Lv Pengfei, Lv Junyi, Hong Zhichao, Xu Lixin
Ocean College, Jiangsu University of Science and Technology, Zhenjiang 212003, China.
Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen 518110, China.
Sensors (Basel). 2024 Aug 21;24(16):5396. doi: 10.3390/s24165396.
When autonomous underwater vehicles (AUVs) perform underwater tasks, the absence of GPS position assistance can lead to a decrease in the accuracy of traditional navigation systems, such as the extended Kalman filter (EKF), due to the accumulation of errors. To enhance the navigation accuracy of AUVs in the absence of position assistance, this paper proposes an innovative navigation method that integrates a position correction model and a velocity model. Specifically, a velocity model is developed using a dynamic model and the Optimal Pruning Extreme Learning Machine (OP-ELM) method. This velocity model is trained online to provide velocity outputs during the intervals when the Doppler Velocity Log (DVL) is not updating, ensuring more consistent and reliable velocity estimation. Additionally, a position correction model (PCM) is constructed, based on a hybrid gated recurrent neural network (HGRNN). This model is specifically designed to correct the AUV's navigation position when GPS data are unavailable underwater. The HGRNN utilizes historical navigation data and patterns learned during training to predict and adjust the AUV's estimated position, thereby reducing the drift caused by the lack of real-time position updates. Experimental results demonstrate that the proposed VM-PCM-EKF algorithm can significantly improve the positioning accuracy of the navigation system, with a maximum accuracy improvement of 87.2% compared to conventional EKF algorithms. This method not only improves the reliability and accuracy of AUV missions but also opens up new possibilities for more complex and extended underwater operations.
当自主水下航行器（AUV）执行水下任务时，由于误差的累积，缺乏全球定位系统（GPS）位置辅助会导致传统导航系统（如扩展卡尔曼滤波器（EKF））的精度下降。为了在没有位置辅助的情况下提高AUV的导航精度，本文提出了一种创新的导航方法，该方法集成了位置校正模型和速度模型。具体而言，利用动态模型和最优剪枝极限学习机（OP-ELM）方法开发了一个速度模型。该速度模型在线训练，以便在多普勒速度计（DVL）不更新的时间间隔内提供速度输出，确保更一致、可靠的速度估计。此外，基于混合门控循环神经网络（HGRNN）构建了一个位置校正模型（PCM）。该模型专门设计用于在水下无法获取GPS数据时校正AUV的导航位置。HGRNN利用训练期间学习的历史导航数据和模式来预测和调整AUV的估计位置，从而减少因缺乏实时位置更新而导致的漂移。实验结果表明，所提出的VM-PCM-EKF算法能够显著提高导航系统的定位精度，与传统EKF算法相比，最大精度提高了87.2%。该方法不仅提高了AUV任务的可靠性和精度，还为更复杂、更广泛的水下作业开辟了新的可能性。
