606.59 meters, and maintains a per-update computation time under 10 milliseconds. These results demonstrate a favorable balance of accuracy, robustness, and real-time performance, highlighting its practical applicability.

Technology Category

• Intelligent Robots: State Estimation
• Search and Optimization: Algorithm Configuration
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Systems and Infrastructure for Web, Mobile and WoT: Location- and context-aware Web and WoT applications and services
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

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 ($\alpha, \beta, \kappa, Q, R$), 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 $\mathbf{2 1, 6 0 6. 5 9 m}$. 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.

Problem

• sensor fusion
• vehicle positioning
• nonlinearity
• instability
• computational cost

Innovation

• Particle Swarm Optimization
• Unscented Kalman Filter
• IMU-GPS Fusion
• Adaptive Tuning
• Real-time Localization