Autonomous Subsea Cable Search and Tracking with Graph-Optimised Priors and Visual Tracking

2026-06-22

AI Summary

This work proposes an autonomous cable-tracking method that integrates graph-based optimization with physical constraints to address the challenges of uncertain prior path information, small cable diameter, and partial burial. The system fuses uncertain prior path data into a graph-optimization framework that continuously incorporates visual observations to dynamically refine the estimated cable trajectory. A physics-based catenary model is introduced to constrain the search space, enhancing geometric plausibility. Additionally, an onboard semi-supervised classifier enables efficient real-time detection and tracking. This approach represents the first integration of graph optimization and a catenary model for AUV-based cable tracking, allowing rapid recovery even after tracking loss. In field trials on a 120-meter cable segment containing intentional errors, the method successfully localized and inspected up to 59% of the cable.

Abstract

Global communications rely on subsea cable infrastructure that remains vulnerable to damage from natural hazards and human activity. Autonomous underwater vehicles (AUVs) offer an efficient means to inspect long sections of exposed cable, but uncertainty in cable route maps, small cable diameters and partial burial makes continuous tracking a challenge. This paper presents a novel cable search and tracking method that leverages uncertain prior cable route maps. Graph-based optimisation continuously update the cable route to remain consistent with visual observations. Route uncertainty is constrained as a function of distance from observations using physics-based catenary models that account for cable parameters (i.e., lay depth, diameter, and density), bounding the search space to physically feasible regions and improving search efficiency. Cable detection is performed using a semi-supervised classifier running in real-time on-board a camera-equipped AUV. These detections both update the graph-based optimisation and enable visual cable tracking. When tracking is lost due to misclassification, burial or imperfect control, the bounded search space enables efficient recovery. The approach was demonstrated in field trials using the University of Southampton's Smarty200 AUV. The system successfully located the cable despite deliberate errors in it initial cable route map, updating this to be consistent with observations and using visual tracking to inspect up to 59% of a 120m test cable, with successful recovered after tracking loss.

Problem

• subsea cable
• autonomous underwater vehicle
• cable tracking
• route uncertainty
• visual tracking

Innovation

• graph-optimised priors
• visual tracking
• catenary model
• semi-supervised classification
• autonomous underwater vehicle