cs.ROMar 28, 2026

Predictive Modeling in AUV Navigation: A Perspective from Kalman Filtering

Authors: Zizhan Tang, Yao Liu, Jessica Liu

Organizations: Department of Electrical and Computer Engineering, University of Southern California, Los Angeles, CA, USA · Department of Computer and Information Science, University of Pennsylvania, Philadelphia, PA, USA

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

We present a safety-oriented framework for autonomous underwater vehicles (AUVs) that improves localization accuracy, enhances trajectory prediction, and supports efficient search operations during communication loss. Acoustic signals emitted by the AUV are detected by a network of fixed buoys, which compute Time-Difference-of-Arrival (TDOA) range-difference measurements serving as position observations. These observations are subsequently fused with a Kalman-based prediction model to obtain continuous, noise-robust state estimates. The combined method achieves significantly better localization precision and trajectory stability than TDOA-only baselines. Beyond real-time tracking, our framework offers targeted search-and-recovery capability by predicting post-disconnection motion and explicitly modeling uncertainty growth. The search module differentiates between continued navigation and propulsion failure, allowing search resources to be deployed toward the most probable recovery region. Our framework fuses multi-buoy acoustic data with Kalman filtering and uncertainty propagation to maintain navigation accuracy and yield robust search-region definitions during communication loss.

Figures & tables

Fig. 1: Illustration of the TDOA-based localization system. The submersible emits acoustic signals received by multiple buoys at different times, from which the travel time differences are used to estimate its position.
Fig. 2: Mechanical interpretation of the submersible motion under combined engine and ocean-current accelerations.
Fig. 3: Illustration of the search process under communication loss. The predicted trajectory (red) is generated by the Kalman filter, while the blue curve denotes the true motion. The shaded circles illustrate the evolving search regions under different operating conditions.
Fig. 4: Localization results for 1000 test points. Blue circles denote true positions; yellow markers represent TDOA estimates.
Fig. 5: Cumulative Distribution Function (CDF) of Mean Absolute Error (MAE) for Submarine Localization. The CDF curve illustrates the probability that the localization error is less than or equal to a given MAE threshold. Nearly all test points have errors below 4 m, demonstrating high localization accuracy.
Fig. 6: Simulation result of the prediction model. The real trajectory, TDOA measurements, and Kalman filter predictions are shown together for comparison.
Fig. 7: MSE comparison between the TDOA model and Kalman filter prediction. The Kalman filter achieves consistently lower error across time steps.
Fig. 8: Simulation of the search process when disconnection occurs at t=50 st=50~\mathrm{s} . The predicted trajectory (red) closely follows the real trajectory (blue) along the predetermined route.
Fig. 9: Simulation of the search process when disconnection occurs at t=80 st=80~\mathrm{s} . The divergence between predicted and real positions increases with time as uncertainty accumulates.

Explore similar work

CardsList

  1. BIND-USBL: Bounding IMU Navigation Drift using USBL in Heterogeneous ASV-AUV Teams

    Apr 13, 2026Pranav Kedia, Rajini Makam, Heiko Hamann +1Autonomous Underwater NavigationCooperative Localization

    Dept of Computer and Information Science, University of Konstanz, Germany · Centre for the Advanced Study of Collective Behaviour, University of Konstanz, Germany · Dept of Aerospace Engineering, Indian Institute of Science, Bangalore, India

  2. Communication Outage-Resistant UUV State Estimation: A Variational History Distillation Approach

    Mar 31, 2026Shuyue Li, Miguel López-Benítez, Eng Gee Lim +5Robot State EstimationRobust Estimation

    School of Advanced Technology, Xi’an Jiaotong-Liverpool University, Suzhou, China · School of Engineering, University of Liverpool, Liverpool, UK · Jiangsu JITRI Tsingunited Intelligent Control Technology Co., Ltd., Wuxi, China +4

  3. NAViLoss: An Underwater Navigation-Aware Dual-Residual Objective for Physics-Consistent Learning

    Oct 7, 2026Arup Kumar Sahoo, Itzik KleinAutonomous Underwater NavigationRobust Loss Functions

    The Hatter Department of Marine Technologies, Leon H. Charney School of Marine Sciences, University of Haifa, Haifa, 3498838, Israel