Virtual DVL Reconstruction Method for an Integrated Navigation System Based on DS-LSSVM Algorithm

TLDR

Autonomous underwater vehicles rely on an integrated strap‑down inertial navigation system and Doppler velocity log to provide continuous, accurate navigation, yet DVL performance can degrade in adverse acoustic conditions. The study proposes a novel DS‑LSSVM method that fuses SINS and DVL data to generate a virtual DVL signal. By applying Dempster–Shafer theory to fuse SINS and DVL measurements and training a least‑squares support vector machine to model SINS error, the DS‑LSSVM framework constructs a virtual DVL that sustains navigation during extended DVL outages. Experiments show the virtual DVL method is effective and achieves higher positioning accuracy than a pure LSSVM approach.

Abstract

Autonomous underwater vehicle (AUV) mostly relies on an integrated navigation system, which consists of a strap-down inertial navigation system (SINS) and Doppler velocity log (DVL). The integrated system provides continuous and accurate navigation information when compared to stand-alone SINS or DVL. However, the dependence of DVL signals on the acoustic environment may cause any DVL malfunction due to marine organisms or strong wave-absorbing material. This article introduces a novel method utilizing Dempster–Shafer (DS) theory augmented by least squares support vector machines (LSSVMs) known as DS-LSSVM. The SINS and DVL data fusion are designed by DS theory whereas LSSVM models the SINS error. The virtual DVL is built by the proposed DS-LSSVM method, which makes AUV navigation purposes possible during the long-term DVL outage. The test results demonstrate the effectiveness of the proposed virtual DVL signal estimation method. In addition, the positioning accuracy of the proposed method outperforms that of the LSSVM method.