DVL-DeepONet: A Physics-Guided Operator Learning for Resilient Underwater Navigation

2026-06-22

AI Summary

This study addresses the challenge of reliable velocity estimation for autonomous underwater vehicles (AUVs) under degraded sensing conditions—such as missing Doppler Velocity Log (DVL) beams, high measurement noise, or the absence of inertial sensors—which severely compromise navigation performance. To this end, the authors propose DVL-DeepONet, a novel framework that, for the first time, integrates physics-informed deep neural operators into underwater navigation. The approach directly maps sequential inertial and DVL observations to vehicle velocity while embedding physical consistency constraints derived from DVL measurement principles. The method operates flexibly across three modes: noisy sensor fusion, DVL-only estimation, and DVL beam recovery, thereby significantly enhancing system robustness. Validated on approximately 10,000 meters of real-world AUV trajectories, the proposed method improves velocity estimation accuracy by 40% over conventional models and existing learning-based approaches.

Abstract

Autonomous Underwater Vehicles (AUVs) rely heavily on the fusion of inertial sensors and Doppler velocity logs (DVLs) for navigation. In standard autonomous navigation systems, the DVL measures four beam velocities, thereby enabling the estimation of the AUV velocity vector. However, during real-world missions, the DVL may receive noisy or incomplete beam measurements due to marine obstacles, seabed reflections, or environmental disturbances. Furthermore, some low-cost underwater platforms operate without inertial sensors to reduce system complexity and cost. In such cases, reliable estimation of the AUV velocity vector in real-world missing beam scenarios becomes challenging, leading to degraded navigation solutions. To circumvent these challenges and enable resilient underwater navigation, we propose DVL-DeepONet, a physics-guided deep neural operator framework along with three variants. The proposed models are designed to estimate DVL-based velocity information under multiple operational scenarios, including (i) noise-resilient estimation in coupled inertial/DVL measurements, (ii) DVL-only learning, and (iii) beam measurement recovery. By learning a nonlinear operator that maps temporal inertial/DVL observations directly to vehicle velocity while enforcing DVL measurement physics through a consistency constraint, the proposed approach enables robust velocity estimation even under degraded sensing conditions. The proposed framework is validated using real-world AUV experiments, comprising a cumulative path length of approximately 10,000 m. Experimental results demonstrate that the proposed DVL-DeepONet architectures outperform baseline model-based approaches and learning-based algorithms by 40%.

Problem

• Autonomous Underwater Vehicles
• Doppler Velocity Log
• missing beam measurements
• velocity estimation
• underwater navigation

Innovation

• physics-guided learning
• operator learning
• Doppler velocity log (DVL)
• underwater navigation
• missing data recovery