ResAlignNet: A data-driven approach for INS/DVL alignment

Autonomous underwater vehicles rely on precise integration of inertial navigation systems and Doppler velocity logs for successful missions where satellite navigation is unavailable. The effectiveness of this integration critically depends on accurate alignment between sensor reference frames. Standard model-based alignment methods suffer from lengthy convergence times, dependence on prescribed motion patterns, and over-reliance on external positioning infrastructure such as satellite signals or acoustic positioning systems, significantly limiting operational flexibility. To address these limitations, this paper presents ResAlignNet, a data-driven approach using 1D ResNet-18 architecture that transforms the alignment problem into deep neural network optimization. Operating as an in-situ solution, ResAlignNet requires only onboard sensors without external positioning aids or complex vehicle maneuvers while achieving rapid convergence in seconds. The approach demonstrates Sim2Real transfer learning capabilities, enabling training on synthetic data while deploying on operational sensor measurements. Experimental validation using the Snapir autonomous underwater vehicle demonstrates that ResAlignNet achieves alignment accuracy within 0.8° using only 25 seconds of data collection, representing a 65% reduction in convergence time compared to standard velocity-based methods. The trajectory-independent solution eliminates motion pattern requirements and enables immediate vehicle deployment without lengthy pre-mission procedures, advancing underwater navigation through robust sensor-agnostic alignment that scales across different operational scenarios and sensor specifications.