2026· IEEE Transactions on Instrumentation and Measurement· Vol 75, pp. 8515115-8515115· 0 citations· 51 references
TL;DR
This study presents the first successful verification of a data-driven navigation method for AUV, offering a robust and high-precision solution for scenarios where acoustic systems fail.
Abstract
Currently, high-precision underwater navigation for autonomous underwater vehicle (AUV) is primarily achieved using acoustic sensors such as Doppler velocity log (DVL), long baseline (LBL), and ultrashort baseline (USBL). However, acoustic sensors are costly, exclusively offer limited range, and are susceptible to environmental noise, which leads to measurement instability and undermines navigation continuity. In response, this article proposes a deep learning-enhanced strapdown inertial navigation system (SINS)/propeller/pressure sensor (PS) integrated navigation algorithm to guarantee navigation continuity for AUV during acoustic measurement outages. Based on the dynamic equations of AUV, the relationship between its velocity and the specific dynamic information is analytically derived. Subsequently, an adaptive Hampel filter (AHF) enhanced backpropagation neural network (AHFBPNN) model is constructed to mitigate low-frequency data outliers and precisely process AUV kinematics and propeller rotation rates when acoustic sensors are available. During acoustic observation outages, the model activates to estimate AUV velocity from the trained network, working with the SINS and PS to form an integrated navigation system. The algorithm is validated using measured data from AUV missions conducted in both shallow-water and deep-sea environments. Experimental results demonstrate that during the 1000-s voyages, navigation accuracies of 1.350 %, 2.052 %, and 0.754 % were achieved for the straight-line and elliptical trajectories in shallow water, and the straight-line trajectory in deep sea, respectively. This study presents the first successful verification of a data-driven navigation method for AUV, offering a robust and high-precision solution for scenarios where acoustic systems fail.
Navigation-aware loss (NAViLoss), a robust and uncertainty-aware objective function for learning-based AUV velocity estimation, is introduced, demonstrating the effectiveness of navigation-aware and uncertainty-adaptive loss design for robust learning-based underwater velocity estimation.
In complex surface and underwater environments, the loss of external position observations degrades strapdown inertial navigation system (SINS)/Doppler velocity log (DVL) navigation accuracy. This article develops an intelligent measurement-compensated sliding-window factor graph optimization (FGO) method for robust su...
En-Dong Liu, Li-Hui Wang, Ye Li et al.· IEEE Transactions on Instrum...· 0 citations
Autonomous underwater vehicles require the integration of inertial, velocity, optical, and acoustic measurements for reliable underwater navigation where GPS signals are unavailable or intermittent. During a mission, the utility of these modalities may vary due to changes in environmental visibility, Doppler velocity l...
Christos Alexandris, P. Papageorgas, Dimitrios D. Piromalis· Applied Sciences· 0 citations
Underwater ego-motion estimation is crucial for achieving autonomous navigation in Autonomous Underwater Vehicles (AUVs). Obtaining continuous and robust velocity observations in shallow, acoustically and visually constrained environments remains an open problem, especially for compact platforms where acoustic bottom-t...
Zhi-Peng Fei, Yi-Cheng Lin, Heng-Peng Xie et al.· IEEE Robotics and Automation...· 0 citations
As expansion and scalability in underwater oper- ations becomes more important and challenging, autonomous underwater vehicles (AUVs) become more relevant and the necessity for reliable autonomy more critical. A fundamental challenge in any autonomous underwater operation, from control to safe navigation and mapping, i...
Chinmay Burgul, Xiao-Ming Zhao, Ye-Wei Huang et al.· 0 citations
Autonomous Underwater Vehicles (AUVs) navigating without GPS typically fuse inertial measurements with acoustic Doppler Velocity Log (DVL) velocities and pressure-derived depth. Posing the navigation state on a Lie group improves accuracy and consistency. However, state-of-the-art filters based on the Invariant Extende...
Arihant Lunawat, Pieter van Goor, F. Dellaert et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.