University of Edinburgh Featured PhD Programmes
Norwich Research Park Featured PhD Programmes
Birkbeck, University of London Featured PhD Programmes
University of Dundee Featured PhD Programmes
University of Leeds Featured PhD Programmes

Data-Based Automation of Underwater Vehicle Operations

  • Full or part time
  • Application Deadline
    Sunday, December 15, 2019
  • Funded PhD Project (European/UK Students Only)
    Funded PhD Project (European/UK Students Only)

Project Description

Autonomous underwater vehicles (AUVs) have become a fundamental tool for the exploration and study of the oceans. Recent advances in AUV technology have resulted in smaller, cheaper vehicles, with much longer deployment duration and depth rating. However, the level of autonomy associated with most AUVs is still quite limited, with human pilots required to prepare missions, configure vehicle flight and monitor mission execution. At present, the number of vehicles which can be deployed simultaneously is limited by the availability of highly-skilled pilots, especially during the intensive launch and recovery phases of a vehicle deployment. To help address this scalability issue, the National Oceanography Centre (NOC - https://www.noc.ac.uk/) is developing a common server-based command and control infrastructure to enable the piloting of multiple vehicle types from a single web-based tool. As part of this work, NOC is developing an automated piloting framework and application programming interfaces (APls), which allow algorithms to safely control vehicles within the NOC fleet.

This collaborative project between UCL and NOC seeks to develop an innovative approach to automating the operations of underwater vehicles using artificial intelligence.

This project will build on an existing collaboration between UCL and NOC. The student will have access to a wealth of deployment data provided by the NOC. The research will involve the development of software tools that will be integrated within the NOC's automated piloting framework based on the following topic areas:
• Develop a recommender system for the flight configuration of underwater gliders to include dynamic effects in addition to steady-state conditions with either dynamic modelling or machine learning,
• Generalise condition monitoring tools for underwater gliders to predictive maintenance with deep learning strategies,
• Experimentally investigate the impact of sensor loss using UCL' s ecoSUB,
• Develop a tool for NOC's autoSUBs to switch from high- to low-fidelity sensors in emergencies.

Person specification: Final year degree students and graduates of naval architecture, mechanical engineering, mechatronics and computer science disciplines are particularly encouraged to apply. A first or upper-second class UK Bachelor's degree or an overseas qualification of an equivalent standard from a recognised higher education institution, or a recognised taught or research M aster ' s degree. Relevant work experience may also be taken into consideration.

Closing Date and Start Date: Closing date for applications is l51 December 2019. Start date will be by mutual agreement but preferably by January 2020.

Application Procedure: In the first instance you are encouraged to contact Dr Enrico Anderlini: providing a copy of your CV.

Full details on the application process can be found here: https://www.ucl.ac.uk/prospective­ students/graduate/research-degrees/mechanical-engineering-mphil-phd for inform action.

Funding Notes

Value of award: Full tuition fees and a stipend starting at £17,323.16 per annum (increasing over the 3 years).

Eligibility: Funding requirements dictate only UK and EU passport holders are eligible to apply.

Email Now

Insert previous message below for editing? 
You haven’t included a message. Providing a specific message means universities will take your enquiry more seriously and helps them provide the information you need.
Why not add a message here
* required field
Send a copy to me for my own records.

Your enquiry has been emailed successfully





FindAPhD. Copyright 2005-2019
All rights reserved.