Aim

This project aims at developing novel detection, classification and tracking solutions for underwater surveillance using active sonar.

Objectives

1. Investigate event-based processing for discrimination of slow-moving objects from static clutter, using a single platform’s underwater sensor
2. Develop a tracking pipeline for objects with soft labels (e.g., noisy classification labels)
3. Extend methods above to mitigate range and bearing errors and platform motion

Description

Dstl and the Sonar Technical Team are very keen to engage with SPADS on Defence underwater acoustic sensing and in particular on advanced automated processing for Submarine Detection Systems. This project primarily focuses on single-platform sensors, but potentially multi-sensor systems, in cluttered acoustic environments. While Dstl possesses expertise and solutions for sonar-based detection and tracking, enhanced estimation extraction and lower levels of user input (to reduce operator requirements) is becoming increasingly important for reducing cost and improving efficiency.

The first objective of this project is to develop data-driven approaches for reliable clutter detection using either raw sonar measurements or detections from pre-processing pipelines, using limited environment information. This objective will be addressed using spiking neural network architectures used either as pre-processing stages or for end-to-end architectures. While tracking options going only once through the data will be preferred, batching alternatives will also be considered to mitigate high clutter levels and multiple object types. The second challenge investigated is tracking with uncertain and missing labels, which might help with track crossing but also brings additional uncertainties that need to be incorporated in the tracking problem. This will be tackled using Bayesian filters empowered by data-driven modules (e.g., classifiers) trained with limited data. Finally, we will investigate how the pipeline outputs can be leveraged in a navigation context.  

Further Information

Through working with the Dstl partner, there will be opportunities to gather data under multinational trials opportunities with the NATO Centre for Maritime Research and Experimentation (CMRE). A set of trials entitled “Cognitive Sonar” are anticipated to take place from 2026, and Dstl are able to influence the trials plan and potentially include serials with specific data collection that assists with the PhD project goals, provided there is general alignment with the multinational objectives. Some existing datasets may also be available and sharable with the project. As part of this work, there may be opportunity for the PhD student to participate in trials planning meetings and even the trial itself. Throughout the project and particularly in the lead up to trials planning, it will be beneficial for the student to consider what data collection could be useful and suggest trial serials that achieve this.

The Dstl partners can arrange placements at Dstl (or partners such as CMRE) depending on holding security clearances (which Dstl can sponsor for UK nationals)

Placements can be used to access classified data and other information plus engage with Dstl’s sonar and underwater acoustic sensing teams