Scholarlink

Abstract <p>Accurate attitude determination of unmanned aerial vehicles (UAVs) is crucial for autonomous navigation, particularly when relying solely on gyroscope, accelerometer, and magnetometer measurements without utilizing the Global Positioning System (GPS). Reinforcement learning (RL) has emerged as a promising artificial intelligence technique applicable across various domains. This research introduces a novel approach that leverages RL to enhance the performance of the extended Kalman filter (EKF) in attitude estimation. The proposed method depends of RL which uses the <i>Q</i>-learning model and policy to find&#xa0;best solution to adjust autonomously the measurement noise covariance matrix within the EKF. By establishing a reward mechanism that incentivizes actions minimizing the prediction error relative to true measurements, the RL dynamically optimizes the measurement noise covariance matrix. This innovative integration of RL and EKF, referred to as RL-EKF, has been implemented and tested. Results demonstrate that RL-EKF significantly outperforms the traditional EKF, yielding marked improvements in attitude estimation accuracy. The improvement ratios showed that selected method is very effective in the field of attitude estimation.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Adaptation of Noise Covariance in Extended Kalman Filter Using Reinforcement Learning for Improved UAV Attitude Estimation

  • 期刊论文

  • 发表日期：

    2025年9月1日

查看全文
  • A. Assad,
  • S. A. Serikov

摘要

Abstract

Accurate attitude determination of unmanned aerial vehicles (UAVs) is crucial for autonomous navigation, particularly when relying solely on gyroscope, accelerometer, and magnetometer measurements without utilizing the Global Positioning System (GPS). Reinforcement learning (RL) has emerged as a promising artificial intelligence technique applicable across various domains. This research introduces a novel approach that leverages RL to enhance the performance of the extended Kalman filter (EKF) in attitude estimation. The proposed method depends of RL which uses the Q-learning model and policy to find best solution to adjust autonomously the measurement noise covariance matrix within the EKF. By establishing a reward mechanism that incentivizes actions minimizing the prediction error relative to true measurements, the RL dynamically optimizes the measurement noise covariance matrix. This innovative integration of RL and EKF, referred to as RL-EKF, has been implemented and tested. Results demonstrate that RL-EKF significantly outperforms the traditional EKF, yielding marked improvements in attitude estimation accuracy. The improvement ratios showed that selected method is very effective in the field of attitude estimation.