Perception and decision making for autonomous surface vessel

Applications are invited for a self-funded, 3-year full-time or 6-year part time PhD project.

The PhD will be based in the School of Energy and Electronic Engineering and will be supervised by Dr Hongjie Ma and Dr Edward Smart.

The work on this project could involve:

• Research on multi-sensor fusion algorithm to reliably perceive the environment/objects around the autonomous ship in various restricted environments, such as choppy seas or foggy weather.
• Research on autonomous vessel decision-making algorithm based on reinforcement learning to realise autonomous driving in complex waterways and climates.
• Integrate and test the developed algorithms in a ship simulator or a prototype ship.

Project description

Unlike industry that still takes a wait-and-see attitude towards autonomous cars, autonomous vessels(AV) are starting to be used various industrial applications, such as marine monitoring, cargo/passenger transportation, border patrols, etc. It has brought billions of pounds of benefits to the industry, and the trend keeps increasing year by year.

As a famous port city, it has unique geographical advantages and a mature shipbuilding environment to develop its shipbuilding industry. Therefore, the headquarters of many autonomous ship companies are located in Portsmouth and its surrounding areas, such as L3 Harris, etc. The University of Portsmouth also benefits from this.

In the past few years, the mentor team of this project has led several projects in cooperation with the autonomous ship industry. The topics of these projects cover high-reliability positioning, environment awareness, fault diagnosis, etc. Funding for these projects comes from Innovate UK, EU, etc., worth over £500k.

The challenge that restricts the further application of AV is that the intelligence level of AV in tricky weather or difficult environments needs to be further improved. For example, rainy or foggy days will bring the challenge to the environmental perception of AV, and driving in a crowded and choppy channel is also a big challenge for the decision-making of AV. In this context, this project was proposed. The candidate for this project is expected to develop reliable perception algorithms based on multi-sensor fusion and decision-making algorithms based on reinforcement learning that can handle complex driving scenarios. These two algorithms will be integrated and tested on a simulator or an experimental prototype vessel.

General admissions criteria

You'll need a good first degree from an internationally recognised university or a Master’s degree in an appropriate subject. In exceptional cases, we may consider equivalent professional experience and/or qualifications. English language proficiency at a minimum of IELTS band 6.5 with no component score below 6.0.

Specific candidate requirements

You should have knowledge of machine learning and Python or Matlab programming skills.

How to Apply

We encourage you to contact Dr Hongjie Ma ([Email Address Removed]) to discuss your interest before you apply, quoting the project code below.

When you are ready to apply, please follow the 'Apply now' link on the Electronic Engineering PhD subject area page and select the link for the relevant intake. Make sure you submit a personal statement, proof of your degrees and grades, details of two referees, proof of your English language proficiency and an up-to-date CV. Our ‘How to Apply’ page offers further guidance on the PhD application process. 

When applying please quote project code: SENE5671023.