University of Leeds Featured PhD Programmes
Engineering and Physical Sciences Research Council Featured PhD Programmes
Bournemouth University Featured PhD Programmes

Safe, flexible and explainable reinforcement learning for autonomous systems

This project is no longer listed on and may not be available.

Click here to search for PhD studentship opportunities
  • Full or part time
    Prof T Norman
  • Application Deadline
    No more applications being accepted
  • Competition Funded PhD Project (European/UK Students Only)
    Competition Funded PhD Project (European/UK Students Only)

Project Description

Supervisor: Tim Norman and Chris Freeman

Project description

For future AI systems to operate effectively in the real world, we need them to be trusted to work safely but also have the flexibility to adapt to changing circumstances. How do we develop systems that can both optimise their behaviour but be trusted, and how can we learn good behavioural abstractions that are less brittle to changes in the environment? In this project we will explore safety-constrained reinforcement and active learning techniques and evaluate their use in autonomous system control. We will explore research challenges around:
1. What safety requirements mean operationally with respect to the behaviour of autonomous (or human/agent mixed initiative) systems;
2. Learning effective but flexible behavioural abstractions that are guided by safety constraints; and
3. How such systems can explain/expose the alignment of their behaviour with respect to these constraints to facilitate situational awareness.

The supervision team for the PhD is:
• Prof Tim Norman, an expert in AI and Machine Learning,
• Prof Chris Freeman, an expert in control engineering and robotics,

This project is funded through the UKRI MINDS Centre for Doctoral Training ( This is one of 16 PhD training centres in the UK with a unique focus on advancing AI techniques in the context of real-world engineered systems with a remit that spans novel hardware for AI, AI and machine learning, pervasive systems and IoT, and human-AI collaboration. We provide enhanced cross-disciplinary training in electronics and AI, entrepreneurship, responsible research and innovation, communication strategies, outreach and impact development as part of an integrated 4-year iPhD programme.

The MINDS CDT is based in a dedicated laboratory on Highfield Campus at the University of Southampton. The lab provides a supportive environment for individual research, ideas sharing and collaboration, and the wider campus provides access to substantial high-performance computing (including dedicated GPU servers), maker and cleanroom facilities. You will take part in our annual, student-designed innovation camps, be able to work with industry and government partners through our internship scheme and be able to take part in exchanges with international university partners.

If you wish to discuss any details of the project informally, please contact the MINDS CDT, Email: [Email Address Removed], Tel: +44 (0) 2380 596057.

Funding: full tuition for EU/UK Students plus, for UK and EU students resident in the UK for previous 3 years, an enhanced stipend of £18,285, tax-free per annum for 4 years. years.

Entry Requirements
A very good undergraduate degree (at least a UK 2:1 honours degree, or its international equivalent).

Closing date: applications should be received no later than 3 April 2020 for entry in October 2020.

How To Apply

Applications should be made online. Please enter Safe, flexible and explainable reinforcement learning for autonomous systems under the Topic or Field of Research.

Applications should include:
Research Proposal
Curriculum Vitae
Two reference letters
Degree Transcripts to date

Apply online:

For further information please contact: [Email Address Removed]

How good is research at University of Southampton in General Engineering?

FTE Category A staff submitted: 192.23

Research output data provided by the Research Excellence Framework (REF)

Click here to see the results for all UK universities

FindAPhD. Copyright 2005-2020
All rights reserved.